Re: [vpp-dev] Performance of PAPI request in multi threaded VPP

2021-03-05 Thread Xuo Guoto via lists.fd.io
Hi Andrew, It does make things way faster. Now I am getting time in the range of 2.5 secs. Is this patch ready for prime time? X. ‐‐‐ Original Message ‐‐‐ On Tuesday, March 2, 2021 7:35 PM, Andrew Yourtchenko wrote: > Hi Xuo, > > I’ve seen a maybe related problem recently - could

Re: [vpp-dev] Performance of PAPI request in multi threaded VPP

2021-03-02 Thread Andrew Yourtchenko
Hi Xuo, I’ve seen a maybe related problem recently - could you try an image with https://gerrit.fd.io/r/c/vpp/+/31368 in it and see if you still have a similarly large difference or does it make things faster for you ? --a > On 25 Feb 2021, at 16:20, Xuo Guoto via lists.fd.io > wrote: >  >

Re: [vpp-dev] Performance of PAPI request in multi threaded VPP

2021-03-01 Thread Paul Vinciguerra
Hi Xuo, Neale is the maintainer of the policer code. Maybe he can chime in if it is safe to simply mark the binary apis as multiple parallel vector safe `am->is_mp_safe`. There is a brief reference to this in the developer docs [0]. [0]

[vpp-dev] Performance of PAPI request in multi threaded VPP

2021-02-25 Thread Xuo Guoto via lists.fd.io
Hi List, We have been using policer_add_del and classify_add_del_session in single threaded VPP (ie one main thread only) and both API were giving decent performance, but after switching to multi thread VPP the performance seems be drastically less. To test this out a small test program was