From mboxrd@z Thu Jan 1 00:00:00 1970 From: Bart Van Assche Subject: Re: [PATCHv5 00/36] asynchronous ALUA device handler Date: Tue, 13 Oct 2015 08:40:31 -0700 Message-ID: <561D25EF.2060209@sandisk.com> References: <1443523658-87622-1-git-send-email-hare@suse.de> <560AD88B.9050902@sandisk.com> <560BE1DC.9060600@suse.de> <560C5509.6050206@sandisk.com> <561CD294.3080905@suse.de> <561D1E3E.5030201@sandisk.com> <561D1F7D.7070803@suse.de> Mime-Version: 1.0 Content-Type: text/plain; charset="utf-8"; format=flowed Content-Transfer-Encoding: 7bit Return-path: Received: from mail-bn1bon0086.outbound.protection.outlook.com ([157.56.111.86]:20352 "EHLO na01-bn1-obe.outbound.protection.outlook.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S932341AbbJMPkh (ORCPT ); Tue, 13 Oct 2015 11:40:37 -0400 In-Reply-To: <561D1F7D.7070803@suse.de> Sender: linux-scsi-owner@vger.kernel.org List-Id: linux-scsi@vger.kernel.org To: Hannes Reinecke , James Bottomley Cc: "linux-scsi@vger.kernel.org" , Christoph Hellwig , Ewan Milne , "Martin K. Petersen" On 10/13/2015 08:13 AM, Hannes Reinecke wrote: > On 10/13/2015 05:07 PM, Bart Van Assche wrote: >> On 10/13/2015 02:44 AM, Hannes Reinecke wrote: >>> I have rebased my patches to 4.3.0-rc5 and didn't see any lockups; >>> tested with hpsa and lpfc, both mq enabled and disabled. >>> >>> Can you check if it's specific to ib_srp? Is there a way to simulate >>> an ib_srp setup? >> >> This infinite loop was due to the scsi_dh_alua handler not being >> loaded during my test (as mentioned in >> https://www.mail-archive.com/linux-scsi@vger.kernel.org/msg42645.html). > > So it works with that patch? Hello Hannes, Manually loading the scsi_dh_alua handler or adding the patch that loads that handler again automatically indeed fixed the infinite loop. But I'm still very concerned about the scalability issues caused by submitting RTPG commands synchronously instead of asynchronously. Bart.