Date: Wed, 14 Sep 2005 16:23:17 -0400 From: Kris Kennaway <kris@obsecurity.org> To: Oliver Lehmann <lehmann@ans-netz.de> Cc: current@freebsd.org Subject: Re: low(er) disk performance with sched_4bsd then with sched_ule Message-ID: <20050914202317.GA96154@xor.obsecurity.org> In-Reply-To: <20050914222013.178dc4dc.lehmann@ans-netz.de> References: <20050914194612.15692485.lehmann@ans-netz.de> <43286E37.40203@samsco.org> <20050914222013.178dc4dc.lehmann@ans-netz.de>
next in thread | previous in thread | raw e-mail | index | archive | help
--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+--
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20050914202317.GA96154>