libata and md issues with 2.9.1-rc1

libata and md issues with 2.9.1-rc1

[Brad Campbell]

Just a heads up. I'm experiencing "issues" with 2.6.9-rc1 that don't occur with 2.6.5.

I run a 10 disk raid-5 on 3xPromise SATA150 cards and a 2 disk raid-0 on the on-board VIA chipset.
The 10 disks are Maxtor Maxline-II SATA drives and the raid-0 is a pair of WD2000JB drives with
Addonics SATA->PATA converters.

I am not seeing any issues with the Promise/Maxtor combo at this stage, but I'm getting random
read/write errors with the VIA/WD combo that don't appear under 2.6.5 or DOS (I also use Spinrite to
check the disks when I get issues).

This only appears when the 2 drives are run in the raid-0.

Under 2.6.5 I ran a complete badlocks -n on both drives simultaneously, and repeated the same under 
2.6.9-rc1 with no problems (7 hours for a complete run). I even ran 5 simultaneous badblocks runs on 
host 1, 6, 9, 12 & 13 for about 30 minutes with no problems (except PCI bus saturation!)

After starting the raid I ran a complete badblocks -n on /dev/md1 under 2.6.5 with no problems. 
Under 2.6.9-rc1 I get timeouts immediately I start badblocks -n (the -n is the key as I have to 
write something to cause the problem)

Aug 24 18:55:03 srv kernel: raid0: looking at sdk1
Aug 24 18:55:03 srv kernel: raid0:   comparing sdk1(195310080) with sdk1(195310080)
Aug 24 18:55:03 srv kernel: raid0:   END
Aug 24 18:55:03 srv kernel: raid0:   ==> UNIQUE
Aug 24 18:55:03 srv kernel: raid0: 1 zones
Aug 24 18:55:03 srv kernel: raid0: looking at sdl1
Aug 24 18:55:03 srv kernel: raid0:   comparing sdl1(195358336) with sdk1(195310080)
Aug 24 18:55:03 srv kernel: raid0:   NOT EQUAL
Aug 24 18:55:03 srv kernel: raid0:   comparing sdl1(195358336) with sdl1(195358336)
Aug 24 18:55:03 srv kernel: raid0:   END
Aug 24 18:55:03 srv kernel: raid0:   ==> UNIQUE
Aug 24 18:55:03 srv kernel: raid0: 2 zones
Aug 24 18:55:03 srv kernel: raid0: FINAL 2 zones
Aug 24 18:55:03 srv kernel: raid0: zone 1
Aug 24 18:55:03 srv kernel: raid0: checking sdk1 ... nope.
Aug 24 18:55:03 srv kernel: raid0: checking sdl1 ... contained as device 0
Aug 24 18:55:03 srv kernel:   (195358336) is smallest!.
Aug 24 18:55:03 srv kernel: raid0: zone->nb_dev: 1, size: 48256
Aug 24 18:55:03 srv kernel: raid0: current zone offset: 195358336
Aug 24 18:55:03 srv kernel: raid0: done.
Aug 24 18:55:03 srv kernel: raid0 : md_size is 390668416 blocks.
Aug 24 18:55:03 srv kernel: raid0 : conf->hash_spacing is 390620160 blocks.
Aug 24 18:55:03 srv kernel: raid0 : nb_zone is 2.
Aug 24 18:55:03 srv kernel: raid0 : Allocating 8 bytes for hash.
Aug 24 19:01:37 srv kernel: ata13: command 0x35 timeout, stat 0xd0 host_stat 0x0
Aug 24 19:01:37 srv kernel: ata13: status=0xd0 { Busy }
Aug 24 19:01:37 srv kernel: SCSI error : <12 0 0 0> return code = 0x8000002
Aug 24 19:01:37 srv kernel: FMK EOM ILI Current sdk: sense = 70 ef
Aug 24 19:01:37 srv kernel: ASC=28 ASCQ=c0
Aug 24 19:01:37 srv kernel: end_request: I/O error, dev sdk, sector 63
Aug 24 19:01:37 srv kernel: ATA: abnormal status 0xD0 on port 0x8807
Aug 24 19:01:37 srv last message repeated 2 times
Aug 24 19:02:07 srv kernel: ata13: command 0x35 timeout, stat 0xd0 host_stat 0x1
Aug 24 19:02:07 srv kernel: ata13: status=0xd0 { Busy }
Aug 24 19:02:07 srv kernel: SCSI error : <12 0 0 0> return code = 0x8000002
Aug 24 19:02:07 srv kernel: FMK EOM ILI Current sdk: sense = 70 ef
Aug 24 19:02:07 srv kernel: ASC=28 ASCQ=c0
Aug 24 19:02:07 srv kernel: end_request: I/O error, dev sdk, sector 71
Aug 24 19:02:07 srv kernel: ATA: abnormal status 0xD0 on port 0x8807
Aug 24 19:02:07 srv last message repeated 2 times

