All of lore.kernel.org
 help / color / mirror / Atom feed
From: Sowmini Varadhan <sowmini.varadhan@oracle.com>
To: intel-wired-lan@osuosl.org
Subject: [Intel-wired-lan] [net PATCH] i40e/i40evf: Limit TSO to 7 descriptors for payload instead of 8 per packet
Date: Wed, 30 Mar 2016 16:40:23 -0400	[thread overview]
Message-ID: <20160330204023.GK27540@oracle.com> (raw)
In-Reply-To: <1459368904.6473.207.camel@edumazet-glaptop3.roam.corp.google.com>

On (03/30/16 13:15), Eric Dumazet wrote:
> You might try netperf -t TCP_SENDFILE -- -m 150
> 
> to let netperf use sendfile() on small frags.

that still did not reproduce it but let me try beating on
that approach with more permutations.

BTW, another data-point that may help debug this: even with i40e,
if you use the "-o" option to the rds-stress invocation, there are
no problems: the "-o" option  enforces uni-directional data
transfer, so one side is pure-Tx, other side is pure-Rx. 

It is only when both sides simultaneously do both Tx and Rx
on the tcp socket that you see the issue. I dont know if
that provides any clues.

--Sowmini


WARNING: multiple messages have this Message-ID (diff)
From: Sowmini Varadhan <sowmini.varadhan@oracle.com>
To: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Jesse Brandeburg <jesse.brandeburg@intel.com>,
	Alexander Duyck <alexander.duyck@gmail.com>,
	Alexander Duyck <aduyck@mirantis.com>,
	Netdev <netdev@vger.kernel.org>,
	intel-wired-lan <intel-wired-lan@lists.osuosl.org>,
	Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Subject: Re: [net PATCH] i40e/i40evf: Limit TSO to 7 descriptors for payload instead of 8 per packet
Date: Wed, 30 Mar 2016 16:40:23 -0400	[thread overview]
Message-ID: <20160330204023.GK27540@oracle.com> (raw)
In-Reply-To: <1459368904.6473.207.camel@edumazet-glaptop3.roam.corp.google.com>

On (03/30/16 13:15), Eric Dumazet wrote:
> You might try netperf -t TCP_SENDFILE -- -m 150
> 
> to let netperf use sendfile() on small frags.

that still did not reproduce it but let me try beating on
that approach with more permutations.

BTW, another data-point that may help debug this: even with i40e,
if you use the "-o" option to the rds-stress invocation, there are
no problems: the "-o" option  enforces uni-directional data
transfer, so one side is pure-Tx, other side is pure-Rx. 

It is only when both sides simultaneously do both Tx and Rx
on the tcp socket that you see the issue. I dont know if
that provides any clues.

--Sowmini

  reply	other threads:[~2016-03-30 20:40 UTC|newest]

Thread overview: 24+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-03-30  6:44 [Intel-wired-lan] [net PATCH] i40e/i40evf: Limit TSO to 7 descriptors for payload instead of 8 per packet Alexander Duyck
2016-03-30  6:44 ` Alexander Duyck
2016-03-30 17:00 ` [Intel-wired-lan] " Sowmini Varadhan
2016-03-30 17:00   ` Sowmini Varadhan
2016-03-30 17:12   ` [Intel-wired-lan] " Alexander Duyck
2016-03-30 17:12     ` Alexander Duyck
2016-03-30 17:20     ` [Intel-wired-lan] " Sowmini Varadhan
2016-03-30 17:20       ` Sowmini Varadhan
2016-03-30 17:35       ` [Intel-wired-lan] " Alexander Duyck
2016-03-30 17:35         ` Alexander Duyck
2016-03-30 19:41         ` [Intel-wired-lan] " Jesse Brandeburg
2016-03-30 19:41           ` Jesse Brandeburg
2016-03-30 20:09           ` [Intel-wired-lan] " Sowmini Varadhan
2016-03-30 20:09             ` Sowmini Varadhan
2016-03-30 20:15             ` [Intel-wired-lan] " Eric Dumazet
2016-03-30 20:15               ` Eric Dumazet
2016-03-30 20:40               ` Sowmini Varadhan [this message]
2016-03-30 20:40                 ` Sowmini Varadhan
2016-03-30 21:20           ` [Intel-wired-lan] " Alexander Duyck
2016-03-30 21:20             ` Alexander Duyck
2016-03-30 23:06             ` [Intel-wired-lan] " Alexander Duyck
2016-03-30 23:06               ` Alexander Duyck
2016-03-30 18:38     ` [Intel-wired-lan] " Jesse Brandeburg
2016-03-30 18:38       ` Jesse Brandeburg

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=20160330204023.GK27540@oracle.com \
    --to=sowmini.varadhan@oracle.com \
    --cc=intel-wired-lan@osuosl.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.