From mboxrd@z Thu Jan 1 00:00:00 1970 From: Jens Axboe Subject: Re: [dm-devel] [PATCH 05/10] block: remove per-queue plugging Date: Mon, 18 Apr 2011 11:47:39 +0200 Message-ID: <4DAC08BB.6060202@fusionio.com> References: <20110411205928.13915719@notabene.brown> <4DA2E03A.2080607@fusionio.com> <20110411212635.7959de70@notabene.brown> <4DA2E7F0.9010904@fusionio.com> <20110411220505.1028816e@notabene.brown> <4DA2F00E.6010907@fusionio.com> <20110418081922.1651474a@notabene.brown> <4DABDC60.2090009@fusionio.com> <20110418172551.55629fc6@notabene.brown> <4DABF1EA.3070301@fusionio.com> <20110418091959.GA32013@infradead.org> <4DAC070C.6010403@suse.de> Mime-Version: 1.0 Content-Type: text/plain; charset="ISO-8859-1" Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: <4DAC070C.6010403@suse.de> Sender: linux-raid-owner@vger.kernel.org To: Hannes Reinecke Cc: device-mapper development , "hch@infradead.org" , "linux-raid@vger.kernel.org" , Mike Snitzer , "linux-kernel@vger.kernel.org" , Alasdair G Kergon List-Id: linux-raid.ids On 2011-04-18 11:40, Hannes Reinecke wrote: > On 04/18/2011 11:19 AM, hch@infradead.org wrote: >> Btw, I really start to wonder if the request level is the right place >> to do this on-stack plugging. Wouldn't it be better to just plug >> bios in the on-stack queue? That way we could also stop doing the >> special case merging when adding to the plug list, and leave all the >> merging / I/O schedule logic in the __make_request path. Probably >> not .39 material, but worth a prototype? >> >> Also what this dicussion brought up is that the block layer data >> structures are highly confusing. Using a small subset of the >> request_queue also for make_request based driver just doesn't make >> sense. It seems like we should try to migrate the required state >> to struct gendisk, and submit I/O through a block_device_ops.submit >> method, leaving the request_queue as an internal abstraction for >> the request based drivers. >> > Good point. > It would also help us we the device-mapper redesign agk and myself > discussed at LSF. Having a block_device_ops.submit function would > allow us remap the actual request queue generically; and we would > even be able to address more than one request queue, which sounds > awfully similar to what Jens is trying to do ... The multiqueue bits would still have one request_queue, but multiple queueing structures (I called those blk_queue_ctx, iirc). -- Jens Axboe