From patchwork Wed Jan 25 08:07:27 2017 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Hannes Reinecke X-Patchwork-Id: 9536505 Return-Path: Received: from mail.wl.linuxfoundation.org (pdx-wl-mail.web.codeaurora.org [172.30.200.125]) by pdx-korg-patchwork.web.codeaurora.org (Postfix) with ESMTP id C5DD9601D7 for ; Wed, 25 Jan 2017 08:07:33 +0000 (UTC) Received: from mail.wl.linuxfoundation.org (localhost [127.0.0.1]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id B40F026224 for ; Wed, 25 Jan 2017 08:07:33 +0000 (UTC) Received: by mail.wl.linuxfoundation.org (Postfix, from userid 486) id A8D5726E96; Wed, 25 Jan 2017 08:07:33 +0000 (UTC) X-Spam-Checker-Version: SpamAssassin 3.3.1 (2010-03-16) on pdx-wl-mail.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-6.9 required=2.0 tests=BAYES_00,RCVD_IN_DNSWL_HI autolearn=ham version=3.3.1 Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id 2858B26224 for ; Wed, 25 Jan 2017 08:07:33 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751319AbdAYIHc (ORCPT ); Wed, 25 Jan 2017 03:07:32 -0500 Received: from mx2.suse.de ([195.135.220.15]:40345 "EHLO mx2.suse.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751297AbdAYIHc (ORCPT ); Wed, 25 Jan 2017 03:07:32 -0500 X-Virus-Scanned: by amavisd-new at test-mx.suse.de Received: from relay2.suse.de (charybdis-ext.suse.de [195.135.220.254]) by mx2.suse.de (Postfix) with ESMTP id CA94FAD21; Wed, 25 Jan 2017 08:07:30 +0000 (UTC) Subject: Re: [PATCH] queue stall with blk-mq-sched To: Jens Axboe References: <762cb508-1de0-93e2-5643-3fe946428eb5@fb.com> <8abc2430-e1fd-bece-ad52-c6d1d482c1e0@suse.de> <1663de5d-cdf7-a6ed-7539-c7d1f5e98f6c@fb.com> <717c595a-a3a6-0508-b537-8cf9e273271e@kernel.dk> <8178340b-dd64-c02d-0ef2-97ad5f928dc8@suse.de> Cc: "linux-block@vger.kernel.org" , Omar Sandoval From: Hannes Reinecke Message-ID: <2b40b443-3bd6-717a-11ba-043886780adf@suse.de> Date: Wed, 25 Jan 2017 09:07:27 +0100 User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:45.0) Gecko/20100101 Thunderbird/45.6.0 MIME-Version: 1.0 In-Reply-To: <8178340b-dd64-c02d-0ef2-97ad5f928dc8@suse.de> Sender: linux-block-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-block@vger.kernel.org X-Virus-Scanned: ClamAV using ClamSMTP On 01/25/2017 08:39 AM, Hannes Reinecke wrote: > On 01/24/2017 11:06 PM, Jens Axboe wrote: >> On 01/24/2017 12:55 PM, Jens Axboe wrote: >>> Try this patch. We only want to bump it for the driver tags, not the >>> scheduler side. >> >> More complete version, this one actually tested. I think this should fix >> your issue, let me know. >> > Nearly there. > The initial stall is gone, but the test got hung at the 'stonewall' > sequence again: > > [global] > bs=4k > ioengine=libaio > iodepth=256 > size=4g > direct=1 > runtime=60 > # directory=/mnt > numjobs=32 > group_reporting > cpus_allowed_policy=split > filename=/dev/md127 > > [seq-read] > rw=read > -> stonewall > > [rand-read] > rw=randread > stonewall > > Restarting all queues made the fio job continue. > There were 4 queues with state 'restart', and one queue with state 'active'. > So we're missing a queue run somewhere. > I've found the queue stalls are gone with this patch: Cheers, Hannes diff --git a/block/blk-mq-sched.h b/block/blk-mq-sched.h index 6b465bc..de5db6c 100644 --- a/block/blk-mq-sched.h +++ b/block/blk-mq-sched.h @@ -113,6 +113,15 @@ static inline void blk_mq_sched_put_rq_priv(struct request_queue *q, } static inline void +blk_mq_sched_restart(struct blk_mq_hw_ctx *hctx) +{ + if (test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state)) { + clear_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state); + blk_mq_run_hw_queue(hctx, true); + } +} + +static inline void blk_mq_sched_completed_request(struct blk_mq_hw_ctx *hctx, struct request *rq) { struct elevator_queue *e = hctx->queue->elevator; @@ -123,11 +132,6 @@ static inline void blk_mq_sched_put_rq_priv(struct request_queue *q, BUG_ON(rq->internal_tag == -1); blk_mq_put_tag(hctx, hctx->sched_tags, rq->mq_ctx, rq->internal_tag); - - if (test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state)) { - clear_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state); - blk_mq_run_hw_queue(hctx, true); - } } static inline void blk_mq_sched_started_request(struct request *rq) diff --git a/block/blk-mq.c b/block/blk-mq.c index e872555..63799ad 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -345,6 +345,7 @@ void __blk_mq_finish_request(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx, blk_mq_put_tag(hctx, hctx->tags, ctx, rq->tag); if (sched_tag != -1) blk_mq_sched_completed_request(hctx, rq); + blk_mq_sched_restart(hctx); blk_queue_exit(q); }