All of lore.kernel.org
 help / color / mirror / Atom feed
From: Eric Dumazet <dada1@cosmosbay.com>
To: Benjamin LaHaise <bcrl@lhnet.ca>
Cc: Denys Fedoryschenko <denys@visp.net.lb>, netdev@vger.kernel.org
Subject: Re: regression: unregister_netdev() unusably slow
Date: Mon, 25 May 2009 00:47:39 +0200	[thread overview]
Message-ID: <4A19CE8B.3070302@cosmosbay.com> (raw)
In-Reply-To: <20090524221240.GI24757@kvack.org>

Benjamin LaHaise a écrit :
> On Mon, May 25, 2009 at 12:07:07AM +0200, Eric Dumazet wrote:
>> Maybe your HZ is too low ? Changing to 1000 HZ helps a lot
> 
> HZ is set to 1000.  I turned off CONFIG_NO_HZ
> 
>> Also your hotplug config might do strange things at device removal ?
> 
> If it were CPU bound, maybe, but this behaviour is tied to the kernel 
> version in use.
> 
>> What distro do you use ?
> 
> It's an older Fedora 7 install inside kvm on a Fedora 10 host running 
> 2.6.30-rc7.
> 

OK thanks

I switched HZ from 250 to 1000 and got :

time ip link del vlan.899

real    0m0.011s
user    0m0.000s
sys     0m0.002s

There is a strong dependancy against HZ
BTW, I am using TREE_RCU

# RCU Subsystem
# CONFIG_CLASSIC_RCU is not set
CONFIG_TREE_RCU=y
# CONFIG_PREEMPT_RCU is not set
CONFIG_RCU_TRACE=y
CONFIG_RCU_FANOUT=32
# CONFIG_RCU_FANOUT_EXACT is not set
CONFIG_TREE_RCU_TRACE=y
# CONFIG_PREEMPT_RCU_TRACE is not set
# CONFIG_RCU_TORTURE_TEST is not set
# CONFIG_RCU_CPU_STALL_DETECTOR is not set



  reply	other threads:[~2009-05-24 22:47 UTC|newest]

Thread overview: 12+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2009-05-24 19:21 regression: unregister_netdev() unusably slow Benjamin LaHaise
2009-05-24 21:23 ` Denys Fedoryschenko
2009-05-24 21:37   ` Benjamin LaHaise
2009-05-24 21:42     ` Eric Dumazet
2009-05-24 21:44       ` Benjamin LaHaise
2009-05-24 22:07         ` Eric Dumazet
2009-05-24 22:12           ` Benjamin LaHaise
2009-05-24 22:47             ` Eric Dumazet [this message]
2009-05-25  0:00               ` Benjamin LaHaise
2009-05-25  5:22                 ` Eric Dumazet
2009-05-25  8:04                   ` Damien Wyart
2009-05-25 16:21                   ` Paul E. McKenney

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=4A19CE8B.3070302@cosmosbay.com \
    --to=dada1@cosmosbay.com \
    --cc=bcrl@lhnet.ca \
    --cc=denys@visp.net.lb \
    --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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.