I'm not really even sure where to start here as it only occurs when the 2 drives are in a Raid-0 and 
  depending on what is going on with the system it can take a while to manifest. (Never more than a 
hundred megs or so of data though)

Relevant boot log from 2.6.9-rc1 attached

Regards,
Brad (Certified libata torturer)

Aug 24 19:03:55 srv kernel: Uniform Multi-Platform E-IDE driver Revision: 7.00alpha2
Aug 24 19:03:55 srv kernel: ide: Assuming 33MHz system bus speed for PIO modes; override with idebus=xx
Aug 24 19:03:55 srv kernel: VP_IDE: IDE controller at PCI slot 0000:00:0f.1
Aug 24 19:03:55 srv kernel: VP_IDE: chipset revision 6
Aug 24 19:03:55 srv kernel: VP_IDE: not 100%% native mode: will probe irqs later
Aug 24 19:03:55 srv kernel: VP_IDE: VIA vt8237 (rev 00) IDE UDMA133 controller on pci0000:00:0f.1
Aug 24 19:03:55 srv kernel:     ide0: BM-DMA at 0x6800-0x6807, BIOS settings: hda:DMA, hdb:pio
Aug 24 19:03:55 srv kernel:     ide1: BM-DMA at 0x6808-0x680f, BIOS settings: hdc:pio, hdd:pio
Aug 24 19:03:55 srv kernel: hda: WDC WD400EB-00CPF0, ATA DISK drive
Aug 24 19:03:55 srv kernel: Using anticipatory io scheduler
Aug 24 19:03:55 srv kernel: ide0 at 0x1f0-0x1f7,0x3f6 on irq 14
Aug 24 19:03:55 srv kernel: hda: max request size: 128KiB
Aug 24 19:03:55 srv kernel: hda: Host Protected Area detected.
Aug 24 19:03:55 srv kernel: ^Icurrent capacity is 78159151 sectors (40017 MB)
Aug 24 19:03:55 srv kernel: ^Inative  capacity is 78165360 sectors (40020 MB)
Aug 24 19:03:55 srv kernel: hda: 78159151 sectors (40017 MB) w/2048KiB Cache, CHS=65535/16/63, UDMA(100)
Aug 24 19:03:55 srv kernel:  /dev/ide/host0/bus0/target0/lun0: p1 p2 p3
Aug 24 19:03:55 srv kernel: libata version 1.02 loaded.
Aug 24 19:03:55 srv kernel: sata_promise version 0.91
Aug 24 19:03:55 srv kernel: ata1: SATA max UDMA/133 cmd 0xE080B200 ctl 0xE080B238 bmdma 0x0 irq 19
Aug 24 19:03:55 srv kernel: ata2: SATA max UDMA/133 cmd 0xE080B280 ctl 0xE080B2B8 bmdma 0x0 irq 19
Aug 24 19:03:55 srv kernel: ata3: SATA max UDMA/133 cmd 0xE080B300 ctl 0xE080B338 bmdma 0x0 irq 19
Aug 24 19:03:55 srv kernel: ata4: SATA max UDMA/133 cmd 0xE080B380 ctl 0xE080B3B8 bmdma 0x0 irq 19
Aug 24 19:03:55 srv kernel: ata1: dev 0 cfg 49:2f00 82:7c6b 83:7f09 84:4003 85:7c69 86:3e01 87:4003 
88:407f
Aug 24 19:03:55 srv kernel: ata1: dev 0 ATA, max UDMA/133, 490234752 sectors (lba48)
Aug 24 19:03:55 srv kernel: ata1: dev 0 configured for UDMA/133
Aug 24 19:03:55 srv kernel: scsi0 : sata_promise
Aug 24 19:03:55 srv kernel: ata2: dev 0 cfg 49:2f00 82:7c6b 83:7f09 84:4003 85:7c69 86:3e01 87:4003 
88:407f
Aug 24 19:03:55 srv kernel: ata2: dev 0 ATA, max UDMA/133, 490234752 sectors (lba48)
Aug 24 19:03:55 srv kernel: ata2: dev 0 configured for UDMA/133
Aug 24 19:03:55 srv kernel: scsi1 : sata_promise
Aug 24 19:03:55 srv kernel: ata3: dev 0 cfg 49:2f00 82:7c6b 83:7f09 84:4003 85:7c69 86:3e01 87:4003 
88:407f
