[dpdk-dev] [PATCH 0/2] hash: add lock free support for ext bkt

[dpdk-dev] [PATCH 0/2] hash: add lock free support for ext bkt

[Dharmik Thakkar]

This patch series:
- Enables lock-free read-write concurrency support for extendable
bucket feature.
- Adds lock-free read-write concurrency tests for ext bkt 

Dharmik Thakkar (2):
  hash: add lock free support for extendable bucket
  test/hash: lock-free rw concurrency test ext bkt

 app/test/test_hash_readwrite_lf.c  | 350 +++++++++++++++++++++++------
 doc/guides/prog_guide/hash_lib.rst |   3 +-
 lib/librte_hash/rte_cuckoo_hash.c  | 163 +++++++++-----
 lib/librte_hash/rte_cuckoo_hash.h  |   7 +
 4 files changed, 405 insertions(+), 118 deletions(-)

-- 
2.17.1

[dpdk-dev] [PATCH 0/2] hash: add lock free support for ext bkt

[Dharmik Thakkar]

This patch series:
- Enables lock-free read-write concurrency support for extendable
bucket feature.
- Adds lock-free read-write concurrency tests for ext bkt 

Dharmik Thakkar (2):
  hash: add lock free support for extendable bucket
  test/hash: lock-free rw concurrency test ext bkt

 app/test/test_hash_readwrite_lf.c  | 350 +++++++++++++++++++++++------
 doc/guides/prog_guide/hash_lib.rst |   3 +-
 lib/librte_hash/rte_cuckoo_hash.c  | 163 +++++++++-----
 lib/librte_hash/rte_cuckoo_hash.h  |   7 +
 4 files changed, 405 insertions(+), 118 deletions(-)

-- 
2.17.1

[dpdk-dev] [PATCH 1/2] hash: add lock free support for extendable bucket

[Dharmik Thakkar]

This patch enables lock-free read-write concurrency support for
extendable bucket feature.

Suggested-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
Signed-off-by: Dharmik Thakkar <dharmik.thakkar@arm.com>
Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
Reviewed-by: Gavin Hu <gavin.hu@arm.com>
Reviewed-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
---
 doc/guides/prog_guide/hash_lib.rst |   3 +-
 lib/librte_hash/rte_cuckoo_hash.c  | 163 ++++++++++++++++++++---------
 lib/librte_hash/rte_cuckoo_hash.h  |   7 ++
 3 files changed, 121 insertions(+), 52 deletions(-)

diff --git a/doc/guides/prog_guide/hash_lib.rst b/doc/guides/prog_guide/hash_lib.rst
index 85a6edfa8b16..b00446e949ba 100644
--- a/doc/guides/prog_guide/hash_lib.rst
+++ b/doc/guides/prog_guide/hash_lib.rst
@@ -108,8 +108,7 @@ Extendable Bucket Functionality support
 An extra flag is used to enable this functionality (flag is not set by default). When the (RTE_HASH_EXTRA_FLAGS_EXT_TABLE) is set and
 in the very unlikely case due to excessive hash collisions that a key has failed to be inserted, the hash table bucket is extended with a linked
 list to insert these failed keys. This feature is important for the workloads (e.g. telco workloads) that need to insert up to 100% of the
-hash table size and can't tolerate any key insertion failure (even if very few). Currently the extendable bucket is not supported
-with the lock-free concurrency implementation (RTE_HASH_EXTRA_FLAGS_RW_CONCURRENCY_LF).
+hash table size and can't tolerate any key insertion failure (even if very few).
 
 
 Implementation Details (non Extendable Bucket Case)
diff --git a/lib/librte_hash/rte_cuckoo_hash.c b/lib/librte_hash/rte_cuckoo_hash.c
index c01489ba5193..4cb05a5528c1 100644
--- a/lib/librte_hash/rte_cuckoo_hash.c
+++ b/lib/librte_hash/rte_cuckoo_hash.c
@@ -140,6 +140,7 @@ rte_hash_create(const struct rte_hash_parameters *params)
 	unsigned int readwrite_concur_support = 0;
 	unsigned int writer_takes_lock = 0;
 	unsigned int no_free_on_del = 0;
+	uint32_t *ext_bkt_to_free = NULL;
 	uint32_t *tbl_chng_cnt = NULL;
 	unsigned int readwrite_concur_lf_support = 0;
 
@@ -170,15 +171,6 @@ rte_hash_create(const struct rte_hash_parameters *params)
 		return NULL;
 	}
 
-	if ((params->extra_flag & RTE_HASH_EXTRA_FLAGS_RW_CONCURRENCY_LF) &&
-	    (params->extra_flag & RTE_HASH_EXTRA_FLAGS_EXT_TABLE)) {
-		rte_errno = EINVAL;
-		RTE_LOG(ERR, HASH, "rte_hash_create: extendable bucket "
-			"feature not supported with rw concurrency "
-			"lock free\n");
-		return NULL;
-	}
-
 	/* Check extra flags field to check extra options. */
 	if (params->extra_flag & RTE_HASH_EXTRA_FLAGS_TRANS_MEM_SUPPORT)
 		hw_trans_mem_support = 1;
@@ -302,6 +294,16 @@ rte_hash_create(const struct rte_hash_parameters *params)
 		 */
 		for (i = 1; i <= num_buckets; i++)
 			rte_ring_sp_enqueue(r_ext, (void *)((uintptr_t) i));
+
+		if (readwrite_concur_lf_support) {
+			ext_bkt_to_free = rte_zmalloc(NULL, sizeof(uint32_t) *
+								num_key_slots, 0);
+			if (ext_bkt_to_free == NULL) {
+				RTE_LOG(ERR, HASH, "ext bkt to free memory allocation "
+								"failed\n");
+				goto err_unlock;
+			}
+		}
 	}
 
 	const uint32_t key_entry_size =
@@ -393,6 +395,7 @@ rte_hash_create(const struct rte_hash_parameters *params)
 		default_hash_func : params->hash_func;
 	h->key_store = k;
 	h->free_slots = r;
+	h->ext_bkt_to_free = ext_bkt_to_free;
 	h->tbl_chng_cnt = tbl_chng_cnt;
 	*h->tbl_chng_cnt = 0;
 	h->hw_trans_mem_support = hw_trans_mem_support;
@@ -443,6 +446,7 @@ rte_hash_create(const struct rte_hash_parameters *params)
 	rte_free(buckets_ext);
 	rte_free(k);
 	rte_free(tbl_chng_cnt);
+	rte_free(ext_bkt_to_free);
 	return NULL;
 }
 
@@ -484,6 +488,7 @@ rte_hash_free(struct rte_hash *h)
 	rte_free(h->buckets);
 	rte_free(h->buckets_ext);
 	rte_free(h->tbl_chng_cnt);
+	rte_free(h->ext_bkt_to_free);
 	rte_free(h);
 	rte_free(te);
 }
@@ -799,7 +804,7 @@ rte_hash_cuckoo_move_insert_mw(const struct rte_hash *h,
 			__atomic_store_n(h->tbl_chng_cnt,
 					 *h->tbl_chng_cnt + 1,
 					 __ATOMIC_RELEASE);
-			/* The stores to sig_alt and sig_current should not
+			/* The store to sig_current should not
 			 * move above the store to tbl_chng_cnt.
 			 */
 			__atomic_thread_fence(__ATOMIC_RELEASE);
@@ -831,7 +836,7 @@ rte_hash_cuckoo_move_insert_mw(const struct rte_hash *h,
 		__atomic_store_n(h->tbl_chng_cnt,
 				 *h->tbl_chng_cnt + 1,
 				 __ATOMIC_RELEASE);
-		/* The stores to sig_alt and sig_current should not
+		/* The store to sig_current should not
 		 * move above the store to tbl_chng_cnt.
 		 */
 		__atomic_thread_fence(__ATOMIC_RELEASE);
@@ -1054,7 +1059,15 @@ __rte_hash_add_key_with_hash(const struct rte_hash *h, const void *key,
 			/* Check if slot is available */
 			if (likely(cur_bkt->key_idx[i] == EMPTY_SLOT)) {
 				cur_bkt->sig_current[i] = short_sig;
-				cur_bkt->key_idx[i] = new_idx;
+				/* Key can be of arbitrary length, so it is
+				 * not possible to store it atomically.
+				 * Hence the new key element's memory stores
+				 * (key as well as data) should be complete
+				 * before it is referenced.
+				 */
+				__atomic_store_n(&cur_bkt->key_idx[i],
+						 new_idx,
+						 __ATOMIC_RELEASE);
 				__hash_rw_writer_unlock(h);
 				return new_idx - 1;
 			}
@@ -1072,7 +1085,15 @@ __rte_hash_add_key_with_hash(const struct rte_hash *h, const void *key,
 	bkt_id = (uint32_t)((uintptr_t)ext_bkt_id) - 1;
 	/* Use the first location of the new bucket */
 	(h->buckets_ext[bkt_id]).sig_current[0] = short_sig;
-	(h->buckets_ext[bkt_id]).key_idx[0] = new_idx;
+	/* Key can be of arbitrary length, so it is
+	 * not possible to store it atomically.
+	 * Hence the new key element's memory stores
+	 * (key as well as data) should be complete
+	 * before it is referenced.
+	 */
+	__atomic_store_n(&(h->buckets_ext[bkt_id]).key_idx[0],
+			 new_idx,
+			 __ATOMIC_RELEASE);
 	/* Link the new bucket to sec bucket linked list */
 	last = rte_hash_get_last_bkt(sec_bkt);
 	last->next = &h->buckets_ext[bkt_id];
@@ -1366,7 +1387,8 @@ remove_entry(const struct rte_hash *h, struct rte_hash_bucket *bkt, unsigned i)
  * empty slot.
  */
 static inline void
-__rte_hash_compact_ll(struct rte_hash_bucket *cur_bkt, int pos) {
+__rte_hash_compact_ll(const struct rte_hash *h,
+			struct rte_hash_bucket *cur_bkt, int pos) {
 	int i;
 	struct rte_hash_bucket *last_bkt;
 
@@ -1377,10 +1399,27 @@ __rte_hash_compact_ll(struct rte_hash_bucket *cur_bkt, int pos) {
 
 	for (i = RTE_HASH_BUCKET_ENTRIES - 1; i >= 0; i--) {
 		if (last_bkt->key_idx[i] != EMPTY_SLOT) {
-			cur_bkt->key_idx[pos] = last_bkt->key_idx[i];
 			cur_bkt->sig_current[pos] = last_bkt->sig_current[i];
+			__atomic_store_n(&cur_bkt->key_idx[pos],
+					 last_bkt->key_idx[i],
+					 __ATOMIC_RELEASE);
+			if (h->readwrite_concur_lf_support) {
+				/* Inform the readers that the table has changed
+				 * Since there is one writer, load acquire on
+				 * tbl_chng_cnt is not required.
+				 */
+				__atomic_store_n(h->tbl_chng_cnt,
+					 *h->tbl_chng_cnt + 1,
+					 __ATOMIC_RELEASE);
+				/* The store to sig_current should
+				 * not move above the store to tbl_chng_cnt.
+				 */
+				__atomic_thread_fence(__ATOMIC_RELEASE);
+			}
 			last_bkt->sig_current[i] = NULL_SIGNATURE;
-			last_bkt->key_idx[i] = EMPTY_SLOT;
+			__atomic_store_n(&last_bkt->key_idx[i],
+					 EMPTY_SLOT,
+					 __ATOMIC_RELEASE);
 			return;
 		}
 	}
@@ -1449,7 +1488,7 @@ __rte_hash_del_key_with_hash(const struct rte_hash *h, const void *key,
 	/* look for key in primary bucket */
 	ret = search_and_remove(h, key, prim_bkt, short_sig, &pos);
 	if (ret != -1) {
-		__rte_hash_compact_ll(prim_bkt, pos);
+		__rte_hash_compact_ll(h, prim_bkt, pos);
 		last_bkt = prim_bkt->next;
 		prev_bkt = prim_bkt;
 		goto return_bkt;
@@ -1461,7 +1500,7 @@ __rte_hash_del_key_with_hash(const struct rte_hash *h, const void *key,
 	FOR_EACH_BUCKET(cur_bkt, sec_bkt) {
 		ret = search_and_remove(h, key, cur_bkt, short_sig, &pos);
 		if (ret != -1) {
-			__rte_hash_compact_ll(cur_bkt, pos);
+			__rte_hash_compact_ll(h, cur_bkt, pos);
 			last_bkt = sec_bkt->next;
 			prev_bkt = sec_bkt;
 			goto return_bkt;
@@ -1488,11 +1527,24 @@ __rte_hash_del_key_with_hash(const struct rte_hash *h, const void *key,
 	}
 	/* found empty bucket and recycle */
 	if (i == RTE_HASH_BUCKET_ENTRIES) {
-		prev_bkt->next = last_bkt->next = NULL;
+		prev_bkt->next = NULL;
 		uint32_t index = last_bkt - h->buckets_ext + 1;
-		rte_ring_sp_enqueue(h->free_ext_bkts, (void *)(uintptr_t)index);
+		/* Recycle the empty bkt if
+		 * no_free_on_del is disabled.
+		 */
+		if (h->no_free_on_del)
+			/* Store index of an empty ext bkt to be recycled
+			 * on calling rte_hash_del_xxx APIs.
+			 * When lock free read-write concurrency is enabled,
+			 * an empty ext bkt cannot be put into free list
+			 * immediately (as readers might be using it still).
+			 * Hence freeing of the ext bkt is piggy-backed to
+			 * freeing of the key index.
+			 */
+			h->ext_bkt_to_free[ret] = index;
+		else
+			rte_ring_sp_enqueue(h->free_ext_bkts, (void *)(uintptr_t)index);
 	}
-
 	__hash_rw_writer_unlock(h);
 	return ret;
 }
@@ -1545,6 +1597,14 @@ rte_hash_free_key_with_position(const struct rte_hash *h,
 	/* Out of bounds */
 	if (position >= total_entries)
 		return -EINVAL;
+	if (h->ext_table_support) {
+		uint32_t index = h->ext_bkt_to_free[position];
+		if (index) {
+			/* Recycle empty ext bkt to free list. */
+			rte_ring_sp_enqueue(h->free_ext_bkts, (void *)(uintptr_t)index);
+			h->ext_bkt_to_free[position] = 0;
+		}
+	}
 
 	if (h->use_local_cache) {
 		lcore_id = rte_lcore_id();
@@ -1855,6 +1915,9 @@ __rte_hash_lookup_bulk_lf(const struct rte_hash *h, const void **keys,
 		rte_prefetch0(secondary_bkt[i]);
 	}
 
+	for (i = 0; i < num_keys; i++)
+		positions[i] = -ENOENT;
+
 	do {
 		/* Load the table change counter before the lookup
 		 * starts. Acquire semantics will make sure that
@@ -1899,7 +1962,6 @@ __rte_hash_lookup_bulk_lf(const struct rte_hash *h, const void **keys,
 
 		/* Compare keys, first hits in primary first */
 		for (i = 0; i < num_keys; i++) {
-			positions[i] = -ENOENT;
 			while (prim_hitmask[i]) {
 				uint32_t hit_index =
 						__builtin_ctzl(prim_hitmask[i])
@@ -1972,6 +2034,35 @@ __rte_hash_lookup_bulk_lf(const struct rte_hash *h, const void **keys,
 			continue;
 		}
 
+		/* all found, do not need to go through ext bkt */
+		if (hits == ((1ULL << num_keys) - 1)) {
+			if (hit_mask != NULL)
+				*hit_mask = hits;
+			return;
+		}
+		/* need to check ext buckets for match */
+		if (h->ext_table_support) {
+			for (i = 0; i < num_keys; i++) {
+				if ((hits & (1ULL << i)) != 0)
+					continue;
+				next_bkt = secondary_bkt[i]->next;
+				FOR_EACH_BUCKET(cur_bkt, next_bkt) {
+					if (data != NULL)
+						ret = search_one_bucket_lf(h,
+							keys[i], sig[i],
+							&data[i], cur_bkt);
+					else
+						ret = search_one_bucket_lf(h,
+								keys[i], sig[i],
+								NULL, cur_bkt);
+					if (ret != -1) {
+						positions[i] = ret;
+						hits |= 1ULL << i;
+						break;
+					}
+				}
+			}
+		}
 		/* The loads of sig_current in compare_signatures
 		 * should not move below the load from tbl_chng_cnt.
 		 */
@@ -1988,34 +2079,6 @@ __rte_hash_lookup_bulk_lf(const struct rte_hash *h, const void **keys,
 					__ATOMIC_ACQUIRE);
 	} while (cnt_b != cnt_a);
 
-	/* all found, do not need to go through ext bkt */
-	if ((hits == ((1ULL << num_keys) - 1)) || !h->ext_table_support) {
-		if (hit_mask != NULL)
-			*hit_mask = hits;
-		__hash_rw_reader_unlock(h);
-		return;
-	}
-
-	/* need to check ext buckets for match */
-	for (i = 0; i < num_keys; i++) {
-		if ((hits & (1ULL << i)) != 0)
-			continue;
-		next_bkt = secondary_bkt[i]->next;
-		FOR_EACH_BUCKET(cur_bkt, next_bkt) {
-			if (data != NULL)
-				ret = search_one_bucket_lf(h, keys[i],
-						sig[i], &data[i], cur_bkt);
-			else
-				ret = search_one_bucket_lf(h, keys[i],
-						sig[i], NULL, cur_bkt);
-			if (ret != -1) {
-				positions[i] = ret;
-				hits |= 1ULL << i;
-				break;
-			}
-		}
-	}
-
 	if (hit_mask != NULL)
 		*hit_mask = hits;
 }
diff --git a/lib/librte_hash/rte_cuckoo_hash.h b/lib/librte_hash/rte_cuckoo_hash.h
index eacdaa8d4684..48c85c890712 100644
--- a/lib/librte_hash/rte_cuckoo_hash.h
+++ b/lib/librte_hash/rte_cuckoo_hash.h
@@ -210,6 +210,13 @@ struct rte_hash {
 	rte_rwlock_t *readwrite_lock; /**< Read-write lock thread-safety. */
 	struct rte_hash_bucket *buckets_ext; /**< Extra buckets array */
 	struct rte_ring *free_ext_bkts; /**< Ring of indexes of free buckets */
+	/* Stores index of an empty ext bkt to be recycled on calling
+	 * rte_hash_del_xxx APIs. When lock free read-write concurrency is
+	 * enabled, an empty ext bkt cannot be put into free list immediately
+	 * (as readers might be using it still). Hence freeing of the ext bkt
+	 * is piggy-backed to freeing of the key index.
+	 */
+	uint32_t *ext_bkt_to_free;
 	uint32_t *tbl_chng_cnt;
 	/**< Indicates if the hash table changed from last read. */
 } __rte_cache_aligned;
-- 
2.17.1

[dpdk-dev] [PATCH 1/2] hash: add lock free support for extendable bucket

[Dharmik Thakkar]

This patch enables lock-free read-write concurrency support for
extendable bucket feature.

Suggested-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
Signed-off-by: Dharmik Thakkar <dharmik.thakkar@arm.com>
Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
Reviewed-by: Gavin Hu <gavin.hu@arm.com>
Reviewed-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
---
 doc/guides/prog_guide/hash_lib.rst |   3 +-
 lib/librte_hash/rte_cuckoo_hash.c  | 163 ++++++++++++++++++++---------
 lib/librte_hash/rte_cuckoo_hash.h  |   7 ++
 3 files changed, 121 insertions(+), 52 deletions(-)

diff --git a/doc/guides/prog_guide/hash_lib.rst b/doc/guides/prog_guide/hash_lib.rst
index 85a6edfa8b16..b00446e949ba 100644
--- a/doc/guides/prog_guide/hash_lib.rst
+++ b/doc/guides/prog_guide/hash_lib.rst
@@ -108,8 +108,7 @@ Extendable Bucket Functionality support
 An extra flag is used to enable this functionality (flag is not set by default). When the (RTE_HASH_EXTRA_FLAGS_EXT_TABLE) is set and
 in the very unlikely case due to excessive hash collisions that a key has failed to be inserted, the hash table bucket is extended with a linked
 list to insert these failed keys. This feature is important for the workloads (e.g. telco workloads) that need to insert up to 100% of the
-hash table size and can't tolerate any key insertion failure (even if very few). Currently the extendable bucket is not supported
-with the lock-free concurrency implementation (RTE_HASH_EXTRA_FLAGS_RW_CONCURRENCY_LF).
+hash table size and can't tolerate any key insertion failure (even if very few).
 
 
 Implementation Details (non Extendable Bucket Case)
diff --git a/lib/librte_hash/rte_cuckoo_hash.c b/lib/librte_hash/rte_cuckoo_hash.c
index c01489ba5193..4cb05a5528c1 100644
--- a/lib/librte_hash/rte_cuckoo_hash.c
+++ b/lib/librte_hash/rte_cuckoo_hash.c
@@ -140,6 +140,7 @@ rte_hash_create(const struct rte_hash_parameters *params)
 	unsigned int readwrite_concur_support = 0;
 	unsigned int writer_takes_lock = 0;
 	unsigned int no_free_on_del = 0;
+	uint32_t *ext_bkt_to_free = NULL;
 	uint32_t *tbl_chng_cnt = NULL;
 	unsigned int readwrite_concur_lf_support = 0;
 
@@ -170,15 +171,6 @@ rte_hash_create(const struct rte_hash_parameters *params)
 		return NULL;
 	}
 
-	if ((params->extra_flag & RTE_HASH_EXTRA_FLAGS_RW_CONCURRENCY_LF) &&
-	    (params->extra_flag & RTE_HASH_EXTRA_FLAGS_EXT_TABLE)) {
-		rte_errno = EINVAL;
-		RTE_LOG(ERR, HASH, "rte_hash_create: extendable bucket "
-			"feature not supported with rw concurrency "
-			"lock free\n");
-		return NULL;
-	}
-
 	/* Check extra flags field to check extra options. */
 	if (params->extra_flag & RTE_HASH_EXTRA_FLAGS_TRANS_MEM_SUPPORT)
 		hw_trans_mem_support = 1;
@@ -302,6 +294,16 @@ rte_hash_create(const struct rte_hash_parameters *params)
 		 */
 		for (i = 1; i <= num_buckets; i++)
 			rte_ring_sp_enqueue(r_ext, (void *)((uintptr_t) i));
+
+		if (readwrite_concur_lf_support) {
+			ext_bkt_to_free = rte_zmalloc(NULL, sizeof(uint32_t) *
+								num_key_slots, 0);
+			if (ext_bkt_to_free == NULL) {
+				RTE_LOG(ERR, HASH, "ext bkt to free memory allocation "
+								"failed\n");
+				goto err_unlock;
+			}
+		}
 	}
 
 	const uint32_t key_entry_size =
@@ -393,6 +395,7 @@ rte_hash_create(const struct rte_hash_parameters *params)
 		default_hash_func : params->hash_func;
 	h->key_store = k;
 	h->free_slots = r;
+	h->ext_bkt_to_free = ext_bkt_to_free;
 	h->tbl_chng_cnt = tbl_chng_cnt;
 	*h->tbl_chng_cnt = 0;
 	h->hw_trans_mem_support = hw_trans_mem_support;
@@ -443,6 +446,7 @@ rte_hash_create(const struct rte_hash_parameters *params)
 	rte_free(buckets_ext);
 	rte_free(k);
 	rte_free(tbl_chng_cnt);
+	rte_free(ext_bkt_to_free);
 	return NULL;
 }
 
@@ -484,6 +488,7 @@ rte_hash_free(struct rte_hash *h)
 	rte_free(h->buckets);
 	rte_free(h->buckets_ext);
 	rte_free(h->tbl_chng_cnt);
+	rte_free(h->ext_bkt_to_free);
 	rte_free(h);
 	rte_free(te);
 }
@@ -799,7 +804,7 @@ rte_hash_cuckoo_move_insert_mw(const struct rte_hash *h,
 			__atomic_store_n(h->tbl_chng_cnt,
 					 *h->tbl_chng_cnt + 1,
 					 __ATOMIC_RELEASE);
-			/* The stores to sig_alt and sig_current should not
+			/* The store to sig_current should not
 			 * move above the store to tbl_chng_cnt.
 			 */
 			__atomic_thread_fence(__ATOMIC_RELEASE);
@@ -831,7 +836,7 @@ rte_hash_cuckoo_move_insert_mw(const struct rte_hash *h,
 		__atomic_store_n(h->tbl_chng_cnt,
 				 *h->tbl_chng_cnt + 1,
 				 __ATOMIC_RELEASE);
-		/* The stores to sig_alt and sig_current should not
+		/* The store to sig_current should not
 		 * move above the store to tbl_chng_cnt.
 		 */
 		__atomic_thread_fence(__ATOMIC_RELEASE);
@@ -1054,7 +1059,15 @@ __rte_hash_add_key_with_hash(const struct rte_hash *h, const void *key,
 			/* Check if slot is available */
 			if (likely(cur_bkt->key_idx[i] == EMPTY_SLOT)) {
 				cur_bkt->sig_current[i] = short_sig;
-				cur_bkt->key_idx[i] = new_idx;
+				/* Key can be of arbitrary length, so it is
+				 * not possible to store it atomically.
+				 * Hence the new key element's memory stores
+				 * (key as well as data) should be complete
+				 * before it is referenced.
+				 */
+				__atomic_store_n(&cur_bkt->key_idx[i],
+						 new_idx,
+						 __ATOMIC_RELEASE);
 				__hash_rw_writer_unlock(h);
 				return new_idx - 1;
 			}
@@ -1072,7 +1085,15 @@ __rte_hash_add_key_with_hash(const struct rte_hash *h, const void *key,
 	bkt_id = (uint32_t)((uintptr_t)ext_bkt_id) - 1;
 	/* Use the first location of the new bucket */
 	(h->buckets_ext[bkt_id]).sig_current[0] = short_sig;
-	(h->buckets_ext[bkt_id]).key_idx[0] = new_idx;
+	/* Key can be of arbitrary length, so it is
+	 * not possible to store it atomically.
+	 * Hence the new key element's memory stores
+	 * (key as well as data) should be complete
+	 * before it is referenced.
+	 */
+	__atomic_store_n(&(h->buckets_ext[bkt_id]).key_idx[0],
+			 new_idx,
+			 __ATOMIC_RELEASE);
 	/* Link the new bucket to sec bucket linked list */
 	last = rte_hash_get_last_bkt(sec_bkt);
 	last->next = &h->buckets_ext[bkt_id];
@@ -1366,7 +1387,8 @@ remove_entry(const struct rte_hash *h, struct rte_hash_bucket *bkt, unsigned i)
  * empty slot.
  */
 static inline void
-__rte_hash_compact_ll(struct rte_hash_bucket *cur_bkt, int pos) {
+__rte_hash_compact_ll(const struct rte_hash *h,
+			struct rte_hash_bucket *cur_bkt, int pos) {
 	int i;
 	struct rte_hash_bucket *last_bkt;
 
@@ -1377,10 +1399,27 @@ __rte_hash_compact_ll(struct rte_hash_bucket *cur_bkt, int pos) {
 
 	for (i = RTE_HASH_BUCKET_ENTRIES - 1; i >= 0; i--) {
 		if (last_bkt->key_idx[i] != EMPTY_SLOT) {
-			cur_bkt->key_idx[pos] = last_bkt->key_idx[i];
 			cur_bkt->sig_current[pos] = last_bkt->sig_current[i];
+			__atomic_store_n(&cur_bkt->key_idx[pos],
+					 last_bkt->key_idx[i],
+					 __ATOMIC_RELEASE);
+			if (h->readwrite_concur_lf_support) {
+				/* Inform the readers that the table has changed
+				 * Since there is one writer, load acquire on
+				 * tbl_chng_cnt is not required.
+				 */
+				__atomic_store_n(h->tbl_chng_cnt,
+					 *h->tbl_chng_cnt + 1,
+					 __ATOMIC_RELEASE);
+				/* The store to sig_current should
+				 * not move above the store to tbl_chng_cnt.
+				 */
+				__atomic_thread_fence(__ATOMIC_RELEASE);
+			}
 			last_bkt->sig_current[i] = NULL_SIGNATURE;
-			last_bkt->key_idx[i] = EMPTY_SLOT;
+			__atomic_store_n(&last_bkt->key_idx[i],
+					 EMPTY_SLOT,
+					 __ATOMIC_RELEASE);
 			return;
 		}
 	}
@@ -1449,7 +1488,7 @@ __rte_hash_del_key_with_hash(const struct rte_hash *h, const void *key,
 	/* look for key in primary bucket */
 	ret = search_and_remove(h, key, prim_bkt, short_sig, &pos);
 	if (ret != -1) {
-		__rte_hash_compact_ll(prim_bkt, pos);
+		__rte_hash_compact_ll(h, prim_bkt, pos);
 		last_bkt = prim_bkt->next;
 		prev_bkt = prim_bkt;
 		goto return_bkt;
@@ -1461,7 +1500,7 @@ __rte_hash_del_key_with_hash(const struct rte_hash *h, const void *key,
 	FOR_EACH_BUCKET(cur_bkt, sec_bkt) {
 		ret = search_and_remove(h, key, cur_bkt, short_sig, &pos);
 		if (ret != -1) {
-			__rte_hash_compact_ll(cur_bkt, pos);
+			__rte_hash_compact_ll(h, cur_bkt, pos);
 			last_bkt = sec_bkt->next;
 			prev_bkt = sec_bkt;
 			goto return_bkt;
@@ -1488,11 +1527,24 @@ __rte_hash_del_key_with_hash(const struct rte_hash *h, const void *key,
 	}
 	/* found empty bucket and recycle */
 	if (i == RTE_HASH_BUCKET_ENTRIES) {
-		prev_bkt->next = last_bkt->next = NULL;
+		prev_bkt->next = NULL;
 		uint32_t index = last_bkt - h->buckets_ext + 1;
-		rte_ring_sp_enqueue(h->free_ext_bkts, (void *)(uintptr_t)index);
+		/* Recycle the empty bkt if
+		 * no_free_on_del is disabled.
+		 */
+		if (h->no_free_on_del)
+			/* Store index of an empty ext bkt to be recycled
+			 * on calling rte_hash_del_xxx APIs.
+			 * When lock free read-write concurrency is enabled,
+			 * an empty ext bkt cannot be put into free list
+			 * immediately (as readers might be using it still).
+			 * Hence freeing of the ext bkt is piggy-backed to
+			 * freeing of the key index.
+			 */
+			h->ext_bkt_to_free[ret] = index;
+		else
+			rte_ring_sp_enqueue(h->free_ext_bkts, (void *)(uintptr_t)index);
 	}
-
 	__hash_rw_writer_unlock(h);
 	return ret;
 }
@@ -1545,6 +1597,14 @@ rte_hash_free_key_with_position(const struct rte_hash *h,
 	/* Out of bounds */
 	if (position >= total_entries)
 		return -EINVAL;
+	if (h->ext_table_support) {
+		uint32_t index = h->ext_bkt_to_free[position];
+		if (index) {
+			/* Recycle empty ext bkt to free list. */
+			rte_ring_sp_enqueue(h->free_ext_bkts, (void *)(uintptr_t)index);
+			h->ext_bkt_to_free[position] = 0;
+		}
+	}
 
 	if (h->use_local_cache) {
 		lcore_id = rte_lcore_id();
@@ -1855,6 +1915,9 @@ __rte_hash_lookup_bulk_lf(const struct rte_hash *h, const void **keys,
 		rte_prefetch0(secondary_bkt[i]);
 	}
 
+	for (i = 0; i < num_keys; i++)
+		positions[i] = -ENOENT;
+
 	do {
 		/* Load the table change counter before the lookup
 		 * starts. Acquire semantics will make sure that
@@ -1899,7 +1962,6 @@ __rte_hash_lookup_bulk_lf(const struct rte_hash *h, const void **keys,
 
 		/* Compare keys, first hits in primary first */
 		for (i = 0; i < num_keys; i++) {
-			positions[i] = -ENOENT;
 			while (prim_hitmask[i]) {
 				uint32_t hit_index =
 						__builtin_ctzl(prim_hitmask[i])
@@ -1972,6 +2034,35 @@ __rte_hash_lookup_bulk_lf(const struct rte_hash *h, const void **keys,
 			continue;
 		}
 
+		/* all found, do not need to go through ext bkt */
+		if (hits == ((1ULL << num_keys) - 1)) {
+			if (hit_mask != NULL)
+				*hit_mask = hits;
+			return;
+		}
+		/* need to check ext buckets for match */
+		if (h->ext_table_support) {
+			for (i = 0; i < num_keys; i++) {
+				if ((hits & (1ULL << i)) != 0)
+					continue;
+				next_bkt = secondary_bkt[i]->next;
+				FOR_EACH_BUCKET(cur_bkt, next_bkt) {
+					if (data != NULL)
+						ret = search_one_bucket_lf(h,
+							keys[i], sig[i],
+							&data[i], cur_bkt);
+					else
+						ret = search_one_bucket_lf(h,
+								keys[i], sig[i],
+								NULL, cur_bkt);
+					if (ret != -1) {
+						positions[i] = ret;
+						hits |= 1ULL << i;
+						break;
+					}
+				}
+			}
+		}
 		/* The loads of sig_current in compare_signatures
 		 * should not move below the load from tbl_chng_cnt.
 		 */
@@ -1988,34 +2079,6 @@ __rte_hash_lookup_bulk_lf(const struct rte_hash *h, const void **keys,
 					__ATOMIC_ACQUIRE);
 	} while (cnt_b != cnt_a);
 
-	/* all found, do not need to go through ext bkt */
-	if ((hits == ((1ULL << num_keys) - 1)) || !h->ext_table_support) {
-		if (hit_mask != NULL)
-			*hit_mask = hits;
-		__hash_rw_reader_unlock(h);
-		return;
-	}
-
-	/* need to check ext buckets for match */
-	for (i = 0; i < num_keys; i++) {
-		if ((hits & (1ULL << i)) != 0)
-			continue;
-		next_bkt = secondary_bkt[i]->next;
-		FOR_EACH_BUCKET(cur_bkt, next_bkt) {
-			if (data != NULL)
-				ret = search_one_bucket_lf(h, keys[i],
-						sig[i], &data[i], cur_bkt);
-			else
-				ret = search_one_bucket_lf(h, keys[i],
-						sig[i], NULL, cur_bkt);
-			if (ret != -1) {
-				positions[i] = ret;
-				hits |= 1ULL << i;
-				break;
-			}
-		}
-	}
-
 	if (hit_mask != NULL)
 		*hit_mask = hits;
 }
diff --git a/lib/librte_hash/rte_cuckoo_hash.h b/lib/librte_hash/rte_cuckoo_hash.h
index eacdaa8d4684..48c85c890712 100644
--- a/lib/librte_hash/rte_cuckoo_hash.h
+++ b/lib/librte_hash/rte_cuckoo_hash.h
@@ -210,6 +210,13 @@ struct rte_hash {
 	rte_rwlock_t *readwrite_lock; /**< Read-write lock thread-safety. */
 	struct rte_hash_bucket *buckets_ext; /**< Extra buckets array */
 	struct rte_ring *free_ext_bkts; /**< Ring of indexes of free buckets */
+	/* Stores index of an empty ext bkt to be recycled on calling
+	 * rte_hash_del_xxx APIs. When lock free read-write concurrency is
+	 * enabled, an empty ext bkt cannot be put into free list immediately
+	 * (as readers might be using it still). Hence freeing of the ext bkt
+	 * is piggy-backed to freeing of the key index.
+	 */
+	uint32_t *ext_bkt_to_free;
 	uint32_t *tbl_chng_cnt;
 	/**< Indicates if the hash table changed from last read. */
 } __rte_cache_aligned;
-- 
2.17.1

Re: [dpdk-dev] [PATCH 1/2] hash: add lock free support for extendable bucket

[Wang, Yipeng1]

Thanks for the patch! 

Comments inlined:

>-----Original Message-----
>From: Dharmik Thakkar [mailto:dharmik.thakkar@arm.com]
>Sent: Wednesday, March 20, 2019 3:35 PM
>To: Wang, Yipeng1 <yipeng1.wang@intel.com>; Gobriel, Sameh <sameh.gobriel@intel.com>; Richardson, Bruce
><bruce.richardson@intel.com>; De Lara Guarch, Pablo <pablo.de.lara.guarch@intel.com>; Mcnamara, John
><john.mcnamara@intel.com>; Kovacevic, Marko <marko.kovacevic@intel.com>
>Cc: dev@dpdk.org; Dharmik Thakkar <dharmik.thakkar@arm.com>
>Subject: [PATCH 1/2] hash: add lock free support for extendable bucket
>
>This patch enables lock-free read-write concurrency support for
>extendable bucket feature.
>
>Suggested-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
>Signed-off-by: Dharmik Thakkar <dharmik.thakkar@arm.com>
>Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
>Reviewed-by: Gavin Hu <gavin.hu@arm.com>
>Reviewed-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
>---
> doc/guides/prog_guide/hash_lib.rst |   3 +-
> lib/librte_hash/rte_cuckoo_hash.c  | 163 ++++++++++++++++++++---------
> lib/librte_hash/rte_cuckoo_hash.h  |   7 ++
> 3 files changed, 121 insertions(+), 52 deletions(-)
>
>diff --git a/doc/guides/prog_guide/hash_lib.rst b/doc/guides/prog_guide/hash_lib.rst
>index 85a6edfa8b16..b00446e949ba 100644
>--- a/doc/guides/prog_guide/hash_lib.rst
>+++ b/doc/guides/prog_guide/hash_lib.rst
>@@ -108,8 +108,7 @@ Extendable Bucket Functionality support
> An extra flag is used to enable this functionality (flag is not set by default). When the (RTE_HASH_EXTRA_FLAGS_EXT_TABLE) is set
>and
> in the very unlikely case due to excessive hash collisions that a key has failed to be inserted, the hash table bucket is extended with a
>linked
> list to insert these failed keys. This feature is important for the workloads (e.g. telco workloads) that need to insert up to 100% of the
>-hash table size and can't tolerate any key insertion failure (even if very few). Currently the extendable bucket is not supported
>-with the lock-free concurrency implementation (RTE_HASH_EXTRA_FLAGS_RW_CONCURRENCY_LF).
>+hash table size and can't tolerate any key insertion failure (even if very few).
[Wang, Yipeng] I am thinking maybe make it a bit more clear here by adding something like:
Please note that with the lock-free flag enabled, users need to promptly free the deleted keys, to maintain the 100% capacity guarantee.

I want to add this because of the piggy-back mechanism, one un-recycled key with an un-recycled ext bucket may actually makes in total
of 9 entries unavailable (8 entries in the ext bucket). So it would be useful to remind the user here.
>
>
>@@ -1054,7 +1059,15 @@ __rte_hash_add_key_with_hash(const struct rte_hash *h, const void *key,
> 			/* Check if slot is available */
> 			if (likely(cur_bkt->key_idx[i] == EMPTY_SLOT)) {
> 				cur_bkt->sig_current[i] = short_sig;
>-				cur_bkt->key_idx[i] = new_idx;
>+				/* Key can be of arbitrary length, so it is
>+				 * not possible to store it atomically.
>+				 * Hence the new key element's memory stores
>+				 * (key as well as data) should be complete
>+				 * before it is referenced.
>+				 */
[Wang, Yipeng]  My understanding is this atomic store is to prevent the signature store leaking after the key_idx store.
But the comment does not exactly describe this reason.
>+				__atomic_store_n(&cur_bkt->key_idx[i],
>+						 new_idx,
>+						 __ATOMIC_RELEASE);
> 				__hash_rw_writer_unlock(h);
> 				return new_idx - 1;
> 			}
>@@ -1545,6 +1597,14 @@ rte_hash_free_key_with_position(const struct rte_hash *h,
> 	/* Out of bounds */
> 	if (position >= total_entries)
> 		return -EINVAL;
>+	if (h->ext_table_support) {
>+		uint32_t index = h->ext_bkt_to_free[position];
[Wang, Yipeng] I think user can theoretically set  RTE_HASH_EXTRA_FLAGS_NO_FREE_ON_DEL to be 1
But LF flag to be 0. I think here you assume this function only called when LF flag is 1. You may need to
Add another condition e.g. if(h->ext_table_support && h->readwrite_concur_lf_support)
>+		if (index) {
>+			/* Recycle empty ext bkt to free list. */
>+			rte_ring_sp_enqueue(h->free_ext_bkts, (void *)(uintptr_t)index);
>+			h->ext_bkt_to_free[position] = 0;
>+		}
>+	}
>
> 	if (h->use_local_cache) {
> 		lcore_id = rte_lcore_id();

Re: [dpdk-dev] [PATCH 1/2] hash: add lock free support for extendable bucket

[Wang, Yipeng1]

Thanks for the patch! 

Comments inlined:

>-----Original Message-----
>From: Dharmik Thakkar [mailto:dharmik.thakkar@arm.com]
>Sent: Wednesday, March 20, 2019 3:35 PM
>To: Wang, Yipeng1 <yipeng1.wang@intel.com>; Gobriel, Sameh <sameh.gobriel@intel.com>; Richardson, Bruce
><bruce.richardson@intel.com>; De Lara Guarch, Pablo <pablo.de.lara.guarch@intel.com>; Mcnamara, John
><john.mcnamara@intel.com>; Kovacevic, Marko <marko.kovacevic@intel.com>
>Cc: dev@dpdk.org; Dharmik Thakkar <dharmik.thakkar@arm.com>
>Subject: [PATCH 1/2] hash: add lock free support for extendable bucket
>
>This patch enables lock-free read-write concurrency support for
>extendable bucket feature.
>
>Suggested-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
>Signed-off-by: Dharmik Thakkar <dharmik.thakkar@arm.com>
>Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
>Reviewed-by: Gavin Hu <gavin.hu@arm.com>
>Reviewed-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
>---
> doc/guides/prog_guide/hash_lib.rst |   3 +-
> lib/librte_hash/rte_cuckoo_hash.c  | 163 ++++++++++++++++++++---------
> lib/librte_hash/rte_cuckoo_hash.h  |   7 ++
> 3 files changed, 121 insertions(+), 52 deletions(-)
>
>diff --git a/doc/guides/prog_guide/hash_lib.rst b/doc/guides/prog_guide/hash_lib.rst
>index 85a6edfa8b16..b00446e949ba 100644
>--- a/doc/guides/prog_guide/hash_lib.rst
>+++ b/doc/guides/prog_guide/hash_lib.rst
>@@ -108,8 +108,7 @@ Extendable Bucket Functionality support
> An extra flag is used to enable this functionality (flag is not set by default). When the (RTE_HASH_EXTRA_FLAGS_EXT_TABLE) is set
>and
> in the very unlikely case due to excessive hash collisions that a key has failed to be inserted, the hash table bucket is extended with a
>linked
> list to insert these failed keys. This feature is important for the workloads (e.g. telco workloads) that need to insert up to 100% of the
>-hash table size and can't tolerate any key insertion failure (even if very few). Currently the extendable bucket is not supported
>-with the lock-free concurrency implementation (RTE_HASH_EXTRA_FLAGS_RW_CONCURRENCY_LF).
>+hash table size and can't tolerate any key insertion failure (even if very few).
[Wang, Yipeng] I am thinking maybe make it a bit more clear here by adding something like:
Please note that with the lock-free flag enabled, users need to promptly free the deleted keys, to maintain the 100% capacity guarantee.

I want to add this because of the piggy-back mechanism, one un-recycled key with an un-recycled ext bucket may actually makes in total
of 9 entries unavailable (8 entries in the ext bucket). So it would be useful to remind the user here.
>
>
>@@ -1054,7 +1059,15 @@ __rte_hash_add_key_with_hash(const struct rte_hash *h, const void *key,
> 			/* Check if slot is available */
> 			if (likely(cur_bkt->key_idx[i] == EMPTY_SLOT)) {
> 				cur_bkt->sig_current[i] = short_sig;
>-				cur_bkt->key_idx[i] = new_idx;
>+				/* Key can be of arbitrary length, so it is
>+				 * not possible to store it atomically.
>+				 * Hence the new key element's memory stores
>+				 * (key as well as data) should be complete
>+				 * before it is referenced.
>+				 */
[Wang, Yipeng]  My understanding is this atomic store is to prevent the signature store leaking after the key_idx store.
But the comment does not exactly describe this reason.
>+				__atomic_store_n(&cur_bkt->key_idx[i],
>+						 new_idx,
>+						 __ATOMIC_RELEASE);
> 				__hash_rw_writer_unlock(h);
> 				return new_idx - 1;
> 			}
>@@ -1545,6 +1597,14 @@ rte_hash_free_key_with_position(const struct rte_hash *h,
> 	/* Out of bounds */
> 	if (position >= total_entries)
> 		return -EINVAL;
>+	if (h->ext_table_support) {
>+		uint32_t index = h->ext_bkt_to_free[position];
[Wang, Yipeng] I think user can theoretically set  RTE_HASH_EXTRA_FLAGS_NO_FREE_ON_DEL to be 1
But LF flag to be 0. I think here you assume this function only called when LF flag is 1. You may need to
Add another condition e.g. if(h->ext_table_support && h->readwrite_concur_lf_support)
>+		if (index) {
>+			/* Recycle empty ext bkt to free list. */
>+			rte_ring_sp_enqueue(h->free_ext_bkts, (void *)(uintptr_t)index);
>+			h->ext_bkt_to_free[position] = 0;
>+		}
>+	}
>
> 	if (h->use_local_cache) {
> 		lcore_id = rte_lcore_id();

Re: [dpdk-dev] [PATCH 1/2] hash: add lock free support for extendable bucket

[Dharmik Thakkar]

+Honnappa

Hi Yipeng,

Thank you for reviewing!

> On Mar 22, 2019, at 6:48 PM, Wang, Yipeng1 <yipeng1.wang@intel.com> wrote:
> 
> Thanks for the patch! 
> 
> Comments inlined:
> 
>> -----Original Message-----
>> From: Dharmik Thakkar [mailto:dharmik.thakkar@arm.com]
>> Sent: Wednesday, March 20, 2019 3:35 PM
>> To: Wang, Yipeng1 <yipeng1.wang@intel.com>; Gobriel, Sameh <sameh.gobriel@intel.com>; Richardson, Bruce
>> <bruce.richardson@intel.com>; De Lara Guarch, Pablo <pablo.de.lara.guarch@intel.com>; Mcnamara, John
>> <john.mcnamara@intel.com>; Kovacevic, Marko <marko.kovacevic@intel.com>
>> Cc: dev@dpdk.org; Dharmik Thakkar <dharmik.thakkar@arm.com>
>> Subject: [PATCH 1/2] hash: add lock free support for extendable bucket
>> 
>> This patch enables lock-free read-write concurrency support for
>> extendable bucket feature.
>> 
>> Suggested-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
>> Signed-off-by: Dharmik Thakkar <dharmik.thakkar@arm.com>
>> Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
>> Reviewed-by: Gavin Hu <gavin.hu@arm.com>
>> Reviewed-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
>> ---
>> doc/guides/prog_guide/hash_lib.rst |   3 +-
>> lib/librte_hash/rte_cuckoo_hash.c  | 163 ++++++++++++++++++++---------
>> lib/librte_hash/rte_cuckoo_hash.h  |   7 ++
>> 3 files changed, 121 insertions(+), 52 deletions(-)
>> 
>> diff --git a/doc/guides/prog_guide/hash_lib.rst b/doc/guides/prog_guide/hash_lib.rst
>> index 85a6edfa8b16..b00446e949ba 100644
>> --- a/doc/guides/prog_guide/hash_lib.rst
>> +++ b/doc/guides/prog_guide/hash_lib.rst
>> @@ -108,8 +108,7 @@ Extendable Bucket Functionality support
>> An extra flag is used to enable this functionality (flag is not set by default). When the (RTE_HASH_EXTRA_FLAGS_EXT_TABLE) is set
>> and
>> in the very unlikely case due to excessive hash collisions that a key has failed to be inserted, the hash table bucket is extended with a
>> linked
>> list to insert these failed keys. This feature is important for the workloads (e.g. telco workloads) that need to insert up to 100% of the
>> -hash table size and can't tolerate any key insertion failure (even if very few). Currently the extendable bucket is not supported
>> -with the lock-free concurrency implementation (RTE_HASH_EXTRA_FLAGS_RW_CONCURRENCY_LF).
>> +hash table size and can't tolerate any key insertion failure (even if very few).
> [Wang, Yipeng] I am thinking maybe make it a bit more clear here by adding something like:
> Please note that with the lock-free flag enabled, users need to promptly free the deleted keys, to maintain the 100% capacity guarantee.
> 
> I want to add this because of the piggy-back mechanism, one un-recycled key with an un-recycled ext bucket may actually makes in total
> of 9 entries unavailable (8 entries in the ext bucket). So it would be useful to remind the user here.
All right. I will add it.
>> 
>> 
>> @@ -1054,7 +1059,15 @@ __rte_hash_add_key_with_hash(const struct rte_hash *h, const void *key,
>> 			/* Check if slot is available */
>> 			if (likely(cur_bkt->key_idx[i] == EMPTY_SLOT)) {
>> 				cur_bkt->sig_current[i] = short_sig;
>> -				cur_bkt->key_idx[i] = new_idx;
>> +				/* Key can be of arbitrary length, so it is
>> +				 * not possible to store it atomically.
>> +				 * Hence the new key element's memory stores
>> +				 * (key as well as data) should be complete
>> +				 * before it is referenced.
>> +				 */
> [Wang, Yipeng]  My understanding is this atomic store is to prevent the signature store leaking after the key_idx store.
> But the comment does not exactly describe this reason.
I will update the comment.
>> +				__atomic_store_n(&cur_bkt->key_idx[i],
>> +						 new_idx,
>> +						 __ATOMIC_RELEASE);
>> 				__hash_rw_writer_unlock(h);
>> 				return new_idx - 1;
>> 			}
>> @@ -1545,6 +1597,14 @@ rte_hash_free_key_with_position(const struct rte_hash *h,
>> 	/* Out of bounds */
>> 	if (position >= total_entries)
>> 		return -EINVAL;
>> +	if (h->ext_table_support) {
>> +		uint32_t index = h->ext_bkt_to_free[position];
> [Wang, Yipeng] I think user can theoretically set  RTE_HASH_EXTRA_FLAGS_NO_FREE_ON_DEL to be 1
> But LF flag to be 0. I think here you assume this function only called when LF flag is 1. You may need to
> Add another condition e.g. if(h->ext_table_support && h->readwrite_concur_lf_support)
Correct. I will update it.
>> +		if (index) {
>> +			/* Recycle empty ext bkt to free list. */
>> +			rte_ring_sp_enqueue(h->free_ext_bkts, (void *)(uintptr_t)index);
>> +			h->ext_bkt_to_free[position] = 0;
>> +		}
>> +	}
>> 
>> 	if (h->use_local_cache) {
>> 		lcore_id = rte_lcore_id();

Re: [dpdk-dev] [PATCH 1/2] hash: add lock free support for extendable bucket

[Dharmik Thakkar]

+Honnappa

Hi Yipeng,

Thank you for reviewing!

> On Mar 22, 2019, at 6:48 PM, Wang, Yipeng1 <yipeng1.wang@intel.com> wrote:
> 
> Thanks for the patch! 
> 
> Comments inlined:
> 
>> -----Original Message-----
>> From: Dharmik Thakkar [mailto:dharmik.thakkar@arm.com]
>> Sent: Wednesday, March 20, 2019 3:35 PM
>> To: Wang, Yipeng1 <yipeng1.wang@intel.com>; Gobriel, Sameh <sameh.gobriel@intel.com>; Richardson, Bruce
>> <bruce.richardson@intel.com>; De Lara Guarch, Pablo <pablo.de.lara.guarch@intel.com>; Mcnamara, John
>> <john.mcnamara@intel.com>; Kovacevic, Marko <marko.kovacevic@intel.com>
>> Cc: dev@dpdk.org; Dharmik Thakkar <dharmik.thakkar@arm.com>
>> Subject: [PATCH 1/2] hash: add lock free support for extendable bucket
>> 
>> This patch enables lock-free read-write concurrency support for
>> extendable bucket feature.
>> 
>> Suggested-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
>> Signed-off-by: Dharmik Thakkar <dharmik.thakkar@arm.com>
>> Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
>> Reviewed-by: Gavin Hu <gavin.hu@arm.com>
>> Reviewed-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
>> ---
>> doc/guides/prog_guide/hash_lib.rst |   3 +-
>> lib/librte_hash/rte_cuckoo_hash.c  | 163 ++++++++++++++++++++---------
>> lib/librte_hash/rte_cuckoo_hash.h  |   7 ++
>> 3 files changed, 121 insertions(+), 52 deletions(-)
>> 
>> diff --git a/doc/guides/prog_guide/hash_lib.rst b/doc/guides/prog_guide/hash_lib.rst
>> index 85a6edfa8b16..b00446e949ba 100644
>> --- a/doc/guides/prog_guide/hash_lib.rst
>> +++ b/doc/guides/prog_guide/hash_lib.rst
>> @@ -108,8 +108,7 @@ Extendable Bucket Functionality support
>> An extra flag is used to enable this functionality (flag is not set by default). When the (RTE_HASH_EXTRA_FLAGS_EXT_TABLE) is set
>> and
>> in the very unlikely case due to excessive hash collisions that a key has failed to be inserted, the hash table bucket is extended with a
>> linked
>> list to insert these failed keys. This feature is important for the workloads (e.g. telco workloads) that need to insert up to 100% of the
>> -hash table size and can't tolerate any key insertion failure (even if very few). Currently the extendable bucket is not supported
>> -with the lock-free concurrency implementation (RTE_HASH_EXTRA_FLAGS_RW_CONCURRENCY_LF).
>> +hash table size and can't tolerate any key insertion failure (even if very few).
> [Wang, Yipeng] I am thinking maybe make it a bit more clear here by adding something like:
> Please note that with the lock-free flag enabled, users need to promptly free the deleted keys, to maintain the 100% capacity guarantee.
> 
> I want to add this because of the piggy-back mechanism, one un-recycled key with an un-recycled ext bucket may actually makes in total
> of 9 entries unavailable (8 entries in the ext bucket). So it would be useful to remind the user here.
All right. I will add it.
>> 
>> 
>> @@ -1054,7 +1059,15 @@ __rte_hash_add_key_with_hash(const struct rte_hash *h, const void *key,
>> 			/* Check if slot is available */
>> 			if (likely(cur_bkt->key_idx[i] == EMPTY_SLOT)) {
>> 				cur_bkt->sig_current[i] = short_sig;
>> -				cur_bkt->key_idx[i] = new_idx;
>> +				/* Key can be of arbitrary length, so it is
>> +				 * not possible to store it atomically.
>> +				 * Hence the new key element's memory stores
>> +				 * (key as well as data) should be complete
>> +				 * before it is referenced.
>> +				 */
> [Wang, Yipeng]  My understanding is this atomic store is to prevent the signature store leaking after the key_idx store.
> But the comment does not exactly describe this reason.
I will update the comment.
>> +				__atomic_store_n(&cur_bkt->key_idx[i],
>> +						 new_idx,
>> +						 __ATOMIC_RELEASE);
>> 				__hash_rw_writer_unlock(h);
>> 				return new_idx - 1;
>> 			}
>> @@ -1545,6 +1597,14 @@ rte_hash_free_key_with_position(const struct rte_hash *h,
>> 	/* Out of bounds */
>> 	if (position >= total_entries)
>> 		return -EINVAL;
>> +	if (h->ext_table_support) {
>> +		uint32_t index = h->ext_bkt_to_free[position];
> [Wang, Yipeng] I think user can theoretically set  RTE_HASH_EXTRA_FLAGS_NO_FREE_ON_DEL to be 1
> But LF flag to be 0. I think here you assume this function only called when LF flag is 1. You may need to
> Add another condition e.g. if(h->ext_table_support && h->readwrite_concur_lf_support)
Correct. I will update it.
>> +		if (index) {
>> +			/* Recycle empty ext bkt to free list. */
>> +			rte_ring_sp_enqueue(h->free_ext_bkts, (void *)(uintptr_t)index);
>> +			h->ext_bkt_to_free[position] = 0;
>> +		}
>> +	}
>> 
>> 	if (h->use_local_cache) {
>> 		lcore_id = rte_lcore_id();

[dpdk-dev] [PATCH 2/2] test/hash: lock-free rw concurrency test ext bkt

[Dharmik Thakkar]

Add unit test to check for hash lookup and bulk-lookup perf.
Test with lock-free enabled and with lock-free disabled.

Test include:

- hash lookup on keys in ext bkt,
hash delete causing key-shifts of keys from ext bkt to secondary bkt

Suggested-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
Signed-off-by: Dharmik Thakkar <dharmik.thakkar@arm.com>
---
 app/test/test_hash_readwrite_lf.c | 350 ++++++++++++++++++++++++------
 1 file changed, 284 insertions(+), 66 deletions(-)

diff --git a/app/test/test_hash_readwrite_lf.c b/app/test/test_hash_readwrite_lf.c
index cbfd9322696b..ddd8d7aa6a7d 100644
--- a/app/test/test_hash_readwrite_lf.c
+++ b/app/test/test_hash_readwrite_lf.c
@@ -41,6 +41,12 @@
 #define READ_PASS_SHIFT_PATH 4
 #define READ_PASS_NON_SHIFT_PATH 8
 #define BULK_LOOKUP 16
+#define READ_PASS_KEY_SHIFTS_EXTBKT 32
+
+#define WRITE_NO_KEY_SHIFT 0
+#define WRITE_KEY_SHIFT 1
+#define WRITE_EXT_BKT 2
+
 #define NUM_TEST 3
 unsigned int rwc_core_cnt[NUM_TEST] = {1, 2, 4};
 
@@ -51,6 +57,7 @@ struct rwc_perf {
 	uint32_t w_ks_r_hit_sp[2][NUM_TEST];
 	uint32_t w_ks_r_miss[2][NUM_TEST];
 	uint32_t multi_rw[NUM_TEST - 1][2][NUM_TEST];
+	uint32_t w_ks_r_hit_extbkt[2][NUM_TEST];
 };
 
 static struct rwc_perf rwc_lf_results, rwc_non_lf_results;
@@ -62,11 +69,15 @@ struct {
 	uint32_t *keys_absent;
 	uint32_t *keys_shift_path;
 	uint32_t *keys_non_shift_path;
+	uint32_t *keys_ext_bkt;
+	uint32_t *keys_ks_extbkt;
 	uint32_t count_keys_no_ks;
 	uint32_t count_keys_ks;
 	uint32_t count_keys_absent;
 	uint32_t count_keys_shift_path;
 	uint32_t count_keys_non_shift_path;
+	uint32_t count_keys_extbkt;
+	uint32_t count_keys_ks_extbkt;
 	uint32_t single_insert;
 	struct rte_hash *h;
 } tbl_rwc_test_param;
@@ -81,6 +92,35 @@ uint16_t enabled_core_ids[RTE_MAX_LCORE];
 
 uint8_t *scanned_bkts;
 
+static inline uint16_t
+get_short_sig(const hash_sig_t hash)
+{
+	return hash >> 16;
+}
+
+static inline uint32_t
+get_prim_bucket_index(__attribute__((unused)) const struct rte_hash *h,
+		      const hash_sig_t hash)
+{
+	uint32_t num_buckets;
+	uint32_t bucket_bitmask;
+	num_buckets  = rte_align32pow2(TOTAL_ENTRY) / 8;
+	bucket_bitmask = num_buckets - 1;
+	return hash & bucket_bitmask;
+}
+
+static inline uint32_t
+get_alt_bucket_index(__attribute__((unused)) const struct rte_hash *h,
+			uint32_t cur_bkt_idx, uint16_t sig)
+{
+	uint32_t num_buckets;
+	uint32_t bucket_bitmask;
+	num_buckets  = rte_align32pow2(TOTAL_ENTRY) / 8;
+	bucket_bitmask = num_buckets - 1;
+	return (cur_bkt_idx ^ sig) & bucket_bitmask;
+}
+
+
 static inline int
 get_enabled_cores_list(void)
 {
@@ -168,9 +208,12 @@ generate_keys(void)
 	uint32_t *keys_ks = NULL;
 	uint32_t *keys_absent = NULL;
 	uint32_t *keys_non_shift_path = NULL;
+	uint32_t *keys_ext_bkt = NULL;
+	uint32_t *keys_ks_extbkt = NULL;
 	uint32_t *found = NULL;
 	uint32_t count_keys_no_ks = 0;
 	uint32_t count_keys_ks = 0;
+	uint32_t count_keys_extbkt = 0;
 	uint32_t i;
 
 	/*
@@ -251,14 +294,32 @@ generate_keys(void)
 		goto err;
 	}
 
+	/*
+	 * This consist of keys which will be stored in extended buckets
+	 */
+	keys_ext_bkt = rte_malloc(NULL, sizeof(uint32_t) * TOTAL_INSERT, 0);
+	if (keys_ext_bkt == NULL) {
+		printf("RTE_MALLOC failed\n");
+		goto err;
+	}
+
+	/*
+	 * This consist of keys which when deleted causes shifting of keys
+	 * in extended buckets to respective secondary buckets
+	 */
+	keys_ks_extbkt = rte_malloc(NULL, sizeof(uint32_t) * TOTAL_INSERT, 0);
+	if (keys_ks_extbkt == NULL) {
+		printf("RTE_MALLOC failed\n");
+		goto err;
+	}
 
 	hash_sig_t sig;
 	uint32_t prim_bucket_idx;
-	int ret;
+	uint32_t sec_bucket_idx;
+	uint16_t short_sig;
 	uint32_t num_buckets;
-	uint32_t bucket_bitmask;
 	num_buckets  = rte_align32pow2(TOTAL_ENTRY) / 8;
-	bucket_bitmask = num_buckets - 1;
+	int ret;
 
 	/*
 	 * Used to mark bkts in which at least one key was shifted to its
@@ -275,6 +336,8 @@ generate_keys(void)
 	tbl_rwc_test_param.keys_ks = keys_ks;
 	tbl_rwc_test_param.keys_absent = keys_absent;
 	tbl_rwc_test_param.keys_non_shift_path = keys_non_shift_path;
+	tbl_rwc_test_param.keys_ext_bkt = keys_ext_bkt;
+	tbl_rwc_test_param.keys_ks_extbkt = keys_ks_extbkt;
 	/* Generate keys by adding previous two keys, neglect overflow */
 	printf("Generating keys...\n");
 	keys[0] = 0;
@@ -287,7 +350,8 @@ generate_keys(void)
 		/* Check if primary bucket has space.*/
 		sig = rte_hash_hash(tbl_rwc_test_param.h,
 					tbl_rwc_test_param.keys+i);
-		prim_bucket_idx = sig & bucket_bitmask;
+		prim_bucket_idx = get_prim_bucket_index(tbl_rwc_test_param.h,
+							sig);
 		ret = check_bucket(prim_bucket_idx, keys[i]);
 		if (ret < 0) {
 			/*
@@ -368,6 +432,47 @@ generate_keys(void)
 	tbl_rwc_test_param.count_keys_absent = count_keys_absent;
 	tbl_rwc_test_param.count_keys_non_shift_path = count;
 
+	memset(scanned_bkts, 0, num_buckets);
+	count = 0;
+	/* Find keys that will be in extended buckets */
+	for (i = 0; i < count_keys_ks; i++) {
+		ret = rte_hash_add_key(tbl_rwc_test_param.h, keys_ks + i);
+		if (ret < 0) {
+			/* Key will be added to ext bkt */
+			keys_ext_bkt[count_keys_extbkt++] = keys_ks[i];
+			/* Sec bkt to be added to keys_ks_extbkt */
+			sig = rte_hash_hash(tbl_rwc_test_param.h,
+					tbl_rwc_test_param.keys_ks + i);
+			prim_bucket_idx = get_prim_bucket_index(
+						tbl_rwc_test_param.h, sig);
+			short_sig = get_short_sig(sig);
+			sec_bucket_idx = get_alt_bucket_index(
+						tbl_rwc_test_param.h,
+						prim_bucket_idx, short_sig);
+			if (scanned_bkts[sec_bucket_idx] == 0)
+				scanned_bkts[sec_bucket_idx] = 1;
+		}
+	}
+
+	/* Find keys that will shift keys in ext bucket*/
+	for (i = 0; i < num_buckets; i++) {
+		if (scanned_bkts[i] == 1) {
+			iter = i * 8;
+			while (rte_hash_iterate(tbl_rwc_test_param.h,
+				&next_key, &next_data, &iter) >= 0) {
+				/* Check if key belongs to the current bucket */
+				if (i >= (iter-1)/8)
+					keys_ks_extbkt[count++]
+						= *(const uint32_t *)next_key;
+				else
+					break;
+			}
+		}
+	}
+
+	tbl_rwc_test_param.count_keys_ks_extbkt = count;
+	tbl_rwc_test_param.count_keys_extbkt = count_keys_extbkt;
+
 	printf("\nCount of keys NOT causing shifting of existing keys to "
 	"alternate location: %d\n", tbl_rwc_test_param.count_keys_no_ks);
 	printf("\nCount of keys causing shifting of existing keys to alternate "
@@ -378,6 +483,10 @@ generate_keys(void)
 	       tbl_rwc_test_param.count_keys_shift_path);
 	printf("Count of keys not likely to be on the shift path: %d\n\n",
 	       tbl_rwc_test_param.count_keys_non_shift_path);
+	printf("Count of keys in extended buckets: %d\n\n",
+	       tbl_rwc_test_param.count_keys_extbkt);
+	printf("Count of keys shifting keys in ext buckets: %d\n\n",
+	       tbl_rwc_test_param.count_keys_ks_extbkt);
 
 	rte_free(found);
 	rte_hash_free(tbl_rwc_test_param.h);
@@ -390,12 +499,14 @@ generate_keys(void)
 	rte_free(keys_absent);
 	rte_free(found);
 	rte_free(tbl_rwc_test_param.keys_shift_path);
+	rte_free(keys_ext_bkt);
+	rte_free(keys_ks_extbkt);
 	rte_free(scanned_bkts);
 	return -1;
 }
 
 static int
-init_params(int rwc_lf, int use_jhash, int htm)
+init_params(int rwc_lf, int use_jhash, int htm, int ext_bkt)
 {
 	struct rte_hash *handle;
 
@@ -425,6 +536,9 @@ init_params(int rwc_lf, int use_jhash, int htm)
 			RTE_HASH_EXTRA_FLAGS_RW_CONCURRENCY |
 			RTE_HASH_EXTRA_FLAGS_MULTI_WRITER_ADD;
 
+	if (ext_bkt)
+		hash_params.extra_flag |= RTE_HASH_EXTRA_FLAGS_EXT_TABLE;
+
 	hash_params.name = "tests";
 
 	handle = rte_hash_create(&hash_params);
@@ -452,7 +566,7 @@ test_rwc_reader(__attribute__((unused)) void *arg)
 	void *temp_a[BULK_LOOKUP_SIZE];
 
 	/* Used to identify keys not inserted in the hash table */
-	pos = rte_zmalloc(NULL, sizeof(uint32_t) * BULK_LOOKUP_SIZE, 0);
+	pos = rte_malloc(NULL, sizeof(uint32_t) * BULK_LOOKUP_SIZE, 0);
 	if (pos == NULL) {
 		printf("RTE_MALLOC failed\n");
 		return -1;
@@ -467,6 +581,9 @@ test_rwc_reader(__attribute__((unused)) void *arg)
 	} else if (read_type & READ_PASS_SHIFT_PATH) {
 		keys = tbl_rwc_test_param.keys_shift_path;
 		read_cnt = tbl_rwc_test_param.count_keys_shift_path;
+	} else if (read_type & READ_PASS_KEY_SHIFTS_EXTBKT) {
+		keys = tbl_rwc_test_param.keys_ext_bkt;
+		read_cnt = tbl_rwc_test_param.count_keys_extbkt;
 	} else {
 		keys = tbl_rwc_test_param.keys_non_shift_path;
 		read_cnt = tbl_rwc_test_param.count_keys_non_shift_path;
@@ -482,7 +599,6 @@ test_rwc_reader(__attribute__((unused)) void *arg)
 				/* Array of  pointer to the list of keys */
 				for (j = 0; j < BULK_LOOKUP_SIZE; j++)
 					temp_a[j] = keys + i + j;
-
 				rte_hash_lookup_bulk(tbl_rwc_test_param.h,
 						   (const void **)
 						   ((uintptr_t)temp_a),
@@ -539,22 +655,25 @@ test_rwc_reader(__attribute__((unused)) void *arg)
 }
 
 static int
-write_keys(uint8_t key_shift)
+write_keys(uint8_t write_type)
 {
 	uint32_t i;
 	int ret;
 	uint32_t key_cnt;
 	uint32_t *keys;
-	if (key_shift) {
+	if (write_type == WRITE_KEY_SHIFT) {
 		key_cnt = tbl_rwc_test_param.count_keys_ks;
 		keys = tbl_rwc_test_param.keys_ks;
-	} else {
+	} else if (write_type == WRITE_NO_KEY_SHIFT) {
 		key_cnt = tbl_rwc_test_param.count_keys_no_ks;
 		keys = tbl_rwc_test_param.keys_no_ks;
+	} else if (write_type == WRITE_EXT_BKT) {
+		key_cnt = tbl_rwc_test_param.count_keys_extbkt;
+		keys = tbl_rwc_test_param.keys_ext_bkt;
 	}
 	for (i = 0; i < key_cnt; i++) {
 		ret = rte_hash_add_key(tbl_rwc_test_param.h, keys + i);
-		if (!key_shift && ret < 0) {
+		if ((write_type == WRITE_NO_KEY_SHIFT) && ret < 0) {
 			printf("writer failed %"PRIu32"\n", i);
 			return -1;
 		}
@@ -581,18 +700,18 @@ test_rwc_multi_writer(__attribute__((unused)) void *arg)
  */
 static int
 test_hash_add_no_ks_lookup_hit(struct rwc_perf *rwc_perf_results, int rwc_lf,
-				int htm)
+				int htm, int ext_bkt)
 {
 	unsigned int n, m;
 	uint64_t i;
 	int use_jhash = 0;
-	uint8_t key_shift = 0;
+	uint8_t write_type = WRITE_NO_KEY_SHIFT;
 	uint8_t read_type = READ_PASS_NO_KEY_SHIFTS;
 
 	rte_atomic64_init(&greads);
 	rte_atomic64_init(&gread_cycles);
 
