From mboxrd@z Thu Jan 1 00:00:00 1970 From: Christoph Hellwig Subject: Re: [dm-devel] [PATCH 0/4] scsi_dh: Make scsi_dh_activate asynchronous Date: Wed, 21 Oct 2009 21:06:08 -0400 Message-ID: <20091022010608.GA10445@infradead.org> References: <20091021162240.8473.99556.sendpatchset@chandra-ubuntu> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Return-path: Received: from bombadil.infradead.org ([18.85.46.34]:37218 "EHLO bombadil.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753536AbZJVBGF (ORCPT ); Wed, 21 Oct 2009 21:06:05 -0400 Content-Disposition: inline In-Reply-To: <20091021162240.8473.99556.sendpatchset@chandra-ubuntu> Sender: linux-scsi-owner@vger.kernel.org List-Id: linux-scsi@vger.kernel.org To: device-mapper development Cc: linux-scsi@vger.kernel.org, michaelc@cs.wisc.edu, Benoit_Arthur@emc.com, Eddie.Williams@steeleye.com On Wed, Oct 21, 2009 at 09:22:40AM -0700, Chandra Seetharaman wrote: > Hello All, > > Currently, device handlers process path activation in series. This leads > to a lot of time delay when more than 100 luns are involved. For example, > with lsi rdac 100+ luns take about 12-15 minutes. This was found by Moger > Babu of LSI. So what happened to the suggestion to just switch over per target instead of per lun? It's the obviously much better way to do, and unless there are bugs in the hardware preventing it from working it should be the way to go.