Date: Fri, 27 Feb 2009 15:56:36 +0100 From: Julien Cigar <jcigar@ulb.ac.be> To: Wojciech Puchar <wojtek@wojtek.tensor.gdynia.pl> Cc: freebsd-questions@freebsd.org Subject: Re: poor performances with Intel Raid Controller (iir) Message-ID: <1235746596.2747.30.camel@frodon.be-bif.ulb.ac.be> In-Reply-To: <alpine.BSF.2.00.0902271537070.20505@wojtek.tensor.gdynia.pl> References: <1235740489.2747.17.camel@frodon.be-bif.ulb.ac.be> <alpine.BSF.2.00.0902271537070.20505@wojtek.tensor.gdynia.pl>
next in thread | previous in thread | raw e-mail | index | archive | help
On Fri, 2009-02-27 at 15:37 +0100, Wojciech Puchar wrote: > > > > I've a machine with an integrated Intel RAID controller (U320) which > > uses the iir driver. I have two arrays, one RAID 1 with two disks and > > one RAID 5 with 8 disks. The disks are all Seagate 320MB/s. The system > > is running FreeBSD 7.0-RELEASE with 8 processors (2,40 Ghz) and 4GB or > > RAM. > > > > I have very poor performances, around ~50 MB/s, is it normal ? > > > > jcigar@bccm-it ~ % dd if=/dev/zero of=blah bs=10M count=100 > > 100+0 records in > > 100+0 records out > > 1048576000 bytes transferred in 20.168689 secs (51990290 bytes/sec) > > > > Are there any tool to detect what could be the bottleneck(s) ? > > are you sure it isn't NORMAL performance of this card. > Not sure, I admit that the card is quite old (4 years), but 50 MB/s seems really slow to me (especially for U320 SCSI) .. > i think it is, the "hardware" RAID solutions are usually much slower than > software, even more with RAID5. I tend to use software RAID too (at least on system with multiple processors)... when I have choice. -- Julien Cigar Belgian Biodiversity Platform http://www.biodiversity.be Université Libre de Bruxelles (ULB) Campus de la Plaine CP 257 Bâtiment NO, Bureau 4 N4 115C (Niveau 4) Boulevard du Triomphe, entrée ULB 2 B-1050 Bruxelles Mail: jcigar@ulb.ac.be @biobel: http://biobel.biodiversity.be/person/show/471 Tel : 02 650 57 52
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?1235746596.2747.30.camel>