From mboxrd@z Thu Jan 1 00:00:00 1970 From: Tejun Heo Subject: Re: [PATCH block:for-3.3/core] cfq: merged request shouldn't jump to a different cfqq Date: Thu, 5 Jan 2012 20:40:06 -0800 Message-ID: References: <20120103200906.GG31746@google.com> <4F03631C.8080501@kernel.dk> <20120103221301.GH31746@google.com> <20120103223505.GI31746@google.com> <20120105012445.GP31746@google.com> <20120105183842.GF18486@google.com> <20120106021707.GA6276@google.com> <20120106023638.GC6276@google.com> <1325819655.22361.513.camel@sli10-conroe> <20120106030406.GD6276@google.com> <1325820878.22361.518.camel@sli10-conroe> <1325823349.22361.523.camel@sli10-conroe> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Return-path: In-Reply-To: <1325823349.22361.523.camel@sli10-conroe> Sender: linux-ide-owner@vger.kernel.org To: Shaohua Li Cc: Jens Axboe , Hugh Dickins , Andrew Morton , Stephen Rothwell , linux-next@vger.kernel.org, LKML , linux-scsi@vger.kernel.org, linux-ide@vger.kernel.org, x86@kernel.org List-Id: linux-scsi@vger.kernel.org Hello, On Thu, Jan 5, 2012 at 8:15 PM, Shaohua Li wrote: > don't know. I don't think a tweak for merge impacts isolation so much. > For rotate disk, request size hasn't impact to request cost, so this > doesn't impact isolation. Even for ssd, big size request is more > efficient to dispatch. And we already have breakage of fairness for SSD, > such as no idle. I'm not saying they shouldn't be merged but the decision should be elevator's. Block core shouldn't decide it for the elevator. So, whether cross cfqq merge is a good idea or not is mostly irrelevant in this thread. Thanks. -- tejun