[dpdk-dev] [PATCH v2 5/6] hash: fix to have more accurate key slot size

[Yipeng Wang]

This commit calculates the needed key slot size more
accurately. The previous local cache fix requires
the free slot ring to be larger than actually needed.
The calculation of the value is inaccurate.

Fixes: 5915699153d7 ("hash: fix scaling by reducing contention")

Signed-off-by: Yipeng Wang <yipeng1.wang at intel.com>
---
 lib/librte_hash/rte_cuckoo_hash.c | 16 +++++++++++-----
 1 file changed, 11 insertions(+), 5 deletions(-)

diff --git a/lib/librte_hash/rte_cuckoo_hash.c b/lib/librte_hash/rte_cuckoo_hash.c
index d2c7629..4a90049 100644
--- a/lib/librte_hash/rte_cuckoo_hash.c
+++ b/lib/librte_hash/rte_cuckoo_hash.c
@@ -133,13 +133,13 @@ rte_hash_create(const struct rte_hash_parameters *params)
 		 * except for the first cache
 		 */
 		num_key_slots = params->entries + (RTE_MAX_LCORE - 1) *
-					LCORE_CACHE_SIZE + 1;
+					(LCORE_CACHE_SIZE - 1) + 1;
 	else
 		num_key_slots = params->entries + 1;
 
 	snprintf(ring_name, sizeof(ring_name), "HT_%s", params->name);
 	/* Create ring (Dummy slot index is not enqueued) */
-	r = rte_ring_create(ring_name, rte_align32pow2(num_key_slots - 1),
+	r = rte_ring_create(ring_name, rte_align32pow2(num_key_slots),
 			params->socket_id, 0);
 	if (r == NULL) {
 		RTE_LOG(ERR, HASH, "memory allocation failed\n");
@@ -293,7 +293,7 @@ rte_hash_create(const struct rte_hash_parameters *params)
 	}
 
 	/* Populate free slots ring. Entry zero is reserved for key misses. */
-	for (i = 1; i < params->entries + 1; i++)
+	for (i = 1; i < num_key_slots; i++)
 		rte_ring_sp_enqueue(r, (void *)((uintptr_t) i));
 
 	te->data = (void *) h;
@@ -412,7 +412,7 @@ void
 rte_hash_reset(struct rte_hash *h)
 {
 	void *ptr;
-	unsigned i;
+	uint32_t tot_ring_cnt, i;
 
 	if (h == NULL)
 		return;
@@ -426,7 +426,13 @@ rte_hash_reset(struct rte_hash *h)
 		rte_pause();
 
 	/* Repopulate the free slots ring. Entry zero is reserved for key misses */
-	for (i = 1; i < h->entries + 1; i++)
+	if (h->multi_writer_support)
+		tot_ring_cnt = h->entries + (RTE_MAX_LCORE - 1) *
+					(LCORE_CACHE_SIZE - 1);
+	else
+		tot_ring_cnt = h->entries;
+
+	for (i = 1; i < tot_ring_cnt + 1; i++)
 		rte_ring_sp_enqueue(h->free_slots, (void *)((uintptr_t) i));
 
 	if (h->multi_writer_support) {
-- 
2.7.4