[memnic PATCH 5/7] pmd: packet receiving optimization with prefetch

From: Hiroshi Shimamoto <h-shimamoto-ehU+Cx/zZe18UrSeD/g0lQ@public.gmane.org>

Prefetch the next packet area to reduce memory stall cycles.

Prefetching the next packet area could hide memory stall, because the next
area will be accessed just after processing the current receive operations.

We can see performance improvements with memnic-tester.
Using Xeon E5-2697 v2 @ 2.70GHz, 4 vCPU.
 size |  before  |  after
   64 | 4.59Mpps | 5.54Mpps
  128 | 4.87Mpps | 5.46Mpps
  256 | 4.72Mpps | 5.21Mpps
  512 | 4.41Mpps | 4.50Mpps
 1024 | 3.64Mpps | 3.71Mpps
 1280 | 3.15Mpps | 3.21Mpps
 1518 | 2.87Mpps | 2.92Mpps

Signed-off-by: Hiroshi Shimamoto <h-shimamoto-ehU+Cx/zZe18UrSeD/g0lQ@public.gmane.org>
Reviewed-by: Hayato Momma <h-momma-JhyGz2TFV9J8UrSeD/g0lQ@public.gmane.org>
---
 pmd/pmd_memnic.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/pmd/pmd_memnic.c b/pmd/pmd_memnic.c
index c22a14d..dbe5033 100644
--- a/pmd/pmd_memnic.c
+++ b/pmd/pmd_memnic.c

@@ -286,7 +286,7 @@ static uint16_t memnic_recv_pkts(void *rx_queue,
 	uint16_t nr;
 	uint64_t pkts, bytes, errs;
 	uint32_t framesz = adapter->framesz;
-	int idx;
+	int idx, next;
 	struct rte_eth_stats *st = &adapter->stats[rte_lcore_id()];
 
 	if (!adapter->nic->hdr.valid)

@@ -298,6 +298,11 @@ static uint16_t memnic_recv_pkts(void *rx_queue,
 		p = &data->packets[idx];
 		if (p->status != MEMNIC_PKT_ST_FILLED)
 			break;
+		/* prefetch the next area */
+		next = idx;
+		if (++next >= MEMNIC_NR_PACKET)
+			next = 0;
+		rte_prefetch0(&data->packets[next]);
 		if (p->len > framesz) {
 			errs++;
 			goto drop;

@@ -318,9 +323,7 @@ static uint16_t memnic_recv_pkts(void *rx_queue,
 drop:
 		rte_compiler_barrier();
 		p->status = MEMNIC_PKT_ST_FREE;
-
-		if (++idx >= MEMNIC_NR_PACKET)
-			idx = 0;
+		idx = next;
 	}
 	adapter->up_idx = idx;
 

-- 
1.8.3.1