From: Sridhar Samudrala <sri@us.ibm.com>
To: Herbert Xu <herbert@gondor.apana.org.au>
Cc: Rusty Russell <rusty@rustcorp.com.au>,
mst@redhat.com, netdev@vger.kernel.org
Subject: Re: [RFC PATCH] Regression in linux 2.6.32 virtio_net seen with vhost-net
Date: Wed, 16 Dec 2009 21:02:50 -0800 [thread overview]
Message-ID: <4B29BB7A.8000307@us.ibm.com> (raw)
In-Reply-To: <20091217031233.GA26027@gondor.apana.org.au>
Herbert Xu wrote:
> On Wed, Dec 16, 2009 at 05:43:00PM -0800, Sridhar Samudrala wrote:
>
>> I had to change virtnet_xmit_poll() to get it working. See below.
>> With this change, i don't see any 'queue full' warnings, but requeues
>> are still happening at the qdisc level (sch_direct_xmit() finds that
>> tx queue is stopped and does requeues).
>>
>
> More importantly how does the performance look?
>
TCP stream throughput is around the same 3200Mb/sec
Thanks
Sridhar
next prev parent reply other threads:[~2009-12-17 5:03 UTC|newest]
Thread overview: 58+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-12-08 22:50 [RFC PATCH] Regression in linux 2.6.32 virtio_net seen with vhost-net Sridhar Samudrala
2009-12-13 12:25 ` Herbert Xu
2009-12-13 23:40 ` Michael S. Tsirkin
2009-12-15 14:42 ` Herbert Xu
2009-12-15 16:26 ` Sridhar Samudrala
2009-12-16 1:21 ` Herbert Xu
2009-12-15 23:32 ` Michael S. Tsirkin
2009-12-16 1:58 ` Herbert Xu
2009-12-16 4:37 ` Rusty Russell
2009-12-16 10:37 ` Michael S. Tsirkin
2009-12-16 2:41 ` Rusty Russell
2009-12-16 2:53 ` Herbert Xu
2009-12-16 12:45 ` Rusty Russell
2009-12-16 13:22 ` Michael S. Tsirkin
2009-12-16 13:35 ` Herbert Xu
2009-12-16 13:38 ` Michael S. Tsirkin
2009-12-16 13:48 ` Herbert Xu
2009-12-17 2:02 ` Rusty Russell
2009-12-17 9:25 ` Michael S. Tsirkin
2009-12-18 1:55 ` Rusty Russell
2009-12-16 13:30 ` Herbert Xu
2009-12-17 1:43 ` Sridhar Samudrala
2009-12-17 3:12 ` Herbert Xu
2009-12-17 5:02 ` Sridhar Samudrala [this message]
2009-12-17 3:15 ` Herbert Xu
2009-12-17 5:05 ` Sridhar Samudrala
2009-12-17 6:28 ` Herbert Xu
2009-12-17 6:45 ` Sridhar Samudrala
2009-12-17 10:03 ` Krishna Kumar2
2009-12-17 11:27 ` Jarek Poplawski
2009-12-17 11:45 ` Herbert Xu
2009-12-17 11:49 ` Herbert Xu
2009-12-17 12:08 ` Herbert Xu
2009-12-17 12:27 ` Krishna Kumar2
2009-12-17 12:42 ` Jarek Poplawski
2009-12-17 12:56 ` Herbert Xu
2009-12-17 13:22 ` Krishna Kumar2
2009-12-17 13:04 ` Krishna Kumar2
2009-12-17 13:44 ` Herbert Xu
2009-12-17 14:35 ` Krishna Kumar2
2009-12-17 14:36 ` Herbert Xu
2009-12-17 21:50 ` Sridhar Samudrala
2009-12-17 22:28 ` Sridhar Samudrala
2009-12-17 22:41 ` Jarek Poplawski
2009-12-18 13:46 ` Krishna Kumar2
2009-12-18 19:13 ` Sridhar Samudrala
2009-12-17 11:59 ` Krishna Kumar2
2009-12-17 12:19 ` Jarek Poplawski
2009-12-17 11:56 ` Krishna Kumar2
2009-12-17 13:17 ` Jarek Poplawski
2009-12-17 14:10 ` Krishna Kumar2
2009-12-17 14:16 ` Herbert Xu
2009-12-16 17:42 ` Sridhar Samudrala
-- strict thread matches above, loose matches on Subject: below --
2009-12-17 11:20 Krishna Kumar
2009-12-17 19:28 ` Jarek Poplawski
[not found] <20091217111219.9809.27432.sendpatchset@krkumar2.in.ibm.com>
[not found] ` <20091217123153.GA31131@gondor.apana.org.au>
2009-12-17 12:56 ` Krishna Kumar2
2009-12-17 13:40 ` Herbert Xu
2009-12-17 13:56 ` Krishna Kumar2
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=4B29BB7A.8000307@us.ibm.com \
--to=sri@us.ibm.com \
--cc=herbert@gondor.apana.org.au \
--cc=mst@redhat.com \
--cc=netdev@vger.kernel.org \
--cc=rusty@rustcorp.com.au \
/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).