From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from relay.sgi.com (relay1.corp.sgi.com [137.38.102.111]) by oss.sgi.com (Postfix) with ESMTP id E1D237CA2 for ; Thu, 28 Jan 2016 16:31:44 -0600 (CST) Received: from cuda.sgi.com (cuda1.sgi.com [192.48.157.11]) by relay1.corp.sgi.com (Postfix) with ESMTP id B3C918F8040 for ; Thu, 28 Jan 2016 14:31:38 -0800 (PST) Received: from userp1040.oracle.com (userp1040.oracle.com [156.151.31.81]) by cuda.sgi.com with ESMTP id 6Wo7kuHEPyJlPbZe (version=TLSv1.2 cipher=ECDHE-RSA-AES256-GCM-SHA384 bits=256 verify=NO) for ; Thu, 28 Jan 2016 14:31:37 -0800 (PST) Date: Thu, 28 Jan 2016 14:31:31 -0800 From: "Darrick J. Wong" Subject: Re: stop using ioends for direct write completions Message-ID: <20160128223131.GD6431@birch.djwong.org> References: <1452766237-2314-1-git-send-email-hch@lst.de> <20160128131656.GB14876@infradead.org> <20160128205333.GF20038@birch.djwong.org> <20160128211056.GA27287@lst.de> <20160128215853.GC6431@birch.djwong.org> <20160128220255.GA28202@lst.de> MIME-Version: 1.0 Content-Disposition: inline In-Reply-To: <20160128220255.GA28202@lst.de> List-Id: XFS Filesystem from SGI List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Errors-To: xfs-bounces@oss.sgi.com Sender: xfs-bounces@oss.sgi.com To: Christoph Hellwig Cc: xfs@oss.sgi.com On Thu, Jan 28, 2016 at 11:02:55PM +0100, Christoph Hellwig wrote: > On Thu, Jan 28, 2016 at 01:58:53PM -0800, Darrick J. Wong wrote: > > Aw, snap, I knew I'd forgotten something. Yep, we'll need that... I think > > xfs_end_io_direct_write will have to sniff out the error status from "size" > > and either remap or discard the CoW allocations as appropriate. > > I'd rather fix the direct I/O code to give us that information directly > (pun intended). I'll add that to my short term todo list as it seems > useful for the existing code as well. Ok. As for the generic/154... the code on github is sadly not very bisectable, other than to say that until yesterday I was still tacking new code onto the end of the patchset. That said, I was seeing occasional hangs in generic/154 (I needed to roll the transactions between key parts of wrapping up a CoW) and they seem to have gone away, so it's possible that I've fixed it already. --D _______________________________________________ xfs mailing list xfs@oss.sgi.com http://oss.sgi.com/mailman/listinfo/xfs