From owner-freebsd-current@FreeBSD.ORG Wed Sep 14 21:08:11 2005 Return-Path: X-Original-To: current@freebsd.org Delivered-To: freebsd-current@FreeBSD.ORG Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 48FE216A41F for ; Wed, 14 Sep 2005 21:08:11 +0000 (GMT) (envelope-from kris@obsecurity.org) Received: from fileserver.fields.utoronto.ca (fileserver.fields.utoronto.ca [128.100.216.10]) by mx1.FreeBSD.org (Postfix) with ESMTP id C93E843D46 for ; Wed, 14 Sep 2005 21:08:10 +0000 (GMT) (envelope-from kris@obsecurity.org) Received: from fields.fields.utoronto.ca (fields.localdomain [192.168.216.11]) by fileserver.fields.utoronto.ca (8.12.8/8.12.8/Fields 6.0) with ESMTP id j8EL880r017361 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=NO); Wed, 14 Sep 2005 17:08:08 -0400 Received: from obsecurity.dyndns.org (localhost.localdomain [127.0.0.1]) by fields.fields.utoronto.ca (8.12.8/8.12.8/Fields WS 6.0) with ESMTP id j8EL856P009594; Wed, 14 Sep 2005 17:08:05 -0400 Received: by obsecurity.dyndns.org (Postfix, from userid 1000) id 09B8D51237; Wed, 14 Sep 2005 16:23:18 -0400 (EDT) Date: Wed, 14 Sep 2005 16:23:17 -0400 From: Kris Kennaway To: Oliver Lehmann Message-ID: <20050914202317.GA96154@xor.obsecurity.org> References: <20050914194612.15692485.lehmann@ans-netz.de> <43286E37.40203@samsco.org> <20050914222013.178dc4dc.lehmann@ans-netz.de> Mime-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="8t9RHnE3ZwKMSgU+" Content-Disposition: inline In-Reply-To: <20050914222013.178dc4dc.lehmann@ans-netz.de> User-Agent: Mutt/1.4.2.1i Cc: current@freebsd.org Subject: Re: low(er) disk performance with sched_4bsd then with sched_ule X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 14 Sep 2005 21:08:11 -0000 --8t9RHnE3ZwKMSgU+ Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On Wed, Sep 14, 2005 at 10:20:13PM +0200, Oliver Lehmann wrote: > Scott Long wrote: >=20 > > Oliver Lehmann wrote: > >=20 > > > Any idea where the 30MB/sec drawback comes from and if I missed sth.? > > > I mean why there are 30MB/s more or less is worth to think about imho. > > >=20 > >=20 > > Indeed. This definitely warrants much more testing and investigation.= =20 > > My best guess is that ULE is allowing the uio copies of the data between > > kernel and userland to complete with fewer interruptions. It could also > > be better about keeping the threads from ping-ponging between CPUs. Can > > you retest with different block sizes, ranging from 4k to 1m? >=20 > http://pofo.de/tmp/dd_ULE.txt > http://pofo.de/tmp/dd_4BSD.txt >=20 > btw. the RAID strip size is 64k Using schedgraph should be helpful to investigate why the two schedulers differ so much. Kris --8t9RHnE3ZwKMSgU+ Content-Type: application/pgp-signature Content-Disposition: inline -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.2 (FreeBSD) iD8DBQFDKIa1Wry0BWjoQKURAi0RAJsEUc7pGEPWegPxyf09+pbbmDgoVACePNd9 1Pqf9FDV286BofRlwDQNzLg= =2FwR -----END PGP SIGNATURE----- --8t9RHnE3ZwKMSgU+--