From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S933168Ab2LGLSy (ORCPT ); Fri, 7 Dec 2012 06:18:54 -0500 Received: from mga03.intel.com ([143.182.124.21]:20067 "EHLO mga03.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932136Ab2LGLSx (ORCPT ); Fri, 7 Dec 2012 06:18:53 -0500 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="4.84,236,1355126400"; d="asc'?scan'208";a="227956807" Date: Fri, 7 Dec 2012 13:20:14 +0200 From: "Kirill A. Shutemov" To: Paolo Bonzini , Stephen Cameron Cc: "James E.J. Bottomley" , Matthew Wilcox , Tim Chen , linux-scsi@vger.kernel.org, linux-kernel@vger.kernel.org Subject: Re: [PATCH] scsi_ram: a RAM-based SCSI driver Message-ID: <20121207112014.GA4466@otc-wbsnb-06> References: <1354725918-14713-1-git-send-email-kirill.shutemov@linux.intel.com> <50C06EC3.20002@redhat.com> MIME-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="pf9I7BMVVzbSWLtt" Content-Disposition: inline In-Reply-To: <50C06EC3.20002@redhat.com> 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 --pf9I7BMVVzbSWLtt Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On Thu, Dec 06, 2012 at 11:09:07AM +0100, Paolo Bonzini wrote: > Il 05/12/2012 17:45, Kirill A. Shutemov ha scritto: > > From: "Kirill A. Shutemov" > >=20 > > This driver is intended to run as fast as possible, hence the options to > > discard writes and reads. It's designed to let us find latency issues > > elsewhere in the storage stack (eg filesystem, block layer, scsi layer). > >=20 > > There are a few different options, controlled through module parameters. > > The sector size and disc capacity are load-time parameters, but the > > parameters affecting performance are tweakable at runtime. > >=20 > > By default, it'll allocate half a gigabyte of RAM to use as a ramdisc; > > you can change this with the `capacity' module parameter. >=20 > Is this that much faster than scsi-debug? The discarding options surely > can be added there. scsi_ram is about 9% faster (without fake_rw/throw_away_*) on my machine: fio job file (slightly modified ssd-test): [global] bs=3D4k ioengine=3Dlibaio iodepth=3D4 size=3D10g direct=3D1 runtime=3D60 filename=3D/dev/sdb [seq-read] rw=3Dread stonewall [rand-read] rw=3Drandread stonewall [seq-write] rw=3Dwrite stonewall [rand-write] rw=3Drandwrite stonewall ---------------------- scsi_ram capacity=3D41943040: Run status group 0 (all jobs): READ: io=3D6975.2MB, aggrb=3D119040KB/s, minb=3D119040KB/s, maxb=3D11904= 0KB/s, mint=3D60001msec, maxt=3D60001msec Run status group 1 (all jobs): READ: io=3D7006.8MB, aggrb=3D119579KB/s, minb=3D119579KB/s, maxb=3D11957= 9KB/s, mint=3D60001msec, maxt=3D60001msec Run status group 2 (all jobs): WRITE: io=3D7009.9MB, aggrb=3D119632KB/s, minb=3D119632KB/s, maxb=3D11963= 2KB/s, mint=3D60001msec, maxt=3D60001msec Run status group 3 (all jobs): WRITE: io=3D6919.8MB, aggrb=3D118094KB/s, minb=3D118094KB/s, maxb=3D11809= 4KB/s, mint=3D60001msec, maxt=3D60001msec Disk stats (read/write): sdb: ios=3D3579612/3559798, merge=3D0/0, ticks=3D128180/125565, in_queue= =3D240098, util=3D77.79% ---------------------- scsi_debug dev_size_mb=3D10240 delay=3D0: Run status group 0 (all jobs): READ: io=3D6393.2MB, aggrb=3D109110KB/s, minb=3D109110KB/s, maxb=3D10911= 0KB/s, mint=3D60000msec, maxt=3D60000msec Run status group 1 (all jobs): READ: io=3D6327.6MB, aggrb=3D107988KB/s, minb=3D107988KB/s, maxb=3D10798= 8KB/s, mint=3D60001msec, maxt=3D60001msec Run status group 2 (all jobs): WRITE: io=3D6473.3MB, aggrb=3D110474KB/s, minb=3D110474KB/s, maxb=3D11047= 4KB/s, mint=3D60001msec, maxt=3D60001msec Run status group 3 (all jobs): WRITE: io=3D6330.5MB, aggrb=3D108037KB/s, minb=3D108037KB/s, maxb=3D10803= 7KB/s, mint=3D60001msec, maxt=3D60001msec Disk stats (read/write): sdb: ios=3D3256653/3272376, merge=3D0/0, ticks=3D54502/54150, in_queue=3D= 101165, util=3D42.09% --=20 Kirill A. Shutemov --pf9I7BMVVzbSWLtt Content-Type: application/pgp-signature; name="signature.asc" Content-Description: Digital signature -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.12 (GNU/Linux) iQIcBAEBAgAGBQJQwdDuAAoJEAd+omnVudOMmsUP/0QkaIWSavjw48K6qyvmcXsa tzzI1sz4iqesYFwfemE49CcEQOYPU7RZJj+Vt4MMEbe5YPY5CUYnxb1JFtDUL0Qm hO+5EVcuMvM96ljXkIw1Zt0tk2M9IDi81OQweByP5R8YFeubgZP3tNWPr8dCtC4B GMiQJD7WTSwoc4Gj6DnMX84sbjWChnrJJliqjH/YM6be97T34rwEFY44AzVYCF64 4r4tU1oHeUV290R1D3MLONiPHvQQa+4DHZfcJQsK7PXhFuEEBktXbHWj34lJrjo8 Y2N/unV+ZiiFsAB76JKxvpnOR2QGD8JEl37fg5fPxha96uSv9DlUBaF4oDQVgqCQ CefJJI4yjG236UsbEOdlAl/oyeNe5hvHJCbpvn6cKtz0EQnSD5ZqrRunSAtT1DhT DPWmuKIKuVA/XigdkbijICWsBAsKQbnTWQ1/il+EuVfwtilOTXsS+dQYKzGM7fVh EqvoY1iOL3qq0dRPRaF05kiEYnd32e8D5tiRBc1C2YN2kx5hie0hd7OZWw6Lgb2M qO20lntKXICQuHEGjdNoL6c4lIbHWNxnWLL44VBD+iMzU64UI6sEGFBQRrGQd9Gs QDZ2UazZeAvnqUh58myrQxwZ3I42o61oQYx6YJx2wi2pajTT/3ftj1PL3s1GOMp6 yzpPoB3SDk/raXZFY3yM =RR8t -----END PGP SIGNATURE----- --pf9I7BMVVzbSWLtt--