From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from [140.186.70.92] (port=53540 helo=eggs.gnu.org) by lists.gnu.org with esmtp (Exim 4.43) id 1OGwsk-0006yY-Lw for qemu-devel@nongnu.org; Tue, 25 May 2010 12:21:31 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.69) (envelope-from ) id 1OGwsj-0004X4-2C for qemu-devel@nongnu.org; Tue, 25 May 2010 12:21:30 -0400 Received: from mail-gy0-f173.google.com ([209.85.160.173]:45022) by eggs.gnu.org with esmtp (Exim 4.69) (envelope-from ) id 1OGwsi-0004Wu-WA for qemu-devel@nongnu.org; Tue, 25 May 2010 12:21:29 -0400 Received: by gyd5 with SMTP id 5so2156848gyd.4 for ; Tue, 25 May 2010 09:21:28 -0700 (PDT) Message-ID: <4BFBF905.1030901@codemonkey.ws> Date: Tue, 25 May 2010 11:21:25 -0500 From: Anthony Liguori MIME-Version: 1.0 Subject: Re: [Qemu-devel] [RFC PATCH 1/1] ceph/rbd block driver for qemu-kvm References: <20100519192222.GD61706@ncolin.muc.de> <4BF5A9D2.5080609@codemonkey.ws> <4BF91937.2070801@redhat.com> <4BFBAE46.5050801@redhat.com> <4BFBB3C1.9020905@redhat.com> <4BFBCFAC.9070807@codemonkey.ws> <4BFBD13C.60605@redhat.com> <4BFBD20E.5060207@codemonkey.ws> <4BFBD2D5.2000201@redhat.com> <4BFBD6CD.3000503@codemonkey.ws> <4BFBD82F.3020404@redhat.com> <4BFBD943.8020704@codemonkey.ws> <4BFBE614.9080306@redhat.com> <4BFBE64F.6020901@codemonkey.ws> <4BFBF7D4.80900@redhat.com> In-Reply-To: <4BFBF7D4.80900@redhat.com> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit List-Id: qemu-devel.nongnu.org List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: Avi Kivity Cc: Kevin Wolf , kvm@vger.kernel.org, qemu-devel@nongnu.org, Blue Swirl , ceph-devel@vger.kernel.org, Christian Brunner On 05/25/2010 11:16 AM, Avi Kivity wrote: > On 05/25/2010 06:01 PM, Anthony Liguori wrote: >> On 05/25/2010 10:00 AM, Avi Kivity wrote: >>> The latter. Why is it less important? If you don't inherit the >>> memory, you can't access it. >>> >>>> You can also pass /dev/shm fd's via SCM_RIGHTs to establish shared >>>> memory segments dynamically. >>> >>> Doesn't work for anonymous memory. >> >> What's wrong with /dev/shm memory? > > The kernel treats anonymous and nonymous memory differently for > swapping (see /proc/sys/vm/swappiness); transparent hugepages won't > work for /dev/shm (though it may be argued that that's a problem with > thp); setup (/dev/shm defaults to half memory IIRC, we want mem+swap); > different cgroup handling; somewhat clunky (a minor concern to be sure). Surely, with mmu notifiers, it wouldn't be that hard to share anonymous memory via an fd though, no? Regards, Anthony Liguori > > Nothing is a killer, but we should prefer anonymous memory. >