Aug 24 19:03:55 srv kernel: ata3: dev 0 ATA, max UDMA/133, 490234752 sectors (lba48)
Aug 24 19:03:55 srv kernel: ata3: dev 0 configured for UDMA/133
Aug 24 19:03:55 srv kernel: scsi2 : sata_promise
Aug 24 19:03:55 srv kernel: ata4: dev 0 cfg 49:2f00 82:7c6b 83:7f09 84:4003 85:7c69 86:3e01 87:4003 
88:407f
Aug 24 19:03:55 srv kernel: ata4: dev 0 ATA, max UDMA/133, 490234752 sectors (lba48)
Aug 24 19:03:55 srv kernel: ata4: dev 0 configured for UDMA/133
Aug 24 19:03:55 srv kernel: scsi3 : sata_promise
Aug 24 19:03:55 srv kernel:   Vendor: ATA       Model: Maxtor 7Y250M0    Rev: 1.02
Aug 24 19:03:55 srv kernel:   Type:   Direct-Access                      ANSI SCSI revision: 05
Aug 24 19:03:55 srv kernel:   Vendor: ATA       Model: Maxtor 7Y250M0    Rev: 1.02
Aug 24 19:03:55 srv kernel:   Type:   Direct-Access                      ANSI SCSI revision: 05
Aug 24 19:03:55 srv kernel:   Vendor: ATA       Model: Maxtor 7Y250M0    Rev: 1.02
Aug 24 19:03:55 srv kernel:   Type:   Direct-Access                      ANSI SCSI revision: 05
Aug 24 19:03:55 srv kernel:   Vendor: ATA       Model: Maxtor 7Y250M0    Rev: 1.02
Aug 24 19:03:55 srv kernel:   Type:   Direct-Access                      ANSI SCSI revision: 05
Aug 24 19:03:55 srv kernel: ata5: SATA max UDMA/133 cmd 0xE080D200 ctl 0xE080D238 bmdma 0x0 irq 17
Aug 24 19:03:55 srv kernel: ata6: SATA max UDMA/133 cmd 0xE080D280 ctl 0xE080D2B8 bmdma 0x0 irq 17
Aug 24 19:03:55 srv kernel: ata7: SATA max UDMA/133 cmd 0xE080D300 ctl 0xE080D338 bmdma 0x0 irq 17
Aug 24 19:03:55 srv kernel: ata8: SATA max UDMA/133 cmd 0xE080D380 ctl 0xE080D3B8 bmdma 0x0 irq 17
Aug 24 19:03:55 srv kernel: ata5: dev 0 cfg 49:2f00 82:7c6b 83:7f09 84:4003 85:7c69 86:3e01 87:4003 
88:407fAug 24 19:03:55 srv kernel: ata5: dev 0 ATA, max UDMA/133, 490234752 sectors (lba48)
Aug 24 19:03:55 srv kernel: ata5: dev 0 configured for UDMA/133
Aug 24 19:03:55 srv kernel: scsi4 : sata_promise
Aug 24 19:03:55 srv kernel: ata6: dev 0 cfg 49:2f00 82:7c6b 83:7f09 84:4003 85:7c69 86:3e01 87:4003 
88:407f
Aug 24 19:03:55 srv kernel: ata6: dev 0 ATA, max UDMA/133, 490234752 sectors (lba48)
Aug 24 19:03:55 srv kernel: ata6: dev 0 configured for UDMA/133
Aug 24 19:03:55 srv kernel: scsi5 : sata_promise
Aug 24 19:03:55 srv kernel: ata7: dev 0 cfg 49:2f00 82:7c6b 83:7f09 84:4003 85:7c69 86:3e01 87:4003 
88:407f
Aug 24 19:03:55 srv kernel: ata7: dev 0 ATA, max UDMA/133, 490234752 sectors (lba48)
Aug 24 19:03:55 srv kernel: ata7: dev 0 configured for UDMA/133
Aug 24 19:03:55 srv kernel: scsi6 : sata_promise
Aug 24 19:03:55 srv kernel: ata8: dev 0 cfg 49:2f00 82:7c6b 83:7f09 84:4003 85:7c69 86:3e01 87:4003 
88:407f
Aug 24 19:03:55 srv kernel: ata8: dev 0 ATA, max UDMA/133, 490234752 sectors (lba48)
Aug 24 19:03:55 srv kernel: ata8: dev 0 configured for UDMA/133
Aug 24 19:03:55 srv kernel: scsi7 : sata_promise
