From mboxrd@z Thu Jan 1 00:00:00 1970 From: Rob Evers Subject: Re: [PATCH] delay transition requeues for 2 seconds - alua Date: Wed, 25 Apr 2012 18:16:43 -0400 Message-ID: <4F9877CB.9060501@redhat.com> References: <1325618414-26992-1-git-send-email-revers@redhat.com> <4F085F8F.2080006@redhat.com> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Return-path: Received: from mx1.redhat.com ([209.132.183.28]:28351 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1757501Ab2DYWQq (ORCPT ); Wed, 25 Apr 2012 18:16:46 -0400 In-Reply-To: <4F085F8F.2080006@redhat.com> Sender: linux-scsi-owner@vger.kernel.org List-Id: linux-scsi@vger.kernel.org To: James Bottomley Cc: linux-scsi@vger.kernel.org On 01/07/2012 10:06 AM, Rob Evers wrote: > On 01/03/2012 02:20 PM, Rob Evers wrote: >> From: Rob Evers >> >> When alua targets are transitioning, the scsi midlayer retry mechanism >> continuously retries the scsi commands that are returning with not ready >> transitioning status. The target is not capable of handling the >> commands for time on the order of several seconds during these >> transistions. >> >> This patch delays the device queue for 2 seconds, which is in the same >> order of aas transition time. >> >> Also, handle all other cases where ADD_TO_MLQUEUE_DELAY could be >> returned >> instead of ADD_TO_MLQUEUE as if ADD_TO_MLQUEUE were being returned. >> >> Problem found by array partner testing >> >> change MLQUEUE_DEV_DLY_RTY to MLQUEUE_DELAYED_RETRY > > Hi James, > > I noticed this didn't get included yet. > > If you are planning to include this, please hold off. > I misunderstood the testing status initially and we > need to collect more information. It may take some > time. > > Rob Our partner provided some updated results on testing of this and the results are mixed. Read/write traffic is reduced to the array during IO transitions as was expected. However, IO stalls during alua array transitions have been seen to get longer in some cases. Based on this, I withdraw the request to include this patch. Rob