From: Avi Kivity Subject: Re: [RFC] ext4: Don't send extra barrier during fsync if there are no dirty pages. Date: Thu, 05 Aug 2010 05:20:12 +0300 Message-ID: <4C5A1FDC.3010700@redhat.com> References: <20100429235102.GC15607@tux1.beaverton.ibm.com> <1272934667.2544.3.camel@mingming-laptop> <4BE02C45.6010608@redhat.com> <20100504154553.GA22777@infradead.org> <20100630124832.GA1333@thunk.org> <4C5818A1.9070102@redhat.com> <20100804233206.GA2901@thunk.org> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit To: "Ted Ts'o" , Christoph Hellwig , Ric Wheeler , Mingming Cao , djwong@us.ibm.com, linux-ext4 Received: from mx1.redhat.com ([209.132.183.28]:30850 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1758600Ab0HECUX (ORCPT ); Wed, 4 Aug 2010 22:20:23 -0400 In-Reply-To: <20100804233206.GA2901@thunk.org> Sender: linux-ext4-owner@vger.kernel.org List-ID: On 08/05/2010 02:32 AM, Ted Ts'o wrote: > On Tue, Aug 03, 2010 at 04:24:49PM +0300, Avi Kivity wrote: >> On 06/30/2010 03:48 PM, tytso@mit.edu wrote: >>> I wonder if it's worthwhile to think about a new system call which >>> allows users to provide an array of fd's which are collectively should >>> be fsync'ed out at the same time. Otherwise, we end up issuing >>> multiple barrier operations in cases where the application needs to >>> do: >>> >>> fsync(control_fd); >>> fsync(data_fd); >>> >> The system call exists, it's called io_submit(). > Um, not the same thing at all. Why not? To be clear, I'm talking about an io_submit() with multiple IO_CMD_FSYNC requests, with a kernel implementation that is able to batch these requests. -- I have a truly marvellous patch that fixes the bug which this signature is too narrow to contain.