Aug 24 19:03:55 srv kernel:   Vendor: ATA       Model: Maxtor 7Y250M0    Rev: 1.02
Aug 24 19:03:55 srv kernel:   Type:   Direct-Access                      ANSI SCSI revision: 05
Aug 24 19:03:55 srv kernel:   Vendor: ATA       Model: Maxtor 7Y250M0    Rev: 1.02
Aug 24 19:03:55 srv kernel:   Type:   Direct-Access                      ANSI SCSI revision: 05
Aug 24 19:03:55 srv kernel:   Vendor: ATA       Model: Maxtor 7Y250M0    Rev: 1.02
Aug 24 19:03:55 srv kernel:   Type:   Direct-Access                      ANSI SCSI revision: 05
Aug 24 19:03:55 srv kernel:   Vendor: ATA       Model: Maxtor 7Y250M0    Rev: 1.02
Aug 24 19:03:55 srv kernel:   Type:   Direct-Access                      ANSI SCSI revision: 05
Aug 24 19:03:55 srv kernel: ata9: SATA max UDMA/133 cmd 0xE080F200 ctl 0xE080F238 bmdma 0x0 irq 18
Aug 24 19:03:55 srv kernel: ata10: SATA max UDMA/133 cmd 0xE080F280 ctl 0xE080F2B8 bmdma 0x0 irq 18
Aug 24 19:03:55 srv kernel: ata11: SATA max UDMA/133 cmd 0xE080F300 ctl 0xE080F338 bmdma 0x0 irq 18
Aug 24 19:03:55 srv kernel: ata12: SATA max UDMA/133 cmd 0xE080F380 ctl 0xE080F3B8 bmdma 0x0 irq 18
Aug 24 19:03:55 srv kernel: ata9: dev 0 cfg 49:2f00 82:7c6b 83:7f09 84:4003 85:7c69 86:3e01 87:4003 
88:407f
Aug 24 19:03:55 srv kernel: ata9: dev 0 ATA, max UDMA/133, 490234752 sectors (lba48)
Aug 24 19:03:55 srv kernel: ata9: dev 0 configured for UDMA/133
Aug 24 19:03:55 srv kernel: scsi8 : sata_promise
Aug 24 19:03:55 srv kernel: ata10: dev 0 cfg 49:2f00 82:7c6b 83:7f09 84:4003 85:7c69 86:3e01 87:4003 
88:407f
Aug 24 19:03:55 srv kernel: ata10: dev 0 ATA, max UDMA/133, 490234752 sectors (lba48)
Aug 24 19:03:55 srv kernel: ata10: dev 0 configured for UDMA/133
Aug 24 19:03:55 srv kernel: scsi9 : sata_promise
Aug 24 19:03:55 srv kernel: ata11: no device found (phy stat 00000000)
Aug 24 19:03:55 srv kernel: ata11: thread exiting
Aug 24 19:03:55 srv kernel: scsi10 : sata_promise
Aug 24 19:03:55 srv kernel: ata12: no device found (phy stat 00000000)
Aug 24 19:03:55 srv kernel: ata12: thread exiting
Aug 24 19:03:55 srv kernel: scsi11 : sata_promise
Aug 24 19:03:55 srv kernel:   Vendor: ATA       Model: Maxtor 7Y250M0    Rev: 1.02
Aug 24 19:03:55 srv kernel:   Type:   Direct-Access                      ANSI SCSI revision: 05
Aug 24 19:03:55 srv kernel:   Vendor: ATA       Model: Maxtor 7Y250M0    Rev: 1.02
Aug 24 19:03:55 srv kernel:   Type:   Direct-Access                      ANSI SCSI revision: 05
Aug 24 19:03:55 srv kernel: sata_via version 0.20
Aug 24 19:03:55 srv kernel: sata_via(0000:00:0f.0): routed to hard irq line 6
Aug 24 19:03:55 srv kernel: ata13: SATA max UDMA/133 cmd 0x8800 ctl 0x8402 bmdma 0x7400 irq 20
Aug 24 19:03:55 srv kernel: ata14: SATA max UDMA/133 cmd 0x8000 ctl 0x7802 bmdma 0x7408 irq 20
Aug 24 19:03:55 srv kernel: ata13: dev 0 cfg 49:2f00 82:346b 83:7f01 84:4003 85:3469 86:3c01 87:4003 
88:203f
Aug 24 19:03:55 srv kernel: ata13: dev 0 ATA, max UDMA/100, 390622887 sectors (lba48)
