From: Wei Liu <wei.liu2@citrix.com>
To: xen-devel@lists.xen.org
Cc: Wei Liu <wei.liu2@citrix.com>,
ian.campbell@citrix.com, annie.li@oracle.com,
david.vrabel@citrix.com, msw@amazon.com,
andrew.bennieston@citrix.com
Subject: Re: [PATCH V4 0/3] xen-netback: switch to NAPI + kthread 1:1 model
Date: Thu, 15 Aug 2013 14:20:17 +0100 [thread overview]
Message-ID: <20130815132017.GC7042@zion.uk.xensource.com> (raw)
In-Reply-To: <1375779963-24090-1-git-send-email-wei.liu2@citrix.com>
Any more comments?
Wei.
On Tue, Aug 06, 2013 at 10:06:00AM +0100, Wei Liu wrote:
> This series implements NAPI + kthread 1:1 model for Xen netback.
>
> This model
> - provides better scheduling fairness among vifs
> - is prerequisite for implementing multiqueue for Xen network driver
>
> The first two patches are ground work for the third patch. First one
> simplifies code in netback, second one can reduce memory footprint if we
> switch to 1:1 model.
>
> The third patch has the real meat:
> - make use of NAPI to mitigate interrupt
> - kthreads are not bound to CPUs any more, so that we can take
> advantage of backend scheduler and trust it to do the right thing
>
> Benchmark done on a Dell T3400 workstation with 4 cores, running 4
> DomUs. Netserver running in Dom0. DomUs do netperf to Dom0 with
> following command: /root/netperf -H Dom0 -fm -l120
>
> IRQs are distributed to 4 cores by hand in the new model, while in the
> old model vifs are automatically distributed to 4 kthreads.
>
> * New model
> %Cpu0 : 0.5 us, 20.3 sy, 0.0 ni, 28.9 id, 0.0 wa, 0.0 hi, 24.4 si, 25.9 st
> %Cpu1 : 0.5 us, 17.8 sy, 0.0 ni, 28.8 id, 0.0 wa, 0.0 hi, 27.7 si, 25.1 st
> %Cpu2 : 0.5 us, 18.8 sy, 0.0 ni, 30.7 id, 0.0 wa, 0.0 hi, 22.9 si, 27.1 st
> %Cpu3 : 0.0 us, 20.1 sy, 0.0 ni, 30.4 id, 0.0 wa, 0.0 hi, 22.7 si, 26.8 st
> Throughputs: 2027.89 2025.95 2018.57 2016.23 aggregated: 8088.64
>
> * Old model
> %Cpu0 : 0.5 us, 68.8 sy, 0.0 ni, 16.1 id, 0.5 wa, 0.0 hi, 2.8 si, 11.5 st
> %Cpu1 : 0.4 us, 45.1 sy, 0.0 ni, 31.1 id, 0.4 wa, 0.0 hi, 2.1 si, 20.9 st
> %Cpu2 : 0.9 us, 44.8 sy, 0.0 ni, 30.9 id, 0.0 wa, 0.0 hi, 1.3 si, 22.2 st
> %Cpu3 : 0.8 us, 46.4 sy, 0.0 ni, 28.3 id, 1.3 wa, 0.0 hi, 2.1 si, 21.1 st
> Throughputs: 1899.14 2280.43 1963.33 1893.47 aggregated: 8036.37
>
> We can see that the impact is mainly on CPU usage. The new model moves
> processing from kthread to NAPI (software interrupt).
>
> Changes since V3:
> * rebase on top of net-next
> * group TX and RX fields in different regions of the structure
> * minor bugfix : use GFP_ATOMIC to avoid sleeping in SI context
> * split functional changes and funcation renames into two patches
> * minor coding style fixes
>
> Wei Liu (3):
> xen-netback: remove page tracking facility
> xen-netback: switch to NAPI + kthread 1:1 model
> xen-netback: rename functions
>
> drivers/net/xen-netback/common.h | 127 ++++--
> drivers/net/xen-netback/interface.c | 119 +++--
> drivers/net/xen-netback/netback.c | 833 +++++++++++------------------------
> 3 files changed, 406 insertions(+), 673 deletions(-)
>
> --
> 1.7.10.4
prev parent reply other threads:[~2013-08-15 13:20 UTC|newest]
Thread overview: 27+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-08-06 9:06 [PATCH V4 0/3] xen-netback: switch to NAPI + kthread 1:1 model Wei Liu
2013-08-06 9:06 ` [PATCH V4 1/3] xen-netback: remove page tracking facility Wei Liu
2013-08-07 2:52 ` Matt Wilson
2013-08-06 9:06 ` [PATCH V4 2/3] xen-netback: switch to NAPI + kthread 1:1 model Wei Liu
2013-08-06 13:33 ` Wei Liu
2013-08-06 13:50 ` Ian Campbell
2013-08-06 14:50 ` Wei Liu
2013-08-06 14:56 ` Ian Campbell
2013-08-06 15:05 ` Wei Liu
2013-08-06 15:21 ` Ian Campbell
2013-08-06 15:24 ` Wei Liu
2013-08-06 15:33 ` Wei Liu
2013-08-06 15:38 ` Ian Campbell
2013-08-06 15:47 ` Wei Liu
2013-08-06 15:50 ` Ian Campbell
2013-08-06 15:54 ` Wei Liu
2013-08-06 15:58 ` Ian Campbell
2013-08-06 9:06 ` [PATCH V4 3/3] xen-netback: rename functions Wei Liu
2013-08-06 13:16 ` [PATCH V4 0/3] xen-netback: switch to NAPI + kthread 1:1 model Pasi Kärkkäinen
2013-08-06 13:28 ` Wei Liu
2013-08-06 13:29 ` David Vrabel
2013-08-06 14:17 ` Andrew Bennieston
2013-08-22 15:12 ` Wei Liu
2013-08-22 15:19 ` Wei Liu
2013-08-22 17:14 ` Matt Wilson
2013-08-23 2:24 ` annie li
2013-08-15 13:20 ` Wei Liu [this message]
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=20130815132017.GC7042@zion.uk.xensource.com \
--to=wei.liu2@citrix.com \
--cc=andrew.bennieston@citrix.com \
--cc=annie.li@oracle.com \
--cc=david.vrabel@citrix.com \
--cc=ian.campbell@citrix.com \
--cc=msw@amazon.com \
--cc=xen-devel@lists.xen.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).