Re: [2.6.23-rc3] Regression: "spurious completions during NCQ"

[Carsten Otto <c-otto@gmx.de>]

[-- Attachment #1: Type: text/plain, Size: 2474 bytes --]

Hi!

(I am referring to the thread at
http://marc.info/?l=linux-ide&m=118703097726277&w=2)

I also experience a lot of NCQ errors which look like these:

Sep 22 10:11:53 server kernel: ata1.00: exception Emask 0x2 SAct 0x7 SErr 0x0 action 0x2 frozen
Sep 22 10:11:53 server kernel: ata1.00: (spurious completions during NCQ issue=0x0 SAct=0x7 FIS=004040a1:00000010)
Sep 22 10:11:53 server kernel: ata1.00: cmd 60/38:00:bd:ee:01/00:00:13:00:00/40 tag 0 cdb 0x0 data 28672 in
Sep 22 10:11:53 server kernel:          res 40/00:20:5d:1d:eb/00:00:13:00:00/40 Emask 0x2 (HSM violation)
Sep 22 10:11:53 server kernel: ata1.00: cmd 60/40:08:f5:ee:01/00:00:13:00:00/40 tag 1 cdb 0x0 data 32768 in
Sep 22 10:11:53 server kernel:          res 40/00:20:5d:1d:eb/00:00:13:00:00/40 Emask 0x2 (HSM violation)
Sep 22 10:11:53 server kernel: ata1.00: cmd 60/08:10:35:ef:01/00:00:13:00:00/40 tag 2 cdb 0x0 data 4096 in
Sep 22 10:11:53 server kernel:          res 40/00:20:5d:1d:eb/00:00:13:00:00/40 Emask 0x2 (HSM violation)
Sep 22 10:11:53 server kernel: ata1: soft resetting port
Sep 22 10:11:53 server kernel: ata1: SATA link up 3.0 Gbps (SStatus 123 SControl 300)
Sep 22 10:11:53 server kernel: ata1.00: configured for UDMA/133
Sep 22 10:11:53 server kernel: ata1: EH complete
Sep 22 10:11:53 server kernel: sd 0:0:0:0: [sda] 586114704 512-byte hardware sectors (300091 MB)
Sep 22 10:11:53 server kernel: sd 0:0:0:0: [sda] Write Protect is off
Sep 22 10:11:53 server kernel: sd 0:0:0:0: [sda] Mode Sense: 00 3a 00 00
Sep 22 10:11:53 server kernel: sd 0:0:0:0: [sda] Write cache: disabled, read cache: enabled, doesn't support DPO or FUA

In total I have 355 such entries regarding my SATA disks starting on
September 15 when I installed kernel 2.6.22.6 (before I had
2.6.18-rc4-mm1 or so).

In addition I also see messages like this one:

kern.log:Sep 20 00:42:23 server kernel: ata2.00: NCQ disabled due to excessive errors

Please tell me how I can help resolving the issue (if it is a bug) or,
if possible, tell me how to fix it myself.

Information about my system:
- 4x Maxtor 7V300F0 (MaxLine III, 300GB, 7200rpm, 16MB cache, SATA2),
  firmware VA111900
- 1x Samsung 2SP2014N (SpinPoint P, 200GB, 7200rpm, 8MB cache, PATA),
  firmware VC100-33
- 4 software RAIDs on the SATA disks, 1x RAID1, 3x RAID5
- heavy usage of the RAIDs
- ICH7R
- 2.6.22.6
- Pentium D 805, 2GB RAM

Thanks a lot,
-- 
Carsten Otto
c-otto@gmx.de
www.c-otto.de

[-- Attachment #2: Digital signature --]
[-- Type: application/pgp-signature, Size: 189 bytes --]