diff mbox

[dpdk-dev] app/test: decrease memory requirements for sched

Message ID 1473680329-29595-1-git-send-email-olivier.matz@6wind.com (mailing list archive)
State Accepted, archived
Delegated to: Thomas Monjalon
Headers

Commit Message

Olivier Matz Sept. 12, 2016, 11:38 a.m. UTC 
  The sched test consumes 35MB memory. When memory is too fragmented (with
2M hugepages), the test can fail.

To reduce this risk, decrease it to 4.5MB by modifying
n_pipes_per_subport and qsize.

Signed-off-by: Olivier Matz <olivier.matz@6wind.com>
---
 app/test/test_sched.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

Comments

Cristian Dumitrescu Sept. 15, 2016, 2:15 p.m. UTC | #1 
> -----Original Message-----
> From: Olivier Matz [mailto:olivier.matz@6wind.com]
> Sent: Monday, September 12, 2016 12:39 PM
> To: dev@dpdk.org; Dumitrescu, Cristian <cristian.dumitrescu@intel.com>
> Subject: [PATCH] app/test: decrease memory requirements for sched
> 
> The sched test consumes 35MB memory. When memory is too fragmented
> (with
> 2M hugepages), the test can fail.
> 
> To reduce this risk, decrease it to 4.5MB by modifying
> n_pipes_per_subport and qsize.
> 
> Signed-off-by: Olivier Matz <olivier.matz@6wind.com>
> ---

Acked-by: Cristian Dumitrescu <cristian.dumitrescu@intel.com>
Thomas Monjalon Sept. 23, 2016, 4:44 p.m. UTC | #2 
> > The sched test consumes 35MB memory. When memory is too fragmented
> > (with
> > 2M hugepages), the test can fail.
> > 
> > To reduce this risk, decrease it to 4.5MB by modifying
> > n_pipes_per_subport and qsize.
> > 
> > Signed-off-by: Olivier Matz <olivier.matz@6wind.com>
> 
> Acked-by: Cristian Dumitrescu <cristian.dumitrescu@intel.com>

Applied, thanks
diff mbox

Patch

diff --git a/app/test/test_sched.c b/app/test/test_sched.c
index 63ab084..bd2776d 100644
--- a/app/test/test_sched.c
+++ b/app/test/test_sched.c
@@ -79,8 +79,8 @@  static struct rte_sched_port_params port_param = {
 	.mtu = 1522,
 	.frame_overhead = RTE_SCHED_FRAME_OVERHEAD_DEFAULT,
 	.n_subports_per_port = 1,
-	.n_pipes_per_subport = 4096,
-	.qsize = {64, 64, 64, 64},
+	.n_pipes_per_subport = 1024,
+	.qsize = {32, 32, 32, 32},
 	.pipe_profiles = pipe_profile,
 	.n_pipe_profiles = 1,
 };