lkml.org 
[lkml]   [2007]   [Jan]   [8]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: SATA problems
Tejun Heo wrote:
> Pablo Sebastian Greco wrote:
>
>> After an uptime of 13:34 under heavy load and no errors, I'm pretty
>> sure your patch is correct. Is there a way to backport this to 2.6.18.x?
>>
>
> I forgot this (even though I implemented it) but you can turn off NCQ by
> doing the following.
>
> # echo 1 > /sys/block/sdX/device/queue_depth
>
> Can you put the seagate drive under load to verify that it's the samsung
> drive's problem not the controller's?
>
>
>> Just an off topic question, does anyone know why I get so uneven IRQ
>> handling on 2.6.19-20 and almost perfect on 2.6.20-rc2-mm1?
>>
>
> I dunno. You have much better chance of getting a useful answer by
> asking it on a separate thread with proper subject line. People usualyl
> screen threads by subject. There are just too many message in LKML for
> anyone to follow all the message.
>
> Thanks.
>
>
Guess I spoke too soon :(
Today I found this
Jan 8 04:01:40 squid kernel: ata2.00: exception Emask 0x0 SAct 0x0 SErr
0x0 action 0x2 frozen
Jan 8 04:01:40 squid kernel: ata2.00: cmd
25/00:08:49:ee:e8/00:00:16:00:00/e0 tag 0 cdb 0x0 data 4096 in
Jan 8 04:01:40 squid kernel: res
40/00:00:00:4f:c2/00:00:00:00:00/00 Emask 0x4 (timeout)
Jan 8 04:01:40 squid kernel: ata2: soft resetting port
Jan 8 04:01:40 squid kernel: ata2: softreset failed (port busy but CLO
unavailable)
Jan 8 04:01:40 squid kernel: ata2: softreset failed, retrying in 5 secs
Jan 8 04:01:45 squid kernel: ata2: hard resetting port
Jan 8 04:01:53 squid kernel: ata2: port is slow to respond, please be
patient (Status 0x80)
Jan 8 04:02:16 squid kernel: ata2: port failed to respond (30 secs,
Status 0x80)
Jan 8 04:02:16 squid kernel: ata2: COMRESET failed (device not ready)
Jan 8 04:02:16 squid kernel: ata2: hardreset failed, retrying in 5 secs
Jan 8 04:02:21 squid kernel: ata2: hard resetting port
Jan 8 04:02:21 squid kernel: ata2: SATA link up 3.0 Gbps (SStatus 123
SControl 300)
Jan 8 04:02:21 squid kernel: ata2.00: configured for UDMA/133
Jan 8 04:02:21 squid kernel: ata2: EH complete
Jan 8 04:02:21 squid kernel: SCSI device sdb: 488397168 512-byte hdwr
sectors (250059 MB)
Jan 8 04:02:21 squid kernel: sdb: Write Protect is off
Jan 8 04:02:21 squid kernel: SCSI device sdb: write cache: enabled,
read cache: enabled, doesn't support DPO or FUA
#uptime
10:10:12 up 3 days, 22:48, 1 user, load average: 0.22, 0.19, 0.18
4 am is the lowest load ever, so I don't get it.
I've found two differences with older errors
SAct is now 0x0 when before was 0x7fffffff
And the cmd/res used to be really long, now it's just one command
About heavy loading the seagate, I've tested as suggested on other
thread dd if=<drive> of=/dev/null
for all 4 drives simultaneously, on top of usual load, and all was
perfect with current kernel (2.6.20-rc3 + blacklist).
Don't know what to do to help
Thanks.
Pablo.
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/

\
 
 \ /
  Last update: 2007-01-08 13:25    [from the cache]
©2003-2011 Jasper Spaans