From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from mailman by lists.gnu.org with tmda-scanned (Exim 4.43) id 1LB8wW-00029O-1s for qemu-devel@nongnu.org; Fri, 12 Dec 2008 09:24:36 -0500 Received: from exim by lists.gnu.org with spam-scanned (Exim 4.43) id 1LB8wU-000294-J1 for qemu-devel@nongnu.org; Fri, 12 Dec 2008 09:24:35 -0500 Received: from [199.232.76.173] (port=47046 helo=monty-python.gnu.org) by lists.gnu.org with esmtp (Exim 4.43) id 1LB8wU-00028w-G5 for qemu-devel@nongnu.org; Fri, 12 Dec 2008 09:24:34 -0500 Received: from yw-out-1718.google.com ([74.125.46.157]:11656) by monty-python.gnu.org with esmtp (Exim 4.60) (envelope-from ) id 1LB8wU-00031W-6R for qemu-devel@nongnu.org; Fri, 12 Dec 2008 09:24:34 -0500 Received: by yw-out-1718.google.com with SMTP id 6so665030ywa.82 for ; Fri, 12 Dec 2008 06:24:33 -0800 (PST) Message-ID: <4942741C.4090802@codemonkey.ws> Date: Fri, 12 Dec 2008 08:24:28 -0600 From: Anthony Liguori MIME-Version: 1.0 Subject: Re: [Qemu-devel] [RFC] Replace posix-aio with custom thread pool References: <20081211131222.GA14908@random.random> <494130B5.2080800@redhat.com> <20081211155335.GE14908@random.random> <49413B9C.3030703@redhat.com> <20081211164947.GD6809@random.random> <49414BC9.5090905@redhat.com> <20081211181116.GE6809@random.random> <20081212082309.GI23742@kernel.dk> <20081212115133.GI6809@random.random> <20081212115420.GR23742@kernel.dk> <20081212141333.GJ6809@random.random> In-Reply-To: <20081212141333.GJ6809@random.random> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Reply-To: qemu-devel@nongnu.org List-Id: qemu-devel.nongnu.org List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: Andrea Arcangeli Cc: Chris Wright , qemu-devel@nongnu.org, kvm-devel , Gerd Hoffmann Andrea Arcangeli wrote: > On Fri, Dec 12, 2008 at 12:54:21PM +0100, Jens Axboe wrote: > > In the meantime I think it'd be better to -EINVAL (so the userland > thread can fallback to userland thread pool) instead of just behaving > synchronously that can break GUI and interactive behavior... > Yes, IMHO, this is the major problem with the current state of linux-aio. I really don't want to expose an aio= flag for users to configure. I'd rather just do the Right Thing automatically. >> I added CLONE_IO some time ago to avoid that, so it's perfectly possible >> to share cfq io contexts with threads or processes even in userspace! >> > > It's available in recent kernels I see! so the fix is easy. Only > problem is how to pass CLONE_IO to pthread_create... We'll have to > make a linux-only change and call clone by hand under some #ifdef > CLONE_IO. > I have no problem with this and I believe Chris was going to attempt an implementation. Regards, Anthony Liguori > -- > To unsubscribe from this list: send the line "unsubscribe kvm" in > the body of a message to majordomo@vger.kernel.org > More majordomo info at http://vger.kernel.org/majordomo-info.html >