From mboxrd@z Thu Jan 1 00:00:00 1970 From: "Daniel P. Berrange" Subject: Re: VM start time slows with large number of VMs Date: Wed, 5 Sep 2007 18:37:32 +0100 Message-ID: <20070905173732.GH5503@redhat.com> References: <089B0D75973E1241B941D0A9854F23FC08E17469@USEA-EXCH2.na.uis.unisys.com> Reply-To: "Daniel P. Berrange" Mime-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: quoted-printable Return-path: Content-Disposition: inline In-Reply-To: List-Unsubscribe: , List-Post: List-Help: List-Subscribe: , Sender: xen-devel-bounces@lists.xensource.com Errors-To: xen-devel-bounces@lists.xensource.com To: Keir Fraser Cc: xen-devel@lists.xensource.com, "Carb, Brian A" List-Id: xen-devel@lists.xenproject.org On Wed, Sep 05, 2007 at 06:11:06PM +0100, Keir Fraser wrote: > xenstore slowness seems a reasonable hypothesis. How does performance o= f > =8Ctime xenstore-ls >/dev/null=B9 change as you increase the number of = guests? There's another issue with the way hotplug scripts do locking which exhbi= ts fairly pathelogical behaviour when a large number of guests are started=20 concurrently. We've got a patch we're evaluating which changes the use o= f lock files + looping + sleeps, to instead use the 'flock' shell util. I suspect the performance issues will be a combination of both the lockin= g stuff and the xenstore I/O. You might also want to try putting /var/lib/xenstor= ed onto tmpfs eg in initscripts before xenstored starts ... mkdir /dev/shm/xenstored mount --bind /dev/shm/xenstored /var/lib/xenstored Dan. --=20 |=3D- Red Hat, Engineering, Emerging Technologies, Boston. +1 978 392 24= 96 -=3D| |=3D- Perl modules: http://search.cpan.org/~danberr/ = -=3D| |=3D- Projects: http://freshmeat.net/~danielpb/ = -=3D| |=3D- GnuPG: 7D3B9505 F3C9 553F A1DA 4AC2 5648 23C1 B3DF F742 7D3B 950= 5 -=3D|=20