From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: From: Martin Steigerwald To: Ming Lei Cc: Jens Axboe , Tetsuo Handa , Bart.VanAssche@wdc.com, dvyukov@google.com, linux-kernel@vger.kernel.org, linux-block@vger.kernel.org, jthumshirn@suse.de, alan.christopher.jenkins@gmail.com, syzbot+c4f9cebf9d651f6e54de@syzkaller.appspotmail.com, martin.petersen@oracle.com, dan.j.williams@intel.com, hch@lst.de, oleksandr@natalenko.name, hare@suse.com, syzkaller-bugs@googlegroups.com, ross.zwisler@linux.intel.com, keith.busch@intel.com, linux-ext4@vger.kernel.org Subject: Re: INFO: task hung in blk_queue_enter Date: Sat, 02 Jun 2018 10:07:26 +0200 Message-ID: <6992049.xPdnW5VfcJ@merkaba> In-Reply-To: <20180602045353.GA20257@ming.t460p> References: <20180602045353.GA20257@ming.t460p> MIME-Version: 1.0 Content-Type: text/plain; charset="UTF-8" List-ID: Ming Lei - 02.06.18, 06:54: > On Fri, Jun 01, 2018 at 10:31:13PM -0600, Jens Axboe wrote: > > On 6/1/18 8:36 PM, Ming Lei wrote: > > >> clear the bit when we need to, potentially even adding a debug > > >> check to blk_queue_enter_live() that complains if the ref was > > >> not already elevated. Though that would be expensive, compared > > >> to the percpu inc now. Not saying the bit is necessarily the > > >> best way forward, but I do like it a LOT more than adding an > > >> argument to generic_make_request.> >=20 > > > We may introduce generic_make_request_with_ref() for > > > blk_queue_split(), what do you think of the following patch? > >=20 > > Functionally it'll work as well. >=20 > If you are fine with this one, I'm glad to prepare for a normal one, > so that we can save one precious bio flag, and the total number is > just 13. [=E2=80=A6] I am completely lost about what you are talking about. That is fine with me, but in case there is anything to test=E2=80=A6 let me= =20 know. I do not promise quick responses tough, as I have been quite a bit=20 overwhelmed with stuff lately. Currently I run 4.17-rc7 without any blk-mq related patches and it=20 appears to be free of hangs or stalls related to blk-mq. Thanks, =2D-=20 Martin From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751338AbeFBIHh convert rfc822-to-8bit (ORCPT ); Sat, 2 Jun 2018 04:07:37 -0400 Received: from mondschein.lichtvoll.de ([194.150.191.11]:58195 "EHLO mail.lichtvoll.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750821AbeFBIHa (ORCPT ); Sat, 2 Jun 2018 04:07:30 -0400 Authentication-Results: auth=pass smtp.auth=martin smtp.mailfrom=martin@lichtvoll.de From: Martin Steigerwald To: Ming Lei Cc: Jens Axboe , Tetsuo Handa , Bart.VanAssche@wdc.com, dvyukov@google.com, linux-kernel@vger.kernel.org, linux-block@vger.kernel.org, jthumshirn@suse.de, alan.christopher.jenkins@gmail.com, syzbot+c4f9cebf9d651f6e54de@syzkaller.appspotmail.com, martin.petersen@oracle.com, dan.j.williams@intel.com, hch@lst.de, oleksandr@natalenko.name, hare@suse.com, syzkaller-bugs@googlegroups.com, ross.zwisler@linux.intel.com, keith.busch@intel.com, linux-ext4@vger.kernel.org Subject: Re: INFO: task hung in blk_queue_enter Date: Sat, 02 Jun 2018 10:07:26 +0200 Message-ID: <6992049.xPdnW5VfcJ@merkaba> In-Reply-To: <20180602045353.GA20257@ming.t460p> References: <20180602045353.GA20257@ming.t460p> MIME-Version: 1.0 Content-Transfer-Encoding: 8BIT Content-Type: text/plain; charset="UTF-8" Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Ming Lei - 02.06.18, 06:54: > On Fri, Jun 01, 2018 at 10:31:13PM -0600, Jens Axboe wrote: > > On 6/1/18 8:36 PM, Ming Lei wrote: > > >> clear the bit when we need to, potentially even adding a debug > > >> check to blk_queue_enter_live() that complains if the ref was > > >> not already elevated. Though that would be expensive, compared > > >> to the percpu inc now. Not saying the bit is necessarily the > > >> best way forward, but I do like it a LOT more than adding an > > >> argument to generic_make_request.> > > > > We may introduce generic_make_request_with_ref() for > > > blk_queue_split(), what do you think of the following patch? > > > > Functionally it'll work as well. > > If you are fine with this one, I'm glad to prepare for a normal one, > so that we can save one precious bio flag, and the total number is > just 13. […] I am completely lost about what you are talking about. That is fine with me, but in case there is anything to test… let me know. I do not promise quick responses tough, as I have been quite a bit overwhelmed with stuff lately. Currently I run 4.17-rc7 without any blk-mq related patches and it appears to be free of hangs or stalls related to blk-mq. Thanks, -- Martin