Hi Vyshakh,
This is only configurable in the startup config file. For performance reasons,
we do not want the VPP threads to move across CPUs.
Thanks
Aloÿs
> On 17 Mar 2020, at 06:29, Vyshakh Krishnan wrote:
>
> Thanks Aloys. Setting the main-core to different CPUs helped. ping is taking
> l
Thanks Aloys. Setting the main-core to different CPUs helped. ping is
taking less than a ms now.
Is there a way to do it from the code rather than from configuration file?
or a way to let linux scheduling decide the CPU?
Thanks
Vyshakh
On Thu, Mar 12, 2020 at 7:24 PM Aloys Augustin (aloaugus) <
a
Hello,
For what it’s worth, I observed ~10ms memif pings when both VPPs were scheduled
on the same CPU, which happens with the default configuration (VPP takes CPU 1
by default). You can try changing the configuration of one of your VPPs by
setting the main-core in the cpu section:
https://fd.
Hi Damjan,
Please find the trace on both side
vpp1 (10.1.1.1) (10.1.1.2) vpp2
DBGvpp# ping 10.1.1.2
116 bytes from 10.1.1.2: icmp_seq=1 ttl=64 time=31.8174 ms
116 bytes from 10.1.1.2: icmp_seq=2 ttl=64 time=47.9716 ms
116 bytes from 10.1.1.2: icmp_seq=3 ttl=64 time=40.0259 ms
116 bytes from
That’s weird…. Can you capture packet trace on both sides?
> On 12 Mar 2020, at 11:16, vyshakh krishnan wrote:
>
> Hi Damjan,
>
> We don't have any worker threads and memif is in polling mode:
>
> DBGvpp# sh int rx-placement
> Thread 0 (vpp_main):
> node memif-input:
> memif11/11 queue
Hi Damjan,
We don't have any worker threads and memif is in polling mode:
DBGvpp# sh int rx-placement
Thread 0 (vpp_main):
node memif-input:
memif11/11 queue 0 (polling)
memif222/222 queue 0 (polling)
Thanks
Vyshakh
On Wed, Mar 11, 2020 at 9:03 PM Damjan Marion wrote:
>
> Are you ru
Are you running VPP with worker threads and using interrupt mode in memif?
can you capture “sh int rx-placement” on both sides?
—
Damjan
> On 11 Mar 2020, at 15:44, vyshakh krishnan wrote:
>
> Hi All,
>
> When we try to ping back to back connected memif interface, its taking around
> 20 mi
Hi All,
When we try to ping back to back connected memif interface, its taking
around 20 milli secs:
vpp1 (10.1.1.1) (10.1.1.2) vpp2
DBGvpp# ping 10.1.1.2
116 bytes from 10.1.1.2: icmp_seq=1 ttl=64 time=15.1229 ms
116 bytes from 10.1.1.2: icmp_seq=2 ttl=64 time=20.1475 ms
116 bytes from 10
