From mboxrd@z Thu Jan 1 00:00:00 1970 From: Mike Anderson Subject: Re: [PATCH] block: add support for shared tag maps Date: Fri, 1 Sep 2006 13:11:44 -0700 Message-ID: <20060901201144.GA16135@us.ibm.com> References: <1157117328.3675.6.camel@mulgrave.il.steeleye.com> <20060901190423.806416@bebe.enoyolf.org> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Return-path: Received: from e35.co.us.ibm.com ([32.97.110.153]:5341 "EHLO e35.co.us.ibm.com") by vger.kernel.org with ESMTP id S1751859AbWIAUKC (ORCPT ); Fri, 1 Sep 2006 16:10:02 -0400 Received: from d03relay04.boulder.ibm.com (d03relay04.boulder.ibm.com [9.17.195.106]) by e35.co.us.ibm.com (8.13.8/8.12.11) with ESMTP id k81KA0F6022740 for ; Fri, 1 Sep 2006 16:10:00 -0400 Received: from d03av03.boulder.ibm.com (d03av03.boulder.ibm.com [9.17.195.169]) by d03relay04.boulder.ibm.com (8.13.6/8.13.6/NCO v8.1.1) with ESMTP id k81KA0ga273096 for ; Fri, 1 Sep 2006 14:10:00 -0600 Received: from d03av03.boulder.ibm.com (loopback [127.0.0.1]) by d03av03.boulder.ibm.com (8.12.11.20060308/8.13.3) with ESMTP id k81K9xkn025566 for ; Fri, 1 Sep 2006 14:10:00 -0600 Content-Disposition: inline In-Reply-To: <20060901190423.806416@bebe.enoyolf.org> Sender: linux-scsi-owner@vger.kernel.org List-Id: linux-scsi@vger.kernel.org To: Doug Maxey Cc: Ravi Anand , James Bottomley , mikec linux-scsi , Jens Axboe Doug Maxey wrote: > > Ravi, > > While working on a patch to add shared tags to qla4xxx was looking at > the shost->can_queue settings, I see the value is set pretty high: > > qla4xxx_probe() > ... > host->can_queue = REQUEST_QUEUE_DEPTH + 128; > > where REQUEST_QUEUE_DEPTH works out to be 1024. > > My question: > what is the relationship between the can_queue and the > setting in > qla4xxx_slave_configure() > if (sdev->tagged_supported) > scsi_activate_tcq(sdev, 32); > else > scsi_deactivate_tcq(sdev, 32); > > Does this imply that the firmware can ultimately track more requests > than we can possibly stuff in it? Where do the other 1012 requests get > queued, in the block layer? Maybe I misreading your question. host->can_queue is the per host instance (adapter) limit and scsi_activate_tcq will set the per dev (lun) limit. host->can_queue being large is a good thing (if it is backed by real resources). In theory can_queue should be scaled to support a hosts ${max_number_of_devices} * ${max_queue_depth}. -andmike -- Michael Anderson andmike@us.ibm.com