[dpdk-dev] [PATCH v4] mempool: reduce rte_mempool structure size

[Keith Wiles]

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.

Change to be effective in release 16.07.

Signed-off-by: Keith Wiles <keith.wiles at intel.com>
---
* Patch v4 remove RTE_NEXT_ABI ifdefs for 16.07 integration, plus split
  out the deprecation notice into another patch email for 16.04 release.
* 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          |  4 +--
 lib/librte_mempool/rte_mempool.c | 55 ++++++++++++++++++----------------------
 lib/librte_mempool/rte_mempool.h | 29 ++++++++++-----------
 3 files changed, 40 insertions(+), 48 deletions(-)

diff --git a/app/test/test_mempool.c b/app/test/test_mempool.c
index f0f823b..10e1fa4 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..6f067f3 100644
--- a/lib/librte_mempool/rte_mempool.c
+++ b/lib/librte_mempool/rte_mempool.c
@@ -452,12 +452,8 @@ 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);
-#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);
@@ -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 +670,16 @@ 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 +687,6 @@ 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 +751,16 @@ 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 +769,6 @@ 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 9745bf0..8595e77 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);
 }
 
 /**
-- 
2.5.4 (Apple Git-61)