Re: [dpdk-dev] [PATCH v2] mempool: reduce rte_mempool structure size

Re: [dpdk-dev] [PATCH v2] mempool: reduce rte_mempool structure size

[Wiles, Keith]

>>Hi Keith,
>>
>>Thank you for adding the RTE_NEXT_ABI. I think this is the way
>>described in the process. Your changes will be available in next
>>version (16.4) for people compiling with RTE_NEXT_ABI=y, and in
>>16.7 without option (I'm just surprised that RTE_NEXT_ABI=y in
>>default configs...).
>>
>>I think a deprecation notice should also be added in this commit
>>in doc/guides/rel_notes/deprecation.rst.
>
>Will add the text.
>>
>>Please also find comments below.
>>
>>On 02/09/2016 06:30 PM, Keith Wiles wrote:
>>
>>> diff --git a/config/defconfig_x86_64-native-linuxapp-gcc b/config/defconfig_x86_64-native-linuxapp-gcc
>>> index 60baf5b..02e9ace 100644
>>> --- a/config/defconfig_x86_64-native-linuxapp-gcc
>>> +++ b/config/defconfig_x86_64-native-linuxapp-gcc
>>> @@ -40,3 +40,8 @@ CONFIG_RTE_ARCH_64=y
>>>  
>>>  CONFIG_RTE_TOOLCHAIN="gcc"
>>>  CONFIG_RTE_TOOLCHAIN_GCC=y
>>> +CONFIG_RTE_BUILD_SHARED_LIB=y
>>> +CONFIG_RTE_NEXT_ABI=n
>>> +CONFIG_RTE_EAL_IGB_UIO=n
>>> +CONFIG_RTE_LIBRTE_KNI=n
>>> +CONFIG_RTE_KNI_KMOD=n
>
>Hmm, not sure where this came from, but will remove it.

I think this was from the ABI-Checker I ran and the tool should leave the repo in its original state.

>>
>>I think this should not be part of the patch.
>>
>>> @@ -672,6 +704,24 @@ rte_mempool_count(const struct rte_mempool *mp)
>>>  static unsigned
>>>  rte_mempool_dump_cache(FILE *f, const struct rte_mempool *mp)
>>>  {
>>> +#ifdef RTE_NEXT_ABI
>>> +	unsigned lcore_id;
>>> +	unsigned count = 0;
>>> +	unsigned cache_count;
>>> +
>>> +	fprintf(f, "  cache infos:\n");
>>> +	fprintf(f, "    cache_size=%"PRIu32"\n", mp->cache_size);
>>> +	if (mp->cache_size == 0)
>>> +		return count;
>>> +
>>> +	for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++) {
>>> +		cache_count = mp->local_cache[lcore_id].len;
>>> +		fprintf(f, "    cache_count[%u]=%u\n", lcore_id, cache_count);
>>> +		count += cache_count;
>>> +	}
>>> +	fprintf(f, "    total_cache_count=%u\n", count);
>>> +	return count;
>>> +#else
>>>  #if RTE_MEMPOOL_CACHE_MAX_SIZE > 0
>>>  	unsigned lcore_id;
>>>  	unsigned count = 0;
>>
>>I think in this case we could avoid to duplicate the code without
>>beeing unclear by using the proper #ifdefs:
>
>I was struggling with how it should be done. I like to see clear ifdefs and be able to see the complete code for a given case. In these cases I wanted to make it simple to remove the code quickly by just deleting lines instead of editing lines. I will follow your suggestion.
>>
>>#if RTE_MEMPOOL_CACHE_MAX_SIZE > 0 || defined(RTE_NEXT_ABI)
>>	/* common code */
>>#ifdef RTE_NEXT_ABI
>>	if (mp->cache_size == 0)
>>		return count;
>>#endif
>>	/* common code */
>>#else
>>...
>>#endif
>>
>>
>>> @@ -755,6 +806,26 @@ mempool_audit_cookies(const struct rte_mempool *mp)
>>>  #define mempool_audit_cookies(mp) do {} while(0)
>>>  #endif
>>>  
>>> +#ifdef RTE_NEXT_ABI
>>> +/* check cookies before and after objects */
>>> +static void
>>> +mempool_audit_cache(const struct rte_mempool *mp)
>>> +{
>>> +	/* check cache size consistency */
>>> +	unsigned lcore_id;
>>> +
>>> +	if (mp->cache_size == 0)
>>> +		return;
>>> +
>>> +	for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++) {
>>> +		if (mp->local_cache[lcore_id].len > mp->cache_flushthresh) {
>>> +			RTE_LOG(CRIT, MEMPOOL, "badness on cache[%u]\n",
>>> +				lcore_id);
>>> +			rte_panic("MEMPOOL: invalid cache len\n");
>>> +		}
>>> +	}
>>> +}
>>> +#else
>>
>>same here
>>
>>> diff --git a/lib/librte_mempool/rte_mempool.h b/lib/librte_mempool/rte_mempool.h
>>> index 6e2390a..fc9b595 100644
>>> --- a/lib/librte_mempool/rte_mempool.h
>>> +++ b/lib/librte_mempool/rte_mempool.h
>>> @@ -95,6 +95,19 @@ struct rte_mempool_debug_stats {
>>>  } __rte_cache_aligned;
>>>  #endif
>>>  
>>> +#ifdef RTE_NEXT_ABI
>>> +/**
>>> + * A structure that stores a per-core object cache.
>>> + */
>>> +struct rte_mempool_cache {
>>> +	unsigned len; /**< Cache len */
>>> +	/*
>>> +	 * Cache is allocated to this size to allow it to overflow in certain
>>> +	 * cases to avoid needless emptying of cache.
>>> +	 */
>>> +	void *objs[RTE_MEMPOOL_CACHE_MAX_SIZE * 3]; /**< Cache objects */
>>> +} __rte_cache_aligned;
>>> +#else
>>
>>same here
>>
>>
>>
>>> @@ -755,19 +793,25 @@ static inline void __attribute__((always_inline))
>>>  __mempool_put_bulk(struct rte_mempool *mp, void * const *obj_table,
>>>  		    unsigned n, int is_mp)
>>>  {
>>> +#ifndef RTE_NEXT_ABI	/* Note: ifndef */
>>>  #if RTE_MEMPOOL_CACHE_MAX_SIZE > 0
>>> +#endif /* RTE_NEXT_ABI */
>>>  	struct rte_mempool_cache *cache;
>>>  	uint32_t index;
>>>  	void **cache_objs;
>>>  	unsigned lcore_id = rte_lcore_id();
>>>  	uint32_t cache_size = mp->cache_size;
>>>  	uint32_t flushthresh = mp->cache_flushthresh;
>>> +#ifndef RTE_NEXT_ABI	/* Note: ifndef */
>>>  #endif /* RTE_MEMPOOL_CACHE_MAX_SIZE > 0 */
>>> +#endif /* RTE_NEXT_ABI */
>>
>>this looks strange... I think it does not work properly.
>>Why not
>>#if RTE_MEMPOOL_CACHE_MAX_SIZE > 0 || defined(RTE_NEXT_ABI)
>
>Yes, it is strange :-(
>>
>>>  	/* increment stat now, adding in mempool always success */
>>>  	__MEMPOOL_STAT_ADD(mp, put, n);
>>>  
>>> +#ifndef RTE_NEXT_ABI	/* Note: ifndef */
>>>  #if RTE_MEMPOOL_CACHE_MAX_SIZE > 0
>>> +#endif /* RTE_NEXT_ABI */
>>>  	/* cache is not enabled or single producer or non-EAL thread */
>>>  	if (unlikely(cache_size == 0 || is_mp == 0 ||
>>>  		     lcore_id >= RTE_MAX_LCORE))
>>> @@ -802,7 +846,9 @@ __mempool_put_bulk(struct rte_mempool *mp, void * const *obj_table,
>>>  	return;
>>>  
>>>  ring_enqueue:
>>> +#ifndef RTE_NEXT_ABI	/* Note: ifndef */
>>>  #endif /* RTE_MEMPOOL_CACHE_MAX_SIZE > 0 */
>>> +#endif /* RTE_NEXT_ABI */
>>>  
>>>  	/* push remaining objects in ring */
>>>  #ifdef RTE_LIBRTE_MEMPOOL_DEBUG
>>> @@ -946,7 +992,9 @@ __mempool_get_bulk(struct rte_mempool *mp, void **obj_table,
>>>  		   unsigned n, int is_mc)
>>>  {
>>>  	int ret;
>>> +#ifndef RTE_NEXT_ABI	/* Note: ifndef */
>>>  #if RTE_MEMPOOL_CACHE_MAX_SIZE > 0
>>> +#endif /* RTE_NEXT_ABI */
>>>  	struct rte_mempool_cache *cache;
>>>  	uint32_t index, len;
>>>  	void **cache_objs;
>>> @@ -992,7 +1040,9 @@ __mempool_get_bulk(struct rte_mempool *mp, void **obj_table,
>>>  	return 0;
>>>  
>>>  ring_dequeue:
>>> +#ifndef RTE_NEXT_ABI	/* Note: ifndef */
>>>  #endif /* RTE_MEMPOOL_CACHE_MAX_SIZE > 0 */
>>> +#endif /* RTE_NEXT_ABI */
>>>  
>>>  	/* get remaining objects from ring */
>>>  	if (is_mc)
>>
>>Same in those cases.
>>
>>
>>
>>Regards,
>>Olivier
>>
>
>
>Regards,
>Keith
>
>
>
>
>


Regards,
Keith

Re: [dpdk-dev] [PATCH v2] mempool: reduce rte_mempool structure size

[Thomas Monjalon]

2016-02-10 18:01, Wiles, Keith:
> >>> --- a/config/defconfig_x86_64-native-linuxapp-gcc
> >>> +++ b/config/defconfig_x86_64-native-linuxapp-gcc
> >>> @@ -40,3 +40,8 @@ CONFIG_RTE_ARCH_64=y
> >>>  
> >>>  CONFIG_RTE_TOOLCHAIN="gcc"
> >>>  CONFIG_RTE_TOOLCHAIN_GCC=y
> >>> +CONFIG_RTE_BUILD_SHARED_LIB=y
> >>> +CONFIG_RTE_NEXT_ABI=n
> >>> +CONFIG_RTE_EAL_IGB_UIO=n
> >>> +CONFIG_RTE_LIBRTE_KNI=n
> >>> +CONFIG_RTE_KNI_KMOD=n
> >
> >Hmm, not sure where this came from, but will remove it.
> 
> I think this was from the ABI-Checker I ran and the tool should leave the repo in its original state.

