From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:47677) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1ZZVxf-0002LO-73 for qemu-devel@nongnu.org; Tue, 08 Sep 2015 23:22:16 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1ZZVxe-0005HZ-1H for qemu-devel@nongnu.org; Tue, 08 Sep 2015 23:22:15 -0400 Date: Wed, 9 Sep 2015 11:22:05 +0800 From: Fam Zheng Message-ID: <20150909032205.GA10922@ad.nay.redhat.com> References: <1438144934-23619-1-git-send-email-famz@redhat.com> <1438144934-23619-12-git-send-email-famz@redhat.com> <55B882C1.8070500@redhat.com> <20150729105725.GA10376@ad.nay.redhat.com> <55B8B2C3.9050307@redhat.com> <20150729115333.GA15022@ad.nay.redhat.com> <55B8C12D.2070105@redhat.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <55B8C12D.2070105@redhat.com> Subject: Re: [Qemu-devel] [PATCH v2 11/11] block: Only poll block layer fds in bdrv_aio_poll List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: Paolo Bonzini Cc: kwolf@redhat.com, stefanha@redhat.com, qemu-devel@nongnu.org, qemu-block@nongnu.org On Wed, 07/29 14:03, Paolo Bonzini wrote: > > > On 29/07/2015 13:53, Fam Zheng wrote: > >> > Yes, though I think you'd end up reverting patches 10 and 11 in the end. > > We will add outer disable/enable pairs to prevent another threads's aio_poll > > from sneaking in between bdrv_aio_poll calls, but we needn't obsolete > > bdrv_aio_poll() because of that - it can be useful by itself. For example > > bdrv_aio_cancel shouldn't look at ioeventfd, otherwise it could spin for too > > long on high load. Does that make sense? > > Did you mean bdrv_drain() (when it is not already surrounded by > disable/enable pairs in the caller)? But yes, that makes sense. > > I'm not sure that it makes sense to disable/enable in places such as > bdrv_pread. The caller's block, if any, should suffice. In this sense > you'd end up reverting large parts of patch 10. > > Then you would have to see how many calls to bdrv_aio_poll are still > there, and how many can be converted with no semantic change to aio_poll > (e.g. there's no difference in qemu-img.c), and you'd end up reverting > patches 9 and 11 too. But we can look at that later. Another advantage for bdrv_aio_poll() is, in main loop we will not need a separate AioContext in changes like: http://patchwork.ozlabs.org/patch/514968/ Because nested aio_poll will automatically be limited to only process block layer events. My idea is to eventually let main loop use aio_poll, which means we would also move chardev onto it. It would be neat to put all fds of the main thread into a single AioContext. Fam