mempool: add cache guard to per-lcore debug statistics

The per-lcore debug statistics, if enabled, are frequently written by their individual lcores, so add a cache guard to prevent false sharing in case the CPU employs a next-N-lines (or similar) hardware prefetcher. Signed-off-by: Morten Brørup <[email protected]> Reviewed-by: Andrew Rybchenko <[email protected]>
DPDK · Oct 11, 2023 · a193421 · a193421
1 parent 0b765b4
commit a193421
Showing 1 changed file with 1 addition and 0 deletions.
diff --git a/lib/mempool/rte_mempool.h b/lib/mempool/rte_mempool.h
@@ -78,6 +78,7 @@ struct rte_mempool_debug_stats {
 	uint64_t get_fail_objs;        /**< Objects that failed to be allocated. */
 	uint64_t get_success_blks;     /**< Successful allocation number of contiguous blocks. */
 	uint64_t get_fail_blks;        /**< Failed allocation number of contiguous blocks. */
+	RTE_CACHE_GUARD;
 } __rte_cache_aligned;
 #endif