Yes you're right. The ABI checker modify the defconfig instead of modifying
the generated .config file.
Anyone for a patch?

Re: [dpdk-dev] [PATCH v2] mempool: reduce rte_mempool structure size

[Panu Matilainen]

On 02/10/2016 08:02 PM, Thomas Monjalon wrote:
> 2016-02-10 18:01, Wiles, Keith:
>>>>> --- a/config/defconfig_x86_64-native-linuxapp-gcc
>>>>> +++ b/config/defconfig_x86_64-native-linuxapp-gcc
>>>>> @@ -40,3 +40,8 @@ CONFIG_RTE_ARCH_64=y
>>>>>
>>>>>   CONFIG_RTE_TOOLCHAIN="gcc"
>>>>>   CONFIG_RTE_TOOLCHAIN_GCC=y
>>>>> +CONFIG_RTE_BUILD_SHARED_LIB=y
>>>>> +CONFIG_RTE_NEXT_ABI=n
>>>>> +CONFIG_RTE_EAL_IGB_UIO=n
>>>>> +CONFIG_RTE_LIBRTE_KNI=n
>>>>> +CONFIG_RTE_KNI_KMOD=n
>>>
>>> Hmm, not sure where this came from, but will remove it.
>>
>> I think this was from the ABI-Checker I ran and the tool should leave the repo in its original state.
>
> Yes you're right. The ABI checker modify the defconfig instead of modifying
> the generated .config file.

Its "by design" according to Neil (this was discussed when the abi 
checker was introduced, see 
http://dpdk.org/ml/archives/dev/2015-March/014636.html)

I actually agree with Neil that changing .config after make config seems 
counter-intuitive compared to how this works in other projects, but that 
doesn't make modifying the default templates the right thing to do in DPDK.

> Anyone for a patch?

I can add it to my TODO among a couple of other things - it should not 
leave clutter like this behind no matter what. As to how exactly it 
should be fixed, it could of course just change .config, or 
alternatively create (and later clean up) a temporary defconfig file 
with the necessary contents, which would be closer to the current 
approach I guess.

	- Panu -

[dpdk-dev] [PATCH] mempool: Reduce rte_mempool structure size

[Keith Wiles]

The rte_mempool structure is changed, which will cause an ABI change
for this structure.

Allow mempool cache support to be dynamic depending on if the
mempool being created needs cache support. Saves about 1.5M of
memory used by the rte_mempool structure. Performance does not seem
to be effected running l3fwd and the test_mempool execution passed.

Allocating small mempools which do not require cache can consume
larges amounts of memory if you have a number of these mempools.

Signed-off-by: Keith Wiles <keith.wiles@intel.com>
---
 app/test/test_mempool.c          |  4 +--
 lib/librte_mempool/rte_mempool.c | 56 ++++++++++++++++++----------------------
 lib/librte_mempool/rte_mempool.h | 29 ++++++++++-----------
 3 files changed, 40 insertions(+), 49 deletions(-)

diff --git a/app/test/test_mempool.c b/app/test/test_mempool.c
index 72f8fb6..7b479f8 100644
--- a/app/test/test_mempool.c
+++ b/app/test/test_mempool.c
@@ -122,8 +122,8 @@ test_mempool_basic(void)
 		return -1;
 
 	printf("get private data\n");
-	if (rte_mempool_get_priv(mp) !=
-			(char*) mp + MEMPOOL_HEADER_SIZE(mp, mp->pg_num))
+	if (rte_mempool_get_priv(mp) != (char *)mp +
+			MEMPOOL_HEADER_SIZE(mp, mp->pg_num, mp->cache_size))
 		return -1;
 
 	printf("get physical address of an object\n");
diff --git a/lib/librte_mempool/rte_mempool.c b/lib/librte_mempool/rte_mempool.c
index aff5f6d..bdf8e2e 100644
--- a/lib/librte_mempool/rte_mempool.c
+++ b/lib/librte_mempool/rte_mempool.c
@@ -450,15 +450,11 @@ rte_mempool_xmem_create(const char *name, unsigned n, unsigned elt_size,
 	int page_size = getpagesize();
 
 	/* compilation-time checks */
+#ifdef RTE_LIBRTE_MEMPOOL_DEBUG
 	RTE_BUILD_BUG_ON((sizeof(struct rte_mempool) &
 			  RTE_CACHE_LINE_MASK) != 0);
-#if RTE_MEMPOOL_CACHE_MAX_SIZE > 0
 	RTE_BUILD_BUG_ON((sizeof(struct rte_mempool_cache) &
 			  RTE_CACHE_LINE_MASK) != 0);
-	RTE_BUILD_BUG_ON((offsetof(struct rte_mempool, local_cache) &
-			  RTE_CACHE_LINE_MASK) != 0);
-#endif
-#ifdef RTE_LIBRTE_MEMPOOL_DEBUG
 	RTE_BUILD_BUG_ON((sizeof(struct rte_mempool_debug_stats) &
 			  RTE_CACHE_LINE_MASK) != 0);
 	RTE_BUILD_BUG_ON((offsetof(struct rte_mempool, stats) &
@@ -527,9 +523,8 @@ rte_mempool_xmem_create(const char *name, unsigned n, unsigned elt_size,
 		 */
 		int head = sizeof(struct rte_mempool);
 		int new_size = (private_data_size + head) % page_size;
-		if (new_size) {
+		if (new_size)
 			private_data_size += page_size - new_size;
-		}
 	}
 
 	/* try to allocate tailq entry */
@@ -544,7 +539,8 @@ rte_mempool_xmem_create(const char *name, unsigned n, unsigned elt_size,
 	 * store mempool objects. Otherwise reserve a memzone that is large
 	 * enough to hold mempool header and metadata plus mempool objects.
 	 */
-	mempool_size = MEMPOOL_HEADER_SIZE(mp, pg_num) + private_data_size;
+	mempool_size = MEMPOOL_HEADER_SIZE(mp, pg_num, cache_size);
+	mempool_size += private_data_size;
 	mempool_size = RTE_ALIGN_CEIL(mempool_size, RTE_MEMPOOL_ALIGN);
 	if (vaddr == NULL)
 		mempool_size += (size_t)objsz.total_size * n;
@@ -598,8 +594,15 @@ rte_mempool_xmem_create(const char *name, unsigned n, unsigned elt_size,
 	mp->cache_flushthresh = CALC_CACHE_FLUSHTHRESH(cache_size);
 	mp->private_data_size = private_data_size;
 
+	/*
+	 * local_cache pointer is set even if cache_size is zero.
+	 * The local_cache points to just past the elt_pa[] array.
+	 */
+	mp->local_cache = (struct rte_mempool_cache *)
+			((char *)mp + MEMPOOL_HEADER_SIZE(mp, pg_num, 0));
+
 	/* calculate address of the first element for continuous mempool. */
-	obj = (char *)mp + MEMPOOL_HEADER_SIZE(mp, pg_num) +
+	obj = (char *)mp + MEMPOOL_HEADER_SIZE(mp, pg_num, cache_size) +
 		private_data_size;
 	obj = RTE_PTR_ALIGN_CEIL(obj, RTE_MEMPOOL_ALIGN);
 
@@ -613,9 +616,8 @@ rte_mempool_xmem_create(const char *name, unsigned n, unsigned elt_size,
 		mp->elt_va_start = (uintptr_t)obj;
 		mp->elt_pa[0] = mp->phys_addr +
 			(mp->elt_va_start - (uintptr_t)mp);
-
-	/* mempool elements in a separate chunk of memory. */
 	} else {
+		/* mempool elements in a separate chunk of memory. */
 		mp->elt_va_start = (uintptr_t)vaddr;
 		memcpy(mp->elt_pa, paddr, sizeof (mp->elt_pa[0]) * pg_num);
 	}
@@ -645,19 +647,15 @@ unsigned
 rte_mempool_count(const struct rte_mempool *mp)
 {
 	unsigned count;
+	unsigned lcore_id;
 
 	count = rte_ring_count(mp->ring);
 
