From mboxrd@z Thu Jan 1 00:00:00 1970 From: Linus Torvalds Subject: Re: [Regression 3.16-rc kernel] -55% reduction in throughput for OLTP benchmark Date: Thu, 31 Jul 2014 10:07:55 -0700 Message-ID: References: <1406584299.2970.924.camel@schen9-DESK> <20140729141908.GA4464@infradead.org> <1406651702.2970.927.camel@schen9-DESK> <20140729164951.GA23863@infradead.org> <1406678232.2970.943.camel@schen9-DESK> <20140730001248.GA32367@infradead.org> <1406823230.2970.946.camel@schen9-DESK> Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Cc: Christoph Hellwig , Al Viro , suruchi , ak , Dave Hansen , Matthew Wilcox , "hubert.nueckel" , beth.marsh-prime@intel.com, "doug.nelson" , linux-kernel , linux-fsdevel To: Tim Chen Return-path: In-Reply-To: <1406823230.2970.946.camel@schen9-DESK> Sender: linux-kernel-owner@vger.kernel.org List-Id: linux-fsdevel.vger.kernel.org On Thu, Jul 31, 2014 at 9:13 AM, Tim Chen wrote: > On Tue, 2014-07-29 at 17:12 -0700, Christoph Hellwig wrote: >> >> Can I get a tested-by tag from you for the patch? Can anyone else >> please cross check it? The new total value might be different from >> the old size value when we do a short write, but I can't see how >> an async write would be a good thing if we had to finish the remainder >> using buffered I/O if the old code really allowed that. >> > > Yes, please put in > > Tested-by: Tim Chen > Tested-by: Suruchi Kadu Ok, good, patch looks fine. Christoph, do you have a commit message for it? Linus