-	if (init_params(rwc_lf, use_jhash, htm) != 0)
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
 		goto err;
 	printf("\nTest: Hash add - no key-shifts, read - hit\n");
 	for (m = 0; m < 2; m++) {
@@ -612,7 +731,7 @@ test_hash_add_no_ks_lookup_hit(struct rwc_perf *rwc_perf_results, int rwc_lf,
 
 			rte_hash_reset(tbl_rwc_test_param.h);
 			writer_done = 0;
-			if (write_keys(key_shift) < 0)
+			if (write_keys(write_type) < 0)
 				goto err;
 			writer_done = 1;
 			for (i = 1; i <= rwc_core_cnt[n]; i++)
@@ -650,19 +769,19 @@ test_hash_add_no_ks_lookup_hit(struct rwc_perf *rwc_perf_results, int rwc_lf,
  */
 static int
 test_hash_add_no_ks_lookup_miss(struct rwc_perf *rwc_perf_results, int rwc_lf,
-				int htm)
+				int htm, int ext_bkt)
 {
 	unsigned int n, m;
 	uint64_t i;
 	int use_jhash = 0;
-	uint8_t key_shift = 0;
+	uint8_t write_type = WRITE_NO_KEY_SHIFT;
 	uint8_t read_type = READ_FAIL;
 	int ret;
 
 	rte_atomic64_init(&greads);
 	rte_atomic64_init(&gread_cycles);
 
-	if (init_params(rwc_lf, use_jhash, htm) != 0)
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
 		goto err;
 	printf("\nTest: Hash add - no key-shifts, Hash lookup - miss\n");
 	for (m = 0; m < 2; m++) {
@@ -687,7 +806,7 @@ test_hash_add_no_ks_lookup_miss(struct rwc_perf *rwc_perf_results, int rwc_lf,
 				rte_eal_remote_launch(test_rwc_reader,
 						(void *)(uintptr_t)read_type,
 							enabled_core_ids[i]);
-			ret = write_keys(key_shift);
+			ret = write_keys(write_type);
 			writer_done = 1;
 			rte_eal_mp_wait_lcore();
 
@@ -722,19 +841,19 @@ test_hash_add_no_ks_lookup_miss(struct rwc_perf *rwc_perf_results, int rwc_lf,
  */
 static int
 test_hash_add_ks_lookup_hit_non_sp(struct rwc_perf *rwc_perf_results,
-				    int rwc_lf, int htm)
+				    int rwc_lf, int htm, int ext_bkt)
 {
 	unsigned int n, m;
 	uint64_t i;
 	int use_jhash = 0;
 	int ret;
-	uint8_t key_shift;
+	uint8_t write_type;
 	uint8_t read_type = READ_PASS_NON_SHIFT_PATH;
 
 	rte_atomic64_init(&greads);
 	rte_atomic64_init(&gread_cycles);
 
-	if (init_params(rwc_lf, use_jhash, htm) != 0)
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
 		goto err;
 	printf("\nTest: Hash add - key shift, Hash lookup - hit"
 	       " (non-shift-path)\n");
@@ -755,15 +874,15 @@ test_hash_add_ks_lookup_hit_non_sp(struct rwc_perf *rwc_perf_results,
 
 			rte_hash_reset(tbl_rwc_test_param.h);
 			writer_done = 0;
-			key_shift = 0;
-			if (write_keys(key_shift) < 0)
+			write_type = WRITE_NO_KEY_SHIFT;
+			if (write_keys(write_type) < 0)
 				goto err;
 			for (i = 1; i <= rwc_core_cnt[n]; i++)
 				rte_eal_remote_launch(test_rwc_reader,
 						(void *)(uintptr_t)read_type,
 							enabled_core_ids[i]);
-			key_shift = 1;
-			ret = write_keys(key_shift);
+			write_type = WRITE_KEY_SHIFT;
+			ret = write_keys(write_type);
 			writer_done = 1;
 			rte_eal_mp_wait_lcore();
 
@@ -798,19 +917,19 @@ test_hash_add_ks_lookup_hit_non_sp(struct rwc_perf *rwc_perf_results,
  */
 static int
 test_hash_add_ks_lookup_hit_sp(struct rwc_perf *rwc_perf_results, int rwc_lf,
-				int htm)
+				int htm, int ext_bkt)
 {
 	unsigned int n, m;
 	uint64_t i;
 	int use_jhash = 0;
 	int ret;
-	uint8_t key_shift;
+	uint8_t write_type;
 	uint8_t read_type = READ_PASS_SHIFT_PATH;
 
 	rte_atomic64_init(&greads);
 	rte_atomic64_init(&gread_cycles);
 
-	if (init_params(rwc_lf, use_jhash, htm) != 0)
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
 		goto err;
 	printf("\nTest: Hash add - key shift, Hash lookup - hit (shift-path)"
 	       "\n");
@@ -831,15 +950,15 @@ test_hash_add_ks_lookup_hit_sp(struct rwc_perf *rwc_perf_results, int rwc_lf,
 
 			rte_hash_reset(tbl_rwc_test_param.h);
 			writer_done = 0;
-			key_shift = 0;
-			if (write_keys(key_shift) < 0)
+			write_type = WRITE_NO_KEY_SHIFT;
+			if (write_keys(write_type) < 0)
 				goto err;
 			for (i = 1; i <= rwc_core_cnt[n]; i++)
 				rte_eal_remote_launch(test_rwc_reader,
 						(void *)(uintptr_t)read_type,
 						enabled_core_ids[i]);
-			key_shift = 1;
-			ret = write_keys(key_shift);
+			write_type = WRITE_KEY_SHIFT;
+			ret = write_keys(write_type);
 			writer_done = 1;
 			rte_eal_mp_wait_lcore();
 
@@ -874,19 +993,19 @@ test_hash_add_ks_lookup_hit_sp(struct rwc_perf *rwc_perf_results, int rwc_lf,
  */
 static int
 test_hash_add_ks_lookup_miss(struct rwc_perf *rwc_perf_results, int rwc_lf, int
-			     htm)
+			     htm, int ext_bkt)
 {
 	unsigned int n, m;
 	uint64_t i;
 	int use_jhash = 0;
 	int ret;
-	uint8_t key_shift;
+	uint8_t write_type;
 	uint8_t read_type = READ_FAIL;
 
 	rte_atomic64_init(&greads);
 	rte_atomic64_init(&gread_cycles);
 
-	if (init_params(rwc_lf, use_jhash, htm) != 0)
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
 		goto err;
 	printf("\nTest: Hash add - key shift, Hash lookup - miss\n");
 	for (m = 0; m < 2; m++) {
@@ -906,15 +1025,15 @@ test_hash_add_ks_lookup_miss(struct rwc_perf *rwc_perf_results, int rwc_lf, int
 
 			rte_hash_reset(tbl_rwc_test_param.h);
 			writer_done = 0;
-			key_shift = 0;
-			if (write_keys(key_shift) < 0)
+			write_type = WRITE_NO_KEY_SHIFT;
+			if (write_keys(write_type) < 0)
 				goto err;
 			for (i = 1; i <= rwc_core_cnt[n]; i++)
 				rte_eal_remote_launch(test_rwc_reader,
 						(void *)(uintptr_t)read_type,
 							enabled_core_ids[i]);
-			key_shift = 1;
-			ret = write_keys(key_shift);
+			write_type = WRITE_KEY_SHIFT;
+			ret = write_keys(write_type);
 			writer_done = 1;
 			rte_eal_mp_wait_lcore();
 
@@ -949,18 +1068,18 @@ test_hash_add_ks_lookup_miss(struct rwc_perf *rwc_perf_results, int rwc_lf, int
  */
 static int
 test_hash_multi_add_lookup(struct rwc_perf *rwc_perf_results, int rwc_lf,
-			   int htm)
+			   int htm, int ext_bkt)
 {
 	unsigned int n, m, k;
 	uint64_t i;
 	int use_jhash = 0;
-	uint8_t key_shift;
+	uint8_t write_type;
 	uint8_t read_type = READ_PASS_SHIFT_PATH;
 
 	rte_atomic64_init(&greads);
 	rte_atomic64_init(&gread_cycles);
 
-	if (init_params(rwc_lf, use_jhash, htm) != 0)
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
 		goto err;
 	printf("\nTest: Multi-add-lookup\n");
 	uint8_t pos_core;
@@ -991,8 +1110,8 @@ test_hash_multi_add_lookup(struct rwc_perf *rwc_perf_results, int rwc_lf,
 				writer_done = 0;
 				for (i = 0; i < 4; i++)
 					multi_writer_done[i] = 0;
-				key_shift = 0;
-				if (write_keys(key_shift) < 0)
+				write_type = WRITE_NO_KEY_SHIFT;
+				if (write_keys(write_type) < 0)
 					goto err;
 
 				/* Launch reader(s) */
@@ -1000,7 +1119,7 @@ test_hash_multi_add_lookup(struct rwc_perf *rwc_perf_results, int rwc_lf,
 					rte_eal_remote_launch(test_rwc_reader,
 						(void *)(uintptr_t)read_type,
 						enabled_core_ids[i]);
-				key_shift = 1;
+				write_type = WRITE_KEY_SHIFT;
 				pos_core = 0;
 
 				/* Launch writers */
@@ -1045,6 +1164,88 @@ test_hash_multi_add_lookup(struct rwc_perf *rwc_perf_results, int rwc_lf,
 	return -1;
 }
 
+/*
+ * Test lookup perf:
+ * Reader(s) lookup keys present in the extendable bkt.
+ */
+static int
+test_hash_add_ks_lookup_hit_extbkt(struct rwc_perf *rwc_perf_results,
+				int rwc_lf, int htm, int ext_bkt)
+{
+	unsigned int n, m;
+	uint64_t i;
+	int use_jhash = 0;
+	uint8_t write_type;
+	uint8_t read_type = READ_PASS_KEY_SHIFTS_EXTBKT;
+
+	rte_atomic64_init(&greads);
+	rte_atomic64_init(&gread_cycles);
+
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
+		goto err;
+	printf("\nTest: Hash add - key-shifts, read - hit (ext_bkt)\n");
+	for (m = 0; m < 2; m++) {
+		if (m == 1) {
+			printf("\n** With bulk-lookup **\n");
+			read_type |= BULK_LOOKUP;
+		}
+		for (n = 0; n < NUM_TEST; n++) {
+			unsigned int tot_lcore = rte_lcore_count();
+			if (tot_lcore < rwc_core_cnt[n] + 1)
+				goto finish;
+
+			printf("\nNumber of readers: %u\n", rwc_core_cnt[n]);
+
+			rte_atomic64_clear(&greads);
+			rte_atomic64_clear(&gread_cycles);
+
+			rte_hash_reset(tbl_rwc_test_param.h);
+			write_type = WRITE_NO_KEY_SHIFT;
+			if (write_keys(write_type) < 0)
+				goto err;
+			write_type = WRITE_KEY_SHIFT;
+			if (write_keys(write_type) < 0)
+				goto err;
+			writer_done = 0;
+			for (i = 1; i <= rwc_core_cnt[n]; i++)
+				rte_eal_remote_launch(test_rwc_reader,
+						(void *)(uintptr_t)read_type,
+							enabled_core_ids[i]);
+			for (i = 0; i < tbl_rwc_test_param.count_keys_ks_extbkt;
+			     i++) {
+				if (rte_hash_del_key(tbl_rwc_test_param.h,
+					tbl_rwc_test_param.keys_ks_extbkt + i)
+							< 0) {
+					printf("Delete Failed: %u\n",
+					tbl_rwc_test_param.keys_ks_extbkt[i]);
+					goto err;
+				}
+			}
+			writer_done = 1;
+			rte_eal_mp_wait_lcore();
+
+			for (i = 1; i <= rwc_core_cnt[n]; i++)
+				if (lcore_config[i].ret < 0)
+					goto err;
+
+			unsigned long long cycles_per_lookup =
+				rte_atomic64_read(&gread_cycles) /
+				rte_atomic64_read(&greads);
+			rwc_perf_results->w_ks_r_hit_extbkt[m][n]
+						= cycles_per_lookup;
+			printf("Cycles per lookup: %llu\n", cycles_per_lookup);
+		}
+	}
+
+finish:
+	rte_hash_free(tbl_rwc_test_param.h);
+	return 0;
+
+err:
+	rte_hash_free(tbl_rwc_test_param.h);
+	return -1;
+}
+
 static int
 test_hash_readwrite_lf_main(void)
 {
@@ -1057,6 +1258,7 @@ test_hash_readwrite_lf_main(void)
 	int rwc_lf = 0;
 	int htm;
 	int use_jhash = 0;
+	int ext_bkt = 0;
 	if (rte_lcore_count() == 1) {
 		printf("More than one lcore is required "
 			"to do read write lock-free concurrency test\n");
@@ -1070,7 +1272,7 @@ test_hash_readwrite_lf_main(void)
 	else
 		htm = 0;
 
-	if (init_params(rwc_lf, use_jhash, htm) != 0)
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
 		return -1;
 	if (generate_keys() != 0)
 		return -1;
@@ -1079,25 +1281,29 @@ test_hash_readwrite_lf_main(void)
 
 	if (RTE_HASH_EXTRA_FLAGS_RW_CONCURRENCY_LF) {
 		rwc_lf = 1;
+		ext_bkt = 1;
 		printf("Test lookup with read-write concurrency lock free support"
 		       " enabled\n");
 		if (test_hash_add_no_ks_lookup_hit(&rwc_lf_results, rwc_lf,
-							htm) < 0)
+							htm, ext_bkt) < 0)
 			return -1;
 		if (test_hash_add_no_ks_lookup_miss(&rwc_lf_results, rwc_lf,
-							htm) < 0)
+							htm, ext_bkt) < 0)
 			return -1;
 		if (test_hash_add_ks_lookup_hit_non_sp(&rwc_lf_results, rwc_lf,
-							htm) < 0)
+							htm, ext_bkt) < 0)
 			return -1;
 		if (test_hash_add_ks_lookup_hit_sp(&rwc_lf_results, rwc_lf,
-							htm) < 0)
+							htm, ext_bkt) < 0)
 			return -1;
-		if (test_hash_add_ks_lookup_miss(&rwc_lf_results, rwc_lf, htm)
-							< 0)
+		if (test_hash_add_ks_lookup_miss(&rwc_lf_results, rwc_lf, htm,
+						 ext_bkt) < 0)
 			return -1;
-		if (test_hash_multi_add_lookup(&rwc_lf_results, rwc_lf, htm)
-							< 0)
+		if (test_hash_multi_add_lookup(&rwc_lf_results, rwc_lf, htm,
+					       ext_bkt) < 0)
+			return -1;
+		if (test_hash_add_ks_lookup_hit_extbkt(&rwc_lf_results, rwc_lf,
+							htm, ext_bkt) < 0)
 			return -1;
 	}
 	printf("\nTest lookup with read-write concurrency lock free support"
@@ -1112,21 +1318,26 @@ test_hash_readwrite_lf_main(void)
 		}
 	} else
 		printf("With HTM Enabled\n");
-	if (test_hash_add_no_ks_lookup_hit(&rwc_non_lf_results, rwc_lf, htm)
-						< 0)
+	if (test_hash_add_no_ks_lookup_hit(&rwc_non_lf_results, rwc_lf, htm,
+					   ext_bkt) < 0)
 		return -1;
-	if (test_hash_add_no_ks_lookup_miss(&rwc_non_lf_results, rwc_lf, htm)
-						< 0)
+	if (test_hash_add_no_ks_lookup_miss(&rwc_non_lf_results, rwc_lf, htm,
+						ext_bkt) < 0)
 		return -1;
 	if (test_hash_add_ks_lookup_hit_non_sp(&rwc_non_lf_results, rwc_lf,
-						htm) < 0)
+						htm, ext_bkt) < 0)
+		return -1;
+	if (test_hash_add_ks_lookup_hit_sp(&rwc_non_lf_results, rwc_lf, htm,
+						ext_bkt) < 0)
 		return -1;
-	if (test_hash_add_ks_lookup_hit_sp(&rwc_non_lf_results, rwc_lf, htm)
-						< 0)
+	if (test_hash_add_ks_lookup_miss(&rwc_non_lf_results, rwc_lf, htm,
+					 ext_bkt) < 0)
 		return -1;
-	if (test_hash_add_ks_lookup_miss(&rwc_non_lf_results, rwc_lf, htm) < 0)
+	if (test_hash_multi_add_lookup(&rwc_non_lf_results, rwc_lf, htm,
+							ext_bkt) < 0)
 		return -1;
-	if (test_hash_multi_add_lookup(&rwc_non_lf_results, rwc_lf, htm) < 0)
+	if (test_hash_add_ks_lookup_hit_extbkt(&rwc_non_lf_results, rwc_lf,
+						htm, ext_bkt) < 0)
 		return -1;
 results:
 	printf("\n\t\t\t\t\t\t********** Results summary **********\n\n");
@@ -1158,8 +1369,11 @@ test_hash_readwrite_lf_main(void)
 			       "(shift-path)\t\t%u\n\t\t\t\t\t\t\t\t",
 			       rwc_lf_results.w_ks_r_hit_sp[j][i]);
 			printf("Hash add - key-shifts, Hash lookup miss\t\t\t\t"
-				"%u\n\n\t\t\t\t",
+				"%u\n\t\t\t\t\t\t\t\t",
 				rwc_lf_results.w_ks_r_miss[j][i]);
+			printf("Hash add - key-shifts, Hash lookup hit (ext_bkt)\t\t"
+				"%u\n\n\t\t\t\t",
+				rwc_lf_results.w_ks_r_hit_extbkt[j][i]);
 
 			printf("Disabled\t");
 			if (htm)
@@ -1179,7 +1393,11 @@ test_hash_readwrite_lf_main(void)
 			       "(shift-path)\t\t%u\n\t\t\t\t\t\t\t\t",
 			       rwc_non_lf_results.w_ks_r_hit_sp[j][i]);
 			printf("Hash add - key-shifts, Hash lookup miss\t\t\t\t"
-			       "%u\n", rwc_non_lf_results.w_ks_r_miss[j][i]);
+			       "%u\n\t\t\t\t\t\t\t\t",
+			       rwc_non_lf_results.w_ks_r_miss[j][i]);
+			printf("Hash add - key-shifts, Hash lookup hit (ext_bkt)\t\t"
+				"%u\n",
+				rwc_non_lf_results.w_ks_r_hit_extbkt[j][i]);
 
 			printf("_______\t\t_______\t\t_________\t___\t\t"
 			       "_________\t\t\t\t\t\t_________________\n");
-- 
2.17.1

[dpdk-dev] [PATCH 2/2] test/hash: lock-free rw concurrency test ext bkt

[Dharmik Thakkar]

Add unit test to check for hash lookup and bulk-lookup perf.
Test with lock-free enabled and with lock-free disabled.

Test include:

- hash lookup on keys in ext bkt,
hash delete causing key-shifts of keys from ext bkt to secondary bkt

Suggested-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
Signed-off-by: Dharmik Thakkar <dharmik.thakkar@arm.com>
---
 app/test/test_hash_readwrite_lf.c | 350 ++++++++++++++++++++++++------
 1 file changed, 284 insertions(+), 66 deletions(-)

diff --git a/app/test/test_hash_readwrite_lf.c b/app/test/test_hash_readwrite_lf.c
index cbfd9322696b..ddd8d7aa6a7d 100644
--- a/app/test/test_hash_readwrite_lf.c
+++ b/app/test/test_hash_readwrite_lf.c
@@ -41,6 +41,12 @@
 #define READ_PASS_SHIFT_PATH 4
 #define READ_PASS_NON_SHIFT_PATH 8
 #define BULK_LOOKUP 16
+#define READ_PASS_KEY_SHIFTS_EXTBKT 32
+
+#define WRITE_NO_KEY_SHIFT 0
+#define WRITE_KEY_SHIFT 1
+#define WRITE_EXT_BKT 2
+
 #define NUM_TEST 3
 unsigned int rwc_core_cnt[NUM_TEST] = {1, 2, 4};
 
@@ -51,6 +57,7 @@ struct rwc_perf {
 	uint32_t w_ks_r_hit_sp[2][NUM_TEST];
 	uint32_t w_ks_r_miss[2][NUM_TEST];
 	uint32_t multi_rw[NUM_TEST - 1][2][NUM_TEST];
+	uint32_t w_ks_r_hit_extbkt[2][NUM_TEST];
 };
 
 static struct rwc_perf rwc_lf_results, rwc_non_lf_results;
@@ -62,11 +69,15 @@ struct {
 	uint32_t *keys_absent;
 	uint32_t *keys_shift_path;
 	uint32_t *keys_non_shift_path;
+	uint32_t *keys_ext_bkt;
+	uint32_t *keys_ks_extbkt;
 	uint32_t count_keys_no_ks;
 	uint32_t count_keys_ks;
 	uint32_t count_keys_absent;
 	uint32_t count_keys_shift_path;
 	uint32_t count_keys_non_shift_path;
+	uint32_t count_keys_extbkt;
+	uint32_t count_keys_ks_extbkt;
 	uint32_t single_insert;
 	struct rte_hash *h;
 } tbl_rwc_test_param;
@@ -81,6 +92,35 @@ uint16_t enabled_core_ids[RTE_MAX_LCORE];
 
 uint8_t *scanned_bkts;
 
+static inline uint16_t
+get_short_sig(const hash_sig_t hash)
+{
+	return hash >> 16;
+}
+
+static inline uint32_t
+get_prim_bucket_index(__attribute__((unused)) const struct rte_hash *h,
+		      const hash_sig_t hash)
+{
+	uint32_t num_buckets;
+	uint32_t bucket_bitmask;
+	num_buckets  = rte_align32pow2(TOTAL_ENTRY) / 8;
+	bucket_bitmask = num_buckets - 1;
+	return hash & bucket_bitmask;
+}
+
+static inline uint32_t
+get_alt_bucket_index(__attribute__((unused)) const struct rte_hash *h,
+			uint32_t cur_bkt_idx, uint16_t sig)
+{
+	uint32_t num_buckets;
+	uint32_t bucket_bitmask;
+	num_buckets  = rte_align32pow2(TOTAL_ENTRY) / 8;
+	bucket_bitmask = num_buckets - 1;
+	return (cur_bkt_idx ^ sig) & bucket_bitmask;
+}
+
+
 static inline int
 get_enabled_cores_list(void)
 {
@@ -168,9 +208,12 @@ generate_keys(void)
 	uint32_t *keys_ks = NULL;
 	uint32_t *keys_absent = NULL;
 	uint32_t *keys_non_shift_path = NULL;
+	uint32_t *keys_ext_bkt = NULL;
+	uint32_t *keys_ks_extbkt = NULL;
 	uint32_t *found = NULL;
 	uint32_t count_keys_no_ks = 0;
 	uint32_t count_keys_ks = 0;
+	uint32_t count_keys_extbkt = 0;
 	uint32_t i;
 
 	/*
@@ -251,14 +294,32 @@ generate_keys(void)
 		goto err;
 	}
 
+	/*
+	 * This consist of keys which will be stored in extended buckets
+	 */
+	keys_ext_bkt = rte_malloc(NULL, sizeof(uint32_t) * TOTAL_INSERT, 0);
+	if (keys_ext_bkt == NULL) {
+		printf("RTE_MALLOC failed\n");
+		goto err;
+	}
+
+	/*
+	 * This consist of keys which when deleted causes shifting of keys
+	 * in extended buckets to respective secondary buckets
+	 */
+	keys_ks_extbkt = rte_malloc(NULL, sizeof(uint32_t) * TOTAL_INSERT, 0);
+	if (keys_ks_extbkt == NULL) {
+		printf("RTE_MALLOC failed\n");
+		goto err;
+	}
 
 	hash_sig_t sig;
 	uint32_t prim_bucket_idx;
-	int ret;
+	uint32_t sec_bucket_idx;
+	uint16_t short_sig;
 	uint32_t num_buckets;
-	uint32_t bucket_bitmask;
 	num_buckets  = rte_align32pow2(TOTAL_ENTRY) / 8;
-	bucket_bitmask = num_buckets - 1;
+	int ret;
 
 	/*
 	 * Used to mark bkts in which at least one key was shifted to its
@@ -275,6 +336,8 @@ generate_keys(void)
 	tbl_rwc_test_param.keys_ks = keys_ks;
 	tbl_rwc_test_param.keys_absent = keys_absent;
 	tbl_rwc_test_param.keys_non_shift_path = keys_non_shift_path;
+	tbl_rwc_test_param.keys_ext_bkt = keys_ext_bkt;
+	tbl_rwc_test_param.keys_ks_extbkt = keys_ks_extbkt;
 	/* Generate keys by adding previous two keys, neglect overflow */
 	printf("Generating keys...\n");
 	keys[0] = 0;
@@ -287,7 +350,8 @@ generate_keys(void)
 		/* Check if primary bucket has space.*/
 		sig = rte_hash_hash(tbl_rwc_test_param.h,
 					tbl_rwc_test_param.keys+i);
-		prim_bucket_idx = sig & bucket_bitmask;
+		prim_bucket_idx = get_prim_bucket_index(tbl_rwc_test_param.h,
+							sig);
 		ret = check_bucket(prim_bucket_idx, keys[i]);
 		if (ret < 0) {
 			/*
@@ -368,6 +432,47 @@ generate_keys(void)
 	tbl_rwc_test_param.count_keys_absent = count_keys_absent;
 	tbl_rwc_test_param.count_keys_non_shift_path = count;
 
+	memset(scanned_bkts, 0, num_buckets);
+	count = 0;
+	/* Find keys that will be in extended buckets */
+	for (i = 0; i < count_keys_ks; i++) {
+		ret = rte_hash_add_key(tbl_rwc_test_param.h, keys_ks + i);
+		if (ret < 0) {
+			/* Key will be added to ext bkt */
+			keys_ext_bkt[count_keys_extbkt++] = keys_ks[i];
+			/* Sec bkt to be added to keys_ks_extbkt */
+			sig = rte_hash_hash(tbl_rwc_test_param.h,
+					tbl_rwc_test_param.keys_ks + i);
+			prim_bucket_idx = get_prim_bucket_index(
+						tbl_rwc_test_param.h, sig);
+			short_sig = get_short_sig(sig);
+			sec_bucket_idx = get_alt_bucket_index(
+						tbl_rwc_test_param.h,
+						prim_bucket_idx, short_sig);
+			if (scanned_bkts[sec_bucket_idx] == 0)
+				scanned_bkts[sec_bucket_idx] = 1;
+		}
+	}
+
+	/* Find keys that will shift keys in ext bucket*/
+	for (i = 0; i < num_buckets; i++) {
+		if (scanned_bkts[i] == 1) {
+			iter = i * 8;
+			while (rte_hash_iterate(tbl_rwc_test_param.h,
+				&next_key, &next_data, &iter) >= 0) {
+				/* Check if key belongs to the current bucket */
+				if (i >= (iter-1)/8)
+					keys_ks_extbkt[count++]
+						= *(const uint32_t *)next_key;
+				else
+					break;
+			}
+		}
+	}
+
+	tbl_rwc_test_param.count_keys_ks_extbkt = count;
+	tbl_rwc_test_param.count_keys_extbkt = count_keys_extbkt;
+
 	printf("\nCount of keys NOT causing shifting of existing keys to "
 	"alternate location: %d\n", tbl_rwc_test_param.count_keys_no_ks);
 	printf("\nCount of keys causing shifting of existing keys to alternate "
@@ -378,6 +483,10 @@ generate_keys(void)
 	       tbl_rwc_test_param.count_keys_shift_path);
 	printf("Count of keys not likely to be on the shift path: %d\n\n",
 	       tbl_rwc_test_param.count_keys_non_shift_path);
+	printf("Count of keys in extended buckets: %d\n\n",
+	       tbl_rwc_test_param.count_keys_extbkt);
+	printf("Count of keys shifting keys in ext buckets: %d\n\n",
+	       tbl_rwc_test_param.count_keys_ks_extbkt);
 
 	rte_free(found);
 	rte_hash_free(tbl_rwc_test_param.h);
@@ -390,12 +499,14 @@ generate_keys(void)
 	rte_free(keys_absent);
 	rte_free(found);
 	rte_free(tbl_rwc_test_param.keys_shift_path);
+	rte_free(keys_ext_bkt);
+	rte_free(keys_ks_extbkt);
 	rte_free(scanned_bkts);
 	return -1;
 }
 
 static int
-init_params(int rwc_lf, int use_jhash, int htm)
+init_params(int rwc_lf, int use_jhash, int htm, int ext_bkt)
 {
 	struct rte_hash *handle;
 
@@ -425,6 +536,9 @@ init_params(int rwc_lf, int use_jhash, int htm)
 			RTE_HASH_EXTRA_FLAGS_RW_CONCURRENCY |
 			RTE_HASH_EXTRA_FLAGS_MULTI_WRITER_ADD;
 
+	if (ext_bkt)
+		hash_params.extra_flag |= RTE_HASH_EXTRA_FLAGS_EXT_TABLE;
+
 	hash_params.name = "tests";
 
 	handle = rte_hash_create(&hash_params);
@@ -452,7 +566,7 @@ test_rwc_reader(__attribute__((unused)) void *arg)
 	void *temp_a[BULK_LOOKUP_SIZE];
 
 	/* Used to identify keys not inserted in the hash table */
-	pos = rte_zmalloc(NULL, sizeof(uint32_t) * BULK_LOOKUP_SIZE, 0);
+	pos = rte_malloc(NULL, sizeof(uint32_t) * BULK_LOOKUP_SIZE, 0);
 	if (pos == NULL) {
 		printf("RTE_MALLOC failed\n");
 		return -1;
@@ -467,6 +581,9 @@ test_rwc_reader(__attribute__((unused)) void *arg)
 	} else if (read_type & READ_PASS_SHIFT_PATH) {
 		keys = tbl_rwc_test_param.keys_shift_path;
 		read_cnt = tbl_rwc_test_param.count_keys_shift_path;
+	} else if (read_type & READ_PASS_KEY_SHIFTS_EXTBKT) {
+		keys = tbl_rwc_test_param.keys_ext_bkt;
+		read_cnt = tbl_rwc_test_param.count_keys_extbkt;
 	} else {
 		keys = tbl_rwc_test_param.keys_non_shift_path;
 		read_cnt = tbl_rwc_test_param.count_keys_non_shift_path;
@@ -482,7 +599,6 @@ test_rwc_reader(__attribute__((unused)) void *arg)
 				/* Array of  pointer to the list of keys */
 				for (j = 0; j < BULK_LOOKUP_SIZE; j++)
 					temp_a[j] = keys + i + j;
-
 				rte_hash_lookup_bulk(tbl_rwc_test_param.h,
 						   (const void **)
 						   ((uintptr_t)temp_a),
@@ -539,22 +655,25 @@ test_rwc_reader(__attribute__((unused)) void *arg)
 }
 
 static int
-write_keys(uint8_t key_shift)
+write_keys(uint8_t write_type)
 {
 	uint32_t i;
 	int ret;
 	uint32_t key_cnt;
 	uint32_t *keys;
-	if (key_shift) {
+	if (write_type == WRITE_KEY_SHIFT) {
 		key_cnt = tbl_rwc_test_param.count_keys_ks;
 		keys = tbl_rwc_test_param.keys_ks;
-	} else {
+	} else if (write_type == WRITE_NO_KEY_SHIFT) {
 		key_cnt = tbl_rwc_test_param.count_keys_no_ks;
 		keys = tbl_rwc_test_param.keys_no_ks;
+	} else if (write_type == WRITE_EXT_BKT) {
+		key_cnt = tbl_rwc_test_param.count_keys_extbkt;
+		keys = tbl_rwc_test_param.keys_ext_bkt;
 	}
 	for (i = 0; i < key_cnt; i++) {
 		ret = rte_hash_add_key(tbl_rwc_test_param.h, keys + i);
-		if (!key_shift && ret < 0) {
+		if ((write_type == WRITE_NO_KEY_SHIFT) && ret < 0) {
 			printf("writer failed %"PRIu32"\n", i);
 			return -1;
 		}
@@ -581,18 +700,18 @@ test_rwc_multi_writer(__attribute__((unused)) void *arg)
  */
 static int
 test_hash_add_no_ks_lookup_hit(struct rwc_perf *rwc_perf_results, int rwc_lf,
-				int htm)
+				int htm, int ext_bkt)
 {
 	unsigned int n, m;
 	uint64_t i;
 	int use_jhash = 0;
-	uint8_t key_shift = 0;
+	uint8_t write_type = WRITE_NO_KEY_SHIFT;
 	uint8_t read_type = READ_PASS_NO_KEY_SHIFTS;
 
 	rte_atomic64_init(&greads);
 	rte_atomic64_init(&gread_cycles);
 
-	if (init_params(rwc_lf, use_jhash, htm) != 0)
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
 		goto err;
 	printf("\nTest: Hash add - no key-shifts, read - hit\n");
 	for (m = 0; m < 2; m++) {
@@ -612,7 +731,7 @@ test_hash_add_no_ks_lookup_hit(struct rwc_perf *rwc_perf_results, int rwc_lf,
 
 			rte_hash_reset(tbl_rwc_test_param.h);
 			writer_done = 0;
-			if (write_keys(key_shift) < 0)
+			if (write_keys(write_type) < 0)
 				goto err;
 			writer_done = 1;
 			for (i = 1; i <= rwc_core_cnt[n]; i++)
@@ -650,19 +769,19 @@ test_hash_add_no_ks_lookup_hit(struct rwc_perf *rwc_perf_results, int rwc_lf,
  */
 static int
 test_hash_add_no_ks_lookup_miss(struct rwc_perf *rwc_perf_results, int rwc_lf,
-				int htm)
+				int htm, int ext_bkt)
 {
 	unsigned int n, m;
 	uint64_t i;
 	int use_jhash = 0;
-	uint8_t key_shift = 0;
+	uint8_t write_type = WRITE_NO_KEY_SHIFT;
 	uint8_t read_type = READ_FAIL;
 	int ret;
 
 	rte_atomic64_init(&greads);
 	rte_atomic64_init(&gread_cycles);
 
-	if (init_params(rwc_lf, use_jhash, htm) != 0)
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
 		goto err;
 	printf("\nTest: Hash add - no key-shifts, Hash lookup - miss\n");
 	for (m = 0; m < 2; m++) {
@@ -687,7 +806,7 @@ test_hash_add_no_ks_lookup_miss(struct rwc_perf *rwc_perf_results, int rwc_lf,
 				rte_eal_remote_launch(test_rwc_reader,
 						(void *)(uintptr_t)read_type,
 							enabled_core_ids[i]);
-			ret = write_keys(key_shift);
+			ret = write_keys(write_type);
 			writer_done = 1;
 			rte_eal_mp_wait_lcore();
 
@@ -722,19 +841,19 @@ test_hash_add_no_ks_lookup_miss(struct rwc_perf *rwc_perf_results, int rwc_lf,
  */
 static int
 test_hash_add_ks_lookup_hit_non_sp(struct rwc_perf *rwc_perf_results,
-				    int rwc_lf, int htm)
+				    int rwc_lf, int htm, int ext_bkt)
 {
 	unsigned int n, m;
 	uint64_t i;
 	int use_jhash = 0;
 	int ret;
-	uint8_t key_shift;
+	uint8_t write_type;
 	uint8_t read_type = READ_PASS_NON_SHIFT_PATH;
 
 	rte_atomic64_init(&greads);
 	rte_atomic64_init(&gread_cycles);
 
-	if (init_params(rwc_lf, use_jhash, htm) != 0)
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
 		goto err;
 	printf("\nTest: Hash add - key shift, Hash lookup - hit"
 	       " (non-shift-path)\n");
@@ -755,15 +874,15 @@ test_hash_add_ks_lookup_hit_non_sp(struct rwc_perf *rwc_perf_results,
 
 			rte_hash_reset(tbl_rwc_test_param.h);
 			writer_done = 0;
-			key_shift = 0;
-			if (write_keys(key_shift) < 0)
+			write_type = WRITE_NO_KEY_SHIFT;
+			if (write_keys(write_type) < 0)
 				goto err;
 			for (i = 1; i <= rwc_core_cnt[n]; i++)
 				rte_eal_remote_launch(test_rwc_reader,
 						(void *)(uintptr_t)read_type,
 							enabled_core_ids[i]);
-			key_shift = 1;
-			ret = write_keys(key_shift);
+			write_type = WRITE_KEY_SHIFT;
+			ret = write_keys(write_type);
 			writer_done = 1;
 			rte_eal_mp_wait_lcore();
 
@@ -798,19 +917,19 @@ test_hash_add_ks_lookup_hit_non_sp(struct rwc_perf *rwc_perf_results,
  */
 static int
 test_hash_add_ks_lookup_hit_sp(struct rwc_perf *rwc_perf_results, int rwc_lf,
-				int htm)
+				int htm, int ext_bkt)
 {
 	unsigned int n, m;
 	uint64_t i;
 	int use_jhash = 0;
 	int ret;
-	uint8_t key_shift;
+	uint8_t write_type;
 	uint8_t read_type = READ_PASS_SHIFT_PATH;
 
 	rte_atomic64_init(&greads);
 	rte_atomic64_init(&gread_cycles);
 
-	if (init_params(rwc_lf, use_jhash, htm) != 0)
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
 		goto err;
 	printf("\nTest: Hash add - key shift, Hash lookup - hit (shift-path)"
 	       "\n");
@@ -831,15 +950,15 @@ test_hash_add_ks_lookup_hit_sp(struct rwc_perf *rwc_perf_results, int rwc_lf,
 
 			rte_hash_reset(tbl_rwc_test_param.h);
 			writer_done = 0;
-			key_shift = 0;
-			if (write_keys(key_shift) < 0)
+			write_type = WRITE_NO_KEY_SHIFT;
+			if (write_keys(write_type) < 0)
 				goto err;
 			for (i = 1; i <= rwc_core_cnt[n]; i++)
 				rte_eal_remote_launch(test_rwc_reader,
 						(void *)(uintptr_t)read_type,
 						enabled_core_ids[i]);
-			key_shift = 1;
-			ret = write_keys(key_shift);
+			write_type = WRITE_KEY_SHIFT;
+			ret = write_keys(write_type);
 			writer_done = 1;
 			rte_eal_mp_wait_lcore();
 
@@ -874,19 +993,19 @@ test_hash_add_ks_lookup_hit_sp(struct rwc_perf *rwc_perf_results, int rwc_lf,
  */
 static int
 test_hash_add_ks_lookup_miss(struct rwc_perf *rwc_perf_results, int rwc_lf, int
-			     htm)
+			     htm, int ext_bkt)
 {
 	unsigned int n, m;
 	uint64_t i;
 	int use_jhash = 0;
 	int ret;
-	uint8_t key_shift;
+	uint8_t write_type;
 	uint8_t read_type = READ_FAIL;
 
 	rte_atomic64_init(&greads);
 	rte_atomic64_init(&gread_cycles);
 
-	if (init_params(rwc_lf, use_jhash, htm) != 0)
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
 		goto err;
 	printf("\nTest: Hash add - key shift, Hash lookup - miss\n");
 	for (m = 0; m < 2; m++) {
@@ -906,15 +1025,15 @@ test_hash_add_ks_lookup_miss(struct rwc_perf *rwc_perf_results, int rwc_lf, int
 
 			rte_hash_reset(tbl_rwc_test_param.h);
 			writer_done = 0;
-			key_shift = 0;
-			if (write_keys(key_shift) < 0)
+			write_type = WRITE_NO_KEY_SHIFT;
+			if (write_keys(write_type) < 0)
 				goto err;
 			for (i = 1; i <= rwc_core_cnt[n]; i++)
 				rte_eal_remote_launch(test_rwc_reader,
 						(void *)(uintptr_t)read_type,
 							enabled_core_ids[i]);
-			key_shift = 1;
-			ret = write_keys(key_shift);
+			write_type = WRITE_KEY_SHIFT;
+			ret = write_keys(write_type);
 			writer_done = 1;
 			rte_eal_mp_wait_lcore();
 
@@ -949,18 +1068,18 @@ test_hash_add_ks_lookup_miss(struct rwc_perf *rwc_perf_results, int rwc_lf, int
  */
 static int
 test_hash_multi_add_lookup(struct rwc_perf *rwc_perf_results, int rwc_lf,
-			   int htm)
+			   int htm, int ext_bkt)
 {
 	unsigned int n, m, k;
 	uint64_t i;
 	int use_jhash = 0;
-	uint8_t key_shift;
+	uint8_t write_type;
 	uint8_t read_type = READ_PASS_SHIFT_PATH;
 
 	rte_atomic64_init(&greads);
 	rte_atomic64_init(&gread_cycles);
 
-	if (init_params(rwc_lf, use_jhash, htm) != 0)
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
 		goto err;
 	printf("\nTest: Multi-add-lookup\n");
 	uint8_t pos_core;
@@ -991,8 +1110,8 @@ test_hash_multi_add_lookup(struct rwc_perf *rwc_perf_results, int rwc_lf,
 				writer_done = 0;
 				for (i = 0; i < 4; i++)
 					multi_writer_done[i] = 0;
-				key_shift = 0;
-				if (write_keys(key_shift) < 0)
+				write_type = WRITE_NO_KEY_SHIFT;
+				if (write_keys(write_type) < 0)
 					goto err;
 
 				/* Launch reader(s) */
@@ -1000,7 +1119,7 @@ test_hash_multi_add_lookup(struct rwc_perf *rwc_perf_results, int rwc_lf,
 					rte_eal_remote_launch(test_rwc_reader,
 						(void *)(uintptr_t)read_type,
 						enabled_core_ids[i]);
-				key_shift = 1;
+				write_type = WRITE_KEY_SHIFT;
 				pos_core = 0;
 
 				/* Launch writers */
@@ -1045,6 +1164,88 @@ test_hash_multi_add_lookup(struct rwc_perf *rwc_perf_results, int rwc_lf,
 	return -1;
 }
 
+/*
+ * Test lookup perf:
+ * Reader(s) lookup keys present in the extendable bkt.
+ */
+static int
+test_hash_add_ks_lookup_hit_extbkt(struct rwc_perf *rwc_perf_results,
+				int rwc_lf, int htm, int ext_bkt)
+{
+	unsigned int n, m;
+	uint64_t i;
+	int use_jhash = 0;
+	uint8_t write_type;
+	uint8_t read_type = READ_PASS_KEY_SHIFTS_EXTBKT;
+
+	rte_atomic64_init(&greads);
+	rte_atomic64_init(&gread_cycles);
+
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
+		goto err;
+	printf("\nTest: Hash add - key-shifts, read - hit (ext_bkt)\n");
+	for (m = 0; m < 2; m++) {
+		if (m == 1) {
+			printf("\n** With bulk-lookup **\n");
+			read_type |= BULK_LOOKUP;
+		}
+		for (n = 0; n < NUM_TEST; n++) {
+			unsigned int tot_lcore = rte_lcore_count();
+			if (tot_lcore < rwc_core_cnt[n] + 1)
+				goto finish;
+
+			printf("\nNumber of readers: %u\n", rwc_core_cnt[n]);
+
+			rte_atomic64_clear(&greads);
+			rte_atomic64_clear(&gread_cycles);
+
+			rte_hash_reset(tbl_rwc_test_param.h);
+			write_type = WRITE_NO_KEY_SHIFT;
+			if (write_keys(write_type) < 0)
+				goto err;
+			write_type = WRITE_KEY_SHIFT;
+			if (write_keys(write_type) < 0)
+				goto err;
+			writer_done = 0;
+			for (i = 1; i <= rwc_core_cnt[n]; i++)
+				rte_eal_remote_launch(test_rwc_reader,
+						(void *)(uintptr_t)read_type,
+							enabled_core_ids[i]);
+			for (i = 0; i < tbl_rwc_test_param.count_keys_ks_extbkt;
+			     i++) {
+				if (rte_hash_del_key(tbl_rwc_test_param.h,
+					tbl_rwc_test_param.keys_ks_extbkt + i)
+							< 0) {
+					printf("Delete Failed: %u\n",
+					tbl_rwc_test_param.keys_ks_extbkt[i]);
+					goto err;
+				}
+			}
+			writer_done = 1;
+			rte_eal_mp_wait_lcore();
+
+			for (i = 1; i <= rwc_core_cnt[n]; i++)
+				if (lcore_config[i].ret < 0)
+					goto err;
+
+			unsigned long long cycles_per_lookup =
+				rte_atomic64_read(&gread_cycles) /
+				rte_atomic64_read(&greads);
+			rwc_perf_results->w_ks_r_hit_extbkt[m][n]
+						= cycles_per_lookup;
+			printf("Cycles per lookup: %llu\n", cycles_per_lookup);
+		}
+	}
+
+finish:
+	rte_hash_free(tbl_rwc_test_param.h);
+	return 0;
+
+err:
+	rte_hash_free(tbl_rwc_test_param.h);
+	return -1;
+}
+
 static int
 test_hash_readwrite_lf_main(void)
 {
@@ -1057,6 +1258,7 @@ test_hash_readwrite_lf_main(void)
 	int rwc_lf = 0;
 	int htm;
 	int use_jhash = 0;
+	int ext_bkt = 0;
 	if (rte_lcore_count() == 1) {
 		printf("More than one lcore is required "
 			"to do read write lock-free concurrency test\n");
@@ -1070,7 +1272,7 @@ test_hash_readwrite_lf_main(void)
 	else
 		htm = 0;
 
-	if (init_params(rwc_lf, use_jhash, htm) != 0)
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
 		return -1;
 	if (generate_keys() != 0)
 		return -1;
@@ -1079,25 +1281,29 @@ test_hash_readwrite_lf_main(void)
 
 	if (RTE_HASH_EXTRA_FLAGS_RW_CONCURRENCY_LF) {
 		rwc_lf = 1;
+		ext_bkt = 1;
 		printf("Test lookup with read-write concurrency lock free support"
 		       " enabled\n");
 		if (test_hash_add_no_ks_lookup_hit(&rwc_lf_results, rwc_lf,
-							htm) < 0)
+							htm, ext_bkt) < 0)
 			return -1;
 		if (test_hash_add_no_ks_lookup_miss(&rwc_lf_results, rwc_lf,
-							htm) < 0)
+							htm, ext_bkt) < 0)
 			return -1;
 		if (test_hash_add_ks_lookup_hit_non_sp(&rwc_lf_results, rwc_lf,
-							htm) < 0)
+							htm, ext_bkt) < 0)
 			return -1;
 		if (test_hash_add_ks_lookup_hit_sp(&rwc_lf_results, rwc_lf,
-							htm) < 0)
+							htm, ext_bkt) < 0)
 			return -1;
-		if (test_hash_add_ks_lookup_miss(&rwc_lf_results, rwc_lf, htm)
-							< 0)
+		if (test_hash_add_ks_lookup_miss(&rwc_lf_results, rwc_lf, htm,
+						 ext_bkt) < 0)
 			return -1;
-		if (test_hash_multi_add_lookup(&rwc_lf_results, rwc_lf, htm)
-							< 0)
+		if (test_hash_multi_add_lookup(&rwc_lf_results, rwc_lf, htm,
+					       ext_bkt) < 0)
+			return -1;
+		if (test_hash_add_ks_lookup_hit_extbkt(&rwc_lf_results, rwc_lf,
+							htm, ext_bkt) < 0)
 			return -1;
 	}
 	printf("\nTest lookup with read-write concurrency lock free support"
@@ -1112,21 +1318,26 @@ test_hash_readwrite_lf_main(void)
 		}
 	} else
 		printf("With HTM Enabled\n");
-	if (test_hash_add_no_ks_lookup_hit(&rwc_non_lf_results, rwc_lf, htm)
-						< 0)
+	if (test_hash_add_no_ks_lookup_hit(&rwc_non_lf_results, rwc_lf, htm,
+					   ext_bkt) < 0)
 		return -1;
-	if (test_hash_add_no_ks_lookup_miss(&rwc_non_lf_results, rwc_lf, htm)
-						< 0)
+	if (test_hash_add_no_ks_lookup_miss(&rwc_non_lf_results, rwc_lf, htm,
+						ext_bkt) < 0)
 		return -1;
 	if (test_hash_add_ks_lookup_hit_non_sp(&rwc_non_lf_results, rwc_lf,
-						htm) < 0)
+						htm, ext_bkt) < 0)
+		return -1;
+	if (test_hash_add_ks_lookup_hit_sp(&rwc_non_lf_results, rwc_lf, htm,
+						ext_bkt) < 0)
 		return -1;
-	if (test_hash_add_ks_lookup_hit_sp(&rwc_non_lf_results, rwc_lf, htm)
-						< 0)
+	if (test_hash_add_ks_lookup_miss(&rwc_non_lf_results, rwc_lf, htm,
+					 ext_bkt) < 0)
 		return -1;
-	if (test_hash_add_ks_lookup_miss(&rwc_non_lf_results, rwc_lf, htm) < 0)
+	if (test_hash_multi_add_lookup(&rwc_non_lf_results, rwc_lf, htm,
+							ext_bkt) < 0)
 		return -1;
-	if (test_hash_multi_add_lookup(&rwc_non_lf_results, rwc_lf, htm) < 0)
+	if (test_hash_add_ks_lookup_hit_extbkt(&rwc_non_lf_results, rwc_lf,
+						htm, ext_bkt) < 0)
 		return -1;
 results:
 	printf("\n\t\t\t\t\t\t********** Results summary **********\n\n");
@@ -1158,8 +1369,11 @@ test_hash_readwrite_lf_main(void)
 			       "(shift-path)\t\t%u\n\t\t\t\t\t\t\t\t",
 			       rwc_lf_results.w_ks_r_hit_sp[j][i]);
 			printf("Hash add - key-shifts, Hash lookup miss\t\t\t\t"
-				"%u\n\n\t\t\t\t",
+				"%u\n\t\t\t\t\t\t\t\t",
 				rwc_lf_results.w_ks_r_miss[j][i]);
+			printf("Hash add - key-shifts, Hash lookup hit (ext_bkt)\t\t"
+				"%u\n\n\t\t\t\t",
+				rwc_lf_results.w_ks_r_hit_extbkt[j][i]);
 
 			printf("Disabled\t");
 			if (htm)
@@ -1179,7 +1393,11 @@ test_hash_readwrite_lf_main(void)
 			       "(shift-path)\t\t%u\n\t\t\t\t\t\t\t\t",
 			       rwc_non_lf_results.w_ks_r_hit_sp[j][i]);
 			printf("Hash add - key-shifts, Hash lookup miss\t\t\t\t"
-			       "%u\n", rwc_non_lf_results.w_ks_r_miss[j][i]);
+			       "%u\n\t\t\t\t\t\t\t\t",
+			       rwc_non_lf_results.w_ks_r_miss[j][i]);
+			printf("Hash add - key-shifts, Hash lookup hit (ext_bkt)\t\t"
+				"%u\n",
+				rwc_non_lf_results.w_ks_r_hit_extbkt[j][i]);
 
 			printf("_______\t\t_______\t\t_________\t___\t\t"
 			       "_________\t\t\t\t\t\t_________________\n");
-- 
2.17.1

[dpdk-dev] [PATCH v2 0/2] hash: add lock free support for ext bkt

[Dharmik Thakkar]

This patch series:
- Enables lock-free read-write concurrency support for extendable
bucket feature.
- Adds lock-free read-write concurrency tests for ext bkt 

Dharmik Thakkar (2):
  hash: add lock free support for extendable bucket
  test/hash: lock-free rw concurrency test ext bkt

 app/test/test_hash_readwrite_lf.c  | 350 +++++++++++++++++++++++------
 doc/guides/prog_guide/hash_lib.rst |   6 +-
 lib/librte_hash/rte_cuckoo_hash.c  | 160 ++++++++-----
 lib/librte_hash/rte_cuckoo_hash.h  |   7 +
 4 files changed, 404 insertions(+), 119 deletions(-)

-- 
2.17.1

[dpdk-dev] [PATCH v2 0/2] hash: add lock free support for ext bkt

[Dharmik Thakkar]

This patch series:
- Enables lock-free read-write concurrency support for extendable
bucket feature.
- Adds lock-free read-write concurrency tests for ext bkt 

Dharmik Thakkar (2):
  hash: add lock free support for extendable bucket
  test/hash: lock-free rw concurrency test ext bkt

 app/test/test_hash_readwrite_lf.c  | 350 +++++++++++++++++++++++------
 doc/guides/prog_guide/hash_lib.rst |   6 +-
 lib/librte_hash/rte_cuckoo_hash.c  | 160 ++++++++-----
 lib/librte_hash/rte_cuckoo_hash.h  |   7 +
 4 files changed, 404 insertions(+), 119 deletions(-)

-- 
2.17.1

[dpdk-dev] [PATCH v2 1/2] hash: add lock free support for extendable bucket

[Dharmik Thakkar]

This patch enables lock-free read-write concurrency support for
extendable bucket feature.

Suggested-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
Signed-off-by: Dharmik Thakkar <dharmik.thakkar@arm.com>
Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
Reviewed-by: Gavin Hu <gavin.hu@arm.com>
Reviewed-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
---
v2:
 - Update doc (Yipeng)
 - Update lib/librte_hash/rte_cuckoo_hash.c (Yipeng)
---
doc/guides/prog_guide/hash_lib.rst |   6 +-
 lib/librte_hash/rte_cuckoo_hash.c  | 160 ++++++++++++++++++++---------
 lib/librte_hash/rte_cuckoo_hash.h  |   7 ++
 3 files changed, 120 insertions(+), 53 deletions(-)

diff --git a/doc/guides/prog_guide/hash_lib.rst b/doc/guides/prog_guide/hash_lib.rst
index 85a6edfa8b16..d06c7de2ead1 100644
--- a/doc/guides/prog_guide/hash_lib.rst
+++ b/doc/guides/prog_guide/hash_lib.rst
@@ -108,9 +108,9 @@ Extendable Bucket Functionality support
 An extra flag is used to enable this functionality (flag is not set by default). When the (RTE_HASH_EXTRA_FLAGS_EXT_TABLE) is set and
 in the very unlikely case due to excessive hash collisions that a key has failed to be inserted, the hash table bucket is extended with a linked
 list to insert these failed keys. This feature is important for the workloads (e.g. telco workloads) that need to insert up to 100% of the
-hash table size and can't tolerate any key insertion failure (even if very few). Currently the extendable bucket is not supported
-with the lock-free concurrency implementation (RTE_HASH_EXTRA_FLAGS_RW_CONCURRENCY_LF).
-
+hash table size and can't tolerate any key insertion failure (even if very few).
+Please note that with the 'lock free read/write concurrency' flag enabled, users need to call 'rte_hash_free_key_with_position' API in order to free the empty buckets and
+deleted keys, to maintain the 100% capacity guarantee.
 
 Implementation Details (non Extendable Bucket Case)
 ---------------------------------------------------
diff --git a/lib/librte_hash/rte_cuckoo_hash.c b/lib/librte_hash/rte_cuckoo_hash.c
index c01489ba5193..98ec929a54eb 100644
--- a/lib/librte_hash/rte_cuckoo_hash.c
+++ b/lib/librte_hash/rte_cuckoo_hash.c
@@ -140,6 +140,7 @@ rte_hash_create(const struct rte_hash_parameters *params)
 	unsigned int readwrite_concur_support = 0;
 	unsigned int writer_takes_lock = 0;
 	unsigned int no_free_on_del = 0;
+	uint32_t *ext_bkt_to_free = NULL;
 	uint32_t *tbl_chng_cnt = NULL;
 	unsigned int readwrite_concur_lf_support = 0;
 
@@ -170,15 +171,6 @@ rte_hash_create(const struct rte_hash_parameters *params)
 		return NULL;
 	}
 
-	if ((params->extra_flag & RTE_HASH_EXTRA_FLAGS_RW_CONCURRENCY_LF) &&
-	    (params->extra_flag & RTE_HASH_EXTRA_FLAGS_EXT_TABLE)) {
-		rte_errno = EINVAL;
-		RTE_LOG(ERR, HASH, "rte_hash_create: extendable bucket "
-			"feature not supported with rw concurrency "
-			"lock free\n");
-		return NULL;
-	}
-
 	/* Check extra flags field to check extra options. */
 	if (params->extra_flag & RTE_HASH_EXTRA_FLAGS_TRANS_MEM_SUPPORT)
 		hw_trans_mem_support = 1;
@@ -302,6 +294,16 @@ rte_hash_create(const struct rte_hash_parameters *params)
 		 */
 		for (i = 1; i <= num_buckets; i++)
 			rte_ring_sp_enqueue(r_ext, (void *)((uintptr_t) i));
+
+		if (readwrite_concur_lf_support) {
+			ext_bkt_to_free = rte_zmalloc(NULL, sizeof(uint32_t) *
+								num_key_slots, 0);
+			if (ext_bkt_to_free == NULL) {
+				RTE_LOG(ERR, HASH, "ext bkt to free memory allocation "
+								"failed\n");
+				goto err_unlock;
+			}
+		}
 	}
 
 	const uint32_t key_entry_size =
@@ -393,6 +395,7 @@ rte_hash_create(const struct rte_hash_parameters *params)
 		default_hash_func : params->hash_func;
 	h->key_store = k;
 	h->free_slots = r;
+	h->ext_bkt_to_free = ext_bkt_to_free;
 	h->tbl_chng_cnt = tbl_chng_cnt;
 	*h->tbl_chng_cnt = 0;
 	h->hw_trans_mem_support = hw_trans_mem_support;
@@ -443,6 +446,7 @@ rte_hash_create(const struct rte_hash_parameters *params)
 	rte_free(buckets_ext);
 	rte_free(k);
 	rte_free(tbl_chng_cnt);
+	rte_free(ext_bkt_to_free);
 	return NULL;
 }
 
@@ -484,6 +488,7 @@ rte_hash_free(struct rte_hash *h)
 	rte_free(h->buckets);
 	rte_free(h->buckets_ext);
 	rte_free(h->tbl_chng_cnt);
+	rte_free(h->ext_bkt_to_free);
 	rte_free(h);
 	rte_free(te);
 }
@@ -799,7 +804,7 @@ rte_hash_cuckoo_move_insert_mw(const struct rte_hash *h,
 			__atomic_store_n(h->tbl_chng_cnt,
 					 *h->tbl_chng_cnt + 1,
 					 __ATOMIC_RELEASE);
-			/* The stores to sig_alt and sig_current should not
+			/* The store to sig_current should not
 			 * move above the store to tbl_chng_cnt.
 			 */
 			__atomic_thread_fence(__ATOMIC_RELEASE);
@@ -831,7 +836,7 @@ rte_hash_cuckoo_move_insert_mw(const struct rte_hash *h,
 		__atomic_store_n(h->tbl_chng_cnt,
 				 *h->tbl_chng_cnt + 1,
 				 __ATOMIC_RELEASE);
-		/* The stores to sig_alt and sig_current should not
+		/* The store to sig_current should not
 		 * move above the store to tbl_chng_cnt.
 		 */
 		__atomic_thread_fence(__ATOMIC_RELEASE);
@@ -1054,7 +1059,12 @@ __rte_hash_add_key_with_hash(const struct rte_hash *h, const void *key,
 			/* Check if slot is available */
 			if (likely(cur_bkt->key_idx[i] == EMPTY_SLOT)) {
 				cur_bkt->sig_current[i] = short_sig;
-				cur_bkt->key_idx[i] = new_idx;
+				/* Store to signature should not leak after
+				 * the store to key_idx
+				 */
+				__atomic_store_n(&cur_bkt->key_idx[i],
+						 new_idx,
+						 __ATOMIC_RELEASE);
 				__hash_rw_writer_unlock(h);
 				return new_idx - 1;
 			}
@@ -1072,7 +1082,15 @@ __rte_hash_add_key_with_hash(const struct rte_hash *h, const void *key,
 	bkt_id = (uint32_t)((uintptr_t)ext_bkt_id) - 1;
 	/* Use the first location of the new bucket */
 	(h->buckets_ext[bkt_id]).sig_current[0] = short_sig;
-	(h->buckets_ext[bkt_id]).key_idx[0] = new_idx;
+	/* Key can be of arbitrary length, so it is
+	 * not possible to store it atomically.
+	 * Hence the new key element's memory stores
+	 * (key as well as data) should be complete
+	 * before it is referenced.
+	 */
+	__atomic_store_n(&(h->buckets_ext[bkt_id]).key_idx[0],
+			 new_idx,
+			 __ATOMIC_RELEASE);
 	/* Link the new bucket to sec bucket linked list */
 	last = rte_hash_get_last_bkt(sec_bkt);
 	last->next = &h->buckets_ext[bkt_id];
@@ -1366,7 +1384,8 @@ remove_entry(const struct rte_hash *h, struct rte_hash_bucket *bkt, unsigned i)
  * empty slot.
  */
 static inline void
-__rte_hash_compact_ll(struct rte_hash_bucket *cur_bkt, int pos) {
+__rte_hash_compact_ll(const struct rte_hash *h,
+			struct rte_hash_bucket *cur_bkt, int pos) {
 	int i;
 	struct rte_hash_bucket *last_bkt;
 
@@ -1377,10 +1396,27 @@ __rte_hash_compact_ll(struct rte_hash_bucket *cur_bkt, int pos) {
 
 	for (i = RTE_HASH_BUCKET_ENTRIES - 1; i >= 0; i--) {
 		if (last_bkt->key_idx[i] != EMPTY_SLOT) {
-			cur_bkt->key_idx[pos] = last_bkt->key_idx[i];
 			cur_bkt->sig_current[pos] = last_bkt->sig_current[i];
+			__atomic_store_n(&cur_bkt->key_idx[pos],
+					 last_bkt->key_idx[i],
+					 __ATOMIC_RELEASE);
+			if (h->readwrite_concur_lf_support) {
+				/* Inform the readers that the table has changed
+				 * Since there is one writer, load acquire on
+				 * tbl_chng_cnt is not required.
+				 */
+				__atomic_store_n(h->tbl_chng_cnt,
+					 *h->tbl_chng_cnt + 1,
+					 __ATOMIC_RELEASE);
+				/* The store to sig_current should
+				 * not move above the store to tbl_chng_cnt.
+				 */
+				__atomic_thread_fence(__ATOMIC_RELEASE);
+			}
 			last_bkt->sig_current[i] = NULL_SIGNATURE;
-			last_bkt->key_idx[i] = EMPTY_SLOT;
+			__atomic_store_n(&last_bkt->key_idx[i],
+					 EMPTY_SLOT,
+					 __ATOMIC_RELEASE);
 			return;
 		}
 	}
@@ -1449,7 +1485,7 @@ __rte_hash_del_key_with_hash(const struct rte_hash *h, const void *key,
 	/* look for key in primary bucket */
 	ret = search_and_remove(h, key, prim_bkt, short_sig, &pos);
 	if (ret != -1) {
-		__rte_hash_compact_ll(prim_bkt, pos);
+		__rte_hash_compact_ll(h, prim_bkt, pos);
 		last_bkt = prim_bkt->next;
 		prev_bkt = prim_bkt;
 		goto return_bkt;
@@ -1461,7 +1497,7 @@ __rte_hash_del_key_with_hash(const struct rte_hash *h, const void *key,
 	FOR_EACH_BUCKET(cur_bkt, sec_bkt) {
 		ret = search_and_remove(h, key, cur_bkt, short_sig, &pos);
 		if (ret != -1) {
-			__rte_hash_compact_ll(cur_bkt, pos);
+			__rte_hash_compact_ll(h, cur_bkt, pos);
 			last_bkt = sec_bkt->next;
 			prev_bkt = sec_bkt;
 			goto return_bkt;
@@ -1488,11 +1524,24 @@ __rte_hash_del_key_with_hash(const struct rte_hash *h, const void *key,
 	}
 	/* found empty bucket and recycle */
 	if (i == RTE_HASH_BUCKET_ENTRIES) {
-		prev_bkt->next = last_bkt->next = NULL;
+		prev_bkt->next = NULL;
 		uint32_t index = last_bkt - h->buckets_ext + 1;
-		rte_ring_sp_enqueue(h->free_ext_bkts, (void *)(uintptr_t)index);
+		/* Recycle the empty bkt if
+		 * no_free_on_del is disabled.
+		 */
+		if (h->no_free_on_del)
+			/* Store index of an empty ext bkt to be recycled
+			 * on calling rte_hash_del_xxx APIs.
+			 * When lock free read-write concurrency is enabled,
+			 * an empty ext bkt cannot be put into free list
+			 * immediately (as readers might be using it still).
+			 * Hence freeing of the ext bkt is piggy-backed to
+			 * freeing of the key index.
+			 */
+			h->ext_bkt_to_free[ret] = index;
+		else
+			rte_ring_sp_enqueue(h->free_ext_bkts, (void *)(uintptr_t)index);
 	}
-
 	__hash_rw_writer_unlock(h);
 	return ret;
 }
@@ -1545,6 +1594,14 @@ rte_hash_free_key_with_position(const struct rte_hash *h,
 	/* Out of bounds */
 	if (position >= total_entries)
 		return -EINVAL;
+	if (h->ext_table_support && h->readwrite_concur_lf_support) {
+		uint32_t index = h->ext_bkt_to_free[position];
+		if (index) {
+			/* Recycle empty ext bkt to free list. */
+			rte_ring_sp_enqueue(h->free_ext_bkts, (void *)(uintptr_t)index);
+			h->ext_bkt_to_free[position] = 0;
+		}
+	}
 
 	if (h->use_local_cache) {
 		lcore_id = rte_lcore_id();
@@ -1855,6 +1912,9 @@ __rte_hash_lookup_bulk_lf(const struct rte_hash *h, const void **keys,
 		rte_prefetch0(secondary_bkt[i]);
 	}
 
+	for (i = 0; i < num_keys; i++)
+		positions[i] = -ENOENT;
+
 	do {
 		/* Load the table change counter before the lookup
 		 * starts. Acquire semantics will make sure that
@@ -1899,7 +1959,6 @@ __rte_hash_lookup_bulk_lf(const struct rte_hash *h, const void **keys,
 
 		/* Compare keys, first hits in primary first */
 		for (i = 0; i < num_keys; i++) {
-			positions[i] = -ENOENT;
 			while (prim_hitmask[i]) {
 				uint32_t hit_index =
 						__builtin_ctzl(prim_hitmask[i])
@@ -1972,6 +2031,35 @@ __rte_hash_lookup_bulk_lf(const struct rte_hash *h, const void **keys,
 			continue;
 		}
 
+		/* all found, do not need to go through ext bkt */
+		if (hits == ((1ULL << num_keys) - 1)) {
+			if (hit_mask != NULL)
+				*hit_mask = hits;
+			return;
+		}
+		/* need to check ext buckets for match */
+		if (h->ext_table_support) {
+			for (i = 0; i < num_keys; i++) {
+				if ((hits & (1ULL << i)) != 0)
+					continue;
+				next_bkt = secondary_bkt[i]->next;
+				FOR_EACH_BUCKET(cur_bkt, next_bkt) {
+					if (data != NULL)
+						ret = search_one_bucket_lf(h,
+							keys[i], sig[i],
+							&data[i], cur_bkt);
+					else
+						ret = search_one_bucket_lf(h,
+								keys[i], sig[i],
+								NULL, cur_bkt);
+					if (ret != -1) {
+						positions[i] = ret;
+						hits |= 1ULL << i;
+						break;
+					}
+				}
+			}
+		}
 		/* The loads of sig_current in compare_signatures
 		 * should not move below the load from tbl_chng_cnt.
 		 */
@@ -1988,34 +2076,6 @@ __rte_hash_lookup_bulk_lf(const struct rte_hash *h, const void **keys,
 					__ATOMIC_ACQUIRE);
 	} while (cnt_b != cnt_a);
 
-	/* all found, do not need to go through ext bkt */
-	if ((hits == ((1ULL << num_keys) - 1)) || !h->ext_table_support) {
-		if (hit_mask != NULL)
-			*hit_mask = hits;
-		__hash_rw_reader_unlock(h);
-		return;
-	}
-
-	/* need to check ext buckets for match */
-	for (i = 0; i < num_keys; i++) {
-		if ((hits & (1ULL << i)) != 0)
-			continue;
-		next_bkt = secondary_bkt[i]->next;
-		FOR_EACH_BUCKET(cur_bkt, next_bkt) {
-			if (data != NULL)
-				ret = search_one_bucket_lf(h, keys[i],
-						sig[i], &data[i], cur_bkt);
-			else
-				ret = search_one_bucket_lf(h, keys[i],
-						sig[i], NULL, cur_bkt);
-			if (ret != -1) {
-				positions[i] = ret;
-				hits |= 1ULL << i;
-				break;
-			}
-		}
-	}
-
 	if (hit_mask != NULL)
 		*hit_mask = hits;
 }
diff --git a/lib/librte_hash/rte_cuckoo_hash.h b/lib/librte_hash/rte_cuckoo_hash.h
index eacdaa8d4684..48c85c890712 100644
--- a/lib/librte_hash/rte_cuckoo_hash.h
+++ b/lib/librte_hash/rte_cuckoo_hash.h
@@ -210,6 +210,13 @@ struct rte_hash {
 	rte_rwlock_t *readwrite_lock; /**< Read-write lock thread-safety. */
 	struct rte_hash_bucket *buckets_ext; /**< Extra buckets array */
 	struct rte_ring *free_ext_bkts; /**< Ring of indexes of free buckets */
+	/* Stores index of an empty ext bkt to be recycled on calling
+	 * rte_hash_del_xxx APIs. When lock free read-write concurrency is
+	 * enabled, an empty ext bkt cannot be put into free list immediately
+	 * (as readers might be using it still). Hence freeing of the ext bkt
+	 * is piggy-backed to freeing of the key index.
+	 */
+	uint32_t *ext_bkt_to_free;
 	uint32_t *tbl_chng_cnt;
 	/**< Indicates if the hash table changed from last read. */
 } __rte_cache_aligned;
-- 
2.17.1

[dpdk-dev] [PATCH v2 1/2] hash: add lock free support for extendable bucket

[Dharmik Thakkar]

This patch enables lock-free read-write concurrency support for
extendable bucket feature.

