DPDK usage discussions
 help / color / mirror / Atom feed
From: "Wiles, Keith" <keith.wiles@intel.com>
To: Paul Tsvika <mozloverinweb@gmail.com>
Cc: "users@dpdk.org" <users@dpdk.org>
Subject: Re: [dpdk-users] [pktgen] pktgen Tx/Rx rates are not the same in loopback testing case
Date: Wed, 26 Jul 2017 14:55:53 +0000	[thread overview]
Message-ID: <A58763B2-6A49-442A-A3F6-C5F7F26FB0CE@intel.com> (raw)
In-Reply-To: <CAGi_MXm7mGd=50P6uUonOtj2Hy87-y3h6Uca+uR=qcuuJS8a1A@mail.gmail.com>


> On Jul 26, 2017, at 4:02 AM, Paul Tsvika <mozloverinweb@gmail.com> wrote:
> 
> Hi Keith.
> 
> This is a loopback test and I think it somehow affects the performance since there is only one NIC and phy on the mother board.
> 
> I tried two mother boards and the tx/rx ( 9611/9497 ) rates look more reasonable.
> 
> I can also set packet size in pktgen command line. 

If Pktgen performance is OK in other motherboards, then the problem with this machine is most likely not a Pktgen problem. You did not answer my question about the PCIe slots in my previous email.

> 
> However, I still don't understand why  RX Desc 512, TX Desc 1024 are not the same.
> 
> Should the values suppose to be the same ?

The increased TX ring size is to reduce the number of times a TX done cleanup occurs.

> 
> 
> 
> Regards-
> 
> 
> P.T
> 
>  

Regards,
Keith

  reply	other threads:[~2017-07-26 14:55 UTC|newest]

Thread overview: 8+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-07-21 15:11 Paul Tsvika
2017-07-21 15:40 ` Wiles, Keith
2017-07-22  1:49   ` Paul Tsvika
2017-07-25  9:04     ` Paul Tsvika
2017-07-25 14:10       ` Wiles, Keith
2017-07-26  9:02         ` Paul Tsvika
2017-07-26 14:55           ` Wiles, Keith [this message]
2017-07-26 16:44     ` Wiles, Keith

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=A58763B2-6A49-442A-A3F6-C5F7F26FB0CE@intel.com \
    --to=keith.wiles@intel.com \
    --cc=mozloverinweb@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).