From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:34126) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1X9Fct-0005BI-Do for qemu-devel@nongnu.org; Mon, 21 Jul 2014 11:35:51 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1X9Fcl-0001aQ-7D for qemu-devel@nongnu.org; Mon, 21 Jul 2014 11:35:43 -0400 Received: from mail.windriver.com ([147.11.1.11]:42181) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1X9Fck-0001aH-TG for qemu-devel@nongnu.org; Mon, 21 Jul 2014 11:35:35 -0400 Message-ID: <53CD3341.60705@windriver.com> Date: Mon, 21 Jul 2014 09:35:29 -0600 From: Chris Friesen MIME-Version: 1.0 References: <53C9362C.8040507@windriver.com> <53C93C34.7030403@redhat.com> <53C949BA.9040204@windriver.com> <53C97FEB.9060208@redhat.com> <53C9A440.7020306@windriver.com> <53CA06ED.1090102@redhat.com> <53CA0FC4.8080802@windriver.com> <53CA1D06.9090601@redhat.com> <20140719084537.GA3058@irqsave.net> <53CD2AE1.6080803@windriver.com> <20140721151540.GA22161@irqsave.net> In-Reply-To: <20140721151540.GA22161@irqsave.net> Content-Type: text/plain; charset="ISO-8859-1"; format=flowed Content-Transfer-Encoding: quoted-printable Subject: Re: [Qemu-devel] is there a limit on the number of in-flight I/O operations? List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: =?ISO-8859-1?Q?Beno=EEt_Canet?= Cc: Paolo Bonzini , qemu-devel@nongnu.org On 07/21/2014 09:15 AM, Beno=EEt Canet wrote: > The Monday 21 Jul 2014 =E0 08:59:45 (-0600), Chris Friesen wrote : >> On 07/19/2014 02:45 AM, Beno=EEt Canet wrote: >> >>> I think in the throttling case the number of in flight operation is l= imited by >>> the emulated hardware queue. Else request would pile up and throttlin= g would be >>> inefective. >>> >>> So this number should be around: #define VIRTIO_PCI_QUEUE_MAX 64 or s= omething like than that. >> >> Okay, that makes sense. Do you know how much data can be written as p= art of >> a single operation? We're using 2MB hugepages for the guest memory, a= nd we >> saw the qemu RSS numbers jump from 25-30MB during normal operation up = to >> 120-180MB when running dbench. I'd like to know what the worst-case w= ould >> be. > > I think Linux as a limit of 512Kb for io size or something like that. > So the guest would have VIRTIO_PCI_QUEUE_MAX * 512Kb of in flight buffe= rs at max. Those numbers don't line up with what we were seeing...we saw a 120MB+=20 jump when running dbench, which would map to more like 2MB per operation=20 assuming a limit of VIRTIO_PCI_QUEUE_MAX (i.e. 64). Unless there are other buffers involved that we haven't factored in... Chris