Aug 24 19:03:55 srv kernel: ata13: dev 0 configured for UDMA/100
Aug 24 19:03:55 srv kernel: scsi12 : sata_via
Aug 24 19:03:55 srv kernel: ata14: dev 0 cfg 49:2f00 82:346b 83:7f01 84:4003 85:3469 86:3c01 87:4003 
88:203f
Aug 24 19:03:55 srv kernel: ata14: dev 0 ATA, max UDMA/100, 390719855 sectors (lba48)
Aug 24 19:03:55 srv kernel: ata14: dev 0 configured for UDMA/100
Aug 24 19:03:55 srv kernel: scsi13 : sata_via
Aug 24 19:03:55 srv kernel:   Vendor: ATA       Model: WDC WD2000JB-00D  Rev: 1.02
Aug 24 19:03:55 srv kernel:   Type:   Direct-Access                      ANSI SCSI revision: 05
Aug 24 19:03:55 srv kernel:   Vendor: ATA       Model: WDC WD2000JB-00F  Rev: 1.02
Aug 24 19:03:55 srv kernel:   Type:   Direct-Access                      ANSI SCSI revision: 05
Aug 24 19:03:55 srv kernel: SCSI device sda: 490234752 512-byte hdwr sectors (251000 MB)
Aug 24 19:03:55 srv kernel: SCSI device sda: drive cache: write through
Aug 24 19:03:55 srv kernel:  /dev/scsi/host0/bus0/target0/lun0: p1
Aug 24 19:03:55 srv kernel: Attached scsi disk sda at scsi0, channel 0, id 0, lun 0
Aug 24 19:03:55 srv kernel: SCSI device sdb: 490234752 512-byte hdwr sectors (251000 MB)
Aug 24 19:03:55 srv kernel: SCSI device sdb: drive cache: write through
Aug 24 19:03:55 srv kernel:  /dev/scsi/host1/bus0/target0/lun0: p1
Aug 24 19:03:55 srv kernel: Attached scsi disk sdb at scsi1, channel 0, id 0, lun 0
Aug 24 19:03:55 srv kernel: SCSI device sdc: 490234752 512-byte hdwr sectors (251000 MB)
Aug 24 19:03:55 srv kernel: SCSI device sdc: drive cache: write through
Aug 24 19:03:55 srv kernel:  /dev/scsi/host2/bus0/target0/lun0: p1
Aug 24 19:03:55 srv kernel: Attached scsi disk sdc at scsi2, channel 0, id 0, lun 0
Aug 24 19:03:55 srv kernel: SCSI device sdd: 490234752 512-byte hdwr sectors (251000 MB)
Aug 24 19:03:55 srv kernel: SCSI device sdd: drive cache: write through
Aug 24 19:03:55 srv kernel:  /dev/scsi/host3/bus0/target0/lun0: p1
Aug 24 19:03:55 srv kernel: Attached scsi disk sdd at scsi3, channel 0, id 0, lun 0
Aug 24 19:03:55 srv kernel: SCSI device sde: 490234752 512-byte hdwr sectors (251000 MB)
Aug 24 19:03:55 srv kernel: SCSI device sde: drive cache: write through
Aug 24 19:03:55 srv kernel:  /dev/scsi/host4/bus0/target0/lun0: p1
Aug 24 19:03:55 srv kernel: Attached scsi disk sde at scsi4, channel 0, id 0, lun 0
Aug 24 19:03:55 srv kernel: SCSI device sdf: 490234752 512-byte hdwr sectors (251000 MB)
Aug 24 19:03:55 srv kernel: SCSI device sdf: drive cache: write through
Aug 24 19:03:55 srv kernel:  /dev/scsi/host5/bus0/target0/lun0: p1
Aug 24 19:03:55 srv kernel: Attached scsi disk sdf at scsi5, channel 0, id 0, lun 0
Aug 24 19:03:55 srv kernel: SCSI device sdg: 490234752 512-byte hdwr sectors (251000 MB)
Aug 24 19:03:55 srv kernel: SCSI device sdg: drive cache: write through
Aug 24 19:03:55 srv kernel:  /dev/scsi/host6/bus0/target0/lun0: p1