Suggested-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
Signed-off-by: Dharmik Thakkar <dharmik.thakkar@arm.com>
Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
Reviewed-by: Gavin Hu <gavin.hu@arm.com>
Reviewed-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
---
v2:
 - Update doc (Yipeng)
 - Update lib/librte_hash/rte_cuckoo_hash.c (Yipeng)
---
doc/guides/prog_guide/hash_lib.rst |   6 +-
 lib/librte_hash/rte_cuckoo_hash.c  | 160 ++++++++++++++++++++---------
 lib/librte_hash/rte_cuckoo_hash.h  |   7 ++
 3 files changed, 120 insertions(+), 53 deletions(-)

diff --git a/doc/guides/prog_guide/hash_lib.rst b/doc/guides/prog_guide/hash_lib.rst
index 85a6edfa8b16..d06c7de2ead1 100644
--- a/doc/guides/prog_guide/hash_lib.rst
+++ b/doc/guides/prog_guide/hash_lib.rst
@@ -108,9 +108,9 @@ Extendable Bucket Functionality support
 An extra flag is used to enable this functionality (flag is not set by default). When the (RTE_HASH_EXTRA_FLAGS_EXT_TABLE) is set and
 in the very unlikely case due to excessive hash collisions that a key has failed to be inserted, the hash table bucket is extended with a linked
 list to insert these failed keys. This feature is important for the workloads (e.g. telco workloads) that need to insert up to 100% of the
-hash table size and can't tolerate any key insertion failure (even if very few). Currently the extendable bucket is not supported
-with the lock-free concurrency implementation (RTE_HASH_EXTRA_FLAGS_RW_CONCURRENCY_LF).
-
+hash table size and can't tolerate any key insertion failure (even if very few).
+Please note that with the 'lock free read/write concurrency' flag enabled, users need to call 'rte_hash_free_key_with_position' API in order to free the empty buckets and
+deleted keys, to maintain the 100% capacity guarantee.
 
 Implementation Details (non Extendable Bucket Case)
 ---------------------------------------------------
diff --git a/lib/librte_hash/rte_cuckoo_hash.c b/lib/librte_hash/rte_cuckoo_hash.c
index c01489ba5193..98ec929a54eb 100644
--- a/lib/librte_hash/rte_cuckoo_hash.c
+++ b/lib/librte_hash/rte_cuckoo_hash.c
@@ -140,6 +140,7 @@ rte_hash_create(const struct rte_hash_parameters *params)
 	unsigned int readwrite_concur_support = 0;
 	unsigned int writer_takes_lock = 0;
 	unsigned int no_free_on_del = 0;
+	uint32_t *ext_bkt_to_free = NULL;
 	uint32_t *tbl_chng_cnt = NULL;
 	unsigned int readwrite_concur_lf_support = 0;
 
@@ -170,15 +171,6 @@ rte_hash_create(const struct rte_hash_parameters *params)
 		return NULL;
 	}
 
-	if ((params->extra_flag & RTE_HASH_EXTRA_FLAGS_RW_CONCURRENCY_LF) &&
-	    (params->extra_flag & RTE_HASH_EXTRA_FLAGS_EXT_TABLE)) {
-		rte_errno = EINVAL;
-		RTE_LOG(ERR, HASH, "rte_hash_create: extendable bucket "
-			"feature not supported with rw concurrency "
-			"lock free\n");
-		return NULL;
-	}
-
 	/* Check extra flags field to check extra options. */
 	if (params->extra_flag & RTE_HASH_EXTRA_FLAGS_TRANS_MEM_SUPPORT)
 		hw_trans_mem_support = 1;
@@ -302,6 +294,16 @@ rte_hash_create(const struct rte_hash_parameters *params)
 		 */
 		for (i = 1; i <= num_buckets; i++)
 			rte_ring_sp_enqueue(r_ext, (void *)((uintptr_t) i));
+
+		if (readwrite_concur_lf_support) {
+			ext_bkt_to_free = rte_zmalloc(NULL, sizeof(uint32_t) *
+								num_key_slots, 0);
+			if (ext_bkt_to_free == NULL) {
+				RTE_LOG(ERR, HASH, "ext bkt to free memory allocation "
+								"failed\n");
+				goto err_unlock;
+			}
+		}
 	}
 
 	const uint32_t key_entry_size =
@@ -393,6 +395,7 @@ rte_hash_create(const struct rte_hash_parameters *params)
 		default_hash_func : params->hash_func;
 	h->key_store = k;
 	h->free_slots = r;
+	h->ext_bkt_to_free = ext_bkt_to_free;
 	h->tbl_chng_cnt = tbl_chng_cnt;
 	*h->tbl_chng_cnt = 0;
 	h->hw_trans_mem_support = hw_trans_mem_support;
@@ -443,6 +446,7 @@ rte_hash_create(const struct rte_hash_parameters *params)
 	rte_free(buckets_ext);
 	rte_free(k);
 	rte_free(tbl_chng_cnt);
+	rte_free(ext_bkt_to_free);
 	return NULL;
 }
 
@@ -484,6 +488,7 @@ rte_hash_free(struct rte_hash *h)
 	rte_free(h->buckets);
 	rte_free(h->buckets_ext);
 	rte_free(h->tbl_chng_cnt);
+	rte_free(h->ext_bkt_to_free);
 	rte_free(h);
 	rte_free(te);
 }
@@ -799,7 +804,7 @@ rte_hash_cuckoo_move_insert_mw(const struct rte_hash *h,
 			__atomic_store_n(h->tbl_chng_cnt,
 					 *h->tbl_chng_cnt + 1,
 					 __ATOMIC_RELEASE);
-			/* The stores to sig_alt and sig_current should not
+			/* The store to sig_current should not
 			 * move above the store to tbl_chng_cnt.
 			 */
 			__atomic_thread_fence(__ATOMIC_RELEASE);
@@ -831,7 +836,7 @@ rte_hash_cuckoo_move_insert_mw(const struct rte_hash *h,
 		__atomic_store_n(h->tbl_chng_cnt,
 				 *h->tbl_chng_cnt + 1,
 				 __ATOMIC_RELEASE);
-		/* The stores to sig_alt and sig_current should not
+		/* The store to sig_current should not
 		 * move above the store to tbl_chng_cnt.
 		 */
 		__atomic_thread_fence(__ATOMIC_RELEASE);
@@ -1054,7 +1059,12 @@ __rte_hash_add_key_with_hash(const struct rte_hash *h, const void *key,
 			/* Check if slot is available */
 			if (likely(cur_bkt->key_idx[i] == EMPTY_SLOT)) {
 				cur_bkt->sig_current[i] = short_sig;
-				cur_bkt->key_idx[i] = new_idx;
+				/* Store to signature should not leak after
+				 * the store to key_idx
+				 */
+				__atomic_store_n(&cur_bkt->key_idx[i],
+						 new_idx,
+						 __ATOMIC_RELEASE);
 				__hash_rw_writer_unlock(h);
 				return new_idx - 1;
 			}
@@ -1072,7 +1082,15 @@ __rte_hash_add_key_with_hash(const struct rte_hash *h, const void *key,
 	bkt_id = (uint32_t)((uintptr_t)ext_bkt_id) - 1;
 	/* Use the first location of the new bucket */
 	(h->buckets_ext[bkt_id]).sig_current[0] = short_sig;
-	(h->buckets_ext[bkt_id]).key_idx[0] = new_idx;
+	/* Key can be of arbitrary length, so it is
+	 * not possible to store it atomically.
+	 * Hence the new key element's memory stores
+	 * (key as well as data) should be complete
+	 * before it is referenced.
+	 */
+	__atomic_store_n(&(h->buckets_ext[bkt_id]).key_idx[0],
+			 new_idx,
+			 __ATOMIC_RELEASE);
 	/* Link the new bucket to sec bucket linked list */
 	last = rte_hash_get_last_bkt(sec_bkt);
 	last->next = &h->buckets_ext[bkt_id];
@@ -1366,7 +1384,8 @@ remove_entry(const struct rte_hash *h, struct rte_hash_bucket *bkt, unsigned i)
  * empty slot.
  */
 static inline void
-__rte_hash_compact_ll(struct rte_hash_bucket *cur_bkt, int pos) {
+__rte_hash_compact_ll(const struct rte_hash *h,
+			struct rte_hash_bucket *cur_bkt, int pos) {
 	int i;
 	struct rte_hash_bucket *last_bkt;
 
@@ -1377,10 +1396,27 @@ __rte_hash_compact_ll(struct rte_hash_bucket *cur_bkt, int pos) {
 
 	for (i = RTE_HASH_BUCKET_ENTRIES - 1; i >= 0; i--) {
 		if (last_bkt->key_idx[i] != EMPTY_SLOT) {
-			cur_bkt->key_idx[pos] = last_bkt->key_idx[i];
 			cur_bkt->sig_current[pos] = last_bkt->sig_current[i];
+			__atomic_store_n(&cur_bkt->key_idx[pos],
+					 last_bkt->key_idx[i],
+					 __ATOMIC_RELEASE);
+			if (h->readwrite_concur_lf_support) {
+				/* Inform the readers that the table has changed
+				 * Since there is one writer, load acquire on
+				 * tbl_chng_cnt is not required.
+				 */
+				__atomic_store_n(h->tbl_chng_cnt,
+					 *h->tbl_chng_cnt + 1,
+					 __ATOMIC_RELEASE);
+				/* The store to sig_current should
+				 * not move above the store to tbl_chng_cnt.
+				 */
+				__atomic_thread_fence(__ATOMIC_RELEASE);
+			}
 			last_bkt->sig_current[i] = NULL_SIGNATURE;
-			last_bkt->key_idx[i] = EMPTY_SLOT;
+			__atomic_store_n(&last_bkt->key_idx[i],
+					 EMPTY_SLOT,
+					 __ATOMIC_RELEASE);
 			return;
 		}
 	}
@@ -1449,7 +1485,7 @@ __rte_hash_del_key_with_hash(const struct rte_hash *h, const void *key,
 	/* look for key in primary bucket */
 	ret = search_and_remove(h, key, prim_bkt, short_sig, &pos);
 	if (ret != -1) {
-		__rte_hash_compact_ll(prim_bkt, pos);
+		__rte_hash_compact_ll(h, prim_bkt, pos);
 		last_bkt = prim_bkt->next;
 		prev_bkt = prim_bkt;
 		goto return_bkt;
@@ -1461,7 +1497,7 @@ __rte_hash_del_key_with_hash(const struct rte_hash *h, const void *key,
 	FOR_EACH_BUCKET(cur_bkt, sec_bkt) {
 		ret = search_and_remove(h, key, cur_bkt, short_sig, &pos);
 		if (ret != -1) {
-			__rte_hash_compact_ll(cur_bkt, pos);
+			__rte_hash_compact_ll(h, cur_bkt, pos);
 			last_bkt = sec_bkt->next;
 			prev_bkt = sec_bkt;
 			goto return_bkt;
@@ -1488,11 +1524,24 @@ __rte_hash_del_key_with_hash(const struct rte_hash *h, const void *key,
 	}
 	/* found empty bucket and recycle */
 	if (i == RTE_HASH_BUCKET_ENTRIES) {
-		prev_bkt->next = last_bkt->next = NULL;
+		prev_bkt->next = NULL;
 		uint32_t index = last_bkt - h->buckets_ext + 1;
-		rte_ring_sp_enqueue(h->free_ext_bkts, (void *)(uintptr_t)index);
+		/* Recycle the empty bkt if
+		 * no_free_on_del is disabled.
+		 */
+		if (h->no_free_on_del)
+			/* Store index of an empty ext bkt to be recycled
+			 * on calling rte_hash_del_xxx APIs.
+			 * When lock free read-write concurrency is enabled,
+			 * an empty ext bkt cannot be put into free list
+			 * immediately (as readers might be using it still).
+			 * Hence freeing of the ext bkt is piggy-backed to
+			 * freeing of the key index.
+			 */
+			h->ext_bkt_to_free[ret] = index;
+		else
+			rte_ring_sp_enqueue(h->free_ext_bkts, (void *)(uintptr_t)index);
 	}
-
 	__hash_rw_writer_unlock(h);
 	return ret;
 }
@@ -1545,6 +1594,14 @@ rte_hash_free_key_with_position(const struct rte_hash *h,
 	/* Out of bounds */
 	if (position >= total_entries)
 		return -EINVAL;
+	if (h->ext_table_support && h->readwrite_concur_lf_support) {
+		uint32_t index = h->ext_bkt_to_free[position];
+		if (index) {
+			/* Recycle empty ext bkt to free list. */
+			rte_ring_sp_enqueue(h->free_ext_bkts, (void *)(uintptr_t)index);
+			h->ext_bkt_to_free[position] = 0;
+		}
+	}
 
 	if (h->use_local_cache) {
 		lcore_id = rte_lcore_id();
@@ -1855,6 +1912,9 @@ __rte_hash_lookup_bulk_lf(const struct rte_hash *h, const void **keys,
 		rte_prefetch0(secondary_bkt[i]);
 	}
 
+	for (i = 0; i < num_keys; i++)
+		positions[i] = -ENOENT;
+
 	do {
 		/* Load the table change counter before the lookup
 		 * starts. Acquire semantics will make sure that
@@ -1899,7 +1959,6 @@ __rte_hash_lookup_bulk_lf(const struct rte_hash *h, const void **keys,
 
 		/* Compare keys, first hits in primary first */
 		for (i = 0; i < num_keys; i++) {
-			positions[i] = -ENOENT;
 			while (prim_hitmask[i]) {
 				uint32_t hit_index =
 						__builtin_ctzl(prim_hitmask[i])
@@ -1972,6 +2031,35 @@ __rte_hash_lookup_bulk_lf(const struct rte_hash *h, const void **keys,
 			continue;
 		}
 
+		/* all found, do not need to go through ext bkt */
+		if (hits == ((1ULL << num_keys) - 1)) {
+			if (hit_mask != NULL)
+				*hit_mask = hits;
+			return;
+		}
+		/* need to check ext buckets for match */
+		if (h->ext_table_support) {
+			for (i = 0; i < num_keys; i++) {
+				if ((hits & (1ULL << i)) != 0)
+					continue;
+				next_bkt = secondary_bkt[i]->next;
+				FOR_EACH_BUCKET(cur_bkt, next_bkt) {
+					if (data != NULL)
+						ret = search_one_bucket_lf(h,
+							keys[i], sig[i],
+							&data[i], cur_bkt);
+					else
+						ret = search_one_bucket_lf(h,
+								keys[i], sig[i],
+								NULL, cur_bkt);
+					if (ret != -1) {
+						positions[i] = ret;
+						hits |= 1ULL << i;
+						break;
+					}
+				}
+			}
+		}
 		/* The loads of sig_current in compare_signatures
 		 * should not move below the load from tbl_chng_cnt.
 		 */
@@ -1988,34 +2076,6 @@ __rte_hash_lookup_bulk_lf(const struct rte_hash *h, const void **keys,
 					__ATOMIC_ACQUIRE);
 	} while (cnt_b != cnt_a);
 
-	/* all found, do not need to go through ext bkt */
-	if ((hits == ((1ULL << num_keys) - 1)) || !h->ext_table_support) {
-		if (hit_mask != NULL)
-			*hit_mask = hits;
-		__hash_rw_reader_unlock(h);
-		return;
-	}
-
-	/* need to check ext buckets for match */
-	for (i = 0; i < num_keys; i++) {
-		if ((hits & (1ULL << i)) != 0)
-			continue;
-		next_bkt = secondary_bkt[i]->next;
-		FOR_EACH_BUCKET(cur_bkt, next_bkt) {
-			if (data != NULL)
-				ret = search_one_bucket_lf(h, keys[i],
-						sig[i], &data[i], cur_bkt);
-			else
-				ret = search_one_bucket_lf(h, keys[i],
-						sig[i], NULL, cur_bkt);
-			if (ret != -1) {
-				positions[i] = ret;
-				hits |= 1ULL << i;
-				break;
-			}
-		}
-	}
-
 	if (hit_mask != NULL)
 		*hit_mask = hits;
 }
diff --git a/lib/librte_hash/rte_cuckoo_hash.h b/lib/librte_hash/rte_cuckoo_hash.h
index eacdaa8d4684..48c85c890712 100644
--- a/lib/librte_hash/rte_cuckoo_hash.h
+++ b/lib/librte_hash/rte_cuckoo_hash.h
@@ -210,6 +210,13 @@ struct rte_hash {
 	rte_rwlock_t *readwrite_lock; /**< Read-write lock thread-safety. */
 	struct rte_hash_bucket *buckets_ext; /**< Extra buckets array */
 	struct rte_ring *free_ext_bkts; /**< Ring of indexes of free buckets */
+	/* Stores index of an empty ext bkt to be recycled on calling
+	 * rte_hash_del_xxx APIs. When lock free read-write concurrency is
+	 * enabled, an empty ext bkt cannot be put into free list immediately
+	 * (as readers might be using it still). Hence freeing of the ext bkt
+	 * is piggy-backed to freeing of the key index.
+	 */
+	uint32_t *ext_bkt_to_free;
 	uint32_t *tbl_chng_cnt;
 	/**< Indicates if the hash table changed from last read. */
 } __rte_cache_aligned;
-- 
2.17.1

Re: [dpdk-dev] [PATCH v2 1/2] hash: add lock free support for extendable bucket

[Wang, Yipeng1]

>-----Original Message-----
>From: Dharmik Thakkar [mailto:dharmik.thakkar@arm.com]
>Sent: Monday, March 25, 2019 2:09 PM
>To: Wang, Yipeng1 <yipeng1.wang@intel.com>; Gobriel, Sameh <sameh.gobriel@intel.com>; Richardson, Bruce
><bruce.richardson@intel.com>; De Lara Guarch, Pablo <pablo.de.lara.guarch@intel.com>; Mcnamara, John
><john.mcnamara@intel.com>; Kovacevic, Marko <marko.kovacevic@intel.com>
>Cc: dev@dpdk.org; Dharmik Thakkar <dharmik.thakkar@arm.com>
>Subject: [PATCH v2 1/2] hash: add lock free support for extendable bucket
>
>This patch enables lock-free read-write concurrency support for
>extendable bucket feature.
>
>Suggested-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
>Signed-off-by: Dharmik Thakkar <dharmik.thakkar@arm.com>
>Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
>Reviewed-by: Gavin Hu <gavin.hu@arm.com>
>Reviewed-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
>@@ -1072,7 +1082,15 @@ __rte_hash_add_key_with_hash(const struct rte_hash *h, const void *key,
> 	bkt_id = (uint32_t)((uintptr_t)ext_bkt_id) - 1;
> 	/* Use the first location of the new bucket */
> 	(h->buckets_ext[bkt_id]).sig_current[0] = short_sig;
>-	(h->buckets_ext[bkt_id]).key_idx[0] = new_idx;
>+	/* Key can be of arbitrary length, so it is
>+	 * not possible to store it atomically.
>+	 * Hence the new key element's memory stores
>+	 * (key as well as data) should be complete
>+	 * before it is referenced.
>+	 */
[Wang, Yipeng] Minor issue: does this comment need to be fixed too? If so you could include my ack for next version.

Acked-by: Yipeng Wang  <yipeng1.wang@intel.com>


Thanks
Yipeng!

Re: [dpdk-dev] [PATCH v2 1/2] hash: add lock free support for extendable bucket

[Wang, Yipeng1]

>-----Original Message-----
>From: Dharmik Thakkar [mailto:dharmik.thakkar@arm.com]
>Sent: Monday, March 25, 2019 2:09 PM
>To: Wang, Yipeng1 <yipeng1.wang@intel.com>; Gobriel, Sameh <sameh.gobriel@intel.com>; Richardson, Bruce
><bruce.richardson@intel.com>; De Lara Guarch, Pablo <pablo.de.lara.guarch@intel.com>; Mcnamara, John
><john.mcnamara@intel.com>; Kovacevic, Marko <marko.kovacevic@intel.com>
>Cc: dev@dpdk.org; Dharmik Thakkar <dharmik.thakkar@arm.com>
>Subject: [PATCH v2 1/2] hash: add lock free support for extendable bucket
>
>This patch enables lock-free read-write concurrency support for
>extendable bucket feature.
>
>Suggested-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
>Signed-off-by: Dharmik Thakkar <dharmik.thakkar@arm.com>
>Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
>Reviewed-by: Gavin Hu <gavin.hu@arm.com>
>Reviewed-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
>@@ -1072,7 +1082,15 @@ __rte_hash_add_key_with_hash(const struct rte_hash *h, const void *key,
> 	bkt_id = (uint32_t)((uintptr_t)ext_bkt_id) - 1;
> 	/* Use the first location of the new bucket */
> 	(h->buckets_ext[bkt_id]).sig_current[0] = short_sig;
>-	(h->buckets_ext[bkt_id]).key_idx[0] = new_idx;
>+	/* Key can be of arbitrary length, so it is
>+	 * not possible to store it atomically.
>+	 * Hence the new key element's memory stores
>+	 * (key as well as data) should be complete
>+	 * before it is referenced.
>+	 */
[Wang, Yipeng] Minor issue: does this comment need to be fixed too? If so you could include my ack for next version.

Acked-by: Yipeng Wang  <yipeng1.wang@intel.com>


Thanks
Yipeng!

Re: [dpdk-dev] [PATCH v2 1/2] hash: add lock free support for extendable bucket

[Dharmik Thakkar]

+Honnappa

Hi Yipeng,

Thank you for the review!

> On Apr 1, 2019, at 1:20 PM, Wang, Yipeng1 <yipeng1.wang@intel.com> wrote:
> 
>> -----Original Message-----
>> From: Dharmik Thakkar [mailto:dharmik.thakkar@arm.com]
>> Sent: Monday, March 25, 2019 2:09 PM
>> To: Wang, Yipeng1 <yipeng1.wang@intel.com>; Gobriel, Sameh <sameh.gobriel@intel.com>; Richardson, Bruce
>> <bruce.richardson@intel.com>; De Lara Guarch, Pablo <pablo.de.lara.guarch@intel.com>; Mcnamara, John
>> <john.mcnamara@intel.com>; Kovacevic, Marko <marko.kovacevic@intel.com>
>> Cc: dev@dpdk.org; Dharmik Thakkar <dharmik.thakkar@arm.com>
>> Subject: [PATCH v2 1/2] hash: add lock free support for extendable bucket
>> 
>> This patch enables lock-free read-write concurrency support for
>> extendable bucket feature.
>> 
>> Suggested-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
>> Signed-off-by: Dharmik Thakkar <dharmik.thakkar@arm.com>
>> Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
>> Reviewed-by: Gavin Hu <gavin.hu@arm.com>
>> Reviewed-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
>> @@ -1072,7 +1082,15 @@ __rte_hash_add_key_with_hash(const struct rte_hash *h, const void *key,
>> 	bkt_id = (uint32_t)((uintptr_t)ext_bkt_id) - 1;
>> 	/* Use the first location of the new bucket */
>> 	(h->buckets_ext[bkt_id]).sig_current[0] = short_sig;
>> -	(h->buckets_ext[bkt_id]).key_idx[0] = new_idx;
>> +	/* Key can be of arbitrary length, so it is
>> +	 * not possible to store it atomically.
>> +	 * Hence the new key element's memory stores
>> +	 * (key as well as data) should be complete
>> +	 * before it is referenced.
>> +	 */
> [Wang, Yipeng] Minor issue: does this comment need to be fixed too? If so you could include my ack for next version.
Yes, I will fix it in the next version. 
> 
> Acked-by: Yipeng Wang  <yipeng1.wang@intel.com>
> 
> 
> Thanks
> Yipeng!
> 

Re: [dpdk-dev] [PATCH v2 1/2] hash: add lock free support for extendable bucket

[Dharmik Thakkar]

+Honnappa

Hi Yipeng,

Thank you for the review!

> On Apr 1, 2019, at 1:20 PM, Wang, Yipeng1 <yipeng1.wang@intel.com> wrote:
> 
>> -----Original Message-----
>> From: Dharmik Thakkar [mailto:dharmik.thakkar@arm.com]
>> Sent: Monday, March 25, 2019 2:09 PM
>> To: Wang, Yipeng1 <yipeng1.wang@intel.com>; Gobriel, Sameh <sameh.gobriel@intel.com>; Richardson, Bruce
>> <bruce.richardson@intel.com>; De Lara Guarch, Pablo <pablo.de.lara.guarch@intel.com>; Mcnamara, John
>> <john.mcnamara@intel.com>; Kovacevic, Marko <marko.kovacevic@intel.com>
>> Cc: dev@dpdk.org; Dharmik Thakkar <dharmik.thakkar@arm.com>
>> Subject: [PATCH v2 1/2] hash: add lock free support for extendable bucket
>> 
>> This patch enables lock-free read-write concurrency support for
>> extendable bucket feature.
>> 
>> Suggested-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
>> Signed-off-by: Dharmik Thakkar <dharmik.thakkar@arm.com>
>> Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
>> Reviewed-by: Gavin Hu <gavin.hu@arm.com>
>> Reviewed-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
>> @@ -1072,7 +1082,15 @@ __rte_hash_add_key_with_hash(const struct rte_hash *h, const void *key,
>> 	bkt_id = (uint32_t)((uintptr_t)ext_bkt_id) - 1;
>> 	/* Use the first location of the new bucket */
>> 	(h->buckets_ext[bkt_id]).sig_current[0] = short_sig;
>> -	(h->buckets_ext[bkt_id]).key_idx[0] = new_idx;
>> +	/* Key can be of arbitrary length, so it is
>> +	 * not possible to store it atomically.
>> +	 * Hence the new key element's memory stores
>> +	 * (key as well as data) should be complete
>> +	 * before it is referenced.
>> +	 */
> [Wang, Yipeng] Minor issue: does this comment need to be fixed too? If so you could include my ack for next version.
Yes, I will fix it in the next version. 
> 
> Acked-by: Yipeng Wang  <yipeng1.wang@intel.com>
> 
> 
> Thanks
> Yipeng!
> 

[dpdk-dev] [PATCH v2 2/2] test/hash: lock-free rw concurrency test ext bkt

[Dharmik Thakkar]

Add unit test to check for hash lookup and bulk-lookup perf.
Test with lock-free enabled and with lock-free disabled.

Test include:

- hash lookup on keys in ext bkt,
hash delete causing key-shifts of keys from ext bkt to secondary bkt

Suggested-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
Signed-off-by: Dharmik Thakkar <dharmik.thakkar@arm.com>
---
 app/test/test_hash_readwrite_lf.c | 350 ++++++++++++++++++++++++------
 1 file changed, 284 insertions(+), 66 deletions(-)

diff --git a/app/test/test_hash_readwrite_lf.c b/app/test/test_hash_readwrite_lf.c
index cbfd9322696b..ddd8d7aa6a7d 100644
--- a/app/test/test_hash_readwrite_lf.c
+++ b/app/test/test_hash_readwrite_lf.c
@@ -41,6 +41,12 @@
 #define READ_PASS_SHIFT_PATH 4
 #define READ_PASS_NON_SHIFT_PATH 8
 #define BULK_LOOKUP 16
+#define READ_PASS_KEY_SHIFTS_EXTBKT 32
+
+#define WRITE_NO_KEY_SHIFT 0
+#define WRITE_KEY_SHIFT 1
+#define WRITE_EXT_BKT 2
+
 #define NUM_TEST 3
 unsigned int rwc_core_cnt[NUM_TEST] = {1, 2, 4};
 
@@ -51,6 +57,7 @@ struct rwc_perf {
 	uint32_t w_ks_r_hit_sp[2][NUM_TEST];
 	uint32_t w_ks_r_miss[2][NUM_TEST];
 	uint32_t multi_rw[NUM_TEST - 1][2][NUM_TEST];
+	uint32_t w_ks_r_hit_extbkt[2][NUM_TEST];
 };
 
 static struct rwc_perf rwc_lf_results, rwc_non_lf_results;
@@ -62,11 +69,15 @@ struct {
 	uint32_t *keys_absent;
 	uint32_t *keys_shift_path;
 	uint32_t *keys_non_shift_path;
+	uint32_t *keys_ext_bkt;
+	uint32_t *keys_ks_extbkt;
 	uint32_t count_keys_no_ks;
 	uint32_t count_keys_ks;
 	uint32_t count_keys_absent;
 	uint32_t count_keys_shift_path;
 	uint32_t count_keys_non_shift_path;
+	uint32_t count_keys_extbkt;
+	uint32_t count_keys_ks_extbkt;
 	uint32_t single_insert;
 	struct rte_hash *h;
 } tbl_rwc_test_param;
@@ -81,6 +92,35 @@ uint16_t enabled_core_ids[RTE_MAX_LCORE];
 
 uint8_t *scanned_bkts;
 
+static inline uint16_t
+get_short_sig(const hash_sig_t hash)
+{
+	return hash >> 16;
+}
+
+static inline uint32_t
+get_prim_bucket_index(__attribute__((unused)) const struct rte_hash *h,
+		      const hash_sig_t hash)
+{
+	uint32_t num_buckets;
+	uint32_t bucket_bitmask;
+	num_buckets  = rte_align32pow2(TOTAL_ENTRY) / 8;
+	bucket_bitmask = num_buckets - 1;
+	return hash & bucket_bitmask;
+}
+
+static inline uint32_t
+get_alt_bucket_index(__attribute__((unused)) const struct rte_hash *h,
+			uint32_t cur_bkt_idx, uint16_t sig)
+{
+	uint32_t num_buckets;
+	uint32_t bucket_bitmask;
+	num_buckets  = rte_align32pow2(TOTAL_ENTRY) / 8;
+	bucket_bitmask = num_buckets - 1;
+	return (cur_bkt_idx ^ sig) & bucket_bitmask;
+}
+
+
 static inline int
 get_enabled_cores_list(void)
 {
@@ -168,9 +208,12 @@ generate_keys(void)
 	uint32_t *keys_ks = NULL;
 	uint32_t *keys_absent = NULL;
 	uint32_t *keys_non_shift_path = NULL;
+	uint32_t *keys_ext_bkt = NULL;
+	uint32_t *keys_ks_extbkt = NULL;
 	uint32_t *found = NULL;
 	uint32_t count_keys_no_ks = 0;
 	uint32_t count_keys_ks = 0;
+	uint32_t count_keys_extbkt = 0;
 	uint32_t i;
 
 	/*
@@ -251,14 +294,32 @@ generate_keys(void)
 		goto err;
 	}
 
+	/*
+	 * This consist of keys which will be stored in extended buckets
+	 */
+	keys_ext_bkt = rte_malloc(NULL, sizeof(uint32_t) * TOTAL_INSERT, 0);
+	if (keys_ext_bkt == NULL) {
+		printf("RTE_MALLOC failed\n");
+		goto err;
+	}
+
+	/*
+	 * This consist of keys which when deleted causes shifting of keys
+	 * in extended buckets to respective secondary buckets
+	 */
+	keys_ks_extbkt = rte_malloc(NULL, sizeof(uint32_t) * TOTAL_INSERT, 0);
+	if (keys_ks_extbkt == NULL) {
+		printf("RTE_MALLOC failed\n");
+		goto err;
+	}
 
 	hash_sig_t sig;
 	uint32_t prim_bucket_idx;
-	int ret;
+	uint32_t sec_bucket_idx;
+	uint16_t short_sig;
 	uint32_t num_buckets;
-	uint32_t bucket_bitmask;
 	num_buckets  = rte_align32pow2(TOTAL_ENTRY) / 8;
-	bucket_bitmask = num_buckets - 1;
+	int ret;
 
 	/*
 	 * Used to mark bkts in which at least one key was shifted to its
@@ -275,6 +336,8 @@ generate_keys(void)
 	tbl_rwc_test_param.keys_ks = keys_ks;
 	tbl_rwc_test_param.keys_absent = keys_absent;
 	tbl_rwc_test_param.keys_non_shift_path = keys_non_shift_path;
+	tbl_rwc_test_param.keys_ext_bkt = keys_ext_bkt;
+	tbl_rwc_test_param.keys_ks_extbkt = keys_ks_extbkt;
 	/* Generate keys by adding previous two keys, neglect overflow */
 	printf("Generating keys...\n");
 	keys[0] = 0;
@@ -287,7 +350,8 @@ generate_keys(void)
 		/* Check if primary bucket has space.*/
 		sig = rte_hash_hash(tbl_rwc_test_param.h,
 					tbl_rwc_test_param.keys+i);
-		prim_bucket_idx = sig & bucket_bitmask;
+		prim_bucket_idx = get_prim_bucket_index(tbl_rwc_test_param.h,
+							sig);
 		ret = check_bucket(prim_bucket_idx, keys[i]);
 		if (ret < 0) {
 			/*
@@ -368,6 +432,47 @@ generate_keys(void)
 	tbl_rwc_test_param.count_keys_absent = count_keys_absent;
 	tbl_rwc_test_param.count_keys_non_shift_path = count;
 
+	memset(scanned_bkts, 0, num_buckets);
+	count = 0;
+	/* Find keys that will be in extended buckets */
+	for (i = 0; i < count_keys_ks; i++) {
+		ret = rte_hash_add_key(tbl_rwc_test_param.h, keys_ks + i);
+		if (ret < 0) {
+			/* Key will be added to ext bkt */
+			keys_ext_bkt[count_keys_extbkt++] = keys_ks[i];
+			/* Sec bkt to be added to keys_ks_extbkt */
+			sig = rte_hash_hash(tbl_rwc_test_param.h,
+					tbl_rwc_test_param.keys_ks + i);
+			prim_bucket_idx = get_prim_bucket_index(
+						tbl_rwc_test_param.h, sig);
+			short_sig = get_short_sig(sig);
+			sec_bucket_idx = get_alt_bucket_index(
+						tbl_rwc_test_param.h,
+						prim_bucket_idx, short_sig);
+			if (scanned_bkts[sec_bucket_idx] == 0)
+				scanned_bkts[sec_bucket_idx] = 1;
+		}
+	}
+
+	/* Find keys that will shift keys in ext bucket*/
+	for (i = 0; i < num_buckets; i++) {
+		if (scanned_bkts[i] == 1) {
+			iter = i * 8;
+			while (rte_hash_iterate(tbl_rwc_test_param.h,
+				&next_key, &next_data, &iter) >= 0) {
+				/* Check if key belongs to the current bucket */
+				if (i >= (iter-1)/8)
+					keys_ks_extbkt[count++]
+						= *(const uint32_t *)next_key;
+				else
+					break;
+			}
+		}
+	}
+
+	tbl_rwc_test_param.count_keys_ks_extbkt = count;
+	tbl_rwc_test_param.count_keys_extbkt = count_keys_extbkt;
+
 	printf("\nCount of keys NOT causing shifting of existing keys to "
 	"alternate location: %d\n", tbl_rwc_test_param.count_keys_no_ks);
 	printf("\nCount of keys causing shifting of existing keys to alternate "
@@ -378,6 +483,10 @@ generate_keys(void)
 	       tbl_rwc_test_param.count_keys_shift_path);
 	printf("Count of keys not likely to be on the shift path: %d\n\n",
 	       tbl_rwc_test_param.count_keys_non_shift_path);
+	printf("Count of keys in extended buckets: %d\n\n",
+	       tbl_rwc_test_param.count_keys_extbkt);
+	printf("Count of keys shifting keys in ext buckets: %d\n\n",
+	       tbl_rwc_test_param.count_keys_ks_extbkt);
 
 	rte_free(found);
 	rte_hash_free(tbl_rwc_test_param.h);
@@ -390,12 +499,14 @@ generate_keys(void)
 	rte_free(keys_absent);
 	rte_free(found);
 	rte_free(tbl_rwc_test_param.keys_shift_path);
+	rte_free(keys_ext_bkt);
+	rte_free(keys_ks_extbkt);
 	rte_free(scanned_bkts);
 	return -1;
 }
 
 static int
-init_params(int rwc_lf, int use_jhash, int htm)
+init_params(int rwc_lf, int use_jhash, int htm, int ext_bkt)
 {
 	struct rte_hash *handle;
 
@@ -425,6 +536,9 @@ init_params(int rwc_lf, int use_jhash, int htm)
 			RTE_HASH_EXTRA_FLAGS_RW_CONCURRENCY |
 			RTE_HASH_EXTRA_FLAGS_MULTI_WRITER_ADD;
 
+	if (ext_bkt)
+		hash_params.extra_flag |= RTE_HASH_EXTRA_FLAGS_EXT_TABLE;
+
 	hash_params.name = "tests";
 
 	handle = rte_hash_create(&hash_params);
@@ -452,7 +566,7 @@ test_rwc_reader(__attribute__((unused)) void *arg)
 	void *temp_a[BULK_LOOKUP_SIZE];
 
 	/* Used to identify keys not inserted in the hash table */
-	pos = rte_zmalloc(NULL, sizeof(uint32_t) * BULK_LOOKUP_SIZE, 0);
+	pos = rte_malloc(NULL, sizeof(uint32_t) * BULK_LOOKUP_SIZE, 0);
 	if (pos == NULL) {
 		printf("RTE_MALLOC failed\n");
 		return -1;
@@ -467,6 +581,9 @@ test_rwc_reader(__attribute__((unused)) void *arg)
 	} else if (read_type & READ_PASS_SHIFT_PATH) {
 		keys = tbl_rwc_test_param.keys_shift_path;
 		read_cnt = tbl_rwc_test_param.count_keys_shift_path;
+	} else if (read_type & READ_PASS_KEY_SHIFTS_EXTBKT) {
+		keys = tbl_rwc_test_param.keys_ext_bkt;
+		read_cnt = tbl_rwc_test_param.count_keys_extbkt;
 	} else {
 		keys = tbl_rwc_test_param.keys_non_shift_path;
 		read_cnt = tbl_rwc_test_param.count_keys_non_shift_path;
@@ -482,7 +599,6 @@ test_rwc_reader(__attribute__((unused)) void *arg)
 				/* Array of  pointer to the list of keys */
 				for (j = 0; j < BULK_LOOKUP_SIZE; j++)
 					temp_a[j] = keys + i + j;
-
 				rte_hash_lookup_bulk(tbl_rwc_test_param.h,
 						   (const void **)
 						   ((uintptr_t)temp_a),
@@ -539,22 +655,25 @@ test_rwc_reader(__attribute__((unused)) void *arg)
 }
 
 static int
-write_keys(uint8_t key_shift)
+write_keys(uint8_t write_type)
 {
 	uint32_t i;
 	int ret;
 	uint32_t key_cnt;
 	uint32_t *keys;
-	if (key_shift) {
+	if (write_type == WRITE_KEY_SHIFT) {
 		key_cnt = tbl_rwc_test_param.count_keys_ks;
 		keys = tbl_rwc_test_param.keys_ks;
-	} else {
+	} else if (write_type == WRITE_NO_KEY_SHIFT) {
 		key_cnt = tbl_rwc_test_param.count_keys_no_ks;
 		keys = tbl_rwc_test_param.keys_no_ks;
+	} else if (write_type == WRITE_EXT_BKT) {
+		key_cnt = tbl_rwc_test_param.count_keys_extbkt;
+		keys = tbl_rwc_test_param.keys_ext_bkt;
 	}
 	for (i = 0; i < key_cnt; i++) {
 		ret = rte_hash_add_key(tbl_rwc_test_param.h, keys + i);
-		if (!key_shift && ret < 0) {
+		if ((write_type == WRITE_NO_KEY_SHIFT) && ret < 0) {
 			printf("writer failed %"PRIu32"\n", i);
 			return -1;
 		}
@@ -581,18 +700,18 @@ test_rwc_multi_writer(__attribute__((unused)) void *arg)
  */
 static int
 test_hash_add_no_ks_lookup_hit(struct rwc_perf *rwc_perf_results, int rwc_lf,
-				int htm)
+				int htm, int ext_bkt)
 {
 	unsigned int n, m;
 	uint64_t i;
 	int use_jhash = 0;
-	uint8_t key_shift = 0;
+	uint8_t write_type = WRITE_NO_KEY_SHIFT;
 	uint8_t read_type = READ_PASS_NO_KEY_SHIFTS;
 
 	rte_atomic64_init(&greads);
 	rte_atomic64_init(&gread_cycles);
 
-	if (init_params(rwc_lf, use_jhash, htm) != 0)
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
 		goto err;
 	printf("\nTest: Hash add - no key-shifts, read - hit\n");
 	for (m = 0; m < 2; m++) {
@@ -612,7 +731,7 @@ test_hash_add_no_ks_lookup_hit(struct rwc_perf *rwc_perf_results, int rwc_lf,
 
 			rte_hash_reset(tbl_rwc_test_param.h);
 			writer_done = 0;
-			if (write_keys(key_shift) < 0)
+			if (write_keys(write_type) < 0)
 				goto err;
 			writer_done = 1;
 			for (i = 1; i <= rwc_core_cnt[n]; i++)
@@ -650,19 +769,19 @@ test_hash_add_no_ks_lookup_hit(struct rwc_perf *rwc_perf_results, int rwc_lf,
  */
 static int
 test_hash_add_no_ks_lookup_miss(struct rwc_perf *rwc_perf_results, int rwc_lf,
-				int htm)
+				int htm, int ext_bkt)
 {
 	unsigned int n, m;
 	uint64_t i;
 	int use_jhash = 0;
-	uint8_t key_shift = 0;
+	uint8_t write_type = WRITE_NO_KEY_SHIFT;
 	uint8_t read_type = READ_FAIL;
 	int ret;
 
 	rte_atomic64_init(&greads);
 	rte_atomic64_init(&gread_cycles);
 
-	if (init_params(rwc_lf, use_jhash, htm) != 0)
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
 		goto err;
 	printf("\nTest: Hash add - no key-shifts, Hash lookup - miss\n");
 	for (m = 0; m < 2; m++) {
@@ -687,7 +806,7 @@ test_hash_add_no_ks_lookup_miss(struct rwc_perf *rwc_perf_results, int rwc_lf,
 				rte_eal_remote_launch(test_rwc_reader,
 						(void *)(uintptr_t)read_type,
 							enabled_core_ids[i]);
-			ret = write_keys(key_shift);
+			ret = write_keys(write_type);
 			writer_done = 1;
 			rte_eal_mp_wait_lcore();
 
@@ -722,19 +841,19 @@ test_hash_add_no_ks_lookup_miss(struct rwc_perf *rwc_perf_results, int rwc_lf,
  */
 static int
 test_hash_add_ks_lookup_hit_non_sp(struct rwc_perf *rwc_perf_results,
-				    int rwc_lf, int htm)
+				    int rwc_lf, int htm, int ext_bkt)
 {
 	unsigned int n, m;
 	uint64_t i;
 	int use_jhash = 0;
 	int ret;
-	uint8_t key_shift;
+	uint8_t write_type;
 	uint8_t read_type = READ_PASS_NON_SHIFT_PATH;
 
 	rte_atomic64_init(&greads);
 	rte_atomic64_init(&gread_cycles);
 
-	if (init_params(rwc_lf, use_jhash, htm) != 0)
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
 		goto err;
 	printf("\nTest: Hash add - key shift, Hash lookup - hit"
 	       " (non-shift-path)\n");
@@ -755,15 +874,15 @@ test_hash_add_ks_lookup_hit_non_sp(struct rwc_perf *rwc_perf_results,
 
 			rte_hash_reset(tbl_rwc_test_param.h);
 			writer_done = 0;
-			key_shift = 0;
-			if (write_keys(key_shift) < 0)
+			write_type = WRITE_NO_KEY_SHIFT;
+			if (write_keys(write_type) < 0)
 				goto err;
 			for (i = 1; i <= rwc_core_cnt[n]; i++)
 				rte_eal_remote_launch(test_rwc_reader,
 						(void *)(uintptr_t)read_type,
 							enabled_core_ids[i]);
-			key_shift = 1;
-			ret = write_keys(key_shift);
+			write_type = WRITE_KEY_SHIFT;
+			ret = write_keys(write_type);
 			writer_done = 1;
 			rte_eal_mp_wait_lcore();
 
@@ -798,19 +917,19 @@ test_hash_add_ks_lookup_hit_non_sp(struct rwc_perf *rwc_perf_results,
  */
 static int
 test_hash_add_ks_lookup_hit_sp(struct rwc_perf *rwc_perf_results, int rwc_lf,
-				int htm)
+				int htm, int ext_bkt)
 {
 	unsigned int n, m;
 	uint64_t i;
 	int use_jhash = 0;
 	int ret;
-	uint8_t key_shift;
+	uint8_t write_type;
 	uint8_t read_type = READ_PASS_SHIFT_PATH;
 
 	rte_atomic64_init(&greads);
 	rte_atomic64_init(&gread_cycles);
 
-	if (init_params(rwc_lf, use_jhash, htm) != 0)
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
 		goto err;
 	printf("\nTest: Hash add - key shift, Hash lookup - hit (shift-path)"
 	       "\n");
@@ -831,15 +950,15 @@ test_hash_add_ks_lookup_hit_sp(struct rwc_perf *rwc_perf_results, int rwc_lf,
 
 			rte_hash_reset(tbl_rwc_test_param.h);
 			writer_done = 0;
-			key_shift = 0;
-			if (write_keys(key_shift) < 0)
+			write_type = WRITE_NO_KEY_SHIFT;
+			if (write_keys(write_type) < 0)
 				goto err;
 			for (i = 1; i <= rwc_core_cnt[n]; i++)
 				rte_eal_remote_launch(test_rwc_reader,
 						(void *)(uintptr_t)read_type,
 						enabled_core_ids[i]);
-			key_shift = 1;
-			ret = write_keys(key_shift);
+			write_type = WRITE_KEY_SHIFT;
+			ret = write_keys(write_type);
 			writer_done = 1;
 			rte_eal_mp_wait_lcore();
 
@@ -874,19 +993,19 @@ test_hash_add_ks_lookup_hit_sp(struct rwc_perf *rwc_perf_results, int rwc_lf,
  */
 static int
 test_hash_add_ks_lookup_miss(struct rwc_perf *rwc_perf_results, int rwc_lf, int
-			     htm)
+			     htm, int ext_bkt)
 {
 	unsigned int n, m;
 	uint64_t i;
 	int use_jhash = 0;
 	int ret;
-	uint8_t key_shift;
+	uint8_t write_type;
 	uint8_t read_type = READ_FAIL;
 
 	rte_atomic64_init(&greads);
 	rte_atomic64_init(&gread_cycles);
 
-	if (init_params(rwc_lf, use_jhash, htm) != 0)
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
 		goto err;
 	printf("\nTest: Hash add - key shift, Hash lookup - miss\n");
 	for (m = 0; m < 2; m++) {
@@ -906,15 +1025,15 @@ test_hash_add_ks_lookup_miss(struct rwc_perf *rwc_perf_results, int rwc_lf, int
 
 			rte_hash_reset(tbl_rwc_test_param.h);
 			writer_done = 0;
-			key_shift = 0;
-			if (write_keys(key_shift) < 0)
+			write_type = WRITE_NO_KEY_SHIFT;
+			if (write_keys(write_type) < 0)
 				goto err;
 			for (i = 1; i <= rwc_core_cnt[n]; i++)
 				rte_eal_remote_launch(test_rwc_reader,
 						(void *)(uintptr_t)read_type,
 							enabled_core_ids[i]);
-			key_shift = 1;
-			ret = write_keys(key_shift);
+			write_type = WRITE_KEY_SHIFT;
+			ret = write_keys(write_type);
 			writer_done = 1;
 			rte_eal_mp_wait_lcore();
 
@@ -949,18 +1068,18 @@ test_hash_add_ks_lookup_miss(struct rwc_perf *rwc_perf_results, int rwc_lf, int
  */
 static int
 test_hash_multi_add_lookup(struct rwc_perf *rwc_perf_results, int rwc_lf,
-			   int htm)
+			   int htm, int ext_bkt)
 {
 	unsigned int n, m, k;
 	uint64_t i;
 	int use_jhash = 0;
-	uint8_t key_shift;
+	uint8_t write_type;
 	uint8_t read_type = READ_PASS_SHIFT_PATH;
 
 	rte_atomic64_init(&greads);
 	rte_atomic64_init(&gread_cycles);
 
-	if (init_params(rwc_lf, use_jhash, htm) != 0)
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
 		goto err;
 	printf("\nTest: Multi-add-lookup\n");
 	uint8_t pos_core;
@@ -991,8 +1110,8 @@ test_hash_multi_add_lookup(struct rwc_perf *rwc_perf_results, int rwc_lf,
 				writer_done = 0;
 				for (i = 0; i < 4; i++)
 					multi_writer_done[i] = 0;
-				key_shift = 0;
-				if (write_keys(key_shift) < 0)
+				write_type = WRITE_NO_KEY_SHIFT;
+				if (write_keys(write_type) < 0)
 					goto err;
 
 				/* Launch reader(s) */
@@ -1000,7 +1119,7 @@ test_hash_multi_add_lookup(struct rwc_perf *rwc_perf_results, int rwc_lf,
 					rte_eal_remote_launch(test_rwc_reader,
 						(void *)(uintptr_t)read_type,
 						enabled_core_ids[i]);
-				key_shift = 1;
+				write_type = WRITE_KEY_SHIFT;
 				pos_core = 0;
 
 				/* Launch writers */
@@ -1045,6 +1164,88 @@ test_hash_multi_add_lookup(struct rwc_perf *rwc_perf_results, int rwc_lf,
 	return -1;
 }
 
+/*
+ * Test lookup perf:
+ * Reader(s) lookup keys present in the extendable bkt.
+ */
+static int
+test_hash_add_ks_lookup_hit_extbkt(struct rwc_perf *rwc_perf_results,
+				int rwc_lf, int htm, int ext_bkt)
+{
+	unsigned int n, m;
+	uint64_t i;
+	int use_jhash = 0;
+	uint8_t write_type;
+	uint8_t read_type = READ_PASS_KEY_SHIFTS_EXTBKT;
+
+	rte_atomic64_init(&greads);
+	rte_atomic64_init(&gread_cycles);
+
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
+		goto err;
+	printf("\nTest: Hash add - key-shifts, read - hit (ext_bkt)\n");
+	for (m = 0; m < 2; m++) {
+		if (m == 1) {
+			printf("\n** With bulk-lookup **\n");
+			read_type |= BULK_LOOKUP;
+		}
+		for (n = 0; n < NUM_TEST; n++) {
+			unsigned int tot_lcore = rte_lcore_count();
+			if (tot_lcore < rwc_core_cnt[n] + 1)
+				goto finish;
+
+			printf("\nNumber of readers: %u\n", rwc_core_cnt[n]);
+
+			rte_atomic64_clear(&greads);
+			rte_atomic64_clear(&gread_cycles);
+
+			rte_hash_reset(tbl_rwc_test_param.h);
+			write_type = WRITE_NO_KEY_SHIFT;
+			if (write_keys(write_type) < 0)
+				goto err;
+			write_type = WRITE_KEY_SHIFT;
+			if (write_keys(write_type) < 0)
+				goto err;
+			writer_done = 0;
+			for (i = 1; i <= rwc_core_cnt[n]; i++)
+				rte_eal_remote_launch(test_rwc_reader,
+						(void *)(uintptr_t)read_type,
+							enabled_core_ids[i]);
+			for (i = 0; i < tbl_rwc_test_param.count_keys_ks_extbkt;
+			     i++) {
+				if (rte_hash_del_key(tbl_rwc_test_param.h,
+					tbl_rwc_test_param.keys_ks_extbkt + i)
+							< 0) {
+					printf("Delete Failed: %u\n",
+					tbl_rwc_test_param.keys_ks_extbkt[i]);
+					goto err;
+				}
+			}
+			writer_done = 1;
+			rte_eal_mp_wait_lcore();
+
+			for (i = 1; i <= rwc_core_cnt[n]; i++)
+				if (lcore_config[i].ret < 0)
+					goto err;
+
+			unsigned long long cycles_per_lookup =
+				rte_atomic64_read(&gread_cycles) /
+				rte_atomic64_read(&greads);
+			rwc_perf_results->w_ks_r_hit_extbkt[m][n]
+						= cycles_per_lookup;
+			printf("Cycles per lookup: %llu\n", cycles_per_lookup);
+		}
+	}
+
+finish:
+	rte_hash_free(tbl_rwc_test_param.h);
+	return 0;
+
+err:
+	rte_hash_free(tbl_rwc_test_param.h);
+	return -1;
+}
+
 static int
 test_hash_readwrite_lf_main(void)
 {
@@ -1057,6 +1258,7 @@ test_hash_readwrite_lf_main(void)
 	int rwc_lf = 0;
 	int htm;
 	int use_jhash = 0;
+	int ext_bkt = 0;
 	if (rte_lcore_count() == 1) {
 		printf("More than one lcore is required "
 			"to do read write lock-free concurrency test\n");
@@ -1070,7 +1272,7 @@ test_hash_readwrite_lf_main(void)
 	else
 		htm = 0;
 
-	if (init_params(rwc_lf, use_jhash, htm) != 0)
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
 		return -1;
 	if (generate_keys() != 0)
 		return -1;
@@ -1079,25 +1281,29 @@ test_hash_readwrite_lf_main(void)
 
 	if (RTE_HASH_EXTRA_FLAGS_RW_CONCURRENCY_LF) {
 		rwc_lf = 1;
+		ext_bkt = 1;
 		printf("Test lookup with read-write concurrency lock free support"
 		       " enabled\n");
 		if (test_hash_add_no_ks_lookup_hit(&rwc_lf_results, rwc_lf,
-							htm) < 0)
+							htm, ext_bkt) < 0)
 			return -1;
 		if (test_hash_add_no_ks_lookup_miss(&rwc_lf_results, rwc_lf,
-							htm) < 0)
+							htm, ext_bkt) < 0)
 			return -1;
 		if (test_hash_add_ks_lookup_hit_non_sp(&rwc_lf_results, rwc_lf,
-							htm) < 0)
+							htm, ext_bkt) < 0)
 			return -1;
 		if (test_hash_add_ks_lookup_hit_sp(&rwc_lf_results, rwc_lf,
-							htm) < 0)
+							htm, ext_bkt) < 0)
 			return -1;
-		if (test_hash_add_ks_lookup_miss(&rwc_lf_results, rwc_lf, htm)
-							< 0)
+		if (test_hash_add_ks_lookup_miss(&rwc_lf_results, rwc_lf, htm,
+						 ext_bkt) < 0)
 			return -1;
-		if (test_hash_multi_add_lookup(&rwc_lf_results, rwc_lf, htm)
-							< 0)
+		if (test_hash_multi_add_lookup(&rwc_lf_results, rwc_lf, htm,
+					       ext_bkt) < 0)
+			return -1;
+		if (test_hash_add_ks_lookup_hit_extbkt(&rwc_lf_results, rwc_lf,
+							htm, ext_bkt) < 0)
 			return -1;
 	}
 	printf("\nTest lookup with read-write concurrency lock free support"
@@ -1112,21 +1318,26 @@ test_hash_readwrite_lf_main(void)
 		}
 	} else
 		printf("With HTM Enabled\n");
-	if (test_hash_add_no_ks_lookup_hit(&rwc_non_lf_results, rwc_lf, htm)
-						< 0)
+	if (test_hash_add_no_ks_lookup_hit(&rwc_non_lf_results, rwc_lf, htm,
+					   ext_bkt) < 0)
 		return -1;
-	if (test_hash_add_no_ks_lookup_miss(&rwc_non_lf_results, rwc_lf, htm)
-						< 0)
+	if (test_hash_add_no_ks_lookup_miss(&rwc_non_lf_results, rwc_lf, htm,
+						ext_bkt) < 0)
 		return -1;
 	if (test_hash_add_ks_lookup_hit_non_sp(&rwc_non_lf_results, rwc_lf,
-						htm) < 0)
+						htm, ext_bkt) < 0)
+		return -1;
+	if (test_hash_add_ks_lookup_hit_sp(&rwc_non_lf_results, rwc_lf, htm,
+						ext_bkt) < 0)
 		return -1;
-	if (test_hash_add_ks_lookup_hit_sp(&rwc_non_lf_results, rwc_lf, htm)
-						< 0)
+	if (test_hash_add_ks_lookup_miss(&rwc_non_lf_results, rwc_lf, htm,
+					 ext_bkt) < 0)
 		return -1;
-	if (test_hash_add_ks_lookup_miss(&rwc_non_lf_results, rwc_lf, htm) < 0)
+	if (test_hash_multi_add_lookup(&rwc_non_lf_results, rwc_lf, htm,
+							ext_bkt) < 0)
 		return -1;
-	if (test_hash_multi_add_lookup(&rwc_non_lf_results, rwc_lf, htm) < 0)
+	if (test_hash_add_ks_lookup_hit_extbkt(&rwc_non_lf_results, rwc_lf,
+						htm, ext_bkt) < 0)
 		return -1;
 results:
 	printf("\n\t\t\t\t\t\t********** Results summary **********\n\n");
@@ -1158,8 +1369,11 @@ test_hash_readwrite_lf_main(void)
 			       "(shift-path)\t\t%u\n\t\t\t\t\t\t\t\t",
 			       rwc_lf_results.w_ks_r_hit_sp[j][i]);
 			printf("Hash add - key-shifts, Hash lookup miss\t\t\t\t"
-				"%u\n\n\t\t\t\t",
+				"%u\n\t\t\t\t\t\t\t\t",
 				rwc_lf_results.w_ks_r_miss[j][i]);
+			printf("Hash add - key-shifts, Hash lookup hit (ext_bkt)\t\t"
+				"%u\n\n\t\t\t\t",
+				rwc_lf_results.w_ks_r_hit_extbkt[j][i]);
 
 			printf("Disabled\t");
 			if (htm)
@@ -1179,7 +1393,11 @@ test_hash_readwrite_lf_main(void)
 			       "(shift-path)\t\t%u\n\t\t\t\t\t\t\t\t",
 			       rwc_non_lf_results.w_ks_r_hit_sp[j][i]);
 			printf("Hash add - key-shifts, Hash lookup miss\t\t\t\t"
-			       "%u\n", rwc_non_lf_results.w_ks_r_miss[j][i]);
+			       "%u\n\t\t\t\t\t\t\t\t",
+			       rwc_non_lf_results.w_ks_r_miss[j][i]);
+			printf("Hash add - key-shifts, Hash lookup hit (ext_bkt)\t\t"
+				"%u\n",
+				rwc_non_lf_results.w_ks_r_hit_extbkt[j][i]);
 
 			printf("_______\t\t_______\t\t_________\t___\t\t"
 			       "_________\t\t\t\t\t\t_________________\n");
-- 
2.17.1

[dpdk-dev] [PATCH v2 2/2] test/hash: lock-free rw concurrency test ext bkt

[Dharmik Thakkar]

Add unit test to check for hash lookup and bulk-lookup perf.
Test with lock-free enabled and with lock-free disabled.

Test include:

- hash lookup on keys in ext bkt,
hash delete causing key-shifts of keys from ext bkt to secondary bkt

Suggested-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
Signed-off-by: Dharmik Thakkar <dharmik.thakkar@arm.com>
---
 app/test/test_hash_readwrite_lf.c | 350 ++++++++++++++++++++++++------
 1 file changed, 284 insertions(+), 66 deletions(-)

diff --git a/app/test/test_hash_readwrite_lf.c b/app/test/test_hash_readwrite_lf.c
index cbfd9322696b..ddd8d7aa6a7d 100644
--- a/app/test/test_hash_readwrite_lf.c
+++ b/app/test/test_hash_readwrite_lf.c
@@ -41,6 +41,12 @@
 #define READ_PASS_SHIFT_PATH 4
 #define READ_PASS_NON_SHIFT_PATH 8
 #define BULK_LOOKUP 16
+#define READ_PASS_KEY_SHIFTS_EXTBKT 32
+
+#define WRITE_NO_KEY_SHIFT 0
+#define WRITE_KEY_SHIFT 1
+#define WRITE_EXT_BKT 2
+
 #define NUM_TEST 3
 unsigned int rwc_core_cnt[NUM_TEST] = {1, 2, 4};
 
@@ -51,6 +57,7 @@ struct rwc_perf {
 	uint32_t w_ks_r_hit_sp[2][NUM_TEST];
 	uint32_t w_ks_r_miss[2][NUM_TEST];
 	uint32_t multi_rw[NUM_TEST - 1][2][NUM_TEST];
+	uint32_t w_ks_r_hit_extbkt[2][NUM_TEST];
 };
 
 static struct rwc_perf rwc_lf_results, rwc_non_lf_results;
@@ -62,11 +69,15 @@ struct {
 	uint32_t *keys_absent;
 	uint32_t *keys_shift_path;
 	uint32_t *keys_non_shift_path;
+	uint32_t *keys_ext_bkt;
+	uint32_t *keys_ks_extbkt;
 	uint32_t count_keys_no_ks;
 	uint32_t count_keys_ks;
 	uint32_t count_keys_absent;
 	uint32_t count_keys_shift_path;
 	uint32_t count_keys_non_shift_path;
+	uint32_t count_keys_extbkt;
+	uint32_t count_keys_ks_extbkt;
 	uint32_t single_insert;
 	struct rte_hash *h;
 } tbl_rwc_test_param;
@@ -81,6 +92,35 @@ uint16_t enabled_core_ids[RTE_MAX_LCORE];
 
 uint8_t *scanned_bkts;
 
+static inline uint16_t
+get_short_sig(const hash_sig_t hash)
+{
+	return hash >> 16;
+}
+
+static inline uint32_t
+get_prim_bucket_index(__attribute__((unused)) const struct rte_hash *h,
+		      const hash_sig_t hash)
+{
+	uint32_t num_buckets;
+	uint32_t bucket_bitmask;
+	num_buckets  = rte_align32pow2(TOTAL_ENTRY) / 8;
+	bucket_bitmask = num_buckets - 1;
+	return hash & bucket_bitmask;
+}
+
+static inline uint32_t
+get_alt_bucket_index(__attribute__((unused)) const struct rte_hash *h,
+			uint32_t cur_bkt_idx, uint16_t sig)
+{
+	uint32_t num_buckets;
+	uint32_t bucket_bitmask;
+	num_buckets  = rte_align32pow2(TOTAL_ENTRY) / 8;
+	bucket_bitmask = num_buckets - 1;
+	return (cur_bkt_idx ^ sig) & bucket_bitmask;
+}
+
+
 static inline int
 get_enabled_cores_list(void)
 {
@@ -168,9 +208,12 @@ generate_keys(void)
 	uint32_t *keys_ks = NULL;
 	uint32_t *keys_absent = NULL;
 	uint32_t *keys_non_shift_path = NULL;
+	uint32_t *keys_ext_bkt = NULL;
+	uint32_t *keys_ks_extbkt = NULL;
 	uint32_t *found = NULL;
 	uint32_t count_keys_no_ks = 0;
 	uint32_t count_keys_ks = 0;
+	uint32_t count_keys_extbkt = 0;
 	uint32_t i;
 
 	/*
@@ -251,14 +294,32 @@ generate_keys(void)
 		goto err;
 	}
 
+	/*
+	 * This consist of keys which will be stored in extended buckets
+	 */
+	keys_ext_bkt = rte_malloc(NULL, sizeof(uint32_t) * TOTAL_INSERT, 0);
+	if (keys_ext_bkt == NULL) {
+		printf("RTE_MALLOC failed\n");
+		goto err;
+	}
+
+	/*
+	 * This consist of keys which when deleted causes shifting of keys
+	 * in extended buckets to respective secondary buckets
+	 */
+	keys_ks_extbkt = rte_malloc(NULL, sizeof(uint32_t) * TOTAL_INSERT, 0);
+	if (keys_ks_extbkt == NULL) {
+		printf("RTE_MALLOC failed\n");
+		goto err;
+	}
 
 	hash_sig_t sig;
 	uint32_t prim_bucket_idx;
-	int ret;
+	uint32_t sec_bucket_idx;
+	uint16_t short_sig;
 	uint32_t num_buckets;
-	uint32_t bucket_bitmask;
 	num_buckets  = rte_align32pow2(TOTAL_ENTRY) / 8;
-	bucket_bitmask = num_buckets - 1;
+	int ret;
 
 	/*
 	 * Used to mark bkts in which at least one key was shifted to its
@@ -275,6 +336,8 @@ generate_keys(void)
 	tbl_rwc_test_param.keys_ks = keys_ks;
 	tbl_rwc_test_param.keys_absent = keys_absent;
 	tbl_rwc_test_param.keys_non_shift_path = keys_non_shift_path;
+	tbl_rwc_test_param.keys_ext_bkt = keys_ext_bkt;
+	tbl_rwc_test_param.keys_ks_extbkt = keys_ks_extbkt;
 	/* Generate keys by adding previous two keys, neglect overflow */
 	printf("Generating keys...\n");
 	keys[0] = 0;
@@ -287,7 +350,8 @@ generate_keys(void)
 		/* Check if primary bucket has space.*/
 		sig = rte_hash_hash(tbl_rwc_test_param.h,
 					tbl_rwc_test_param.keys+i);
-		prim_bucket_idx = sig & bucket_bitmask;
+		prim_bucket_idx = get_prim_bucket_index(tbl_rwc_test_param.h,
+							sig);
 		ret = check_bucket(prim_bucket_idx, keys[i]);
 		if (ret < 0) {
 			/*
@@ -368,6 +432,47 @@ generate_keys(void)
 	tbl_rwc_test_param.count_keys_absent = count_keys_absent;
 	tbl_rwc_test_param.count_keys_non_shift_path = count;
 
+	memset(scanned_bkts, 0, num_buckets);
+	count = 0;
+	/* Find keys that will be in extended buckets */
+	for (i = 0; i < count_keys_ks; i++) {
+		ret = rte_hash_add_key(tbl_rwc_test_param.h, keys_ks + i);
+		if (ret < 0) {
+			/* Key will be added to ext bkt */
+			keys_ext_bkt[count_keys_extbkt++] = keys_ks[i];
+			/* Sec bkt to be added to keys_ks_extbkt */
+			sig = rte_hash_hash(tbl_rwc_test_param.h,
+					tbl_rwc_test_param.keys_ks + i);
+			prim_bucket_idx = get_prim_bucket_index(
+						tbl_rwc_test_param.h, sig);
+			short_sig = get_short_sig(sig);
+			sec_bucket_idx = get_alt_bucket_index(
+						tbl_rwc_test_param.h,
+						prim_bucket_idx, short_sig);
+			if (scanned_bkts[sec_bucket_idx] == 0)
+				scanned_bkts[sec_bucket_idx] = 1;
+		}
+	}
+
+	/* Find keys that will shift keys in ext bucket*/
+	for (i = 0; i < num_buckets; i++) {
+		if (scanned_bkts[i] == 1) {
+			iter = i * 8;
+			while (rte_hash_iterate(tbl_rwc_test_param.h,
+				&next_key, &next_data, &iter) >= 0) {
+				/* Check if key belongs to the current bucket */
+				if (i >= (iter-1)/8)
+					keys_ks_extbkt[count++]
+						= *(const uint32_t *)next_key;
+				else
+					break;
+			}
+		}
+	}
+
+	tbl_rwc_test_param.count_keys_ks_extbkt = count;
+	tbl_rwc_test_param.count_keys_extbkt = count_keys_extbkt;
+
 	printf("\nCount of keys NOT causing shifting of existing keys to "
 	"alternate location: %d\n", tbl_rwc_test_param.count_keys_no_ks);
 	printf("\nCount of keys causing shifting of existing keys to alternate "
@@ -378,6 +483,10 @@ generate_keys(void)
 	       tbl_rwc_test_param.count_keys_shift_path);
 	printf("Count of keys not likely to be on the shift path: %d\n\n",
 	       tbl_rwc_test_param.count_keys_non_shift_path);
+	printf("Count of keys in extended buckets: %d\n\n",
+	       tbl_rwc_test_param.count_keys_extbkt);
+	printf("Count of keys shifting keys in ext buckets: %d\n\n",
+	       tbl_rwc_test_param.count_keys_ks_extbkt);
 
 	rte_free(found);
 	rte_hash_free(tbl_rwc_test_param.h);
@@ -390,12 +499,14 @@ generate_keys(void)
 	rte_free(keys_absent);
 	rte_free(found);
 	rte_free(tbl_rwc_test_param.keys_shift_path);
+	rte_free(keys_ext_bkt);
+	rte_free(keys_ks_extbkt);
 	rte_free(scanned_bkts);
 	return -1;
 }
 
 static int
-init_params(int rwc_lf, int use_jhash, int htm)
+init_params(int rwc_lf, int use_jhash, int htm, int ext_bkt)
 {
 	struct rte_hash *handle;
 
@@ -425,6 +536,9 @@ init_params(int rwc_lf, int use_jhash, int htm)
 			RTE_HASH_EXTRA_FLAGS_RW_CONCURRENCY |
 			RTE_HASH_EXTRA_FLAGS_MULTI_WRITER_ADD;
 
+	if (ext_bkt)
+		hash_params.extra_flag |= RTE_HASH_EXTRA_FLAGS_EXT_TABLE;
+
 	hash_params.name = "tests";
 
 	handle = rte_hash_create(&hash_params);
@@ -452,7 +566,7 @@ test_rwc_reader(__attribute__((unused)) void *arg)
 	void *temp_a[BULK_LOOKUP_SIZE];
 
