From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from relay.sgi.com (relay2.corp.sgi.com [137.38.102.29]) by oss.sgi.com (Postfix) with ESMTP id B6A537F3F for ; Tue, 13 Jan 2015 16:58:36 -0600 (CST) Received: from cuda.sgi.com (cuda1.sgi.com [192.48.157.11]) by relay2.corp.sgi.com (Postfix) with ESMTP id 88CD9304039 for ; Tue, 13 Jan 2015 14:58:33 -0800 (PST) Received: from sandeen.net (sandeen.net [63.231.237.45]) by cuda.sgi.com with ESMTP id EB7jGnCe6WyXNO1H for ; Tue, 13 Jan 2015 14:58:30 -0800 (PST) Message-ID: <54B5A313.2030300@sandeen.net> Date: Tue, 13 Jan 2015 16:58:27 -0600 From: Eric Sandeen MIME-Version: 1.0 Subject: Re: [PATCH 2/2] xfs: mark the xfs-alloc workqueue as high priority References: <20150109182310.GA2785@htj.dyndns.org> <54B03BCC.7040207@sandeen.net> <20150110192852.GD25319@htj.dyndns.org> <54B429EB.9050807@sandeen.net> <20150112225314.GC22156@htj.dyndns.org> <54B454E2.70707@sandeen.net> <20150112233755.GD22156@htj.dyndns.org> <54B56D2B.6090401@sandeen.net> <20150113201900.GA9489@htj.dyndns.org> <54B58041.9070502@sandeen.net> <20150113204633.GC9489@htj.dyndns.org> In-Reply-To: <20150113204633.GC9489@htj.dyndns.org> List-Id: XFS Filesystem from SGI List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Errors-To: xfs-bounces@oss.sgi.com Sender: xfs-bounces@oss.sgi.com To: Tejun Heo Cc: Eric Sandeen , xfs-oss On 1/13/15 2:46 PM, Tejun Heo wrote: > So, > > nr_workers == 15, > nr_idle == 0, > nr_running == 0, > > That means one worker must be playing the role of manager by executing > manage_workers() whic his also responsible for kicking off the > rescuers if it fails to create new workers in a short period of time. > The manager is identifier as the holder of pool->manager_arb and while > a manager is trying to creat a worker, pool->mayday_timer must be > armed continuously firing off every MAYDAY_INTERVAL summoning rescuers > to the pool, which should be visible through the pool_pwq->mayday_node > corresponding to the stalled pool being queued on wq->maydays. > > Can you post the full dump of the pool, wq and all kworkers? > > Thanks. > Just for mailing list archive posterity, Tejun thinks he's found the culprit in the workqueue code, I or he can follow up again when he has a patch ready to go. Thanks Tejun! -Eric _______________________________________________ xfs mailing list xfs@oss.sgi.com http://oss.sgi.com/mailman/listinfo/xfs