-#if RTE_MEMPOOL_CACHE_MAX_SIZE > 0
-	{
-		unsigned lcore_id;
-		if (mp->cache_size == 0)
-			return count;
+	if (mp->cache_size == 0)
+		return count;
 
-		for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++)
-			count += mp->local_cache[lcore_id].len;
-	}
-#endif
+	for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++)
+		count += mp->local_cache[lcore_id].len;
 
 	/*
 	 * due to race condition (access to len is not locked), the
@@ -672,13 +670,15 @@ rte_mempool_count(const struct rte_mempool *mp)
 static unsigned
 rte_mempool_dump_cache(FILE *f, const struct rte_mempool *mp)
 {
-#if RTE_MEMPOOL_CACHE_MAX_SIZE > 0
 	unsigned lcore_id;
 	unsigned count = 0;
 	unsigned cache_count;
 
 	fprintf(f, "  cache infos:\n");
 	fprintf(f, "    cache_size=%"PRIu32"\n", mp->cache_size);
+	if (mp->cache_size == 0)
+		return count;
+
 	for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++) {
 		cache_count = mp->local_cache[lcore_id].len;
 		fprintf(f, "    cache_count[%u]=%u\n", lcore_id, cache_count);
@@ -686,11 +686,6 @@ rte_mempool_dump_cache(FILE *f, const struct rte_mempool *mp)
 	}
 	fprintf(f, "    total_cache_count=%u\n", count);
 	return count;
-#else
-	RTE_SET_USED(mp);
-	fprintf(f, "  cache disabled\n");
-	return 0;
-#endif
 }
 
 #ifdef RTE_LIBRTE_MEMPOOL_DEBUG
@@ -755,13 +750,16 @@ mempool_audit_cookies(const struct rte_mempool *mp)
 #define mempool_audit_cookies(mp) do {} while(0)
 #endif
 
-#if RTE_MEMPOOL_CACHE_MAX_SIZE > 0
 /* check cookies before and after objects */
 static void
 mempool_audit_cache(const struct rte_mempool *mp)
 {
 	/* check cache size consistency */
 	unsigned lcore_id;
+
+	if (mp->cache_size == 0)
+		return;
+
 	for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++) {
 		if (mp->local_cache[lcore_id].len > mp->cache_flushthresh) {
 			RTE_LOG(CRIT, MEMPOOL, "badness on cache[%u]\n",
@@ -770,10 +768,6 @@ mempool_audit_cache(const struct rte_mempool *mp)
 		}
 	}
 }
-#else
-#define mempool_audit_cache(mp) do {} while(0)
-#endif
-
 
 /* check the consistency of mempool (size, cookies, ...) */
 void
diff --git a/lib/librte_mempool/rte_mempool.h b/lib/librte_mempool/rte_mempool.h
index 6e2390a..434ef98 100644
--- a/lib/librte_mempool/rte_mempool.h
+++ b/lib/librte_mempool/rte_mempool.h
@@ -95,7 +95,6 @@ struct rte_mempool_debug_stats {
 } __rte_cache_aligned;
 #endif
 
-#if RTE_MEMPOOL_CACHE_MAX_SIZE > 0
 /**
  * A structure that stores a per-core object cache.
  */
@@ -107,7 +106,6 @@ struct rte_mempool_cache {
 	 */
 	void *objs[RTE_MEMPOOL_CACHE_MAX_SIZE * 3]; /**< Cache objects */
 } __rte_cache_aligned;
-#endif /* RTE_MEMPOOL_CACHE_MAX_SIZE > 0 */
 
 /**
  * A structure that stores the size of mempool elements.
@@ -194,10 +192,7 @@ struct rte_mempool {
 
 	unsigned private_data_size;      /**< Size of private data. */
 
-#if RTE_MEMPOOL_CACHE_MAX_SIZE > 0
-	/** Per-lcore local cache. */
-	struct rte_mempool_cache local_cache[RTE_MAX_LCORE];
-#endif
+	struct rte_mempool_cache *local_cache; /**< Per-lcore local cache */
 
 #ifdef RTE_LIBRTE_MEMPOOL_DEBUG
 	/** Per-lcore statistics. */
@@ -247,6 +242,13 @@ struct rte_mempool {
 #endif
 
 /**
+ * Size of elt_pa array size based on number of pages. (Internal use)
+ */
+#define __PA_SIZE(mp, pgn) \
+	RTE_ALIGN_CEIL((((pgn) - RTE_DIM((mp)->elt_pa)) * \
+	sizeof((mp)->elt_pa[0])), RTE_CACHE_LINE_SIZE)
+
+/**
  * Calculate the size of the mempool header.
  *
  * @param mp
@@ -254,9 +256,9 @@ struct rte_mempool {
  * @param pgn
  *   Number of pages used to store mempool objects.
  */
-#define	MEMPOOL_HEADER_SIZE(mp, pgn)	(sizeof(*(mp)) + \
-	RTE_ALIGN_CEIL(((pgn) - RTE_DIM((mp)->elt_pa)) * \
-	sizeof ((mp)->elt_pa[0]), RTE_CACHE_LINE_SIZE))
+#define MEMPOOL_HEADER_SIZE(mp, pgn, cs) \
+	(sizeof(*(mp)) + __PA_SIZE(mp, pgn) + (((cs) == 0) ? 0 : \
+	(sizeof(struct rte_mempool_cache) * RTE_MAX_LCORE)))
 
 /**
  * Return true if the whole mempool is in contiguous memory.
@@ -755,19 +757,16 @@ static inline void __attribute__((always_inline))
 __mempool_put_bulk(struct rte_mempool *mp, void * const *obj_table,
 		    unsigned n, int is_mp)
 {
-#if RTE_MEMPOOL_CACHE_MAX_SIZE > 0
 	struct rte_mempool_cache *cache;
 	uint32_t index;
 	void **cache_objs;
 	unsigned lcore_id = rte_lcore_id();
 	uint32_t cache_size = mp->cache_size;
 	uint32_t flushthresh = mp->cache_flushthresh;
-#endif /* RTE_MEMPOOL_CACHE_MAX_SIZE > 0 */
 
 	/* increment stat now, adding in mempool always success */
 	__MEMPOOL_STAT_ADD(mp, put, n);
 
-#if RTE_MEMPOOL_CACHE_MAX_SIZE > 0
 	/* cache is not enabled or single producer or non-EAL thread */
 	if (unlikely(cache_size == 0 || is_mp == 0 ||
 		     lcore_id >= RTE_MAX_LCORE))
@@ -802,7 +801,6 @@ __mempool_put_bulk(struct rte_mempool *mp, void * const *obj_table,
 	return;
 
 ring_enqueue:
-#endif /* RTE_MEMPOOL_CACHE_MAX_SIZE > 0 */
 
 	/* push remaining objects in ring */
 #ifdef RTE_LIBRTE_MEMPOOL_DEBUG
@@ -946,7 +944,6 @@ __mempool_get_bulk(struct rte_mempool *mp, void **obj_table,
 		   unsigned n, int is_mc)
 {
 	int ret;
-#if RTE_MEMPOOL_CACHE_MAX_SIZE > 0
 	struct rte_mempool_cache *cache;
 	uint32_t index, len;
 	void **cache_objs;
@@ -992,7 +989,6 @@ __mempool_get_bulk(struct rte_mempool *mp, void **obj_table,
 	return 0;
 
 ring_dequeue:
-#endif /* RTE_MEMPOOL_CACHE_MAX_SIZE > 0 */
 
 	/* get remaining objects from ring */
 	if (is_mc)
@@ -1293,7 +1289,8 @@ void rte_mempool_audit(const struct rte_mempool *mp);
  */
 static inline void *rte_mempool_get_priv(struct rte_mempool *mp)
 {
-	return (char *)mp + MEMPOOL_HEADER_SIZE(mp, mp->pg_num);
+	return (char *)mp +
+		MEMPOOL_HEADER_SIZE(mp, mp->pg_num, mp->cache_size);
 }
 
 /**
-- 
2.7.0

[dpdk-dev] [PATCH v2] mempool: reduce rte_mempool structure size

[Keith Wiles]

Patch v2 to add some comments and setup for RTE_NEXT_ABI changes.

The rte_mempool structure is changed, which will cause an ABI change
for this structure. Providing backward compat is not reasonable
here as this structure is used in multiple defines/inlines.

Allow mempool cache support to be dynamic depending on if the
mempool being created needs cache support. Saves about 1.5M of
memory used by the rte_mempool structure.

Allocating small mempools which do not require cache can consume
larges amounts of memory if you have a number of these mempools.

