From: Evgeniy Polyakov <zbr@ioremap.net>
To: David Miller <davem@davemloft.net>
Cc: netdev@vger.kernel.org, efault@gmx.de, mingo@elte.hu,
a.p.zijlstra@chello.nl, herbert@gondor.apana.org.au
Subject: Re: tbench wrt. loopback TSO
Date: Sun, 26 Oct 2008 15:34:42 +0300 [thread overview]
Message-ID: <20081026123442.GA31506@ioremap.net> (raw)
In-Reply-To: <20081015.171408.193701292.davem@davemloft.net>
Hi.
On Wed, Oct 15, 2008 at 05:14:08PM -0700, David Miller (davem@davemloft.net) wrote:
>
> I got curious about this aspect of the investigation so I wanted
> to see it first-hand :-)
>
> To be honest, this reported effect of disabling TSO in the loopback
> driver surprised me because:
>
> 1) If the benchmark is doing small writes, TSO should have zero
> effect. The TSO logic won't kick in.
But GSO will try to create a huge packet and that overhead will not be
overweighted?
That's what I got with the current tree for 8 threads on a 4-way 32-bit
Xeons (2 physical CPUs) and 8gb of ram:
gso/tso off: 361.367
tso/gso on: 354.635
Disabled/enabled via ethtools: -k tso off/on gso off/on
> 2) If larger than MTU writes are being done, TSO should help,
> and this is supported by other benchmarks :-)
Yes, that's where it is useful.
--
Evgeniy Polyakov
next prev parent reply other threads:[~2008-10-26 12:34 UTC|newest]
Thread overview: 26+ messages / expand[flat|nested] mbox.gz Atom feed top
2008-10-16 0:14 tbench wrt. loopback TSO David Miller
2008-10-17 3:49 ` non-TCP tbench (was Re: tbench wrt. loopback TSO) David Miller
2008-10-26 12:34 ` Evgeniy Polyakov [this message]
2008-10-27 1:59 ` tbench wrt. loopback TSO David Miller
2008-10-27 7:49 ` Ilpo Järvinen
2008-10-27 14:13 ` Evgeniy Polyakov
2008-10-27 15:19 ` Ilpo Järvinen
2008-10-27 17:03 ` Evgeniy Polyakov
2008-10-27 18:39 ` David Miller
2008-10-27 19:35 ` Evgeniy Polyakov
2008-10-27 19:37 ` David Miller
2008-11-05 11:42 ` David Miller
2008-11-05 11:49 ` Evgeniy Polyakov
2008-11-05 11:54 ` David Miller
2008-11-05 12:04 ` Ilpo Järvinen
2008-11-05 12:09 ` David Miller
2008-11-05 12:25 ` Ilpo Järvinen
2008-11-05 13:04 ` Evgeniy Polyakov
2008-11-05 13:33 ` Ilpo Järvinen
2008-11-05 18:48 ` Rick Jones
2008-11-05 19:46 ` Ilpo Järvinen
2008-11-05 21:06 ` Rick Jones
2008-10-27 22:17 ` Ilpo Järvinen
2008-10-31 8:14 ` David Miller
2008-10-31 9:16 ` Ilpo Järvinen
2008-10-31 9:47 ` David Miller
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=20081026123442.GA31506@ioremap.net \
--to=zbr@ioremap.net \
--cc=a.p.zijlstra@chello.nl \
--cc=davem@davemloft.net \
--cc=efault@gmx.de \
--cc=herbert@gondor.apana.org.au \
--cc=mingo@elte.hu \
--cc=netdev@vger.kernel.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).