 	/* Used to identify keys not inserted in the hash table */
-	pos = rte_zmalloc(NULL, sizeof(uint32_t) * BULK_LOOKUP_SIZE, 0);
+	pos = rte_malloc(NULL, sizeof(uint32_t) * BULK_LOOKUP_SIZE, 0);
 	if (pos == NULL) {
 		printf("RTE_MALLOC failed\n");
 		return -1;
@@ -467,6 +581,9 @@ test_rwc_reader(__attribute__((unused)) void *arg)
 	} else if (read_type & READ_PASS_SHIFT_PATH) {
 		keys = tbl_rwc_test_param.keys_shift_path;
 		read_cnt = tbl_rwc_test_param.count_keys_shift_path;
+	} else if (read_type & READ_PASS_KEY_SHIFTS_EXTBKT) {
+		keys = tbl_rwc_test_param.keys_ext_bkt;
+		read_cnt = tbl_rwc_test_param.count_keys_extbkt;
 	} else {
 		keys = tbl_rwc_test_param.keys_non_shift_path;
 		read_cnt = tbl_rwc_test_param.count_keys_non_shift_path;
@@ -482,7 +599,6 @@ test_rwc_reader(__attribute__((unused)) void *arg)
 				/* Array of  pointer to the list of keys */
 				for (j = 0; j < BULK_LOOKUP_SIZE; j++)
 					temp_a[j] = keys + i + j;
-
 				rte_hash_lookup_bulk(tbl_rwc_test_param.h,
 						   (const void **)
 						   ((uintptr_t)temp_a),
@@ -539,22 +655,25 @@ test_rwc_reader(__attribute__((unused)) void *arg)
 }
 
 static int
-write_keys(uint8_t key_shift)
+write_keys(uint8_t write_type)
 {
 	uint32_t i;
 	int ret;
 	uint32_t key_cnt;
 	uint32_t *keys;
-	if (key_shift) {
+	if (write_type == WRITE_KEY_SHIFT) {
 		key_cnt = tbl_rwc_test_param.count_keys_ks;
 		keys = tbl_rwc_test_param.keys_ks;
-	} else {
+	} else if (write_type == WRITE_NO_KEY_SHIFT) {
 		key_cnt = tbl_rwc_test_param.count_keys_no_ks;
 		keys = tbl_rwc_test_param.keys_no_ks;
+	} else if (write_type == WRITE_EXT_BKT) {
+		key_cnt = tbl_rwc_test_param.count_keys_extbkt;
+		keys = tbl_rwc_test_param.keys_ext_bkt;
 	}
 	for (i = 0; i < key_cnt; i++) {
 		ret = rte_hash_add_key(tbl_rwc_test_param.h, keys + i);
-		if (!key_shift && ret < 0) {
+		if ((write_type == WRITE_NO_KEY_SHIFT) && ret < 0) {
 			printf("writer failed %"PRIu32"\n", i);
 			return -1;
 		}
@@ -581,18 +700,18 @@ test_rwc_multi_writer(__attribute__((unused)) void *arg)
  */
 static int
 test_hash_add_no_ks_lookup_hit(struct rwc_perf *rwc_perf_results, int rwc_lf,
-				int htm)
+				int htm, int ext_bkt)
 {
 	unsigned int n, m;
 	uint64_t i;
 	int use_jhash = 0;
-	uint8_t key_shift = 0;
+	uint8_t write_type = WRITE_NO_KEY_SHIFT;
 	uint8_t read_type = READ_PASS_NO_KEY_SHIFTS;
 
 	rte_atomic64_init(&greads);
 	rte_atomic64_init(&gread_cycles);
 
-	if (init_params(rwc_lf, use_jhash, htm) != 0)
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
 		goto err;
 	printf("\nTest: Hash add - no key-shifts, read - hit\n");
 	for (m = 0; m < 2; m++) {
@@ -612,7 +731,7 @@ test_hash_add_no_ks_lookup_hit(struct rwc_perf *rwc_perf_results, int rwc_lf,
 
 			rte_hash_reset(tbl_rwc_test_param.h);
 			writer_done = 0;
-			if (write_keys(key_shift) < 0)
+			if (write_keys(write_type) < 0)
 				goto err;
 			writer_done = 1;
 			for (i = 1; i <= rwc_core_cnt[n]; i++)
@@ -650,19 +769,19 @@ test_hash_add_no_ks_lookup_hit(struct rwc_perf *rwc_perf_results, int rwc_lf,
  */
 static int
 test_hash_add_no_ks_lookup_miss(struct rwc_perf *rwc_perf_results, int rwc_lf,
-				int htm)
+				int htm, int ext_bkt)
 {
 	unsigned int n, m;
 	uint64_t i;
 	int use_jhash = 0;
-	uint8_t key_shift = 0;
+	uint8_t write_type = WRITE_NO_KEY_SHIFT;
 	uint8_t read_type = READ_FAIL;
 	int ret;
 
 	rte_atomic64_init(&greads);
 	rte_atomic64_init(&gread_cycles);
 
-	if (init_params(rwc_lf, use_jhash, htm) != 0)
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
 		goto err;
 	printf("\nTest: Hash add - no key-shifts, Hash lookup - miss\n");
 	for (m = 0; m < 2; m++) {
@@ -687,7 +806,7 @@ test_hash_add_no_ks_lookup_miss(struct rwc_perf *rwc_perf_results, int rwc_lf,
 				rte_eal_remote_launch(test_rwc_reader,
 						(void *)(uintptr_t)read_type,
 							enabled_core_ids[i]);
-			ret = write_keys(key_shift);
+			ret = write_keys(write_type);
 			writer_done = 1;
 			rte_eal_mp_wait_lcore();
 
@@ -722,19 +841,19 @@ test_hash_add_no_ks_lookup_miss(struct rwc_perf *rwc_perf_results, int rwc_lf,
  */
 static int
 test_hash_add_ks_lookup_hit_non_sp(struct rwc_perf *rwc_perf_results,
-				    int rwc_lf, int htm)
+				    int rwc_lf, int htm, int ext_bkt)
 {
 	unsigned int n, m;
 	uint64_t i;
 	int use_jhash = 0;
 	int ret;
-	uint8_t key_shift;
+	uint8_t write_type;
 	uint8_t read_type = READ_PASS_NON_SHIFT_PATH;
 
 	rte_atomic64_init(&greads);
 	rte_atomic64_init(&gread_cycles);
 
-	if (init_params(rwc_lf, use_jhash, htm) != 0)
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
 		goto err;
 	printf("\nTest: Hash add - key shift, Hash lookup - hit"
 	       " (non-shift-path)\n");
@@ -755,15 +874,15 @@ test_hash_add_ks_lookup_hit_non_sp(struct rwc_perf *rwc_perf_results,
 
 			rte_hash_reset(tbl_rwc_test_param.h);
 			writer_done = 0;
-			key_shift = 0;
-			if (write_keys(key_shift) < 0)
+			write_type = WRITE_NO_KEY_SHIFT;
+			if (write_keys(write_type) < 0)
 				goto err;
 			for (i = 1; i <= rwc_core_cnt[n]; i++)
 				rte_eal_remote_launch(test_rwc_reader,
 						(void *)(uintptr_t)read_type,
 							enabled_core_ids[i]);
-			key_shift = 1;
-			ret = write_keys(key_shift);
+			write_type = WRITE_KEY_SHIFT;
+			ret = write_keys(write_type);
 			writer_done = 1;
 			rte_eal_mp_wait_lcore();
 
@@ -798,19 +917,19 @@ test_hash_add_ks_lookup_hit_non_sp(struct rwc_perf *rwc_perf_results,
  */
 static int
 test_hash_add_ks_lookup_hit_sp(struct rwc_perf *rwc_perf_results, int rwc_lf,
-				int htm)
+				int htm, int ext_bkt)
 {
 	unsigned int n, m;
 	uint64_t i;
 	int use_jhash = 0;
 	int ret;
-	uint8_t key_shift;
+	uint8_t write_type;
 	uint8_t read_type = READ_PASS_SHIFT_PATH;
 
 	rte_atomic64_init(&greads);
 	rte_atomic64_init(&gread_cycles);
 
-	if (init_params(rwc_lf, use_jhash, htm) != 0)
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
 		goto err;
 	printf("\nTest: Hash add - key shift, Hash lookup - hit (shift-path)"
 	       "\n");
@@ -831,15 +950,15 @@ test_hash_add_ks_lookup_hit_sp(struct rwc_perf *rwc_perf_results, int rwc_lf,
 
 			rte_hash_reset(tbl_rwc_test_param.h);
 			writer_done = 0;
-			key_shift = 0;
-			if (write_keys(key_shift) < 0)
+			write_type = WRITE_NO_KEY_SHIFT;
+			if (write_keys(write_type) < 0)
 				goto err;
 			for (i = 1; i <= rwc_core_cnt[n]; i++)
 				rte_eal_remote_launch(test_rwc_reader,
 						(void *)(uintptr_t)read_type,
 						enabled_core_ids[i]);
-			key_shift = 1;
-			ret = write_keys(key_shift);
+			write_type = WRITE_KEY_SHIFT;
+			ret = write_keys(write_type);
 			writer_done = 1;
 			rte_eal_mp_wait_lcore();
 
@@ -874,19 +993,19 @@ test_hash_add_ks_lookup_hit_sp(struct rwc_perf *rwc_perf_results, int rwc_lf,
  */
 static int
 test_hash_add_ks_lookup_miss(struct rwc_perf *rwc_perf_results, int rwc_lf, int
-			     htm)
+			     htm, int ext_bkt)
 {
 	unsigned int n, m;
 	uint64_t i;
 	int use_jhash = 0;
 	int ret;
-	uint8_t key_shift;
+	uint8_t write_type;
 	uint8_t read_type = READ_FAIL;
 
 	rte_atomic64_init(&greads);
 	rte_atomic64_init(&gread_cycles);
 
-	if (init_params(rwc_lf, use_jhash, htm) != 0)
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
 		goto err;
 	printf("\nTest: Hash add - key shift, Hash lookup - miss\n");
 	for (m = 0; m < 2; m++) {
@@ -906,15 +1025,15 @@ test_hash_add_ks_lookup_miss(struct rwc_perf *rwc_perf_results, int rwc_lf, int
 
 			rte_hash_reset(tbl_rwc_test_param.h);
 			writer_done = 0;
-			key_shift = 0;
-			if (write_keys(key_shift) < 0)
+			write_type = WRITE_NO_KEY_SHIFT;
+			if (write_keys(write_type) < 0)
 				goto err;
 			for (i = 1; i <= rwc_core_cnt[n]; i++)
 				rte_eal_remote_launch(test_rwc_reader,
 						(void *)(uintptr_t)read_type,
 							enabled_core_ids[i]);
-			key_shift = 1;
-			ret = write_keys(key_shift);
+			write_type = WRITE_KEY_SHIFT;
+			ret = write_keys(write_type);
 			writer_done = 1;
 			rte_eal_mp_wait_lcore();
 
@@ -949,18 +1068,18 @@ test_hash_add_ks_lookup_miss(struct rwc_perf *rwc_perf_results, int rwc_lf, int
  */
 static int
 test_hash_multi_add_lookup(struct rwc_perf *rwc_perf_results, int rwc_lf,
-			   int htm)
+			   int htm, int ext_bkt)
 {
 	unsigned int n, m, k;
 	uint64_t i;
 	int use_jhash = 0;
-	uint8_t key_shift;
+	uint8_t write_type;
 	uint8_t read_type = READ_PASS_SHIFT_PATH;
 
 	rte_atomic64_init(&greads);
 	rte_atomic64_init(&gread_cycles);
 
-	if (init_params(rwc_lf, use_jhash, htm) != 0)
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
 		goto err;
 	printf("\nTest: Multi-add-lookup\n");
 	uint8_t pos_core;
@@ -991,8 +1110,8 @@ test_hash_multi_add_lookup(struct rwc_perf *rwc_perf_results, int rwc_lf,
 				writer_done = 0;
 				for (i = 0; i < 4; i++)
 					multi_writer_done[i] = 0;
-				key_shift = 0;
-				if (write_keys(key_shift) < 0)
+				write_type = WRITE_NO_KEY_SHIFT;
+				if (write_keys(write_type) < 0)
 					goto err;
 
 				/* Launch reader(s) */
@@ -1000,7 +1119,7 @@ test_hash_multi_add_lookup(struct rwc_perf *rwc_perf_results, int rwc_lf,
 					rte_eal_remote_launch(test_rwc_reader,
 						(void *)(uintptr_t)read_type,
 						enabled_core_ids[i]);
-				key_shift = 1;
+				write_type = WRITE_KEY_SHIFT;
 				pos_core = 0;
 
 				/* Launch writers */
@@ -1045,6 +1164,88 @@ test_hash_multi_add_lookup(struct rwc_perf *rwc_perf_results, int rwc_lf,
 	return -1;
 }
 
+/*
+ * Test lookup perf:
+ * Reader(s) lookup keys present in the extendable bkt.
+ */
+static int
+test_hash_add_ks_lookup_hit_extbkt(struct rwc_perf *rwc_perf_results,
+				int rwc_lf, int htm, int ext_bkt)
+{
+	unsigned int n, m;
+	uint64_t i;
+	int use_jhash = 0;
+	uint8_t write_type;
+	uint8_t read_type = READ_PASS_KEY_SHIFTS_EXTBKT;
+
+	rte_atomic64_init(&greads);
+	rte_atomic64_init(&gread_cycles);
+
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
+		goto err;
+	printf("\nTest: Hash add - key-shifts, read - hit (ext_bkt)\n");
+	for (m = 0; m < 2; m++) {
+		if (m == 1) {
+			printf("\n** With bulk-lookup **\n");
+			read_type |= BULK_LOOKUP;
+		}
+		for (n = 0; n < NUM_TEST; n++) {
+			unsigned int tot_lcore = rte_lcore_count();
+			if (tot_lcore < rwc_core_cnt[n] + 1)
+				goto finish;
+
+			printf("\nNumber of readers: %u\n", rwc_core_cnt[n]);
+
+			rte_atomic64_clear(&greads);
+			rte_atomic64_clear(&gread_cycles);
+
+			rte_hash_reset(tbl_rwc_test_param.h);
+			write_type = WRITE_NO_KEY_SHIFT;
+			if (write_keys(write_type) < 0)
+				goto err;
+			write_type = WRITE_KEY_SHIFT;
+			if (write_keys(write_type) < 0)
+				goto err;
+			writer_done = 0;
+			for (i = 1; i <= rwc_core_cnt[n]; i++)
+				rte_eal_remote_launch(test_rwc_reader,
+						(void *)(uintptr_t)read_type,
+							enabled_core_ids[i]);
+			for (i = 0; i < tbl_rwc_test_param.count_keys_ks_extbkt;
+			     i++) {
+				if (rte_hash_del_key(tbl_rwc_test_param.h,
+					tbl_rwc_test_param.keys_ks_extbkt + i)
+							< 0) {
+					printf("Delete Failed: %u\n",
+					tbl_rwc_test_param.keys_ks_extbkt[i]);
+					goto err;
+				}
+			}
+			writer_done = 1;
+			rte_eal_mp_wait_lcore();
+
+			for (i = 1; i <= rwc_core_cnt[n]; i++)
+				if (lcore_config[i].ret < 0)
+					goto err;
+
+			unsigned long long cycles_per_lookup =
+				rte_atomic64_read(&gread_cycles) /
+				rte_atomic64_read(&greads);
+			rwc_perf_results->w_ks_r_hit_extbkt[m][n]
+						= cycles_per_lookup;
+			printf("Cycles per lookup: %llu\n", cycles_per_lookup);
+		}
+	}
+
+finish:
+	rte_hash_free(tbl_rwc_test_param.h);
+	return 0;
+
+err:
+	rte_hash_free(tbl_rwc_test_param.h);
+	return -1;
+}
+
 static int
 test_hash_readwrite_lf_main(void)
 {
@@ -1057,6 +1258,7 @@ test_hash_readwrite_lf_main(void)
 	int rwc_lf = 0;
 	int htm;
 	int use_jhash = 0;
+	int ext_bkt = 0;
 	if (rte_lcore_count() == 1) {
 		printf("More than one lcore is required "
 			"to do read write lock-free concurrency test\n");
@@ -1070,7 +1272,7 @@ test_hash_readwrite_lf_main(void)
 	else
 		htm = 0;
 
-	if (init_params(rwc_lf, use_jhash, htm) != 0)
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
 		return -1;
 	if (generate_keys() != 0)
 		return -1;
@@ -1079,25 +1281,29 @@ test_hash_readwrite_lf_main(void)
 
 	if (RTE_HASH_EXTRA_FLAGS_RW_CONCURRENCY_LF) {
 		rwc_lf = 1;
+		ext_bkt = 1;
 		printf("Test lookup with read-write concurrency lock free support"
 		       " enabled\n");
 		if (test_hash_add_no_ks_lookup_hit(&rwc_lf_results, rwc_lf,
-							htm) < 0)
+							htm, ext_bkt) < 0)
 			return -1;
 		if (test_hash_add_no_ks_lookup_miss(&rwc_lf_results, rwc_lf,
-							htm) < 0)
+							htm, ext_bkt) < 0)
 			return -1;
 		if (test_hash_add_ks_lookup_hit_non_sp(&rwc_lf_results, rwc_lf,
-							htm) < 0)
+							htm, ext_bkt) < 0)
 			return -1;
 		if (test_hash_add_ks_lookup_hit_sp(&rwc_lf_results, rwc_lf,
-							htm) < 0)
+							htm, ext_bkt) < 0)
 			return -1;
-		if (test_hash_add_ks_lookup_miss(&rwc_lf_results, rwc_lf, htm)
-							< 0)
+		if (test_hash_add_ks_lookup_miss(&rwc_lf_results, rwc_lf, htm,
+						 ext_bkt) < 0)
 			return -1;
-		if (test_hash_multi_add_lookup(&rwc_lf_results, rwc_lf, htm)
-							< 0)
+		if (test_hash_multi_add_lookup(&rwc_lf_results, rwc_lf, htm,
+					       ext_bkt) < 0)
+			return -1;
+		if (test_hash_add_ks_lookup_hit_extbkt(&rwc_lf_results, rwc_lf,
+							htm, ext_bkt) < 0)
 			return -1;
 	}
 	printf("\nTest lookup with read-write concurrency lock free support"
@@ -1112,21 +1318,26 @@ test_hash_readwrite_lf_main(void)
 		}
 	} else
 		printf("With HTM Enabled\n");
-	if (test_hash_add_no_ks_lookup_hit(&rwc_non_lf_results, rwc_lf, htm)
-						< 0)
+	if (test_hash_add_no_ks_lookup_hit(&rwc_non_lf_results, rwc_lf, htm,
+					   ext_bkt) < 0)
 		return -1;
-	if (test_hash_add_no_ks_lookup_miss(&rwc_non_lf_results, rwc_lf, htm)
-						< 0)
+	if (test_hash_add_no_ks_lookup_miss(&rwc_non_lf_results, rwc_lf, htm,
+						ext_bkt) < 0)
 		return -1;
 	if (test_hash_add_ks_lookup_hit_non_sp(&rwc_non_lf_results, rwc_lf,
-						htm) < 0)
+						htm, ext_bkt) < 0)
+		return -1;
+	if (test_hash_add_ks_lookup_hit_sp(&rwc_non_lf_results, rwc_lf, htm,
+						ext_bkt) < 0)
 		return -1;
-	if (test_hash_add_ks_lookup_hit_sp(&rwc_non_lf_results, rwc_lf, htm)
-						< 0)
+	if (test_hash_add_ks_lookup_miss(&rwc_non_lf_results, rwc_lf, htm,
+					 ext_bkt) < 0)
 		return -1;
-	if (test_hash_add_ks_lookup_miss(&rwc_non_lf_results, rwc_lf, htm) < 0)
+	if (test_hash_multi_add_lookup(&rwc_non_lf_results, rwc_lf, htm,
+							ext_bkt) < 0)
 		return -1;
-	if (test_hash_multi_add_lookup(&rwc_non_lf_results, rwc_lf, htm) < 0)
+	if (test_hash_add_ks_lookup_hit_extbkt(&rwc_non_lf_results, rwc_lf,
+						htm, ext_bkt) < 0)
 		return -1;
 results:
 	printf("\n\t\t\t\t\t\t********** Results summary **********\n\n");
@@ -1158,8 +1369,11 @@ test_hash_readwrite_lf_main(void)
 			       "(shift-path)\t\t%u\n\t\t\t\t\t\t\t\t",
 			       rwc_lf_results.w_ks_r_hit_sp[j][i]);
 			printf("Hash add - key-shifts, Hash lookup miss\t\t\t\t"
-				"%u\n\n\t\t\t\t",
+				"%u\n\t\t\t\t\t\t\t\t",
 				rwc_lf_results.w_ks_r_miss[j][i]);
+			printf("Hash add - key-shifts, Hash lookup hit (ext_bkt)\t\t"
+				"%u\n\n\t\t\t\t",
+				rwc_lf_results.w_ks_r_hit_extbkt[j][i]);
 
 			printf("Disabled\t");
 			if (htm)
@@ -1179,7 +1393,11 @@ test_hash_readwrite_lf_main(void)
 			       "(shift-path)\t\t%u\n\t\t\t\t\t\t\t\t",
 			       rwc_non_lf_results.w_ks_r_hit_sp[j][i]);
 			printf("Hash add - key-shifts, Hash lookup miss\t\t\t\t"
-			       "%u\n", rwc_non_lf_results.w_ks_r_miss[j][i]);
+			       "%u\n\t\t\t\t\t\t\t\t",
+			       rwc_non_lf_results.w_ks_r_miss[j][i]);
+			printf("Hash add - key-shifts, Hash lookup hit (ext_bkt)\t\t"
+				"%u\n",
+				rwc_non_lf_results.w_ks_r_hit_extbkt[j][i]);
 
 			printf("_______\t\t_______\t\t_________\t___\t\t"
 			       "_________\t\t\t\t\t\t_________________\n");
-- 
2.17.1

Re: [dpdk-dev] [PATCH v2 2/2] test/hash: lock-free rw concurrency test ext bkt

[Wang, Yipeng1]

A little bit improvement on commit-message maybe needed.

>-----Original Message-----
>From: Dharmik Thakkar [mailto:dharmik.thakkar@arm.com]
>Sent: Monday, March 25, 2019 2:09 PM
>To: Wang, Yipeng1 <yipeng1.wang@intel.com>; Gobriel, Sameh <sameh.gobriel@intel.com>; Richardson, Bruce
><bruce.richardson@intel.com>; De Lara Guarch, Pablo <pablo.de.lara.guarch@intel.com>
>Cc: dev@dpdk.org; Dharmik Thakkar <dharmik.thakkar@arm.com>
>Subject: [PATCH v2 2/2] test/hash: lock-free rw concurrency test ext bkt
[Wang, Yipeng] *for* ext bucket
>
>Add unit test to check for hash lookup and bulk-lookup perf.
[Wang, Yipeng] for extendable bucket feature.
>Test with lock-free enabled and with lock-free disabled.
[Wang, Yipeng] It is tested with both lock-free enabled and disabled case.
>
>Test include:
>
>- hash lookup on keys in ext bkt,
>hash delete causing key-shifts of keys from ext bkt to secondary bkt
[Wang, Yipeng] 
Two test scenarios right? A bit of formatting..
Tests include:
- hash lookup on keys in ext bucket.
- hash delete causing key-shifts of keys from ext bucket to secondary bucket.

>
>Suggested-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
>Signed-off-by: Dharmik Thakkar <dharmik.thakkar@arm.com>
>---
>+/*
>+ * Test lookup perf:
>+ * Reader(s) lookup keys present in the extendable bkt.
>+ */
>+static int
>+test_hash_add_ks_lookup_hit_extbkt(struct rwc_perf *rwc_perf_results,
>+				int rwc_lf, int htm, int ext_bkt)
>+{
>+	unsigned int n, m;
>+	uint64_t i;
>+	int use_jhash = 0;
>+	uint8_t write_type;
>+	uint8_t read_type = READ_PASS_KEY_SHIFTS_EXTBKT;
>+
>+	rte_atomic64_init(&greads);
>+	rte_atomic64_init(&gread_cycles);
>+
>+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
>+		goto err;
>+	printf("\nTest: Hash add - key-shifts, read - hit (ext_bkt)\n");
>+	for (m = 0; m < 2; m++) {
>+		if (m == 1) {
>+			printf("\n** With bulk-lookup **\n");
>+			read_type |= BULK_LOOKUP;
>+		}
>+		for (n = 0; n < NUM_TEST; n++) {
>+			unsigned int tot_lcore = rte_lcore_count();
>+			if (tot_lcore < rwc_core_cnt[n] + 1)
>+				goto finish;
>+
>+			printf("\nNumber of readers: %u\n", rwc_core_cnt[n]);
>+
>+			rte_atomic64_clear(&greads);
>+			rte_atomic64_clear(&gread_cycles);
>+
>+			rte_hash_reset(tbl_rwc_test_param.h);
>+			write_type = WRITE_NO_KEY_SHIFT;
>+			if (write_keys(write_type) < 0)
>+				goto err;
>+			write_type = WRITE_KEY_SHIFT;
>+			if (write_keys(write_type) < 0)
>+				goto err;
>+			writer_done = 0;
>+			for (i = 1; i <= rwc_core_cnt[n]; i++)
>+				rte_eal_remote_launch(test_rwc_reader,
>+						(void *)(uintptr_t)read_type,
>+							enabled_core_ids[i]);
>+			for (i = 0; i < tbl_rwc_test_param.count_keys_ks_extbkt;
>+			     i++) {
>+				if (rte_hash_del_key(tbl_rwc_test_param.h,
>+					tbl_rwc_test_param.keys_ks_extbkt + i)
>+							< 0) {
>+					printf("Delete Failed: %u\n",
>+					tbl_rwc_test_param.keys_ks_extbkt[i]);
>+					goto err;
>+				}
>+			}
>+			writer_done = 1;
>+			rte_eal_mp_wait_lcore();
[Wang, Yipeng] Not requirement for this perf patch, but is it better to read the shifted key again
Just to verify the logic? If not difficult please add.

Re: [dpdk-dev] [PATCH v2 2/2] test/hash: lock-free rw concurrency test ext bkt

[Wang, Yipeng1]

A little bit improvement on commit-message maybe needed.

>-----Original Message-----
>From: Dharmik Thakkar [mailto:dharmik.thakkar@arm.com]
>Sent: Monday, March 25, 2019 2:09 PM
>To: Wang, Yipeng1 <yipeng1.wang@intel.com>; Gobriel, Sameh <sameh.gobriel@intel.com>; Richardson, Bruce
><bruce.richardson@intel.com>; De Lara Guarch, Pablo <pablo.de.lara.guarch@intel.com>
>Cc: dev@dpdk.org; Dharmik Thakkar <dharmik.thakkar@arm.com>
>Subject: [PATCH v2 2/2] test/hash: lock-free rw concurrency test ext bkt
[Wang, Yipeng] *for* ext bucket
>
>Add unit test to check for hash lookup and bulk-lookup perf.
[Wang, Yipeng] for extendable bucket feature.
>Test with lock-free enabled and with lock-free disabled.
[Wang, Yipeng] It is tested with both lock-free enabled and disabled case.
>
>Test include:
>
>- hash lookup on keys in ext bkt,
>hash delete causing key-shifts of keys from ext bkt to secondary bkt
[Wang, Yipeng] 
Two test scenarios right? A bit of formatting..
Tests include:
- hash lookup on keys in ext bucket.
- hash delete causing key-shifts of keys from ext bucket to secondary bucket.

>
>Suggested-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
>Signed-off-by: Dharmik Thakkar <dharmik.thakkar@arm.com>
>---
>+/*
>+ * Test lookup perf:
>+ * Reader(s) lookup keys present in the extendable bkt.
>+ */
>+static int
>+test_hash_add_ks_lookup_hit_extbkt(struct rwc_perf *rwc_perf_results,
>+				int rwc_lf, int htm, int ext_bkt)
>+{
>+	unsigned int n, m;
>+	uint64_t i;
>+	int use_jhash = 0;
>+	uint8_t write_type;
>+	uint8_t read_type = READ_PASS_KEY_SHIFTS_EXTBKT;
>+
>+	rte_atomic64_init(&greads);
>+	rte_atomic64_init(&gread_cycles);
>+
>+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
>+		goto err;
>+	printf("\nTest: Hash add - key-shifts, read - hit (ext_bkt)\n");
>+	for (m = 0; m < 2; m++) {
>+		if (m == 1) {
>+			printf("\n** With bulk-lookup **\n");
>+			read_type |= BULK_LOOKUP;
>+		}
>+		for (n = 0; n < NUM_TEST; n++) {
>+			unsigned int tot_lcore = rte_lcore_count();
>+			if (tot_lcore < rwc_core_cnt[n] + 1)
>+				goto finish;
>+
>+			printf("\nNumber of readers: %u\n", rwc_core_cnt[n]);
>+
>+			rte_atomic64_clear(&greads);
>+			rte_atomic64_clear(&gread_cycles);
>+
>+			rte_hash_reset(tbl_rwc_test_param.h);
>+			write_type = WRITE_NO_KEY_SHIFT;
>+			if (write_keys(write_type) < 0)
>+				goto err;
>+			write_type = WRITE_KEY_SHIFT;
>+			if (write_keys(write_type) < 0)
>+				goto err;
>+			writer_done = 0;
>+			for (i = 1; i <= rwc_core_cnt[n]; i++)
>+				rte_eal_remote_launch(test_rwc_reader,
>+						(void *)(uintptr_t)read_type,
>+							enabled_core_ids[i]);
>+			for (i = 0; i < tbl_rwc_test_param.count_keys_ks_extbkt;
>+			     i++) {
>+				if (rte_hash_del_key(tbl_rwc_test_param.h,
>+					tbl_rwc_test_param.keys_ks_extbkt + i)
>+							< 0) {
>+					printf("Delete Failed: %u\n",
>+					tbl_rwc_test_param.keys_ks_extbkt[i]);
>+					goto err;
>+				}
>+			}
>+			writer_done = 1;
>+			rte_eal_mp_wait_lcore();
[Wang, Yipeng] Not requirement for this perf patch, but is it better to read the shifted key again
Just to verify the logic? If not difficult please add.

Re: [dpdk-dev] [PATCH v2 2/2] test/hash: lock-free rw concurrency test ext bkt

[Dharmik Thakkar]

+Honnappa

Hi Yipeng,

Thank you for the review comments!

> On Apr 1, 2019, at 1:55 PM, Wang, Yipeng1 <yipeng1.wang@intel.com> wrote:
> 
> A little bit improvement on commit-message maybe needed.
> 
>> -----Original Message-----
>> From: Dharmik Thakkar [mailto:dharmik.thakkar@arm.com]
>> Sent: Monday, March 25, 2019 2:09 PM
>> To: Wang, Yipeng1 <yipeng1.wang@intel.com>; Gobriel, Sameh <sameh.gobriel@intel.com>; Richardson, Bruce
>> <bruce.richardson@intel.com>; De Lara Guarch, Pablo <pablo.de.lara.guarch@intel.com>
>> Cc: dev@dpdk.org; Dharmik Thakkar <dharmik.thakkar@arm.com>
>> Subject: [PATCH v2 2/2] test/hash: lock-free rw concurrency test ext bkt
> [Wang, Yipeng] *for* ext bucket
Exceeds 50 characters limit.
>> 
>> Add unit test to check for hash lookup and bulk-lookup perf.
> [Wang, Yipeng] for extendable bucket feature.
Will update in the next version.
>> Test with lock-free enabled and with lock-free disabled.
> [Wang, Yipeng] It is tested with both lock-free enabled and disabled case.
Will update in the next version.
> 
>> 
>> Test include:
>> 
>> - hash lookup on keys in ext bkt,
>> hash delete causing key-shifts of keys from ext bkt to secondary bkt
> [Wang, Yipeng] 
> Two test scenarios right? A bit of formatting..
> Tests include:
It is a single test wherein lookup perf is tested for with hash delete causing key-shifts.
I will put it as Test includes:
> - hash lookup on keys in ext bucket.
> - hash delete causing key-shifts of keys from ext bucket to secondary bucket.
>  
>> 
>> Suggested-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
>> Signed-off-by: Dharmik Thakkar <dharmik.thakkar@arm.com>
>> ---
>> +/*
>> + * Test lookup perf:
>> + * Reader(s) lookup keys present in the extendable bkt.
>> + */
>> +static int
>> +test_hash_add_ks_lookup_hit_extbkt(struct rwc_perf *rwc_perf_results,
>> +				int rwc_lf, int htm, int ext_bkt)
>> +{
>> +	unsigned int n, m;
>> +	uint64_t i;
>> +	int use_jhash = 0;
>> +	uint8_t write_type;
>> +	uint8_t read_type = READ_PASS_KEY_SHIFTS_EXTBKT;
>> +
>> +	rte_atomic64_init(&greads);
>> +	rte_atomic64_init(&gread_cycles);
>> +
>> +	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
>> +		goto err;
>> +	printf("\nTest: Hash add - key-shifts, read - hit (ext_bkt)\n");
>> +	for (m = 0; m < 2; m++) {
>> +		if (m == 1) {
>> +			printf("\n** With bulk-lookup **\n");
>> +			read_type |= BULK_LOOKUP;
>> +		}
>> +		for (n = 0; n < NUM_TEST; n++) {
>> +			unsigned int tot_lcore = rte_lcore_count();
>> +			if (tot_lcore < rwc_core_cnt[n] + 1)
>> +				goto finish;
>> +
>> +			printf("\nNumber of readers: %u\n", rwc_core_cnt[n]);
>> +
>> +			rte_atomic64_clear(&greads);
>> +			rte_atomic64_clear(&gread_cycles);
>> +
>> +			rte_hash_reset(tbl_rwc_test_param.h);
>> +			write_type = WRITE_NO_KEY_SHIFT;
>> +			if (write_keys(write_type) < 0)
>> +				goto err;
>> +			write_type = WRITE_KEY_SHIFT;
>> +			if (write_keys(write_type) < 0)
>> +				goto err;
>> +			writer_done = 0;
>> +			for (i = 1; i <= rwc_core_cnt[n]; i++)
>> +				rte_eal_remote_launch(test_rwc_reader,
>> +						(void *)(uintptr_t)read_type,
>> +							enabled_core_ids[i]);
>> +			for (i = 0; i < tbl_rwc_test_param.count_keys_ks_extbkt;
>> +			     i++) {
>> +				if (rte_hash_del_key(tbl_rwc_test_param.h,
>> +					tbl_rwc_test_param.keys_ks_extbkt + i)
>> +							< 0) {
>> +					printf("Delete Failed: %u\n",
>> +					tbl_rwc_test_param.keys_ks_extbkt[i]);
>> +					goto err;
>> +				}
>> +			}
>> +			writer_done = 1;
>> +			rte_eal_mp_wait_lcore();
> [Wang, Yipeng] Not requirement for this perf patch, but is it better to read the shifted key again
> Just to verify the logic? If not difficult please add.
Keys in ext bkt (including shifted keys) are being read in a loop while writer_done equals 0 i.e. while keys are being deleted.
Test fails if look up fails. Do you think there is still a need to add one more round of look up on all the keys in ext bkt (some of which have now been shifted to secondary bkts)?

Re: [dpdk-dev] [PATCH v2 2/2] test/hash: lock-free rw concurrency test ext bkt

[Dharmik Thakkar]

+Honnappa

Hi Yipeng,

Thank you for the review comments!

> On Apr 1, 2019, at 1:55 PM, Wang, Yipeng1 <yipeng1.wang@intel.com> wrote:
> 
> A little bit improvement on commit-message maybe needed.
> 
>> -----Original Message-----
>> From: Dharmik Thakkar [mailto:dharmik.thakkar@arm.com]
>> Sent: Monday, March 25, 2019 2:09 PM
>> To: Wang, Yipeng1 <yipeng1.wang@intel.com>; Gobriel, Sameh <sameh.gobriel@intel.com>; Richardson, Bruce
>> <bruce.richardson@intel.com>; De Lara Guarch, Pablo <pablo.de.lara.guarch@intel.com>
>> Cc: dev@dpdk.org; Dharmik Thakkar <dharmik.thakkar@arm.com>
>> Subject: [PATCH v2 2/2] test/hash: lock-free rw concurrency test ext bkt
> [Wang, Yipeng] *for* ext bucket
Exceeds 50 characters limit.
>> 
>> Add unit test to check for hash lookup and bulk-lookup perf.
> [Wang, Yipeng] for extendable bucket feature.
Will update in the next version.
>> Test with lock-free enabled and with lock-free disabled.
> [Wang, Yipeng] It is tested with both lock-free enabled and disabled case.
Will update in the next version.
> 
>> 
>> Test include:
>> 
>> - hash lookup on keys in ext bkt,
>> hash delete causing key-shifts of keys from ext bkt to secondary bkt
> [Wang, Yipeng] 
> Two test scenarios right? A bit of formatting..
> Tests include:
It is a single test wherein lookup perf is tested for with hash delete causing key-shifts.
I will put it as Test includes:
> - hash lookup on keys in ext bucket.
> - hash delete causing key-shifts of keys from ext bucket to secondary bucket.
>  
>> 
>> Suggested-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
>> Signed-off-by: Dharmik Thakkar <dharmik.thakkar@arm.com>
>> ---
>> +/*
>> + * Test lookup perf:
>> + * Reader(s) lookup keys present in the extendable bkt.
>> + */
>> +static int
>> +test_hash_add_ks_lookup_hit_extbkt(struct rwc_perf *rwc_perf_results,
>> +				int rwc_lf, int htm, int ext_bkt)
>> +{
>> +	unsigned int n, m;
>> +	uint64_t i;
>> +	int use_jhash = 0;
>> +	uint8_t write_type;
>> +	uint8_t read_type = READ_PASS_KEY_SHIFTS_EXTBKT;
>> +
>> +	rte_atomic64_init(&greads);
>> +	rte_atomic64_init(&gread_cycles);
>> +
>> +	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
>> +		goto err;
>> +	printf("\nTest: Hash add - key-shifts, read - hit (ext_bkt)\n");
>> +	for (m = 0; m < 2; m++) {
>> +		if (m == 1) {
>> +			printf("\n** With bulk-lookup **\n");
>> +			read_type |= BULK_LOOKUP;
>> +		}
>> +		for (n = 0; n < NUM_TEST; n++) {
>> +			unsigned int tot_lcore = rte_lcore_count();
>> +			if (tot_lcore < rwc_core_cnt[n] + 1)
>> +				goto finish;
>> +
>> +			printf("\nNumber of readers: %u\n", rwc_core_cnt[n]);
>> +
>> +			rte_atomic64_clear(&greads);
>> +			rte_atomic64_clear(&gread_cycles);
>> +
>> +			rte_hash_reset(tbl_rwc_test_param.h);
>> +			write_type = WRITE_NO_KEY_SHIFT;
>> +			if (write_keys(write_type) < 0)
>> +				goto err;
>> +			write_type = WRITE_KEY_SHIFT;
>> +			if (write_keys(write_type) < 0)
>> +				goto err;
>> +			writer_done = 0;
>> +			for (i = 1; i <= rwc_core_cnt[n]; i++)
>> +				rte_eal_remote_launch(test_rwc_reader,
>> +						(void *)(uintptr_t)read_type,
>> +							enabled_core_ids[i]);
>> +			for (i = 0; i < tbl_rwc_test_param.count_keys_ks_extbkt;
>> +			     i++) {
>> +				if (rte_hash_del_key(tbl_rwc_test_param.h,
>> +					tbl_rwc_test_param.keys_ks_extbkt + i)
>> +							< 0) {
>> +					printf("Delete Failed: %u\n",
>> +					tbl_rwc_test_param.keys_ks_extbkt[i]);
>> +					goto err;
>> +				}
>> +			}
>> +			writer_done = 1;
>> +			rte_eal_mp_wait_lcore();
> [Wang, Yipeng] Not requirement for this perf patch, but is it better to read the shifted key again
> Just to verify the logic? If not difficult please add.
Keys in ext bkt (including shifted keys) are being read in a loop while writer_done equals 0 i.e. while keys are being deleted.
Test fails if look up fails. Do you think there is still a need to add one more round of look up on all the keys in ext bkt (some of which have now been shifted to secondary bkts)?

[dpdk-dev] [PATCH v3 0/2] hash: add lock free support for ext bkt

[Dharmik Thakkar]

This patch series:
- Enables lock-free read-write concurrency support for extendable
bucket feature.
- Adds lock-free read-write concurrency tests for ext bkt 

Dharmik Thakkar (2):
  hash: add lock free support for extendable bucket
  test/hash: lock-free rw concurrency test ext bkt

 app/test/test_hash_readwrite_lf.c  | 350 +++++++++++++++++++++++------
 doc/guides/prog_guide/hash_lib.rst |   6 +-
 lib/librte_hash/rte_cuckoo_hash.c  | 157 ++++++++-----
 lib/librte_hash/rte_cuckoo_hash.h  |   7 +
 4 files changed, 401 insertions(+), 119 deletions(-)

-- 
2.17.1

[dpdk-dev] [PATCH v3 0/2] hash: add lock free support for ext bkt

[Dharmik Thakkar]

This patch series:
- Enables lock-free read-write concurrency support for extendable
bucket feature.
- Adds lock-free read-write concurrency tests for ext bkt 

Dharmik Thakkar (2):
  hash: add lock free support for extendable bucket
  test/hash: lock-free rw concurrency test ext bkt

 app/test/test_hash_readwrite_lf.c  | 350 +++++++++++++++++++++++------
 doc/guides/prog_guide/hash_lib.rst |   6 +-
 lib/librte_hash/rte_cuckoo_hash.c  | 157 ++++++++-----
 lib/librte_hash/rte_cuckoo_hash.h  |   7 +
 4 files changed, 401 insertions(+), 119 deletions(-)

-- 
2.17.1

[dpdk-dev] [PATCH v3 1/2] hash: add lock free support for extendable bucket

[Dharmik Thakkar]

This patch enables lock-free read-write concurrency support for
extendable bucket feature.

Suggested-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
Signed-off-by: Dharmik Thakkar <dharmik.thakkar@arm.com>
Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
Reviewed-by: Gavin Hu <gavin.hu@arm.com>
Reviewed-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
Acked-by: Yipeng Wang <yipeng1.wang@intel.com>
---
 doc/guides/prog_guide/hash_lib.rst |   6 +-
 lib/librte_hash/rte_cuckoo_hash.c  | 157 ++++++++++++++++++++---------
 lib/librte_hash/rte_cuckoo_hash.h  |   7 ++
 3 files changed, 117 insertions(+), 53 deletions(-)

diff --git a/doc/guides/prog_guide/hash_lib.rst b/doc/guides/prog_guide/hash_lib.rst
index 85a6edfa8b16..d06c7de2ead1 100644
--- a/doc/guides/prog_guide/hash_lib.rst
+++ b/doc/guides/prog_guide/hash_lib.rst
@@ -108,9 +108,9 @@ Extendable Bucket Functionality support
 An extra flag is used to enable this functionality (flag is not set by default). When the (RTE_HASH_EXTRA_FLAGS_EXT_TABLE) is set and
 in the very unlikely case due to excessive hash collisions that a key has failed to be inserted, the hash table bucket is extended with a linked
 list to insert these failed keys. This feature is important for the workloads (e.g. telco workloads) that need to insert up to 100% of the
-hash table size and can't tolerate any key insertion failure (even if very few). Currently the extendable bucket is not supported
-with the lock-free concurrency implementation (RTE_HASH_EXTRA_FLAGS_RW_CONCURRENCY_LF).
-
+hash table size and can't tolerate any key insertion failure (even if very few).
+Please note that with the 'lock free read/write concurrency' flag enabled, users need to call 'rte_hash_free_key_with_position' API in order to free the empty buckets and
+deleted keys, to maintain the 100% capacity guarantee.
 
 Implementation Details (non Extendable Bucket Case)
 ---------------------------------------------------
diff --git a/lib/librte_hash/rte_cuckoo_hash.c b/lib/librte_hash/rte_cuckoo_hash.c
index c01489ba5193..8213dbf5f782 100644
--- a/lib/librte_hash/rte_cuckoo_hash.c
+++ b/lib/librte_hash/rte_cuckoo_hash.c
@@ -140,6 +140,7 @@ rte_hash_create(const struct rte_hash_parameters *params)
 	unsigned int readwrite_concur_support = 0;
 	unsigned int writer_takes_lock = 0;
 	unsigned int no_free_on_del = 0;
+	uint32_t *ext_bkt_to_free = NULL;
 	uint32_t *tbl_chng_cnt = NULL;
 	unsigned int readwrite_concur_lf_support = 0;
 
@@ -170,15 +171,6 @@ rte_hash_create(const struct rte_hash_parameters *params)
 		return NULL;
 	}
 
-	if ((params->extra_flag & RTE_HASH_EXTRA_FLAGS_RW_CONCURRENCY_LF) &&
-	    (params->extra_flag & RTE_HASH_EXTRA_FLAGS_EXT_TABLE)) {
-		rte_errno = EINVAL;
-		RTE_LOG(ERR, HASH, "rte_hash_create: extendable bucket "
-			"feature not supported with rw concurrency "
-			"lock free\n");
-		return NULL;
-	}
-
 	/* Check extra flags field to check extra options. */
 	if (params->extra_flag & RTE_HASH_EXTRA_FLAGS_TRANS_MEM_SUPPORT)
 		hw_trans_mem_support = 1;
@@ -302,6 +294,16 @@ rte_hash_create(const struct rte_hash_parameters *params)
 		 */
 		for (i = 1; i <= num_buckets; i++)
 			rte_ring_sp_enqueue(r_ext, (void *)((uintptr_t) i));
+
+		if (readwrite_concur_lf_support) {
+			ext_bkt_to_free = rte_zmalloc(NULL, sizeof(uint32_t) *
+								num_key_slots, 0);
+			if (ext_bkt_to_free == NULL) {
+				RTE_LOG(ERR, HASH, "ext bkt to free memory allocation "
+								"failed\n");
+				goto err_unlock;
+			}
+		}
 	}
 
 	const uint32_t key_entry_size =
@@ -393,6 +395,7 @@ rte_hash_create(const struct rte_hash_parameters *params)
 		default_hash_func : params->hash_func;
 	h->key_store = k;
 	h->free_slots = r;
+	h->ext_bkt_to_free = ext_bkt_to_free;
 	h->tbl_chng_cnt = tbl_chng_cnt;
 	*h->tbl_chng_cnt = 0;
 	h->hw_trans_mem_support = hw_trans_mem_support;
@@ -443,6 +446,7 @@ rte_hash_create(const struct rte_hash_parameters *params)
 	rte_free(buckets_ext);
 	rte_free(k);
 	rte_free(tbl_chng_cnt);
+	rte_free(ext_bkt_to_free);
 	return NULL;
 }
 
@@ -484,6 +488,7 @@ rte_hash_free(struct rte_hash *h)
 	rte_free(h->buckets);
 	rte_free(h->buckets_ext);
 	rte_free(h->tbl_chng_cnt);
+	rte_free(h->ext_bkt_to_free);
 	rte_free(h);
 	rte_free(te);
 }
@@ -799,7 +804,7 @@ rte_hash_cuckoo_move_insert_mw(const struct rte_hash *h,
 			__atomic_store_n(h->tbl_chng_cnt,
 					 *h->tbl_chng_cnt + 1,
 					 __ATOMIC_RELEASE);
-			/* The stores to sig_alt and sig_current should not
+			/* The store to sig_current should not
 			 * move above the store to tbl_chng_cnt.
 			 */
 			__atomic_thread_fence(__ATOMIC_RELEASE);
@@ -831,7 +836,7 @@ rte_hash_cuckoo_move_insert_mw(const struct rte_hash *h,
 		__atomic_store_n(h->tbl_chng_cnt,
 				 *h->tbl_chng_cnt + 1,
 				 __ATOMIC_RELEASE);
-		/* The stores to sig_alt and sig_current should not
+		/* The store to sig_current should not
 		 * move above the store to tbl_chng_cnt.
 		 */
 		__atomic_thread_fence(__ATOMIC_RELEASE);
@@ -1054,7 +1059,12 @@ __rte_hash_add_key_with_hash(const struct rte_hash *h, const void *key,
 			/* Check if slot is available */
 			if (likely(cur_bkt->key_idx[i] == EMPTY_SLOT)) {
 				cur_bkt->sig_current[i] = short_sig;
-				cur_bkt->key_idx[i] = new_idx;
+				/* Store to signature should not leak after
+				 * the store to key_idx
+				 */
+				__atomic_store_n(&cur_bkt->key_idx[i],
+						 new_idx,
+						 __ATOMIC_RELEASE);
 				__hash_rw_writer_unlock(h);
 				return new_idx - 1;
 			}
@@ -1072,7 +1082,12 @@ __rte_hash_add_key_with_hash(const struct rte_hash *h, const void *key,
 	bkt_id = (uint32_t)((uintptr_t)ext_bkt_id) - 1;
 	/* Use the first location of the new bucket */
 	(h->buckets_ext[bkt_id]).sig_current[0] = short_sig;
-	(h->buckets_ext[bkt_id]).key_idx[0] = new_idx;
+	/* Store to signature should not leak after
+	 * the store to key_idx
+	 */
+	__atomic_store_n(&(h->buckets_ext[bkt_id]).key_idx[0],
+			 new_idx,
+			 __ATOMIC_RELEASE);
 	/* Link the new bucket to sec bucket linked list */
 	last = rte_hash_get_last_bkt(sec_bkt);
 	last->next = &h->buckets_ext[bkt_id];
@@ -1366,7 +1381,8 @@ remove_entry(const struct rte_hash *h, struct rte_hash_bucket *bkt, unsigned i)
  * empty slot.
  */
 static inline void
-__rte_hash_compact_ll(struct rte_hash_bucket *cur_bkt, int pos) {
+__rte_hash_compact_ll(const struct rte_hash *h,
+			struct rte_hash_bucket *cur_bkt, int pos) {
 	int i;
 	struct rte_hash_bucket *last_bkt;
 
@@ -1377,10 +1393,27 @@ __rte_hash_compact_ll(struct rte_hash_bucket *cur_bkt, int pos) {
 
 	for (i = RTE_HASH_BUCKET_ENTRIES - 1; i >= 0; i--) {
 		if (last_bkt->key_idx[i] != EMPTY_SLOT) {
-			cur_bkt->key_idx[pos] = last_bkt->key_idx[i];
 			cur_bkt->sig_current[pos] = last_bkt->sig_current[i];
+			__atomic_store_n(&cur_bkt->key_idx[pos],
+					 last_bkt->key_idx[i],
+					 __ATOMIC_RELEASE);
+			if (h->readwrite_concur_lf_support) {
+				/* Inform the readers that the table has changed
+				 * Since there is one writer, load acquire on
+				 * tbl_chng_cnt is not required.
+				 */
+				__atomic_store_n(h->tbl_chng_cnt,
+					 *h->tbl_chng_cnt + 1,
+					 __ATOMIC_RELEASE);
+				/* The store to sig_current should
+				 * not move above the store to tbl_chng_cnt.
+				 */
+				__atomic_thread_fence(__ATOMIC_RELEASE);
+			}
 			last_bkt->sig_current[i] = NULL_SIGNATURE;
-			last_bkt->key_idx[i] = EMPTY_SLOT;
+			__atomic_store_n(&last_bkt->key_idx[i],
+					 EMPTY_SLOT,
+					 __ATOMIC_RELEASE);
 			return;
 		}
 	}
@@ -1449,7 +1482,7 @@ __rte_hash_del_key_with_hash(const struct rte_hash *h, const void *key,
 	/* look for key in primary bucket */
 	ret = search_and_remove(h, key, prim_bkt, short_sig, &pos);
 	if (ret != -1) {
-		__rte_hash_compact_ll(prim_bkt, pos);
+		__rte_hash_compact_ll(h, prim_bkt, pos);
 		last_bkt = prim_bkt->next;
 		prev_bkt = prim_bkt;
 		goto return_bkt;
@@ -1461,7 +1494,7 @@ __rte_hash_del_key_with_hash(const struct rte_hash *h, const void *key,
 	FOR_EACH_BUCKET(cur_bkt, sec_bkt) {
 		ret = search_and_remove(h, key, cur_bkt, short_sig, &pos);
 		if (ret != -1) {
-			__rte_hash_compact_ll(cur_bkt, pos);
+			__rte_hash_compact_ll(h, cur_bkt, pos);
 			last_bkt = sec_bkt->next;
 			prev_bkt = sec_bkt;
 			goto return_bkt;
@@ -1488,11 +1521,24 @@ __rte_hash_del_key_with_hash(const struct rte_hash *h, const void *key,
 	}
 	/* found empty bucket and recycle */
 	if (i == RTE_HASH_BUCKET_ENTRIES) {
-		prev_bkt->next = last_bkt->next = NULL;
+		prev_bkt->next = NULL;
 		uint32_t index = last_bkt - h->buckets_ext + 1;
-		rte_ring_sp_enqueue(h->free_ext_bkts, (void *)(uintptr_t)index);
+		/* Recycle the empty bkt if
+		 * no_free_on_del is disabled.
+		 */
+		if (h->no_free_on_del)
+			/* Store index of an empty ext bkt to be recycled
+			 * on calling rte_hash_del_xxx APIs.
+			 * When lock free read-write concurrency is enabled,
+			 * an empty ext bkt cannot be put into free list
+			 * immediately (as readers might be using it still).
+			 * Hence freeing of the ext bkt is piggy-backed to
+			 * freeing of the key index.
+			 */
+			h->ext_bkt_to_free[ret] = index;
+		else
+			rte_ring_sp_enqueue(h->free_ext_bkts, (void *)(uintptr_t)index);
 	}
-
 	__hash_rw_writer_unlock(h);
 	return ret;
 }
@@ -1545,6 +1591,14 @@ rte_hash_free_key_with_position(const struct rte_hash *h,
 	/* Out of bounds */
 	if (position >= total_entries)
 		return -EINVAL;
+	if (h->ext_table_support && h->readwrite_concur_lf_support) {
+		uint32_t index = h->ext_bkt_to_free[position];
+		if (index) {
+			/* Recycle empty ext bkt to free list. */
+			rte_ring_sp_enqueue(h->free_ext_bkts, (void *)(uintptr_t)index);
+			h->ext_bkt_to_free[position] = 0;
+		}
+	}
 
 	if (h->use_local_cache) {
 		lcore_id = rte_lcore_id();
@@ -1855,6 +1909,9 @@ __rte_hash_lookup_bulk_lf(const struct rte_hash *h, const void **keys,
 		rte_prefetch0(secondary_bkt[i]);
 	}
 
+	for (i = 0; i < num_keys; i++)
+		positions[i] = -ENOENT;
+
 	do {
 		/* Load the table change counter before the lookup
 		 * starts. Acquire semantics will make sure that
@@ -1899,7 +1956,6 @@ __rte_hash_lookup_bulk_lf(const struct rte_hash *h, const void **keys,
 
 		/* Compare keys, first hits in primary first */
 		for (i = 0; i < num_keys; i++) {
-			positions[i] = -ENOENT;
 			while (prim_hitmask[i]) {
 				uint32_t hit_index =
 						__builtin_ctzl(prim_hitmask[i])
@@ -1972,6 +2028,35 @@ __rte_hash_lookup_bulk_lf(const struct rte_hash *h, const void **keys,
 			continue;
 		}
 
+		/* all found, do not need to go through ext bkt */
+		if (hits == ((1ULL << num_keys) - 1)) {
+			if (hit_mask != NULL)
+				*hit_mask = hits;
+			return;
+		}
+		/* need to check ext buckets for match */
+		if (h->ext_table_support) {
+			for (i = 0; i < num_keys; i++) {
+				if ((hits & (1ULL << i)) != 0)
+					continue;
+				next_bkt = secondary_bkt[i]->next;
+				FOR_EACH_BUCKET(cur_bkt, next_bkt) {
+					if (data != NULL)
+						ret = search_one_bucket_lf(h,
+							keys[i], sig[i],
+							&data[i], cur_bkt);
+					else
+						ret = search_one_bucket_lf(h,
+								keys[i], sig[i],
+								NULL, cur_bkt);
+					if (ret != -1) {
+						positions[i] = ret;
+						hits |= 1ULL << i;
+						break;
+					}
+				}
+			}
+		}
 		/* The loads of sig_current in compare_signatures
 		 * should not move below the load from tbl_chng_cnt.
 		 */
@@ -1988,34 +2073,6 @@ __rte_hash_lookup_bulk_lf(const struct rte_hash *h, const void **keys,
 					__ATOMIC_ACQUIRE);
 	} while (cnt_b != cnt_a);
 
-	/* all found, do not need to go through ext bkt */
-	if ((hits == ((1ULL << num_keys) - 1)) || !h->ext_table_support) {
-		if (hit_mask != NULL)
-			*hit_mask = hits;
-		__hash_rw_reader_unlock(h);
-		return;
-	}
-
-	/* need to check ext buckets for match */
-	for (i = 0; i < num_keys; i++) {
-		if ((hits & (1ULL << i)) != 0)
-			continue;
-		next_bkt = secondary_bkt[i]->next;
-		FOR_EACH_BUCKET(cur_bkt, next_bkt) {
-			if (data != NULL)
-				ret = search_one_bucket_lf(h, keys[i],
-						sig[i], &data[i], cur_bkt);
-			else
-				ret = search_one_bucket_lf(h, keys[i],
-						sig[i], NULL, cur_bkt);
-			if (ret != -1) {
-				positions[i] = ret;
-				hits |= 1ULL << i;
-				break;
-			}
-		}
-	}
-
 	if (hit_mask != NULL)
 		*hit_mask = hits;
 }
diff --git a/lib/librte_hash/rte_cuckoo_hash.h b/lib/librte_hash/rte_cuckoo_hash.h
index eacdaa8d4684..48c85c890712 100644
--- a/lib/librte_hash/rte_cuckoo_hash.h
+++ b/lib/librte_hash/rte_cuckoo_hash.h
@@ -210,6 +210,13 @@ struct rte_hash {
 	rte_rwlock_t *readwrite_lock; /**< Read-write lock thread-safety. */
 	struct rte_hash_bucket *buckets_ext; /**< Extra buckets array */
 	struct rte_ring *free_ext_bkts; /**< Ring of indexes of free buckets */
+	/* Stores index of an empty ext bkt to be recycled on calling
+	 * rte_hash_del_xxx APIs. When lock free read-write concurrency is
+	 * enabled, an empty ext bkt cannot be put into free list immediately
+	 * (as readers might be using it still). Hence freeing of the ext bkt
+	 * is piggy-backed to freeing of the key index.
+	 */
+	uint32_t *ext_bkt_to_free;
 	uint32_t *tbl_chng_cnt;
 	/**< Indicates if the hash table changed from last read. */
 } __rte_cache_aligned;
-- 
2.17.1

[dpdk-dev] [PATCH v3 1/2] hash: add lock free support for extendable bucket

[Dharmik Thakkar]

This patch enables lock-free read-write concurrency support for
extendable bucket feature.

Suggested-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
Signed-off-by: Dharmik Thakkar <dharmik.thakkar@arm.com>
Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
Reviewed-by: Gavin Hu <gavin.hu@arm.com>
Reviewed-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
Acked-by: Yipeng Wang <yipeng1.wang@intel.com>
---
 doc/guides/prog_guide/hash_lib.rst |   6 +-
 lib/librte_hash/rte_cuckoo_hash.c  | 157 ++++++++++++++++++++---------
 lib/librte_hash/rte_cuckoo_hash.h  |   7 ++
 3 files changed, 117 insertions(+), 53 deletions(-)

diff --git a/doc/guides/prog_guide/hash_lib.rst b/doc/guides/prog_guide/hash_lib.rst
index 85a6edfa8b16..d06c7de2ead1 100644
--- a/doc/guides/prog_guide/hash_lib.rst
+++ b/doc/guides/prog_guide/hash_lib.rst
@@ -108,9 +108,9 @@ Extendable Bucket Functionality support
 An extra flag is used to enable this functionality (flag is not set by default). When the (RTE_HASH_EXTRA_FLAGS_EXT_TABLE) is set and
 in the very unlikely case due to excessive hash collisions that a key has failed to be inserted, the hash table bucket is extended with a linked
 list to insert these failed keys. This feature is important for the workloads (e.g. telco workloads) that need to insert up to 100% of the
-hash table size and can't tolerate any key insertion failure (even if very few). Currently the extendable bucket is not supported
-with the lock-free concurrency implementation (RTE_HASH_EXTRA_FLAGS_RW_CONCURRENCY_LF).
-
+hash table size and can't tolerate any key insertion failure (even if very few).
+Please note that with the 'lock free read/write concurrency' flag enabled, users need to call 'rte_hash_free_key_with_position' API in order to free the empty buckets and
+deleted keys, to maintain the 100% capacity guarantee.
 
 Implementation Details (non Extendable Bucket Case)
 ---------------------------------------------------
diff --git a/lib/librte_hash/rte_cuckoo_hash.c b/lib/librte_hash/rte_cuckoo_hash.c
index c01489ba5193..8213dbf5f782 100644
--- a/lib/librte_hash/rte_cuckoo_hash.c
+++ b/lib/librte_hash/rte_cuckoo_hash.c
@@ -140,6 +140,7 @@ rte_hash_create(const struct rte_hash_parameters *params)
 	unsigned int readwrite_concur_support = 0;
 	unsigned int writer_takes_lock = 0;
 	unsigned int no_free_on_del = 0;
+	uint32_t *ext_bkt_to_free = NULL;
 	uint32_t *tbl_chng_cnt = NULL;
 	unsigned int readwrite_concur_lf_support = 0;
 
@@ -170,15 +171,6 @@ rte_hash_create(const struct rte_hash_parameters *params)
 		return NULL;
 	}
 
-	if ((params->extra_flag & RTE_HASH_EXTRA_FLAGS_RW_CONCURRENCY_LF) &&
-	    (params->extra_flag & RTE_HASH_EXTRA_FLAGS_EXT_TABLE)) {
-		rte_errno = EINVAL;
-		RTE_LOG(ERR, HASH, "rte_hash_create: extendable bucket "
-			"feature not supported with rw concurrency "
-			"lock free\n");
-		return NULL;
-	}
-
 	/* Check extra flags field to check extra options. */
 	if (params->extra_flag & RTE_HASH_EXTRA_FLAGS_TRANS_MEM_SUPPORT)
 		hw_trans_mem_support = 1;
@@ -302,6 +294,16 @@ rte_hash_create(const struct rte_hash_parameters *params)
 		 */
 		for (i = 1; i <= num_buckets; i++)
 			rte_ring_sp_enqueue(r_ext, (void *)((uintptr_t) i));
+
+		if (readwrite_concur_lf_support) {
+			ext_bkt_to_free = rte_zmalloc(NULL, sizeof(uint32_t) *
+								num_key_slots, 0);
+			if (ext_bkt_to_free == NULL) {
+				RTE_LOG(ERR, HASH, "ext bkt to free memory allocation "
+								"failed\n");
+				goto err_unlock;
+			}
+		}
 	}
 
 	const uint32_t key_entry_size =
@@ -393,6 +395,7 @@ rte_hash_create(const struct rte_hash_parameters *params)
 		default_hash_func : params->hash_func;
 	h->key_store = k;
 	h->free_slots = r;
+	h->ext_bkt_to_free = ext_bkt_to_free;
 	h->tbl_chng_cnt = tbl_chng_cnt;
 	*h->tbl_chng_cnt = 0;
 	h->hw_trans_mem_support = hw_trans_mem_support;
@@ -443,6 +446,7 @@ rte_hash_create(const struct rte_hash_parameters *params)
 	rte_free(buckets_ext);
 	rte_free(k);
 	rte_free(tbl_chng_cnt);
+	rte_free(ext_bkt_to_free);
 	return NULL;
 }
 
@@ -484,6 +488,7 @@ rte_hash_free(struct rte_hash *h)
 	rte_free(h->buckets);
 	rte_free(h->buckets_ext);
 	rte_free(h->tbl_chng_cnt);
+	rte_free(h->ext_bkt_to_free);
 	rte_free(h);
 	rte_free(te);
 }
@@ -799,7 +804,7 @@ rte_hash_cuckoo_move_insert_mw(const struct rte_hash *h,
 			__atomic_store_n(h->tbl_chng_cnt,
 					 *h->tbl_chng_cnt + 1,
 					 __ATOMIC_RELEASE);
-			/* The stores to sig_alt and sig_current should not
+			/* The store to sig_current should not
 			 * move above the store to tbl_chng_cnt.
 			 */
 			__atomic_thread_fence(__ATOMIC_RELEASE);
@@ -831,7 +836,7 @@ rte_hash_cuckoo_move_insert_mw(const struct rte_hash *h,
 		__atomic_store_n(h->tbl_chng_cnt,
 				 *h->tbl_chng_cnt + 1,
 				 __ATOMIC_RELEASE);
-		/* The stores to sig_alt and sig_current should not
+		/* The store to sig_current should not
 		 * move above the store to tbl_chng_cnt.
 		 */
 		__atomic_thread_fence(__ATOMIC_RELEASE);
@@ -1054,7 +1059,12 @@ __rte_hash_add_key_with_hash(const struct rte_hash *h, const void *key,
 			/* Check if slot is available */
 			if (likely(cur_bkt->key_idx[i] == EMPTY_SLOT)) {
 				cur_bkt->sig_current[i] = short_sig;
-				cur_bkt->key_idx[i] = new_idx;
+				/* Store to signature should not leak after
+				 * the store to key_idx
+				 */
+				__atomic_store_n(&cur_bkt->key_idx[i],
+						 new_idx,
+						 __ATOMIC_RELEASE);
 				__hash_rw_writer_unlock(h);
 				return new_idx - 1;
 			}
@@ -1072,7 +1082,12 @@ __rte_hash_add_key_with_hash(const struct rte_hash *h, const void *key,
 	bkt_id = (uint32_t)((uintptr_t)ext_bkt_id) - 1;
 	/* Use the first location of the new bucket */
 	(h->buckets_ext[bkt_id]).sig_current[0] = short_sig;
-	(h->buckets_ext[bkt_id]).key_idx[0] = new_idx;
+	/* Store to signature should not leak after
+	 * the store to key_idx
+	 */
+	__atomic_store_n(&(h->buckets_ext[bkt_id]).key_idx[0],
+			 new_idx,
+			 __ATOMIC_RELEASE);
 	/* Link the new bucket to sec bucket linked list */
 	last = rte_hash_get_last_bkt(sec_bkt);
 	last->next = &h->buckets_ext[bkt_id];
@@ -1366,7 +1381,8 @@ remove_entry(const struct rte_hash *h, struct rte_hash_bucket *bkt, unsigned i)
  * empty slot.
  */
 static inline void
-__rte_hash_compact_ll(struct rte_hash_bucket *cur_bkt, int pos) {
+__rte_hash_compact_ll(const struct rte_hash *h,
+			struct rte_hash_bucket *cur_bkt, int pos) {
 	int i;
 	struct rte_hash_bucket *last_bkt;
 
@@ -1377,10 +1393,27 @@ __rte_hash_compact_ll(struct rte_hash_bucket *cur_bkt, int pos) {
 
 	for (i = RTE_HASH_BUCKET_ENTRIES - 1; i >= 0; i--) {
 		if (last_bkt->key_idx[i] != EMPTY_SLOT) {
-			cur_bkt->key_idx[pos] = last_bkt->key_idx[i];
 			cur_bkt->sig_current[pos] = last_bkt->sig_current[i];
+			__atomic_store_n(&cur_bkt->key_idx[pos],
+					 last_bkt->key_idx[i],
+					 __ATOMIC_RELEASE);
+			if (h->readwrite_concur_lf_support) {
+				/* Inform the readers that the table has changed
+				 * Since there is one writer, load acquire on
+				 * tbl_chng_cnt is not required.
+				 */
+				__atomic_store_n(h->tbl_chng_cnt,
+					 *h->tbl_chng_cnt + 1,
+					 __ATOMIC_RELEASE);
+				/* The store to sig_current should
+				 * not move above the store to tbl_chng_cnt.
+				 */
+				__atomic_thread_fence(__ATOMIC_RELEASE);
+			}
 			last_bkt->sig_current[i] = NULL_SIGNATURE;
-			last_bkt->key_idx[i] = EMPTY_SLOT;
+			__atomic_store_n(&last_bkt->key_idx[i],
+					 EMPTY_SLOT,
+					 __ATOMIC_RELEASE);
 			return;
 		}
 	}
@@ -1449,7 +1482,7 @@ __rte_hash_del_key_with_hash(const struct rte_hash *h, const void *key,
 	/* look for key in primary bucket */
 	ret = search_and_remove(h, key, prim_bkt, short_sig, &pos);
 	if (ret != -1) {
-		__rte_hash_compact_ll(prim_bkt, pos);
+		__rte_hash_compact_ll(h, prim_bkt, pos);
 		last_bkt = prim_bkt->next;
 		prev_bkt = prim_bkt;
 		goto return_bkt;
@@ -1461,7 +1494,7 @@ __rte_hash_del_key_with_hash(const struct rte_hash *h, const void *key,
 	FOR_EACH_BUCKET(cur_bkt, sec_bkt) {
 		ret = search_and_remove(h, key, cur_bkt, short_sig, &pos);
 		if (ret != -1) {
-			__rte_hash_compact_ll(cur_bkt, pos);
+			__rte_hash_compact_ll(h, cur_bkt, pos);
 			last_bkt = sec_bkt->next;
 			prev_bkt = sec_bkt;
 			goto return_bkt;
@@ -1488,11 +1521,24 @@ __rte_hash_del_key_with_hash(const struct rte_hash *h, const void *key,
 	}
 	/* found empty bucket and recycle */
 	if (i == RTE_HASH_BUCKET_ENTRIES) {
-		prev_bkt->next = last_bkt->next = NULL;
+		prev_bkt->next = NULL;
 		uint32_t index = last_bkt - h->buckets_ext + 1;
-		rte_ring_sp_enqueue(h->free_ext_bkts, (void *)(uintptr_t)index);
+		/* Recycle the empty bkt if
+		 * no_free_on_del is disabled.
+		 */
+		if (h->no_free_on_del)
+			/* Store index of an empty ext bkt to be recycled
+			 * on calling rte_hash_del_xxx APIs.
+			 * When lock free read-write concurrency is enabled,
+			 * an empty ext bkt cannot be put into free list
+			 * immediately (as readers might be using it still).
+			 * Hence freeing of the ext bkt is piggy-backed to
+			 * freeing of the key index.
+			 */
+			h->ext_bkt_to_free[ret] = index;
+		else
+			rte_ring_sp_enqueue(h->free_ext_bkts, (void *)(uintptr_t)index);
 	}
-
 	__hash_rw_writer_unlock(h);
 	return ret;
 }
@@ -1545,6 +1591,14 @@ rte_hash_free_key_with_position(const struct rte_hash *h,
 	/* Out of bounds */
 	if (position >= total_entries)
 		return -EINVAL;
+	if (h->ext_table_support && h->readwrite_concur_lf_support) {
+		uint32_t index = h->ext_bkt_to_free[position];
+		if (index) {
+			/* Recycle empty ext bkt to free list. */
+			rte_ring_sp_enqueue(h->free_ext_bkts, (void *)(uintptr_t)index);
+			h->ext_bkt_to_free[position] = 0;
+		}
+	}
 
 	if (h->use_local_cache) {
 		lcore_id = rte_lcore_id();
@@ -1855,6 +1909,9 @@ __rte_hash_lookup_bulk_lf(const struct rte_hash *h, const void **keys,
 		rte_prefetch0(secondary_bkt[i]);
 	}
 
+	for (i = 0; i < num_keys; i++)
+		positions[i] = -ENOENT;
+
 	do {
 		/* Load the table change counter before the lookup
 		 * starts. Acquire semantics will make sure that
@@ -1899,7 +1956,6 @@ __rte_hash_lookup_bulk_lf(const struct rte_hash *h, const void **keys,
 
 		/* Compare keys, first hits in primary first */
 		for (i = 0; i < num_keys; i++) {
-			positions[i] = -ENOENT;
 			while (prim_hitmask[i]) {
 				uint32_t hit_index =
 						__builtin_ctzl(prim_hitmask[i])
@@ -1972,6 +2028,35 @@ __rte_hash_lookup_bulk_lf(const struct rte_hash *h, const void **keys,
 			continue;
 		}
 
+		/* all found, do not need to go through ext bkt */
+		if (hits == ((1ULL << num_keys) - 1)) {
+			if (hit_mask != NULL)
+				*hit_mask = hits;
+			return;
+		}
+		/* need to check ext buckets for match */
+		if (h->ext_table_support) {
+			for (i = 0; i < num_keys; i++) {
+				if ((hits & (1ULL << i)) != 0)
+					continue;
+				next_bkt = secondary_bkt[i]->next;
+				FOR_EACH_BUCKET(cur_bkt, next_bkt) {
+					if (data != NULL)
+						ret = search_one_bucket_lf(h,
+							keys[i], sig[i],
+							&data[i], cur_bkt);
+					else
+						ret = search_one_bucket_lf(h,
+								keys[i], sig[i],
+								NULL, cur_bkt);
+					if (ret != -1) {
+						positions[i] = ret;
+						hits |= 1ULL << i;
+						break;
+					}
+				}
+			}
+		}
 		/* The loads of sig_current in compare_signatures
 		 * should not move below the load from tbl_chng_cnt.
 		 */
@@ -1988,34 +2073,6 @@ __rte_hash_lookup_bulk_lf(const struct rte_hash *h, const void **keys,
 					__ATOMIC_ACQUIRE);
 	} while (cnt_b != cnt_a);
 
-	/* all found, do not need to go through ext bkt */
-	if ((hits == ((1ULL << num_keys) - 1)) || !h->ext_table_support) {
-		if (hit_mask != NULL)
-			*hit_mask = hits;
-		__hash_rw_reader_unlock(h);
-		return;
-	}
-
-	/* need to check ext buckets for match */
-	for (i = 0; i < num_keys; i++) {
-		if ((hits & (1ULL << i)) != 0)
-			continue;
-		next_bkt = secondary_bkt[i]->next;
-		FOR_EACH_BUCKET(cur_bkt, next_bkt) {
-			if (data != NULL)
-				ret = search_one_bucket_lf(h, keys[i],
-						sig[i], &data[i], cur_bkt);
-			else
-				ret = search_one_bucket_lf(h, keys[i],
-						sig[i], NULL, cur_bkt);
-			if (ret != -1) {
-				positions[i] = ret;
-				hits |= 1ULL << i;
-				break;
-			}
-		}
-	}
-
 	if (hit_mask != NULL)
 		*hit_mask = hits;
 }
diff --git a/lib/librte_hash/rte_cuckoo_hash.h b/lib/librte_hash/rte_cuckoo_hash.h
index eacdaa8d4684..48c85c890712 100644
--- a/lib/librte_hash/rte_cuckoo_hash.h
+++ b/lib/librte_hash/rte_cuckoo_hash.h
@@ -210,6 +210,13 @@ struct rte_hash {
 	rte_rwlock_t *readwrite_lock; /**< Read-write lock thread-safety. */
 	struct rte_hash_bucket *buckets_ext; /**< Extra buckets array */
 	struct rte_ring *free_ext_bkts; /**< Ring of indexes of free buckets */
+	/* Stores index of an empty ext bkt to be recycled on calling
+	 * rte_hash_del_xxx APIs. When lock free read-write concurrency is
+	 * enabled, an empty ext bkt cannot be put into free list immediately
+	 * (as readers might be using it still). Hence freeing of the ext bkt
+	 * is piggy-backed to freeing of the key index.
+	 */
+	uint32_t *ext_bkt_to_free;
 	uint32_t *tbl_chng_cnt;
 	/**< Indicates if the hash table changed from last read. */
 } __rte_cache_aligned;
-- 
2.17.1

[dpdk-dev] [PATCH v3 2/2] test/hash: lock-free rw concurrency test ext bkt

[Dharmik Thakkar]

Add unit test to check for hash lookup and bulk-lookup perf for
extendable bucket feature.
It is tested with both lock-free enabled and lock-free disabled case.