Signed-off-by: Keith Wiles <keith.wiles@intel.com>
---
 app/test/test_mempool.c                     |  5 ++
 config/defconfig_x86_64-native-linuxapp-gcc |  5 ++
 lib/librte_mempool/rte_mempool.c            | 83 ++++++++++++++++++++++++++---
 lib/librte_mempool/rte_mempool.h            | 57 +++++++++++++++++++-
 4 files changed, 143 insertions(+), 7 deletions(-)

diff --git a/app/test/test_mempool.c b/app/test/test_mempool.c
index 72f8fb6..2829d40 100644
--- a/app/test/test_mempool.c
+++ b/app/test/test_mempool.c
@@ -122,8 +122,13 @@ test_mempool_basic(void)
 		return -1;
 
 	printf("get private data\n");
+#ifdef RTE_NEXT_ABI
+	if (rte_mempool_get_priv(mp) != (char *)mp +
+			MEMPOOL_HEADER_SIZE(mp, mp->pg_num, mp->cache_size))
+#else
 	if (rte_mempool_get_priv(mp) !=
 			(char*) mp + MEMPOOL_HEADER_SIZE(mp, mp->pg_num))
+#endif
 		return -1;
 
 	printf("get physical address of an object\n");
diff --git a/config/defconfig_x86_64-native-linuxapp-gcc b/config/defconfig_x86_64-native-linuxapp-gcc
index 60baf5b..02e9ace 100644
--- a/config/defconfig_x86_64-native-linuxapp-gcc
+++ b/config/defconfig_x86_64-native-linuxapp-gcc
@@ -40,3 +40,8 @@ CONFIG_RTE_ARCH_64=y
 
 CONFIG_RTE_TOOLCHAIN="gcc"
 CONFIG_RTE_TOOLCHAIN_GCC=y
+CONFIG_RTE_BUILD_SHARED_LIB=y
+CONFIG_RTE_NEXT_ABI=n
+CONFIG_RTE_EAL_IGB_UIO=n
+CONFIG_RTE_LIBRTE_KNI=n
+CONFIG_RTE_KNI_KMOD=n
diff --git a/lib/librte_mempool/rte_mempool.c b/lib/librte_mempool/rte_mempool.c
index aff5f6d..c61dc44 100644
--- a/lib/librte_mempool/rte_mempool.c
+++ b/lib/librte_mempool/rte_mempool.c
@@ -452,12 +452,17 @@ rte_mempool_xmem_create(const char *name, unsigned n, unsigned elt_size,
 	/* compilation-time checks */
 	RTE_BUILD_BUG_ON((sizeof(struct rte_mempool) &
 			  RTE_CACHE_LINE_MASK) != 0);
+#ifdef RTE_NEXT_ABI
+	RTE_BUILD_BUG_ON((sizeof(struct rte_mempool_cache) &
+			  RTE_CACHE_LINE_MASK) != 0);
+#else
 #if RTE_MEMPOOL_CACHE_MAX_SIZE > 0
 	RTE_BUILD_BUG_ON((sizeof(struct rte_mempool_cache) &
 			  RTE_CACHE_LINE_MASK) != 0);
 	RTE_BUILD_BUG_ON((offsetof(struct rte_mempool, local_cache) &
 			  RTE_CACHE_LINE_MASK) != 0);
 #endif
+#endif /* RTE_NEXT_ABI */
 #ifdef RTE_LIBRTE_MEMPOOL_DEBUG
 	RTE_BUILD_BUG_ON((sizeof(struct rte_mempool_debug_stats) &
 			  RTE_CACHE_LINE_MASK) != 0);
@@ -527,9 +532,8 @@ rte_mempool_xmem_create(const char *name, unsigned n, unsigned elt_size,
 		 */
 		int head = sizeof(struct rte_mempool);
 		int new_size = (private_data_size + head) % page_size;
-		if (new_size) {
+		if (new_size)
 			private_data_size += page_size - new_size;
-		}
 	}
 
 	/* try to allocate tailq entry */
@@ -544,7 +548,12 @@ rte_mempool_xmem_create(const char *name, unsigned n, unsigned elt_size,
 	 * store mempool objects. Otherwise reserve a memzone that is large
 	 * enough to hold mempool header and metadata plus mempool objects.
 	 */
+#ifdef RTE_NEXT_ABI
+	mempool_size = MEMPOOL_HEADER_SIZE(mp, pg_num, cache_size);
+	mempool_size += private_data_size;
+#else
 	mempool_size = MEMPOOL_HEADER_SIZE(mp, pg_num) + private_data_size;
+#endif /* RTE_NEXT_ABI */
 	mempool_size = RTE_ALIGN_CEIL(mempool_size, RTE_MEMPOOL_ALIGN);
 	if (vaddr == NULL)
 		mempool_size += (size_t)objsz.total_size * n;
@@ -598,9 +607,22 @@ rte_mempool_xmem_create(const char *name, unsigned n, unsigned elt_size,
 	mp->cache_flushthresh = CALC_CACHE_FLUSHTHRESH(cache_size);
 	mp->private_data_size = private_data_size;
 
+#ifdef RTE_NEXT_ABI
+	/*
+	 * local_cache pointer is set even if cache_size is zero.
+	 * The local_cache points to just past the elt_pa[] array.
+	 */
+	mp->local_cache = (struct rte_mempool_cache *)
+			((char *)mp + MEMPOOL_HEADER_SIZE(mp, pg_num, 0));
+
+	/* calculate address of the first element for continuous mempool. */
+	obj = (char *)mp + MEMPOOL_HEADER_SIZE(mp, pg_num, cache_size) +
+		private_data_size;
+#else
 	/* calculate address of the first element for continuous mempool. */
 	obj = (char *)mp + MEMPOOL_HEADER_SIZE(mp, pg_num) +
 		private_data_size;
+#endif /* RTE_NEXT_ABI */
 	obj = RTE_PTR_ALIGN_CEIL(obj, RTE_MEMPOOL_ALIGN);
 
 	/* populate address translation fields. */
@@ -613,9 +635,8 @@ rte_mempool_xmem_create(const char *name, unsigned n, unsigned elt_size,
 		mp->elt_va_start = (uintptr_t)obj;
 		mp->elt_pa[0] = mp->phys_addr +
 			(mp->elt_va_start - (uintptr_t)mp);
-
-	/* mempool elements in a separate chunk of memory. */
 	} else {
+		/* mempool elements in a separate chunk of memory. */
 		mp->elt_va_start = (uintptr_t)vaddr;
 		memcpy(mp->elt_pa, paddr, sizeof (mp->elt_pa[0]) * pg_num);
 	}
@@ -645,10 +666,21 @@ unsigned
 rte_mempool_count(const struct rte_mempool *mp)
 {
 	unsigned count;
+#ifdef RTE_NEXT_ABI
+	unsigned lcore_id;
 
 	count = rte_ring_count(mp->ring);
 
+	if (mp->cache_size == 0)
+		return count;
+
+	for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++)
+		count += mp->local_cache[lcore_id].len;
+#else
 #if RTE_MEMPOOL_CACHE_MAX_SIZE > 0
+
+	count = rte_ring_count(mp->ring);
+
 	{
 		unsigned lcore_id;
 		if (mp->cache_size == 0)
@@ -658,7 +690,7 @@ rte_mempool_count(const struct rte_mempool *mp)
 			count += mp->local_cache[lcore_id].len;
 	}
 #endif
-
+#endif /* RTE_NEXT_ABI */
 	/*
 	 * due to race condition (access to len is not locked), the
 	 * total can be greater than size... so fix the result
@@ -672,6 +704,24 @@ rte_mempool_count(const struct rte_mempool *mp)
 static unsigned
 rte_mempool_dump_cache(FILE *f, const struct rte_mempool *mp)
 {
+#ifdef RTE_NEXT_ABI
+	unsigned lcore_id;
+	unsigned count = 0;
+	unsigned cache_count;
+
+	fprintf(f, "  cache infos:\n");
+	fprintf(f, "    cache_size=%"PRIu32"\n", mp->cache_size);
+	if (mp->cache_size == 0)
+		return count;
+
+	for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++) {
+		cache_count = mp->local_cache[lcore_id].len;
+		fprintf(f, "    cache_count[%u]=%u\n", lcore_id, cache_count);
+		count += cache_count;
+	}
+	fprintf(f, "    total_cache_count=%u\n", count);
+	return count;
+#else
 #if RTE_MEMPOOL_CACHE_MAX_SIZE > 0
 	unsigned lcore_id;
 	unsigned count = 0;
@@ -691,6 +741,7 @@ rte_mempool_dump_cache(FILE *f, const struct rte_mempool *mp)
 	fprintf(f, "  cache disabled\n");
 	return 0;
 #endif
+#endif /* RTE_NEXT_ABI */
 }
 
 #ifdef RTE_LIBRTE_MEMPOOL_DEBUG
@@ -755,6 +806,26 @@ mempool_audit_cookies(const struct rte_mempool *mp)
 #define mempool_audit_cookies(mp) do {} while(0)
 #endif
 
+#ifdef RTE_NEXT_ABI
+/* check cookies before and after objects */
+static void
+mempool_audit_cache(const struct rte_mempool *mp)
+{
+	/* check cache size consistency */
+	unsigned lcore_id;
+
+	if (mp->cache_size == 0)
+		return;
+
+	for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++) {
+		if (mp->local_cache[lcore_id].len > mp->cache_flushthresh) {
+			RTE_LOG(CRIT, MEMPOOL, "badness on cache[%u]\n",
+				lcore_id);
+			rte_panic("MEMPOOL: invalid cache len\n");
+		}
+	}
+}
+#else
 #if RTE_MEMPOOL_CACHE_MAX_SIZE > 0
 /* check cookies before and after objects */
 static void
@@ -773,7 +844,7 @@ mempool_audit_cache(const struct rte_mempool *mp)
 #else
 #define mempool_audit_cache(mp) do {} while(0)
 #endif
-
+#endif /* RTE_NEXT_ABI */
 
