From mboxrd@z Thu Jan 1 00:00:00 1970 From: Tim Pepper Subject: Re: Bad reactions to QUEUE FULL Date: Sun, 4 May 2003 21:09:24 -0700 Sender: linux-scsi-owner@vger.kernel.org Message-ID: <20030504210924.A27219@jose.vato.org> References: <20030429220259.A13386@jose.vato.org> <1051714713.1818.32.camel@mulgrave> <20030430160851.GA2350@beaverton.ibm.com> <20030430091335.A14743@jose.vato.org> <20030430165130.GC2350@beaverton.ibm.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Return-path: Received: from cpe-24-221-186-48.ca.sprintbbd.net ([24.221.186.48]:2828 "HELO jose.vato.org") by vger.kernel.org with SMTP id S261886AbTEED5B (ORCPT ); Sun, 4 May 2003 23:57:01 -0400 Content-Disposition: inline In-Reply-To: <20030430165130.GC2350@beaverton.ibm.com>; from andmike@us.ibm.com on Wed, Apr 30, 2003 at 09:51:30AM -0700 List-Id: linux-scsi@vger.kernel.org To: James Bottomley , SCSI Mailing List , Jens Axboe , olh@suse.de Bad news...this doesn't appear to have made much difference. With it 3 of the six machines were pretty much dead the morning after and the other three all have hung IO. On the other front I'm still waiting for word back from Emulex and Qlogic on the detailed tracing I sent them. > > --- linux-2.4/drivers/scsi/scsi_lib.c Wed Apr 30 09:04:16 2003 > +++ linux-2.4-p/drivers/scsi/scsi_lib.c Wed Apr 30 09:04:17 2003 > @@ -256,6 +256,17 @@ > if (SCpnt != NULL) { > > /* > + * This is a work around for a case where this Scsi_Cmnd > + * may have been through the busy retry paths already. We > + * clear the special flag and try to restore the > + * read/write request cmd value. > + */ > + if (SCpnt->request.cmd == SPECIAL) > + SCpnt->request.cmd = > + (SCpnt->sc_data_direction == > + SCSI_DATA_WRITE) ? WRITE : READ; > + > + /* > * For some reason, we are not done with this request. > * This happens for I/O errors in the middle of the request, > * in which case we need to request the blocks that come after -- ********************************************************* * tpepper@vato dot org * Venimus, Vidimus, * * http://www.vato.org/~tpepper * Dolavimus * *********************************************************