[dpdk-dev,v4] app/testpmd: initialize port_numa and ring_numa
Checks
Commit Message
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
> -----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>
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.
@@ -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;
}
@@ -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