netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: David Miller <davem@davemloft.net>
To: tom@herbertland.com
Cc: ecree@solarflare.com, herbert@gondor.apana.org.au,
	alexander.duyck@gmail.com, aduyck@mirantis.com, jesse@kernel.org,
	edumazet@google.com, netdev@vger.kernel.org
Subject: Re: [net PATCH v2 2/2] ipv4/GRO: Make GRO conform to RFC 6864
Date: Wed, 06 Apr 2016 15:30:07 -0400 (EDT)	[thread overview]
Message-ID: <20160406.153007.1347001580998282428.davem@davemloft.net> (raw)
In-Reply-To: <CALx6S36h4nZy10=dzfjgEgyXzokEfiteSNM_L3k4jFgg9-kgYA@mail.gmail.com>

From: Tom Herbert <tom@herbertland.com>
Date: Wed, 6 Apr 2016 14:42:26 -0300

> On Wed, Apr 6, 2016 at 12:43 PM, David Miller <davem@davemloft.net> wrote:
>> From: Tom Herbert <tom@herbertland.com>
>> Date: Wed, 6 Apr 2016 10:53:52 -0300
>>
>>> Packets that are forwarded really should not be GRO'ed in the first
>>> place because of the loss of information and added latency.
>>
>> First of all GRO is supposed to be lossless, so please stop saying this
>> would be a reason to turn it off on a router.
>>
>> Second of all, the biggest piece of overhead is the routing lookup,
>> therefore GRO batching helps enormously with routing workloads, and
>> therefore is appropriate to be enabled on routers.
>>
>> Yes, I agree that for locally terminated stuff it helps more, but don't
>> turn this into a "GRO on routers, meh..." type argument.  It simply is
>> not true at all.
>>
> GRO on routers will help in a limited case where there is little load
> and the traffic is nicely groomed high tput TCP connections. But for
> routers with significant load, handling large quantities other
> protocols like UDP, GRO is not necessarily helpful and presents a
> nondeterministic performance improvement. For instance, I cannot
> provision a router with any assumptions that GRO will be effective for
> any % of packets to save any % of CPU, we need to provision based
> purely on ability to forward by pps assuming no benefit from GRO.

Just because you cannot predict how effective a facility will be,
that doesn't mean you shouldn't use it at all.

  reply	other threads:[~2016-04-06 19:30 UTC|newest]

Thread overview: 25+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-04-04 16:27 [net PATCH v2 0/2] Fixes for GRO and GRE tunnels Alexander Duyck
2016-04-04 16:28 ` [net PATCH v2 1/2] GRE: Disable segmentation offloads w/ CSUM and we are encapsulated via FOU Alexander Duyck
2016-04-04 16:31 ` [net PATCH v2 2/2] ipv4/GRO: Make GRO conform to RFC 6864 Alexander Duyck
2016-04-05  0:38   ` subashab
2016-04-05  3:44   ` Herbert Xu
2016-04-05  4:26     ` Alexander Duyck
2016-04-05  4:32       ` Herbert Xu
2016-04-05 15:07         ` Edward Cree
2016-04-05 15:36           ` Tom Herbert
2016-04-05 17:06             ` Edward Cree
2016-04-05 17:38               ` Tom Herbert
2016-04-06  0:04             ` Marcelo Ricardo Leitner
2016-04-05 23:45           ` David Miller
2016-04-06 11:21             ` Edward Cree
2016-04-06 13:53               ` Tom Herbert
2016-04-06 14:26                 ` Edward Cree
2016-04-06 15:39                   ` Eric Dumazet
2016-04-06 15:55                     ` Edward Cree
2016-04-06 16:03                       ` Eric Dumazet
2016-04-06 15:43                 ` David Miller
2016-04-06 17:42                   ` Tom Herbert
2016-04-06 19:30                     ` David Miller [this message]
2016-04-05 15:52         ` Alexander Duyck
2016-04-05 16:30           ` Eric Dumazet
2016-04-05 16:45             ` Alexander Duyck

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=20160406.153007.1347001580998282428.davem@davemloft.net \
    --to=davem@davemloft.net \
    --cc=aduyck@mirantis.com \
    --cc=alexander.duyck@gmail.com \
    --cc=ecree@solarflare.com \
    --cc=edumazet@google.com \
    --cc=herbert@gondor.apana.org.au \
    --cc=jesse@kernel.org \
    --cc=netdev@vger.kernel.org \
    --cc=tom@herbertland.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).