From mboxrd@z Thu Jan 1 00:00:00 1970 From: Greg Kroah-Hartman Subject: Re: System slow down from udev Date: Wed, 29 May 2013 10:07:16 +0900 Message-ID: <20130529010716.GD1893@kroah.com> References: <1826731.cQudjZKeXZ@vostro.rjw.lan> <2013173.c6WKZTQWxj@vostro.rjw.lan> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Return-path: Received: from mail.linuxfoundation.org ([140.211.169.12]:34890 "EHLO mail.linuxfoundation.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932863Ab3E2BGx (ORCPT ); Tue, 28 May 2013 21:06:53 -0400 Content-Disposition: inline In-Reply-To: <2013173.c6WKZTQWxj@vostro.rjw.lan> Sender: linux-acpi-owner@vger.kernel.org List-Id: linux-acpi@vger.kernel.org To: "Rafael J. Wysocki" Cc: Yinghai Lu , ACPI Devel Maling List , Linux Kernel Mailing List On Wed, May 29, 2013 at 02:30:12AM +0200, Rafael J. Wysocki wrote: > On Tuesday, May 28, 2013 05:01:41 PM Yinghai Lu wrote: > > On Tue, May 28, 2013 at 4:57 PM, Rafael J. Wysocki wrote: > > > On Tuesday, May 28, 2013 04:46:30 PM Yinghai Lu wrote: > > >> On Tue, May 28, 2013 at 4:50 PM, Rafael J. Wysocki wrote: > > >> > On Tuesday, May 28, 2013 04:39:37 PM Yinghai Lu wrote: > > >> >> Raphael: > > >> >> > > >> >> Found one commit in your linus-pm cause user space very slow... > > >> >> at least from udev start... > > >> > > > >> > I obviously can't reproduce it, so it would be great if you could give me > > >> > more details. > > >> > > > >> > Is there anything unusual about your test system? > > >> > > >> they are normal nehalem ex, westmere ex and ivybridge ex 8 sockets system. > > > > > > Do all of them have the same problem? > > > > yes > > > > > > > > What distro is running there? > > > > Using rescue initrd/root disk from opensuse 11.4 (?) and boot from network. > > > > udevd version is 128. > > I'm successfully running kernels including that commit on two different boxes > (dual-core and quad-core, both Intel, the quad-core one is Sandy Bridge) with > OpenSUSE 12.2 and 12.3. > > There's a machine with an older OpenSUSE on it somewhere here, but I won't be > able to get to it before tomorrow evening. > > I have no idea what's wrong at the moment. > > Please attach your .config for comparison and maybe Greg will have an idea about what's up with udev vs that commit (Greg, the > commit in question, unfortunately far from trivial, is http://git.kernel.org/cgit/linux/kernel/git/rafael/linux-pm.git/commit/?h=acpi-hotplug&id=ac212b6980d8d5eda705864fc5a8ecddc6d6eacc). I don't see how this would "slow down" the boot process. Can someone run the bootchart tool on the machine to see where the delays are? thanks, greg k-h