sata_promise ata exceptions (2.6.20.6)

I've recently moved to a Promise Sata controller with two SATA drives in a RAID1 mirror. But I get lots of ata exceptions and the kernel eventually slows down my drive to UDMA/33.

It usually happens on ata1 (sda), but sometimes it'll kick in on ata2 (sdb). I can definitely cause this to happen more by increasing load on the disks. But even low load (checking email) causes this. Full hardware and software specs are below, but first, the errors:

ata1.00: exception Emask 0x10 SAct 0x0 SErr 0x180100 action 0x2 ata1.00: cmd c8/00:d0:8a:31:ae/00:00:00:00:00/e0 tag 0 cdb 0x0 data 106496 in

         res 51/0c:0f:4b:32:ae/00:00:00:00:00/e0 Emask 0x10 (ATA bus error)

ata1: soft resetting port
ata1: SATA link up 1.5 Gbps (SStatus 113 SControl 300)
ata1.00: configured for UDMA/133
ata1: EH complete
SCSI device sda: 312581808 512-byte hdwr sectors (160042 MB)
sda: Write Protect is off
sda: Mode Sense: 00 3a 00 00
SCSI device sda: write cache: enabled, read cache: enabled, doesn't support DPO or FUA
ata1.00: exception Emask 0x10 SAct 0x0 SErr 0x380100 action 0x2 ata1.00: cmd c8/00:a0:12:fa:bc/00:00:00:00:00/e0 tag 0 cdb 0x0 data 81920 in

         res 51/0c:1f:93:fa:bc/00:00:00:00:00/e0 Emask 0x10 (ATA bus error)

ata1: soft resetting port
ata1: SATA link up 1.5 Gbps (SStatus 113 SControl 300)
ata1.00: configured for UDMA/133
ata1: EH complete
SCSI device sda: 312581808 512-byte hdwr sectors (160042 MB)
sda: Write Protect is off
sda: Mode Sense: 00 3a 00 00
SCSI device sda: write cache: enabled, read cache: enabled, doesn't support DPO or FUA
ata1.00: limiting speed to UDMA/100
ata1.00: exception Emask 0x10 SAct 0x0 SErr 0x380100 action 0x2 ata1.00: cmd c8/00:48:2a:27:ac/00:00:00:00:00/e0 tag 0 cdb 0x0 data 36864 in

         res 51/0c:27:4b:27:ac/00:00:00:00:00/e0 Emask 0x10 (ATA bus error)

ata1: soft resetting port
ata1: SATA link up 1.5 Gbps (SStatus 113 SControl 300)
ata1.00: configured for UDMA/100
ata1: EH complete
SCSI device sda: 312581808 512-byte hdwr sectors (160042 MB)
sda: Write Protect is off
sda: Mode Sense: 00 3a 00 00
SCSI device sda: write cache: enabled, read cache: enabled, doesn't support DPO or FUA
ata1.00: limiting speed to UDMA/66
ata1.00: exception Emask 0x10 SAct 0x0 SErr 0x180100 action 0x2 ata1.00: cmd c8/00:f8:6a:7a:ae/00:00:00:00:00/e0 tag 0 cdb 0x0 data 126976 in

         res 51/0c:97:cb:7a:ae/00:00:00:00:00/e0 Emask 0x10 (ATA bus error)

ata1: soft resetting port
ata1: SATA link up 1.5 Gbps (SStatus 113 SControl 300)
ata1.00: configured for UDMA/66
ata1: EH complete
SCSI device sda: 312581808 512-byte hdwr sectors (160042 MB)
sda: Write Protect is off
sda: Mode Sense: 00 3a 00 00
SCSI device sda: write cache: enabled, read cache: enabled, doesn't support DPO or FUA

Kernel: 2.6.20.6 (PREEMT & SMP)
SATA Controller:
02:04.0 RAID bus controller: Promise Technology, Inc. PDC20378 (FastTrak 378/SATA 378) (rev 02)

        Subsystem: ASUSTeK Computer Inc. K8V Deluxe/PC-DL Deluxe motherboard
        Flags: bus master, 66MHz, medium devsel, latency 96, IRQ 16
        I/O ports at df00 [size=64]
        I/O ports at dfa0 [size=16]
        I/O ports at dc00 [size=128]
        Memory at feafe000 (32-bit, non-prefetchable) [size=4K]
        Memory at feac0000 (32-bit, non-prefetchable) [size=128K]
        Capabilities: [60] Power Management version 2

Drives:
2 x Western Digital WD1600JS-00N

Other Setup Details:
3 software RAID1 mirrors (md0, 1, 2 made up of sd{a,b}1 - 3 respectively) md3 is an LVM physical group with 2 volumes in it. In other words:

    /dev/md0 = /boot
    /dev/md1 = swap
    /dev/md2 = LVM:
            /dev/vg00/root = /
            /dev/vg00/home = /home

The sata controller isn't brand new, but it's never been used and is relatively new. The sata drives and cables are fresh out of the box. Any help would be greatly appreciated.

Phil Dibowitz                             [email protected]
Open Source software and tech docs        Insanity Palace of Metallica
http://www.phildev.net/                   http://www.ipom.com/

"Never write it in C if you can do it in 'awk';
 Never do it in 'awk' if 'sed' can handle it;
 Never use 'sed' when 'tr' can do the job;
 Never invoke 'tr' when 'cat' is sufficient;
 Avoid using 'cat' whenever possible" -- Taylor's Laws of Programming

I got similar errors since kernel 2.6.20-xx and the LBA48/EH fix between 2.6.21-rc5-git10 and 2.6.21-rc5-git13 seems to fix it. I'm no developer, but you should perhaps try kernel 2.6.21-rc5-git13 or later.

Greetings
Ansgar Knappheide

I tried 2.6.21-rc6-git1 as I figure it was likely to be a bit more stable (closer to a 'stable' release), but I'm still getting these messages.

Any other thoughts?

Phil Dibowitz                             [email protected]
Open Source software and tech docs        Insanity Palace of Metallica
http://www.phildev.net/                   http://www.ipom.com/

"Never write it in C if you can do it in 'awk';
 Never do it in 'awk' if 'sed' can handle it;
 Never use 'sed' when 'tr' can do the job;
 Never invoke 'tr' when 'cat' is sufficient;
 Avoid using 'cat' whenever possible" -- Taylor's Laws of Programming