Test includes:

- hash lookup on keys in ext bkt
- hash delete causing key-shifts of keys from ext bkt to secondary bkt

Suggested-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
Signed-off-by: Dharmik Thakkar <dharmik.thakkar@arm.com>
---
 app/test/test_hash_readwrite_lf.c | 350 ++++++++++++++++++++++++------
 1 file changed, 284 insertions(+), 66 deletions(-)

diff --git a/app/test/test_hash_readwrite_lf.c b/app/test/test_hash_readwrite_lf.c
index cbfd9322696b..ddd8d7aa6a7d 100644
--- a/app/test/test_hash_readwrite_lf.c
+++ b/app/test/test_hash_readwrite_lf.c
@@ -41,6 +41,12 @@
 #define READ_PASS_SHIFT_PATH 4
 #define READ_PASS_NON_SHIFT_PATH 8
 #define BULK_LOOKUP 16
+#define READ_PASS_KEY_SHIFTS_EXTBKT 32
+
+#define WRITE_NO_KEY_SHIFT 0
+#define WRITE_KEY_SHIFT 1
+#define WRITE_EXT_BKT 2
+
 #define NUM_TEST 3
 unsigned int rwc_core_cnt[NUM_TEST] = {1, 2, 4};
 
@@ -51,6 +57,7 @@ struct rwc_perf {
 	uint32_t w_ks_r_hit_sp[2][NUM_TEST];
 	uint32_t w_ks_r_miss[2][NUM_TEST];
 	uint32_t multi_rw[NUM_TEST - 1][2][NUM_TEST];
+	uint32_t w_ks_r_hit_extbkt[2][NUM_TEST];
 };
 
 static struct rwc_perf rwc_lf_results, rwc_non_lf_results;
@@ -62,11 +69,15 @@ struct {
 	uint32_t *keys_absent;
 	uint32_t *keys_shift_path;
 	uint32_t *keys_non_shift_path;
+	uint32_t *keys_ext_bkt;
+	uint32_t *keys_ks_extbkt;
 	uint32_t count_keys_no_ks;
 	uint32_t count_keys_ks;
 	uint32_t count_keys_absent;
 	uint32_t count_keys_shift_path;
 	uint32_t count_keys_non_shift_path;
+	uint32_t count_keys_extbkt;
+	uint32_t count_keys_ks_extbkt;
 	uint32_t single_insert;
 	struct rte_hash *h;
 } tbl_rwc_test_param;
@@ -81,6 +92,35 @@ uint16_t enabled_core_ids[RTE_MAX_LCORE];
 
 uint8_t *scanned_bkts;
 
+static inline uint16_t
+get_short_sig(const hash_sig_t hash)
+{
+	return hash >> 16;
+}
+
+static inline uint32_t
+get_prim_bucket_index(__attribute__((unused)) const struct rte_hash *h,
+		      const hash_sig_t hash)
+{
+	uint32_t num_buckets;
+	uint32_t bucket_bitmask;
+	num_buckets  = rte_align32pow2(TOTAL_ENTRY) / 8;
+	bucket_bitmask = num_buckets - 1;
+	return hash & bucket_bitmask;
+}
+
+static inline uint32_t
+get_alt_bucket_index(__attribute__((unused)) const struct rte_hash *h,
+			uint32_t cur_bkt_idx, uint16_t sig)
+{
+	uint32_t num_buckets;
+	uint32_t bucket_bitmask;
+	num_buckets  = rte_align32pow2(TOTAL_ENTRY) / 8;
+	bucket_bitmask = num_buckets - 1;
+	return (cur_bkt_idx ^ sig) & bucket_bitmask;
+}
+
+
 static inline int
 get_enabled_cores_list(void)
 {
@@ -168,9 +208,12 @@ generate_keys(void)
 	uint32_t *keys_ks = NULL;
 	uint32_t *keys_absent = NULL;
 	uint32_t *keys_non_shift_path = NULL;
+	uint32_t *keys_ext_bkt = NULL;
+	uint32_t *keys_ks_extbkt = NULL;
 	uint32_t *found = NULL;
 	uint32_t count_keys_no_ks = 0;
 	uint32_t count_keys_ks = 0;
+	uint32_t count_keys_extbkt = 0;
 	uint32_t i;
 
 	/*
@@ -251,14 +294,32 @@ generate_keys(void)
 		goto err;
 	}
 
+	/*
+	 * This consist of keys which will be stored in extended buckets
+	 */
+	keys_ext_bkt = rte_malloc(NULL, sizeof(uint32_t) * TOTAL_INSERT, 0);
+	if (keys_ext_bkt == NULL) {
+		printf("RTE_MALLOC failed\n");
+		goto err;
+	}
+
+	/*
+	 * This consist of keys which when deleted causes shifting of keys
+	 * in extended buckets to respective secondary buckets
+	 */
+	keys_ks_extbkt = rte_malloc(NULL, sizeof(uint32_t) * TOTAL_INSERT, 0);
+	if (keys_ks_extbkt == NULL) {
+		printf("RTE_MALLOC failed\n");
+		goto err;
+	}
 
 	hash_sig_t sig;
 	uint32_t prim_bucket_idx;
-	int ret;
+	uint32_t sec_bucket_idx;
+	uint16_t short_sig;
 	uint32_t num_buckets;
-	uint32_t bucket_bitmask;
 	num_buckets  = rte_align32pow2(TOTAL_ENTRY) / 8;
-	bucket_bitmask = num_buckets - 1;
+	int ret;
 
 	/*
 	 * Used to mark bkts in which at least one key was shifted to its
@@ -275,6 +336,8 @@ generate_keys(void)
 	tbl_rwc_test_param.keys_ks = keys_ks;
 	tbl_rwc_test_param.keys_absent = keys_absent;
 	tbl_rwc_test_param.keys_non_shift_path = keys_non_shift_path;
+	tbl_rwc_test_param.keys_ext_bkt = keys_ext_bkt;
+	tbl_rwc_test_param.keys_ks_extbkt = keys_ks_extbkt;
 	/* Generate keys by adding previous two keys, neglect overflow */
 	printf("Generating keys...\n");
 	keys[0] = 0;
@@ -287,7 +350,8 @@ generate_keys(void)
 		/* Check if primary bucket has space.*/
 		sig = rte_hash_hash(tbl_rwc_test_param.h,
 					tbl_rwc_test_param.keys+i);
-		prim_bucket_idx = sig & bucket_bitmask;
+		prim_bucket_idx = get_prim_bucket_index(tbl_rwc_test_param.h,
+							sig);
 		ret = check_bucket(prim_bucket_idx, keys[i]);
 		if (ret < 0) {
 			/*
@@ -368,6 +432,47 @@ generate_keys(void)
 	tbl_rwc_test_param.count_keys_absent = count_keys_absent;
 	tbl_rwc_test_param.count_keys_non_shift_path = count;
 
+	memset(scanned_bkts, 0, num_buckets);
+	count = 0;
+	/* Find keys that will be in extended buckets */
+	for (i = 0; i < count_keys_ks; i++) {
+		ret = rte_hash_add_key(tbl_rwc_test_param.h, keys_ks + i);
+		if (ret < 0) {
+			/* Key will be added to ext bkt */
+			keys_ext_bkt[count_keys_extbkt++] = keys_ks[i];
+			/* Sec bkt to be added to keys_ks_extbkt */
+			sig = rte_hash_hash(tbl_rwc_test_param.h,
+					tbl_rwc_test_param.keys_ks + i);
+			prim_bucket_idx = get_prim_bucket_index(
+						tbl_rwc_test_param.h, sig);
+			short_sig = get_short_sig(sig);
+			sec_bucket_idx = get_alt_bucket_index(
+						tbl_rwc_test_param.h,
+						prim_bucket_idx, short_sig);
+			if (scanned_bkts[sec_bucket_idx] == 0)
+				scanned_bkts[sec_bucket_idx] = 1;
+		}
+	}
+
+	/* Find keys that will shift keys in ext bucket*/
+	for (i = 0; i < num_buckets; i++) {
+		if (scanned_bkts[i] == 1) {
+			iter = i * 8;
+			while (rte_hash_iterate(tbl_rwc_test_param.h,
+				&next_key, &next_data, &iter) >= 0) {
+				/* Check if key belongs to the current bucket */
+				if (i >= (iter-1)/8)
+					keys_ks_extbkt[count++]
+						= *(const uint32_t *)next_key;
+				else
+					break;
+			}
+		}
+	}
+
+	tbl_rwc_test_param.count_keys_ks_extbkt = count;
+	tbl_rwc_test_param.count_keys_extbkt = count_keys_extbkt;
+
 	printf("\nCount of keys NOT causing shifting of existing keys to "
 	"alternate location: %d\n", tbl_rwc_test_param.count_keys_no_ks);
 	printf("\nCount of keys causing shifting of existing keys to alternate "
@@ -378,6 +483,10 @@ generate_keys(void)
 	       tbl_rwc_test_param.count_keys_shift_path);
 	printf("Count of keys not likely to be on the shift path: %d\n\n",
 	       tbl_rwc_test_param.count_keys_non_shift_path);
+	printf("Count of keys in extended buckets: %d\n\n",
+	       tbl_rwc_test_param.count_keys_extbkt);
+	printf("Count of keys shifting keys in ext buckets: %d\n\n",
+	       tbl_rwc_test_param.count_keys_ks_extbkt);
 
 	rte_free(found);
 	rte_hash_free(tbl_rwc_test_param.h);
@@ -390,12 +499,14 @@ generate_keys(void)
 	rte_free(keys_absent);
 	rte_free(found);
 	rte_free(tbl_rwc_test_param.keys_shift_path);
+	rte_free(keys_ext_bkt);
+	rte_free(keys_ks_extbkt);
 	rte_free(scanned_bkts);
 	return -1;
 }
 
 static int
-init_params(int rwc_lf, int use_jhash, int htm)
+init_params(int rwc_lf, int use_jhash, int htm, int ext_bkt)
 {
 	struct rte_hash *handle;
 
@@ -425,6 +536,9 @@ init_params(int rwc_lf, int use_jhash, int htm)
 			RTE_HASH_EXTRA_FLAGS_RW_CONCURRENCY |
 			RTE_HASH_EXTRA_FLAGS_MULTI_WRITER_ADD;
 
+	if (ext_bkt)
+		hash_params.extra_flag |= RTE_HASH_EXTRA_FLAGS_EXT_TABLE;
+
 	hash_params.name = "tests";
 
 	handle = rte_hash_create(&hash_params);
@@ -452,7 +566,7 @@ test_rwc_reader(__attribute__((unused)) void *arg)
 	void *temp_a[BULK_LOOKUP_SIZE];
 
 	/* Used to identify keys not inserted in the hash table */
-	pos = rte_zmalloc(NULL, sizeof(uint32_t) * BULK_LOOKUP_SIZE, 0);
+	pos = rte_malloc(NULL, sizeof(uint32_t) * BULK_LOOKUP_SIZE, 0);
 	if (pos == NULL) {
 		printf("RTE_MALLOC failed\n");
 		return -1;
@@ -467,6 +581,9 @@ test_rwc_reader(__attribute__((unused)) void *arg)
 	} else if (read_type & READ_PASS_SHIFT_PATH) {
 		keys = tbl_rwc_test_param.keys_shift_path;
 		read_cnt = tbl_rwc_test_param.count_keys_shift_path;
+	} else if (read_type & READ_PASS_KEY_SHIFTS_EXTBKT) {
+		keys = tbl_rwc_test_param.keys_ext_bkt;
+		read_cnt = tbl_rwc_test_param.count_keys_extbkt;
 	} else {
 		keys = tbl_rwc_test_param.keys_non_shift_path;
 		read_cnt = tbl_rwc_test_param.count_keys_non_shift_path;
@@ -482,7 +599,6 @@ test_rwc_reader(__attribute__((unused)) void *arg)
 				/* Array of  pointer to the list of keys */
 				for (j = 0; j < BULK_LOOKUP_SIZE; j++)
 					temp_a[j] = keys + i + j;
-
 				rte_hash_lookup_bulk(tbl_rwc_test_param.h,
 						   (const void **)
 						   ((uintptr_t)temp_a),
@@ -539,22 +655,25 @@ test_rwc_reader(__attribute__((unused)) void *arg)
 }
 
 static int
-write_keys(uint8_t key_shift)
+write_keys(uint8_t write_type)
 {
 	uint32_t i;
 	int ret;
 	uint32_t key_cnt;
 	uint32_t *keys;
-	if (key_shift) {
+	if (write_type == WRITE_KEY_SHIFT) {
 		key_cnt = tbl_rwc_test_param.count_keys_ks;
 		keys = tbl_rwc_test_param.keys_ks;
-	} else {
+	} else if (write_type == WRITE_NO_KEY_SHIFT) {
 		key_cnt = tbl_rwc_test_param.count_keys_no_ks;
 		keys = tbl_rwc_test_param.keys_no_ks;
+	} else if (write_type == WRITE_EXT_BKT) {
+		key_cnt = tbl_rwc_test_param.count_keys_extbkt;
+		keys = tbl_rwc_test_param.keys_ext_bkt;
 	}
 	for (i = 0; i < key_cnt; i++) {
 		ret = rte_hash_add_key(tbl_rwc_test_param.h, keys + i);
-		if (!key_shift && ret < 0) {
+		if ((write_type == WRITE_NO_KEY_SHIFT) && ret < 0) {
 			printf("writer failed %"PRIu32"\n", i);
 			return -1;
 		}
@@ -581,18 +700,18 @@ test_rwc_multi_writer(__attribute__((unused)) void *arg)
  */
 static int
 test_hash_add_no_ks_lookup_hit(struct rwc_perf *rwc_perf_results, int rwc_lf,
-				int htm)
+				int htm, int ext_bkt)
 {
 	unsigned int n, m;
 	uint64_t i;
 	int use_jhash = 0;
-	uint8_t key_shift = 0;
+	uint8_t write_type = WRITE_NO_KEY_SHIFT;
 	uint8_t read_type = READ_PASS_NO_KEY_SHIFTS;
 
 	rte_atomic64_init(&greads);
 	rte_atomic64_init(&gread_cycles);
 
-	if (init_params(rwc_lf, use_jhash, htm) != 0)
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
 		goto err;
 	printf("\nTest: Hash add - no key-shifts, read - hit\n");
 	for (m = 0; m < 2; m++) {
@@ -612,7 +731,7 @@ test_hash_add_no_ks_lookup_hit(struct rwc_perf *rwc_perf_results, int rwc_lf,
 
 			rte_hash_reset(tbl_rwc_test_param.h);
 			writer_done = 0;
-			if (write_keys(key_shift) < 0)
+			if (write_keys(write_type) < 0)
 				goto err;
 			writer_done = 1;
 			for (i = 1; i <= rwc_core_cnt[n]; i++)
@@ -650,19 +769,19 @@ test_hash_add_no_ks_lookup_hit(struct rwc_perf *rwc_perf_results, int rwc_lf,
  */
 static int
 test_hash_add_no_ks_lookup_miss(struct rwc_perf *rwc_perf_results, int rwc_lf,
-				int htm)
+				int htm, int ext_bkt)
 {
 	unsigned int n, m;
 	uint64_t i;
 	int use_jhash = 0;
-	uint8_t key_shift = 0;
+	uint8_t write_type = WRITE_NO_KEY_SHIFT;
 	uint8_t read_type = READ_FAIL;
 	int ret;
 
 	rte_atomic64_init(&greads);
 	rte_atomic64_init(&gread_cycles);
 
-	if (init_params(rwc_lf, use_jhash, htm) != 0)
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
 		goto err;
 	printf("\nTest: Hash add - no key-shifts, Hash lookup - miss\n");
 	for (m = 0; m < 2; m++) {
@@ -687,7 +806,7 @@ test_hash_add_no_ks_lookup_miss(struct rwc_perf *rwc_perf_results, int rwc_lf,
 				rte_eal_remote_launch(test_rwc_reader,
 						(void *)(uintptr_t)read_type,
 							enabled_core_ids[i]);
-			ret = write_keys(key_shift);
+			ret = write_keys(write_type);
 			writer_done = 1;
 			rte_eal_mp_wait_lcore();
 
@@ -722,19 +841,19 @@ test_hash_add_no_ks_lookup_miss(struct rwc_perf *rwc_perf_results, int rwc_lf,
  */
 static int
 test_hash_add_ks_lookup_hit_non_sp(struct rwc_perf *rwc_perf_results,
-				    int rwc_lf, int htm)
+				    int rwc_lf, int htm, int ext_bkt)
 {
 	unsigned int n, m;
 	uint64_t i;
 	int use_jhash = 0;
 	int ret;
-	uint8_t key_shift;
+	uint8_t write_type;
 	uint8_t read_type = READ_PASS_NON_SHIFT_PATH;
 
 	rte_atomic64_init(&greads);
 	rte_atomic64_init(&gread_cycles);
 
-	if (init_params(rwc_lf, use_jhash, htm) != 0)
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
 		goto err;
 	printf("\nTest: Hash add - key shift, Hash lookup - hit"
 	       " (non-shift-path)\n");
@@ -755,15 +874,15 @@ test_hash_add_ks_lookup_hit_non_sp(struct rwc_perf *rwc_perf_results,
 
 			rte_hash_reset(tbl_rwc_test_param.h);
 			writer_done = 0;
-			key_shift = 0;
-			if (write_keys(key_shift) < 0)
+			write_type = WRITE_NO_KEY_SHIFT;
+			if (write_keys(write_type) < 0)
 				goto err;
 			for (i = 1; i <= rwc_core_cnt[n]; i++)
 				rte_eal_remote_launch(test_rwc_reader,
 						(void *)(uintptr_t)read_type,
 							enabled_core_ids[i]);
-			key_shift = 1;
-			ret = write_keys(key_shift);
+			write_type = WRITE_KEY_SHIFT;
+			ret = write_keys(write_type);
 			writer_done = 1;
 			rte_eal_mp_wait_lcore();
 
@@ -798,19 +917,19 @@ test_hash_add_ks_lookup_hit_non_sp(struct rwc_perf *rwc_perf_results,
  */
 static int
 test_hash_add_ks_lookup_hit_sp(struct rwc_perf *rwc_perf_results, int rwc_lf,
-				int htm)
+				int htm, int ext_bkt)
 {
 	unsigned int n, m;
 	uint64_t i;
 	int use_jhash = 0;
 	int ret;
-	uint8_t key_shift;
+	uint8_t write_type;
 	uint8_t read_type = READ_PASS_SHIFT_PATH;
 
 	rte_atomic64_init(&greads);
 	rte_atomic64_init(&gread_cycles);
 
-	if (init_params(rwc_lf, use_jhash, htm) != 0)
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
 		goto err;
 	printf("\nTest: Hash add - key shift, Hash lookup - hit (shift-path)"
 	       "\n");
@@ -831,15 +950,15 @@ test_hash_add_ks_lookup_hit_sp(struct rwc_perf *rwc_perf_results, int rwc_lf,
 
 			rte_hash_reset(tbl_rwc_test_param.h);
 			writer_done = 0;
-			key_shift = 0;
-			if (write_keys(key_shift) < 0)
+			write_type = WRITE_NO_KEY_SHIFT;
+			if (write_keys(write_type) < 0)
 				goto err;
 			for (i = 1; i <= rwc_core_cnt[n]; i++)
 				rte_eal_remote_launch(test_rwc_reader,
 						(void *)(uintptr_t)read_type,
 						enabled_core_ids[i]);
-			key_shift = 1;
-			ret = write_keys(key_shift);
+			write_type = WRITE_KEY_SHIFT;
+			ret = write_keys(write_type);
 			writer_done = 1;
 			rte_eal_mp_wait_lcore();
 
@@ -874,19 +993,19 @@ test_hash_add_ks_lookup_hit_sp(struct rwc_perf *rwc_perf_results, int rwc_lf,
  */
 static int
 test_hash_add_ks_lookup_miss(struct rwc_perf *rwc_perf_results, int rwc_lf, int
-			     htm)
+			     htm, int ext_bkt)
 {
 	unsigned int n, m;
 	uint64_t i;
 	int use_jhash = 0;
 	int ret;
-	uint8_t key_shift;
+	uint8_t write_type;
 	uint8_t read_type = READ_FAIL;
 
 	rte_atomic64_init(&greads);
 	rte_atomic64_init(&gread_cycles);
 
-	if (init_params(rwc_lf, use_jhash, htm) != 0)
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
 		goto err;
 	printf("\nTest: Hash add - key shift, Hash lookup - miss\n");
 	for (m = 0; m < 2; m++) {
@@ -906,15 +1025,15 @@ test_hash_add_ks_lookup_miss(struct rwc_perf *rwc_perf_results, int rwc_lf, int
 
 			rte_hash_reset(tbl_rwc_test_param.h);
 			writer_done = 0;
-			key_shift = 0;
-			if (write_keys(key_shift) < 0)
+			write_type = WRITE_NO_KEY_SHIFT;
+			if (write_keys(write_type) < 0)
 				goto err;
 			for (i = 1; i <= rwc_core_cnt[n]; i++)
 				rte_eal_remote_launch(test_rwc_reader,
 						(void *)(uintptr_t)read_type,
 							enabled_core_ids[i]);
-			key_shift = 1;
-			ret = write_keys(key_shift);
+			write_type = WRITE_KEY_SHIFT;
+			ret = write_keys(write_type);
 			writer_done = 1;
 			rte_eal_mp_wait_lcore();
 
@@ -949,18 +1068,18 @@ test_hash_add_ks_lookup_miss(struct rwc_perf *rwc_perf_results, int rwc_lf, int
  */
 static int
 test_hash_multi_add_lookup(struct rwc_perf *rwc_perf_results, int rwc_lf,
-			   int htm)
+			   int htm, int ext_bkt)
 {
 	unsigned int n, m, k;
 	uint64_t i;
 	int use_jhash = 0;
-	uint8_t key_shift;
+	uint8_t write_type;
 	uint8_t read_type = READ_PASS_SHIFT_PATH;
 
 	rte_atomic64_init(&greads);
 	rte_atomic64_init(&gread_cycles);
 
-	if (init_params(rwc_lf, use_jhash, htm) != 0)
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
 		goto err;
 	printf("\nTest: Multi-add-lookup\n");
 	uint8_t pos_core;
@@ -991,8 +1110,8 @@ test_hash_multi_add_lookup(struct rwc_perf *rwc_perf_results, int rwc_lf,
 				writer_done = 0;
 				for (i = 0; i < 4; i++)
 					multi_writer_done[i] = 0;
-				key_shift = 0;
-				if (write_keys(key_shift) < 0)
+				write_type = WRITE_NO_KEY_SHIFT;
+				if (write_keys(write_type) < 0)
 					goto err;
 
 				/* Launch reader(s) */
@@ -1000,7 +1119,7 @@ test_hash_multi_add_lookup(struct rwc_perf *rwc_perf_results, int rwc_lf,
 					rte_eal_remote_launch(test_rwc_reader,
 						(void *)(uintptr_t)read_type,
 						enabled_core_ids[i]);
-				key_shift = 1;
+				write_type = WRITE_KEY_SHIFT;
 				pos_core = 0;
 
 				/* Launch writers */
@@ -1045,6 +1164,88 @@ test_hash_multi_add_lookup(struct rwc_perf *rwc_perf_results, int rwc_lf,
 	return -1;
 }
 
+/*
+ * Test lookup perf:
+ * Reader(s) lookup keys present in the extendable bkt.
+ */
+static int
+test_hash_add_ks_lookup_hit_extbkt(struct rwc_perf *rwc_perf_results,
+				int rwc_lf, int htm, int ext_bkt)
+{
+	unsigned int n, m;
+	uint64_t i;
+	int use_jhash = 0;
+	uint8_t write_type;
+	uint8_t read_type = READ_PASS_KEY_SHIFTS_EXTBKT;
+
+	rte_atomic64_init(&greads);
+	rte_atomic64_init(&gread_cycles);
+
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
+		goto err;
+	printf("\nTest: Hash add - key-shifts, read - hit (ext_bkt)\n");
+	for (m = 0; m < 2; m++) {
+		if (m == 1) {
+			printf("\n** With bulk-lookup **\n");
+			read_type |= BULK_LOOKUP;
+		}
+		for (n = 0; n < NUM_TEST; n++) {
+			unsigned int tot_lcore = rte_lcore_count();
+			if (tot_lcore < rwc_core_cnt[n] + 1)
+				goto finish;
+
+			printf("\nNumber of readers: %u\n", rwc_core_cnt[n]);
+
+			rte_atomic64_clear(&greads);
+			rte_atomic64_clear(&gread_cycles);
+
+			rte_hash_reset(tbl_rwc_test_param.h);
+			write_type = WRITE_NO_KEY_SHIFT;
+			if (write_keys(write_type) < 0)
+				goto err;
+			write_type = WRITE_KEY_SHIFT;
+			if (write_keys(write_type) < 0)
+				goto err;
+			writer_done = 0;
+			for (i = 1; i <= rwc_core_cnt[n]; i++)
+				rte_eal_remote_launch(test_rwc_reader,
+						(void *)(uintptr_t)read_type,
+							enabled_core_ids[i]);
+			for (i = 0; i < tbl_rwc_test_param.count_keys_ks_extbkt;
+			     i++) {
+				if (rte_hash_del_key(tbl_rwc_test_param.h,
+					tbl_rwc_test_param.keys_ks_extbkt + i)
+							< 0) {
+					printf("Delete Failed: %u\n",
+					tbl_rwc_test_param.keys_ks_extbkt[i]);
+					goto err;
+				}
+			}
+			writer_done = 1;
+			rte_eal_mp_wait_lcore();
+
+			for (i = 1; i <= rwc_core_cnt[n]; i++)
+				if (lcore_config[i].ret < 0)
+					goto err;
+
+			unsigned long long cycles_per_lookup =
+				rte_atomic64_read(&gread_cycles) /
+				rte_atomic64_read(&greads);
+			rwc_perf_results->w_ks_r_hit_extbkt[m][n]
+						= cycles_per_lookup;
+			printf("Cycles per lookup: %llu\n", cycles_per_lookup);
+		}
+	}
+
+finish:
+	rte_hash_free(tbl_rwc_test_param.h);
+	return 0;
+
+err:
+	rte_hash_free(tbl_rwc_test_param.h);
+	return -1;
+}
+
 static int
 test_hash_readwrite_lf_main(void)
 {
@@ -1057,6 +1258,7 @@ test_hash_readwrite_lf_main(void)
 	int rwc_lf = 0;
 	int htm;
 	int use_jhash = 0;
+	int ext_bkt = 0;
 	if (rte_lcore_count() == 1) {
 		printf("More than one lcore is required "
 			"to do read write lock-free concurrency test\n");
@@ -1070,7 +1272,7 @@ test_hash_readwrite_lf_main(void)
 	else
 		htm = 0;
 
-	if (init_params(rwc_lf, use_jhash, htm) != 0)
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
 		return -1;
 	if (generate_keys() != 0)
 		return -1;
@@ -1079,25 +1281,29 @@ test_hash_readwrite_lf_main(void)
 
 	if (RTE_HASH_EXTRA_FLAGS_RW_CONCURRENCY_LF) {
 		rwc_lf = 1;
+		ext_bkt = 1;
 		printf("Test lookup with read-write concurrency lock free support"
 		       " enabled\n");
 		if (test_hash_add_no_ks_lookup_hit(&rwc_lf_results, rwc_lf,
-							htm) < 0)
+							htm, ext_bkt) < 0)
 			return -1;
 		if (test_hash_add_no_ks_lookup_miss(&rwc_lf_results, rwc_lf,
-							htm) < 0)
+							htm, ext_bkt) < 0)
 			return -1;
 		if (test_hash_add_ks_lookup_hit_non_sp(&rwc_lf_results, rwc_lf,
-							htm) < 0)
+							htm, ext_bkt) < 0)
 			return -1;
 		if (test_hash_add_ks_lookup_hit_sp(&rwc_lf_results, rwc_lf,
-							htm) < 0)
+							htm, ext_bkt) < 0)
 			return -1;
-		if (test_hash_add_ks_lookup_miss(&rwc_lf_results, rwc_lf, htm)
-							< 0)
+		if (test_hash_add_ks_lookup_miss(&rwc_lf_results, rwc_lf, htm,
+						 ext_bkt) < 0)
 			return -1;
-		if (test_hash_multi_add_lookup(&rwc_lf_results, rwc_lf, htm)
-							< 0)
+		if (test_hash_multi_add_lookup(&rwc_lf_results, rwc_lf, htm,
+					       ext_bkt) < 0)
+			return -1;
+		if (test_hash_add_ks_lookup_hit_extbkt(&rwc_lf_results, rwc_lf,
+							htm, ext_bkt) < 0)
 			return -1;
 	}
 	printf("\nTest lookup with read-write concurrency lock free support"
@@ -1112,21 +1318,26 @@ test_hash_readwrite_lf_main(void)
 		}
 	} else
 		printf("With HTM Enabled\n");
-	if (test_hash_add_no_ks_lookup_hit(&rwc_non_lf_results, rwc_lf, htm)
-						< 0)
+	if (test_hash_add_no_ks_lookup_hit(&rwc_non_lf_results, rwc_lf, htm,
+					   ext_bkt) < 0)
 		return -1;
-	if (test_hash_add_no_ks_lookup_miss(&rwc_non_lf_results, rwc_lf, htm)
-						< 0)
+	if (test_hash_add_no_ks_lookup_miss(&rwc_non_lf_results, rwc_lf, htm,
+						ext_bkt) < 0)
 		return -1;
 	if (test_hash_add_ks_lookup_hit_non_sp(&rwc_non_lf_results, rwc_lf,
-						htm) < 0)
+						htm, ext_bkt) < 0)
+		return -1;
+	if (test_hash_add_ks_lookup_hit_sp(&rwc_non_lf_results, rwc_lf, htm,
+						ext_bkt) < 0)
 		return -1;
-	if (test_hash_add_ks_lookup_hit_sp(&rwc_non_lf_results, rwc_lf, htm)
-						< 0)
+	if (test_hash_add_ks_lookup_miss(&rwc_non_lf_results, rwc_lf, htm,
+					 ext_bkt) < 0)
 		return -1;
-	if (test_hash_add_ks_lookup_miss(&rwc_non_lf_results, rwc_lf, htm) < 0)
+	if (test_hash_multi_add_lookup(&rwc_non_lf_results, rwc_lf, htm,
+							ext_bkt) < 0)
 		return -1;
-	if (test_hash_multi_add_lookup(&rwc_non_lf_results, rwc_lf, htm) < 0)
+	if (test_hash_add_ks_lookup_hit_extbkt(&rwc_non_lf_results, rwc_lf,
+						htm, ext_bkt) < 0)
 		return -1;
 results:
 	printf("\n\t\t\t\t\t\t********** Results summary **********\n\n");
@@ -1158,8 +1369,11 @@ test_hash_readwrite_lf_main(void)
 			       "(shift-path)\t\t%u\n\t\t\t\t\t\t\t\t",
 			       rwc_lf_results.w_ks_r_hit_sp[j][i]);
 			printf("Hash add - key-shifts, Hash lookup miss\t\t\t\t"
-				"%u\n\n\t\t\t\t",
+				"%u\n\t\t\t\t\t\t\t\t",
 				rwc_lf_results.w_ks_r_miss[j][i]);
+			printf("Hash add - key-shifts, Hash lookup hit (ext_bkt)\t\t"
+				"%u\n\n\t\t\t\t",
+				rwc_lf_results.w_ks_r_hit_extbkt[j][i]);
 
 			printf("Disabled\t");
 			if (htm)
@@ -1179,7 +1393,11 @@ test_hash_readwrite_lf_main(void)
 			       "(shift-path)\t\t%u\n\t\t\t\t\t\t\t\t",
 			       rwc_non_lf_results.w_ks_r_hit_sp[j][i]);
 			printf("Hash add - key-shifts, Hash lookup miss\t\t\t\t"
-			       "%u\n", rwc_non_lf_results.w_ks_r_miss[j][i]);
+			       "%u\n\t\t\t\t\t\t\t\t",
+			       rwc_non_lf_results.w_ks_r_miss[j][i]);
+			printf("Hash add - key-shifts, Hash lookup hit (ext_bkt)\t\t"
+				"%u\n",
+				rwc_non_lf_results.w_ks_r_hit_extbkt[j][i]);
 
 			printf("_______\t\t_______\t\t_________\t___\t\t"
 			       "_________\t\t\t\t\t\t_________________\n");
-- 
2.17.1

[dpdk-dev] [PATCH v3 2/2] test/hash: lock-free rw concurrency test ext bkt

[Dharmik Thakkar]

Add unit test to check for hash lookup and bulk-lookup perf for
extendable bucket feature.
It is tested with both lock-free enabled and lock-free disabled case.

Test includes:

- hash lookup on keys in ext bkt
- hash delete causing key-shifts of keys from ext bkt to secondary bkt

Suggested-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
Signed-off-by: Dharmik Thakkar <dharmik.thakkar@arm.com>
---
 app/test/test_hash_readwrite_lf.c | 350 ++++++++++++++++++++++++------
 1 file changed, 284 insertions(+), 66 deletions(-)

diff --git a/app/test/test_hash_readwrite_lf.c b/app/test/test_hash_readwrite_lf.c
index cbfd9322696b..ddd8d7aa6a7d 100644
--- a/app/test/test_hash_readwrite_lf.c
+++ b/app/test/test_hash_readwrite_lf.c
@@ -41,6 +41,12 @@
 #define READ_PASS_SHIFT_PATH 4
 #define READ_PASS_NON_SHIFT_PATH 8
 #define BULK_LOOKUP 16
+#define READ_PASS_KEY_SHIFTS_EXTBKT 32
+
+#define WRITE_NO_KEY_SHIFT 0
+#define WRITE_KEY_SHIFT 1
+#define WRITE_EXT_BKT 2
+
 #define NUM_TEST 3
 unsigned int rwc_core_cnt[NUM_TEST] = {1, 2, 4};
 
@@ -51,6 +57,7 @@ struct rwc_perf {
 	uint32_t w_ks_r_hit_sp[2][NUM_TEST];
 	uint32_t w_ks_r_miss[2][NUM_TEST];
 	uint32_t multi_rw[NUM_TEST - 1][2][NUM_TEST];
+	uint32_t w_ks_r_hit_extbkt[2][NUM_TEST];
 };
 
 static struct rwc_perf rwc_lf_results, rwc_non_lf_results;
@@ -62,11 +69,15 @@ struct {
 	uint32_t *keys_absent;
 	uint32_t *keys_shift_path;
 	uint32_t *keys_non_shift_path;
+	uint32_t *keys_ext_bkt;
+	uint32_t *keys_ks_extbkt;
 	uint32_t count_keys_no_ks;
 	uint32_t count_keys_ks;
 	uint32_t count_keys_absent;
 	uint32_t count_keys_shift_path;
 	uint32_t count_keys_non_shift_path;
+	uint32_t count_keys_extbkt;
+	uint32_t count_keys_ks_extbkt;
 	uint32_t single_insert;
 	struct rte_hash *h;
 } tbl_rwc_test_param;
@@ -81,6 +92,35 @@ uint16_t enabled_core_ids[RTE_MAX_LCORE];
 
 uint8_t *scanned_bkts;
 
+static inline uint16_t
+get_short_sig(const hash_sig_t hash)
+{
+	return hash >> 16;
+}
+
+static inline uint32_t
+get_prim_bucket_index(__attribute__((unused)) const struct rte_hash *h,
+		      const hash_sig_t hash)
+{
+	uint32_t num_buckets;
+	uint32_t bucket_bitmask;
+	num_buckets  = rte_align32pow2(TOTAL_ENTRY) / 8;
+	bucket_bitmask = num_buckets - 1;
+	return hash & bucket_bitmask;
+}
+
+static inline uint32_t
+get_alt_bucket_index(__attribute__((unused)) const struct rte_hash *h,
+			uint32_t cur_bkt_idx, uint16_t sig)
+{
+	uint32_t num_buckets;
+	uint32_t bucket_bitmask;
+	num_buckets  = rte_align32pow2(TOTAL_ENTRY) / 8;
+	bucket_bitmask = num_buckets - 1;
+	return (cur_bkt_idx ^ sig) & bucket_bitmask;
+}
+
+
 static inline int
 get_enabled_cores_list(void)
 {
@@ -168,9 +208,12 @@ generate_keys(void)
 	uint32_t *keys_ks = NULL;
 	uint32_t *keys_absent = NULL;
 	uint32_t *keys_non_shift_path = NULL;
+	uint32_t *keys_ext_bkt = NULL;
+	uint32_t *keys_ks_extbkt = NULL;
 	uint32_t *found = NULL;
 	uint32_t count_keys_no_ks = 0;
 	uint32_t count_keys_ks = 0;
+	uint32_t count_keys_extbkt = 0;
 	uint32_t i;
 
 	/*
@@ -251,14 +294,32 @@ generate_keys(void)
 		goto err;
 	}
 
+	/*
+	 * This consist of keys which will be stored in extended buckets
+	 */
+	keys_ext_bkt = rte_malloc(NULL, sizeof(uint32_t) * TOTAL_INSERT, 0);
+	if (keys_ext_bkt == NULL) {
+		printf("RTE_MALLOC failed\n");
+		goto err;
+	}
+
+	/*
+	 * This consist of keys which when deleted causes shifting of keys
+	 * in extended buckets to respective secondary buckets
+	 */
+	keys_ks_extbkt = rte_malloc(NULL, sizeof(uint32_t) * TOTAL_INSERT, 0);
+	if (keys_ks_extbkt == NULL) {
+		printf("RTE_MALLOC failed\n");
+		goto err;
+	}
 
 	hash_sig_t sig;
 	uint32_t prim_bucket_idx;
-	int ret;
+	uint32_t sec_bucket_idx;
+	uint16_t short_sig;
 	uint32_t num_buckets;
-	uint32_t bucket_bitmask;
 	num_buckets  = rte_align32pow2(TOTAL_ENTRY) / 8;
-	bucket_bitmask = num_buckets - 1;
+	int ret;
 
 	/*
 	 * Used to mark bkts in which at least one key was shifted to its
@@ -275,6 +336,8 @@ generate_keys(void)
 	tbl_rwc_test_param.keys_ks = keys_ks;
 	tbl_rwc_test_param.keys_absent = keys_absent;
 	tbl_rwc_test_param.keys_non_shift_path = keys_non_shift_path;
+	tbl_rwc_test_param.keys_ext_bkt = keys_ext_bkt;
+	tbl_rwc_test_param.keys_ks_extbkt = keys_ks_extbkt;
 	/* Generate keys by adding previous two keys, neglect overflow */
 	printf("Generating keys...\n");
 	keys[0] = 0;
@@ -287,7 +350,8 @@ generate_keys(void)
 		/* Check if primary bucket has space.*/
 		sig = rte_hash_hash(tbl_rwc_test_param.h,
 					tbl_rwc_test_param.keys+i);
-		prim_bucket_idx = sig & bucket_bitmask;
+		prim_bucket_idx = get_prim_bucket_index(tbl_rwc_test_param.h,
+							sig);
 		ret = check_bucket(prim_bucket_idx, keys[i]);
 		if (ret < 0) {
 			/*
@@ -368,6 +432,47 @@ generate_keys(void)
 	tbl_rwc_test_param.count_keys_absent = count_keys_absent;
 	tbl_rwc_test_param.count_keys_non_shift_path = count;
 
+	memset(scanned_bkts, 0, num_buckets);
+	count = 0;
+	/* Find keys that will be in extended buckets */
+	for (i = 0; i < count_keys_ks; i++) {
+		ret = rte_hash_add_key(tbl_rwc_test_param.h, keys_ks + i);
+		if (ret < 0) {
+			/* Key will be added to ext bkt */
+			keys_ext_bkt[count_keys_extbkt++] = keys_ks[i];
+			/* Sec bkt to be added to keys_ks_extbkt */
+			sig = rte_hash_hash(tbl_rwc_test_param.h,
+					tbl_rwc_test_param.keys_ks + i);
+			prim_bucket_idx = get_prim_bucket_index(
+						tbl_rwc_test_param.h, sig);
+			short_sig = get_short_sig(sig);
+			sec_bucket_idx = get_alt_bucket_index(
+						tbl_rwc_test_param.h,
+						prim_bucket_idx, short_sig);
+			if (scanned_bkts[sec_bucket_idx] == 0)
+				scanned_bkts[sec_bucket_idx] = 1;
+		}
+	}
+
+	/* Find keys that will shift keys in ext bucket*/
+	for (i = 0; i < num_buckets; i++) {
+		if (scanned_bkts[i] == 1) {
+			iter = i * 8;
+			while (rte_hash_iterate(tbl_rwc_test_param.h,
+				&next_key, &next_data, &iter) >= 0) {
+				/* Check if key belongs to the current bucket */
+				if (i >= (iter-1)/8)
+					keys_ks_extbkt[count++]
+						= *(const uint32_t *)next_key;
+				else
+					break;
+			}
+		}
+	}
+
+	tbl_rwc_test_param.count_keys_ks_extbkt = count;
+	tbl_rwc_test_param.count_keys_extbkt = count_keys_extbkt;
+
 	printf("\nCount of keys NOT causing shifting of existing keys to "
 	"alternate location: %d\n", tbl_rwc_test_param.count_keys_no_ks);
 	printf("\nCount of keys causing shifting of existing keys to alternate "
@@ -378,6 +483,10 @@ generate_keys(void)
 	       tbl_rwc_test_param.count_keys_shift_path);
 	printf("Count of keys not likely to be on the shift path: %d\n\n",
 	       tbl_rwc_test_param.count_keys_non_shift_path);
+	printf("Count of keys in extended buckets: %d\n\n",
+	       tbl_rwc_test_param.count_keys_extbkt);
+	printf("Count of keys shifting keys in ext buckets: %d\n\n",
+	       tbl_rwc_test_param.count_keys_ks_extbkt);
 
 	rte_free(found);
 	rte_hash_free(tbl_rwc_test_param.h);
@@ -390,12 +499,14 @@ generate_keys(void)
 	rte_free(keys_absent);
 	rte_free(found);
 	rte_free(tbl_rwc_test_param.keys_shift_path);
+	rte_free(keys_ext_bkt);
+	rte_free(keys_ks_extbkt);
 	rte_free(scanned_bkts);
 	return -1;
 }
 
 static int
-init_params(int rwc_lf, int use_jhash, int htm)
+init_params(int rwc_lf, int use_jhash, int htm, int ext_bkt)
 {
 	struct rte_hash *handle;
 
@@ -425,6 +536,9 @@ init_params(int rwc_lf, int use_jhash, int htm)
 			RTE_HASH_EXTRA_FLAGS_RW_CONCURRENCY |
 			RTE_HASH_EXTRA_FLAGS_MULTI_WRITER_ADD;
 
+	if (ext_bkt)
+		hash_params.extra_flag |= RTE_HASH_EXTRA_FLAGS_EXT_TABLE;
+
 	hash_params.name = "tests";
 
 	handle = rte_hash_create(&hash_params);
@@ -452,7 +566,7 @@ test_rwc_reader(__attribute__((unused)) void *arg)
 	void *temp_a[BULK_LOOKUP_SIZE];
 
 	/* Used to identify keys not inserted in the hash table */
-	pos = rte_zmalloc(NULL, sizeof(uint32_t) * BULK_LOOKUP_SIZE, 0);
+	pos = rte_malloc(NULL, sizeof(uint32_t) * BULK_LOOKUP_SIZE, 0);
 	if (pos == NULL) {
 		printf("RTE_MALLOC failed\n");
 		return -1;
@@ -467,6 +581,9 @@ test_rwc_reader(__attribute__((unused)) void *arg)
 	} else if (read_type & READ_PASS_SHIFT_PATH) {
 		keys = tbl_rwc_test_param.keys_shift_path;
 		read_cnt = tbl_rwc_test_param.count_keys_shift_path;
+	} else if (read_type & READ_PASS_KEY_SHIFTS_EXTBKT) {
+		keys = tbl_rwc_test_param.keys_ext_bkt;
+		read_cnt = tbl_rwc_test_param.count_keys_extbkt;
 	} else {
 		keys = tbl_rwc_test_param.keys_non_shift_path;
 		read_cnt = tbl_rwc_test_param.count_keys_non_shift_path;
@@ -482,7 +599,6 @@ test_rwc_reader(__attribute__((unused)) void *arg)
 				/* Array of  pointer to the list of keys */
 				for (j = 0; j < BULK_LOOKUP_SIZE; j++)
 					temp_a[j] = keys + i + j;
-
 				rte_hash_lookup_bulk(tbl_rwc_test_param.h,
 						   (const void **)
 						   ((uintptr_t)temp_a),
@@ -539,22 +655,25 @@ test_rwc_reader(__attribute__((unused)) void *arg)
 }
 
 static int
-write_keys(uint8_t key_shift)
+write_keys(uint8_t write_type)
 {
 	uint32_t i;
 	int ret;
 	uint32_t key_cnt;
 	uint32_t *keys;
-	if (key_shift) {
+	if (write_type == WRITE_KEY_SHIFT) {
 		key_cnt = tbl_rwc_test_param.count_keys_ks;
 		keys = tbl_rwc_test_param.keys_ks;
-	} else {
+	} else if (write_type == WRITE_NO_KEY_SHIFT) {
 		key_cnt = tbl_rwc_test_param.count_keys_no_ks;
 		keys = tbl_rwc_test_param.keys_no_ks;
+	} else if (write_type == WRITE_EXT_BKT) {
+		key_cnt = tbl_rwc_test_param.count_keys_extbkt;
+		keys = tbl_rwc_test_param.keys_ext_bkt;
 	}
 	for (i = 0; i < key_cnt; i++) {
 		ret = rte_hash_add_key(tbl_rwc_test_param.h, keys + i);
-		if (!key_shift && ret < 0) {
+		if ((write_type == WRITE_NO_KEY_SHIFT) && ret < 0) {
 			printf("writer failed %"PRIu32"\n", i);
 			return -1;
 		}
@@ -581,18 +700,18 @@ test_rwc_multi_writer(__attribute__((unused)) void *arg)
  */
 static int
 test_hash_add_no_ks_lookup_hit(struct rwc_perf *rwc_perf_results, int rwc_lf,
-				int htm)
+				int htm, int ext_bkt)
 {
 	unsigned int n, m;
 	uint64_t i;
 	int use_jhash = 0;
-	uint8_t key_shift = 0;
+	uint8_t write_type = WRITE_NO_KEY_SHIFT;
 	uint8_t read_type = READ_PASS_NO_KEY_SHIFTS;
 
 	rte_atomic64_init(&greads);
 	rte_atomic64_init(&gread_cycles);
 
-	if (init_params(rwc_lf, use_jhash, htm) != 0)
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
 		goto err;
 	printf("\nTest: Hash add - no key-shifts, read - hit\n");
 	for (m = 0; m < 2; m++) {
@@ -612,7 +731,7 @@ test_hash_add_no_ks_lookup_hit(struct rwc_perf *rwc_perf_results, int rwc_lf,
 
 			rte_hash_reset(tbl_rwc_test_param.h);
 			writer_done = 0;
-			if (write_keys(key_shift) < 0)
+			if (write_keys(write_type) < 0)
 				goto err;
 			writer_done = 1;
 			for (i = 1; i <= rwc_core_cnt[n]; i++)
@@ -650,19 +769,19 @@ test_hash_add_no_ks_lookup_hit(struct rwc_perf *rwc_perf_results, int rwc_lf,
  */
 static int
 test_hash_add_no_ks_lookup_miss(struct rwc_perf *rwc_perf_results, int rwc_lf,
-				int htm)
+				int htm, int ext_bkt)
 {
 	unsigned int n, m;
 	uint64_t i;
 	int use_jhash = 0;
-	uint8_t key_shift = 0;
+	uint8_t write_type = WRITE_NO_KEY_SHIFT;
 	uint8_t read_type = READ_FAIL;
 	int ret;
 
 	rte_atomic64_init(&greads);
 	rte_atomic64_init(&gread_cycles);
 
-	if (init_params(rwc_lf, use_jhash, htm) != 0)
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
 		goto err;
 	printf("\nTest: Hash add - no key-shifts, Hash lookup - miss\n");
 	for (m = 0; m < 2; m++) {
@@ -687,7 +806,7 @@ test_hash_add_no_ks_lookup_miss(struct rwc_perf *rwc_perf_results, int rwc_lf,
 				rte_eal_remote_launch(test_rwc_reader,
 						(void *)(uintptr_t)read_type,
 							enabled_core_ids[i]);
-			ret = write_keys(key_shift);
+			ret = write_keys(write_type);
 			writer_done = 1;
 			rte_eal_mp_wait_lcore();
 
@@ -722,19 +841,19 @@ test_hash_add_no_ks_lookup_miss(struct rwc_perf *rwc_perf_results, int rwc_lf,
  */
 static int
 test_hash_add_ks_lookup_hit_non_sp(struct rwc_perf *rwc_perf_results,
-				    int rwc_lf, int htm)
+				    int rwc_lf, int htm, int ext_bkt)
 {
 	unsigned int n, m;
 	uint64_t i;
 	int use_jhash = 0;
 	int ret;
-	uint8_t key_shift;
+	uint8_t write_type;
 	uint8_t read_type = READ_PASS_NON_SHIFT_PATH;
 
 	rte_atomic64_init(&greads);
 	rte_atomic64_init(&gread_cycles);
 
-	if (init_params(rwc_lf, use_jhash, htm) != 0)
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
 		goto err;
 	printf("\nTest: Hash add - key shift, Hash lookup - hit"
 	       " (non-shift-path)\n");
@@ -755,15 +874,15 @@ test_hash_add_ks_lookup_hit_non_sp(struct rwc_perf *rwc_perf_results,
 
 			rte_hash_reset(tbl_rwc_test_param.h);
 			writer_done = 0;
-			key_shift = 0;
-			if (write_keys(key_shift) < 0)
+			write_type = WRITE_NO_KEY_SHIFT;
+			if (write_keys(write_type) < 0)
 				goto err;
 			for (i = 1; i <= rwc_core_cnt[n]; i++)
 				rte_eal_remote_launch(test_rwc_reader,
 						(void *)(uintptr_t)read_type,
 							enabled_core_ids[i]);
-			key_shift = 1;
-			ret = write_keys(key_shift);
+			write_type = WRITE_KEY_SHIFT;
+			ret = write_keys(write_type);
 			writer_done = 1;
 			rte_eal_mp_wait_lcore();
 
@@ -798,19 +917,19 @@ test_hash_add_ks_lookup_hit_non_sp(struct rwc_perf *rwc_perf_results,
  */
 static int
 test_hash_add_ks_lookup_hit_sp(struct rwc_perf *rwc_perf_results, int rwc_lf,
-				int htm)
+				int htm, int ext_bkt)
 {
 	unsigned int n, m;
 	uint64_t i;
 	int use_jhash = 0;
 	int ret;
-	uint8_t key_shift;
+	uint8_t write_type;
 	uint8_t read_type = READ_PASS_SHIFT_PATH;
 
 	rte_atomic64_init(&greads);
 	rte_atomic64_init(&gread_cycles);
 
-	if (init_params(rwc_lf, use_jhash, htm) != 0)
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
 		goto err;
 	printf("\nTest: Hash add - key shift, Hash lookup - hit (shift-path)"
 	       "\n");
@@ -831,15 +950,15 @@ test_hash_add_ks_lookup_hit_sp(struct rwc_perf *rwc_perf_results, int rwc_lf,
 
 			rte_hash_reset(tbl_rwc_test_param.h);
 			writer_done = 0;
-			key_shift = 0;
-			if (write_keys(key_shift) < 0)
+			write_type = WRITE_NO_KEY_SHIFT;
+			if (write_keys(write_type) < 0)
 				goto err;
 			for (i = 1; i <= rwc_core_cnt[n]; i++)
 				rte_eal_remote_launch(test_rwc_reader,
 						(void *)(uintptr_t)read_type,
 						enabled_core_ids[i]);
-			key_shift = 1;
-			ret = write_keys(key_shift);
+			write_type = WRITE_KEY_SHIFT;
+			ret = write_keys(write_type);
 			writer_done = 1;
 			rte_eal_mp_wait_lcore();
 
@@ -874,19 +993,19 @@ test_hash_add_ks_lookup_hit_sp(struct rwc_perf *rwc_perf_results, int rwc_lf,
  */
 static int
 test_hash_add_ks_lookup_miss(struct rwc_perf *rwc_perf_results, int rwc_lf, int
-			     htm)
+			     htm, int ext_bkt)
 {
 	unsigned int n, m;
 	uint64_t i;
 	int use_jhash = 0;
 	int ret;
-	uint8_t key_shift;
+	uint8_t write_type;
 	uint8_t read_type = READ_FAIL;
 
 	rte_atomic64_init(&greads);
 	rte_atomic64_init(&gread_cycles);
 
-	if (init_params(rwc_lf, use_jhash, htm) != 0)
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
 		goto err;
 	printf("\nTest: Hash add - key shift, Hash lookup - miss\n");
 	for (m = 0; m < 2; m++) {
@@ -906,15 +1025,15 @@ test_hash_add_ks_lookup_miss(struct rwc_perf *rwc_perf_results, int rwc_lf, int
 
 			rte_hash_reset(tbl_rwc_test_param.h);
 			writer_done = 0;
-			key_shift = 0;
-			if (write_keys(key_shift) < 0)
+			write_type = WRITE_NO_KEY_SHIFT;
+			if (write_keys(write_type) < 0)
 				goto err;
 			for (i = 1; i <= rwc_core_cnt[n]; i++)
 				rte_eal_remote_launch(test_rwc_reader,
 						(void *)(uintptr_t)read_type,
 							enabled_core_ids[i]);
-			key_shift = 1;
-			ret = write_keys(key_shift);
+			write_type = WRITE_KEY_SHIFT;
+			ret = write_keys(write_type);
 			writer_done = 1;
 			rte_eal_mp_wait_lcore();
 
@@ -949,18 +1068,18 @@ test_hash_add_ks_lookup_miss(struct rwc_perf *rwc_perf_results, int rwc_lf, int
  */
 static int
 test_hash_multi_add_lookup(struct rwc_perf *rwc_perf_results, int rwc_lf,
-			   int htm)
+			   int htm, int ext_bkt)
 {
 	unsigned int n, m, k;
 	uint64_t i;
 	int use_jhash = 0;
-	uint8_t key_shift;
+	uint8_t write_type;
 	uint8_t read_type = READ_PASS_SHIFT_PATH;
 
 	rte_atomic64_init(&greads);
 	rte_atomic64_init(&gread_cycles);
 
-	if (init_params(rwc_lf, use_jhash, htm) != 0)
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
 		goto err;
 	printf("\nTest: Multi-add-lookup\n");
 	uint8_t pos_core;
@@ -991,8 +1110,8 @@ test_hash_multi_add_lookup(struct rwc_perf *rwc_perf_results, int rwc_lf,
 				writer_done = 0;
 				for (i = 0; i < 4; i++)
 					multi_writer_done[i] = 0;
-				key_shift = 0;
-				if (write_keys(key_shift) < 0)
+				write_type = WRITE_NO_KEY_SHIFT;
+				if (write_keys(write_type) < 0)
 					goto err;
 
 				/* Launch reader(s) */
@@ -1000,7 +1119,7 @@ test_hash_multi_add_lookup(struct rwc_perf *rwc_perf_results, int rwc_lf,
 					rte_eal_remote_launch(test_rwc_reader,
 						(void *)(uintptr_t)read_type,
 						enabled_core_ids[i]);
-				key_shift = 1;
+				write_type = WRITE_KEY_SHIFT;
 				pos_core = 0;
 
 				/* Launch writers */
@@ -1045,6 +1164,88 @@ test_hash_multi_add_lookup(struct rwc_perf *rwc_perf_results, int rwc_lf,
 	return -1;
 }
 
+/*
+ * Test lookup perf:
+ * Reader(s) lookup keys present in the extendable bkt.
+ */
+static int
+test_hash_add_ks_lookup_hit_extbkt(struct rwc_perf *rwc_perf_results,
+				int rwc_lf, int htm, int ext_bkt)
+{
+	unsigned int n, m;
+	uint64_t i;
+	int use_jhash = 0;
+	uint8_t write_type;
+	uint8_t read_type = READ_PASS_KEY_SHIFTS_EXTBKT;
+
+	rte_atomic64_init(&greads);
+	rte_atomic64_init(&gread_cycles);
+
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
+		goto err;
+	printf("\nTest: Hash add - key-shifts, read - hit (ext_bkt)\n");
+	for (m = 0; m < 2; m++) {
+		if (m == 1) {
+			printf("\n** With bulk-lookup **\n");
+			read_type |= BULK_LOOKUP;
+		}
+		for (n = 0; n < NUM_TEST; n++) {
+			unsigned int tot_lcore = rte_lcore_count();
+			if (tot_lcore < rwc_core_cnt[n] + 1)
+				goto finish;
+
+			printf("\nNumber of readers: %u\n", rwc_core_cnt[n]);
+
+			rte_atomic64_clear(&greads);
+			rte_atomic64_clear(&gread_cycles);
+
+			rte_hash_reset(tbl_rwc_test_param.h);
+			write_type = WRITE_NO_KEY_SHIFT;
+			if (write_keys(write_type) < 0)
+				goto err;
+			write_type = WRITE_KEY_SHIFT;
+			if (write_keys(write_type) < 0)
+				goto err;
+			writer_done = 0;
+			for (i = 1; i <= rwc_core_cnt[n]; i++)
+				rte_eal_remote_launch(test_rwc_reader,
+						(void *)(uintptr_t)read_type,
+							enabled_core_ids[i]);
+			for (i = 0; i < tbl_rwc_test_param.count_keys_ks_extbkt;
+			     i++) {
+				if (rte_hash_del_key(tbl_rwc_test_param.h,
+					tbl_rwc_test_param.keys_ks_extbkt + i)
+							< 0) {
+					printf("Delete Failed: %u\n",
+					tbl_rwc_test_param.keys_ks_extbkt[i]);
+					goto err;
+				}
+			}
+			writer_done = 1;
+			rte_eal_mp_wait_lcore();
+
+			for (i = 1; i <= rwc_core_cnt[n]; i++)
+				if (lcore_config[i].ret < 0)
+					goto err;
+
+			unsigned long long cycles_per_lookup =
+				rte_atomic64_read(&gread_cycles) /
+				rte_atomic64_read(&greads);
+			rwc_perf_results->w_ks_r_hit_extbkt[m][n]
+						= cycles_per_lookup;
+			printf("Cycles per lookup: %llu\n", cycles_per_lookup);
+		}
+	}
+
+finish:
+	rte_hash_free(tbl_rwc_test_param.h);
+	return 0;
+
+err:
+	rte_hash_free(tbl_rwc_test_param.h);
+	return -1;
+}
+
 static int
 test_hash_readwrite_lf_main(void)
 {
@@ -1057,6 +1258,7 @@ test_hash_readwrite_lf_main(void)
 	int rwc_lf = 0;
 	int htm;
 	int use_jhash = 0;
+	int ext_bkt = 0;
 	if (rte_lcore_count() == 1) {
 		printf("More than one lcore is required "
 			"to do read write lock-free concurrency test\n");
@@ -1070,7 +1272,7 @@ test_hash_readwrite_lf_main(void)
 	else
 		htm = 0;
 
-	if (init_params(rwc_lf, use_jhash, htm) != 0)
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
 		return -1;
 	if (generate_keys() != 0)
 		return -1;
@@ -1079,25 +1281,29 @@ test_hash_readwrite_lf_main(void)
 
 	if (RTE_HASH_EXTRA_FLAGS_RW_CONCURRENCY_LF) {
 		rwc_lf = 1;
+		ext_bkt = 1;
 		printf("Test lookup with read-write concurrency lock free support"
 		       " enabled\n");
 		if (test_hash_add_no_ks_lookup_hit(&rwc_lf_results, rwc_lf,
-							htm) < 0)
+							htm, ext_bkt) < 0)
 			return -1;
 		if (test_hash_add_no_ks_lookup_miss(&rwc_lf_results, rwc_lf,
-							htm) < 0)
+							htm, ext_bkt) < 0)
 			return -1;
 		if (test_hash_add_ks_lookup_hit_non_sp(&rwc_lf_results, rwc_lf,
-							htm) < 0)
+							htm, ext_bkt) < 0)
 			return -1;
 		if (test_hash_add_ks_lookup_hit_sp(&rwc_lf_results, rwc_lf,
-							htm) < 0)
+							htm, ext_bkt) < 0)
 			return -1;
-		if (test_hash_add_ks_lookup_miss(&rwc_lf_results, rwc_lf, htm)
-							< 0)
+		if (test_hash_add_ks_lookup_miss(&rwc_lf_results, rwc_lf, htm,
+						 ext_bkt) < 0)
 			return -1;
-		if (test_hash_multi_add_lookup(&rwc_lf_results, rwc_lf, htm)
-							< 0)
+		if (test_hash_multi_add_lookup(&rwc_lf_results, rwc_lf, htm,
+					       ext_bkt) < 0)
+			return -1;
+		if (test_hash_add_ks_lookup_hit_extbkt(&rwc_lf_results, rwc_lf,
+							htm, ext_bkt) < 0)
 			return -1;
 	}
 	printf("\nTest lookup with read-write concurrency lock free support"
@@ -1112,21 +1318,26 @@ test_hash_readwrite_lf_main(void)
 		}
 	} else
 		printf("With HTM Enabled\n");
-	if (test_hash_add_no_ks_lookup_hit(&rwc_non_lf_results, rwc_lf, htm)
-						< 0)
+	if (test_hash_add_no_ks_lookup_hit(&rwc_non_lf_results, rwc_lf, htm,
+					   ext_bkt) < 0)
 		return -1;
-	if (test_hash_add_no_ks_lookup_miss(&rwc_non_lf_results, rwc_lf, htm)
-						< 0)
+	if (test_hash_add_no_ks_lookup_miss(&rwc_non_lf_results, rwc_lf, htm,
+						ext_bkt) < 0)
 		return -1;
 	if (test_hash_add_ks_lookup_hit_non_sp(&rwc_non_lf_results, rwc_lf,
-						htm) < 0)
+						htm, ext_bkt) < 0)
+		return -1;
+	if (test_hash_add_ks_lookup_hit_sp(&rwc_non_lf_results, rwc_lf, htm,
+						ext_bkt) < 0)
 		return -1;
-	if (test_hash_add_ks_lookup_hit_sp(&rwc_non_lf_results, rwc_lf, htm)
-						< 0)
+	if (test_hash_add_ks_lookup_miss(&rwc_non_lf_results, rwc_lf, htm,
+					 ext_bkt) < 0)
 		return -1;
-	if (test_hash_add_ks_lookup_miss(&rwc_non_lf_results, rwc_lf, htm) < 0)
+	if (test_hash_multi_add_lookup(&rwc_non_lf_results, rwc_lf, htm,
+							ext_bkt) < 0)
 		return -1;
-	if (test_hash_multi_add_lookup(&rwc_non_lf_results, rwc_lf, htm) < 0)
+	if (test_hash_add_ks_lookup_hit_extbkt(&rwc_non_lf_results, rwc_lf,
+						htm, ext_bkt) < 0)
 		return -1;
 results:
 	printf("\n\t\t\t\t\t\t********** Results summary **********\n\n");
@@ -1158,8 +1369,11 @@ test_hash_readwrite_lf_main(void)
 			       "(shift-path)\t\t%u\n\t\t\t\t\t\t\t\t",
 			       rwc_lf_results.w_ks_r_hit_sp[j][i]);
 			printf("Hash add - key-shifts, Hash lookup miss\t\t\t\t"
-				"%u\n\n\t\t\t\t",
+				"%u\n\t\t\t\t\t\t\t\t",
 				rwc_lf_results.w_ks_r_miss[j][i]);
+			printf("Hash add - key-shifts, Hash lookup hit (ext_bkt)\t\t"
+				"%u\n\n\t\t\t\t",
+				rwc_lf_results.w_ks_r_hit_extbkt[j][i]);
 
 			printf("Disabled\t");
 			if (htm)
@@ -1179,7 +1393,11 @@ test_hash_readwrite_lf_main(void)
 			       "(shift-path)\t\t%u\n\t\t\t\t\t\t\t\t",
 			       rwc_non_lf_results.w_ks_r_hit_sp[j][i]);
 			printf("Hash add - key-shifts, Hash lookup miss\t\t\t\t"
-			       "%u\n", rwc_non_lf_results.w_ks_r_miss[j][i]);
+			       "%u\n\t\t\t\t\t\t\t\t",
+			       rwc_non_lf_results.w_ks_r_miss[j][i]);
+			printf("Hash add - key-shifts, Hash lookup hit (ext_bkt)\t\t"
+				"%u\n",
+				rwc_non_lf_results.w_ks_r_hit_extbkt[j][i]);
 
 			printf("_______\t\t_______\t\t_________\t___\t\t"
 			       "_________\t\t\t\t\t\t_________________\n");
-- 
2.17.1

Re: [dpdk-dev] [PATCH v3 2/2] test/hash: lock-free rw concurrency test ext bkt

[Wang, Yipeng1]

>-----Original Message-----
>From: Dharmik Thakkar [mailto:dharmik.thakkar@arm.com]
>Sent: Monday, April 1, 2019 3:19 PM
>To: Wang, Yipeng1 <yipeng1.wang@intel.com>; Gobriel, Sameh <sameh.gobriel@intel.com>; Richardson, Bruce
><bruce.richardson@intel.com>; De Lara Guarch, Pablo <pablo.de.lara.guarch@intel.com>
>Cc: dev@dpdk.org; honnappa.nagarahalli@arm.com; Dharmik Thakkar <dharmik.thakkar@arm.com>
>Subject: [PATCH v3 2/2] test/hash: lock-free rw concurrency test ext bkt
>
>Add unit test to check for hash lookup and bulk-lookup perf for
>extendable bucket feature.
>It is tested with both lock-free enabled and lock-free disabled case.
>
>Test includes:
>
>- hash lookup on keys in ext bkt
>- hash delete causing key-shifts of keys from ext bkt to secondary bkt
>
>Suggested-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
>Signed-off-by: Dharmik Thakkar <dharmik.thakkar@arm.com>
Acked-by: Yipeng Wang <yipeng1.wang@intel.com>

Re: [dpdk-dev] [PATCH v3 2/2] test/hash: lock-free rw concurrency test ext bkt

[Wang, Yipeng1]

>-----Original Message-----
>From: Dharmik Thakkar [mailto:dharmik.thakkar@arm.com]
>Sent: Monday, April 1, 2019 3:19 PM
>To: Wang, Yipeng1 <yipeng1.wang@intel.com>; Gobriel, Sameh <sameh.gobriel@intel.com>; Richardson, Bruce
><bruce.richardson@intel.com>; De Lara Guarch, Pablo <pablo.de.lara.guarch@intel.com>
>Cc: dev@dpdk.org; honnappa.nagarahalli@arm.com; Dharmik Thakkar <dharmik.thakkar@arm.com>
>Subject: [PATCH v3 2/2] test/hash: lock-free rw concurrency test ext bkt
>
>Add unit test to check for hash lookup and bulk-lookup perf for
>extendable bucket feature.
>It is tested with both lock-free enabled and lock-free disabled case.
>
>Test includes:
>
>- hash lookup on keys in ext bkt
>- hash delete causing key-shifts of keys from ext bkt to secondary bkt
>
>Suggested-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
>Signed-off-by: Dharmik Thakkar <dharmik.thakkar@arm.com>
Acked-by: Yipeng Wang <yipeng1.wang@intel.com>

[dpdk-dev] [PATCH v4 0/2] hash: add lock free support for ext bkt

[Dharmik Thakkar]

This patch series:
- Enables lock-free read-write concurrency support for extendable
bucket feature.
- Adds lock-free read-write concurrency tests for ext bkt 

Dharmik Thakkar (2):
  hash: add lock free support for extendable bucket
  test/hash: lock-free rw concurrency test ext bkt

 app/test/test_hash_readwrite_lf.c  | 350 +++++++++++++++++++++++------
 doc/guides/prog_guide/hash_lib.rst |   6 +-
 lib/librte_hash/rte_cuckoo_hash.c  | 157 ++++++++-----
 lib/librte_hash/rte_cuckoo_hash.h  |   7 +
 4 files changed, 401 insertions(+), 119 deletions(-)

-- 
2.17.1

[dpdk-dev] [PATCH v4 0/2] hash: add lock free support for ext bkt

[Dharmik Thakkar]

This patch series:
- Enables lock-free read-write concurrency support for extendable
bucket feature.
- Adds lock-free read-write concurrency tests for ext bkt 

Dharmik Thakkar (2):
  hash: add lock free support for extendable bucket
  test/hash: lock-free rw concurrency test ext bkt

 app/test/test_hash_readwrite_lf.c  | 350 +++++++++++++++++++++++------
 doc/guides/prog_guide/hash_lib.rst |   6 +-
 lib/librte_hash/rte_cuckoo_hash.c  | 157 ++++++++-----
 lib/librte_hash/rte_cuckoo_hash.h  |   7 +
 4 files changed, 401 insertions(+), 119 deletions(-)

-- 
2.17.1

[dpdk-dev] [PATCH v4 1/2] hash: add lock free support for extendable bucket

[Dharmik Thakkar]

This patch enables lock-free read-write concurrency support for
extendable bucket feature.

