diff mbox series

app/flow-perf: use macro for cache alignment

Message ID 20200629210443.371664-1-thomas@monjalon.net (mailing list archive)
State Accepted, archived
Delegated to: Thomas Monjalon
Headers
Series app/flow-perf: use macro for cache alignment |

Checks

Context Check Description
ci/checkpatch success coding style OK
ci/travis-robot success Travis build: passed
ci/Intel-compilation fail apply issues

Commit Message

Thomas Monjalon June 29, 2020, 9:04 p.m. UTC 
  The macro __rte_cache_aligned is better suited for aligning
a structure on a cache line (of any size).

Fixes: 15c431864000 ("app/flow-perf: add packet forwarding support")

Signed-off-by: Thomas Monjalon <thomas@monjalon.net>
---
 app/test-flow-perf/main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

Comments

Wisam Jaddo June 30, 2020, 7:34 a.m. UTC | #1 
Hi,

>-----Original Message-----
>From: Thomas Monjalon <thomas@monjalon.net>
>Sent: Tuesday, June 30, 2020 12:05 AM
>To: dev@dpdk.org
>Cc: david.marchand@redhat.com; Wisam Monther
><wisamm@mellanox.com>; Jack Min <jackmin@mellanox.com>
>Subject: [PATCH] app/flow-perf: use macro for cache alignment
>
>The macro __rte_cache_aligned is better suited for aligning a structure on a
>cache line (of any size).
>
>Fixes: 15c431864000 ("app/flow-perf: add packet forwarding support")
>
>Signed-off-by: Thomas Monjalon <thomas@monjalon.net>

Acked-by: Wisam Jaddo <wisamm@mellanox.com>
Thomas Monjalon June 30, 2020, 9:58 a.m. UTC | #2 
> >The macro __rte_cache_aligned is better suited for aligning a structure on a
> >cache line (of any size).
> >
> >Fixes: 15c431864000 ("app/flow-perf: add packet forwarding support")
> >
> >Signed-off-by: Thomas Monjalon <thomas@monjalon.net>
> 
> Acked-by: Wisam Jaddo <wisamm@mellanox.com>

Applied
diff mbox series

Patch

diff --git a/app/test-flow-perf/main.c b/app/test-flow-perf/main.c
index e155e49c37..1ae2856556 100644
--- a/app/test-flow-perf/main.c
+++ b/app/test-flow-perf/main.c
@@ -84,7 +84,7 @@  struct lcore_info {
 	uint64_t tx_drops;
 	uint64_t rx_pkts;
 	struct rte_mbuf *pkts[MAX_PKT_BURST];
-} __attribute__((__aligned__(64))); /* let it be cacheline aligned */
+} __rte_cache_aligned;
 
 static struct lcore_info lcore_infos[MAX_LCORES];