From mboxrd@z Thu Jan 1 00:00:00 1970 From: Hannes Reinecke Subject: Re: [dm-devel] LSF: Multipathing and path checking question Date: Tue, 21 Apr 2009 09:26:27 +0200 Message-ID: <49ED7523.5080108@suse.de> References: <49E7B845.70400@cs.wisc.edu> <49E834CD.1090306@suse.de> <49E89866.50205@cs.wisc.edu> <49E89E92.7070709@cs.wisc.edu> <49EC3010.5050502@suse.de> <49ECCBAC.70308@cs.wisc.edu> <49ECFF0F.5080003@cs.wisc.edu> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: QUOTED-PRINTABLE Return-path: Received: from cantor2.suse.de ([195.135.220.15]:55308 "EHLO mx2.suse.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752365AbZDUH02 (ORCPT ); Tue, 21 Apr 2009 03:26:28 -0400 In-Reply-To: <49ECFF0F.5080003@cs.wisc.edu> Sender: linux-scsi-owner@vger.kernel.org List-Id: linux-scsi@vger.kernel.org To: Mike Christie Cc: device-mapper development , SCSI Mailing List Mike Christie wrote: > Mike Christie wrote: >>> For starters we just should send a netlink event when fast_fail_io = has >>> fired. We could easily integrate that one in multipathd and would g= ain >>> an instant benefit from that as we can switch paths in advance. >>> Next step would be to implement an additional sdev state which woul= d >>> return 'DID_TRANSPORT_FASTFAIL' for any 'normal' I/O; it would be >>> inserted between 'RUNNING' and 'CANCEL'. >>> Transition would be possible between 'RUNNING' and 'FASTFAIL', but >>> it would only be possible to transition into 'CANCEL' from 'FASTFAI= L'. >>> >> >> >> Yeah, a new sdev state might be nice. Right now this state is handle= d >> by the classes. For iscsi and FC the port/session will be in >> blocked/ISCSI_SESSION_FAILED. Then internally the classes are >> decieding what to do with IO in the *_chkready functions. >> >> >=20 >=20 > How about setting the device to the offline state for this case where > fast_io_fail has fired but the dev_loss_tmo has not yet fired? As fas= t > as failing IO we get the same result. scsi-ml would fail the incoming= IO > instead of it getting to the class _chkready functions, but the scsi > device state indicates that it cannot execute IO which might be nice = for > users. >=20 Ah, no. OFFLINE is a dead end status out of which we cannot transition from inside the kernel. I'd prefer a new state here. 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) -- To unsubscribe from this list: send the line "unsubscribe linux-scsi" i= n the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html