Suggested-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
Signed-off-by: Dharmik Thakkar <dharmik.thakkar@arm.com>
Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
Reviewed-by: Gavin Hu <gavin.hu@arm.com>
Reviewed-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
Acked-by: Yipeng Wang <yipeng1.wang@intel.com>
---
v3:
- Update lib/librte_hash/rte_cuckoo_hash.c (Yipeng)
- Add Acked-by tag.
---
v2:
- Update doc (Yipeng)
- Update lib/librte_hash/rte_cuckoo_hash.c (Yipeng)
---
 doc/guides/prog_guide/hash_lib.rst |   6 +-
 lib/librte_hash/rte_cuckoo_hash.c  | 157 ++++++++++++++++++++---------
 lib/librte_hash/rte_cuckoo_hash.h  |   7 ++
 3 files changed, 117 insertions(+), 53 deletions(-)

diff --git a/doc/guides/prog_guide/hash_lib.rst b/doc/guides/prog_guide/hash_lib.rst
index 85a6edfa8b16..d06c7de2ead1 100644
--- a/doc/guides/prog_guide/hash_lib.rst
+++ b/doc/guides/prog_guide/hash_lib.rst
@@ -108,9 +108,9 @@ Extendable Bucket Functionality support
 An extra flag is used to enable this functionality (flag is not set by default). When the (RTE_HASH_EXTRA_FLAGS_EXT_TABLE) is set and
 in the very unlikely case due to excessive hash collisions that a key has failed to be inserted, the hash table bucket is extended with a linked
 list to insert these failed keys. This feature is important for the workloads (e.g. telco workloads) that need to insert up to 100% of the
-hash table size and can't tolerate any key insertion failure (even if very few). Currently the extendable bucket is not supported
-with the lock-free concurrency implementation (RTE_HASH_EXTRA_FLAGS_RW_CONCURRENCY_LF).
-
+hash table size and can't tolerate any key insertion failure (even if very few).
+Please note that with the 'lock free read/write concurrency' flag enabled, users need to call 'rte_hash_free_key_with_position' API in order to free the empty buckets and
+deleted keys, to maintain the 100% capacity guarantee.
 
 Implementation Details (non Extendable Bucket Case)
 ---------------------------------------------------
diff --git a/lib/librte_hash/rte_cuckoo_hash.c b/lib/librte_hash/rte_cuckoo_hash.c
index c01489ba5193..8213dbf5f782 100644
--- a/lib/librte_hash/rte_cuckoo_hash.c
+++ b/lib/librte_hash/rte_cuckoo_hash.c
@@ -140,6 +140,7 @@ rte_hash_create(const struct rte_hash_parameters *params)
 	unsigned int readwrite_concur_support = 0;
 	unsigned int writer_takes_lock = 0;
 	unsigned int no_free_on_del = 0;
+	uint32_t *ext_bkt_to_free = NULL;
 	uint32_t *tbl_chng_cnt = NULL;
 	unsigned int readwrite_concur_lf_support = 0;
 
@@ -170,15 +171,6 @@ rte_hash_create(const struct rte_hash_parameters *params)
 		return NULL;
 	}
 
-	if ((params->extra_flag & RTE_HASH_EXTRA_FLAGS_RW_CONCURRENCY_LF) &&
-	    (params->extra_flag & RTE_HASH_EXTRA_FLAGS_EXT_TABLE)) {
-		rte_errno = EINVAL;
-		RTE_LOG(ERR, HASH, "rte_hash_create: extendable bucket "
-			"feature not supported with rw concurrency "
-			"lock free\n");
-		return NULL;
-	}
-
 	/* Check extra flags field to check extra options. */
 	if (params->extra_flag & RTE_HASH_EXTRA_FLAGS_TRANS_MEM_SUPPORT)
 		hw_trans_mem_support = 1;
@@ -302,6 +294,16 @@ rte_hash_create(const struct rte_hash_parameters *params)
 		 */
 		for (i = 1; i <= num_buckets; i++)
 			rte_ring_sp_enqueue(r_ext, (void *)((uintptr_t) i));
+
+		if (readwrite_concur_lf_support) {
+			ext_bkt_to_free = rte_zmalloc(NULL, sizeof(uint32_t) *
+								num_key_slots, 0);
+			if (ext_bkt_to_free == NULL) {
+				RTE_LOG(ERR, HASH, "ext bkt to free memory allocation "
+								"failed\n");
+				goto err_unlock;
+			}
+		}
 	}
 
 	const uint32_t key_entry_size =
@@ -393,6 +395,7 @@ rte_hash_create(const struct rte_hash_parameters *params)
 		default_hash_func : params->hash_func;
 	h->key_store = k;
 	h->free_slots = r;
+	h->ext_bkt_to_free = ext_bkt_to_free;
 	h->tbl_chng_cnt = tbl_chng_cnt;
 	*h->tbl_chng_cnt = 0;
 	h->hw_trans_mem_support = hw_trans_mem_support;
@@ -443,6 +446,7 @@ rte_hash_create(const struct rte_hash_parameters *params)
 	rte_free(buckets_ext);
 	rte_free(k);
 	rte_free(tbl_chng_cnt);
+	rte_free(ext_bkt_to_free);
 	return NULL;
 }
 
@@ -484,6 +488,7 @@ rte_hash_free(struct rte_hash *h)
 	rte_free(h->buckets);
 	rte_free(h->buckets_ext);
 	rte_free(h->tbl_chng_cnt);
+	rte_free(h->ext_bkt_to_free);
 	rte_free(h);
 	rte_free(te);
 }
@@ -799,7 +804,7 @@ rte_hash_cuckoo_move_insert_mw(const struct rte_hash *h,
 			__atomic_store_n(h->tbl_chng_cnt,
 					 *h->tbl_chng_cnt + 1,
 					 __ATOMIC_RELEASE);
-			/* The stores to sig_alt and sig_current should not
+			/* The store to sig_current should not
 			 * move above the store to tbl_chng_cnt.
 			 */
 			__atomic_thread_fence(__ATOMIC_RELEASE);
@@ -831,7 +836,7 @@ rte_hash_cuckoo_move_insert_mw(const struct rte_hash *h,
 		__atomic_store_n(h->tbl_chng_cnt,
 				 *h->tbl_chng_cnt + 1,
 				 __ATOMIC_RELEASE);
-		/* The stores to sig_alt and sig_current should not
+		/* The store to sig_current should not
 		 * move above the store to tbl_chng_cnt.
 		 */
 		__atomic_thread_fence(__ATOMIC_RELEASE);
@@ -1054,7 +1059,12 @@ __rte_hash_add_key_with_hash(const struct rte_hash *h, const void *key,
 			/* Check if slot is available */
 			if (likely(cur_bkt->key_idx[i] == EMPTY_SLOT)) {
 				cur_bkt->sig_current[i] = short_sig;
-				cur_bkt->key_idx[i] = new_idx;
+				/* Store to signature should not leak after
+				 * the store to key_idx
+				 */
+				__atomic_store_n(&cur_bkt->key_idx[i],
+						 new_idx,
+						 __ATOMIC_RELEASE);
 				__hash_rw_writer_unlock(h);
 				return new_idx - 1;
 			}
@@ -1072,7 +1082,12 @@ __rte_hash_add_key_with_hash(const struct rte_hash *h, const void *key,
 	bkt_id = (uint32_t)((uintptr_t)ext_bkt_id) - 1;
 	/* Use the first location of the new bucket */
 	(h->buckets_ext[bkt_id]).sig_current[0] = short_sig;
-	(h->buckets_ext[bkt_id]).key_idx[0] = new_idx;
+	/* Store to signature should not leak after
+	 * the store to key_idx
+	 */
+	__atomic_store_n(&(h->buckets_ext[bkt_id]).key_idx[0],
+			 new_idx,
+			 __ATOMIC_RELEASE);
 	/* Link the new bucket to sec bucket linked list */
 	last = rte_hash_get_last_bkt(sec_bkt);
 	last->next = &h->buckets_ext[bkt_id];
@@ -1366,7 +1381,8 @@ remove_entry(const struct rte_hash *h, struct rte_hash_bucket *bkt, unsigned i)
  * empty slot.
  */
 static inline void
-__rte_hash_compact_ll(struct rte_hash_bucket *cur_bkt, int pos) {
+__rte_hash_compact_ll(const struct rte_hash *h,
+			struct rte_hash_bucket *cur_bkt, int pos) {
 	int i;
 	struct rte_hash_bucket *last_bkt;
 
@@ -1377,10 +1393,27 @@ __rte_hash_compact_ll(struct rte_hash_bucket *cur_bkt, int pos) {
 
 	for (i = RTE_HASH_BUCKET_ENTRIES - 1; i >= 0; i--) {
 		if (last_bkt->key_idx[i] != EMPTY_SLOT) {
-			cur_bkt->key_idx[pos] = last_bkt->key_idx[i];
 			cur_bkt->sig_current[pos] = last_bkt->sig_current[i];
+			__atomic_store_n(&cur_bkt->key_idx[pos],
+					 last_bkt->key_idx[i],
+					 __ATOMIC_RELEASE);
+			if (h->readwrite_concur_lf_support) {
+				/* Inform the readers that the table has changed
+				 * Since there is one writer, load acquire on
+				 * tbl_chng_cnt is not required.
+				 */
+				__atomic_store_n(h->tbl_chng_cnt,
+					 *h->tbl_chng_cnt + 1,
+					 __ATOMIC_RELEASE);
+				/* The store to sig_current should
+				 * not move above the store to tbl_chng_cnt.
+				 */
+				__atomic_thread_fence(__ATOMIC_RELEASE);
+			}
 			last_bkt->sig_current[i] = NULL_SIGNATURE;
-			last_bkt->key_idx[i] = EMPTY_SLOT;
+			__atomic_store_n(&last_bkt->key_idx[i],
+					 EMPTY_SLOT,
+					 __ATOMIC_RELEASE);
 			return;
 		}
 	}
@@ -1449,7 +1482,7 @@ __rte_hash_del_key_with_hash(const struct rte_hash *h, const void *key,
 	/* look for key in primary bucket */
 	ret = search_and_remove(h, key, prim_bkt, short_sig, &pos);
 	if (ret != -1) {
-		__rte_hash_compact_ll(prim_bkt, pos);
+		__rte_hash_compact_ll(h, prim_bkt, pos);
 		last_bkt = prim_bkt->next;
 		prev_bkt = prim_bkt;
 		goto return_bkt;
@@ -1461,7 +1494,7 @@ __rte_hash_del_key_with_hash(const struct rte_hash *h, const void *key,
 	FOR_EACH_BUCKET(cur_bkt, sec_bkt) {
 		ret = search_and_remove(h, key, cur_bkt, short_sig, &pos);
 		if (ret != -1) {
-			__rte_hash_compact_ll(cur_bkt, pos);
+			__rte_hash_compact_ll(h, cur_bkt, pos);
 			last_bkt = sec_bkt->next;
 			prev_bkt = sec_bkt;
 			goto return_bkt;
@@ -1488,11 +1521,24 @@ __rte_hash_del_key_with_hash(const struct rte_hash *h, const void *key,
 	}
 	/* found empty bucket and recycle */
 	if (i == RTE_HASH_BUCKET_ENTRIES) {
-		prev_bkt->next = last_bkt->next = NULL;
+		prev_bkt->next = NULL;
 		uint32_t index = last_bkt - h->buckets_ext + 1;
-		rte_ring_sp_enqueue(h->free_ext_bkts, (void *)(uintptr_t)index);
+		/* Recycle the empty bkt if
+		 * no_free_on_del is disabled.
+		 */
+		if (h->no_free_on_del)
+			/* Store index of an empty ext bkt to be recycled
+			 * on calling rte_hash_del_xxx APIs.
+			 * When lock free read-write concurrency is enabled,
+			 * an empty ext bkt cannot be put into free list
+			 * immediately (as readers might be using it still).
+			 * Hence freeing of the ext bkt is piggy-backed to
+			 * freeing of the key index.
+			 */
+			h->ext_bkt_to_free[ret] = index;
+		else
+			rte_ring_sp_enqueue(h->free_ext_bkts, (void *)(uintptr_t)index);
 	}
-
 	__hash_rw_writer_unlock(h);
 	return ret;
 }
@@ -1545,6 +1591,14 @@ rte_hash_free_key_with_position(const struct rte_hash *h,
 	/* Out of bounds */
 	if (position >= total_entries)
 		return -EINVAL;
+	if (h->ext_table_support && h->readwrite_concur_lf_support) {
+		uint32_t index = h->ext_bkt_to_free[position];
+		if (index) {
+			/* Recycle empty ext bkt to free list. */
+			rte_ring_sp_enqueue(h->free_ext_bkts, (void *)(uintptr_t)index);
+			h->ext_bkt_to_free[position] = 0;
+		}
+	}
 
 	if (h->use_local_cache) {
 		lcore_id = rte_lcore_id();
@@ -1855,6 +1909,9 @@ __rte_hash_lookup_bulk_lf(const struct rte_hash *h, const void **keys,
 		rte_prefetch0(secondary_bkt[i]);
 	}
 
+	for (i = 0; i < num_keys; i++)
+		positions[i] = -ENOENT;
+
 	do {
 		/* Load the table change counter before the lookup
 		 * starts. Acquire semantics will make sure that
@@ -1899,7 +1956,6 @@ __rte_hash_lookup_bulk_lf(const struct rte_hash *h, const void **keys,
 
 		/* Compare keys, first hits in primary first */
 		for (i = 0; i < num_keys; i++) {
-			positions[i] = -ENOENT;
 			while (prim_hitmask[i]) {
 				uint32_t hit_index =
 						__builtin_ctzl(prim_hitmask[i])
@@ -1972,6 +2028,35 @@ __rte_hash_lookup_bulk_lf(const struct rte_hash *h, const void **keys,
 			continue;
 		}
 
+		/* all found, do not need to go through ext bkt */
+		if (hits == ((1ULL << num_keys) - 1)) {
+			if (hit_mask != NULL)
+				*hit_mask = hits;
+			return;
+		}
+		/* need to check ext buckets for match */
+		if (h->ext_table_support) {
+			for (i = 0; i < num_keys; i++) {
+				if ((hits & (1ULL << i)) != 0)
+					continue;
+				next_bkt = secondary_bkt[i]->next;
+				FOR_EACH_BUCKET(cur_bkt, next_bkt) {
+					if (data != NULL)
+						ret = search_one_bucket_lf(h,
+							keys[i], sig[i],
+							&data[i], cur_bkt);
+					else
+						ret = search_one_bucket_lf(h,
+								keys[i], sig[i],
+								NULL, cur_bkt);
+					if (ret != -1) {
+						positions[i] = ret;
+						hits |= 1ULL << i;
+						break;
+					}
+				}
+			}
+		}
 		/* The loads of sig_current in compare_signatures
 		 * should not move below the load from tbl_chng_cnt.
 		 */
@@ -1988,34 +2073,6 @@ __rte_hash_lookup_bulk_lf(const struct rte_hash *h, const void **keys,
 					__ATOMIC_ACQUIRE);
 	} while (cnt_b != cnt_a);
 
-	/* all found, do not need to go through ext bkt */
-	if ((hits == ((1ULL << num_keys) - 1)) || !h->ext_table_support) {
-		if (hit_mask != NULL)
-			*hit_mask = hits;
-		__hash_rw_reader_unlock(h);
-		return;
-	}
-
-	/* need to check ext buckets for match */
-	for (i = 0; i < num_keys; i++) {
-		if ((hits & (1ULL << i)) != 0)
-			continue;
-		next_bkt = secondary_bkt[i]->next;
-		FOR_EACH_BUCKET(cur_bkt, next_bkt) {
-			if (data != NULL)
-				ret = search_one_bucket_lf(h, keys[i],
-						sig[i], &data[i], cur_bkt);
-			else
-				ret = search_one_bucket_lf(h, keys[i],
-						sig[i], NULL, cur_bkt);
-			if (ret != -1) {
-				positions[i] = ret;
-				hits |= 1ULL << i;
-				break;
-			}
-		}
-	}
-
 	if (hit_mask != NULL)
 		*hit_mask = hits;
 }
diff --git a/lib/librte_hash/rte_cuckoo_hash.h b/lib/librte_hash/rte_cuckoo_hash.h
index eacdaa8d4684..48c85c890712 100644
--- a/lib/librte_hash/rte_cuckoo_hash.h
+++ b/lib/librte_hash/rte_cuckoo_hash.h
@@ -210,6 +210,13 @@ struct rte_hash {
 	rte_rwlock_t *readwrite_lock; /**< Read-write lock thread-safety. */
 	struct rte_hash_bucket *buckets_ext; /**< Extra buckets array */
 	struct rte_ring *free_ext_bkts; /**< Ring of indexes of free buckets */
+	/* Stores index of an empty ext bkt to be recycled on calling
+	 * rte_hash_del_xxx APIs. When lock free read-write concurrency is
+	 * enabled, an empty ext bkt cannot be put into free list immediately
+	 * (as readers might be using it still). Hence freeing of the ext bkt
+	 * is piggy-backed to freeing of the key index.
+	 */
+	uint32_t *ext_bkt_to_free;
 	uint32_t *tbl_chng_cnt;
 	/**< Indicates if the hash table changed from last read. */
 } __rte_cache_aligned;
-- 
2.17.1

[dpdk-dev] [PATCH v4 1/2] hash: add lock free support for extendable bucket

[Dharmik Thakkar]

This patch enables lock-free read-write concurrency support for
extendable bucket feature.

Suggested-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
Signed-off-by: Dharmik Thakkar <dharmik.thakkar@arm.com>
Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
Reviewed-by: Gavin Hu <gavin.hu@arm.com>
Reviewed-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
Acked-by: Yipeng Wang <yipeng1.wang@intel.com>
---
v3:
- Update lib/librte_hash/rte_cuckoo_hash.c (Yipeng)
- Add Acked-by tag.
---
v2:
- Update doc (Yipeng)
- Update lib/librte_hash/rte_cuckoo_hash.c (Yipeng)
---
 doc/guides/prog_guide/hash_lib.rst |   6 +-
 lib/librte_hash/rte_cuckoo_hash.c  | 157 ++++++++++++++++++++---------
 lib/librte_hash/rte_cuckoo_hash.h  |   7 ++
 3 files changed, 117 insertions(+), 53 deletions(-)

diff --git a/doc/guides/prog_guide/hash_lib.rst b/doc/guides/prog_guide/hash_lib.rst
index 85a6edfa8b16..d06c7de2ead1 100644
--- a/doc/guides/prog_guide/hash_lib.rst
+++ b/doc/guides/prog_guide/hash_lib.rst
@@ -108,9 +108,9 @@ Extendable Bucket Functionality support
 An extra flag is used to enable this functionality (flag is not set by default). When the (RTE_HASH_EXTRA_FLAGS_EXT_TABLE) is set and
 in the very unlikely case due to excessive hash collisions that a key has failed to be inserted, the hash table bucket is extended with a linked
 list to insert these failed keys. This feature is important for the workloads (e.g. telco workloads) that need to insert up to 100% of the
-hash table size and can't tolerate any key insertion failure (even if very few). Currently the extendable bucket is not supported
-with the lock-free concurrency implementation (RTE_HASH_EXTRA_FLAGS_RW_CONCURRENCY_LF).
-
+hash table size and can't tolerate any key insertion failure (even if very few).
+Please note that with the 'lock free read/write concurrency' flag enabled, users need to call 'rte_hash_free_key_with_position' API in order to free the empty buckets and
+deleted keys, to maintain the 100% capacity guarantee.
 
 Implementation Details (non Extendable Bucket Case)
 ---------------------------------------------------
diff --git a/lib/librte_hash/rte_cuckoo_hash.c b/lib/librte_hash/rte_cuckoo_hash.c
index c01489ba5193..8213dbf5f782 100644
--- a/lib/librte_hash/rte_cuckoo_hash.c
+++ b/lib/librte_hash/rte_cuckoo_hash.c
@@ -140,6 +140,7 @@ rte_hash_create(const struct rte_hash_parameters *params)
 	unsigned int readwrite_concur_support = 0;
 	unsigned int writer_takes_lock = 0;
 	unsigned int no_free_on_del = 0;
+	uint32_t *ext_bkt_to_free = NULL;
 	uint32_t *tbl_chng_cnt = NULL;
 	unsigned int readwrite_concur_lf_support = 0;
 
@@ -170,15 +171,6 @@ rte_hash_create(const struct rte_hash_parameters *params)
 		return NULL;
 	}
 
-	if ((params->extra_flag & RTE_HASH_EXTRA_FLAGS_RW_CONCURRENCY_LF) &&
-	    (params->extra_flag & RTE_HASH_EXTRA_FLAGS_EXT_TABLE)) {
-		rte_errno = EINVAL;
-		RTE_LOG(ERR, HASH, "rte_hash_create: extendable bucket "
-			"feature not supported with rw concurrency "
-			"lock free\n");
-		return NULL;
-	}
-
 	/* Check extra flags field to check extra options. */
 	if (params->extra_flag & RTE_HASH_EXTRA_FLAGS_TRANS_MEM_SUPPORT)
 		hw_trans_mem_support = 1;
@@ -302,6 +294,16 @@ rte_hash_create(const struct rte_hash_parameters *params)
 		 */
 		for (i = 1; i <= num_buckets; i++)
 			rte_ring_sp_enqueue(r_ext, (void *)((uintptr_t) i));
+
+		if (readwrite_concur_lf_support) {
+			ext_bkt_to_free = rte_zmalloc(NULL, sizeof(uint32_t) *
+								num_key_slots, 0);
+			if (ext_bkt_to_free == NULL) {
+				RTE_LOG(ERR, HASH, "ext bkt to free memory allocation "
+								"failed\n");
+				goto err_unlock;
+			}
+		}
 	}
 
 	const uint32_t key_entry_size =
@@ -393,6 +395,7 @@ rte_hash_create(const struct rte_hash_parameters *params)
 		default_hash_func : params->hash_func;
 	h->key_store = k;
 	h->free_slots = r;
+	h->ext_bkt_to_free = ext_bkt_to_free;
 	h->tbl_chng_cnt = tbl_chng_cnt;
 	*h->tbl_chng_cnt = 0;
 	h->hw_trans_mem_support = hw_trans_mem_support;
@@ -443,6 +446,7 @@ rte_hash_create(const struct rte_hash_parameters *params)
 	rte_free(buckets_ext);
 	rte_free(k);
 	rte_free(tbl_chng_cnt);
+	rte_free(ext_bkt_to_free);
 	return NULL;
 }
 
@@ -484,6 +488,7 @@ rte_hash_free(struct rte_hash *h)
 	rte_free(h->buckets);
 	rte_free(h->buckets_ext);
 	rte_free(h->tbl_chng_cnt);
+	rte_free(h->ext_bkt_to_free);
 	rte_free(h);
 	rte_free(te);
 }
@@ -799,7 +804,7 @@ rte_hash_cuckoo_move_insert_mw(const struct rte_hash *h,
 			__atomic_store_n(h->tbl_chng_cnt,
 					 *h->tbl_chng_cnt + 1,
 					 __ATOMIC_RELEASE);
-			/* The stores to sig_alt and sig_current should not
+			/* The store to sig_current should not
 			 * move above the store to tbl_chng_cnt.
 			 */
 			__atomic_thread_fence(__ATOMIC_RELEASE);
@@ -831,7 +836,7 @@ rte_hash_cuckoo_move_insert_mw(const struct rte_hash *h,
 		__atomic_store_n(h->tbl_chng_cnt,
 				 *h->tbl_chng_cnt + 1,
 				 __ATOMIC_RELEASE);
-		/* The stores to sig_alt and sig_current should not
+		/* The store to sig_current should not
 		 * move above the store to tbl_chng_cnt.
 		 */
 		__atomic_thread_fence(__ATOMIC_RELEASE);
@@ -1054,7 +1059,12 @@ __rte_hash_add_key_with_hash(const struct rte_hash *h, const void *key,
 			/* Check if slot is available */
 			if (likely(cur_bkt->key_idx[i] == EMPTY_SLOT)) {
 				cur_bkt->sig_current[i] = short_sig;
-				cur_bkt->key_idx[i] = new_idx;
+				/* Store to signature should not leak after
+				 * the store to key_idx
+				 */
+				__atomic_store_n(&cur_bkt->key_idx[i],
+						 new_idx,
+						 __ATOMIC_RELEASE);
 				__hash_rw_writer_unlock(h);
 				return new_idx - 1;
 			}
@@ -1072,7 +1082,12 @@ __rte_hash_add_key_with_hash(const struct rte_hash *h, const void *key,
 	bkt_id = (uint32_t)((uintptr_t)ext_bkt_id) - 1;
 	/* Use the first location of the new bucket */
 	(h->buckets_ext[bkt_id]).sig_current[0] = short_sig;
-	(h->buckets_ext[bkt_id]).key_idx[0] = new_idx;
+	/* Store to signature should not leak after
+	 * the store to key_idx
+	 */
+	__atomic_store_n(&(h->buckets_ext[bkt_id]).key_idx[0],
+			 new_idx,
+			 __ATOMIC_RELEASE);
 	/* Link the new bucket to sec bucket linked list */
 	last = rte_hash_get_last_bkt(sec_bkt);
 	last->next = &h->buckets_ext[bkt_id];
@@ -1366,7 +1381,8 @@ remove_entry(const struct rte_hash *h, struct rte_hash_bucket *bkt, unsigned i)
  * empty slot.
  */
 static inline void
-__rte_hash_compact_ll(struct rte_hash_bucket *cur_bkt, int pos) {
+__rte_hash_compact_ll(const struct rte_hash *h,
+			struct rte_hash_bucket *cur_bkt, int pos) {
 	int i;
 	struct rte_hash_bucket *last_bkt;
 
@@ -1377,10 +1393,27 @@ __rte_hash_compact_ll(struct rte_hash_bucket *cur_bkt, int pos) {
 
 	for (i = RTE_HASH_BUCKET_ENTRIES - 1; i >= 0; i--) {
 		if (last_bkt->key_idx[i] != EMPTY_SLOT) {
-			cur_bkt->key_idx[pos] = last_bkt->key_idx[i];
 			cur_bkt->sig_current[pos] = last_bkt->sig_current[i];
+			__atomic_store_n(&cur_bkt->key_idx[pos],
+					 last_bkt->key_idx[i],
+					 __ATOMIC_RELEASE);
+			if (h->readwrite_concur_lf_support) {
+				/* Inform the readers that the table has changed
+				 * Since there is one writer, load acquire on
+				 * tbl_chng_cnt is not required.
+				 */
+				__atomic_store_n(h->tbl_chng_cnt,
+					 *h->tbl_chng_cnt + 1,
+					 __ATOMIC_RELEASE);
+				/* The store to sig_current should
+				 * not move above the store to tbl_chng_cnt.
+				 */
+				__atomic_thread_fence(__ATOMIC_RELEASE);
+			}
 			last_bkt->sig_current[i] = NULL_SIGNATURE;
-			last_bkt->key_idx[i] = EMPTY_SLOT;
+			__atomic_store_n(&last_bkt->key_idx[i],
+					 EMPTY_SLOT,
+					 __ATOMIC_RELEASE);
 			return;
 		}
 	}
@@ -1449,7 +1482,7 @@ __rte_hash_del_key_with_hash(const struct rte_hash *h, const void *key,
 	/* look for key in primary bucket */
 	ret = search_and_remove(h, key, prim_bkt, short_sig, &pos);
 	if (ret != -1) {
-		__rte_hash_compact_ll(prim_bkt, pos);
+		__rte_hash_compact_ll(h, prim_bkt, pos);
 		last_bkt = prim_bkt->next;
 		prev_bkt = prim_bkt;
 		goto return_bkt;
@@ -1461,7 +1494,7 @@ __rte_hash_del_key_with_hash(const struct rte_hash *h, const void *key,
 	FOR_EACH_BUCKET(cur_bkt, sec_bkt) {
 		ret = search_and_remove(h, key, cur_bkt, short_sig, &pos);
 		if (ret != -1) {
-			__rte_hash_compact_ll(cur_bkt, pos);
+			__rte_hash_compact_ll(h, cur_bkt, pos);
 			last_bkt = sec_bkt->next;
 			prev_bkt = sec_bkt;
 			goto return_bkt;
@@ -1488,11 +1521,24 @@ __rte_hash_del_key_with_hash(const struct rte_hash *h, const void *key,
 	}
 	/* found empty bucket and recycle */
 	if (i == RTE_HASH_BUCKET_ENTRIES) {
-		prev_bkt->next = last_bkt->next = NULL;
+		prev_bkt->next = NULL;
 		uint32_t index = last_bkt - h->buckets_ext + 1;
-		rte_ring_sp_enqueue(h->free_ext_bkts, (void *)(uintptr_t)index);
+		/* Recycle the empty bkt if
+		 * no_free_on_del is disabled.
+		 */
+		if (h->no_free_on_del)
+			/* Store index of an empty ext bkt to be recycled
+			 * on calling rte_hash_del_xxx APIs.
+			 * When lock free read-write concurrency is enabled,
+			 * an empty ext bkt cannot be put into free list
+			 * immediately (as readers might be using it still).
+			 * Hence freeing of the ext bkt is piggy-backed to
+			 * freeing of the key index.
+			 */
+			h->ext_bkt_to_free[ret] = index;
+		else
+			rte_ring_sp_enqueue(h->free_ext_bkts, (void *)(uintptr_t)index);
 	}
-
 	__hash_rw_writer_unlock(h);
 	return ret;
 }
@@ -1545,6 +1591,14 @@ rte_hash_free_key_with_position(const struct rte_hash *h,
 	/* Out of bounds */
 	if (position >= total_entries)
 		return -EINVAL;
+	if (h->ext_table_support && h->readwrite_concur_lf_support) {
+		uint32_t index = h->ext_bkt_to_free[position];
+		if (index) {
+			/* Recycle empty ext bkt to free list. */
+			rte_ring_sp_enqueue(h->free_ext_bkts, (void *)(uintptr_t)index);
+			h->ext_bkt_to_free[position] = 0;
+		}
+	}
 
 	if (h->use_local_cache) {
 		lcore_id = rte_lcore_id();
@@ -1855,6 +1909,9 @@ __rte_hash_lookup_bulk_lf(const struct rte_hash *h, const void **keys,
 		rte_prefetch0(secondary_bkt[i]);
 	}
 
+	for (i = 0; i < num_keys; i++)
+		positions[i] = -ENOENT;
+
 	do {
 		/* Load the table change counter before the lookup
 		 * starts. Acquire semantics will make sure that
@@ -1899,7 +1956,6 @@ __rte_hash_lookup_bulk_lf(const struct rte_hash *h, const void **keys,
 
 		/* Compare keys, first hits in primary first */
 		for (i = 0; i < num_keys; i++) {
-			positions[i] = -ENOENT;
 			while (prim_hitmask[i]) {
 				uint32_t hit_index =
 						__builtin_ctzl(prim_hitmask[i])
@@ -1972,6 +2028,35 @@ __rte_hash_lookup_bulk_lf(const struct rte_hash *h, const void **keys,
 			continue;
 		}
 
+		/* all found, do not need to go through ext bkt */
+		if (hits == ((1ULL << num_keys) - 1)) {
+			if (hit_mask != NULL)
+				*hit_mask = hits;
+			return;
+		}
+		/* need to check ext buckets for match */
+		if (h->ext_table_support) {
+			for (i = 0; i < num_keys; i++) {
+				if ((hits & (1ULL << i)) != 0)
+					continue;
+				next_bkt = secondary_bkt[i]->next;
+				FOR_EACH_BUCKET(cur_bkt, next_bkt) {
+					if (data != NULL)
+						ret = search_one_bucket_lf(h,
+							keys[i], sig[i],
+							&data[i], cur_bkt);
+					else
+						ret = search_one_bucket_lf(h,
+								keys[i], sig[i],
+								NULL, cur_bkt);
+					if (ret != -1) {
+						positions[i] = ret;
+						hits |= 1ULL << i;
+						break;
+					}
+				}
+			}
+		}
 		/* The loads of sig_current in compare_signatures
 		 * should not move below the load from tbl_chng_cnt.
 		 */
@@ -1988,34 +2073,6 @@ __rte_hash_lookup_bulk_lf(const struct rte_hash *h, const void **keys,
 					__ATOMIC_ACQUIRE);
 	} while (cnt_b != cnt_a);
 
-	/* all found, do not need to go through ext bkt */
-	if ((hits == ((1ULL << num_keys) - 1)) || !h->ext_table_support) {
-		if (hit_mask != NULL)
-			*hit_mask = hits;
-		__hash_rw_reader_unlock(h);
-		return;
-	}
-
-	/* need to check ext buckets for match */
-	for (i = 0; i < num_keys; i++) {
-		if ((hits & (1ULL << i)) != 0)
-			continue;
-		next_bkt = secondary_bkt[i]->next;
-		FOR_EACH_BUCKET(cur_bkt, next_bkt) {
-			if (data != NULL)
-				ret = search_one_bucket_lf(h, keys[i],
-						sig[i], &data[i], cur_bkt);
-			else
-				ret = search_one_bucket_lf(h, keys[i],
-						sig[i], NULL, cur_bkt);
-			if (ret != -1) {
-				positions[i] = ret;
-				hits |= 1ULL << i;
-				break;
-			}
-		}
-	}
-
 	if (hit_mask != NULL)
 		*hit_mask = hits;
 }
diff --git a/lib/librte_hash/rte_cuckoo_hash.h b/lib/librte_hash/rte_cuckoo_hash.h
index eacdaa8d4684..48c85c890712 100644
--- a/lib/librte_hash/rte_cuckoo_hash.h
+++ b/lib/librte_hash/rte_cuckoo_hash.h
@@ -210,6 +210,13 @@ struct rte_hash {
 	rte_rwlock_t *readwrite_lock; /**< Read-write lock thread-safety. */
 	struct rte_hash_bucket *buckets_ext; /**< Extra buckets array */
 	struct rte_ring *free_ext_bkts; /**< Ring of indexes of free buckets */
+	/* Stores index of an empty ext bkt to be recycled on calling
+	 * rte_hash_del_xxx APIs. When lock free read-write concurrency is
+	 * enabled, an empty ext bkt cannot be put into free list immediately
+	 * (as readers might be using it still). Hence freeing of the ext bkt
+	 * is piggy-backed to freeing of the key index.
+	 */
+	uint32_t *ext_bkt_to_free;
 	uint32_t *tbl_chng_cnt;
 	/**< Indicates if the hash table changed from last read. */
 } __rte_cache_aligned;
-- 
2.17.1

[dpdk-dev] [PATCH v4 2/2] test/hash: lock-free rw concurrency test ext bkt

[Dharmik Thakkar]

Add unit test to check for hash lookup and bulk-lookup perf for
extendable bucket feature.
It is tested with both lock-free enabled and lock-free disabled case.

Test includes:

- hash lookup on keys in ext bkt
- hash delete causing key-shifts of keys from ext bkt to secondary bkt

Suggested-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
Signed-off-by: Dharmik Thakkar <dharmik.thakkar@arm.com>
Acked-by: Yipeng Wang <yipeng1.wang@intel.com>
---
v4:
- Add Acked-by tag.
---
v3:
- Update commit message (Yipeng)
---
 app/test/test_hash_readwrite_lf.c | 350 ++++++++++++++++++++++++------
 1 file changed, 284 insertions(+), 66 deletions(-)

diff --git a/app/test/test_hash_readwrite_lf.c b/app/test/test_hash_readwrite_lf.c
index cbfd9322696b..ddd8d7aa6a7d 100644
--- a/app/test/test_hash_readwrite_lf.c
+++ b/app/test/test_hash_readwrite_lf.c
@@ -41,6 +41,12 @@
 #define READ_PASS_SHIFT_PATH 4
 #define READ_PASS_NON_SHIFT_PATH 8
 #define BULK_LOOKUP 16
+#define READ_PASS_KEY_SHIFTS_EXTBKT 32
+
+#define WRITE_NO_KEY_SHIFT 0
+#define WRITE_KEY_SHIFT 1
+#define WRITE_EXT_BKT 2
+
 #define NUM_TEST 3
 unsigned int rwc_core_cnt[NUM_TEST] = {1, 2, 4};
 
@@ -51,6 +57,7 @@ struct rwc_perf {
 	uint32_t w_ks_r_hit_sp[2][NUM_TEST];
 	uint32_t w_ks_r_miss[2][NUM_TEST];
 	uint32_t multi_rw[NUM_TEST - 1][2][NUM_TEST];
+	uint32_t w_ks_r_hit_extbkt[2][NUM_TEST];
 };
 
 static struct rwc_perf rwc_lf_results, rwc_non_lf_results;
@@ -62,11 +69,15 @@ struct {
 	uint32_t *keys_absent;
 	uint32_t *keys_shift_path;
 	uint32_t *keys_non_shift_path;
+	uint32_t *keys_ext_bkt;
+	uint32_t *keys_ks_extbkt;
 	uint32_t count_keys_no_ks;
 	uint32_t count_keys_ks;
 	uint32_t count_keys_absent;
 	uint32_t count_keys_shift_path;
 	uint32_t count_keys_non_shift_path;
+	uint32_t count_keys_extbkt;
+	uint32_t count_keys_ks_extbkt;
 	uint32_t single_insert;
 	struct rte_hash *h;
 } tbl_rwc_test_param;
@@ -81,6 +92,35 @@ uint16_t enabled_core_ids[RTE_MAX_LCORE];
 
 uint8_t *scanned_bkts;
 
+static inline uint16_t
+get_short_sig(const hash_sig_t hash)
+{
+	return hash >> 16;
+}
+
+static inline uint32_t
+get_prim_bucket_index(__attribute__((unused)) const struct rte_hash *h,
+		      const hash_sig_t hash)
+{
+	uint32_t num_buckets;
+	uint32_t bucket_bitmask;
+	num_buckets  = rte_align32pow2(TOTAL_ENTRY) / 8;
+	bucket_bitmask = num_buckets - 1;
+	return hash & bucket_bitmask;
+}
+
+static inline uint32_t
+get_alt_bucket_index(__attribute__((unused)) const struct rte_hash *h,
+			uint32_t cur_bkt_idx, uint16_t sig)
+{
+	uint32_t num_buckets;
+	uint32_t bucket_bitmask;
+	num_buckets  = rte_align32pow2(TOTAL_ENTRY) / 8;
+	bucket_bitmask = num_buckets - 1;
+	return (cur_bkt_idx ^ sig) & bucket_bitmask;
+}
+
+
 static inline int
 get_enabled_cores_list(void)
 {
@@ -168,9 +208,12 @@ generate_keys(void)
 	uint32_t *keys_ks = NULL;
 	uint32_t *keys_absent = NULL;
 	uint32_t *keys_non_shift_path = NULL;
+	uint32_t *keys_ext_bkt = NULL;
+	uint32_t *keys_ks_extbkt = NULL;
 	uint32_t *found = NULL;
 	uint32_t count_keys_no_ks = 0;
 	uint32_t count_keys_ks = 0;
+	uint32_t count_keys_extbkt = 0;
 	uint32_t i;
 
 	/*
@@ -251,14 +294,32 @@ generate_keys(void)
 		goto err;
 	}
 
+	/*
+	 * This consist of keys which will be stored in extended buckets
+	 */
+	keys_ext_bkt = rte_malloc(NULL, sizeof(uint32_t) * TOTAL_INSERT, 0);
+	if (keys_ext_bkt == NULL) {
+		printf("RTE_MALLOC failed\n");
+		goto err;
+	}
+
+	/*
+	 * This consist of keys which when deleted causes shifting of keys
+	 * in extended buckets to respective secondary buckets
+	 */
+	keys_ks_extbkt = rte_malloc(NULL, sizeof(uint32_t) * TOTAL_INSERT, 0);
+	if (keys_ks_extbkt == NULL) {
+		printf("RTE_MALLOC failed\n");
+		goto err;
+	}
 
 	hash_sig_t sig;
 	uint32_t prim_bucket_idx;
-	int ret;
+	uint32_t sec_bucket_idx;
+	uint16_t short_sig;
 	uint32_t num_buckets;
-	uint32_t bucket_bitmask;
 	num_buckets  = rte_align32pow2(TOTAL_ENTRY) / 8;
-	bucket_bitmask = num_buckets - 1;
+	int ret;
 
 	/*
 	 * Used to mark bkts in which at least one key was shifted to its
@@ -275,6 +336,8 @@ generate_keys(void)
 	tbl_rwc_test_param.keys_ks = keys_ks;
 	tbl_rwc_test_param.keys_absent = keys_absent;
 	tbl_rwc_test_param.keys_non_shift_path = keys_non_shift_path;
+	tbl_rwc_test_param.keys_ext_bkt = keys_ext_bkt;
+	tbl_rwc_test_param.keys_ks_extbkt = keys_ks_extbkt;
 	/* Generate keys by adding previous two keys, neglect overflow */
 	printf("Generating keys...\n");
 	keys[0] = 0;
@@ -287,7 +350,8 @@ generate_keys(void)
 		/* Check if primary bucket has space.*/
 		sig = rte_hash_hash(tbl_rwc_test_param.h,
 					tbl_rwc_test_param.keys+i);
-		prim_bucket_idx = sig & bucket_bitmask;
+		prim_bucket_idx = get_prim_bucket_index(tbl_rwc_test_param.h,
+							sig);
 		ret = check_bucket(prim_bucket_idx, keys[i]);
 		if (ret < 0) {
 			/*
@@ -368,6 +432,47 @@ generate_keys(void)
 	tbl_rwc_test_param.count_keys_absent = count_keys_absent;
 	tbl_rwc_test_param.count_keys_non_shift_path = count;
 
+	memset(scanned_bkts, 0, num_buckets);
+	count = 0;
+	/* Find keys that will be in extended buckets */
+	for (i = 0; i < count_keys_ks; i++) {
+		ret = rte_hash_add_key(tbl_rwc_test_param.h, keys_ks + i);
+		if (ret < 0) {
+			/* Key will be added to ext bkt */
+			keys_ext_bkt[count_keys_extbkt++] = keys_ks[i];
+			/* Sec bkt to be added to keys_ks_extbkt */
+			sig = rte_hash_hash(tbl_rwc_test_param.h,
+					tbl_rwc_test_param.keys_ks + i);
+			prim_bucket_idx = get_prim_bucket_index(
+						tbl_rwc_test_param.h, sig);
+			short_sig = get_short_sig(sig);
+			sec_bucket_idx = get_alt_bucket_index(
+						tbl_rwc_test_param.h,
+						prim_bucket_idx, short_sig);
+			if (scanned_bkts[sec_bucket_idx] == 0)
+				scanned_bkts[sec_bucket_idx] = 1;
+		}
+	}
+
+	/* Find keys that will shift keys in ext bucket*/
+	for (i = 0; i < num_buckets; i++) {
+		if (scanned_bkts[i] == 1) {
+			iter = i * 8;
+			while (rte_hash_iterate(tbl_rwc_test_param.h,
+				&next_key, &next_data, &iter) >= 0) {
+				/* Check if key belongs to the current bucket */
+				if (i >= (iter-1)/8)
+					keys_ks_extbkt[count++]
+						= *(const uint32_t *)next_key;
+				else
+					break;
+			}
+		}
+	}
+
+	tbl_rwc_test_param.count_keys_ks_extbkt = count;
+	tbl_rwc_test_param.count_keys_extbkt = count_keys_extbkt;
+
 	printf("\nCount of keys NOT causing shifting of existing keys to "
 	"alternate location: %d\n", tbl_rwc_test_param.count_keys_no_ks);
 	printf("\nCount of keys causing shifting of existing keys to alternate "
@@ -378,6 +483,10 @@ generate_keys(void)
 	       tbl_rwc_test_param.count_keys_shift_path);
 	printf("Count of keys not likely to be on the shift path: %d\n\n",
 	       tbl_rwc_test_param.count_keys_non_shift_path);
+	printf("Count of keys in extended buckets: %d\n\n",
+	       tbl_rwc_test_param.count_keys_extbkt);
+	printf("Count of keys shifting keys in ext buckets: %d\n\n",
+	       tbl_rwc_test_param.count_keys_ks_extbkt);
 
 	rte_free(found);
 	rte_hash_free(tbl_rwc_test_param.h);
@@ -390,12 +499,14 @@ generate_keys(void)
 	rte_free(keys_absent);
 	rte_free(found);
 	rte_free(tbl_rwc_test_param.keys_shift_path);
+	rte_free(keys_ext_bkt);
+	rte_free(keys_ks_extbkt);
 	rte_free(scanned_bkts);
 	return -1;
 }
 
 static int
-init_params(int rwc_lf, int use_jhash, int htm)
+init_params(int rwc_lf, int use_jhash, int htm, int ext_bkt)
 {
 	struct rte_hash *handle;
 
@@ -425,6 +536,9 @@ init_params(int rwc_lf, int use_jhash, int htm)
 			RTE_HASH_EXTRA_FLAGS_RW_CONCURRENCY |
 			RTE_HASH_EXTRA_FLAGS_MULTI_WRITER_ADD;
 
+	if (ext_bkt)
+		hash_params.extra_flag |= RTE_HASH_EXTRA_FLAGS_EXT_TABLE;
+
 	hash_params.name = "tests";
 
 	handle = rte_hash_create(&hash_params);
@@ -452,7 +566,7 @@ test_rwc_reader(__attribute__((unused)) void *arg)
 	void *temp_a[BULK_LOOKUP_SIZE];
 
 	/* Used to identify keys not inserted in the hash table */
-	pos = rte_zmalloc(NULL, sizeof(uint32_t) * BULK_LOOKUP_SIZE, 0);
+	pos = rte_malloc(NULL, sizeof(uint32_t) * BULK_LOOKUP_SIZE, 0);
 	if (pos == NULL) {
 		printf("RTE_MALLOC failed\n");
 		return -1;
@@ -467,6 +581,9 @@ test_rwc_reader(__attribute__((unused)) void *arg)
 	} else if (read_type & READ_PASS_SHIFT_PATH) {
 		keys = tbl_rwc_test_param.keys_shift_path;
 		read_cnt = tbl_rwc_test_param.count_keys_shift_path;
+	} else if (read_type & READ_PASS_KEY_SHIFTS_EXTBKT) {
+		keys = tbl_rwc_test_param.keys_ext_bkt;
+		read_cnt = tbl_rwc_test_param.count_keys_extbkt;
 	} else {
 		keys = tbl_rwc_test_param.keys_non_shift_path;
 		read_cnt = tbl_rwc_test_param.count_keys_non_shift_path;
@@ -482,7 +599,6 @@ test_rwc_reader(__attribute__((unused)) void *arg)
 				/* Array of  pointer to the list of keys */
 				for (j = 0; j < BULK_LOOKUP_SIZE; j++)
 					temp_a[j] = keys + i + j;
-
 				rte_hash_lookup_bulk(tbl_rwc_test_param.h,
 						   (const void **)
 						   ((uintptr_t)temp_a),
@@ -539,22 +655,25 @@ test_rwc_reader(__attribute__((unused)) void *arg)
 }
 
 static int
-write_keys(uint8_t key_shift)
+write_keys(uint8_t write_type)
 {
 	uint32_t i;
 	int ret;
 	uint32_t key_cnt;
 	uint32_t *keys;
-	if (key_shift) {
+	if (write_type == WRITE_KEY_SHIFT) {
 		key_cnt = tbl_rwc_test_param.count_keys_ks;
 		keys = tbl_rwc_test_param.keys_ks;
-	} else {
+	} else if (write_type == WRITE_NO_KEY_SHIFT) {
 		key_cnt = tbl_rwc_test_param.count_keys_no_ks;
 		keys = tbl_rwc_test_param.keys_no_ks;
+	} else if (write_type == WRITE_EXT_BKT) {
+		key_cnt = tbl_rwc_test_param.count_keys_extbkt;
+		keys = tbl_rwc_test_param.keys_ext_bkt;
 	}
 	for (i = 0; i < key_cnt; i++) {
 		ret = rte_hash_add_key(tbl_rwc_test_param.h, keys + i);
-		if (!key_shift && ret < 0) {
+		if ((write_type == WRITE_NO_KEY_SHIFT) && ret < 0) {
 			printf("writer failed %"PRIu32"\n", i);
 			return -1;
 		}
@@ -581,18 +700,18 @@ test_rwc_multi_writer(__attribute__((unused)) void *arg)
  */
 static int
 test_hash_add_no_ks_lookup_hit(struct rwc_perf *rwc_perf_results, int rwc_lf,
-				int htm)
+				int htm, int ext_bkt)
 {
 	unsigned int n, m;
 	uint64_t i;
 	int use_jhash = 0;
-	uint8_t key_shift = 0;
+	uint8_t write_type = WRITE_NO_KEY_SHIFT;
 	uint8_t read_type = READ_PASS_NO_KEY_SHIFTS;
 
 	rte_atomic64_init(&greads);
 	rte_atomic64_init(&gread_cycles);
 
-	if (init_params(rwc_lf, use_jhash, htm) != 0)
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
 		goto err;
 	printf("\nTest: Hash add - no key-shifts, read - hit\n");
 	for (m = 0; m < 2; m++) {
@@ -612,7 +731,7 @@ test_hash_add_no_ks_lookup_hit(struct rwc_perf *rwc_perf_results, int rwc_lf,
 
 			rte_hash_reset(tbl_rwc_test_param.h);
 			writer_done = 0;
-			if (write_keys(key_shift) < 0)
+			if (write_keys(write_type) < 0)
 				goto err;
 			writer_done = 1;
 			for (i = 1; i <= rwc_core_cnt[n]; i++)
@@ -650,19 +769,19 @@ test_hash_add_no_ks_lookup_hit(struct rwc_perf *rwc_perf_results, int rwc_lf,
  */
 static int
 test_hash_add_no_ks_lookup_miss(struct rwc_perf *rwc_perf_results, int rwc_lf,
-				int htm)
+				int htm, int ext_bkt)
 {
 	unsigned int n, m;
 	uint64_t i;
 	int use_jhash = 0;
-	uint8_t key_shift = 0;
+	uint8_t write_type = WRITE_NO_KEY_SHIFT;
 	uint8_t read_type = READ_FAIL;
 	int ret;
 
 	rte_atomic64_init(&greads);
 	rte_atomic64_init(&gread_cycles);
 
-	if (init_params(rwc_lf, use_jhash, htm) != 0)
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
 		goto err;
 	printf("\nTest: Hash add - no key-shifts, Hash lookup - miss\n");
 	for (m = 0; m < 2; m++) {
@@ -687,7 +806,7 @@ test_hash_add_no_ks_lookup_miss(struct rwc_perf *rwc_perf_results, int rwc_lf,
 				rte_eal_remote_launch(test_rwc_reader,
 						(void *)(uintptr_t)read_type,
 							enabled_core_ids[i]);
-			ret = write_keys(key_shift);
+			ret = write_keys(write_type);
 			writer_done = 1;
 			rte_eal_mp_wait_lcore();
 
@@ -722,19 +841,19 @@ test_hash_add_no_ks_lookup_miss(struct rwc_perf *rwc_perf_results, int rwc_lf,
  */
 static int
 test_hash_add_ks_lookup_hit_non_sp(struct rwc_perf *rwc_perf_results,
-				    int rwc_lf, int htm)
+				    int rwc_lf, int htm, int ext_bkt)
 {
 	unsigned int n, m;
 	uint64_t i;
 	int use_jhash = 0;
 	int ret;
-	uint8_t key_shift;
+	uint8_t write_type;
 	uint8_t read_type = READ_PASS_NON_SHIFT_PATH;
 
 	rte_atomic64_init(&greads);
 	rte_atomic64_init(&gread_cycles);
 
-	if (init_params(rwc_lf, use_jhash, htm) != 0)
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
 		goto err;
 	printf("\nTest: Hash add - key shift, Hash lookup - hit"
 	       " (non-shift-path)\n");
@@ -755,15 +874,15 @@ test_hash_add_ks_lookup_hit_non_sp(struct rwc_perf *rwc_perf_results,
 
 			rte_hash_reset(tbl_rwc_test_param.h);
 			writer_done = 0;
-			key_shift = 0;
-			if (write_keys(key_shift) < 0)
+			write_type = WRITE_NO_KEY_SHIFT;
+			if (write_keys(write_type) < 0)
 				goto err;
 			for (i = 1; i <= rwc_core_cnt[n]; i++)
 				rte_eal_remote_launch(test_rwc_reader,
 						(void *)(uintptr_t)read_type,
 							enabled_core_ids[i]);
-			key_shift = 1;
-			ret = write_keys(key_shift);
+			write_type = WRITE_KEY_SHIFT;
+			ret = write_keys(write_type);
 			writer_done = 1;
 			rte_eal_mp_wait_lcore();
 
@@ -798,19 +917,19 @@ test_hash_add_ks_lookup_hit_non_sp(struct rwc_perf *rwc_perf_results,
  */
 static int
 test_hash_add_ks_lookup_hit_sp(struct rwc_perf *rwc_perf_results, int rwc_lf,
-				int htm)
+				int htm, int ext_bkt)
 {
 	unsigned int n, m;
 	uint64_t i;
 	int use_jhash = 0;
 	int ret;
-	uint8_t key_shift;
+	uint8_t write_type;
 	uint8_t read_type = READ_PASS_SHIFT_PATH;
 
 	rte_atomic64_init(&greads);
 	rte_atomic64_init(&gread_cycles);
 
-	if (init_params(rwc_lf, use_jhash, htm) != 0)
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
 		goto err;
 	printf("\nTest: Hash add - key shift, Hash lookup - hit (shift-path)"
 	       "\n");
@@ -831,15 +950,15 @@ test_hash_add_ks_lookup_hit_sp(struct rwc_perf *rwc_perf_results, int rwc_lf,
 
 			rte_hash_reset(tbl_rwc_test_param.h);
 			writer_done = 0;
-			key_shift = 0;
-			if (write_keys(key_shift) < 0)
+			write_type = WRITE_NO_KEY_SHIFT;
+			if (write_keys(write_type) < 0)
 				goto err;
 			for (i = 1; i <= rwc_core_cnt[n]; i++)
 				rte_eal_remote_launch(test_rwc_reader,
 						(void *)(uintptr_t)read_type,
 						enabled_core_ids[i]);
-			key_shift = 1;
-			ret = write_keys(key_shift);
+			write_type = WRITE_KEY_SHIFT;
+			ret = write_keys(write_type);
 			writer_done = 1;
 			rte_eal_mp_wait_lcore();
 
@@ -874,19 +993,19 @@ test_hash_add_ks_lookup_hit_sp(struct rwc_perf *rwc_perf_results, int rwc_lf,
  */
 static int
 test_hash_add_ks_lookup_miss(struct rwc_perf *rwc_perf_results, int rwc_lf, int
-			     htm)
+			     htm, int ext_bkt)
 {
 	unsigned int n, m;
 	uint64_t i;
 	int use_jhash = 0;
 	int ret;
-	uint8_t key_shift;
+	uint8_t write_type;
 	uint8_t read_type = READ_FAIL;
 
 	rte_atomic64_init(&greads);
 	rte_atomic64_init(&gread_cycles);
 
-	if (init_params(rwc_lf, use_jhash, htm) != 0)
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
 		goto err;
 	printf("\nTest: Hash add - key shift, Hash lookup - miss\n");
 	for (m = 0; m < 2; m++) {
@@ -906,15 +1025,15 @@ test_hash_add_ks_lookup_miss(struct rwc_perf *rwc_perf_results, int rwc_lf, int
 
 			rte_hash_reset(tbl_rwc_test_param.h);
 			writer_done = 0;
-			key_shift = 0;
-			if (write_keys(key_shift) < 0)
+			write_type = WRITE_NO_KEY_SHIFT;
+			if (write_keys(write_type) < 0)
 				goto err;
 			for (i = 1; i <= rwc_core_cnt[n]; i++)
 				rte_eal_remote_launch(test_rwc_reader,
 						(void *)(uintptr_t)read_type,
 							enabled_core_ids[i]);
-			key_shift = 1;
-			ret = write_keys(key_shift);
+			write_type = WRITE_KEY_SHIFT;
+			ret = write_keys(write_type);
 			writer_done = 1;
 			rte_eal_mp_wait_lcore();
 
@@ -949,18 +1068,18 @@ test_hash_add_ks_lookup_miss(struct rwc_perf *rwc_perf_results, int rwc_lf, int
  */
 static int
 test_hash_multi_add_lookup(struct rwc_perf *rwc_perf_results, int rwc_lf,
-			   int htm)
+			   int htm, int ext_bkt)
 {
 	unsigned int n, m, k;
 	uint64_t i;
 	int use_jhash = 0;
-	uint8_t key_shift;
+	uint8_t write_type;
 	uint8_t read_type = READ_PASS_SHIFT_PATH;
 
 	rte_atomic64_init(&greads);
 	rte_atomic64_init(&gread_cycles);
 
-	if (init_params(rwc_lf, use_jhash, htm) != 0)
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
 		goto err;
 	printf("\nTest: Multi-add-lookup\n");
 	uint8_t pos_core;
@@ -991,8 +1110,8 @@ test_hash_multi_add_lookup(struct rwc_perf *rwc_perf_results, int rwc_lf,
 				writer_done = 0;
 				for (i = 0; i < 4; i++)
 					multi_writer_done[i] = 0;
-				key_shift = 0;
-				if (write_keys(key_shift) < 0)
+				write_type = WRITE_NO_KEY_SHIFT;
+				if (write_keys(write_type) < 0)
 					goto err;
 
 				/* Launch reader(s) */
@@ -1000,7 +1119,7 @@ test_hash_multi_add_lookup(struct rwc_perf *rwc_perf_results, int rwc_lf,
 					rte_eal_remote_launch(test_rwc_reader,
 						(void *)(uintptr_t)read_type,
 						enabled_core_ids[i]);
-				key_shift = 1;
+				write_type = WRITE_KEY_SHIFT;
 				pos_core = 0;
 
 				/* Launch writers */
@@ -1045,6 +1164,88 @@ test_hash_multi_add_lookup(struct rwc_perf *rwc_perf_results, int rwc_lf,
 	return -1;
 }
 
+/*
+ * Test lookup perf:
+ * Reader(s) lookup keys present in the extendable bkt.
+ */
+static int
+test_hash_add_ks_lookup_hit_extbkt(struct rwc_perf *rwc_perf_results,
+				int rwc_lf, int htm, int ext_bkt)
+{
+	unsigned int n, m;
+	uint64_t i;
+	int use_jhash = 0;
+	uint8_t write_type;
+	uint8_t read_type = READ_PASS_KEY_SHIFTS_EXTBKT;
+
+	rte_atomic64_init(&greads);
+	rte_atomic64_init(&gread_cycles);
+
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
+		goto err;
+	printf("\nTest: Hash add - key-shifts, read - hit (ext_bkt)\n");
+	for (m = 0; m < 2; m++) {
+		if (m == 1) {
+			printf("\n** With bulk-lookup **\n");
+			read_type |= BULK_LOOKUP;
+		}
+		for (n = 0; n < NUM_TEST; n++) {
+			unsigned int tot_lcore = rte_lcore_count();
+			if (tot_lcore < rwc_core_cnt[n] + 1)
+				goto finish;
+
+			printf("\nNumber of readers: %u\n", rwc_core_cnt[n]);
+
+			rte_atomic64_clear(&greads);
+			rte_atomic64_clear(&gread_cycles);
+
+			rte_hash_reset(tbl_rwc_test_param.h);
+			write_type = WRITE_NO_KEY_SHIFT;
+			if (write_keys(write_type) < 0)
+				goto err;
+			write_type = WRITE_KEY_SHIFT;
+			if (write_keys(write_type) < 0)
+				goto err;
+			writer_done = 0;
+			for (i = 1; i <= rwc_core_cnt[n]; i++)
+				rte_eal_remote_launch(test_rwc_reader,
+						(void *)(uintptr_t)read_type,
+							enabled_core_ids[i]);
+			for (i = 0; i < tbl_rwc_test_param.count_keys_ks_extbkt;
+			     i++) {
+				if (rte_hash_del_key(tbl_rwc_test_param.h,
+					tbl_rwc_test_param.keys_ks_extbkt + i)
+							< 0) {
+					printf("Delete Failed: %u\n",
+					tbl_rwc_test_param.keys_ks_extbkt[i]);
+					goto err;
+				}
+			}
+			writer_done = 1;
+			rte_eal_mp_wait_lcore();
+
+			for (i = 1; i <= rwc_core_cnt[n]; i++)
+				if (lcore_config[i].ret < 0)
+					goto err;
+
+			unsigned long long cycles_per_lookup =
+				rte_atomic64_read(&gread_cycles) /
+				rte_atomic64_read(&greads);
+			rwc_perf_results->w_ks_r_hit_extbkt[m][n]
+						= cycles_per_lookup;
+			printf("Cycles per lookup: %llu\n", cycles_per_lookup);
+		}
+	}
+
+finish:
+	rte_hash_free(tbl_rwc_test_param.h);
+	return 0;
+
+err:
+	rte_hash_free(tbl_rwc_test_param.h);
+	return -1;
+}
+
 static int
 test_hash_readwrite_lf_main(void)
 {
@@ -1057,6 +1258,7 @@ test_hash_readwrite_lf_main(void)
 	int rwc_lf = 0;
 	int htm;
 	int use_jhash = 0;
+	int ext_bkt = 0;
 	if (rte_lcore_count() == 1) {
 		printf("More than one lcore is required "
 			"to do read write lock-free concurrency test\n");
@@ -1070,7 +1272,7 @@ test_hash_readwrite_lf_main(void)
 	else
 		htm = 0;
 
-	if (init_params(rwc_lf, use_jhash, htm) != 0)
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
 		return -1;
 	if (generate_keys() != 0)
 		return -1;
@@ -1079,25 +1281,29 @@ test_hash_readwrite_lf_main(void)
 
 	if (RTE_HASH_EXTRA_FLAGS_RW_CONCURRENCY_LF) {
 		rwc_lf = 1;
+		ext_bkt = 1;
 		printf("Test lookup with read-write concurrency lock free support"
 		       " enabled\n");
 		if (test_hash_add_no_ks_lookup_hit(&rwc_lf_results, rwc_lf,
-							htm) < 0)
+							htm, ext_bkt) < 0)
 			return -1;
 		if (test_hash_add_no_ks_lookup_miss(&rwc_lf_results, rwc_lf,
-							htm) < 0)
+							htm, ext_bkt) < 0)
 			return -1;
 		if (test_hash_add_ks_lookup_hit_non_sp(&rwc_lf_results, rwc_lf,
-							htm) < 0)
+							htm, ext_bkt) < 0)
 			return -1;
 		if (test_hash_add_ks_lookup_hit_sp(&rwc_lf_results, rwc_lf,
-							htm) < 0)
+							htm, ext_bkt) < 0)
 			return -1;
-		if (test_hash_add_ks_lookup_miss(&rwc_lf_results, rwc_lf, htm)
-							< 0)
+		if (test_hash_add_ks_lookup_miss(&rwc_lf_results, rwc_lf, htm,
+						 ext_bkt) < 0)
 			return -1;
-		if (test_hash_multi_add_lookup(&rwc_lf_results, rwc_lf, htm)
-							< 0)
+		if (test_hash_multi_add_lookup(&rwc_lf_results, rwc_lf, htm,
+					       ext_bkt) < 0)
+			return -1;
+		if (test_hash_add_ks_lookup_hit_extbkt(&rwc_lf_results, rwc_lf,
+							htm, ext_bkt) < 0)
 			return -1;
 	}
 	printf("\nTest lookup with read-write concurrency lock free support"
@@ -1112,21 +1318,26 @@ test_hash_readwrite_lf_main(void)
 		}
 	} else
 		printf("With HTM Enabled\n");
-	if (test_hash_add_no_ks_lookup_hit(&rwc_non_lf_results, rwc_lf, htm)
-						< 0)
+	if (test_hash_add_no_ks_lookup_hit(&rwc_non_lf_results, rwc_lf, htm,
+					   ext_bkt) < 0)
 		return -1;
-	if (test_hash_add_no_ks_lookup_miss(&rwc_non_lf_results, rwc_lf, htm)
-						< 0)
+	if (test_hash_add_no_ks_lookup_miss(&rwc_non_lf_results, rwc_lf, htm,
+						ext_bkt) < 0)
 		return -1;
 	if (test_hash_add_ks_lookup_hit_non_sp(&rwc_non_lf_results, rwc_lf,
-						htm) < 0)
+						htm, ext_bkt) < 0)
+		return -1;
+	if (test_hash_add_ks_lookup_hit_sp(&rwc_non_lf_results, rwc_lf, htm,
+						ext_bkt) < 0)
 		return -1;
-	if (test_hash_add_ks_lookup_hit_sp(&rwc_non_lf_results, rwc_lf, htm)
-						< 0)
+	if (test_hash_add_ks_lookup_miss(&rwc_non_lf_results, rwc_lf, htm,
+					 ext_bkt) < 0)
 		return -1;
-	if (test_hash_add_ks_lookup_miss(&rwc_non_lf_results, rwc_lf, htm) < 0)
+	if (test_hash_multi_add_lookup(&rwc_non_lf_results, rwc_lf, htm,
+							ext_bkt) < 0)
 		return -1;
-	if (test_hash_multi_add_lookup(&rwc_non_lf_results, rwc_lf, htm) < 0)
+	if (test_hash_add_ks_lookup_hit_extbkt(&rwc_non_lf_results, rwc_lf,
+						htm, ext_bkt) < 0)
 		return -1;
 results:
 	printf("\n\t\t\t\t\t\t********** Results summary **********\n\n");
@@ -1158,8 +1369,11 @@ test_hash_readwrite_lf_main(void)
 			       "(shift-path)\t\t%u\n\t\t\t\t\t\t\t\t",
 			       rwc_lf_results.w_ks_r_hit_sp[j][i]);
 			printf("Hash add - key-shifts, Hash lookup miss\t\t\t\t"
-				"%u\n\n\t\t\t\t",
+				"%u\n\t\t\t\t\t\t\t\t",
 				rwc_lf_results.w_ks_r_miss[j][i]);
+			printf("Hash add - key-shifts, Hash lookup hit (ext_bkt)\t\t"
+				"%u\n\n\t\t\t\t",
+				rwc_lf_results.w_ks_r_hit_extbkt[j][i]);
 
 			printf("Disabled\t");
 			if (htm)
@@ -1179,7 +1393,11 @@ test_hash_readwrite_lf_main(void)
 			       "(shift-path)\t\t%u\n\t\t\t\t\t\t\t\t",
 			       rwc_non_lf_results.w_ks_r_hit_sp[j][i]);
 			printf("Hash add - key-shifts, Hash lookup miss\t\t\t\t"
-			       "%u\n", rwc_non_lf_results.w_ks_r_miss[j][i]);
+			       "%u\n\t\t\t\t\t\t\t\t",
+			       rwc_non_lf_results.w_ks_r_miss[j][i]);
+			printf("Hash add - key-shifts, Hash lookup hit (ext_bkt)\t\t"
+				"%u\n",
+				rwc_non_lf_results.w_ks_r_hit_extbkt[j][i]);
 
 			printf("_______\t\t_______\t\t_________\t___\t\t"
 			       "_________\t\t\t\t\t\t_________________\n");
-- 
2.17.1

[dpdk-dev] [PATCH v4 2/2] test/hash: lock-free rw concurrency test ext bkt

[Dharmik Thakkar]

Add unit test to check for hash lookup and bulk-lookup perf for
extendable bucket feature.
It is tested with both lock-free enabled and lock-free disabled case.

