LKML Archive on lore.kernel.org
help / color / mirror / Atom feed
From: Manfred Spraul <manfred@colorfullife.com>
To: Mike Galbraith <efault@gmx.de>
Cc: Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
	paulmck@linux.vnet.ibm.com, Nadia Derbey <Nadia.Derbey@bull.net>,
	Andrew Morton <akpm@linux-foundation.org>,
	Peter Zijlstra <peterz@infradead.org>,
	Pavel Emelianov <xemul@openvz.org>
Subject: Re: Scalability requirements for sysv ipc (+namespaces broken with SEM_UNDO)
Date: Sun, 30 Mar 2008 16:12:18 +0200	[thread overview]
Message-ID: <47EF9FC2.3050901@colorfullife.com> (raw)
In-Reply-To: <1206460206.4414.21.camel@marge.simson.net>

Mike Galbraith wrote:
> On Sat, 2008-03-22 at 20:08 +0100, Manfred Spraul wrote:
>
>   
>> just the normal performance of 2.6.25-rc3 is abyssimal, 55 to 60% slower 
>> than 2.6.18.8:
>>     
>
> After manually reverting 3e148c79938aa39035669c1cfa3ff60722134535,
> 2.6.25.git scaled linearly
We can't just revert that patch: with IDR, a global lock is mandatory :-(
We must either revert the whole idea of using IDR or live with the 
reduced scalability.

Actually, there are further bugs: the undo structures are not 
namespace-aware, thus semop with SEM_UNDO, unshare, create new array 
with same id, but more semaphores, another semop with SEM_UNDO will 
corrupt kernel memory :-(
I'll try to clean up the bugs first, then I'll look at the scalability 
again.

--
    Manfred

  parent reply	other threads:[~2008-03-30 14:12 UTC|newest]

Thread overview: 27+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2008-03-21  9:41 Scalability requirements for sysv ipc (was: ipc: store ipcs into IDRs) Manfred Spraul
2008-03-21 12:45 ` Nadia Derbey
2008-03-21 13:33   ` Scalability requirements for sysv ipc Manfred Spraul
2008-03-21 14:13     ` Paul E. McKenney
2008-03-21 16:08       ` Manfred Spraul
2008-03-22  5:43         ` Mike Galbraith
2008-03-22 10:10           ` Manfred Spraul
2008-03-22 11:53             ` Mike Galbraith
2008-03-22 14:22               ` Manfred Spraul
2008-03-22 19:08                 ` Manfred Spraul
2008-03-25 15:50                   ` Mike Galbraith
2008-03-25 16:13                     ` Peter Zijlstra
2008-03-25 18:31                       ` Mike Galbraith
2008-03-26  6:18                       ` Mike Galbraith
2008-03-30 14:12                     ` Manfred Spraul [this message]
2008-03-30 15:21                       ` Scalability requirements for sysv ipc (+namespaces broken with SEM_UNDO) David Newall
2008-03-30 17:18                       ` Mike Galbraith
2008-04-04 14:59                         ` Nadia Derbey
2008-04-04 15:03                           ` Nadia Derbey
2008-03-22 19:35                 ` Scalability requirements for sysv ipc Mike Galbraith
2008-03-23  6:38                   ` Manfred Spraul
2008-03-23  7:15                     ` Mike Galbraith
2008-03-23  7:08                   ` Mike Galbraith
2008-03-23  7:20                     ` Mike Galbraith
2008-03-27 22:29           ` Bill Davidsen
2008-03-28  9:49             ` Manfred Spraul
2008-03-25 16:00     ` Nadia Derbey

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=47EF9FC2.3050901@colorfullife.com \
    --to=manfred@colorfullife.com \
    --cc=Nadia.Derbey@bull.net \
    --cc=akpm@linux-foundation.org \
    --cc=efault@gmx.de \
    --cc=linux-kernel@vger.kernel.org \
    --cc=paulmck@linux.vnet.ibm.com \
    --cc=peterz@infradead.org \
    --cc=xemul@openvz.org \
    --subject='Re: Scalability requirements for sysv ipc (+namespaces broken with SEM_UNDO)' \
    /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

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).