From mboxrd@z Thu Jan 1 00:00:00 1970 From: Sagi Grimberg Subject: Re: [LSF/MM ATTEND][LSF/MM TOPIC] Multipath redesign Date: Wed, 13 Jan 2016 18:30:35 +0200 Message-ID: <56967BAB.9000809@dev.mellanox.co.il> References: <56961493.5010901@suse.de> <56962BDB.4080509@dev.mellanox.co.il> <20160113154243.GA2563@redhat.com> <569675F5.8070501@dev.mellanox.co.il> <20160113162102.GA2933@redhat.com> Mime-Version: 1.0 Content-Type: text/plain; charset=windows-1252; format=flowed Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: <20160113162102.GA2933@redhat.com> Sender: linux-scsi-owner@vger.kernel.org To: Mike Snitzer Cc: Hannes Reinecke , "lsf-pc@lists.linux-foundation.org" , device-mapper development , "linux-nvme@lists.infradead.org" , "linux-scsi@vger.kernel.org" List-Id: dm-devel.ids >> Hmm. I turned on /sys/module/dm_mod/parameters/use_blk_mq and indeed >> saw a significant performance improvement. Anything else I was missing? > > You can enable CONFIG_DM_MQ_DEFAULT so you don't need to manually set > use_blk_mq. I do, I started out with the manual option to test the improvements but got tired of it very quickly :) > OK, so you're only getting 1/3 of the throughput. Time for us to hunt > down the bottleneck (before real devices hit it). I have some initial instrumentation analysis so I'll be happy if we can work on that (probably can free this thread and move it to dm-devel). From mboxrd@z Thu Jan 1 00:00:00 1970 From: sagig@dev.mellanox.co.il (Sagi Grimberg) Date: Wed, 13 Jan 2016 18:30:35 +0200 Subject: [LSF/MM ATTEND][LSF/MM TOPIC] Multipath redesign In-Reply-To: <20160113162102.GA2933@redhat.com> References: <56961493.5010901@suse.de> <56962BDB.4080509@dev.mellanox.co.il> <20160113154243.GA2563@redhat.com> <569675F5.8070501@dev.mellanox.co.il> <20160113162102.GA2933@redhat.com> Message-ID: <56967BAB.9000809@dev.mellanox.co.il> >> Hmm. I turned on /sys/module/dm_mod/parameters/use_blk_mq and indeed >> saw a significant performance improvement. Anything else I was missing? > > You can enable CONFIG_DM_MQ_DEFAULT so you don't need to manually set > use_blk_mq. I do, I started out with the manual option to test the improvements but got tired of it very quickly :) > OK, so you're only getting 1/3 of the throughput. Time for us to hunt > down the bottleneck (before real devices hit it). I have some initial instrumentation analysis so I'll be happy if we can work on that (probably can free this thread and move it to dm-devel).