Test includes:

- hash lookup on keys in ext bkt
- hash delete causing key-shifts of keys from ext bkt to secondary bkt

Suggested-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
Signed-off-by: Dharmik Thakkar <dharmik.thakkar@arm.com>
Acked-by: Yipeng Wang <yipeng1.wang@intel.com>
---
v4:
- Add Acked-by tag.
---
v3:
- Update commit message (Yipeng)
---
 app/test/test_hash_readwrite_lf.c | 350 ++++++++++++++++++++++++------
 1 file changed, 284 insertions(+), 66 deletions(-)

diff --git a/app/test/test_hash_readwrite_lf.c b/app/test/test_hash_readwrite_lf.c
index cbfd9322696b..ddd8d7aa6a7d 100644
--- a/app/test/test_hash_readwrite_lf.c
+++ b/app/test/test_hash_readwrite_lf.c
@@ -41,6 +41,12 @@
 #define READ_PASS_SHIFT_PATH 4
 #define READ_PASS_NON_SHIFT_PATH 8
 #define BULK_LOOKUP 16
+#define READ_PASS_KEY_SHIFTS_EXTBKT 32
+
+#define WRITE_NO_KEY_SHIFT 0
+#define WRITE_KEY_SHIFT 1
+#define WRITE_EXT_BKT 2
+
 #define NUM_TEST 3
 unsigned int rwc_core_cnt[NUM_TEST] = {1, 2, 4};
 
@@ -51,6 +57,7 @@ struct rwc_perf {
 	uint32_t w_ks_r_hit_sp[2][NUM_TEST];
 	uint32_t w_ks_r_miss[2][NUM_TEST];
 	uint32_t multi_rw[NUM_TEST - 1][2][NUM_TEST];
+	uint32_t w_ks_r_hit_extbkt[2][NUM_TEST];
 };
 
 static struct rwc_perf rwc_lf_results, rwc_non_lf_results;
@@ -62,11 +69,15 @@ struct {
 	uint32_t *keys_absent;
 	uint32_t *keys_shift_path;
 	uint32_t *keys_non_shift_path;
+	uint32_t *keys_ext_bkt;
+	uint32_t *keys_ks_extbkt;
 	uint32_t count_keys_no_ks;
 	uint32_t count_keys_ks;
 	uint32_t count_keys_absent;
 	uint32_t count_keys_shift_path;
 	uint32_t count_keys_non_shift_path;
+	uint32_t count_keys_extbkt;
+	uint32_t count_keys_ks_extbkt;
 	uint32_t single_insert;
 	struct rte_hash *h;
 } tbl_rwc_test_param;
@@ -81,6 +92,35 @@ uint16_t enabled_core_ids[RTE_MAX_LCORE];
 
 uint8_t *scanned_bkts;
 
+static inline uint16_t
+get_short_sig(const hash_sig_t hash)
+{
+	return hash >> 16;
+}
+
+static inline uint32_t
+get_prim_bucket_index(__attribute__((unused)) const struct rte_hash *h,
+		      const hash_sig_t hash)
+{
+	uint32_t num_buckets;
+	uint32_t bucket_bitmask;
+	num_buckets  = rte_align32pow2(TOTAL_ENTRY) / 8;
+	bucket_bitmask = num_buckets - 1;
+	return hash & bucket_bitmask;
+}
+
+static inline uint32_t
+get_alt_bucket_index(__attribute__((unused)) const struct rte_hash *h,
+			uint32_t cur_bkt_idx, uint16_t sig)
+{
+	uint32_t num_buckets;
+	uint32_t bucket_bitmask;
+	num_buckets  = rte_align32pow2(TOTAL_ENTRY) / 8;
+	bucket_bitmask = num_buckets - 1;
+	return (cur_bkt_idx ^ sig) & bucket_bitmask;
+}
+
+
 static inline int
 get_enabled_cores_list(void)
 {
@@ -168,9 +208,12 @@ generate_keys(void)
 	uint32_t *keys_ks = NULL;
 	uint32_t *keys_absent = NULL;
 	uint32_t *keys_non_shift_path = NULL;
+	uint32_t *keys_ext_bkt = NULL;
+	uint32_t *keys_ks_extbkt = NULL;
 	uint32_t *found = NULL;
 	uint32_t count_keys_no_ks = 0;
 	uint32_t count_keys_ks = 0;
+	uint32_t count_keys_extbkt = 0;
 	uint32_t i;
 
 	/*
@@ -251,14 +294,32 @@ generate_keys(void)
 		goto err;
 	}
 
+	/*
+	 * This consist of keys which will be stored in extended buckets
+	 */
+	keys_ext_bkt = rte_malloc(NULL, sizeof(uint32_t) * TOTAL_INSERT, 0);
+	if (keys_ext_bkt == NULL) {
+		printf("RTE_MALLOC failed\n");
+		goto err;
+	}
+
+	/*
+	 * This consist of keys which when deleted causes shifting of keys
+	 * in extended buckets to respective secondary buckets
+	 */
+	keys_ks_extbkt = rte_malloc(NULL, sizeof(uint32_t) * TOTAL_INSERT, 0);
+	if (keys_ks_extbkt == NULL) {
+		printf("RTE_MALLOC failed\n");
+		goto err;
+	}
 
 	hash_sig_t sig;
 	uint32_t prim_bucket_idx;
-	int ret;
+	uint32_t sec_bucket_idx;
+	uint16_t short_sig;
 	uint32_t num_buckets;
-	uint32_t bucket_bitmask;
 	num_buckets  = rte_align32pow2(TOTAL_ENTRY) / 8;
-	bucket_bitmask = num_buckets - 1;
+	int ret;
 
 	/*
 	 * Used to mark bkts in which at least one key was shifted to its
@@ -275,6 +336,8 @@ generate_keys(void)
 	tbl_rwc_test_param.keys_ks = keys_ks;
 	tbl_rwc_test_param.keys_absent = keys_absent;
 	tbl_rwc_test_param.keys_non_shift_path = keys_non_shift_path;
+	tbl_rwc_test_param.keys_ext_bkt = keys_ext_bkt;
+	tbl_rwc_test_param.keys_ks_extbkt = keys_ks_extbkt;
 	/* Generate keys by adding previous two keys, neglect overflow */
 	printf("Generating keys...\n");
 	keys[0] = 0;
@@ -287,7 +350,8 @@ generate_keys(void)
 		/* Check if primary bucket has space.*/
 		sig = rte_hash_hash(tbl_rwc_test_param.h,
 					tbl_rwc_test_param.keys+i);
-		prim_bucket_idx = sig & bucket_bitmask;
+		prim_bucket_idx = get_prim_bucket_index(tbl_rwc_test_param.h,
+							sig);
 		ret = check_bucket(prim_bucket_idx, keys[i]);
 		if (ret < 0) {
 			/*
@@ -368,6 +432,47 @@ generate_keys(void)
 	tbl_rwc_test_param.count_keys_absent = count_keys_absent;
 	tbl_rwc_test_param.count_keys_non_shift_path = count;
 
+	memset(scanned_bkts, 0, num_buckets);
+	count = 0;
+	/* Find keys that will be in extended buckets */
+	for (i = 0; i < count_keys_ks; i++) {
+		ret = rte_hash_add_key(tbl_rwc_test_param.h, keys_ks + i);
+		if (ret < 0) {
+			/* Key will be added to ext bkt */
+			keys_ext_bkt[count_keys_extbkt++] = keys_ks[i];
+			/* Sec bkt to be added to keys_ks_extbkt */
+			sig = rte_hash_hash(tbl_rwc_test_param.h,
+					tbl_rwc_test_param.keys_ks + i);
+			prim_bucket_idx = get_prim_bucket_index(
+						tbl_rwc_test_param.h, sig);
+			short_sig = get_short_sig(sig);
+			sec_bucket_idx = get_alt_bucket_index(
+						tbl_rwc_test_param.h,
+						prim_bucket_idx, short_sig);
+			if (scanned_bkts[sec_bucket_idx] == 0)
+				scanned_bkts[sec_bucket_idx] = 1;
+		}
+	}
+
+	/* Find keys that will shift keys in ext bucket*/
+	for (i = 0; i < num_buckets; i++) {
+		if (scanned_bkts[i] == 1) {
+			iter = i * 8;
+			while (rte_hash_iterate(tbl_rwc_test_param.h,
+				&next_key, &next_data, &iter) >= 0) {
+				/* Check if key belongs to the current bucket */
+				if (i >= (iter-1)/8)
+					keys_ks_extbkt[count++]
+						= *(const uint32_t *)next_key;
+				else
+					break;
+			}
+		}
+	}
+
+	tbl_rwc_test_param.count_keys_ks_extbkt = count;
+	tbl_rwc_test_param.count_keys_extbkt = count_keys_extbkt;
+
 	printf("\nCount of keys NOT causing shifting of existing keys to "
 	"alternate location: %d\n", tbl_rwc_test_param.count_keys_no_ks);
 	printf("\nCount of keys causing shifting of existing keys to alternate "
@@ -378,6 +483,10 @@ generate_keys(void)
 	       tbl_rwc_test_param.count_keys_shift_path);
 	printf("Count of keys not likely to be on the shift path: %d\n\n",
 	       tbl_rwc_test_param.count_keys_non_shift_path);
+	printf("Count of keys in extended buckets: %d\n\n",
+	       tbl_rwc_test_param.count_keys_extbkt);
+	printf("Count of keys shifting keys in ext buckets: %d\n\n",
+	       tbl_rwc_test_param.count_keys_ks_extbkt);
 
 	rte_free(found);
 	rte_hash_free(tbl_rwc_test_param.h);
@@ -390,12 +499,14 @@ generate_keys(void)
 	rte_free(keys_absent);
 	rte_free(found);
 	rte_free(tbl_rwc_test_param.keys_shift_path);
+	rte_free(keys_ext_bkt);
+	rte_free(keys_ks_extbkt);
 	rte_free(scanned_bkts);
 	return -1;
 }
 
 static int
-init_params(int rwc_lf, int use_jhash, int htm)
+init_params(int rwc_lf, int use_jhash, int htm, int ext_bkt)
 {
 	struct rte_hash *handle;
 
@@ -425,6 +536,9 @@ init_params(int rwc_lf, int use_jhash, int htm)
 			RTE_HASH_EXTRA_FLAGS_RW_CONCURRENCY |
 			RTE_HASH_EXTRA_FLAGS_MULTI_WRITER_ADD;
 
+	if (ext_bkt)
+		hash_params.extra_flag |= RTE_HASH_EXTRA_FLAGS_EXT_TABLE;
+
 	hash_params.name = "tests";
 
 	handle = rte_hash_create(&hash_params);
@@ -452,7 +566,7 @@ test_rwc_reader(__attribute__((unused)) void *arg)
 	void *temp_a[BULK_LOOKUP_SIZE];
 
 	/* Used to identify keys not inserted in the hash table */
-	pos = rte_zmalloc(NULL, sizeof(uint32_t) * BULK_LOOKUP_SIZE, 0);
+	pos = rte_malloc(NULL, sizeof(uint32_t) * BULK_LOOKUP_SIZE, 0);
 	if (pos == NULL) {
 		printf("RTE_MALLOC failed\n");
 		return -1;
@@ -467,6 +581,9 @@ test_rwc_reader(__attribute__((unused)) void *arg)
 	} else if (read_type & READ_PASS_SHIFT_PATH) {
 		keys = tbl_rwc_test_param.keys_shift_path;
 		read_cnt = tbl_rwc_test_param.count_keys_shift_path;
+	} else if (read_type & READ_PASS_KEY_SHIFTS_EXTBKT) {
+		keys = tbl_rwc_test_param.keys_ext_bkt;
+		read_cnt = tbl_rwc_test_param.count_keys_extbkt;
 	} else {
 		keys = tbl_rwc_test_param.keys_non_shift_path;
 		read_cnt = tbl_rwc_test_param.count_keys_non_shift_path;
@@ -482,7 +599,6 @@ test_rwc_reader(__attribute__((unused)) void *arg)
 				/* Array of  pointer to the list of keys */
 				for (j = 0; j < BULK_LOOKUP_SIZE; j++)
 					temp_a[j] = keys + i + j;
-
 				rte_hash_lookup_bulk(tbl_rwc_test_param.h,
 						   (const void **)
 						   ((uintptr_t)temp_a),
@@ -539,22 +655,25 @@ test_rwc_reader(__attribute__((unused)) void *arg)
 }
 
 static int
-write_keys(uint8_t key_shift)
+write_keys(uint8_t write_type)
 {
 	uint32_t i;
 	int ret;
 	uint32_t key_cnt;
 	uint32_t *keys;
-	if (key_shift) {
+	if (write_type == WRITE_KEY_SHIFT) {
 		key_cnt = tbl_rwc_test_param.count_keys_ks;
 		keys = tbl_rwc_test_param.keys_ks;
-	} else {
+	} else if (write_type == WRITE_NO_KEY_SHIFT) {
 		key_cnt = tbl_rwc_test_param.count_keys_no_ks;
 		keys = tbl_rwc_test_param.keys_no_ks;
+	} else if (write_type == WRITE_EXT_BKT) {
+		key_cnt = tbl_rwc_test_param.count_keys_extbkt;
+		keys = tbl_rwc_test_param.keys_ext_bkt;
 	}
 	for (i = 0; i < key_cnt; i++) {
 		ret = rte_hash_add_key(tbl_rwc_test_param.h, keys + i);
-		if (!key_shift && ret < 0) {
+		if ((write_type == WRITE_NO_KEY_SHIFT) && ret < 0) {
 			printf("writer failed %"PRIu32"\n", i);
 			return -1;
 		}
@@ -581,18 +700,18 @@ test_rwc_multi_writer(__attribute__((unused)) void *arg)
  */
 static int
 test_hash_add_no_ks_lookup_hit(struct rwc_perf *rwc_perf_results, int rwc_lf,
-				int htm)
+				int htm, int ext_bkt)
 {
 	unsigned int n, m;
 	uint64_t i;
 	int use_jhash = 0;
-	uint8_t key_shift = 0;
+	uint8_t write_type = WRITE_NO_KEY_SHIFT;
 	uint8_t read_type = READ_PASS_NO_KEY_SHIFTS;
 
 	rte_atomic64_init(&greads);
 	rte_atomic64_init(&gread_cycles);
 
-	if (init_params(rwc_lf, use_jhash, htm) != 0)
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
 		goto err;
 	printf("\nTest: Hash add - no key-shifts, read - hit\n");
 	for (m = 0; m < 2; m++) {
@@ -612,7 +731,7 @@ test_hash_add_no_ks_lookup_hit(struct rwc_perf *rwc_perf_results, int rwc_lf,
 
 			rte_hash_reset(tbl_rwc_test_param.h);
 			writer_done = 0;
-			if (write_keys(key_shift) < 0)
+			if (write_keys(write_type) < 0)
 				goto err;
 			writer_done = 1;
 			for (i = 1; i <= rwc_core_cnt[n]; i++)
@@ -650,19 +769,19 @@ test_hash_add_no_ks_lookup_hit(struct rwc_perf *rwc_perf_results, int rwc_lf,
  */
 static int
 test_hash_add_no_ks_lookup_miss(struct rwc_perf *rwc_perf_results, int rwc_lf,
-				int htm)
+				int htm, int ext_bkt)
 {
 	unsigned int n, m;
 	uint64_t i;
 	int use_jhash = 0;
-	uint8_t key_shift = 0;
+	uint8_t write_type = WRITE_NO_KEY_SHIFT;
 	uint8_t read_type = READ_FAIL;
 	int ret;
 
 	rte_atomic64_init(&greads);
 	rte_atomic64_init(&gread_cycles);
 
-	if (init_params(rwc_lf, use_jhash, htm) != 0)
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
 		goto err;
 	printf("\nTest: Hash add - no key-shifts, Hash lookup - miss\n");
 	for (m = 0; m < 2; m++) {
@@ -687,7 +806,7 @@ test_hash_add_no_ks_lookup_miss(struct rwc_perf *rwc_perf_results, int rwc_lf,
 				rte_eal_remote_launch(test_rwc_reader,
 						(void *)(uintptr_t)read_type,
 							enabled_core_ids[i]);
-			ret = write_keys(key_shift);
+			ret = write_keys(write_type);
 			writer_done = 1;
 			rte_eal_mp_wait_lcore();
 
@@ -722,19 +841,19 @@ test_hash_add_no_ks_lookup_miss(struct rwc_perf *rwc_perf_results, int rwc_lf,
  */
 static int
 test_hash_add_ks_lookup_hit_non_sp(struct rwc_perf *rwc_perf_results,
-				    int rwc_lf, int htm)
+				    int rwc_lf, int htm, int ext_bkt)
 {
 	unsigned int n, m;
 	uint64_t i;
 	int use_jhash = 0;
 	int ret;
-	uint8_t key_shift;
+	uint8_t write_type;
 	uint8_t read_type = READ_PASS_NON_SHIFT_PATH;
 
 	rte_atomic64_init(&greads);
 	rte_atomic64_init(&gread_cycles);
 
-	if (init_params(rwc_lf, use_jhash, htm) != 0)
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
 		goto err;
 	printf("\nTest: Hash add - key shift, Hash lookup - hit"
 	       " (non-shift-path)\n");
@@ -755,15 +874,15 @@ test_hash_add_ks_lookup_hit_non_sp(struct rwc_perf *rwc_perf_results,
 
 			rte_hash_reset(tbl_rwc_test_param.h);
 			writer_done = 0;
-			key_shift = 0;
-			if (write_keys(key_shift) < 0)
+			write_type = WRITE_NO_KEY_SHIFT;
+			if (write_keys(write_type) < 0)
 				goto err;
 			for (i = 1; i <= rwc_core_cnt[n]; i++)
 				rte_eal_remote_launch(test_rwc_reader,
 						(void *)(uintptr_t)read_type,
 							enabled_core_ids[i]);
-			key_shift = 1;
-			ret = write_keys(key_shift);
+			write_type = WRITE_KEY_SHIFT;
+			ret = write_keys(write_type);
 			writer_done = 1;
 			rte_eal_mp_wait_lcore();
 
@@ -798,19 +917,19 @@ test_hash_add_ks_lookup_hit_non_sp(struct rwc_perf *rwc_perf_results,
  */
 static int
 test_hash_add_ks_lookup_hit_sp(struct rwc_perf *rwc_perf_results, int rwc_lf,
-				int htm)
+				int htm, int ext_bkt)
 {
 	unsigned int n, m;
 	uint64_t i;
 	int use_jhash = 0;
 	int ret;
-	uint8_t key_shift;
+	uint8_t write_type;
 	uint8_t read_type = READ_PASS_SHIFT_PATH;
 
 	rte_atomic64_init(&greads);
 	rte_atomic64_init(&gread_cycles);
 
-	if (init_params(rwc_lf, use_jhash, htm) != 0)
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
 		goto err;
 	printf("\nTest: Hash add - key shift, Hash lookup - hit (shift-path)"
 	       "\n");
@@ -831,15 +950,15 @@ test_hash_add_ks_lookup_hit_sp(struct rwc_perf *rwc_perf_results, int rwc_lf,
 
 			rte_hash_reset(tbl_rwc_test_param.h);
 			writer_done = 0;
-			key_shift = 0;
-			if (write_keys(key_shift) < 0)
+			write_type = WRITE_NO_KEY_SHIFT;
+			if (write_keys(write_type) < 0)
 				goto err;
 			for (i = 1; i <= rwc_core_cnt[n]; i++)
 				rte_eal_remote_launch(test_rwc_reader,
 						(void *)(uintptr_t)read_type,
 						enabled_core_ids[i]);
-			key_shift = 1;
-			ret = write_keys(key_shift);
+			write_type = WRITE_KEY_SHIFT;
+			ret = write_keys(write_type);
 			writer_done = 1;
 			rte_eal_mp_wait_lcore();
 
@@ -874,19 +993,19 @@ test_hash_add_ks_lookup_hit_sp(struct rwc_perf *rwc_perf_results, int rwc_lf,
  */
 static int
 test_hash_add_ks_lookup_miss(struct rwc_perf *rwc_perf_results, int rwc_lf, int
-			     htm)
+			     htm, int ext_bkt)
 {
 	unsigned int n, m;
 	uint64_t i;
 	int use_jhash = 0;
 	int ret;
-	uint8_t key_shift;
+	uint8_t write_type;
 	uint8_t read_type = READ_FAIL;
 
 	rte_atomic64_init(&greads);
 	rte_atomic64_init(&gread_cycles);
 
-	if (init_params(rwc_lf, use_jhash, htm) != 0)
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
 		goto err;
 	printf("\nTest: Hash add - key shift, Hash lookup - miss\n");
 	for (m = 0; m < 2; m++) {
@@ -906,15 +1025,15 @@ test_hash_add_ks_lookup_miss(struct rwc_perf *rwc_perf_results, int rwc_lf, int
 
 			rte_hash_reset(tbl_rwc_test_param.h);
 			writer_done = 0;
-			key_shift = 0;
-			if (write_keys(key_shift) < 0)
+			write_type = WRITE_NO_KEY_SHIFT;
+			if (write_keys(write_type) < 0)
 				goto err;
 			for (i = 1; i <= rwc_core_cnt[n]; i++)
 				rte_eal_remote_launch(test_rwc_reader,
 						(void *)(uintptr_t)read_type,
 							enabled_core_ids[i]);
-			key_shift = 1;
-			ret = write_keys(key_shift);
+			write_type = WRITE_KEY_SHIFT;
+			ret = write_keys(write_type);
 			writer_done = 1;
 			rte_eal_mp_wait_lcore();
 
@@ -949,18 +1068,18 @@ test_hash_add_ks_lookup_miss(struct rwc_perf *rwc_perf_results, int rwc_lf, int
  */
 static int
 test_hash_multi_add_lookup(struct rwc_perf *rwc_perf_results, int rwc_lf,
-			   int htm)
+			   int htm, int ext_bkt)
 {
 	unsigned int n, m, k;
 	uint64_t i;
 	int use_jhash = 0;
-	uint8_t key_shift;
+	uint8_t write_type;
 	uint8_t read_type = READ_PASS_SHIFT_PATH;
 
 	rte_atomic64_init(&greads);
 	rte_atomic64_init(&gread_cycles);
 
-	if (init_params(rwc_lf, use_jhash, htm) != 0)
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
 		goto err;
 	printf("\nTest: Multi-add-lookup\n");
 	uint8_t pos_core;
@@ -991,8 +1110,8 @@ test_hash_multi_add_lookup(struct rwc_perf *rwc_perf_results, int rwc_lf,
 				writer_done = 0;
 				for (i = 0; i < 4; i++)
 					multi_writer_done[i] = 0;
-				key_shift = 0;
-				if (write_keys(key_shift) < 0)
+				write_type = WRITE_NO_KEY_SHIFT;
+				if (write_keys(write_type) < 0)
 					goto err;
 
 				/* Launch reader(s) */
@@ -1000,7 +1119,7 @@ test_hash_multi_add_lookup(struct rwc_perf *rwc_perf_results, int rwc_lf,
 					rte_eal_remote_launch(test_rwc_reader,
 						(void *)(uintptr_t)read_type,
 						enabled_core_ids[i]);
-				key_shift = 1;
+				write_type = WRITE_KEY_SHIFT;
 				pos_core = 0;
 
 				/* Launch writers */
@@ -1045,6 +1164,88 @@ test_hash_multi_add_lookup(struct rwc_perf *rwc_perf_results, int rwc_lf,
 	return -1;
 }
 
+/*
+ * Test lookup perf:
+ * Reader(s) lookup keys present in the extendable bkt.
+ */
+static int
+test_hash_add_ks_lookup_hit_extbkt(struct rwc_perf *rwc_perf_results,
+				int rwc_lf, int htm, int ext_bkt)
+{
+	unsigned int n, m;
+	uint64_t i;
+	int use_jhash = 0;
+	uint8_t write_type;
+	uint8_t read_type = READ_PASS_KEY_SHIFTS_EXTBKT;
+
+	rte_atomic64_init(&greads);
+	rte_atomic64_init(&gread_cycles);
+
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
+		goto err;
+	printf("\nTest: Hash add - key-shifts, read - hit (ext_bkt)\n");
+	for (m = 0; m < 2; m++) {
+		if (m == 1) {
+			printf("\n** With bulk-lookup **\n");
+			read_type |= BULK_LOOKUP;
+		}
+		for (n = 0; n < NUM_TEST; n++) {
+			unsigned int tot_lcore = rte_lcore_count();
+			if (tot_lcore < rwc_core_cnt[n] + 1)
+				goto finish;
+
+			printf("\nNumber of readers: %u\n", rwc_core_cnt[n]);
+
+			rte_atomic64_clear(&greads);
+			rte_atomic64_clear(&gread_cycles);
+
+			rte_hash_reset(tbl_rwc_test_param.h);
+			write_type = WRITE_NO_KEY_SHIFT;
+			if (write_keys(write_type) < 0)
+				goto err;
+			write_type = WRITE_KEY_SHIFT;
+			if (write_keys(write_type) < 0)
+				goto err;
+			writer_done = 0;
+			for (i = 1; i <= rwc_core_cnt[n]; i++)
+				rte_eal_remote_launch(test_rwc_reader,
+						(void *)(uintptr_t)read_type,
+							enabled_core_ids[i]);
+			for (i = 0; i < tbl_rwc_test_param.count_keys_ks_extbkt;
+			     i++) {
+				if (rte_hash_del_key(tbl_rwc_test_param.h,
+					tbl_rwc_test_param.keys_ks_extbkt + i)
+							< 0) {
+					printf("Delete Failed: %u\n",
+					tbl_rwc_test_param.keys_ks_extbkt[i]);
+					goto err;
+				}
+			}
+			writer_done = 1;
+			rte_eal_mp_wait_lcore();
+
+			for (i = 1; i <= rwc_core_cnt[n]; i++)
+				if (lcore_config[i].ret < 0)
+					goto err;
+
+			unsigned long long cycles_per_lookup =
+				rte_atomic64_read(&gread_cycles) /
+				rte_atomic64_read(&greads);
+			rwc_perf_results->w_ks_r_hit_extbkt[m][n]
+						= cycles_per_lookup;
+			printf("Cycles per lookup: %llu\n", cycles_per_lookup);
+		}
+	}
+
+finish:
+	rte_hash_free(tbl_rwc_test_param.h);
+	return 0;
+
+err:
+	rte_hash_free(tbl_rwc_test_param.h);
+	return -1;
+}
+
 static int
 test_hash_readwrite_lf_main(void)
 {
@@ -1057,6 +1258,7 @@ test_hash_readwrite_lf_main(void)
 	int rwc_lf = 0;
 	int htm;
 	int use_jhash = 0;
+	int ext_bkt = 0;
 	if (rte_lcore_count() == 1) {
 		printf("More than one lcore is required "
 			"to do read write lock-free concurrency test\n");
@@ -1070,7 +1272,7 @@ test_hash_readwrite_lf_main(void)
 	else
 		htm = 0;
 
-	if (init_params(rwc_lf, use_jhash, htm) != 0)
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
 		return -1;
 	if (generate_keys() != 0)
 		return -1;
@@ -1079,25 +1281,29 @@ test_hash_readwrite_lf_main(void)
 
 	if (RTE_HASH_EXTRA_FLAGS_RW_CONCURRENCY_LF) {
 		rwc_lf = 1;
+		ext_bkt = 1;
 		printf("Test lookup with read-write concurrency lock free support"
 		       " enabled\n");
 		if (test_hash_add_no_ks_lookup_hit(&rwc_lf_results, rwc_lf,
-							htm) < 0)
+							htm, ext_bkt) < 0)
 			return -1;
 		if (test_hash_add_no_ks_lookup_miss(&rwc_lf_results, rwc_lf,
-							htm) < 0)
+							htm, ext_bkt) < 0)
 			return -1;
 		if (test_hash_add_ks_lookup_hit_non_sp(&rwc_lf_results, rwc_lf,
-							htm) < 0)
+							htm, ext_bkt) < 0)
 			return -1;
 		if (test_hash_add_ks_lookup_hit_sp(&rwc_lf_results, rwc_lf,
-							htm) < 0)
+							htm, ext_bkt) < 0)
 			return -1;
-		if (test_hash_add_ks_lookup_miss(&rwc_lf_results, rwc_lf, htm)
-							< 0)
+		if (test_hash_add_ks_lookup_miss(&rwc_lf_results, rwc_lf, htm,
+						 ext_bkt) < 0)
 			return -1;
-		if (test_hash_multi_add_lookup(&rwc_lf_results, rwc_lf, htm)
-							< 0)
+		if (test_hash_multi_add_lookup(&rwc_lf_results, rwc_lf, htm,
+					       ext_bkt) < 0)
+			return -1;
+		if (test_hash_add_ks_lookup_hit_extbkt(&rwc_lf_results, rwc_lf,
+							htm, ext_bkt) < 0)
 			return -1;
 	}
 	printf("\nTest lookup with read-write concurrency lock free support"
@@ -1112,21 +1318,26 @@ test_hash_readwrite_lf_main(void)
 		}
 	} else
 		printf("With HTM Enabled\n");
-	if (test_hash_add_no_ks_lookup_hit(&rwc_non_lf_results, rwc_lf, htm)
-						< 0)
+	if (test_hash_add_no_ks_lookup_hit(&rwc_non_lf_results, rwc_lf, htm,
+					   ext_bkt) < 0)
 		return -1;
-	if (test_hash_add_no_ks_lookup_miss(&rwc_non_lf_results, rwc_lf, htm)
-						< 0)
+	if (test_hash_add_no_ks_lookup_miss(&rwc_non_lf_results, rwc_lf, htm,
+						ext_bkt) < 0)
 		return -1;
 	if (test_hash_add_ks_lookup_hit_non_sp(&rwc_non_lf_results, rwc_lf,
-						htm) < 0)
+						htm, ext_bkt) < 0)
+		return -1;
+	if (test_hash_add_ks_lookup_hit_sp(&rwc_non_lf_results, rwc_lf, htm,
+						ext_bkt) < 0)
 		return -1;
-	if (test_hash_add_ks_lookup_hit_sp(&rwc_non_lf_results, rwc_lf, htm)
-						< 0)
+	if (test_hash_add_ks_lookup_miss(&rwc_non_lf_results, rwc_lf, htm,
+					 ext_bkt) < 0)
 		return -1;
-	if (test_hash_add_ks_lookup_miss(&rwc_non_lf_results, rwc_lf, htm) < 0)
+	if (test_hash_multi_add_lookup(&rwc_non_lf_results, rwc_lf, htm,
+							ext_bkt) < 0)
 		return -1;
-	if (test_hash_multi_add_lookup(&rwc_non_lf_results, rwc_lf, htm) < 0)
+	if (test_hash_add_ks_lookup_hit_extbkt(&rwc_non_lf_results, rwc_lf,
+						htm, ext_bkt) < 0)
 		return -1;
 results:
 	printf("\n\t\t\t\t\t\t********** Results summary **********\n\n");
@@ -1158,8 +1369,11 @@ test_hash_readwrite_lf_main(void)
 			       "(shift-path)\t\t%u\n\t\t\t\t\t\t\t\t",
 			       rwc_lf_results.w_ks_r_hit_sp[j][i]);
 			printf("Hash add - key-shifts, Hash lookup miss\t\t\t\t"
-				"%u\n\n\t\t\t\t",
+				"%u\n\t\t\t\t\t\t\t\t",
 				rwc_lf_results.w_ks_r_miss[j][i]);
+			printf("Hash add - key-shifts, Hash lookup hit (ext_bkt)\t\t"
+				"%u\n\n\t\t\t\t",
+				rwc_lf_results.w_ks_r_hit_extbkt[j][i]);
 
 			printf("Disabled\t");
 			if (htm)
@@ -1179,7 +1393,11 @@ test_hash_readwrite_lf_main(void)
 			       "(shift-path)\t\t%u\n\t\t\t\t\t\t\t\t",
 			       rwc_non_lf_results.w_ks_r_hit_sp[j][i]);
 			printf("Hash add - key-shifts, Hash lookup miss\t\t\t\t"
-			       "%u\n", rwc_non_lf_results.w_ks_r_miss[j][i]);
+			       "%u\n\t\t\t\t\t\t\t\t",
+			       rwc_non_lf_results.w_ks_r_miss[j][i]);
+			printf("Hash add - key-shifts, Hash lookup hit (ext_bkt)\t\t"
+				"%u\n",
+				rwc_non_lf_results.w_ks_r_hit_extbkt[j][i]);
 
 			printf("_______\t\t_______\t\t_________\t___\t\t"
 			       "_________\t\t\t\t\t\t_________________\n");
-- 
2.17.1

Re: [dpdk-dev] [PATCH v4 2/2] test/hash: lock-free rw concurrency test ext bkt

[Thomas Monjalon]

02/04/2019 01:08, Dharmik Thakkar:
> Add unit test to check for hash lookup and bulk-lookup perf for
> extendable bucket feature.
> It is tested with both lock-free enabled and lock-free disabled case.
> 
> Test includes:
> 
> - hash lookup on keys in ext bkt
> - hash delete causing key-shifts of keys from ext bkt to secondary bkt
> 
> Suggested-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
> Signed-off-by: Dharmik Thakkar <dharmik.thakkar@arm.com>
> Acked-by: Yipeng Wang <yipeng1.wang@intel.com>
> ---
> v4:
> - Add Acked-by tag.

FYI, no need to send a new version just for this.

Please run devtools/test-meson-builds.sh.
When building build-clang-static, I see this error:

app/test/test_hash_readwrite_lf.c:670:13: error:
variable 'key_cnt' is used uninitialized whenever 'if' condition is false

Re: [dpdk-dev] [PATCH v4 2/2] test/hash: lock-free rw concurrency test ext bkt

[Thomas Monjalon]

02/04/2019 01:08, Dharmik Thakkar:
> Add unit test to check for hash lookup and bulk-lookup perf for
> extendable bucket feature.
> It is tested with both lock-free enabled and lock-free disabled case.
> 
> Test includes:
> 
> - hash lookup on keys in ext bkt
> - hash delete causing key-shifts of keys from ext bkt to secondary bkt
> 
> Suggested-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
> Signed-off-by: Dharmik Thakkar <dharmik.thakkar@arm.com>
> Acked-by: Yipeng Wang <yipeng1.wang@intel.com>
> ---
> v4:
> - Add Acked-by tag.

FYI, no need to send a new version just for this.

Please run devtools/test-meson-builds.sh.
When building build-clang-static, I see this error:

app/test/test_hash_readwrite_lf.c:670:13: error:
variable 'key_cnt' is used uninitialized whenever 'if' condition is false

Re: [dpdk-dev] [PATCH v4 2/2] test/hash: lock-free rw concurrency test ext bkt

[Dharmik Thakkar]

Hi Thomas,

Thank you for the review!

> On Apr 1, 2019, at 7:57 PM, Thomas Monjalon <thomas@monjalon.net> wrote:
> 
> 02/04/2019 01:08, Dharmik Thakkar:
>> Add unit test to check for hash lookup and bulk-lookup perf for
>> extendable bucket feature.
>> It is tested with both lock-free enabled and lock-free disabled case.
>> 
>> Test includes:
>> 
>> - hash lookup on keys in ext bkt
>> - hash delete causing key-shifts of keys from ext bkt to secondary bkt
>> 
>> Suggested-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
>> Signed-off-by: Dharmik Thakkar <dharmik.thakkar@arm.com>
>> Acked-by: Yipeng Wang <yipeng1.wang@intel.com>
>> ---
>> v4:
>> - Add Acked-by tag.
> 
> FYI, no need to send a new version just for this.
Sure, thanks!
> 
> Please run devtools/test-meson-builds.sh.
> When building build-clang-static, I see this error:
> 
> app/test/test_hash_readwrite_lf.c:670:13: error:
> variable 'key_cnt' is used uninitialized whenever 'if' condition is false
Will resolve and update.

Re: [dpdk-dev] [PATCH v4 2/2] test/hash: lock-free rw concurrency test ext bkt

[Dharmik Thakkar]

Hi Thomas,

Thank you for the review!

> On Apr 1, 2019, at 7:57 PM, Thomas Monjalon <thomas@monjalon.net> wrote:
> 
> 02/04/2019 01:08, Dharmik Thakkar:
>> Add unit test to check for hash lookup and bulk-lookup perf for
>> extendable bucket feature.
>> It is tested with both lock-free enabled and lock-free disabled case.
>> 
>> Test includes:
>> 
>> - hash lookup on keys in ext bkt
>> - hash delete causing key-shifts of keys from ext bkt to secondary bkt
>> 
>> Suggested-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
>> Signed-off-by: Dharmik Thakkar <dharmik.thakkar@arm.com>
>> Acked-by: Yipeng Wang <yipeng1.wang@intel.com>
>> ---
>> v4:
>> - Add Acked-by tag.
> 
> FYI, no need to send a new version just for this.
Sure, thanks!
> 
> Please run devtools/test-meson-builds.sh.
> When building build-clang-static, I see this error:
> 
> app/test/test_hash_readwrite_lf.c:670:13: error:
> variable 'key_cnt' is used uninitialized whenever 'if' condition is false
Will resolve and update.

[dpdk-dev] [PATCH v5 0/2] hash: add lock free support for ext bkt

[Dharmik Thakkar]

This patch series:
- Enables lock-free read-write concurrency support for extendable
bucket feature.
- Adds lock-free read-write concurrency tests for ext bkt
---
v5:
 * Resolve devtools/test-meson-builds.sh error (Thomas).

v4:
 * Add Acked-by tag.

v3:
 * Update lib/librte_hash/rte_cuckoo_hash.c (Yipeng).
 * Add Acked-by tag.

v2:
 * Update doc (Yipeng).
 * Update lib/librte_hash/rte_cuckoo_hash.c (Yipeng).

Dharmik Thakkar (2):
  hash: add lock free support for extendable bucket
  test/hash: lock-free rw concurrency test ext bkt

 app/test/test_hash_readwrite_lf.c  | 352 +++++++++++++++++++++++------
 doc/guides/prog_guide/hash_lib.rst |   6 +-
 lib/librte_hash/rte_cuckoo_hash.c  | 157 +++++++++----
 lib/librte_hash/rte_cuckoo_hash.h  |   7 +
 4 files changed, 402 insertions(+), 120 deletions(-)

-- 
2.17.1

[dpdk-dev] [PATCH v5 0/2] hash: add lock free support for ext bkt

[Dharmik Thakkar]

This patch series:
- Enables lock-free read-write concurrency support for extendable
bucket feature.
- Adds lock-free read-write concurrency tests for ext bkt
---
v5:
 * Resolve devtools/test-meson-builds.sh error (Thomas).

v4:
 * Add Acked-by tag.

v3:
 * Update lib/librte_hash/rte_cuckoo_hash.c (Yipeng).
 * Add Acked-by tag.

v2:
 * Update doc (Yipeng).
 * Update lib/librte_hash/rte_cuckoo_hash.c (Yipeng).

Dharmik Thakkar (2):
  hash: add lock free support for extendable bucket
  test/hash: lock-free rw concurrency test ext bkt

 app/test/test_hash_readwrite_lf.c  | 352 +++++++++++++++++++++++------
 doc/guides/prog_guide/hash_lib.rst |   6 +-
 lib/librte_hash/rte_cuckoo_hash.c  | 157 +++++++++----
 lib/librte_hash/rte_cuckoo_hash.h  |   7 +
 4 files changed, 402 insertions(+), 120 deletions(-)

-- 
2.17.1

[dpdk-dev] [PATCH v5 1/2] hash: add lock free support for extendable bucket

[Dharmik Thakkar]

This patch enables lock-free read-write concurrency support for
extendable bucket feature.

Suggested-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
Signed-off-by: Dharmik Thakkar <dharmik.thakkar@arm.com>
Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
Reviewed-by: Gavin Hu <gavin.hu@arm.com>
Reviewed-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
Acked-by: Yipeng Wang <yipeng1.wang@intel.com>
---
 doc/guides/prog_guide/hash_lib.rst |   6 +-
 lib/librte_hash/rte_cuckoo_hash.c  | 157 ++++++++++++++++++++---------
 lib/librte_hash/rte_cuckoo_hash.h  |   7 ++
 3 files changed, 117 insertions(+), 53 deletions(-)

diff --git a/doc/guides/prog_guide/hash_lib.rst b/doc/guides/prog_guide/hash_lib.rst
index 85a6edfa8b16..d06c7de2ead1 100644
--- a/doc/guides/prog_guide/hash_lib.rst
+++ b/doc/guides/prog_guide/hash_lib.rst
@@ -108,9 +108,9 @@ Extendable Bucket Functionality support
 An extra flag is used to enable this functionality (flag is not set by default). When the (RTE_HASH_EXTRA_FLAGS_EXT_TABLE) is set and
 in the very unlikely case due to excessive hash collisions that a key has failed to be inserted, the hash table bucket is extended with a linked
 list to insert these failed keys. This feature is important for the workloads (e.g. telco workloads) that need to insert up to 100% of the
-hash table size and can't tolerate any key insertion failure (even if very few). Currently the extendable bucket is not supported
-with the lock-free concurrency implementation (RTE_HASH_EXTRA_FLAGS_RW_CONCURRENCY_LF).
-
+hash table size and can't tolerate any key insertion failure (even if very few).
+Please note that with the 'lock free read/write concurrency' flag enabled, users need to call 'rte_hash_free_key_with_position' API in order to free the empty buckets and
+deleted keys, to maintain the 100% capacity guarantee.
 
 Implementation Details (non Extendable Bucket Case)
 ---------------------------------------------------
diff --git a/lib/librte_hash/rte_cuckoo_hash.c b/lib/librte_hash/rte_cuckoo_hash.c
index c01489ba5193..8213dbf5f782 100644
--- a/lib/librte_hash/rte_cuckoo_hash.c
+++ b/lib/librte_hash/rte_cuckoo_hash.c
@@ -140,6 +140,7 @@ rte_hash_create(const struct rte_hash_parameters *params)
 	unsigned int readwrite_concur_support = 0;
 	unsigned int writer_takes_lock = 0;
 	unsigned int no_free_on_del = 0;
+	uint32_t *ext_bkt_to_free = NULL;
 	uint32_t *tbl_chng_cnt = NULL;
 	unsigned int readwrite_concur_lf_support = 0;
 
@@ -170,15 +171,6 @@ rte_hash_create(const struct rte_hash_parameters *params)
 		return NULL;
 	}
 
-	if ((params->extra_flag & RTE_HASH_EXTRA_FLAGS_RW_CONCURRENCY_LF) &&
-	    (params->extra_flag & RTE_HASH_EXTRA_FLAGS_EXT_TABLE)) {
-		rte_errno = EINVAL;
-		RTE_LOG(ERR, HASH, "rte_hash_create: extendable bucket "
-			"feature not supported with rw concurrency "
-			"lock free\n");
-		return NULL;
-	}
-
 	/* Check extra flags field to check extra options. */
 	if (params->extra_flag & RTE_HASH_EXTRA_FLAGS_TRANS_MEM_SUPPORT)
 		hw_trans_mem_support = 1;
@@ -302,6 +294,16 @@ rte_hash_create(const struct rte_hash_parameters *params)
 		 */
 		for (i = 1; i <= num_buckets; i++)
 			rte_ring_sp_enqueue(r_ext, (void *)((uintptr_t) i));
+
+		if (readwrite_concur_lf_support) {
+			ext_bkt_to_free = rte_zmalloc(NULL, sizeof(uint32_t) *
+								num_key_slots, 0);
+			if (ext_bkt_to_free == NULL) {
+				RTE_LOG(ERR, HASH, "ext bkt to free memory allocation "
+								"failed\n");
+				goto err_unlock;
+			}
+		}
 	}
 
 	const uint32_t key_entry_size =
@@ -393,6 +395,7 @@ rte_hash_create(const struct rte_hash_parameters *params)
 		default_hash_func : params->hash_func;
 	h->key_store = k;
 	h->free_slots = r;
+	h->ext_bkt_to_free = ext_bkt_to_free;
 	h->tbl_chng_cnt = tbl_chng_cnt;
 	*h->tbl_chng_cnt = 0;
 	h->hw_trans_mem_support = hw_trans_mem_support;
@@ -443,6 +446,7 @@ rte_hash_create(const struct rte_hash_parameters *params)
 	rte_free(buckets_ext);
 	rte_free(k);
 	rte_free(tbl_chng_cnt);
+	rte_free(ext_bkt_to_free);
 	return NULL;
 }
 
@@ -484,6 +488,7 @@ rte_hash_free(struct rte_hash *h)
 	rte_free(h->buckets);
 	rte_free(h->buckets_ext);
 	rte_free(h->tbl_chng_cnt);
+	rte_free(h->ext_bkt_to_free);
 	rte_free(h);
 	rte_free(te);
 }
@@ -799,7 +804,7 @@ rte_hash_cuckoo_move_insert_mw(const struct rte_hash *h,
 			__atomic_store_n(h->tbl_chng_cnt,
 					 *h->tbl_chng_cnt + 1,
 					 __ATOMIC_RELEASE);
-			/* The stores to sig_alt and sig_current should not
+			/* The store to sig_current should not
 			 * move above the store to tbl_chng_cnt.
 			 */
 			__atomic_thread_fence(__ATOMIC_RELEASE);
@@ -831,7 +836,7 @@ rte_hash_cuckoo_move_insert_mw(const struct rte_hash *h,
 		__atomic_store_n(h->tbl_chng_cnt,
 				 *h->tbl_chng_cnt + 1,
 				 __ATOMIC_RELEASE);
-		/* The stores to sig_alt and sig_current should not
+		/* The store to sig_current should not
 		 * move above the store to tbl_chng_cnt.
 		 */
 		__atomic_thread_fence(__ATOMIC_RELEASE);
@@ -1054,7 +1059,12 @@ __rte_hash_add_key_with_hash(const struct rte_hash *h, const void *key,
 			/* Check if slot is available */
 			if (likely(cur_bkt->key_idx[i] == EMPTY_SLOT)) {
 				cur_bkt->sig_current[i] = short_sig;
-				cur_bkt->key_idx[i] = new_idx;
+				/* Store to signature should not leak after
+				 * the store to key_idx
+				 */
+				__atomic_store_n(&cur_bkt->key_idx[i],
+						 new_idx,
+						 __ATOMIC_RELEASE);
 				__hash_rw_writer_unlock(h);
 				return new_idx - 1;
 			}
@@ -1072,7 +1082,12 @@ __rte_hash_add_key_with_hash(const struct rte_hash *h, const void *key,
 	bkt_id = (uint32_t)((uintptr_t)ext_bkt_id) - 1;
 	/* Use the first location of the new bucket */
 	(h->buckets_ext[bkt_id]).sig_current[0] = short_sig;
-	(h->buckets_ext[bkt_id]).key_idx[0] = new_idx;
+	/* Store to signature should not leak after
+	 * the store to key_idx
+	 */
+	__atomic_store_n(&(h->buckets_ext[bkt_id]).key_idx[0],
+			 new_idx,
+			 __ATOMIC_RELEASE);
 	/* Link the new bucket to sec bucket linked list */
 	last = rte_hash_get_last_bkt(sec_bkt);
 	last->next = &h->buckets_ext[bkt_id];
@@ -1366,7 +1381,8 @@ remove_entry(const struct rte_hash *h, struct rte_hash_bucket *bkt, unsigned i)
  * empty slot.
  */
 static inline void
-__rte_hash_compact_ll(struct rte_hash_bucket *cur_bkt, int pos) {
+__rte_hash_compact_ll(const struct rte_hash *h,
+			struct rte_hash_bucket *cur_bkt, int pos) {
 	int i;
 	struct rte_hash_bucket *last_bkt;
 
@@ -1377,10 +1393,27 @@ __rte_hash_compact_ll(struct rte_hash_bucket *cur_bkt, int pos) {
 
 	for (i = RTE_HASH_BUCKET_ENTRIES - 1; i >= 0; i--) {
 		if (last_bkt->key_idx[i] != EMPTY_SLOT) {
-			cur_bkt->key_idx[pos] = last_bkt->key_idx[i];
 			cur_bkt->sig_current[pos] = last_bkt->sig_current[i];
+			__atomic_store_n(&cur_bkt->key_idx[pos],
+					 last_bkt->key_idx[i],
+					 __ATOMIC_RELEASE);
+			if (h->readwrite_concur_lf_support) {
+				/* Inform the readers that the table has changed
+				 * Since there is one writer, load acquire on
+				 * tbl_chng_cnt is not required.
+				 */
+				__atomic_store_n(h->tbl_chng_cnt,
+					 *h->tbl_chng_cnt + 1,
+					 __ATOMIC_RELEASE);
+				/* The store to sig_current should
+				 * not move above the store to tbl_chng_cnt.
+				 */
+				__atomic_thread_fence(__ATOMIC_RELEASE);
+			}
 			last_bkt->sig_current[i] = NULL_SIGNATURE;
-			last_bkt->key_idx[i] = EMPTY_SLOT;
+			__atomic_store_n(&last_bkt->key_idx[i],
+					 EMPTY_SLOT,
+					 __ATOMIC_RELEASE);
 			return;
 		}
 	}
@@ -1449,7 +1482,7 @@ __rte_hash_del_key_with_hash(const struct rte_hash *h, const void *key,
 	/* look for key in primary bucket */
 	ret = search_and_remove(h, key, prim_bkt, short_sig, &pos);
 	if (ret != -1) {
-		__rte_hash_compact_ll(prim_bkt, pos);
+		__rte_hash_compact_ll(h, prim_bkt, pos);
 		last_bkt = prim_bkt->next;
 		prev_bkt = prim_bkt;
 		goto return_bkt;
@@ -1461,7 +1494,7 @@ __rte_hash_del_key_with_hash(const struct rte_hash *h, const void *key,
 	FOR_EACH_BUCKET(cur_bkt, sec_bkt) {
 		ret = search_and_remove(h, key, cur_bkt, short_sig, &pos);
 		if (ret != -1) {
-			__rte_hash_compact_ll(cur_bkt, pos);
+			__rte_hash_compact_ll(h, cur_bkt, pos);
 			last_bkt = sec_bkt->next;
 			prev_bkt = sec_bkt;
 			goto return_bkt;
@@ -1488,11 +1521,24 @@ __rte_hash_del_key_with_hash(const struct rte_hash *h, const void *key,
 	}
 	/* found empty bucket and recycle */
 	if (i == RTE_HASH_BUCKET_ENTRIES) {
-		prev_bkt->next = last_bkt->next = NULL;
+		prev_bkt->next = NULL;
 		uint32_t index = last_bkt - h->buckets_ext + 1;
-		rte_ring_sp_enqueue(h->free_ext_bkts, (void *)(uintptr_t)index);
+		/* Recycle the empty bkt if
+		 * no_free_on_del is disabled.
+		 */
+		if (h->no_free_on_del)
+			/* Store index of an empty ext bkt to be recycled
+			 * on calling rte_hash_del_xxx APIs.
+			 * When lock free read-write concurrency is enabled,
+			 * an empty ext bkt cannot be put into free list
+			 * immediately (as readers might be using it still).
+			 * Hence freeing of the ext bkt is piggy-backed to
+			 * freeing of the key index.
+			 */
+			h->ext_bkt_to_free[ret] = index;
+		else
+			rte_ring_sp_enqueue(h->free_ext_bkts, (void *)(uintptr_t)index);
 	}
-
 	__hash_rw_writer_unlock(h);
 	return ret;
 }
@@ -1545,6 +1591,14 @@ rte_hash_free_key_with_position(const struct rte_hash *h,
 	/* Out of bounds */
 	if (position >= total_entries)
 		return -EINVAL;
+	if (h->ext_table_support && h->readwrite_concur_lf_support) {
+		uint32_t index = h->ext_bkt_to_free[position];
+		if (index) {
+			/* Recycle empty ext bkt to free list. */
+			rte_ring_sp_enqueue(h->free_ext_bkts, (void *)(uintptr_t)index);
+			h->ext_bkt_to_free[position] = 0;
+		}
+	}
 
 	if (h->use_local_cache) {
 		lcore_id = rte_lcore_id();
@@ -1855,6 +1909,9 @@ __rte_hash_lookup_bulk_lf(const struct rte_hash *h, const void **keys,
 		rte_prefetch0(secondary_bkt[i]);
 	}
 
+	for (i = 0; i < num_keys; i++)
+		positions[i] = -ENOENT;
+
 	do {
 		/* Load the table change counter before the lookup
 		 * starts. Acquire semantics will make sure that
@@ -1899,7 +1956,6 @@ __rte_hash_lookup_bulk_lf(const struct rte_hash *h, const void **keys,
 
 		/* Compare keys, first hits in primary first */
 		for (i = 0; i < num_keys; i++) {
-			positions[i] = -ENOENT;
 			while (prim_hitmask[i]) {
 				uint32_t hit_index =
 						__builtin_ctzl(prim_hitmask[i])
@@ -1972,6 +2028,35 @@ __rte_hash_lookup_bulk_lf(const struct rte_hash *h, const void **keys,
 			continue;
 		}
 
+		/* all found, do not need to go through ext bkt */
+		if (hits == ((1ULL << num_keys) - 1)) {
+			if (hit_mask != NULL)
+				*hit_mask = hits;
+			return;
+		}
+		/* need to check ext buckets for match */
+		if (h->ext_table_support) {
+			for (i = 0; i < num_keys; i++) {
+				if ((hits & (1ULL << i)) != 0)
+					continue;
+				next_bkt = secondary_bkt[i]->next;
+				FOR_EACH_BUCKET(cur_bkt, next_bkt) {
+					if (data != NULL)
+						ret = search_one_bucket_lf(h,
+							keys[i], sig[i],
+							&data[i], cur_bkt);
+					else
+						ret = search_one_bucket_lf(h,
+								keys[i], sig[i],
+								NULL, cur_bkt);
+					if (ret != -1) {
+						positions[i] = ret;
+						hits |= 1ULL << i;
+						break;
+					}
+				}
+			}
+		}
 		/* The loads of sig_current in compare_signatures
 		 * should not move below the load from tbl_chng_cnt.
 		 */
@@ -1988,34 +2073,6 @@ __rte_hash_lookup_bulk_lf(const struct rte_hash *h, const void **keys,
 					__ATOMIC_ACQUIRE);
 	} while (cnt_b != cnt_a);
 
-	/* all found, do not need to go through ext bkt */
-	if ((hits == ((1ULL << num_keys) - 1)) || !h->ext_table_support) {
-		if (hit_mask != NULL)
-			*hit_mask = hits;
-		__hash_rw_reader_unlock(h);
-		return;
-	}
-
-	/* need to check ext buckets for match */
-	for (i = 0; i < num_keys; i++) {
-		if ((hits & (1ULL << i)) != 0)
-			continue;
-		next_bkt = secondary_bkt[i]->next;
-		FOR_EACH_BUCKET(cur_bkt, next_bkt) {
-			if (data != NULL)
-				ret = search_one_bucket_lf(h, keys[i],
-						sig[i], &data[i], cur_bkt);
-			else
-				ret = search_one_bucket_lf(h, keys[i],
-						sig[i], NULL, cur_bkt);
-			if (ret != -1) {
-				positions[i] = ret;
-				hits |= 1ULL << i;
-				break;
-			}
-		}
-	}
-
 	if (hit_mask != NULL)
 		*hit_mask = hits;
 }
diff --git a/lib/librte_hash/rte_cuckoo_hash.h b/lib/librte_hash/rte_cuckoo_hash.h
index eacdaa8d4684..48c85c890712 100644
--- a/lib/librte_hash/rte_cuckoo_hash.h
+++ b/lib/librte_hash/rte_cuckoo_hash.h
@@ -210,6 +210,13 @@ struct rte_hash {
 	rte_rwlock_t *readwrite_lock; /**< Read-write lock thread-safety. */
 	struct rte_hash_bucket *buckets_ext; /**< Extra buckets array */
 	struct rte_ring *free_ext_bkts; /**< Ring of indexes of free buckets */
+	/* Stores index of an empty ext bkt to be recycled on calling
+	 * rte_hash_del_xxx APIs. When lock free read-write concurrency is
+	 * enabled, an empty ext bkt cannot be put into free list immediately
+	 * (as readers might be using it still). Hence freeing of the ext bkt
+	 * is piggy-backed to freeing of the key index.
+	 */
+	uint32_t *ext_bkt_to_free;
 	uint32_t *tbl_chng_cnt;
 	/**< Indicates if the hash table changed from last read. */
 } __rte_cache_aligned;
-- 
2.17.1

[dpdk-dev] [PATCH v5 1/2] hash: add lock free support for extendable bucket

[Dharmik Thakkar]

This patch enables lock-free read-write concurrency support for
extendable bucket feature.

Suggested-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
Signed-off-by: Dharmik Thakkar <dharmik.thakkar@arm.com>
Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
Reviewed-by: Gavin Hu <gavin.hu@arm.com>
Reviewed-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
Acked-by: Yipeng Wang <yipeng1.wang@intel.com>
---
 doc/guides/prog_guide/hash_lib.rst |   6 +-
 lib/librte_hash/rte_cuckoo_hash.c  | 157 ++++++++++++++++++++---------
 lib/librte_hash/rte_cuckoo_hash.h  |   7 ++
 3 files changed, 117 insertions(+), 53 deletions(-)

diff --git a/doc/guides/prog_guide/hash_lib.rst b/doc/guides/prog_guide/hash_lib.rst
index 85a6edfa8b16..d06c7de2ead1 100644
--- a/doc/guides/prog_guide/hash_lib.rst
+++ b/doc/guides/prog_guide/hash_lib.rst
@@ -108,9 +108,9 @@ Extendable Bucket Functionality support
 An extra flag is used to enable this functionality (flag is not set by default). When the (RTE_HASH_EXTRA_FLAGS_EXT_TABLE) is set and
 in the very unlikely case due to excessive hash collisions that a key has failed to be inserted, the hash table bucket is extended with a linked
 list to insert these failed keys. This feature is important for the workloads (e.g. telco workloads) that need to insert up to 100% of the
-hash table size and can't tolerate any key insertion failure (even if very few). Currently the extendable bucket is not supported
-with the lock-free concurrency implementation (RTE_HASH_EXTRA_FLAGS_RW_CONCURRENCY_LF).
-
+hash table size and can't tolerate any key insertion failure (even if very few).
+Please note that with the 'lock free read/write concurrency' flag enabled, users need to call 'rte_hash_free_key_with_position' API in order to free the empty buckets and
+deleted keys, to maintain the 100% capacity guarantee.
 
 Implementation Details (non Extendable Bucket Case)
 ---------------------------------------------------
diff --git a/lib/librte_hash/rte_cuckoo_hash.c b/lib/librte_hash/rte_cuckoo_hash.c
index c01489ba5193..8213dbf5f782 100644
--- a/lib/librte_hash/rte_cuckoo_hash.c
+++ b/lib/librte_hash/rte_cuckoo_hash.c
@@ -140,6 +140,7 @@ rte_hash_create(const struct rte_hash_parameters *params)
 	unsigned int readwrite_concur_support = 0;
 	unsigned int writer_takes_lock = 0;
 	unsigned int no_free_on_del = 0;
+	uint32_t *ext_bkt_to_free = NULL;
 	uint32_t *tbl_chng_cnt = NULL;
 	unsigned int readwrite_concur_lf_support = 0;
 
@@ -170,15 +171,6 @@ rte_hash_create(const struct rte_hash_parameters *params)
 		return NULL;
 	}
 
-	if ((params->extra_flag & RTE_HASH_EXTRA_FLAGS_RW_CONCURRENCY_LF) &&
-	    (params->extra_flag & RTE_HASH_EXTRA_FLAGS_EXT_TABLE)) {
-		rte_errno = EINVAL;
-		RTE_LOG(ERR, HASH, "rte_hash_create: extendable bucket "
-			"feature not supported with rw concurrency "
-			"lock free\n");
-		return NULL;
-	}
-
 	/* Check extra flags field to check extra options. */
 	if (params->extra_flag & RTE_HASH_EXTRA_FLAGS_TRANS_MEM_SUPPORT)
 		hw_trans_mem_support = 1;
@@ -302,6 +294,16 @@ rte_hash_create(const struct rte_hash_parameters *params)
 		 */
 		for (i = 1; i <= num_buckets; i++)
 			rte_ring_sp_enqueue(r_ext, (void *)((uintptr_t) i));
+
+		if (readwrite_concur_lf_support) {
+			ext_bkt_to_free = rte_zmalloc(NULL, sizeof(uint32_t) *
+								num_key_slots, 0);
+			if (ext_bkt_to_free == NULL) {
+				RTE_LOG(ERR, HASH, "ext bkt to free memory allocation "
+								"failed\n");
+				goto err_unlock;
+			}
+		}
 	}
 
 	const uint32_t key_entry_size =
@@ -393,6 +395,7 @@ rte_hash_create(const struct rte_hash_parameters *params)
 		default_hash_func : params->hash_func;
 	h->key_store = k;
 	h->free_slots = r;
+	h->ext_bkt_to_free = ext_bkt_to_free;
 	h->tbl_chng_cnt = tbl_chng_cnt;
 	*h->tbl_chng_cnt = 0;
 	h->hw_trans_mem_support = hw_trans_mem_support;
@@ -443,6 +446,7 @@ rte_hash_create(const struct rte_hash_parameters *params)
 	rte_free(buckets_ext);
 	rte_free(k);
 	rte_free(tbl_chng_cnt);
+	rte_free(ext_bkt_to_free);
 	return NULL;
 }
 
@@ -484,6 +488,7 @@ rte_hash_free(struct rte_hash *h)
 	rte_free(h->buckets);
 	rte_free(h->buckets_ext);
 	rte_free(h->tbl_chng_cnt);
+	rte_free(h->ext_bkt_to_free);
 	rte_free(h);
 	rte_free(te);
 }
@@ -799,7 +804,7 @@ rte_hash_cuckoo_move_insert_mw(const struct rte_hash *h,
 			__atomic_store_n(h->tbl_chng_cnt,
 					 *h->tbl_chng_cnt + 1,
 					 __ATOMIC_RELEASE);
-			/* The stores to sig_alt and sig_current should not
+			/* The store to sig_current should not
 			 * move above the store to tbl_chng_cnt.
 			 */
 			__atomic_thread_fence(__ATOMIC_RELEASE);
@@ -831,7 +836,7 @@ rte_hash_cuckoo_move_insert_mw(const struct rte_hash *h,
 		__atomic_store_n(h->tbl_chng_cnt,
 				 *h->tbl_chng_cnt + 1,
 				 __ATOMIC_RELEASE);
-		/* The stores to sig_alt and sig_current should not
+		/* The store to sig_current should not
 		 * move above the store to tbl_chng_cnt.
 		 */
 		__atomic_thread_fence(__ATOMIC_RELEASE);
@@ -1054,7 +1059,12 @@ __rte_hash_add_key_with_hash(const struct rte_hash *h, const void *key,
 			/* Check if slot is available */
 			if (likely(cur_bkt->key_idx[i] == EMPTY_SLOT)) {
 				cur_bkt->sig_current[i] = short_sig;
-				cur_bkt->key_idx[i] = new_idx;
+				/* Store to signature should not leak after
+				 * the store to key_idx
+				 */
+				__atomic_store_n(&cur_bkt->key_idx[i],
+						 new_idx,
+						 __ATOMIC_RELEASE);
 				__hash_rw_writer_unlock(h);
 				return new_idx - 1;
 			}
@@ -1072,7 +1082,12 @@ __rte_hash_add_key_with_hash(const struct rte_hash *h, const void *key,
 	bkt_id = (uint32_t)((uintptr_t)ext_bkt_id) - 1;
 	/* Use the first location of the new bucket */
 	(h->buckets_ext[bkt_id]).sig_current[0] = short_sig;
-	(h->buckets_ext[bkt_id]).key_idx[0] = new_idx;
+	/* Store to signature should not leak after
+	 * the store to key_idx
+	 */
+	__atomic_store_n(&(h->buckets_ext[bkt_id]).key_idx[0],
+			 new_idx,
+			 __ATOMIC_RELEASE);
 	/* Link the new bucket to sec bucket linked list */
 	last = rte_hash_get_last_bkt(sec_bkt);
 	last->next = &h->buckets_ext[bkt_id];
@@ -1366,7 +1381,8 @@ remove_entry(const struct rte_hash *h, struct rte_hash_bucket *bkt, unsigned i)
  * empty slot.
  */
 static inline void
-__rte_hash_compact_ll(struct rte_hash_bucket *cur_bkt, int pos) {
+__rte_hash_compact_ll(const struct rte_hash *h,
+			struct rte_hash_bucket *cur_bkt, int pos) {
 	int i;
 	struct rte_hash_bucket *last_bkt;
 
@@ -1377,10 +1393,27 @@ __rte_hash_compact_ll(struct rte_hash_bucket *cur_bkt, int pos) {
 
 	for (i = RTE_HASH_BUCKET_ENTRIES - 1; i >= 0; i--) {
 		if (last_bkt->key_idx[i] != EMPTY_SLOT) {
-			cur_bkt->key_idx[pos] = last_bkt->key_idx[i];
 			cur_bkt->sig_current[pos] = last_bkt->sig_current[i];
+			__atomic_store_n(&cur_bkt->key_idx[pos],
+					 last_bkt->key_idx[i],
+					 __ATOMIC_RELEASE);
+			if (h->readwrite_concur_lf_support) {
+				/* Inform the readers that the table has changed
+				 * Since there is one writer, load acquire on
+				 * tbl_chng_cnt is not required.
+				 */
+				__atomic_store_n(h->tbl_chng_cnt,
+					 *h->tbl_chng_cnt + 1,
+					 __ATOMIC_RELEASE);
+				/* The store to sig_current should
+				 * not move above the store to tbl_chng_cnt.
+				 */
+				__atomic_thread_fence(__ATOMIC_RELEASE);
+			}
 			last_bkt->sig_current[i] = NULL_SIGNATURE;
-			last_bkt->key_idx[i] = EMPTY_SLOT;
+			__atomic_store_n(&last_bkt->key_idx[i],
+					 EMPTY_SLOT,
+					 __ATOMIC_RELEASE);
 			return;
 		}
 	}
@@ -1449,7 +1482,7 @@ __rte_hash_del_key_with_hash(const struct rte_hash *h, const void *key,
 	/* look for key in primary bucket */
 	ret = search_and_remove(h, key, prim_bkt, short_sig, &pos);
 	if (ret != -1) {
-		__rte_hash_compact_ll(prim_bkt, pos);
+		__rte_hash_compact_ll(h, prim_bkt, pos);
 		last_bkt = prim_bkt->next;
 		prev_bkt = prim_bkt;
 		goto return_bkt;
@@ -1461,7 +1494,7 @@ __rte_hash_del_key_with_hash(const struct rte_hash *h, const void *key,
 	FOR_EACH_BUCKET(cur_bkt, sec_bkt) {
 		ret = search_and_remove(h, key, cur_bkt, short_sig, &pos);
 		if (ret != -1) {
-			__rte_hash_compact_ll(cur_bkt, pos);
+			__rte_hash_compact_ll(h, cur_bkt, pos);
 			last_bkt = sec_bkt->next;
 			prev_bkt = sec_bkt;
 			goto return_bkt;
@@ -1488,11 +1521,24 @@ __rte_hash_del_key_with_hash(const struct rte_hash *h, const void *key,
 	}
 	/* found empty bucket and recycle */
 	if (i == RTE_HASH_BUCKET_ENTRIES) {
-		prev_bkt->next = last_bkt->next = NULL;
+		prev_bkt->next = NULL;
 		uint32_t index = last_bkt - h->buckets_ext + 1;
-		rte_ring_sp_enqueue(h->free_ext_bkts, (void *)(uintptr_t)index);
+		/* Recycle the empty bkt if
+		 * no_free_on_del is disabled.
+		 */
+		if (h->no_free_on_del)
+			/* Store index of an empty ext bkt to be recycled
+			 * on calling rte_hash_del_xxx APIs.
+			 * When lock free read-write concurrency is enabled,
+			 * an empty ext bkt cannot be put into free list
+			 * immediately (as readers might be using it still).
+			 * Hence freeing of the ext bkt is piggy-backed to
+			 * freeing of the key index.
+			 */
+			h->ext_bkt_to_free[ret] = index;
+		else
+			rte_ring_sp_enqueue(h->free_ext_bkts, (void *)(uintptr_t)index);
 	}
-
 	__hash_rw_writer_unlock(h);
 	return ret;
 }
@@ -1545,6 +1591,14 @@ rte_hash_free_key_with_position(const struct rte_hash *h,
 	/* Out of bounds */
 	if (position >= total_entries)
 		return -EINVAL;
+	if (h->ext_table_support && h->readwrite_concur_lf_support) {
+		uint32_t index = h->ext_bkt_to_free[position];
+		if (index) {
+			/* Recycle empty ext bkt to free list. */
+			rte_ring_sp_enqueue(h->free_ext_bkts, (void *)(uintptr_t)index);
+			h->ext_bkt_to_free[position] = 0;
+		}
+	}
 
 	if (h->use_local_cache) {
 		lcore_id = rte_lcore_id();
@@ -1855,6 +1909,9 @@ __rte_hash_lookup_bulk_lf(const struct rte_hash *h, const void **keys,
 		rte_prefetch0(secondary_bkt[i]);
 	}
 
+	for (i = 0; i < num_keys; i++)
+		positions[i] = -ENOENT;
+
 	do {
 		/* Load the table change counter before the lookup
 		 * starts. Acquire semantics will make sure that
@@ -1899,7 +1956,6 @@ __rte_hash_lookup_bulk_lf(const struct rte_hash *h, const void **keys,
 
 		/* Compare keys, first hits in primary first */
 		for (i = 0; i < num_keys; i++) {
-			positions[i] = -ENOENT;
 			while (prim_hitmask[i]) {
 				uint32_t hit_index =
 						__builtin_ctzl(prim_hitmask[i])
@@ -1972,6 +2028,35 @@ __rte_hash_lookup_bulk_lf(const struct rte_hash *h, const void **keys,
 			continue;
 		}
 
+		/* all found, do not need to go through ext bkt */
+		if (hits == ((1ULL << num_keys) - 1)) {
+			if (hit_mask != NULL)
+				*hit_mask = hits;
+			return;
+		}
+		/* need to check ext buckets for match */
+		if (h->ext_table_support) {
+			for (i = 0; i < num_keys; i++) {
+				if ((hits & (1ULL << i)) != 0)
+					continue;
+				next_bkt = secondary_bkt[i]->next;
+				FOR_EACH_BUCKET(cur_bkt, next_bkt) {
+					if (data != NULL)
+						ret = search_one_bucket_lf(h,
+							keys[i], sig[i],
+							&data[i], cur_bkt);
+					else
+						ret = search_one_bucket_lf(h,
+								keys[i], sig[i],
+								NULL, cur_bkt);
+					if (ret != -1) {
+						positions[i] = ret;
+						hits |= 1ULL << i;
+						break;
+					}
+				}
+			}
+		}
 		/* The loads of sig_current in compare_signatures
 		 * should not move below the load from tbl_chng_cnt.
 		 */
@@ -1988,34 +2073,6 @@ __rte_hash_lookup_bulk_lf(const struct rte_hash *h, const void **keys,
 					__ATOMIC_ACQUIRE);
 	} while (cnt_b != cnt_a);
 
-	/* all found, do not need to go through ext bkt */
-	if ((hits == ((1ULL << num_keys) - 1)) || !h->ext_table_support) {
-		if (hit_mask != NULL)
-			*hit_mask = hits;
-		__hash_rw_reader_unlock(h);
-		return;
-	}
-
-	/* need to check ext buckets for match */
-	for (i = 0; i < num_keys; i++) {
-		if ((hits & (1ULL << i)) != 0)
-			continue;
-		next_bkt = secondary_bkt[i]->next;
-		FOR_EACH_BUCKET(cur_bkt, next_bkt) {
-			if (data != NULL)
-				ret = search_one_bucket_lf(h, keys[i],
-						sig[i], &data[i], cur_bkt);
-			else
-				ret = search_one_bucket_lf(h, keys[i],
-						sig[i], NULL, cur_bkt);
-			if (ret != -1) {
-				positions[i] = ret;
-				hits |= 1ULL << i;
-				break;
-			}
-		}
-	}
-
 	if (hit_mask != NULL)
 		*hit_mask = hits;
 }
diff --git a/lib/librte_hash/rte_cuckoo_hash.h b/lib/librte_hash/rte_cuckoo_hash.h
index eacdaa8d4684..48c85c890712 100644
--- a/lib/librte_hash/rte_cuckoo_hash.h
+++ b/lib/librte_hash/rte_cuckoo_hash.h
@@ -210,6 +210,13 @@ struct rte_hash {
 	rte_rwlock_t *readwrite_lock; /**< Read-write lock thread-safety. */
 	struct rte_hash_bucket *buckets_ext; /**< Extra buckets array */
 	struct rte_ring *free_ext_bkts; /**< Ring of indexes of free buckets */
+	/* Stores index of an empty ext bkt to be recycled on calling
+	 * rte_hash_del_xxx APIs. When lock free read-write concurrency is
+	 * enabled, an empty ext bkt cannot be put into free list immediately
+	 * (as readers might be using it still). Hence freeing of the ext bkt
+	 * is piggy-backed to freeing of the key index.
+	 */
+	uint32_t *ext_bkt_to_free;
 	uint32_t *tbl_chng_cnt;
 	/**< Indicates if the hash table changed from last read. */
 } __rte_cache_aligned;
-- 
2.17.1

[dpdk-dev] [PATCH v5 2/2] test/hash: lock-free rw concurrency test ext bkt

[Dharmik Thakkar]

Add unit test to check for hash lookup and bulk-lookup perf for
extendable bucket feature.
It is tested with both lock-free enabled and lock-free disabled case.

