[dpdk-dev,v4] app/testpmd: initialize port_numa and ring_numa

Message ID 1493344915-127542-1-git-send-email-yulong.pei@intel.com (mailing list archive)
State Superseded, archived
Delegated to: Thomas Monjalon
Headers

Checks

Context Check Description
ci/Intel-compilation success Compilation OK
ci/checkpatch success coding style OK

Commit Message

Pei, Yulong April 28, 2017, 2:01 a.m. UTC
  Previous numa_support = 0 by default, it need to add --numa to testpmd
command line to enable numa, so port_numa and ring_numa were initialized
at function launch_args_parse(), now testpmd change numa_support = 1 as
default, so port_numa and ring_numa also need to initialize by default,
otherwise port->socket_id will be probed to wrong value.

Fixes: 999b2ee0fe45 ("app/testpmd: enable NUMA support by default")

Signed-off-by: Yulong Pei <yulong.pei@intel.com>
---
 app/test-pmd/parameters.c | 6 +-----
 app/test-pmd/testpmd.c    | 6 ++++++
 2 files changed, 7 insertions(+), 5 deletions(-)
  

Comments

Jingjing Wu April 28, 2017, 8:30 a.m. UTC | #1
> -----Original Message-----
> From: Pei, Yulong
> Sent: Friday, April 28, 2017 10:02 AM
> To: dev@dpdk.org
> Cc: Wu, Jingjing <jingjing.wu@intel.com>; thomas@monjalon.net
> Subject: [PATCH v4] app/testpmd: initialize port_numa and ring_numa
> 
> Previous numa_support = 0 by default, it need to add --numa to testpmd
> command line to enable numa, so port_numa and ring_numa were initialized at
> function launch_args_parse(), now testpmd change numa_support = 1 as default,
> so port_numa and ring_numa also need to initialize by default, otherwise port-
> >socket_id will be probed to wrong value.
> 
> Fixes: 999b2ee0fe45 ("app/testpmd: enable NUMA support by default")
> 
> Signed-off-by: Yulong Pei <yulong.pei@intel.com>

You forgot "fix" in title if the patch is fixing a problem.
Anyway, the change is OK.
Acked-by: Jingjing Wu <jingjing.wu@intel.com>
  
Thomas Monjalon May 1, 2017, 1:35 p.m. UTC | #2
28/04/2017 10:30, Wu, Jingjing:
> From: Pei, Yulong
> > 
> > Previous numa_support = 0 by default, it need to add --numa to testpmd
> > command line to enable numa, so port_numa and ring_numa were initialized at
> > function launch_args_parse(), now testpmd change numa_support = 1 as default,
> > so port_numa and ring_numa also need to initialize by default, otherwise port-
> > >socket_id will be probed to wrong value.
> > 
> > Fixes: 999b2ee0fe45 ("app/testpmd: enable NUMA support by default")
> > 
> > Signed-off-by: Yulong Pei <yulong.pei@intel.com>
> 
> You forgot "fix" in title if the patch is fixing a problem.
> Anyway, the change is OK.
> Acked-by: Jingjing Wu <jingjing.wu@intel.com>

Please rebase on top of http://dpdk.org/commit/3ab64341d
and check if the patch needs to be reworked.
The check of port_numa array below is weird.

PS: please use --in-reply-to for v5.
  

Patch

diff --git a/app/test-pmd/parameters.c b/app/test-pmd/parameters.c
index 3f4d3a2..3296b3a 100644
--- a/app/test-pmd/parameters.c
+++ b/app/test-pmd/parameters.c
@@ -665,12 +665,8 @@  launch_args_parse(int argc, char** argv)
 				parse_fwd_portmask(optarg);
 			if (!strcmp(lgopts[opt_idx].name, "no-numa"))
 				numa_support = 0;
-			if (!strcmp(lgopts[opt_idx].name, "numa")) {
+			if (!strcmp(lgopts[opt_idx].name, "numa"))
 				numa_support = 1;
-				memset(port_numa,NUMA_NO_CONFIG,RTE_MAX_ETHPORTS);
-				memset(rxring_numa,NUMA_NO_CONFIG,RTE_MAX_ETHPORTS);
-				memset(txring_numa,NUMA_NO_CONFIG,RTE_MAX_ETHPORTS);
-			}
 			if (!strcmp(lgopts[opt_idx].name, "mp-anon")) {
 				mp_anon = 1;
 			}
diff --git a/app/test-pmd/testpmd.c b/app/test-pmd/testpmd.c
index 3a57348..606bfd1 100644
--- a/app/test-pmd/testpmd.c
+++ b/app/test-pmd/testpmd.c
@@ -543,6 +543,12 @@  init_config(void)
 		fwd_lcores[lc_id]->cpuid_idx = lc_id;
 	}
 
+	if (numa_support) {
+		memset(port_numa, NUMA_NO_CONFIG, RTE_MAX_ETHPORTS);
+		memset(rxring_numa, NUMA_NO_CONFIG, RTE_MAX_ETHPORTS);
+		memset(txring_numa, NUMA_NO_CONFIG, RTE_MAX_ETHPORTS);
+	}
+
 	/*
 	 * Create pools of mbuf.
 	 * If NUMA support is disabled, create a single pool of mbuf in