Aug 24 19:03:55 srv kernel: Attached scsi disk sdg at scsi6, channel 0, id 0, lun 0
Aug 24 19:03:55 srv kernel: SCSI device sdh: 490234752 512-byte hdwr sectors (251000 MB)
Aug 24 19:03:55 srv kernel: SCSI device sdh: drive cache: write through
Aug 24 19:03:55 srv kernel:  /dev/scsi/host7/bus0/target0/lun0: p1
Aug 24 19:03:55 srv kernel: Attached scsi disk sdh at scsi7, channel 0, id 0, lun 0
Aug 24 19:03:55 srv kernel: SCSI device sdi: 490234752 512-byte hdwr sectors (251000 MB)
Aug 24 19:03:55 srv kernel: SCSI device sdi: drive cache: write through
Aug 24 19:03:55 srv kernel:  /dev/scsi/host8/bus0/target0/lun0: p1
Aug 24 19:03:55 srv kernel: Attached scsi disk sdi at scsi8, channel 0, id 0, lun 0
Aug 24 19:03:55 srv kernel: SCSI device sdj: 490234752 512-byte hdwr sectors (251000 MB)
Aug 24 19:03:55 srv kernel: SCSI device sdj: drive cache: write through
Aug 24 19:03:55 srv kernel:  /dev/scsi/host9/bus0/target0/lun0: p1
Aug 24 19:03:55 srv kernel: Attached scsi disk sdj at scsi9, channel 0, id 0, lun 0
Aug 24 19:03:55 srv kernel: SCSI device sdk: 390622887 512-byte hdwr sectors (199999 MB)
Aug 24 19:03:55 srv kernel: SCSI device sdk: drive cache: write through
Aug 24 19:03:55 srv kernel:  /dev/scsi/host12/bus0/target0/lun0: p1
Aug 24 19:03:55 srv kernel: Attached scsi disk sdk at scsi12, channel 0, id 0, lun 0
Aug 24 19:03:55 srv kernel: SCSI device sdl: 390719855 512-byte hdwr sectors (200049 MB)
Aug 24 19:03:55 srv kernel: SCSI device sdl: drive cache: write through
Aug 24 19:03:55 srv kernel:  /dev/scsi/host13/bus0/target0/lun0: p1
Aug 24 19:03:55 srv kernel: Attached scsi disk sdl at scsi13, channel 0, id 0, lun 0
Aug 24 19:03:55 srv kernel: Attached scsi generic sg0 at scsi0, channel 0, id 0, lun 0,  type 0
Aug 24 19:03:55 srv kernel: Attached scsi generic sg1 at scsi1, channel 0, id 0, lun 0,  type 0
Aug 24 19:03:55 srv kernel: Attached scsi generic sg2 at scsi2, channel 0, id 0, lun 0,  type 0
Aug 24 19:03:55 srv kernel: Attached scsi generic sg3 at scsi3, channel 0, id 0, lun 0,  type 0
Aug 24 19:03:55 srv kernel: Attached scsi generic sg4 at scsi4, channel 0, id 0, lun 0,  type 0
Aug 24 19:03:55 srv kernel: Attached scsi generic sg5 at scsi5, channel 0, id 0, lun 0,  type 0
Aug 24 19:03:55 srv kernel: Attached scsi generic sg6 at scsi6, channel 0, id 0, lun 0,  type 0
Aug 24 19:03:55 srv kernel: Attached scsi generic sg7 at scsi7, channel 0, id 0, lun 0,  type 0
Aug 24 19:03:55 srv kernel: Attached scsi generic sg8 at scsi8, channel 0, id 0, lun 0,  type 0
Aug 24 19:03:55 srv kernel: Attached scsi generic sg9 at scsi9, channel 0, id 0, lun 0,  type 0
Aug 24 19:03:55 srv kernel: Attached scsi generic sg10 at scsi12, channel 0, id 0, lun 0,  type 0
Aug 24 19:03:55 srv kernel: Attached scsi generic sg11 at scsi13, channel 0, id 0, lun 0,  type 0
Aug 24 19:03:55 srv kernel: mice: PS/2 mouse device common for all mice

