From mboxrd@z Thu Jan 1 00:00:00 1970 From: Ronald Moesbergen Subject: Re: [RESEND] [PATCH] readahead:add blk_run_backing_dev Date: Mon, 3 Aug 2009 13:44:28 +0200 Message-ID: References: <4A3CD62B.1020407@vlnb.net> <4A641AAC.9030300@vlnb.net> <4A6DA77B.7080600@vlnb.net> <4A6F4C81.10600@vlnb.net> <4A7338AF.8010407@vlnb.net> <4A76ABD5.9020808@vlnb.net> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: QUOTED-PRINTABLE Cc: fengguang.wu@intel.com, linux-kernel@vger.kernel.org, akpm@linux-foundation.org, kosaki.motohiro@jp.fujitsu.com, Alan.Brunelle@hp.com, linux-fsdevel@vger.kernel.org, jens.axboe@oracle.com, randy.dunlap@oracle.com, Bart Van Assche To: Vladislav Bolkhovitin Return-path: Received: from fg-out-1718.google.com ([72.14.220.159]:26709 "EHLO fg-out-1718.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752937AbZHCLo2 convert rfc822-to-8bit (ORCPT ); Mon, 3 Aug 2009 07:44:28 -0400 In-Reply-To: <4A76ABD5.9020808@vlnb.net> Sender: linux-fsdevel-owner@vger.kernel.org List-ID: 2009/8/3 Vladislav Bolkhovitin : > Ronald Moesbergen, on 08/03/2009 01:15 PM wrote: >> >> 2009/7/31 Vladislav Bolkhovitin : >>> >>> OK, as I expected, on the SCST level everything is clear and the fo= rced >>> ordering change didn't change anything. >>> >>> But still, a single read stream must be the fastest from single thr= ead. >>> Otherwise, there's something wrong somewhere in the I/O path: block >>> layer, >>> RA, I/O scheduler. And, apparently, this is what we have and should= find >>> out >>> the cause. >>> >>> Can you check if noop on the target and/or initiator makes any >>> difference? >>> Case 5 with 1 and 2 threads will be sufficient. >> >> That doesn't seem to help: >> >> client kernel: 2.6.26-15lenny3 (debian) >> server kernel: 2.6.29.5 with readahead-context, blk_run_backing_dev >> and io_context, forced_order >> >> With one IO thread: >> 5) client: default, server: default (server noop, client noop) >> blocksize =A0 =A0 =A0 R =A0 =A0 =A0 =A0R =A0 =A0 =A0 =A0R =A0 R(avg,= =A0 =A0R(std =A0 =A0 =A0 =A0R >> =A0(bytes) =A0 =A0 (s) =A0 =A0 =A0(s) =A0 =A0 =A0(s) =A0 =A0MB/s) =A0= ,MB/s) =A0 (IOPS) >> =A067108864 =A017.612 =A0 21.113 =A0 21.355 =A0 51.532 =A0 =A04.680 = =A0 =A00.805 >> =A033554432 =A018.329 =A0 18.523 =A0 19.049 =A0 54.969 =A0 =A00.891 = =A0 =A01.718 >> =A016777216 =A018.497 =A0 18.219 =A0 17.042 =A0 57.217 =A0 =A02.059 = =A0 =A03.576 >> >> With two threads: >> 5) client: default, server: default (server noop, client noop) >> blocksize =A0 =A0 =A0 R =A0 =A0 =A0 =A0R =A0 =A0 =A0 =A0R =A0 R(avg,= =A0 =A0R(std =A0 =A0 =A0 =A0R >> =A0(bytes) =A0 =A0 (s) =A0 =A0 =A0(s) =A0 =A0 =A0(s) =A0 =A0MB/s) =A0= ,MB/s) =A0 (IOPS) >> =A067108864 =A017.436 =A0 18.376 =A0 20.493 =A0 54.807 =A0 =A03.634 = =A0 =A00.856 >> =A033554432 =A017.466 =A0 16.980 =A0 18.261 =A0 58.337 =A0 =A01.740 = =A0 =A01.823 >> =A016777216 =A018.222 =A0 17.567 =A0 18.077 =A0 57.045 =A0 =A00.901 = =A0 =A03.565 > > And with client cfq, server noop? client kernel: 2.6.26-15lenny3 (debian) server kernel: 2.6.29.5 with readahead-context, blk_run_backing_dev and io_context, forced_order With one IO thread: 5) client: default, server: default (server noop, client cfq) blocksize R R R R(avg, R(std R (bytes) (s) (s) (s) MB/s) ,MB/s) (IOPS) 67108864 16.019 16.434 15.730 63.777 1.144 0.997 33554432 16.020 16.624 15.936 63.258 1.183 1.977 16777216 15.966 15.465 16.115 64.630 1.145 4.039 With two threads: 5) client: default, server: default (server noop, client cfq) blocksize R R R R(avg, R(std R (bytes) (s) (s) (s) MB/s) ,MB/s) (IOPS) 67108864 16.504 15.762 14.842 65.335 2.848 1.021 33554432 16.080 16.627 15.766 63.406 1.386 1.981 16777216 15.489 16.627 16.043 63.842 1.846 3.990 Ronald. -- To unsubscribe from this list: send the line "unsubscribe linux-fsdevel= " in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html