DPDK usage discussions
 help / color / mirror / Atom feed
From: Chris Pappas <chrispappas12@gmail.com>
To: users@dpdk.org
Subject: [dpdk-users] Inconsistent results for varying packet sizes
Date: Mon, 26 Oct 2015 21:22:22 +0100	[thread overview]
Message-ID: <CAE4G5ioHMbLidyL-jqQOFDWYxDwepfMqKH+ixVE=M576bxfGVw@mail.gmail.com> (raw)

Hi everyone,

we have done some basic testing with DPDK. We are testing the baseline
forwarding performance (table lookup code has been commented out and we
statically forward traffic among a 1-1 incoming to outgoing port
assignment), but we get weird results (attached).

For 256-byte packets the average latency is lower than for 128-byte
packets, but for 1500-byte packets the latency is much higher than the
previous two packet sizes.

Could you please let us know if this is something expected, since it is
counter-intuitive,
or if we are having some obvious configuration mistake?
Our configuration is as following:

Best regards,
Chris

*Command*
sudo ./build/l3fwd -c 0xffff -n 4 -- -p 0xfff -P
--config="(0,0,1),(1,0,2),(2,0,3),(3,0,4),(4,0,8),(5,0,9),(
6,0,10),(7,0,11),(8,0,12),(9,0,13),(10,0,14),(11,0,15)"

*Core assignment (one core per one port)*
L3FWD: entering main loop on lcore 1
L3FWD:  -- lcoreid=1 portid=0 rxqueueid=0
L3FWD: entering main loop on lcore 2
L3FWD:  -- lcoreid=2 portid=1 rxqueueid=0
L3FWD: entering main loop on lcore 3
L3FWD:  -- lcoreid=3 portid=2 rxqueueid=0
L3FWD: entering main loop on lcore 4
L3FWD:  -- lcoreid=4 portid=3 rxqueueid=0
L3FWD: lcore 5 has nothing to do
L3FWD: lcore 6 has nothing to do
L3FWD: lcore 7 has nothing to do
L3FWD: entering main loop on lcore 8
L3FWD:  -- lcoreid=8 portid=4 rxqueueid=0
L3FWD: entering main loop on lcore 9
L3FWD:  -- lcoreid=9 portid=5 rxqueueid=0
L3FWD: entering main loop on lcore 10
L3FWD:  -- lcoreid=10 portid=6 rxqueueid=0
L3FWD: entering main loop on lcore 11
L3FWD:  -- lcoreid=11 portid=7 rxqueueid=0
L3FWD: entering main loop on lcore 12
L3FWD:  -- lcoreid=12 portid=8 rxqueueid=0
L3FWD: entering main loop on lcore 13
L3FWD:  -- lcoreid=13 portid=9 rxqueueid=0
L3FWD: entering main loop on lcore 14
L3FWD:  -- lcoreid=14 portid=10 rxqueueid=0
L3FWD: entering main loop on lcore 15
L3FWD:  -- lcoreid=15 portid=11 rxqueueid=0
L3FWD: lcore 0 has nothing to do

                 reply	other threads:[~2015-10-26 20:23 UTC|newest]

Thread overview: [no followups] expand[flat|nested]  mbox.gz  Atom feed

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to='CAE4G5ioHMbLidyL-jqQOFDWYxDwepfMqKH+ixVE=M576bxfGVw@mail.gmail.com' \
    --to=chrispappas12@gmail.com \
    --cc=users@dpdk.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).