Test includes:

- hash lookup on keys in ext bkt
- hash delete causing key-shifts of keys from ext bkt to secondary bkt

Suggested-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
Signed-off-by: Dharmik Thakkar <dharmik.thakkar@arm.com>
Acked-by: Yipeng Wang <yipeng1.wang@intel.com>
---
 app/test/test_hash_readwrite_lf.c | 352 ++++++++++++++++++++++++------
 1 file changed, 285 insertions(+), 67 deletions(-)

diff --git a/app/test/test_hash_readwrite_lf.c b/app/test/test_hash_readwrite_lf.c
index cbfd9322696b..4ab4c8ee64cf 100644
--- a/app/test/test_hash_readwrite_lf.c
+++ b/app/test/test_hash_readwrite_lf.c
@@ -41,6 +41,12 @@
 #define READ_PASS_SHIFT_PATH 4
 #define READ_PASS_NON_SHIFT_PATH 8
 #define BULK_LOOKUP 16
+#define READ_PASS_KEY_SHIFTS_EXTBKT 32
+
+#define WRITE_NO_KEY_SHIFT 0
+#define WRITE_KEY_SHIFT 1
+#define WRITE_EXT_BKT 2
+
 #define NUM_TEST 3
 unsigned int rwc_core_cnt[NUM_TEST] = {1, 2, 4};
 
@@ -51,6 +57,7 @@ struct rwc_perf {
 	uint32_t w_ks_r_hit_sp[2][NUM_TEST];
 	uint32_t w_ks_r_miss[2][NUM_TEST];
 	uint32_t multi_rw[NUM_TEST - 1][2][NUM_TEST];
+	uint32_t w_ks_r_hit_extbkt[2][NUM_TEST];
 };
 
 static struct rwc_perf rwc_lf_results, rwc_non_lf_results;
@@ -62,11 +69,15 @@ struct {
 	uint32_t *keys_absent;
 	uint32_t *keys_shift_path;
 	uint32_t *keys_non_shift_path;
+	uint32_t *keys_ext_bkt;
+	uint32_t *keys_ks_extbkt;
 	uint32_t count_keys_no_ks;
 	uint32_t count_keys_ks;
 	uint32_t count_keys_absent;
 	uint32_t count_keys_shift_path;
 	uint32_t count_keys_non_shift_path;
+	uint32_t count_keys_extbkt;
+	uint32_t count_keys_ks_extbkt;
 	uint32_t single_insert;
 	struct rte_hash *h;
 } tbl_rwc_test_param;
@@ -81,6 +92,35 @@ uint16_t enabled_core_ids[RTE_MAX_LCORE];
 
 uint8_t *scanned_bkts;
 
+static inline uint16_t
+get_short_sig(const hash_sig_t hash)
+{
+	return hash >> 16;
+}
+
+static inline uint32_t
+get_prim_bucket_index(__attribute__((unused)) const struct rte_hash *h,
+		      const hash_sig_t hash)
+{
+	uint32_t num_buckets;
+	uint32_t bucket_bitmask;
+	num_buckets  = rte_align32pow2(TOTAL_ENTRY) / 8;
+	bucket_bitmask = num_buckets - 1;
+	return hash & bucket_bitmask;
+}
+
+static inline uint32_t
+get_alt_bucket_index(__attribute__((unused)) const struct rte_hash *h,
+			uint32_t cur_bkt_idx, uint16_t sig)
+{
+	uint32_t num_buckets;
+	uint32_t bucket_bitmask;
+	num_buckets  = rte_align32pow2(TOTAL_ENTRY) / 8;
+	bucket_bitmask = num_buckets - 1;
+	return (cur_bkt_idx ^ sig) & bucket_bitmask;
+}
+
+
 static inline int
 get_enabled_cores_list(void)
 {
@@ -168,9 +208,12 @@ generate_keys(void)
 	uint32_t *keys_ks = NULL;
 	uint32_t *keys_absent = NULL;
 	uint32_t *keys_non_shift_path = NULL;
+	uint32_t *keys_ext_bkt = NULL;
+	uint32_t *keys_ks_extbkt = NULL;
 	uint32_t *found = NULL;
 	uint32_t count_keys_no_ks = 0;
 	uint32_t count_keys_ks = 0;
+	uint32_t count_keys_extbkt = 0;
 	uint32_t i;
 
 	/*
@@ -251,14 +294,32 @@ generate_keys(void)
 		goto err;
 	}
 
+	/*
+	 * This consist of keys which will be stored in extended buckets
+	 */
+	keys_ext_bkt = rte_malloc(NULL, sizeof(uint32_t) * TOTAL_INSERT, 0);
+	if (keys_ext_bkt == NULL) {
+		printf("RTE_MALLOC failed\n");
+		goto err;
+	}
+
+	/*
+	 * This consist of keys which when deleted causes shifting of keys
+	 * in extended buckets to respective secondary buckets
+	 */
+	keys_ks_extbkt = rte_malloc(NULL, sizeof(uint32_t) * TOTAL_INSERT, 0);
+	if (keys_ks_extbkt == NULL) {
+		printf("RTE_MALLOC failed\n");
+		goto err;
+	}
 
 	hash_sig_t sig;
 	uint32_t prim_bucket_idx;
-	int ret;
+	uint32_t sec_bucket_idx;
+	uint16_t short_sig;
 	uint32_t num_buckets;
-	uint32_t bucket_bitmask;
 	num_buckets  = rte_align32pow2(TOTAL_ENTRY) / 8;
-	bucket_bitmask = num_buckets - 1;
+	int ret;
 
 	/*
 	 * Used to mark bkts in which at least one key was shifted to its
@@ -275,6 +336,8 @@ generate_keys(void)
 	tbl_rwc_test_param.keys_ks = keys_ks;
 	tbl_rwc_test_param.keys_absent = keys_absent;
 	tbl_rwc_test_param.keys_non_shift_path = keys_non_shift_path;
+	tbl_rwc_test_param.keys_ext_bkt = keys_ext_bkt;
+	tbl_rwc_test_param.keys_ks_extbkt = keys_ks_extbkt;
 	/* Generate keys by adding previous two keys, neglect overflow */
 	printf("Generating keys...\n");
 	keys[0] = 0;
@@ -287,7 +350,8 @@ generate_keys(void)
 		/* Check if primary bucket has space.*/
 		sig = rte_hash_hash(tbl_rwc_test_param.h,
 					tbl_rwc_test_param.keys+i);
-		prim_bucket_idx = sig & bucket_bitmask;
+		prim_bucket_idx = get_prim_bucket_index(tbl_rwc_test_param.h,
+							sig);
 		ret = check_bucket(prim_bucket_idx, keys[i]);
 		if (ret < 0) {
 			/*
@@ -368,6 +432,47 @@ generate_keys(void)
 	tbl_rwc_test_param.count_keys_absent = count_keys_absent;
 	tbl_rwc_test_param.count_keys_non_shift_path = count;
 
+	memset(scanned_bkts, 0, num_buckets);
+	count = 0;
+	/* Find keys that will be in extended buckets */
+	for (i = 0; i < count_keys_ks; i++) {
+		ret = rte_hash_add_key(tbl_rwc_test_param.h, keys_ks + i);
+		if (ret < 0) {
+			/* Key will be added to ext bkt */
+			keys_ext_bkt[count_keys_extbkt++] = keys_ks[i];
+			/* Sec bkt to be added to keys_ks_extbkt */
+			sig = rte_hash_hash(tbl_rwc_test_param.h,
+					tbl_rwc_test_param.keys_ks + i);
+			prim_bucket_idx = get_prim_bucket_index(
+						tbl_rwc_test_param.h, sig);
+			short_sig = get_short_sig(sig);
+			sec_bucket_idx = get_alt_bucket_index(
+						tbl_rwc_test_param.h,
+						prim_bucket_idx, short_sig);
+			if (scanned_bkts[sec_bucket_idx] == 0)
+				scanned_bkts[sec_bucket_idx] = 1;
+		}
+	}
+
+	/* Find keys that will shift keys in ext bucket*/
+	for (i = 0; i < num_buckets; i++) {
+		if (scanned_bkts[i] == 1) {
+			iter = i * 8;
+			while (rte_hash_iterate(tbl_rwc_test_param.h,
+				&next_key, &next_data, &iter) >= 0) {
+				/* Check if key belongs to the current bucket */
+				if (i >= (iter-1)/8)
+					keys_ks_extbkt[count++]
+						= *(const uint32_t *)next_key;
+				else
+					break;
+			}
+		}
+	}
+
+	tbl_rwc_test_param.count_keys_ks_extbkt = count;
+	tbl_rwc_test_param.count_keys_extbkt = count_keys_extbkt;
+
 	printf("\nCount of keys NOT causing shifting of existing keys to "
 	"alternate location: %d\n", tbl_rwc_test_param.count_keys_no_ks);
 	printf("\nCount of keys causing shifting of existing keys to alternate "
@@ -378,6 +483,10 @@ generate_keys(void)
 	       tbl_rwc_test_param.count_keys_shift_path);
 	printf("Count of keys not likely to be on the shift path: %d\n\n",
 	       tbl_rwc_test_param.count_keys_non_shift_path);
+	printf("Count of keys in extended buckets: %d\n\n",
+	       tbl_rwc_test_param.count_keys_extbkt);
+	printf("Count of keys shifting keys in ext buckets: %d\n\n",
+	       tbl_rwc_test_param.count_keys_ks_extbkt);
 
 	rte_free(found);
 	rte_hash_free(tbl_rwc_test_param.h);
@@ -390,12 +499,14 @@ generate_keys(void)
 	rte_free(keys_absent);
 	rte_free(found);
 	rte_free(tbl_rwc_test_param.keys_shift_path);
+	rte_free(keys_ext_bkt);
+	rte_free(keys_ks_extbkt);
 	rte_free(scanned_bkts);
 	return -1;
 }
 
 static int
-init_params(int rwc_lf, int use_jhash, int htm)
+init_params(int rwc_lf, int use_jhash, int htm, int ext_bkt)
 {
 	struct rte_hash *handle;
 
@@ -425,6 +536,9 @@ init_params(int rwc_lf, int use_jhash, int htm)
 			RTE_HASH_EXTRA_FLAGS_RW_CONCURRENCY |
 			RTE_HASH_EXTRA_FLAGS_MULTI_WRITER_ADD;
 
+	if (ext_bkt)
+		hash_params.extra_flag |= RTE_HASH_EXTRA_FLAGS_EXT_TABLE;
+
 	hash_params.name = "tests";
 
 	handle = rte_hash_create(&hash_params);
@@ -452,7 +566,7 @@ test_rwc_reader(__attribute__((unused)) void *arg)
 	void *temp_a[BULK_LOOKUP_SIZE];
 
 	/* Used to identify keys not inserted in the hash table */
-	pos = rte_zmalloc(NULL, sizeof(uint32_t) * BULK_LOOKUP_SIZE, 0);
+	pos = rte_malloc(NULL, sizeof(uint32_t) * BULK_LOOKUP_SIZE, 0);
 	if (pos == NULL) {
 		printf("RTE_MALLOC failed\n");
 		return -1;
@@ -467,6 +581,9 @@ test_rwc_reader(__attribute__((unused)) void *arg)
 	} else if (read_type & READ_PASS_SHIFT_PATH) {
 		keys = tbl_rwc_test_param.keys_shift_path;
 		read_cnt = tbl_rwc_test_param.count_keys_shift_path;
+	} else if (read_type & READ_PASS_KEY_SHIFTS_EXTBKT) {
+		keys = tbl_rwc_test_param.keys_ext_bkt;
+		read_cnt = tbl_rwc_test_param.count_keys_extbkt;
 	} else {
 		keys = tbl_rwc_test_param.keys_non_shift_path;
 		read_cnt = tbl_rwc_test_param.count_keys_non_shift_path;
@@ -482,7 +599,6 @@ test_rwc_reader(__attribute__((unused)) void *arg)
 				/* Array of  pointer to the list of keys */
 				for (j = 0; j < BULK_LOOKUP_SIZE; j++)
 					temp_a[j] = keys + i + j;
-
 				rte_hash_lookup_bulk(tbl_rwc_test_param.h,
 						   (const void **)
 						   ((uintptr_t)temp_a),
@@ -539,22 +655,25 @@ test_rwc_reader(__attribute__((unused)) void *arg)
 }
 
 static int
-write_keys(uint8_t key_shift)
+write_keys(uint8_t write_type)
 {
 	uint32_t i;
 	int ret;
-	uint32_t key_cnt;
+	uint32_t key_cnt = 0;
 	uint32_t *keys;
-	if (key_shift) {
+	if (write_type == WRITE_KEY_SHIFT) {
 		key_cnt = tbl_rwc_test_param.count_keys_ks;
 		keys = tbl_rwc_test_param.keys_ks;
-	} else {
+	} else if (write_type == WRITE_NO_KEY_SHIFT) {
 		key_cnt = tbl_rwc_test_param.count_keys_no_ks;
 		keys = tbl_rwc_test_param.keys_no_ks;
+	} else if (write_type == WRITE_EXT_BKT) {
+		key_cnt = tbl_rwc_test_param.count_keys_extbkt;
+		keys = tbl_rwc_test_param.keys_ext_bkt;
 	}
 	for (i = 0; i < key_cnt; i++) {
 		ret = rte_hash_add_key(tbl_rwc_test_param.h, keys + i);
-		if (!key_shift && ret < 0) {
+		if ((write_type == WRITE_NO_KEY_SHIFT) && ret < 0) {
 			printf("writer failed %"PRIu32"\n", i);
 			return -1;
 		}
@@ -581,18 +700,18 @@ test_rwc_multi_writer(__attribute__((unused)) void *arg)
  */
 static int
 test_hash_add_no_ks_lookup_hit(struct rwc_perf *rwc_perf_results, int rwc_lf,
-				int htm)
+				int htm, int ext_bkt)
 {
 	unsigned int n, m;
 	uint64_t i;
 	int use_jhash = 0;
-	uint8_t key_shift = 0;
+	uint8_t write_type = WRITE_NO_KEY_SHIFT;
 	uint8_t read_type = READ_PASS_NO_KEY_SHIFTS;
 
 	rte_atomic64_init(&greads);
 	rte_atomic64_init(&gread_cycles);
 
-	if (init_params(rwc_lf, use_jhash, htm) != 0)
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
 		goto err;
 	printf("\nTest: Hash add - no key-shifts, read - hit\n");
 	for (m = 0; m < 2; m++) {
@@ -612,7 +731,7 @@ test_hash_add_no_ks_lookup_hit(struct rwc_perf *rwc_perf_results, int rwc_lf,
 
 			rte_hash_reset(tbl_rwc_test_param.h);
 			writer_done = 0;
-			if (write_keys(key_shift) < 0)
+			if (write_keys(write_type) < 0)
 				goto err;
 			writer_done = 1;
 			for (i = 1; i <= rwc_core_cnt[n]; i++)
@@ -650,19 +769,19 @@ test_hash_add_no_ks_lookup_hit(struct rwc_perf *rwc_perf_results, int rwc_lf,
  */
 static int
 test_hash_add_no_ks_lookup_miss(struct rwc_perf *rwc_perf_results, int rwc_lf,
-				int htm)
+				int htm, int ext_bkt)
 {
 	unsigned int n, m;
 	uint64_t i;
 	int use_jhash = 0;
-	uint8_t key_shift = 0;
+	uint8_t write_type = WRITE_NO_KEY_SHIFT;
 	uint8_t read_type = READ_FAIL;
 	int ret;
 
 	rte_atomic64_init(&greads);
 	rte_atomic64_init(&gread_cycles);
 
-	if (init_params(rwc_lf, use_jhash, htm) != 0)
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
 		goto err;
 	printf("\nTest: Hash add - no key-shifts, Hash lookup - miss\n");
 	for (m = 0; m < 2; m++) {
@@ -687,7 +806,7 @@ test_hash_add_no_ks_lookup_miss(struct rwc_perf *rwc_perf_results, int rwc_lf,
 				rte_eal_remote_launch(test_rwc_reader,
 						(void *)(uintptr_t)read_type,
 							enabled_core_ids[i]);
-			ret = write_keys(key_shift);
+			ret = write_keys(write_type);
 			writer_done = 1;
 			rte_eal_mp_wait_lcore();
 
@@ -722,19 +841,19 @@ test_hash_add_no_ks_lookup_miss(struct rwc_perf *rwc_perf_results, int rwc_lf,
  */
 static int
 test_hash_add_ks_lookup_hit_non_sp(struct rwc_perf *rwc_perf_results,
-				    int rwc_lf, int htm)
+				    int rwc_lf, int htm, int ext_bkt)
 {
 	unsigned int n, m;
 	uint64_t i;
 	int use_jhash = 0;
 	int ret;
-	uint8_t key_shift;
+	uint8_t write_type;
 	uint8_t read_type = READ_PASS_NON_SHIFT_PATH;
 
 	rte_atomic64_init(&greads);
 	rte_atomic64_init(&gread_cycles);
 
-	if (init_params(rwc_lf, use_jhash, htm) != 0)
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
 		goto err;
 	printf("\nTest: Hash add - key shift, Hash lookup - hit"
 	       " (non-shift-path)\n");
@@ -755,15 +874,15 @@ test_hash_add_ks_lookup_hit_non_sp(struct rwc_perf *rwc_perf_results,
 
 			rte_hash_reset(tbl_rwc_test_param.h);
 			writer_done = 0;
-			key_shift = 0;
-			if (write_keys(key_shift) < 0)
+			write_type = WRITE_NO_KEY_SHIFT;
+			if (write_keys(write_type) < 0)
 				goto err;
 			for (i = 1; i <= rwc_core_cnt[n]; i++)
 				rte_eal_remote_launch(test_rwc_reader,
 						(void *)(uintptr_t)read_type,
 							enabled_core_ids[i]);
-			key_shift = 1;
-			ret = write_keys(key_shift);
+			write_type = WRITE_KEY_SHIFT;
+			ret = write_keys(write_type);
 			writer_done = 1;
 			rte_eal_mp_wait_lcore();
 
@@ -798,19 +917,19 @@ test_hash_add_ks_lookup_hit_non_sp(struct rwc_perf *rwc_perf_results,
  */
 static int
 test_hash_add_ks_lookup_hit_sp(struct rwc_perf *rwc_perf_results, int rwc_lf,
-				int htm)
+				int htm, int ext_bkt)
 {
 	unsigned int n, m;
 	uint64_t i;
 	int use_jhash = 0;
 	int ret;
-	uint8_t key_shift;
+	uint8_t write_type;
 	uint8_t read_type = READ_PASS_SHIFT_PATH;
 
 	rte_atomic64_init(&greads);
 	rte_atomic64_init(&gread_cycles);
 
-	if (init_params(rwc_lf, use_jhash, htm) != 0)
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
 		goto err;
 	printf("\nTest: Hash add - key shift, Hash lookup - hit (shift-path)"
 	       "\n");
@@ -831,15 +950,15 @@ test_hash_add_ks_lookup_hit_sp(struct rwc_perf *rwc_perf_results, int rwc_lf,
 
 			rte_hash_reset(tbl_rwc_test_param.h);
 			writer_done = 0;
-			key_shift = 0;
-			if (write_keys(key_shift) < 0)
+			write_type = WRITE_NO_KEY_SHIFT;
+			if (write_keys(write_type) < 0)
 				goto err;
 			for (i = 1; i <= rwc_core_cnt[n]; i++)
 				rte_eal_remote_launch(test_rwc_reader,
 						(void *)(uintptr_t)read_type,
 						enabled_core_ids[i]);
-			key_shift = 1;
-			ret = write_keys(key_shift);
+			write_type = WRITE_KEY_SHIFT;
+			ret = write_keys(write_type);
 			writer_done = 1;
 			rte_eal_mp_wait_lcore();
 
@@ -874,19 +993,19 @@ test_hash_add_ks_lookup_hit_sp(struct rwc_perf *rwc_perf_results, int rwc_lf,
  */
 static int
 test_hash_add_ks_lookup_miss(struct rwc_perf *rwc_perf_results, int rwc_lf, int
-			     htm)
+			     htm, int ext_bkt)
 {
 	unsigned int n, m;
 	uint64_t i;
 	int use_jhash = 0;
 	int ret;
-	uint8_t key_shift;
+	uint8_t write_type;
 	uint8_t read_type = READ_FAIL;
 
 	rte_atomic64_init(&greads);
 	rte_atomic64_init(&gread_cycles);
 
-	if (init_params(rwc_lf, use_jhash, htm) != 0)
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
 		goto err;
 	printf("\nTest: Hash add - key shift, Hash lookup - miss\n");
 	for (m = 0; m < 2; m++) {
@@ -906,15 +1025,15 @@ test_hash_add_ks_lookup_miss(struct rwc_perf *rwc_perf_results, int rwc_lf, int
 
 			rte_hash_reset(tbl_rwc_test_param.h);
 			writer_done = 0;
-			key_shift = 0;
-			if (write_keys(key_shift) < 0)
+			write_type = WRITE_NO_KEY_SHIFT;
+			if (write_keys(write_type) < 0)
 				goto err;
 			for (i = 1; i <= rwc_core_cnt[n]; i++)
 				rte_eal_remote_launch(test_rwc_reader,
 						(void *)(uintptr_t)read_type,
 							enabled_core_ids[i]);
-			key_shift = 1;
-			ret = write_keys(key_shift);
+			write_type = WRITE_KEY_SHIFT;
+			ret = write_keys(write_type);
 			writer_done = 1;
 			rte_eal_mp_wait_lcore();
 
@@ -949,18 +1068,18 @@ test_hash_add_ks_lookup_miss(struct rwc_perf *rwc_perf_results, int rwc_lf, int
  */
 static int
 test_hash_multi_add_lookup(struct rwc_perf *rwc_perf_results, int rwc_lf,
-			   int htm)
+			   int htm, int ext_bkt)
 {
 	unsigned int n, m, k;
 	uint64_t i;
 	int use_jhash = 0;
-	uint8_t key_shift;
+	uint8_t write_type;
 	uint8_t read_type = READ_PASS_SHIFT_PATH;
 
 	rte_atomic64_init(&greads);
 	rte_atomic64_init(&gread_cycles);
 
-	if (init_params(rwc_lf, use_jhash, htm) != 0)
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
 		goto err;
 	printf("\nTest: Multi-add-lookup\n");
 	uint8_t pos_core;
@@ -991,8 +1110,8 @@ test_hash_multi_add_lookup(struct rwc_perf *rwc_perf_results, int rwc_lf,
 				writer_done = 0;
 				for (i = 0; i < 4; i++)
 					multi_writer_done[i] = 0;
-				key_shift = 0;
-				if (write_keys(key_shift) < 0)
+				write_type = WRITE_NO_KEY_SHIFT;
+				if (write_keys(write_type) < 0)
 					goto err;
 
 				/* Launch reader(s) */
@@ -1000,7 +1119,7 @@ test_hash_multi_add_lookup(struct rwc_perf *rwc_perf_results, int rwc_lf,
 					rte_eal_remote_launch(test_rwc_reader,
 						(void *)(uintptr_t)read_type,
 						enabled_core_ids[i]);
-				key_shift = 1;
+				write_type = WRITE_KEY_SHIFT;
 				pos_core = 0;
 
 				/* Launch writers */
@@ -1045,6 +1164,88 @@ test_hash_multi_add_lookup(struct rwc_perf *rwc_perf_results, int rwc_lf,
 	return -1;
 }
 
+/*
+ * Test lookup perf:
+ * Reader(s) lookup keys present in the extendable bkt.
+ */
+static int
+test_hash_add_ks_lookup_hit_extbkt(struct rwc_perf *rwc_perf_results,
+				int rwc_lf, int htm, int ext_bkt)
+{
+	unsigned int n, m;
+	uint64_t i;
+	int use_jhash = 0;
+	uint8_t write_type;
+	uint8_t read_type = READ_PASS_KEY_SHIFTS_EXTBKT;
+
+	rte_atomic64_init(&greads);
+	rte_atomic64_init(&gread_cycles);
+
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
+		goto err;
+	printf("\nTest: Hash add - key-shifts, read - hit (ext_bkt)\n");
+	for (m = 0; m < 2; m++) {
+		if (m == 1) {
+			printf("\n** With bulk-lookup **\n");
+			read_type |= BULK_LOOKUP;
+		}
+		for (n = 0; n < NUM_TEST; n++) {
+			unsigned int tot_lcore = rte_lcore_count();
+			if (tot_lcore < rwc_core_cnt[n] + 1)
+				goto finish;
+
+			printf("\nNumber of readers: %u\n", rwc_core_cnt[n]);
+
+			rte_atomic64_clear(&greads);
+			rte_atomic64_clear(&gread_cycles);
+
+			rte_hash_reset(tbl_rwc_test_param.h);
+			write_type = WRITE_NO_KEY_SHIFT;
+			if (write_keys(write_type) < 0)
+				goto err;
+			write_type = WRITE_KEY_SHIFT;
+			if (write_keys(write_type) < 0)
+				goto err;
+			writer_done = 0;
+			for (i = 1; i <= rwc_core_cnt[n]; i++)
+				rte_eal_remote_launch(test_rwc_reader,
+						(void *)(uintptr_t)read_type,
+							enabled_core_ids[i]);
+			for (i = 0; i < tbl_rwc_test_param.count_keys_ks_extbkt;
+			     i++) {
+				if (rte_hash_del_key(tbl_rwc_test_param.h,
+					tbl_rwc_test_param.keys_ks_extbkt + i)
+							< 0) {
+					printf("Delete Failed: %u\n",
+					tbl_rwc_test_param.keys_ks_extbkt[i]);
+					goto err;
+				}
+			}
+			writer_done = 1;
+			rte_eal_mp_wait_lcore();
+
+			for (i = 1; i <= rwc_core_cnt[n]; i++)
+				if (lcore_config[i].ret < 0)
+					goto err;
+
+			unsigned long long cycles_per_lookup =
+				rte_atomic64_read(&gread_cycles) /
+				rte_atomic64_read(&greads);
+			rwc_perf_results->w_ks_r_hit_extbkt[m][n]
+						= cycles_per_lookup;
+			printf("Cycles per lookup: %llu\n", cycles_per_lookup);
+		}
+	}
+
+finish:
+	rte_hash_free(tbl_rwc_test_param.h);
+	return 0;
+
+err:
+	rte_hash_free(tbl_rwc_test_param.h);
+	return -1;
+}
+
 static int
 test_hash_readwrite_lf_main(void)
 {
@@ -1057,6 +1258,7 @@ test_hash_readwrite_lf_main(void)
 	int rwc_lf = 0;
 	int htm;
 	int use_jhash = 0;
+	int ext_bkt = 0;
 	if (rte_lcore_count() == 1) {
 		printf("More than one lcore is required "
 			"to do read write lock-free concurrency test\n");
@@ -1070,7 +1272,7 @@ test_hash_readwrite_lf_main(void)
 	else
 		htm = 0;
 
-	if (init_params(rwc_lf, use_jhash, htm) != 0)
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
 		return -1;
 	if (generate_keys() != 0)
 		return -1;
@@ -1079,25 +1281,29 @@ test_hash_readwrite_lf_main(void)
 
 	if (RTE_HASH_EXTRA_FLAGS_RW_CONCURRENCY_LF) {
 		rwc_lf = 1;
+		ext_bkt = 1;
 		printf("Test lookup with read-write concurrency lock free support"
 		       " enabled\n");
 		if (test_hash_add_no_ks_lookup_hit(&rwc_lf_results, rwc_lf,
-							htm) < 0)
+							htm, ext_bkt) < 0)
 			return -1;
 		if (test_hash_add_no_ks_lookup_miss(&rwc_lf_results, rwc_lf,
-							htm) < 0)
+							htm, ext_bkt) < 0)
 			return -1;
 		if (test_hash_add_ks_lookup_hit_non_sp(&rwc_lf_results, rwc_lf,
-							htm) < 0)
+							htm, ext_bkt) < 0)
 			return -1;
 		if (test_hash_add_ks_lookup_hit_sp(&rwc_lf_results, rwc_lf,
-							htm) < 0)
+							htm, ext_bkt) < 0)
 			return -1;
-		if (test_hash_add_ks_lookup_miss(&rwc_lf_results, rwc_lf, htm)
-							< 0)
+		if (test_hash_add_ks_lookup_miss(&rwc_lf_results, rwc_lf, htm,
+						 ext_bkt) < 0)
 			return -1;
-		if (test_hash_multi_add_lookup(&rwc_lf_results, rwc_lf, htm)
-							< 0)
+		if (test_hash_multi_add_lookup(&rwc_lf_results, rwc_lf, htm,
+					       ext_bkt) < 0)
+			return -1;
+		if (test_hash_add_ks_lookup_hit_extbkt(&rwc_lf_results, rwc_lf,
+							htm, ext_bkt) < 0)
 			return -1;
 	}
 	printf("\nTest lookup with read-write concurrency lock free support"
@@ -1112,21 +1318,26 @@ test_hash_readwrite_lf_main(void)
 		}
 	} else
 		printf("With HTM Enabled\n");
-	if (test_hash_add_no_ks_lookup_hit(&rwc_non_lf_results, rwc_lf, htm)
-						< 0)
+	if (test_hash_add_no_ks_lookup_hit(&rwc_non_lf_results, rwc_lf, htm,
+					   ext_bkt) < 0)
 		return -1;
-	if (test_hash_add_no_ks_lookup_miss(&rwc_non_lf_results, rwc_lf, htm)
-						< 0)
+	if (test_hash_add_no_ks_lookup_miss(&rwc_non_lf_results, rwc_lf, htm,
+						ext_bkt) < 0)
 		return -1;
 	if (test_hash_add_ks_lookup_hit_non_sp(&rwc_non_lf_results, rwc_lf,
-						htm) < 0)
+						htm, ext_bkt) < 0)
+		return -1;
+	if (test_hash_add_ks_lookup_hit_sp(&rwc_non_lf_results, rwc_lf, htm,
+						ext_bkt) < 0)
 		return -1;
-	if (test_hash_add_ks_lookup_hit_sp(&rwc_non_lf_results, rwc_lf, htm)
-						< 0)
+	if (test_hash_add_ks_lookup_miss(&rwc_non_lf_results, rwc_lf, htm,
+					 ext_bkt) < 0)
 		return -1;
-	if (test_hash_add_ks_lookup_miss(&rwc_non_lf_results, rwc_lf, htm) < 0)
+	if (test_hash_multi_add_lookup(&rwc_non_lf_results, rwc_lf, htm,
+							ext_bkt) < 0)
 		return -1;
-	if (test_hash_multi_add_lookup(&rwc_non_lf_results, rwc_lf, htm) < 0)
+	if (test_hash_add_ks_lookup_hit_extbkt(&rwc_non_lf_results, rwc_lf,
+						htm, ext_bkt) < 0)
 		return -1;
 results:
 	printf("\n\t\t\t\t\t\t********** Results summary **********\n\n");
@@ -1158,8 +1369,11 @@ test_hash_readwrite_lf_main(void)
 			       "(shift-path)\t\t%u\n\t\t\t\t\t\t\t\t",
 			       rwc_lf_results.w_ks_r_hit_sp[j][i]);
 			printf("Hash add - key-shifts, Hash lookup miss\t\t\t\t"
-				"%u\n\n\t\t\t\t",
+				"%u\n\t\t\t\t\t\t\t\t",
 				rwc_lf_results.w_ks_r_miss[j][i]);
+			printf("Hash add - key-shifts, Hash lookup hit (ext_bkt)\t\t"
+				"%u\n\n\t\t\t\t",
+				rwc_lf_results.w_ks_r_hit_extbkt[j][i]);
 
 			printf("Disabled\t");
 			if (htm)
@@ -1179,7 +1393,11 @@ test_hash_readwrite_lf_main(void)
 			       "(shift-path)\t\t%u\n\t\t\t\t\t\t\t\t",
 			       rwc_non_lf_results.w_ks_r_hit_sp[j][i]);
 			printf("Hash add - key-shifts, Hash lookup miss\t\t\t\t"
-			       "%u\n", rwc_non_lf_results.w_ks_r_miss[j][i]);
+			       "%u\n\t\t\t\t\t\t\t\t",
+			       rwc_non_lf_results.w_ks_r_miss[j][i]);
+			printf("Hash add - key-shifts, Hash lookup hit (ext_bkt)\t\t"
+				"%u\n",
+				rwc_non_lf_results.w_ks_r_hit_extbkt[j][i]);
 
 			printf("_______\t\t_______\t\t_________\t___\t\t"
 			       "_________\t\t\t\t\t\t_________________\n");
-- 
2.17.1

[dpdk-dev] [PATCH v5 2/2] test/hash: lock-free rw concurrency test ext bkt

[Dharmik Thakkar]

Add unit test to check for hash lookup and bulk-lookup perf for
extendable bucket feature.
It is tested with both lock-free enabled and lock-free disabled case.

Test includes:

- hash lookup on keys in ext bkt
- hash delete causing key-shifts of keys from ext bkt to secondary bkt

Suggested-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
Signed-off-by: Dharmik Thakkar <dharmik.thakkar@arm.com>
Acked-by: Yipeng Wang <yipeng1.wang@intel.com>
---
 app/test/test_hash_readwrite_lf.c | 352 ++++++++++++++++++++++++------
 1 file changed, 285 insertions(+), 67 deletions(-)

diff --git a/app/test/test_hash_readwrite_lf.c b/app/test/test_hash_readwrite_lf.c
index cbfd9322696b..4ab4c8ee64cf 100644
--- a/app/test/test_hash_readwrite_lf.c
+++ b/app/test/test_hash_readwrite_lf.c
@@ -41,6 +41,12 @@
 #define READ_PASS_SHIFT_PATH 4
 #define READ_PASS_NON_SHIFT_PATH 8
 #define BULK_LOOKUP 16
+#define READ_PASS_KEY_SHIFTS_EXTBKT 32
+
+#define WRITE_NO_KEY_SHIFT 0
+#define WRITE_KEY_SHIFT 1
+#define WRITE_EXT_BKT 2
+
 #define NUM_TEST 3
 unsigned int rwc_core_cnt[NUM_TEST] = {1, 2, 4};
 
@@ -51,6 +57,7 @@ struct rwc_perf {
 	uint32_t w_ks_r_hit_sp[2][NUM_TEST];
 	uint32_t w_ks_r_miss[2][NUM_TEST];
 	uint32_t multi_rw[NUM_TEST - 1][2][NUM_TEST];
+	uint32_t w_ks_r_hit_extbkt[2][NUM_TEST];
 };
 
 static struct rwc_perf rwc_lf_results, rwc_non_lf_results;
@@ -62,11 +69,15 @@ struct {
 	uint32_t *keys_absent;
 	uint32_t *keys_shift_path;
 	uint32_t *keys_non_shift_path;
+	uint32_t *keys_ext_bkt;
+	uint32_t *keys_ks_extbkt;
 	uint32_t count_keys_no_ks;
 	uint32_t count_keys_ks;
 	uint32_t count_keys_absent;
 	uint32_t count_keys_shift_path;
 	uint32_t count_keys_non_shift_path;
+	uint32_t count_keys_extbkt;
+	uint32_t count_keys_ks_extbkt;
 	uint32_t single_insert;
 	struct rte_hash *h;
 } tbl_rwc_test_param;
@@ -81,6 +92,35 @@ uint16_t enabled_core_ids[RTE_MAX_LCORE];
 
 uint8_t *scanned_bkts;
 
+static inline uint16_t
+get_short_sig(const hash_sig_t hash)
+{
+	return hash >> 16;
+}
+
+static inline uint32_t
+get_prim_bucket_index(__attribute__((unused)) const struct rte_hash *h,
+		      const hash_sig_t hash)
+{
+	uint32_t num_buckets;
+	uint32_t bucket_bitmask;
+	num_buckets  = rte_align32pow2(TOTAL_ENTRY) / 8;
+	bucket_bitmask = num_buckets - 1;
+	return hash & bucket_bitmask;
+}
+
+static inline uint32_t
+get_alt_bucket_index(__attribute__((unused)) const struct rte_hash *h,
+			uint32_t cur_bkt_idx, uint16_t sig)
+{
+	uint32_t num_buckets;
+	uint32_t bucket_bitmask;
+	num_buckets  = rte_align32pow2(TOTAL_ENTRY) / 8;
+	bucket_bitmask = num_buckets - 1;
+	return (cur_bkt_idx ^ sig) & bucket_bitmask;
+}
+
+
 static inline int
 get_enabled_cores_list(void)
 {
@@ -168,9 +208,12 @@ generate_keys(void)
 	uint32_t *keys_ks = NULL;
 	uint32_t *keys_absent = NULL;
 	uint32_t *keys_non_shift_path = NULL;
+	uint32_t *keys_ext_bkt = NULL;
+	uint32_t *keys_ks_extbkt = NULL;
 	uint32_t *found = NULL;
 	uint32_t count_keys_no_ks = 0;
 	uint32_t count_keys_ks = 0;
+	uint32_t count_keys_extbkt = 0;
 	uint32_t i;
 
 	/*
@@ -251,14 +294,32 @@ generate_keys(void)
 		goto err;
 	}
 
+	/*
+	 * This consist of keys which will be stored in extended buckets
+	 */
+	keys_ext_bkt = rte_malloc(NULL, sizeof(uint32_t) * TOTAL_INSERT, 0);
+	if (keys_ext_bkt == NULL) {
+		printf("RTE_MALLOC failed\n");
+		goto err;
+	}
+
+	/*
+	 * This consist of keys which when deleted causes shifting of keys
+	 * in extended buckets to respective secondary buckets
+	 */
+	keys_ks_extbkt = rte_malloc(NULL, sizeof(uint32_t) * TOTAL_INSERT, 0);
+	if (keys_ks_extbkt == NULL) {
+		printf("RTE_MALLOC failed\n");
+		goto err;
+	}
 
 	hash_sig_t sig;
 	uint32_t prim_bucket_idx;
-	int ret;
+	uint32_t sec_bucket_idx;
+	uint16_t short_sig;
 	uint32_t num_buckets;
-	uint32_t bucket_bitmask;
 	num_buckets  = rte_align32pow2(TOTAL_ENTRY) / 8;
-	bucket_bitmask = num_buckets - 1;
+	int ret;
 
 	/*
 	 * Used to mark bkts in which at least one key was shifted to its
@@ -275,6 +336,8 @@ generate_keys(void)
 	tbl_rwc_test_param.keys_ks = keys_ks;
 	tbl_rwc_test_param.keys_absent = keys_absent;
 	tbl_rwc_test_param.keys_non_shift_path = keys_non_shift_path;
+	tbl_rwc_test_param.keys_ext_bkt = keys_ext_bkt;
+	tbl_rwc_test_param.keys_ks_extbkt = keys_ks_extbkt;
 	/* Generate keys by adding previous two keys, neglect overflow */
 	printf("Generating keys...\n");
 	keys[0] = 0;
@@ -287,7 +350,8 @@ generate_keys(void)
 		/* Check if primary bucket has space.*/
 		sig = rte_hash_hash(tbl_rwc_test_param.h,
 					tbl_rwc_test_param.keys+i);
-		prim_bucket_idx = sig & bucket_bitmask;
+		prim_bucket_idx = get_prim_bucket_index(tbl_rwc_test_param.h,
+							sig);
 		ret = check_bucket(prim_bucket_idx, keys[i]);
 		if (ret < 0) {
 			/*
@@ -368,6 +432,47 @@ generate_keys(void)
 	tbl_rwc_test_param.count_keys_absent = count_keys_absent;
 	tbl_rwc_test_param.count_keys_non_shift_path = count;
 
+	memset(scanned_bkts, 0, num_buckets);
+	count = 0;
+	/* Find keys that will be in extended buckets */
+	for (i = 0; i < count_keys_ks; i++) {
+		ret = rte_hash_add_key(tbl_rwc_test_param.h, keys_ks + i);
+		if (ret < 0) {
+			/* Key will be added to ext bkt */
+			keys_ext_bkt[count_keys_extbkt++] = keys_ks[i];
+			/* Sec bkt to be added to keys_ks_extbkt */
+			sig = rte_hash_hash(tbl_rwc_test_param.h,
+					tbl_rwc_test_param.keys_ks + i);
+			prim_bucket_idx = get_prim_bucket_index(
+						tbl_rwc_test_param.h, sig);
+			short_sig = get_short_sig(sig);
+			sec_bucket_idx = get_alt_bucket_index(
+						tbl_rwc_test_param.h,
+						prim_bucket_idx, short_sig);
+			if (scanned_bkts[sec_bucket_idx] == 0)
+				scanned_bkts[sec_bucket_idx] = 1;
+		}
+	}
+
+	/* Find keys that will shift keys in ext bucket*/
+	for (i = 0; i < num_buckets; i++) {
+		if (scanned_bkts[i] == 1) {
+			iter = i * 8;
+			while (rte_hash_iterate(tbl_rwc_test_param.h,
+				&next_key, &next_data, &iter) >= 0) {
+				/* Check if key belongs to the current bucket */
+				if (i >= (iter-1)/8)
+					keys_ks_extbkt[count++]
+						= *(const uint32_t *)next_key;
+				else
+					break;
+			}
+		}
+	}
+
+	tbl_rwc_test_param.count_keys_ks_extbkt = count;
+	tbl_rwc_test_param.count_keys_extbkt = count_keys_extbkt;
+
 	printf("\nCount of keys NOT causing shifting of existing keys to "
 	"alternate location: %d\n", tbl_rwc_test_param.count_keys_no_ks);
 	printf("\nCount of keys causing shifting of existing keys to alternate "
@@ -378,6 +483,10 @@ generate_keys(void)
 	       tbl_rwc_test_param.count_keys_shift_path);
 	printf("Count of keys not likely to be on the shift path: %d\n\n",
 	       tbl_rwc_test_param.count_keys_non_shift_path);
+	printf("Count of keys in extended buckets: %d\n\n",
+	       tbl_rwc_test_param.count_keys_extbkt);
+	printf("Count of keys shifting keys in ext buckets: %d\n\n",
+	       tbl_rwc_test_param.count_keys_ks_extbkt);
 
 	rte_free(found);
 	rte_hash_free(tbl_rwc_test_param.h);
@@ -390,12 +499,14 @@ generate_keys(void)
 	rte_free(keys_absent);
 	rte_free(found);
 	rte_free(tbl_rwc_test_param.keys_shift_path);
+	rte_free(keys_ext_bkt);
+	rte_free(keys_ks_extbkt);
 	rte_free(scanned_bkts);
 	return -1;
 }
 
 static int
-init_params(int rwc_lf, int use_jhash, int htm)
+init_params(int rwc_lf, int use_jhash, int htm, int ext_bkt)
 {
 	struct rte_hash *handle;
 
@@ -425,6 +536,9 @@ init_params(int rwc_lf, int use_jhash, int htm)
 			RTE_HASH_EXTRA_FLAGS_RW_CONCURRENCY |
 			RTE_HASH_EXTRA_FLAGS_MULTI_WRITER_ADD;
 
+	if (ext_bkt)
+		hash_params.extra_flag |= RTE_HASH_EXTRA_FLAGS_EXT_TABLE;
+
 	hash_params.name = "tests";
 
 	handle = rte_hash_create(&hash_params);
@@ -452,7 +566,7 @@ test_rwc_reader(__attribute__((unused)) void *arg)
 	void *temp_a[BULK_LOOKUP_SIZE];
 
 	/* Used to identify keys not inserted in the hash table */
-	pos = rte_zmalloc(NULL, sizeof(uint32_t) * BULK_LOOKUP_SIZE, 0);
+	pos = rte_malloc(NULL, sizeof(uint32_t) * BULK_LOOKUP_SIZE, 0);
 	if (pos == NULL) {
 		printf("RTE_MALLOC failed\n");
 		return -1;
@@ -467,6 +581,9 @@ test_rwc_reader(__attribute__((unused)) void *arg)
 	} else if (read_type & READ_PASS_SHIFT_PATH) {
 		keys = tbl_rwc_test_param.keys_shift_path;
 		read_cnt = tbl_rwc_test_param.count_keys_shift_path;
+	} else if (read_type & READ_PASS_KEY_SHIFTS_EXTBKT) {
+		keys = tbl_rwc_test_param.keys_ext_bkt;
+		read_cnt = tbl_rwc_test_param.count_keys_extbkt;
 	} else {
 		keys = tbl_rwc_test_param.keys_non_shift_path;
 		read_cnt = tbl_rwc_test_param.count_keys_non_shift_path;
@@ -482,7 +599,6 @@ test_rwc_reader(__attribute__((unused)) void *arg)
 				/* Array of  pointer to the list of keys */
 				for (j = 0; j < BULK_LOOKUP_SIZE; j++)
 					temp_a[j] = keys + i + j;
-
 				rte_hash_lookup_bulk(tbl_rwc_test_param.h,
 						   (const void **)
 						   ((uintptr_t)temp_a),
@@ -539,22 +655,25 @@ test_rwc_reader(__attribute__((unused)) void *arg)
 }
 
 static int
-write_keys(uint8_t key_shift)
+write_keys(uint8_t write_type)
 {
 	uint32_t i;
 	int ret;
-	uint32_t key_cnt;
+	uint32_t key_cnt = 0;
 	uint32_t *keys;
-	if (key_shift) {
+	if (write_type == WRITE_KEY_SHIFT) {
 		key_cnt = tbl_rwc_test_param.count_keys_ks;
 		keys = tbl_rwc_test_param.keys_ks;
-	} else {
+	} else if (write_type == WRITE_NO_KEY_SHIFT) {
 		key_cnt = tbl_rwc_test_param.count_keys_no_ks;
 		keys = tbl_rwc_test_param.keys_no_ks;
+	} else if (write_type == WRITE_EXT_BKT) {
+		key_cnt = tbl_rwc_test_param.count_keys_extbkt;
+		keys = tbl_rwc_test_param.keys_ext_bkt;
 	}
 	for (i = 0; i < key_cnt; i++) {
 		ret = rte_hash_add_key(tbl_rwc_test_param.h, keys + i);
-		if (!key_shift && ret < 0) {
+		if ((write_type == WRITE_NO_KEY_SHIFT) && ret < 0) {
 			printf("writer failed %"PRIu32"\n", i);
 			return -1;
 		}
@@ -581,18 +700,18 @@ test_rwc_multi_writer(__attribute__((unused)) void *arg)
  */
 static int
 test_hash_add_no_ks_lookup_hit(struct rwc_perf *rwc_perf_results, int rwc_lf,
-				int htm)
+				int htm, int ext_bkt)
 {
 	unsigned int n, m;
 	uint64_t i;
 	int use_jhash = 0;
-	uint8_t key_shift = 0;
+	uint8_t write_type = WRITE_NO_KEY_SHIFT;
 	uint8_t read_type = READ_PASS_NO_KEY_SHIFTS;
 
 	rte_atomic64_init(&greads);
 	rte_atomic64_init(&gread_cycles);
 
-	if (init_params(rwc_lf, use_jhash, htm) != 0)
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
 		goto err;
 	printf("\nTest: Hash add - no key-shifts, read - hit\n");
 	for (m = 0; m < 2; m++) {
@@ -612,7 +731,7 @@ test_hash_add_no_ks_lookup_hit(struct rwc_perf *rwc_perf_results, int rwc_lf,
 
 			rte_hash_reset(tbl_rwc_test_param.h);
 			writer_done = 0;
-			if (write_keys(key_shift) < 0)
+			if (write_keys(write_type) < 0)
 				goto err;
 			writer_done = 1;
 			for (i = 1; i <= rwc_core_cnt[n]; i++)
@@ -650,19 +769,19 @@ test_hash_add_no_ks_lookup_hit(struct rwc_perf *rwc_perf_results, int rwc_lf,
  */
 static int
 test_hash_add_no_ks_lookup_miss(struct rwc_perf *rwc_perf_results, int rwc_lf,
-				int htm)
+				int htm, int ext_bkt)
 {
 	unsigned int n, m;
 	uint64_t i;
 	int use_jhash = 0;
-	uint8_t key_shift = 0;
+	uint8_t write_type = WRITE_NO_KEY_SHIFT;
 	uint8_t read_type = READ_FAIL;
 	int ret;
 
 	rte_atomic64_init(&greads);
 	rte_atomic64_init(&gread_cycles);
 
-	if (init_params(rwc_lf, use_jhash, htm) != 0)
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
 		goto err;
 	printf("\nTest: Hash add - no key-shifts, Hash lookup - miss\n");
 	for (m = 0; m < 2; m++) {
@@ -687,7 +806,7 @@ test_hash_add_no_ks_lookup_miss(struct rwc_perf *rwc_perf_results, int rwc_lf,
 				rte_eal_remote_launch(test_rwc_reader,
 						(void *)(uintptr_t)read_type,
 							enabled_core_ids[i]);
-			ret = write_keys(key_shift);
+			ret = write_keys(write_type);
 			writer_done = 1;
 			rte_eal_mp_wait_lcore();
 
@@ -722,19 +841,19 @@ test_hash_add_no_ks_lookup_miss(struct rwc_perf *rwc_perf_results, int rwc_lf,
  */
 static int
 test_hash_add_ks_lookup_hit_non_sp(struct rwc_perf *rwc_perf_results,
-				    int rwc_lf, int htm)
+				    int rwc_lf, int htm, int ext_bkt)
 {
 	unsigned int n, m;
 	uint64_t i;
 	int use_jhash = 0;
 	int ret;
-	uint8_t key_shift;
+	uint8_t write_type;
 	uint8_t read_type = READ_PASS_NON_SHIFT_PATH;
 
 	rte_atomic64_init(&greads);
 	rte_atomic64_init(&gread_cycles);
 
-	if (init_params(rwc_lf, use_jhash, htm) != 0)
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
 		goto err;
 	printf("\nTest: Hash add - key shift, Hash lookup - hit"
 	       " (non-shift-path)\n");
@@ -755,15 +874,15 @@ test_hash_add_ks_lookup_hit_non_sp(struct rwc_perf *rwc_perf_results,
 
 			rte_hash_reset(tbl_rwc_test_param.h);
 			writer_done = 0;
-			key_shift = 0;
-			if (write_keys(key_shift) < 0)
+			write_type = WRITE_NO_KEY_SHIFT;
+			if (write_keys(write_type) < 0)
 				goto err;
 			for (i = 1; i <= rwc_core_cnt[n]; i++)
 				rte_eal_remote_launch(test_rwc_reader,
 						(void *)(uintptr_t)read_type,
 							enabled_core_ids[i]);
-			key_shift = 1;
-			ret = write_keys(key_shift);
+			write_type = WRITE_KEY_SHIFT;
+			ret = write_keys(write_type);
 			writer_done = 1;
 			rte_eal_mp_wait_lcore();
 
@@ -798,19 +917,19 @@ test_hash_add_ks_lookup_hit_non_sp(struct rwc_perf *rwc_perf_results,
  */
 static int
 test_hash_add_ks_lookup_hit_sp(struct rwc_perf *rwc_perf_results, int rwc_lf,
-				int htm)
+				int htm, int ext_bkt)
 {
 	unsigned int n, m;
 	uint64_t i;
 	int use_jhash = 0;
 	int ret;
-	uint8_t key_shift;
+	uint8_t write_type;
 	uint8_t read_type = READ_PASS_SHIFT_PATH;
 
 	rte_atomic64_init(&greads);
 	rte_atomic64_init(&gread_cycles);
 
-	if (init_params(rwc_lf, use_jhash, htm) != 0)
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
 		goto err;
 	printf("\nTest: Hash add - key shift, Hash lookup - hit (shift-path)"
 	       "\n");
@@ -831,15 +950,15 @@ test_hash_add_ks_lookup_hit_sp(struct rwc_perf *rwc_perf_results, int rwc_lf,
 
 			rte_hash_reset(tbl_rwc_test_param.h);
 			writer_done = 0;
-			key_shift = 0;
-			if (write_keys(key_shift) < 0)
+			write_type = WRITE_NO_KEY_SHIFT;
+			if (write_keys(write_type) < 0)
 				goto err;
 			for (i = 1; i <= rwc_core_cnt[n]; i++)
 				rte_eal_remote_launch(test_rwc_reader,
 						(void *)(uintptr_t)read_type,
 						enabled_core_ids[i]);
-			key_shift = 1;
-			ret = write_keys(key_shift);
+			write_type = WRITE_KEY_SHIFT;
+			ret = write_keys(write_type);
 			writer_done = 1;
 			rte_eal_mp_wait_lcore();
 
@@ -874,19 +993,19 @@ test_hash_add_ks_lookup_hit_sp(struct rwc_perf *rwc_perf_results, int rwc_lf,
  */
 static int
 test_hash_add_ks_lookup_miss(struct rwc_perf *rwc_perf_results, int rwc_lf, int
-			     htm)
+			     htm, int ext_bkt)
 {
 	unsigned int n, m;
 	uint64_t i;
 	int use_jhash = 0;
 	int ret;
-	uint8_t key_shift;
+	uint8_t write_type;
 	uint8_t read_type = READ_FAIL;
 
 	rte_atomic64_init(&greads);
 	rte_atomic64_init(&gread_cycles);
 
-	if (init_params(rwc_lf, use_jhash, htm) != 0)
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
 		goto err;
 	printf("\nTest: Hash add - key shift, Hash lookup - miss\n");
 	for (m = 0; m < 2; m++) {
@@ -906,15 +1025,15 @@ test_hash_add_ks_lookup_miss(struct rwc_perf *rwc_perf_results, int rwc_lf, int
 
 			rte_hash_reset(tbl_rwc_test_param.h);
 			writer_done = 0;
-			key_shift = 0;
-			if (write_keys(key_shift) < 0)
+			write_type = WRITE_NO_KEY_SHIFT;
+			if (write_keys(write_type) < 0)
 				goto err;
 			for (i = 1; i <= rwc_core_cnt[n]; i++)
 				rte_eal_remote_launch(test_rwc_reader,
 						(void *)(uintptr_t)read_type,
 							enabled_core_ids[i]);
-			key_shift = 1;
-			ret = write_keys(key_shift);
+			write_type = WRITE_KEY_SHIFT;
+			ret = write_keys(write_type);
 			writer_done = 1;
 			rte_eal_mp_wait_lcore();
 
@@ -949,18 +1068,18 @@ test_hash_add_ks_lookup_miss(struct rwc_perf *rwc_perf_results, int rwc_lf, int
  */
 static int
 test_hash_multi_add_lookup(struct rwc_perf *rwc_perf_results, int rwc_lf,
-			   int htm)
+			   int htm, int ext_bkt)
 {
 	unsigned int n, m, k;
 	uint64_t i;
 	int use_jhash = 0;
-	uint8_t key_shift;
+	uint8_t write_type;
 	uint8_t read_type = READ_PASS_SHIFT_PATH;
 
 	rte_atomic64_init(&greads);
 	rte_atomic64_init(&gread_cycles);
 
-	if (init_params(rwc_lf, use_jhash, htm) != 0)
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
 		goto err;
 	printf("\nTest: Multi-add-lookup\n");
 	uint8_t pos_core;
@@ -991,8 +1110,8 @@ test_hash_multi_add_lookup(struct rwc_perf *rwc_perf_results, int rwc_lf,
 				writer_done = 0;
 				for (i = 0; i < 4; i++)
 					multi_writer_done[i] = 0;
-				key_shift = 0;
-				if (write_keys(key_shift) < 0)
+				write_type = WRITE_NO_KEY_SHIFT;
+				if (write_keys(write_type) < 0)
 					goto err;
 
 				/* Launch reader(s) */
@@ -1000,7 +1119,7 @@ test_hash_multi_add_lookup(struct rwc_perf *rwc_perf_results, int rwc_lf,
 					rte_eal_remote_launch(test_rwc_reader,
 						(void *)(uintptr_t)read_type,
 						enabled_core_ids[i]);
-				key_shift = 1;
+				write_type = WRITE_KEY_SHIFT;
 				pos_core = 0;
 
 				/* Launch writers */
@@ -1045,6 +1164,88 @@ test_hash_multi_add_lookup(struct rwc_perf *rwc_perf_results, int rwc_lf,
 	return -1;
 }
 
+/*
+ * Test lookup perf:
+ * Reader(s) lookup keys present in the extendable bkt.
+ */
+static int
+test_hash_add_ks_lookup_hit_extbkt(struct rwc_perf *rwc_perf_results,
+				int rwc_lf, int htm, int ext_bkt)
+{
+	unsigned int n, m;
+	uint64_t i;
+	int use_jhash = 0;
+	uint8_t write_type;
+	uint8_t read_type = READ_PASS_KEY_SHIFTS_EXTBKT;
+
+	rte_atomic64_init(&greads);
+	rte_atomic64_init(&gread_cycles);
+
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
+		goto err;
+	printf("\nTest: Hash add - key-shifts, read - hit (ext_bkt)\n");
+	for (m = 0; m < 2; m++) {
+		if (m == 1) {
+			printf("\n** With bulk-lookup **\n");
+			read_type |= BULK_LOOKUP;
+		}
+		for (n = 0; n < NUM_TEST; n++) {
+			unsigned int tot_lcore = rte_lcore_count();
+			if (tot_lcore < rwc_core_cnt[n] + 1)
+				goto finish;
+
+			printf("\nNumber of readers: %u\n", rwc_core_cnt[n]);
+
+			rte_atomic64_clear(&greads);
+			rte_atomic64_clear(&gread_cycles);
+
+			rte_hash_reset(tbl_rwc_test_param.h);
+			write_type = WRITE_NO_KEY_SHIFT;
+			if (write_keys(write_type) < 0)
+				goto err;
+			write_type = WRITE_KEY_SHIFT;
+			if (write_keys(write_type) < 0)
+				goto err;
+			writer_done = 0;
+			for (i = 1; i <= rwc_core_cnt[n]; i++)
+				rte_eal_remote_launch(test_rwc_reader,
+						(void *)(uintptr_t)read_type,
+							enabled_core_ids[i]);
+			for (i = 0; i < tbl_rwc_test_param.count_keys_ks_extbkt;
+			     i++) {
+				if (rte_hash_del_key(tbl_rwc_test_param.h,
+					tbl_rwc_test_param.keys_ks_extbkt + i)
+							< 0) {
+					printf("Delete Failed: %u\n",
+					tbl_rwc_test_param.keys_ks_extbkt[i]);
+					goto err;
+				}
+			}
+			writer_done = 1;
+			rte_eal_mp_wait_lcore();
+
+			for (i = 1; i <= rwc_core_cnt[n]; i++)
+				if (lcore_config[i].ret < 0)
+					goto err;
+
+			unsigned long long cycles_per_lookup =
+				rte_atomic64_read(&gread_cycles) /
+				rte_atomic64_read(&greads);
+			rwc_perf_results->w_ks_r_hit_extbkt[m][n]
+						= cycles_per_lookup;
+			printf("Cycles per lookup: %llu\n", cycles_per_lookup);
+		}
+	}
+
+finish:
+	rte_hash_free(tbl_rwc_test_param.h);
+	return 0;
+
+err:
+	rte_hash_free(tbl_rwc_test_param.h);
+	return -1;
+}
+
 static int
 test_hash_readwrite_lf_main(void)
 {
@@ -1057,6 +1258,7 @@ test_hash_readwrite_lf_main(void)
 	int rwc_lf = 0;
 	int htm;
 	int use_jhash = 0;
+	int ext_bkt = 0;
 	if (rte_lcore_count() == 1) {
 		printf("More than one lcore is required "
 			"to do read write lock-free concurrency test\n");
@@ -1070,7 +1272,7 @@ test_hash_readwrite_lf_main(void)
 	else
 		htm = 0;
 
-	if (init_params(rwc_lf, use_jhash, htm) != 0)
+	if (init_params(rwc_lf, use_jhash, htm, ext_bkt) != 0)
 		return -1;
 	if (generate_keys() != 0)
 		return -1;
@@ -1079,25 +1281,29 @@ test_hash_readwrite_lf_main(void)
 
 	if (RTE_HASH_EXTRA_FLAGS_RW_CONCURRENCY_LF) {
 		rwc_lf = 1;
+		ext_bkt = 1;
 		printf("Test lookup with read-write concurrency lock free support"
 		       " enabled\n");
 		if (test_hash_add_no_ks_lookup_hit(&rwc_lf_results, rwc_lf,
-							htm) < 0)
+							htm, ext_bkt) < 0)
 			return -1;
 		if (test_hash_add_no_ks_lookup_miss(&rwc_lf_results, rwc_lf,
-							htm) < 0)
+							htm, ext_bkt) < 0)
 			return -1;
 		if (test_hash_add_ks_lookup_hit_non_sp(&rwc_lf_results, rwc_lf,
-							htm) < 0)
+							htm, ext_bkt) < 0)
 			return -1;
 		if (test_hash_add_ks_lookup_hit_sp(&rwc_lf_results, rwc_lf,
-							htm) < 0)
+							htm, ext_bkt) < 0)
 			return -1;
-		if (test_hash_add_ks_lookup_miss(&rwc_lf_results, rwc_lf, htm)
-							< 0)
+		if (test_hash_add_ks_lookup_miss(&rwc_lf_results, rwc_lf, htm,
+						 ext_bkt) < 0)
 			return -1;
-		if (test_hash_multi_add_lookup(&rwc_lf_results, rwc_lf, htm)
-							< 0)
+		if (test_hash_multi_add_lookup(&rwc_lf_results, rwc_lf, htm,
+					       ext_bkt) < 0)
+			return -1;
+		if (test_hash_add_ks_lookup_hit_extbkt(&rwc_lf_results, rwc_lf,
+							htm, ext_bkt) < 0)
 			return -1;
 	}
 	printf("\nTest lookup with read-write concurrency lock free support"
@@ -1112,21 +1318,26 @@ test_hash_readwrite_lf_main(void)
 		}
 	} else
 		printf("With HTM Enabled\n");
-	if (test_hash_add_no_ks_lookup_hit(&rwc_non_lf_results, rwc_lf, htm)
-						< 0)
+	if (test_hash_add_no_ks_lookup_hit(&rwc_non_lf_results, rwc_lf, htm,
+					   ext_bkt) < 0)
 		return -1;
-	if (test_hash_add_no_ks_lookup_miss(&rwc_non_lf_results, rwc_lf, htm)
-						< 0)
+	if (test_hash_add_no_ks_lookup_miss(&rwc_non_lf_results, rwc_lf, htm,
+						ext_bkt) < 0)
 		return -1;
 	if (test_hash_add_ks_lookup_hit_non_sp(&rwc_non_lf_results, rwc_lf,
-						htm) < 0)
+						htm, ext_bkt) < 0)
+		return -1;
+	if (test_hash_add_ks_lookup_hit_sp(&rwc_non_lf_results, rwc_lf, htm,
+						ext_bkt) < 0)
 		return -1;
-	if (test_hash_add_ks_lookup_hit_sp(&rwc_non_lf_results, rwc_lf, htm)
-						< 0)
+	if (test_hash_add_ks_lookup_miss(&rwc_non_lf_results, rwc_lf, htm,
+					 ext_bkt) < 0)
 		return -1;
-	if (test_hash_add_ks_lookup_miss(&rwc_non_lf_results, rwc_lf, htm) < 0)
+	if (test_hash_multi_add_lookup(&rwc_non_lf_results, rwc_lf, htm,
+							ext_bkt) < 0)
 		return -1;
-	if (test_hash_multi_add_lookup(&rwc_non_lf_results, rwc_lf, htm) < 0)
+	if (test_hash_add_ks_lookup_hit_extbkt(&rwc_non_lf_results, rwc_lf,
+						htm, ext_bkt) < 0)
 		return -1;
 results:
 	printf("\n\t\t\t\t\t\t********** Results summary **********\n\n");
@@ -1158,8 +1369,11 @@ test_hash_readwrite_lf_main(void)
 			       "(shift-path)\t\t%u\n\t\t\t\t\t\t\t\t",
 			       rwc_lf_results.w_ks_r_hit_sp[j][i]);
 			printf("Hash add - key-shifts, Hash lookup miss\t\t\t\t"
-				"%u\n\n\t\t\t\t",
+				"%u\n\t\t\t\t\t\t\t\t",
 				rwc_lf_results.w_ks_r_miss[j][i]);
+			printf("Hash add - key-shifts, Hash lookup hit (ext_bkt)\t\t"
+				"%u\n\n\t\t\t\t",
+				rwc_lf_results.w_ks_r_hit_extbkt[j][i]);
 
 			printf("Disabled\t");
 			if (htm)
@@ -1179,7 +1393,11 @@ test_hash_readwrite_lf_main(void)
 			       "(shift-path)\t\t%u\n\t\t\t\t\t\t\t\t",
 			       rwc_non_lf_results.w_ks_r_hit_sp[j][i]);
 			printf("Hash add - key-shifts, Hash lookup miss\t\t\t\t"
-			       "%u\n", rwc_non_lf_results.w_ks_r_miss[j][i]);
+			       "%u\n\t\t\t\t\t\t\t\t",
+			       rwc_non_lf_results.w_ks_r_miss[j][i]);
+			printf("Hash add - key-shifts, Hash lookup hit (ext_bkt)\t\t"
+				"%u\n",
+				rwc_non_lf_results.w_ks_r_hit_extbkt[j][i]);
 
 			printf("_______\t\t_______\t\t_________\t___\t\t"
 			       "_________\t\t\t\t\t\t_________________\n");
-- 
2.17.1

Re: [dpdk-dev] [PATCH v5 0/2] hash: add lock free support for ext bkt

[Thomas Monjalon]

02/04/2019 21:44, Dharmik Thakkar:
> This patch series:
> - Enables lock-free read-write concurrency support for extendable
> bucket feature.
> - Adds lock-free read-write concurrency tests for ext bkt
> ---
> Dharmik Thakkar (2):
>   hash: add lock free support for extendable bucket
>   test/hash: lock-free rw concurrency test ext bkt

Applied, thanks

Re: [dpdk-dev] [PATCH v5 0/2] hash: add lock free support for ext bkt

[Thomas Monjalon]

02/04/2019 21:44, Dharmik Thakkar:
> This patch series:
> - Enables lock-free read-write concurrency support for extendable
> bucket feature.
> - Adds lock-free read-write concurrency tests for ext bkt
> ---
> Dharmik Thakkar (2):
>   hash: add lock free support for extendable bucket
>   test/hash: lock-free rw concurrency test ext bkt

Applied, thanks