 /* check the consistency of mempool (size, cookies, ...) */
 void
diff --git a/lib/librte_mempool/rte_mempool.h b/lib/librte_mempool/rte_mempool.h
index 6e2390a..fc9b595 100644
--- a/lib/librte_mempool/rte_mempool.h
+++ b/lib/librte_mempool/rte_mempool.h
@@ -95,6 +95,19 @@ struct rte_mempool_debug_stats {
 } __rte_cache_aligned;
 #endif
 
+#ifdef RTE_NEXT_ABI
+/**
+ * A structure that stores a per-core object cache.
+ */
+struct rte_mempool_cache {
+	unsigned len; /**< Cache len */
+	/*
+	 * Cache is allocated to this size to allow it to overflow in certain
+	 * cases to avoid needless emptying of cache.
+	 */
+	void *objs[RTE_MEMPOOL_CACHE_MAX_SIZE * 3]; /**< Cache objects */
+} __rte_cache_aligned;
+#else
 #if RTE_MEMPOOL_CACHE_MAX_SIZE > 0
 /**
  * A structure that stores a per-core object cache.
@@ -108,6 +121,7 @@ struct rte_mempool_cache {
 	void *objs[RTE_MEMPOOL_CACHE_MAX_SIZE * 3]; /**< Cache objects */
 } __rte_cache_aligned;
 #endif /* RTE_MEMPOOL_CACHE_MAX_SIZE > 0 */
+#endif /* RTE_NEXT_ABI */
 
 /**
  * A structure that stores the size of mempool elements.
@@ -194,10 +208,14 @@ struct rte_mempool {
 
 	unsigned private_data_size;      /**< Size of private data. */
 
+#ifdef RTE_NEXT_ABI
+	struct rte_mempool_cache *local_cache; /**< Per-lcore local cache */
+#else
 #if RTE_MEMPOOL_CACHE_MAX_SIZE > 0
 	/** Per-lcore local cache. */
 	struct rte_mempool_cache local_cache[RTE_MAX_LCORE];
 #endif
+#endif  /* RTE_NEXT_ABI */
 
 #ifdef RTE_LIBRTE_MEMPOOL_DEBUG
 	/** Per-lcore statistics. */
@@ -246,6 +264,26 @@ struct rte_mempool {
 #define __MEMPOOL_STAT_ADD(mp, name, n) do {} while(0)
 #endif
 
+#ifdef RTE_NEXT_ABI
+/**
+ * Size of elt_pa array size based on number of pages. (Internal use)
+ */
+#define __PA_SIZE(mp, pgn) \
+	RTE_ALIGN_CEIL((((pgn) - RTE_DIM((mp)->elt_pa)) * \
+	sizeof((mp)->elt_pa[0])), RTE_CACHE_LINE_SIZE)
+
+/**
+ * Calculate the size of the mempool header.
+ *
+ * @param mp
+ *   Pointer to the memory pool.
+ * @param pgn
+ *   Number of pages used to store mempool objects.
+ */
+#define MEMPOOL_HEADER_SIZE(mp, pgn, cs) \
+	(sizeof(*(mp)) + __PA_SIZE(mp, pgn) + (((cs) == 0) ? 0 : \
+	(sizeof(struct rte_mempool_cache) * RTE_MAX_LCORE)))
+#else
 /**
  * Calculate the size of the mempool header.
  *
@@ -257,7 +295,7 @@ struct rte_mempool {
 #define	MEMPOOL_HEADER_SIZE(mp, pgn)	(sizeof(*(mp)) + \
 	RTE_ALIGN_CEIL(((pgn) - RTE_DIM((mp)->elt_pa)) * \
 	sizeof ((mp)->elt_pa[0]), RTE_CACHE_LINE_SIZE))
-
+#endif /* RTE_NEXT_ABI */
 /**
  * Return true if the whole mempool is in contiguous memory.
  */
@@ -755,19 +793,25 @@ static inline void __attribute__((always_inline))
 __mempool_put_bulk(struct rte_mempool *mp, void * const *obj_table,
 		    unsigned n, int is_mp)
 {
+#ifndef RTE_NEXT_ABI	/* Note: ifndef */
 #if RTE_MEMPOOL_CACHE_MAX_SIZE > 0
+#endif /* RTE_NEXT_ABI */
 	struct rte_mempool_cache *cache;
 	uint32_t index;
 	void **cache_objs;
 	unsigned lcore_id = rte_lcore_id();
 	uint32_t cache_size = mp->cache_size;
 	uint32_t flushthresh = mp->cache_flushthresh;
+#ifndef RTE_NEXT_ABI	/* Note: ifndef */
 #endif /* RTE_MEMPOOL_CACHE_MAX_SIZE > 0 */
+#endif /* RTE_NEXT_ABI */
 
 	/* increment stat now, adding in mempool always success */
 	__MEMPOOL_STAT_ADD(mp, put, n);
 
+#ifndef RTE_NEXT_ABI	/* Note: ifndef */
 #if RTE_MEMPOOL_CACHE_MAX_SIZE > 0
+#endif /* RTE_NEXT_ABI */
 	/* cache is not enabled or single producer or non-EAL thread */
 	if (unlikely(cache_size == 0 || is_mp == 0 ||
 		     lcore_id >= RTE_MAX_LCORE))
@@ -802,7 +846,9 @@ __mempool_put_bulk(struct rte_mempool *mp, void * const *obj_table,
 	return;
 
 ring_enqueue:
+#ifndef RTE_NEXT_ABI	/* Note: ifndef */
 #endif /* RTE_MEMPOOL_CACHE_MAX_SIZE > 0 */
+#endif /* RTE_NEXT_ABI */
 
 	/* push remaining objects in ring */
 #ifdef RTE_LIBRTE_MEMPOOL_DEBUG
@@ -946,7 +992,9 @@ __mempool_get_bulk(struct rte_mempool *mp, void **obj_table,
 		   unsigned n, int is_mc)
 {
 	int ret;
+#ifndef RTE_NEXT_ABI	/* Note: ifndef */
 #if RTE_MEMPOOL_CACHE_MAX_SIZE > 0
+#endif /* RTE_NEXT_ABI */
 	struct rte_mempool_cache *cache;
 	uint32_t index, len;
 	void **cache_objs;
@@ -992,7 +1040,9 @@ __mempool_get_bulk(struct rte_mempool *mp, void **obj_table,
 	return 0;
 
 ring_dequeue:
+#ifndef RTE_NEXT_ABI	/* Note: ifndef */
 #endif /* RTE_MEMPOOL_CACHE_MAX_SIZE > 0 */
+#endif /* RTE_NEXT_ABI */
 
 	/* get remaining objects from ring */
 	if (is_mc)
@@ -1293,7 +1343,12 @@ void rte_mempool_audit(const struct rte_mempool *mp);
  */
 static inline void *rte_mempool_get_priv(struct rte_mempool *mp)
 {
+#ifdef RTE_NEXT_ABI
+	return (char *)mp +
+		MEMPOOL_HEADER_SIZE(mp, mp->pg_num, mp->cache_size);
+#else
 	return (char *)mp + MEMPOOL_HEADER_SIZE(mp, mp->pg_num);
+#endif /* RTE_NEXT_ABI */
 }
 
 /**
-- 
2.7.0

Re: [dpdk-dev] [PATCH v2] mempool: reduce rte_mempool structure size

[Olivier MATZ]

Hi Keith,

Thank you for adding the RTE_NEXT_ABI. I think this is the way
described in the process. Your changes will be available in next
version (16.4) for people compiling with RTE_NEXT_ABI=y, and in
16.7 without option (I'm just surprised that RTE_NEXT_ABI=y in
default configs...).

I think a deprecation notice should also be added in this commit
in doc/guides/rel_notes/deprecation.rst.

Please also find comments below.

On 02/09/2016 06:30 PM, Keith Wiles wrote:

> diff --git a/config/defconfig_x86_64-native-linuxapp-gcc b/config/defconfig_x86_64-native-linuxapp-gcc
> index 60baf5b..02e9ace 100644
> --- a/config/defconfig_x86_64-native-linuxapp-gcc
> +++ b/config/defconfig_x86_64-native-linuxapp-gcc
> @@ -40,3 +40,8 @@ CONFIG_RTE_ARCH_64=y
>  
>  CONFIG_RTE_TOOLCHAIN="gcc"
>  CONFIG_RTE_TOOLCHAIN_GCC=y
> +CONFIG_RTE_BUILD_SHARED_LIB=y
> +CONFIG_RTE_NEXT_ABI=n
> +CONFIG_RTE_EAL_IGB_UIO=n
> +CONFIG_RTE_LIBRTE_KNI=n
> +CONFIG_RTE_KNI_KMOD=n

I think this should not be part of the patch.

