From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:50472) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1Yivc6-0008JN-VW for qemu-devel@nongnu.org; Thu, 16 Apr 2015 22:02:40 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1Yivc2-0007MC-9H for qemu-devel@nongnu.org; Thu, 16 Apr 2015 22:02:38 -0400 Received: from mx1.redhat.com ([209.132.183.28]:39334) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1Yivc2-0007Lu-4W for qemu-devel@nongnu.org; Thu, 16 Apr 2015 22:02:34 -0400 Received: from int-mx13.intmail.prod.int.phx2.redhat.com (int-mx13.intmail.prod.int.phx2.redhat.com [10.5.11.26]) by mx1.redhat.com (Postfix) with ESMTPS id E6C1BAB847 for ; Fri, 17 Apr 2015 02:02:32 +0000 (UTC) Date: Fri, 17 Apr 2015 10:02:30 +0800 From: Fam Zheng Message-ID: <20150417020230.GF28705@ad.nay.redhat.com> References: <1429160256-27231-1-git-send-email-famz@redhat.com> <20150416130316.GF27070@stefanha-thinkpad.redhat.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20150416130316.GF27070@stefanha-thinkpad.redhat.com> Subject: Re: [Qemu-devel] [PATCH v3 0/7] aio: Support epoll by introducing qemu_poll abstraction List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: Stefan Hajnoczi Cc: Kevin Wolf , Paolo Bonzini , qemu-devel@nongnu.org On Thu, 04/16 14:03, Stefan Hajnoczi wrote: > On Thu, Apr 16, 2015 at 12:57:29PM +0800, Fam Zheng wrote: > > v3: Rebase to master for 2.4. > > Although epoll_pwait1 syscall is still being worked on [1], the QEMU part > > (if any) will base on this, so let's merge it first. > > > > That part is not included in this version because I'm still evaluating by > > comparing epoll_pwait1 with epoll+timerfd as with current master they seem > > to be really close. > > > > [1]: http://www.spinics.net/lists/linux-api/msg08216.html > > > > v2: Emulate nanoseconds precison of timeout with ppoll and timerfd. > > Their performance is on par with each other, but both much better than > > qemu.git: > > > > syscall high # of fd low # of fd > > ------------------------------------------------- > > qemu.git(ppoll) 44 96 > > ppoll+epoll 85 101 > > timerfd+epoll 87 109 > > > > (In high # of fd case, 3 activated but idle virtio-console devices are > > attached, which will add us hundereds of fds to poll) > > Have you rerun benchmarks with this patch series? Yes, here: syscall high # of fd low # of fd (Unit MB/s) (Unit MB/s) ------------------------------------------------- qemu.git(ppoll) 24 73 ppoll+epoll 49 77 timerfd+epoll 49 82 > > I wonder how the ppoll-only performance changes. It seems like there > are now additional copies of information and > corresponding malloc/realloc/frees. > > Stefan