Re: libata and md issues with 2.9.1-rc1

[Jeff Garzik]

Is there a difference between 2.6.8.1 and 2.6.9-rc1?

Any chance we could narrow it down to a specific change?

	Jeff

Re: libata and md issues with 2.9.1-rc1

[Brad Campbell]

Jeff Garzik wrote:
> Is there a difference between 2.6.8.1 and 2.6.9-rc1?

Oooh good point. I was using 2.6.8.1 but with yesterdays BK cset applied. I'll try a raw 2.6.8.1 now.

> Any chance we could narrow it down to a specific change?

I'm thinking about a binary search between 2.6.5 and 2.6.9-rc1. I'm just rebuilding the array at the 
moment and restoring the backups I took this afternoon (Talk about timing!).
Then I'll slot another couple of disks in and try some regression testing.

At least it's easily reproducible.
It has given the error recovery patch a good workout though! :p)

I mainly posted it just as a warning to be careful when upgrading until I figure out what is causing 
the issue.

I'll keep you posted.

Regards,
Brad

Re: libata and md issues with 2.6.9-rc1

[Brad Campbell]

Jeff Garzik wrote:
> Is there a difference between 2.6.8.1 and 2.6.9-rc1?
> 
> Any chance we could narrow it down to a specific change?

2.6.6 -> 2.6.7-rc1 is the problem.
Going in search of finer grained change sets now.

Re: libata and md issues with 2.9.1-rc1

[J. Ryan Earl]

Brad Campbell wrote:

> Just a heads up. I'm experiencing "issues" with 2.6.9-rc1 that don't 
> occur with 2.6.5.
>
> I run a 10 disk raid-5 on 3xPromise SATA150 cards and a 2 disk raid-0 
> on the on-board VIA chipset.
> The 10 disks are Maxtor Maxline-II SATA drives and the raid-0 is a 
> pair of WD2000JB drives with
> Addonics SATA->PATA converters. 

Did you try RAID-0 with the pair of Western Digital drives on the two 
free Promise slots?  If that fails similarly, it might not be a libata 
issue.

-ryan

Re: libata and md issues with 2.9.1-rc1

[Brad Campbell]

J. Ryan Earl wrote:
> Brad Campbell wrote:
> 
>> Just a heads up. I'm experiencing "issues" with 2.6.9-rc1 that don't 
>> occur with 2.6.5.
>>
>> I run a 10 disk raid-5 on 3xPromise SATA150 cards and a 2 disk raid-0 
>> on the on-board VIA chipset.
>> The 10 disks are Maxtor Maxline-II SATA drives and the raid-0 is a 
>> pair of WD2000JB drives with
>> Addonics SATA->PATA converters. 
> 
> 
> Did you try RAID-0 with the pair of Western Digital drives on the two 
> free Promise slots?  If that fails similarly, it might not be a libata 
> issue.

I thought about it. Given the drives are giving write errors when I write to /dev/md1 and not giving 
write errors when the raid is stopped and I write to the individual disks then it *must* be some 
issue with the hardware drivers.

If the block layer can submit a block to the driver that causes the drive to error out, then it's 
really a fault of the driver for trying to do something illegal.

Anyway, I have done a clone of the libata-2.6 bk tree and I'm trying to figure out how to extract 
all the individual csets between 2.6.6 and 2.6.7-rc1 so I can back them out 1 by 1 and see what 
caused the problem.

My other tack is to enable full SCSI debugging and compare the trace from 2.6.5 and 2.6.7-rc1 to see 
what is different.

I will give your suggestion a try when I get home tonight and fire it up on the extra promise channels.

Can anyone point me to a dummys guide to regression testing with BK? I read a great one by the WINE 
guys years ago on regression testing by date with CVS and it has proved immensely helpful over the 
years.

Regards,
Brad