From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mga11.intel.com (mga11.intel.com [192.55.52.93]) by dpdk.org (Postfix) with ESMTP id 527F556A9 for ; Wed, 10 Feb 2016 22:19:42 +0100 (CET) Received: from fmsmga004.fm.intel.com ([10.253.24.48]) by fmsmga102.fm.intel.com with ESMTP; 10 Feb 2016 13:19:41 -0800 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.22,427,1449561600"; d="scan'208";a="45819418" Received: from bvanipen-mobl1.amr.corp.intel.com ([10.254.75.40]) by fmsmga004.fm.intel.com with ESMTP; 10 Feb 2016 13:19:41 -0800 From: Keith Wiles To: dev@dpdk.org Date: Wed, 10 Feb 2016 15:18:54 -0600 Message-Id: <1455139134-9826-1-git-send-email-keith.wiles@intel.com> X-Mailer: git-send-email 2.5.4 (Apple Git-61) In-Reply-To: <1455039006-86816-1-git-send-email-keith.wiles@intel.com> References: <1455039006-86816-1-git-send-email-keith.wiles@intel.com> Subject: [dpdk-dev] [PATCH v3] mempool: reduce rte_mempool structure size X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: patches and discussions about DPDK List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 10 Feb 2016 21:19:43 -0000 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 --- * Patch v3 fix up the ifdefs to correct some problems in removing ifdef lines. Added the ABI deprecation notice to the document file. * Patch v2 to add some comments and setup for RTE_NEXT_ABI changes. app/test/test_mempool.c | 5 +++ doc/guides/rel_notes/deprecation.rst | 7 +++ lib/librte_mempool/rte_mempool.c | 82 +++++++++++++++++++++++++++++++++--- lib/librte_mempool/rte_mempool.h | 46 ++++++++++++++++---- 4 files changed, 127 insertions(+), 13 deletions(-) diff --git a/app/test/test_mempool.c b/app/test/test_mempool.c index f0f823b..f3fba50 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/doc/guides/rel_notes/deprecation.rst b/doc/guides/rel_notes/deprecation.rst index e94d4a2..1b9d25e 100644 --- a/doc/guides/rel_notes/deprecation.rst +++ b/doc/guides/rel_notes/deprecation.rst @@ -49,3 +49,10 @@ Deprecation Notices commands (such as RETA update in testpmd). This should impact CMDLINE_PARSE_RESULT_BUFSIZE, STR_TOKEN_SIZE and RDLINE_BUF_SIZE. It should be integrated in release 2.3. + +* ABI change is planned for the rte_mempool structure to allow mempool + cache support to be dynamic depending on the mempool being created + needing cache support. Saves about 1.5M of memory per rte_mempool structure + by removing the per lcore cache memory. Change will occur after DPDK 16.04 + release. + diff --git a/lib/librte_mempool/rte_mempool.c b/lib/librte_mempool/rte_mempool.c index aff5f6d..5f21eaa 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) @@ -658,6 +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 @@ -672,6 +705,24 @@ 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 +742,7 @@ 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 +807,26 @@ 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 +845,7 @@ 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 9745bf0..b12d6a9 100644 --- a/lib/librte_mempool/rte_mempool.h +++ b/lib/librte_mempool/rte_mempool.h @@ -95,7 +95,7 @@ struct rte_mempool_debug_stats { } __rte_cache_aligned; #endif -#if RTE_MEMPOOL_CACHE_MAX_SIZE > 0 +#if RTE_MEMPOOL_CACHE_MAX_SIZE > 0 || defined(RTE_NEXT_ABI) /* Remove line */ /** * A structure that stores a per-core object cache. */ @@ -107,7 +107,7 @@ 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_MEMPOOL_CACHE_MAX_SIZE > 0 */ /* Remove line RTE_NEXT_ABI */ /** * A structure that stores the size of mempool elements. @@ -194,10 +194,14 @@ 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 +250,26 @@ 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. * @@ -257,6 +281,7 @@ 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 +780,19 @@ 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 +#if RTE_MEMPOOL_CACHE_MAX_SIZE > 0 || defined(RTE_NEXT_ABI) /* Remove line */ 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 */ +#endif /* RTE_MEMPOOL_CACHE_MAX_SIZE > 0 */ /* Remove line RTE_NEXT_ABI */ /* increment stat now, adding in mempool always success */ __MEMPOOL_STAT_ADD(mp, put, n); -#if RTE_MEMPOOL_CACHE_MAX_SIZE > 0 +#if RTE_MEMPOOL_CACHE_MAX_SIZE > 0 || defined(RTE_NEXT_ABI) /* Remove line */ /* 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 +827,7 @@ __mempool_put_bulk(struct rte_mempool *mp, void * const *obj_table, return; ring_enqueue: -#endif /* RTE_MEMPOOL_CACHE_MAX_SIZE > 0 */ +#endif /* RTE_MEMPOOL_CACHE_MAX_SIZE > 0 */ /* Remove line RTE_NEXT_ABI */ /* push remaining objects in ring */ #ifdef RTE_LIBRTE_MEMPOOL_DEBUG @@ -946,7 +971,7 @@ __mempool_get_bulk(struct rte_mempool *mp, void **obj_table, unsigned n, int is_mc) { int ret; -#if RTE_MEMPOOL_CACHE_MAX_SIZE > 0 +#if RTE_MEMPOOL_CACHE_MAX_SIZE > 0 || defined(RTE_NEXT_ABI) /* Remove line */ struct rte_mempool_cache *cache; uint32_t index, len; void **cache_objs; @@ -992,7 +1017,7 @@ __mempool_get_bulk(struct rte_mempool *mp, void **obj_table, return 0; ring_dequeue: -#endif /* RTE_MEMPOOL_CACHE_MAX_SIZE > 0 */ +#endif /* RTE_MEMPOOL_CACHE_MAX_SIZE > 0 */ /* Remove line RTE_NEXT_ABI */ /* get remaining objects from ring */ if (is_mc) @@ -1293,7 +1318,12 @@ 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 */ } /** -- 2.5.4 (Apple Git-61)