Date: Sun, 16 Apr 2006 13:04:20 +0200 From: =?ISO-8859-1?Q?S=F8ren?= Schmidt <sos@DeepCore.dk> To: Mikhail Teterin <mi+kde@aldan.algebra.com> Cc: current@FreeBSD.ORG, Derek Ragona <derek@computinginnovations.com> Subject: Re: pitiful performance of an SATA150 drive Message-ID: <1145185460.912.17.camel@sos.deepcore.dk> In-Reply-To: <200604152153.42411@aldan> References: <200603010505.k2155HfQ003205@aldan.algebra.com> <200603021317.26532.mi%2Bmx@aldan.algebra.com> <4407422C.4020800@deepcore.dk> <200604152153.42411@aldan>
next in thread | previous in thread | raw e-mail | index | archive | help
On Lør, 2006-04-15 at 21:53 -0400, Mikhail Teterin wrote: > On Thursday 02 March 2006 14:06, Søren Schmidt wrote: > = > I noticed a big MFC to dev/ata today and rebuilt the kernel. > = > Unfortunately, the drive's write-performance did not change. Just FYI... > = > = You are sure you dont have hw.ata.wc turned of ? > = Other than that I seriously doubt its a fault in ATA... > > This is still a problem with today's 6.1-RC1. hw.ata.wc is `1'. > What can I do to help you resolve this, Søren? Thanks! I just tried this on a system as close to the one you have as possible here in the lab with this result: atapci3: <SiI 3114 SATA150 controller> port 0xa800-0xa807,0xa400-0xa403,0xa000-0xa007,0x9c00-0x9c03,0x9800-0x980f mem 0xfdfff000-0xfdfff3ff irq 16 at device 13.0 on pci1 ata6: <ATA channel 0> on atapci3 ata7: <ATA channel 1> on atapci3 ata8: <ATA channel 2> on atapci3 ata9: <ATA channel 3> on atapci3 ... ad1: 78533MB <HDS728080PLA380 PF2OA60A> at ata8-master SATA150 devel# dd if=/dev/ad1 of=/dev/null bs=1m count=200 200+0 records in 200+0 records out 209715200 bytes transferred in 3.470972 secs (60419732 bytes/sec) devel# dd if=/dev/zero of=/dev/ad1 bs=1m count=200 200+0 records in 200+0 records out 209715200 bytes transferred in 3.513703 secs (59684956 bytes/sec) That makes me *seriously* doubt that ATA is at fault here... -Søren
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?1145185460.912.17.camel>