From owner-freebsd-current@FreeBSD.ORG Sun Jul 5 00:33:17 2009 Return-Path: Delivered-To: freebsd-current@FreeBSD.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id ED5231065670; Sun, 5 Jul 2009 00:33:16 +0000 (UTC) (envelope-from mike@sentex.net) Received: from lava.sentex.ca (pyroxene.sentex.ca [199.212.134.18]) by mx1.freebsd.org (Postfix) with ESMTP id C1BEC8FC13; Sun, 5 Jul 2009 00:33:16 +0000 (UTC) (envelope-from mike@sentex.net) Received: from mdt-xp.sentex.net (simeon.sentex.ca [192.168.43.27]) by lava.sentex.ca (8.14.3/8.14.3) with ESMTP id n650UkEu028408; Sat, 4 Jul 2009 20:30:46 -0400 (EDT) (envelope-from mike@sentex.net) Message-Id: <200907050030.n650UkEu028408@lava.sentex.ca> X-Mailer: QUALCOMM Windows Eudora Version 7.1.0.9 Date: Sat, 04 Jul 2009 20:33:06 -0400 To: Alexander Motin From: Mike Tancsa In-Reply-To: <7.1.0.9.0.20090703165005.196d3ba0@sentex.net> References: <4A4517BE.9040504@FreeBSD.org> <200906272303.n5RN3rTi070177@lava.sentex.ca> <4A471F44.7010108@FreeBSD.org> <200907021859.n62IxghN009931@lava.sentex.ca> <4A4D0B7E.8060503@FreeBSD.org> <200907022117.n62LHrvZ010791@lava.sentex.ca> <200907031326.n63DQCGM016627@lava.sentex.ca> <4A4E0D51.3080904@FreeBSD.org> <200907031413.n63ED2jl016885@lava.sentex.ca> <4A4E1525.2040809@FreeBSD.org> <200907031430.n63EUMH1016965@lava.sentex.ca> <4A4E1A6C.3090605@FreeBSD.org> <200907031858.n63IwDIt018455@lava.sentex.ca> <4A4E5C82.9070209@FreeBSD.org> <7.1.0.9.0.20090703165005.196d3ba0@sentex.net> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii"; format=flowed Cc: FreeBSD-Current , scottl@FreeBSD.org Subject: Re: RFC: ATA to CAM integration patch (INTEL DX58SO) 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: Sun, 05 Jul 2009 00:33:17 -0000 At 05:30 PM 7/3/2009, Mike Tancsa wrote: >At 03:31 PM 7/3/2009, Alexander Motin wrote: >>It would be more interesting to investigate benefits on NCQ >>suitable workload, as that are new for us. Something like unpacking >>a lot of small files to normal or async-mounted or gjournalled FS, >>or some multi-threaded read, or something else. Would be nice to >>understand on which types of workload NCQ could give us visible effects. >> >>You can track real requests parallelism by looking on dev_active >>field of `camcontrol tags ada0 -v`. > > >We dont have too many disk I/O bound apps here. Where we do, we >typically have used raid controllers in RAID10. But I will >experiment a little more over the weekend. For us, we are >interested in large amounts of storage for backup purposes. Having >things like port multiplier features are very nice to have. But I >will try some random io tests to see if I can measure a difference. I hooked up a Vantec eSata enclosure using a SATA to eSATA cable off the main motherboard. One small difference I noticed is that camcontrol does not get the info from the drive like it does on other devices. Perhaps thats the enclosure messing things up ? 0(ich10)# camcontrol identify ada2 pass2: < > ATA/ATAPI-0 device Protocol ATA/ATAPI revision 0 device model serial number firmware revision cylinders 0 heads 0 sectors/track 0 lba not supported lba48 not supported dma not supported overlap not supported Feature Support Enable Value Vendor write cache no no read ahead no no Tagged Command Queuing (TCQ) no no 0/0x00 SMART no no microcode download no no security no no power management no no advanced power management no no 0/0x00 automatic acoustic management no no 0/0x00 0/0x00 0(ich10)# 0(ich10)# camcontrol identify ada1 pass1: ATA/ATAPI-7 SATA 2.x device Protocol SATA revision 2.x device model ST380811AS serial number 6PS03G9Z firmware revision 3.AAE cylinders 16383 heads 16 sectors/track 63 lba supported 156301488 sectors lba48 supported 156301488 sectors dma supported overlap not supported Feature Support Enable Value Vendor write cache yes yes read ahead yes yes Native Command Queuing (NCQ) yes - 31/0x1F Tagged Command Queuing (TCQ) no no 31/0x1F SMART yes yes microcode download yes yes security yes no power management yes yes advanced power management no no 65278/0xFEFE automatic acoustic management no no 0/0x00 208/0xD0 0(ich10)# camcontrol identify ada0 pass0: ATA/ATAPI-8 SATA 2.x device Protocol SATA revision 2.x device model ST3500410AS serial number 5VM0X6FG firmware revision CC34 cylinders 16383 heads 16 sectors/track 63 lba supported 268435455 sectors lba48 supported 976773168 sectors dma supported overlap not supported Feature Support Enable Value Vendor write cache yes yes read ahead yes yes Native Command Queuing (NCQ) yes - 31/0x1F Tagged Command Queuing (TCQ) no no 31/0x1F SMART yes yes microcode download yes yes security yes no power management yes yes advanced power management no no 0/0x00 automatic acoustic management yes yes 0/0x00 254/0xFE 0(ich10)# There was a previous drive connected. We powered off the external drive, disconnected the cable, hooked up the new drive, powered up the enclosure and then I did a camcontrol rescan all Jul 4 20:19:22 ich10 kernel: (ada2:ahcich2:0:0:0): lost device Jul 4 20:19:22 ich10 kernel: (ada2:ahcich2:0:0:0): removing device entry Jul 4 20:19:37 ich10 kernel: (probe0:ahcich2:0:0:0): SIGNATURE: 0000 Jul 4 20:19:37 ich10 kernel: ada2 at ahcich2 bus 0 target 0 lun 0 Jul 4 20:19:37 ich10 kernel: ada2: ATA/ATAPI-8 SATA 1.x device Jul 4 20:19:37 ich10 kernel: ada2: 150.000MB/s transfers Jul 4 20:19:37 ich10 kernel: ada2: 715404MB (1465149168 512 byte sectors: 16H 63S/T 16383C) Jul 4 20:19:37 ich10 kernel: ada2: Native Command Queueing Enabled The drive we connected has some bad sectors, so I wanted to try a secure wipe as much as possible before RMAing the drive. I also thought it would be useful to test with the new driver how it handles bad disks Is this such an error ? Jul 4 20:25:57 ich10 kernel: ahcich2: ahci_ch_intr ERROR is 40000001 cs 00000004 ss 00000000 rs 00000004 tfd 451 serr 00000000 ---Mike