> @@ -672,6 +704,24 @@ rte_mempool_count(const struct rte_mempool *mp)
>  static unsigned
>  rte_mempool_dump_cache(FILE *f, const struct rte_mempool *mp)
>  {
> +#ifdef RTE_NEXT_ABI
> +	unsigned lcore_id;
> +	unsigned count = 0;
> +	unsigned cache_count;
> +
> +	fprintf(f, "  cache infos:\n");
> +	fprintf(f, "    cache_size=%"PRIu32"\n", mp->cache_size);
> +	if (mp->cache_size == 0)
> +		return count;
> +
> +	for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++) {
> +		cache_count = mp->local_cache[lcore_id].len;
> +		fprintf(f, "    cache_count[%u]=%u\n", lcore_id, cache_count);
> +		count += cache_count;
> +	}
> +	fprintf(f, "    total_cache_count=%u\n", count);
> +	return count;
> +#else
>  #if RTE_MEMPOOL_CACHE_MAX_SIZE > 0
>  	unsigned lcore_id;
>  	unsigned count = 0;

I think in this case we could avoid to duplicate the code without
beeing unclear by using the proper #ifdefs:

#if RTE_MEMPOOL_CACHE_MAX_SIZE > 0 || defined(RTE_NEXT_ABI)
	/* common code */
#ifdef RTE_NEXT_ABI
	if (mp->cache_size == 0)
		return count;
#endif
	/* common code */
#else
...
#endif


> @@ -755,6 +806,26 @@ mempool_audit_cookies(const struct rte_mempool *mp)
>  #define mempool_audit_cookies(mp) do {} while(0)
>  #endif
>  
> +#ifdef RTE_NEXT_ABI
> +/* check cookies before and after objects */
> +static void
> +mempool_audit_cache(const struct rte_mempool *mp)
> +{
> +	/* check cache size consistency */
> +	unsigned lcore_id;
> +
> +	if (mp->cache_size == 0)
> +		return;
> +
> +	for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++) {
> +		if (mp->local_cache[lcore_id].len > mp->cache_flushthresh) {
> +			RTE_LOG(CRIT, MEMPOOL, "badness on cache[%u]\n",
> +				lcore_id);
> +			rte_panic("MEMPOOL: invalid cache len\n");
> +		}
> +	}
> +}
> +#else

same here

> diff --git a/lib/librte_mempool/rte_mempool.h b/lib/librte_mempool/rte_mempool.h
> index 6e2390a..fc9b595 100644
> --- a/lib/librte_mempool/rte_mempool.h
> +++ b/lib/librte_mempool/rte_mempool.h
> @@ -95,6 +95,19 @@ struct rte_mempool_debug_stats {
>  } __rte_cache_aligned;
>  #endif
>  
> +#ifdef RTE_NEXT_ABI
> +/**
> + * A structure that stores a per-core object cache.
> + */
> +struct rte_mempool_cache {
> +	unsigned len; /**< Cache len */
> +	/*
> +	 * Cache is allocated to this size to allow it to overflow in certain
> +	 * cases to avoid needless emptying of cache.
> +	 */
> +	void *objs[RTE_MEMPOOL_CACHE_MAX_SIZE * 3]; /**< Cache objects */
> +} __rte_cache_aligned;
> +#else

same here



> @@ -755,19 +793,25 @@ static inline void __attribute__((always_inline))
>  __mempool_put_bulk(struct rte_mempool *mp, void * const *obj_table,
>  		    unsigned n, int is_mp)
>  {
> +#ifndef RTE_NEXT_ABI	/* Note: ifndef */
>  #if RTE_MEMPOOL_CACHE_MAX_SIZE > 0
> +#endif /* RTE_NEXT_ABI */
>  	struct rte_mempool_cache *cache;
>  	uint32_t index;
>  	void **cache_objs;
>  	unsigned lcore_id = rte_lcore_id();
>  	uint32_t cache_size = mp->cache_size;
>  	uint32_t flushthresh = mp->cache_flushthresh;
> +#ifndef RTE_NEXT_ABI	/* Note: ifndef */
>  #endif /* RTE_MEMPOOL_CACHE_MAX_SIZE > 0 */
> +#endif /* RTE_NEXT_ABI */

this looks strange... I think it does not work properly.
Why not
#if RTE_MEMPOOL_CACHE_MAX_SIZE > 0 || defined(RTE_NEXT_ABI)

>  	/* increment stat now, adding in mempool always success */
>  	__MEMPOOL_STAT_ADD(mp, put, n);
>  
> +#ifndef RTE_NEXT_ABI	/* Note: ifndef */
>  #if RTE_MEMPOOL_CACHE_MAX_SIZE > 0
> +#endif /* RTE_NEXT_ABI */
>  	/* cache is not enabled or single producer or non-EAL thread */
>  	if (unlikely(cache_size == 0 || is_mp == 0 ||
>  		     lcore_id >= RTE_MAX_LCORE))
> @@ -802,7 +846,9 @@ __mempool_put_bulk(struct rte_mempool *mp, void * const *obj_table,
>  	return;
>  
>  ring_enqueue:
> +#ifndef RTE_NEXT_ABI	/* Note: ifndef */
>  #endif /* RTE_MEMPOOL_CACHE_MAX_SIZE > 0 */
> +#endif /* RTE_NEXT_ABI */
>  
>  	/* push remaining objects in ring */
>  #ifdef RTE_LIBRTE_MEMPOOL_DEBUG
> @@ -946,7 +992,9 @@ __mempool_get_bulk(struct rte_mempool *mp, void **obj_table,
>  		   unsigned n, int is_mc)
>  {
>  	int ret;
> +#ifndef RTE_NEXT_ABI	/* Note: ifndef */
>  #if RTE_MEMPOOL_CACHE_MAX_SIZE > 0
> +#endif /* RTE_NEXT_ABI */
>  	struct rte_mempool_cache *cache;
>  	uint32_t index, len;
>  	void **cache_objs;
> @@ -992,7 +1040,9 @@ __mempool_get_bulk(struct rte_mempool *mp, void **obj_table,
>  	return 0;
>  
>  ring_dequeue:
> +#ifndef RTE_NEXT_ABI	/* Note: ifndef */
>  #endif /* RTE_MEMPOOL_CACHE_MAX_SIZE > 0 */
> +#endif /* RTE_NEXT_ABI */
>  
>  	/* get remaining objects from ring */
>  	if (is_mc)

Same in those cases.



Regards,
Olivier

Re: [dpdk-dev] [PATCH v2] mempool: reduce rte_mempool structure size

[Wiles, Keith]

>Hi Keith,
>
>Thank you for adding the RTE_NEXT_ABI. I think this is the way
>described in the process. Your changes will be available in next
>version (16.4) for people compiling with RTE_NEXT_ABI=y, and in
>16.7 without option (I'm just surprised that RTE_NEXT_ABI=y in
>default configs...).
>
>I think a deprecation notice should also be added in this commit
>in doc/guides/rel_notes/deprecation.rst.

Will add the text.
>
>Please also find comments below.
>
>On 02/09/2016 06:30 PM, Keith Wiles wrote:
>
>> diff --git a/config/defconfig_x86_64-native-linuxapp-gcc b/config/defconfig_x86_64-native-linuxapp-gcc
>> index 60baf5b..02e9ace 100644
>> --- a/config/defconfig_x86_64-native-linuxapp-gcc
>> +++ b/config/defconfig_x86_64-native-linuxapp-gcc
>> @@ -40,3 +40,8 @@ CONFIG_RTE_ARCH_64=y
>>  
>>  CONFIG_RTE_TOOLCHAIN="gcc"
>>  CONFIG_RTE_TOOLCHAIN_GCC=y
>> +CONFIG_RTE_BUILD_SHARED_LIB=y
>> +CONFIG_RTE_NEXT_ABI=n
>> +CONFIG_RTE_EAL_IGB_UIO=n
>> +CONFIG_RTE_LIBRTE_KNI=n
>> +CONFIG_RTE_KNI_KMOD=n

Hmm, not sure where this came from, but will remove it.
>
>I think this should not be part of the patch.
>
>> @@ -672,6 +704,24 @@ rte_mempool_count(const struct rte_mempool *mp)
>>  static unsigned
>>  rte_mempool_dump_cache(FILE *f, const struct rte_mempool *mp)
>>  {
>> +#ifdef RTE_NEXT_ABI
>> +	unsigned lcore_id;
>> +	unsigned count = 0;
>> +	unsigned cache_count;
>> +
>> +	fprintf(f, "  cache infos:\n");
>> +	fprintf(f, "    cache_size=%"PRIu32"\n", mp->cache_size);
>> +	if (mp->cache_size == 0)
>> +		return count;
>> +
>> +	for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++) {
>> +		cache_count = mp->local_cache[lcore_id].len;
>> +		fprintf(f, "    cache_count[%u]=%u\n", lcore_id, cache_count);
>> +		count += cache_count;
>> +	}
>> +	fprintf(f, "    total_cache_count=%u\n", count);
>> +	return count;
>> +#else
>>  #if RTE_MEMPOOL_CACHE_MAX_SIZE > 0
>>  	unsigned lcore_id;
>>  	unsigned count = 0;
>
>I think in this case we could avoid to duplicate the code without
>beeing unclear by using the proper #ifdefs:

