From mboxrd@z Thu Jan 1 00:00:00 1970 From: Derek Taubert Subject: Re: Bad write performance with libata-tj-stable-2.6.17.4-20060710, pcmcia based sata_sil24, PMP, and NCQ drive Date: Fri, 1 Sep 2006 22:34:59 -0700 Message-ID: <20060902053459.GA4467@geeks.org> References: <20060828230132.GB20189@geeks.org> <44F3A8FD.6090108@gmail.com> <20060829045816.GA21746@geeks.org> <44F440BE.80000@gmail.com> <20060829164424.GA1603@geeks.org> <44F8365C.2020609@gmail.com> <20060901172435.GA26975@geeks.org> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Return-path: Received: from jacobs.geeks.org ([204.153.247.1]:62188 "EHLO mail.geeks.org") by vger.kernel.org with ESMTP id S1750711AbWIBFfC (ORCPT ); Sat, 2 Sep 2006 01:35:02 -0400 Content-Disposition: inline In-Reply-To: <20060901172435.GA26975@geeks.org> Sender: linux-ide-owner@vger.kernel.org List-Id: linux-ide@vger.kernel.org To: Tejun Heo Cc: Derek Taubert , linux-ide@vger.kernel.org On Fri, Sep 01, 2006 at 10:24:35AM -0700, Derek Taubert wrote: > I'm going to try narrowing the scope of the test next. Will purchase > an eSATA<->SATA cable today and try bypassing the port multiplier. > > If that works, I'll try using one drive at a time on the PMP. Well, that didn't change the performance one bit: ata2: hard resetting port ata2: SATA link up 1.5 Gbps (SStatus 113 SControl 300) ata2.00: ATA-7, max UDMA/133, 1465149168 sectors: LBA48 NCQ (depth 31/32) ata2.00: configured for UDMA/100 ata2: EH complete Vendor: ATA Model: ST3750640AS Rev: 3.AA Type: Direct-Access ANSI SCSI revision: 05 SCSI device sda: 1465149168 512-byte hdwr sectors (750156 MB) sda: Write Protect is off sda: Mode Sense: 00 3a 00 00 SCSI device sda: drive cache: write back SCSI device sda: 1465149168 512-byte hdwr sectors (750156 MB) sda: Write Protect is off sda: Mode Sense: 00 3a 00 00 SCSI device sda: drive cache: write back sda: sda1 sd 1:0:0:0: Attached scsi disk sda sd 1:0:0:0: Attached scsi generic sg0 type 0 root@linux-srv:~ # dd if=/dev/zero of=/dev/sda1 bs=1M count=100 100+0 records in 100+0 records out 104857600 bytes (105 MB) copied, 54.1042 seconds, 1.9 MB/s root@linux-srv:~ # dd of=/dev/zero if=/dev/sda1 bs=1M count=1000 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 20.079 seconds, 52.2 MB/s I'm now suspecting that the performance problems are due to bus issues on the PCMCIA/PCI side. Will poke around there and maybe try this with a different laptop... Thanks, Derek -- VGER BF report: H 5.11438e-07