From: Rick Jones <rick.jones2@hp.com>
To: Willem de Bruijn <willemb@google.com>
Cc: netdev@vger.kernel.org, davem@davemloft.net, edumazet@google.com,
therbert@google.com
Subject: Re: [PATCH net-next] rps: overflow prevention for saturated cpus
Date: Thu, 06 Dec 2012 14:25:17 -0800 [thread overview]
Message-ID: <50C11B4D.4040109@hp.com> (raw)
In-Reply-To: <1354826194-9289-1-git-send-email-willemb@google.com>
On 12/06/2012 12:36 PM, Willem de Bruijn wrote:
> RPS and RFS balance load across cpus with flow affinity. This can
> cause local bottlenecks, where a small number or single large flow
> (DoS) can saturate one CPU while others are idle.
>
> This patch maintains flow affinity in normal conditions, but
> trades it for throughput when a cpu becomes saturated. Then, packets
> destined to that cpu (only) are redirected to the lightest loaded cpu
> in the rxqueue's rps_map. This breaks flow affinity under high load
> for some flows, in favor of processing packets up to the capacity
> of the complete rps_map cpuset in all circumstances.
I thought (one of) the ideas behind RFS at least was to give the CPU
scheduler control over where network processing took place instead of it
being dictated solely by the addressing. I would have expected the CPU
scheduler to migrate some work off the saturated CPU. Or will this only
affect RPS and not RFS?
Allowing individual flows to straddle the CPUs - won't that be somewhat
like what happens in bonding with mode-rr in the outbound case - packet
reordering evil? What kind of workload is this targeting that calls for
such intra-flow parallelism?
With respect to the examples given, what happens when it is TCP traffic
rather than UDP?
happy benchmarking,
rick jones
next prev parent reply other threads:[~2012-12-06 22:25 UTC|newest]
Thread overview: 9+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-12-06 20:36 [PATCH net-next] rps: overflow prevention for saturated cpus Willem de Bruijn
2012-12-06 22:25 ` Rick Jones [this message]
2012-12-06 23:04 ` Willem de Bruijn
2012-12-06 23:45 ` Rick Jones
2012-12-07 16:04 ` Willem de Bruijn
2012-12-07 14:51 ` Ben Hutchings
2012-12-07 16:41 ` Willem de Bruijn
2012-12-07 19:20 ` David Miller
2012-12-10 20:09 ` Willem de Bruijn
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=50C11B4D.4040109@hp.com \
--to=rick.jones2@hp.com \
--cc=davem@davemloft.net \
--cc=edumazet@google.com \
--cc=netdev@vger.kernel.org \
--cc=therbert@google.com \
--cc=willemb@google.com \
/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).