I was struggling with how it should be done. I like to see clear ifdefs and be able to see the complete code for a given case. In these cases I wanted to make it simple to remove the code quickly by just deleting lines instead of editing lines. I will follow your suggestion.
>
>#if RTE_MEMPOOL_CACHE_MAX_SIZE > 0 || defined(RTE_NEXT_ABI)
>	/* common code */
>#ifdef RTE_NEXT_ABI
>	if (mp->cache_size == 0)
>		return count;
>#endif
>	/* common code */
>#else
>...
>#endif
>
>
>> @@ -755,6 +806,26 @@ mempool_audit_cookies(const struct rte_mempool *mp)
>>  #define mempool_audit_cookies(mp) do {} while(0)
>>  #endif
>>  
>> +#ifdef RTE_NEXT_ABI
>> +/* check cookies before and after objects */
>> +static void
>> +mempool_audit_cache(const struct rte_mempool *mp)
>> +{
>> +	/* check cache size consistency */
>> +	unsigned lcore_id;
>> +
>> +	if (mp->cache_size == 0)
>> +		return;
>> +
>> +	for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++) {
>> +		if (mp->local_cache[lcore_id].len > mp->cache_flushthresh) {
>> +			RTE_LOG(CRIT, MEMPOOL, "badness on cache[%u]\n",
>> +				lcore_id);
>> +			rte_panic("MEMPOOL: invalid cache len\n");
>> +		}
>> +	}
>> +}
>> +#else
>
>same here
>
>> diff --git a/lib/librte_mempool/rte_mempool.h b/lib/librte_mempool/rte_mempool.h
>> index 6e2390a..fc9b595 100644
>> --- a/lib/librte_mempool/rte_mempool.h
>> +++ b/lib/librte_mempool/rte_mempool.h
>> @@ -95,6 +95,19 @@ struct rte_mempool_debug_stats {
>>  } __rte_cache_aligned;
>>  #endif
>>  
>> +#ifdef RTE_NEXT_ABI
>> +/**
>> + * A structure that stores a per-core object cache.
>> + */
>> +struct rte_mempool_cache {
>> +	unsigned len; /**< Cache len */
>> +	/*
>> +	 * Cache is allocated to this size to allow it to overflow in certain
>> +	 * cases to avoid needless emptying of cache.
>> +	 */
>> +	void *objs[RTE_MEMPOOL_CACHE_MAX_SIZE * 3]; /**< Cache objects */
>> +} __rte_cache_aligned;
>> +#else
>
>same here
>
>
>
>> @@ -755,19 +793,25 @@ static inline void __attribute__((always_inline))
>>  __mempool_put_bulk(struct rte_mempool *mp, void * const *obj_table,
>>  		    unsigned n, int is_mp)
>>  {
>> +#ifndef RTE_NEXT_ABI	/* Note: ifndef */
>>  #if RTE_MEMPOOL_CACHE_MAX_SIZE > 0
>> +#endif /* RTE_NEXT_ABI */
>>  	struct rte_mempool_cache *cache;
>>  	uint32_t index;
>>  	void **cache_objs;
>>  	unsigned lcore_id = rte_lcore_id();
>>  	uint32_t cache_size = mp->cache_size;
>>  	uint32_t flushthresh = mp->cache_flushthresh;
>> +#ifndef RTE_NEXT_ABI	/* Note: ifndef */
>>  #endif /* RTE_MEMPOOL_CACHE_MAX_SIZE > 0 */
>> +#endif /* RTE_NEXT_ABI */
>
>this looks strange... I think it does not work properly.
>Why not
>#if RTE_MEMPOOL_CACHE_MAX_SIZE > 0 || defined(RTE_NEXT_ABI)

Yes, it is strange :-(
>
>>  	/* increment stat now, adding in mempool always success */
>>  	__MEMPOOL_STAT_ADD(mp, put, n);
>>  
>> +#ifndef RTE_NEXT_ABI	/* Note: ifndef */
>>  #if RTE_MEMPOOL_CACHE_MAX_SIZE > 0
>> +#endif /* RTE_NEXT_ABI */
>>  	/* cache is not enabled or single producer or non-EAL thread */
>>  	if (unlikely(cache_size == 0 || is_mp == 0 ||
>>  		     lcore_id >= RTE_MAX_LCORE))
>> @@ -802,7 +846,9 @@ __mempool_put_bulk(struct rte_mempool *mp, void * const *obj_table,
>>  	return;
>>  
>>  ring_enqueue:
>> +#ifndef RTE_NEXT_ABI	/* Note: ifndef */
>>  #endif /* RTE_MEMPOOL_CACHE_MAX_SIZE > 0 */
>> +#endif /* RTE_NEXT_ABI */
>>  
>>  	/* push remaining objects in ring */
>>  #ifdef RTE_LIBRTE_MEMPOOL_DEBUG
>> @@ -946,7 +992,9 @@ __mempool_get_bulk(struct rte_mempool *mp, void **obj_table,
>>  		   unsigned n, int is_mc)
>>  {
>>  	int ret;
>> +#ifndef RTE_NEXT_ABI	/* Note: ifndef */
>>  #if RTE_MEMPOOL_CACHE_MAX_SIZE > 0
>> +#endif /* RTE_NEXT_ABI */
>>  	struct rte_mempool_cache *cache;
>>  	uint32_t index, len;
>>  	void **cache_objs;
>> @@ -992,7 +1040,9 @@ __mempool_get_bulk(struct rte_mempool *mp, void **obj_table,
>>  	return 0;
>>  
>>  ring_dequeue:
>> +#ifndef RTE_NEXT_ABI	/* Note: ifndef */
>>  #endif /* RTE_MEMPOOL_CACHE_MAX_SIZE > 0 */
>> +#endif /* RTE_NEXT_ABI */
>>  
>>  	/* get remaining objects from ring */
>>  	if (is_mc)
>
>Same in those cases.
>
>
>
>Regards,
>Olivier
>


Regards,
Keith

Re: [dpdk-dev] [PATCH v2] mempool: reduce rte_mempool structure size

[Wiles, Keith]

>Hi Keith,
>
>Thank you for adding the RTE_NEXT_ABI. I think this is the way
>described in the process. Your changes will be available in next
>version (16.4) for people compiling with RTE_NEXT_ABI=y, and in
>16.7 without option (I'm just surprised that RTE_NEXT_ABI=y in
>default configs...).
>
>I think a deprecation notice should also be added in this commit
>in doc/guides/rel_notes/deprecation.rst.
>
>Please also find comments below.
>
>On 02/09/2016 06:30 PM, Keith Wiles wrote:
>
>> diff --git a/config/defconfig_x86_64-native-linuxapp-gcc b/config/defconfig_x86_64-native-linuxapp-gcc
>> index 60baf5b..02e9ace 100644
>> --- a/config/defconfig_x86_64-native-linuxapp-gcc
>> +++ b/config/defconfig_x86_64-native-linuxapp-gcc
>> @@ -40,3 +40,8 @@ CONFIG_RTE_ARCH_64=y
>>  
>>  CONFIG_RTE_TOOLCHAIN="gcc"
>>  CONFIG_RTE_TOOLCHAIN_GCC=y
>> +CONFIG_RTE_BUILD_SHARED_LIB=y
>> +CONFIG_RTE_NEXT_ABI=n
>> +CONFIG_RTE_EAL_IGB_UIO=n
>> +CONFIG_RTE_LIBRTE_KNI=n
>> +CONFIG_RTE_KNI_KMOD=n
>
>I think this should not be part of the patch.
>
>> @@ -672,6 +704,24 @@ rte_mempool_count(const struct rte_mempool *mp)
>>  static unsigned
>>  rte_mempool_dump_cache(FILE *f, const struct rte_mempool *mp)
>>  {
>> +#ifdef RTE_NEXT_ABI
>> +	unsigned lcore_id;
>> +	unsigned count = 0;
>> +	unsigned cache_count;
>> +
>> +	fprintf(f, "  cache infos:\n");
>> +	fprintf(f, "    cache_size=%"PRIu32"\n", mp->cache_size);
>> +	if (mp->cache_size == 0)
>> +		return count;
>> +
>> +	for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++) {
>> +		cache_count = mp->local_cache[lcore_id].len;
>> +		fprintf(f, "    cache_count[%u]=%u\n", lcore_id, cache_count);
>> +		count += cache_count;
>> +	}
>> +	fprintf(f, "    total_cache_count=%u\n", count);
>> +	return count;
>> +#else
>>  #if RTE_MEMPOOL_CACHE_MAX_SIZE > 0
>>  	unsigned lcore_id;
>>  	unsigned count = 0;
>
>I think in this case we could avoid to duplicate the code without
>beeing unclear by using the proper #ifdefs:
>
>#if RTE_MEMPOOL_CACHE_MAX_SIZE > 0 || defined(RTE_NEXT_ABI)
>	/* common code */
>#ifdef RTE_NEXT_ABI
>	if (mp->cache_size == 0)
>		return count;
>#endif
>	/* common code */
>#else
>...
>#endif

Started looking at this change and the problem is I want to remove the ifdef RTE_MEMPOOL.. As well as the #else/#endif code. If I do as you suggest it does not appear to be clearer when someone goes back to remove the code, they may think the #ifdef RTE_MEMPOOL/#else/#endif are still required.

