When getting objects from the mempool, the number of objects to get is
often constant at build time.
This patch adds another code path for this case, so the compiler can
optimize more, e.g. unroll the copy loop when the entire request is
satisfied from the cache.
On an Intel(R) Xeon(R) E5-2620 v4 CPU, and compiled with gcc 9.4.0,
mempool_perf_test with constant n shows an increase in rate_persec by an
average of 17 %, minimum 9.5 %, maximum 24 %.
The code path where the number of objects to get is unknown at build time
remains essentially unchanged.
Signed-off-by: Morten Brørup <m...@smartsharesystems.com>
---
lib/mempool/rte_mempool.h | 24 +++++++++++++++++++++---
1 file changed, 21 insertions(+), 3 deletions(-)
diff --git a/lib/mempool/rte_mempool.h b/lib/mempool/rte_mempool.h
index 9f530db24b..ade0100ec7 100644
--- a/lib/mempool/rte_mempool.h
+++ b/lib/mempool/rte_mempool.h
@@ -1500,15 +1500,33 @@ rte_mempool_do_generic_get(struct rte_mempool *mp, void
**obj_table,
if (unlikely(cache == NULL))
goto driver_dequeue;
- /* Use the cache as much as we have to return hot objects first */
- len = RTE_MIN(remaining, cache->len);
cache_objs = &cache->objs[cache->len];
+
+ if (__extension__(__builtin_constant_p(n)) && n <= cache->len) {
+ /*
+ * The request size is known at build time, and
+ * the entire request can be satisfied from the cache,
+ * so let the compiler unroll the fixed length copy loop.
+ */
+ cache->len -= n;
+ for (index = 0; index < n; index++)
+ *obj_table++ = *--cache_objs;
+
+ RTE_MEMPOOL_CACHE_STAT_ADD(cache, get_success_bulk, 1);
+ RTE_MEMPOOL_CACHE_STAT_ADD(cache, get_success_objs, n);
+
+ return 0;
+ }
+
+ /* Use the cache as much as we have to return hot objects first */
+ len = __extension__(__builtin_constant_p(n)) ? cache->len :
+ RTE_MIN(remaining, cache->len);
cache->len -= len;
remaining -= len;
for (index = 0; index < len; index++)
*obj_table++ = *--cache_objs;
- if (remaining == 0) {
+ if (!__extension__(__builtin_constant_p(n)) && remaining == 0) {
/* The entire request is satisfied from the cache. */
RTE_MEMPOOL_CACHE_STAT_ADD(cache, get_success_bulk, 1);
--
2.17.1
