From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752803Ab3F1Uqf (ORCPT ); Fri, 28 Jun 2013 16:46:35 -0400 Received: from cantor2.suse.de ([195.135.220.15]:54928 "EHLO mx2.suse.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752382Ab3F1Uqe (ORCPT ); Fri, 28 Jun 2013 16:46:34 -0400 Date: Fri, 28 Jun 2013 22:46:31 +0200 From: Jan Kara To: Jens Axboe Cc: Jan Kara , LKML Subject: Re: [PATCH] block: Reserve only one queue tag for sync IO if only 3 tags are available Message-ID: <20130628204631.GB15288@quack.suse.cz> References: <1372432127-9716-1-git-send-email-jack@suse.cz> <20130628193152.GF24293@kernel.dk> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20130628193152.GF24293@kernel.dk> User-Agent: Mutt/1.5.21 (2010-09-15) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Fri 28-06-13 21:31:52, Jens Axboe wrote: > On Fri, Jun 28 2013, Jan Kara wrote: > > In case a device has three tags available we still reserve two of them > > for sync IO. That leaves only a single tag for async IO such as > > writeback from flusher thread which results in poor performance. > > > > Allow async IO to consume two tags in case queue has three tag availabe > > to get a decent async write performance. > > > > This patch improves streaming write performance on a machine with such disk > > from ~21 MB/s to ~52 MB/s. Also postmark throughput in presence of > > streaming writer improves from 8 to 12 transactions per second so sync > > IO doesn't seem to be harmed in presence of heavy async writer. > > That's pretty crazy! Never seen a device like that. But yes, it > obviously exists, and the 2 reserved tags doesn't work well for that. So > it's an improvement. Yeah, I agree it's a weird hardware. It's a ppc64 machine where storage identifies as: scsi2 : IBM 573E Storage Adapter scsi 2:0:4:0: Direct-Access IBM ST373453LC C51C PQ: 0 ANSI: 3 scsi 2:0:5:0: Direct-Access IBM H0 ST373207LC C70D PQ: 0 ANSI: 4 scsi 2:0:8:0: Direct-Access IBM H0 ST373207LC C70D PQ: 0 ANSI: 4 It took me a while to figure out why this machine observes performance characteristics noone else sees. Honza -- Jan Kara SUSE Labs, CR