>
>
>> @@ -755,6 +806,26 @@ mempool_audit_cookies(const struct rte_mempool *mp)
>>  #define mempool_audit_cookies(mp) do {} while(0)
>>  #endif
>>  
>> +#ifdef RTE_NEXT_ABI
>> +/* check cookies before and after objects */
>> +static void
>> +mempool_audit_cache(const struct rte_mempool *mp)
>> +{
>> +	/* check cache size consistency */
>> +	unsigned lcore_id;
>> +
>> +	if (mp->cache_size == 0)
>> +		return;
>> +
>> +	for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++) {
>> +		if (mp->local_cache[lcore_id].len > mp->cache_flushthresh) {
>> +			RTE_LOG(CRIT, MEMPOOL, "badness on cache[%u]\n",
>> +				lcore_id);
>> +			rte_panic("MEMPOOL: invalid cache len\n");
>> +		}
>> +	}
>> +}
>> +#else
>
>same here

The same comment here.
>
>> diff --git a/lib/librte_mempool/rte_mempool.h b/lib/librte_mempool/rte_mempool.h
>> index 6e2390a..fc9b595 100644
>> --- a/lib/librte_mempool/rte_mempool.h
>> +++ b/lib/librte_mempool/rte_mempool.h
>> @@ -95,6 +95,19 @@ struct rte_mempool_debug_stats {
>>  } __rte_cache_aligned;
>>  #endif
>>  
>> +#ifdef RTE_NEXT_ABI
>> +/**
>> + * A structure that stores a per-core object cache.
>> + */
>> +struct rte_mempool_cache {
>> +	unsigned len; /**< Cache len */
>> +	/*
>> +	 * Cache is allocated to this size to allow it to overflow in certain
>> +	 * cases to avoid needless emptying of cache.
>> +	 */
>> +	void *objs[RTE_MEMPOOL_CACHE_MAX_SIZE * 3]; /**< Cache objects */
>> +} __rte_cache_aligned;
>> +#else
>
>same here

Same for this one.
>
>
>
>> @@ -755,19 +793,25 @@ static inline void __attribute__((always_inline))
>>  __mempool_put_bulk(struct rte_mempool *mp, void * const *obj_table,
>>  		    unsigned n, int is_mp)
>>  {
>> +#ifndef RTE_NEXT_ABI	/* Note: ifndef */
>>  #if RTE_MEMPOOL_CACHE_MAX_SIZE > 0
>> +#endif /* RTE_NEXT_ABI */
>>  	struct rte_mempool_cache *cache;
>>  	uint32_t index;
>>  	void **cache_objs;
>>  	unsigned lcore_id = rte_lcore_id();
>>  	uint32_t cache_size = mp->cache_size;
>>  	uint32_t flushthresh = mp->cache_flushthresh;
>> +#ifndef RTE_NEXT_ABI	/* Note: ifndef */
>>  #endif /* RTE_MEMPOOL_CACHE_MAX_SIZE > 0 */
>> +#endif /* RTE_NEXT_ABI */
>
>this looks strange... I think it does not work properly.
>Why not
>#if RTE_MEMPOOL_CACHE_MAX_SIZE > 0 || defined(RTE_NEXT_ABI)

Yes I agree the ifndef looks strange, but it should work as we want to remove the #ifdef RTE_MEMPOOL/#endif lines. This was the reason for the comment that it was a ifndef.
>
>>  	/* increment stat now, adding in mempool always success */
>>  	__MEMPOOL_STAT_ADD(mp, put, n);
>>  
>> +#ifndef RTE_NEXT_ABI	/* Note: ifndef */
>>  #if RTE_MEMPOOL_CACHE_MAX_SIZE > 0
>> +#endif /* RTE_NEXT_ABI */
>>  	/* cache is not enabled or single producer or non-EAL thread */
>>  	if (unlikely(cache_size == 0 || is_mp == 0 ||
>>  		     lcore_id >= RTE_MAX_LCORE))
>> @@ -802,7 +846,9 @@ __mempool_put_bulk(struct rte_mempool *mp, void * const *obj_table,
>>  	return;
>>  
>>  ring_enqueue:
>> +#ifndef RTE_NEXT_ABI	/* Note: ifndef */
>>  #endif /* RTE_MEMPOOL_CACHE_MAX_SIZE > 0 */
>> +#endif /* RTE_NEXT_ABI */
>>  
>>  	/* push remaining objects in ring */
>>  #ifdef RTE_LIBRTE_MEMPOOL_DEBUG
>> @@ -946,7 +992,9 @@ __mempool_get_bulk(struct rte_mempool *mp, void **obj_table,
>>  		   unsigned n, int is_mc)
>>  {
>>  	int ret;
>> +#ifndef RTE_NEXT_ABI	/* Note: ifndef */
>>  #if RTE_MEMPOOL_CACHE_MAX_SIZE > 0
>> +#endif /* RTE_NEXT_ABI */
>>  	struct rte_mempool_cache *cache;
>>  	uint32_t index, len;
>>  	void **cache_objs;
>> @@ -992,7 +1040,9 @@ __mempool_get_bulk(struct rte_mempool *mp, void **obj_table,
>>  	return 0;
>>  
>>  ring_dequeue:
>> +#ifndef RTE_NEXT_ABI	/* Note: ifndef */
>>  #endif /* RTE_MEMPOOL_CACHE_MAX_SIZE > 0 */
>> +#endif /* RTE_NEXT_ABI */
>>  
>>  	/* get remaining objects from ring */
>>  	if (is_mc)
>
>Same in those cases.

The #ifdef RTE_MEMPOOL/#endif lines need to be removed when deprecated.
>
>
>Regards,
>Olivier
>


Regards,
Keith

Re: [dpdk-dev] [PATCH v2] mempool: reduce rte_mempool structure size

[Olivier MATZ]

Hi Keith,

On 02/10/2016 07:35 PM, Wiles, Keith wrote:
>>> @@ -672,6 +704,24 @@ rte_mempool_count(const struct rte_mempool *mp)
>>>  static unsigned
>>>  rte_mempool_dump_cache(FILE *f, const struct rte_mempool *mp)
>>>  {
>>> +#ifdef RTE_NEXT_ABI
>>> +	unsigned lcore_id;
>>> +	unsigned count = 0;
>>> +	unsigned cache_count;
>>> +
>>> +	fprintf(f, "  cache infos:\n");
>>> +	fprintf(f, "    cache_size=%"PRIu32"\n", mp->cache_size);
>>> +	if (mp->cache_size == 0)
>>> +		return count;
>>> +
>>> +	for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++) {
>>> +		cache_count = mp->local_cache[lcore_id].len;
>>> +		fprintf(f, "    cache_count[%u]=%u\n", lcore_id, cache_count);
>>> +		count += cache_count;
>>> +	}
>>> +	fprintf(f, "    total_cache_count=%u\n", count);
>>> +	return count;
>>> +#else
>>>  #if RTE_MEMPOOL_CACHE_MAX_SIZE > 0
>>>  	unsigned lcore_id;
>>>  	unsigned count = 0;
>>
>> I think in this case we could avoid to duplicate the code without
>> beeing unclear by using the proper #ifdefs:
>>
>> #if RTE_MEMPOOL_CACHE_MAX_SIZE > 0 || defined(RTE_NEXT_ABI)
>> 	/* common code */
>> #ifdef RTE_NEXT_ABI
>> 	if (mp->cache_size == 0)
>> 		return count;
>> #endif
>> 	/* common code */
>> #else
>> ...
>> #endif
> 
> Started looking at this change and the problem is I want to remove the ifdef RTE_MEMPOOL.. As well as the #else/#endif code. If I do as you suggest it does not appear to be clearer when someone goes back to remove the code, they may think the #ifdef RTE_MEMPOOL/#else/#endif are still required.

OK, makes sense.

>>> @@ -755,19 +793,25 @@ static inline void __attribute__((always_inline))
>>>  __mempool_put_bulk(struct rte_mempool *mp, void * const *obj_table,
>>>  		    unsigned n, int is_mp)
>>>  {
>>> +#ifndef RTE_NEXT_ABI	/* Note: ifndef */
>>>  #if RTE_MEMPOOL_CACHE_MAX_SIZE > 0
>>> +#endif /* RTE_NEXT_ABI */
>>>  	struct rte_mempool_cache *cache;
>>>  	uint32_t index;
>>>  	void **cache_objs;
>>>  	unsigned lcore_id = rte_lcore_id();
>>>  	uint32_t cache_size = mp->cache_size;
>>>  	uint32_t flushthresh = mp->cache_flushthresh;
>>> +#ifndef RTE_NEXT_ABI	/* Note: ifndef */
>>>  #endif /* RTE_MEMPOOL_CACHE_MAX_SIZE > 0 */
>>> +#endif /* RTE_NEXT_ABI */
>>
>> this looks strange... I think it does not work properly.
>> Why not
>> #if RTE_MEMPOOL_CACHE_MAX_SIZE > 0 || defined(RTE_NEXT_ABI)
> 
> Yes I agree the ifndef looks strange, but it should work as we want to remove the #ifdef RTE_MEMPOOL/#endif lines. This was the reason for the comment that it was a ifndef.

It's not only strange, it's also probably not what you want to do:

	#ifndef RTE_NEXT_ABI	/* Note: ifndef */
	#if RTE_MEMPOOL_CACHE_MAX_SIZE > 0
	#endif /* RTE_NEXT_ABI */
	...

Here, the #endif corresponds to the second #if, not the first #ifdef.

Regards,
Olivier