Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751916AbeANPpJ (ORCPT + 1 other); Sun, 14 Jan 2018 10:45:09 -0500 Received: from mail-wr0-f170.google.com ([209.85.128.170]:37244 "EHLO mail-wr0-f170.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751215AbeANPpH (ORCPT ); Sun, 14 Jan 2018 10:45:07 -0500 X-Google-Smtp-Source: ACJfBou8cdhqwXCQ3Vvvzb15bMKtzNrLQo/9DO/+5YXB9qn+MzXrkFdNXNgS2M84x7Xw+/ZNXhC3S4i9hKE/xhsWkMc= MIME-Version: 1.0 In-Reply-To: <772a286e-48f9-37c5-3687-06ba17322ca3@oracle.com> References: <20180109162953.1211451-1-tj@kernel.org> <1515790585.2396.50.camel@wdc.com> <3b2ad58c-837a-a084-fdb5-7e8913e5e285@kernel.dk> <1515791983.2396.65.camel@wdc.com> <772a286e-48f9-37c5-3687-06ba17322ca3@oracle.com> From: Ming Lei Date: Sun, 14 Jan 2018 23:45:04 +0800 Message-ID: Subject: Re: [PATCHSET v5] blk-mq: reimplement timeout handling To: "jianchao.wang" Cc: Bart Van Assche , "jbacik@fb.com" , "tj@kernel.org" , "jack@suse.cz" , "clm@fb.com" , "axboe@kernel.dk" , "kernel-team@fb.com" , "linux-kernel@vger.kernel.org" , "peterz@infradead.org" , "linux-btrfs@vger.kernel.org" , "linux-block@vger.kernel.org" Content-Type: text/plain; charset="UTF-8" Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Return-Path: On Sun, Jan 14, 2018 at 11:12 PM, jianchao.wang wrote: > > > On 01/13/2018 05:19 AM, Bart Van Assche wrote: >> Sorry but I only retrieved the blk-mq debugfs several minutes after the hang >> started so I'm not sure the state information is relevant. Anyway, I have attached >> it to this e-mail. The most remarkable part is the following: >> >> ./000000009ddfa913/requeue_list:000000009646711c {.op=READ, .state=idle, gen=0x1 >> 18, abort_gen=0x0, .cmd_flags=, .rq_flags=SORTED|1|SOFTBARRIER|IO_STAT, complete >> =0, .tag=-1, .internal_tag=217} >> >> The hexadecimal number at the start is the request_queue pointer (I modified the >> blk-mq-debugfs code such that queues are registered with there address just after >> creation and until a name is assigned). This is a dm-mpath queue. > > There seems to be something wrong in hctx->nr_active. Then looks it is same with the issue I saw during starting multipathd, and the following patch should fix that, if there isn't other issue. https://marc.info/?l=linux-block&m=151586577400558&w=2 -- Ming Lei