From mboxrd@z Thu Jan 1 00:00:00 1970 From: Hannes Reinecke Subject: Re: multipath: expected results of configuring "no_path_retry"? Date: Thu, 30 Apr 2009 11:17:25 +0200 Message-ID: <49F96CA5.9050607@suse.de> References: <7oranp$22o15k@dgate10u.abg.fsc.net> Reply-To: device-mapper development Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable Return-path: In-Reply-To: <7oranp$22o15k@dgate10u.abg.fsc.net> List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: dm-devel-bounces@redhat.com Errors-To: dm-devel-bounces@redhat.com To: device-mapper development List-Id: dm-devel.ids Diedrich Ehlerding wrote: > I have a question concerning the expected behavior of dm_multipath=20 > connected to an EMC Clariion array. Different versions of multipath=20 > give different results when I disconnect all pathes to the storage.=20 >=20 > I have one server (SuSE SLES10 SP2, 2.6.16.60-0.3, multipath-tools=20 > 0.4.7-34.43) and another one (SLES 11, 2.6.27.19-5-default, 0.4.8- > 40.1). Both versions recognize the Clariion without further setting in=20 > multipath.conf. The settings for the Clariion in multipath -t seem to=20 > be the same (especially queue_if_no_path + no_path_retry 60) >=20 > Trying to setup a software mirror on top, i.e. trying to mirror the=20 > data into a second box, I observed the follwoing diffenrent behavior=20 > between these two versions:=20 >=20 > - on the SLES10 machine, disconnecting the disk in one Clariion results= =20 > in IO error, the mirror breaks up, and the use IO continues on the=20 > surviving part of the mirror. This is the behavior which I want, and=20 > which I expected, and this was my understanding of "no_path_retry" -=20 > retry some times, then terminate IO. =20 >=20 > - on the SLES11 machine, the same attempt makes IO hang infinitely. The= =20 > messages display that all pathes fail, and then "Entering recovery=20 > mode: max_retries=3D60" - but then, nothing happens; IOs hang. >=20 Yes, I know. You are triggering Novell bugzilla #485281 Patch is already available from my multipath repository git://git.kernel.org/pub/scm/linux/kernel/git/hare/multipath-tools.git branch sles11 Will be included in the next maintenance update. Cheers, Hannes --=20 Dr. Hannes Reinecke zSeries & Storage hare@suse.de +49 911 74053 688 SUSE LINUX Products GmbH, Maxfeldstr. 5, 90409 N=FCrnberg GF: Markus Rex, HRB 16746 (AG N=FCrnberg)