[dpdk-dev] hash: fix incorrect bucket size usage

Message ID 1476235604-33734-1-git-send-email-pablo.de.lara.guarch@intel.com
State Accepted, archived
Delegated to: Thomas Monjalon
Headers show

Commit Message

De Lara Guarch, Pablo Oct. 12, 2016, 1:26 a.m.
Multiwriter insert function was using a fixed value for
the bucket size, instead of using the
RTE_HASH_BUCKET_ENTRIES macro, which value was changed
recently (making it inconsistent in this case).

Fixes: be856325cba3 ("hash: add scalable multi-writer insertion with Intel TSX")

Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
---
 lib/librte_hash/rte_cuckoo_hash_x86.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

Comments

Thomas Monjalon Oct. 12, 2016, 3:03 p.m. | #1
2016-10-12 02:26, Pablo de Lara:
> Multiwriter insert function was using a fixed value for
> the bucket size, instead of using the
> RTE_HASH_BUCKET_ENTRIES macro, which value was changed
> recently (making it inconsistent in this case).
> 
> Fixes: be856325cba3 ("hash: add scalable multi-writer insertion with Intel TSX")
> 
> Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>

Applied, thanks

Patch

diff --git a/lib/librte_hash/rte_cuckoo_hash_x86.h b/lib/librte_hash/rte_cuckoo_hash_x86.h
index 47aec6d..0c94244 100644
--- a/lib/librte_hash/rte_cuckoo_hash_x86.h
+++ b/lib/librte_hash/rte_cuckoo_hash_x86.h
@@ -167,7 +167,8 @@  rte_hash_cuckoo_make_space_mw_tm(const struct rte_hash *h,
 
 	/* Cuckoo bfs Search */
 	while (likely(tail != head && head <
-					queue + RTE_HASH_BFS_QUEUE_MAX_LEN - 4)) {
+					queue + RTE_HASH_BFS_QUEUE_MAX_LEN -
+					RTE_HASH_BUCKET_ENTRIES)) {
 		curr_bkt = tail->bkt;
 		for (i = 0; i < RTE_HASH_BUCKET_ENTRIES; i++) {
 			if (curr_bkt->key_idx[i] == EMPTY_SLOT) {