Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1762707Ab2FVUmO (ORCPT ); Fri, 22 Jun 2012 16:42:14 -0400 Received: from mx1.redhat.com ([209.132.183.28]:21448 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754538Ab2FVUmN (ORCPT ); Fri, 22 Jun 2012 16:42:13 -0400 Date: Fri, 22 Jun 2012 16:42:07 -0400 From: Vivek Goyal To: Josh Hunt Cc: Jens Axboe , linux-kernel@vger.kernel.org, tj@kernel.org Subject: Re: multi-second application stall in open() Message-ID: <20120622204207.GA22063@redhat.com> References: <20120308234016.GA925@redhat.com> <20120621203217.GC14095@redhat.com> <20120622141211.GB18409@redhat.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: User-Agent: Mutt/1.5.21 (2010-09-15) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 845 Lines: 22 On Fri, Jun 22, 2012 at 03:22:01PM -0500, Josh Hunt wrote: [..] > It looks like my statement about busy_queues isn't entirely accurate. > I'm seeing this later on in the trace: Yes it is being called some times. But it is interesting to see that in the instance you pasted in last mail, we did not see "schedule_dispatch" message. Are you sure that other requests were queued at that point of time and there were busy_queues? You can try printing cfqd->rq_queued to verify that. Also put some message in cfq_select_queue() to see why it did not select a new queue before the stall. Thanks Vivek -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/