public inbox for netdev@vger.kernel.org
 help / color / mirror / Atom feed
From: "Octavian Purdila" <opurdila@ixiacom.com>
To: "Eric W. Biederman" <ebiederm@xmission.com>,
	"David Miller" <davem@davemloft.net>
Cc: <hans.schillstrom@ericsson.com>, <daniel.lezcano@free.fr>,
	<netdev@vger.kernel.org>
Subject: Re: BUG ? ipip unregister_netdevice_many()
Date: Thu, 14 Oct 2010 22:21:02 +0300	[thread overview]
Message-ID: <1287084062.1601.36.camel@Nokia-N900-42-11> (raw)


> > How can it make a real difference even in this case? We'll obliterate
> > all the entries, and then on subsequent passes we'll find nothing
> > matching that namespace any more.
> > 
> > Show me performance tests that show it makes any difference, please.
> 
> Octavian did you happen to measure the performance difference when you
> added batching of routing table flushes?
> 

Unfortunatelly I dont't have the numbers anymore, but I remember it was noticeable when using a large number of interfaces (10K) - if I remember correctly around 1 second out of 10 for the whole unregister process.

BTW, another bottleneck for mass unregister while interfaces are up is dev_deactivate / dev_close. I experimented with "batchifying" it and for 32K interfaces the time went down from 5mins to 30s.

The patch I have is not pretty, it basically creates another 2 functions for each of dev_close and dev_deactivate for pre and post synchronise_rcu barrier.

             reply	other threads:[~2010-10-14 19:20 UTC|newest]

Thread overview: 28+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2010-10-14 19:21 Octavian Purdila [this message]
  -- strict thread matches above, loose matches on Subject: below --
2010-10-07  8:48 BUG ? ipip unregister_netdevice_many() Hans Schillstrom
2010-10-08 11:19 ` Daniel Lezcano
2010-10-08 11:53   ` Hans Schillstrom
2010-10-08 12:28     ` Hans Schillstrom
2010-10-08 15:53       ` Daniel Lezcano
2010-10-08 16:17         ` Daniel Lezcano
2010-10-08 16:58           ` Eric W. Biederman
2010-10-08 17:29             ` Daniel Lezcano
2010-10-08 17:47               ` Daniel Lezcano
2010-10-08 16:45       ` Eric W. Biederman
2010-10-08 17:20         ` David Miller
2010-10-08 17:32           ` Eric W. Biederman
2010-10-12 20:05             ` David Miller
2010-10-13 11:19               ` Jarek Poplawski
2010-10-13 21:58                 ` David Miller
2010-10-14  6:41                   ` Hans Schillstrom
2010-10-13 22:16               ` Daniel Lezcano
2010-10-13 23:23                 ` David Miller
2010-10-14  3:57                   ` Eric Dumazet
2010-10-14 23:28                     ` Paul E. McKenney
2010-10-14  4:40               ` Eric W. Biederman
2010-10-14  4:50                 ` David Miller
2010-10-14  5:20                   ` Eric W. Biederman
2010-10-14 15:09                     ` David Miller
2010-10-14 18:35                       ` Eric W. Biederman
2010-10-08 16:51   ` Eric W. Biederman
2010-10-08 16:06 ` Eric W. Biederman

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=1287084062.1601.36.camel@Nokia-N900-42-11 \
    --to=opurdila@ixiacom.com \
    --cc=daniel.lezcano@free.fr \
    --cc=davem@davemloft.net \
    --cc=ebiederm@xmission.com \
    --cc=hans.schillstrom@ericsson.com \
    --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