From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-pf0-f173.google.com ([209.85.192.173]:34269 "EHLO mail-pf0-f173.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753192AbdCBDI0 (ORCPT ); Wed, 1 Mar 2017 22:08:26 -0500 Received: by mail-pf0-f173.google.com with SMTP id b5so10118252pfa.1 for ; Wed, 01 Mar 2017 19:08:20 -0800 (PST) Date: Wed, 1 Mar 2017 19:07:33 -0800 From: Omar Sandoval To: Jens Axboe Cc: linux-block@vger.kernel.org, kernel-team@fb.com Subject: Re: [PATCH 2/2] blk-mq-debugfs: add q->mq_freeze_depth output Message-ID: <20170302030733.GA7792@vader> References: <7e888cad9e6c35835559281d3ab9e05ea48836d0.1488393750.git.osandov@fb.com> <6fb18656-799e-6221-6b82-44f14cd59418@fb.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii In-Reply-To: <6fb18656-799e-6221-6b82-44f14cd59418@fb.com> Sender: linux-block-owner@vger.kernel.org List-Id: linux-block@vger.kernel.org On Wed, Mar 01, 2017 at 07:25:59PM -0700, Jens Axboe wrote: > On 03/01/2017 11:42 AM, Omar Sandoval wrote: > > From: Omar Sandoval > > > > This can be used to diagnose freeze-related hangs. > > Do we really need this? For the loop case, it was painfully > obvious that it was a count issue. And I can't think of any > cases where it would have helped us, outside of rewriting > core parts (like the first edition of the shadow requests > for the scheduler). > > Not strongly opposed to it, feel free to convince me. I don't feel a burning need for it, let's just drop it.