WD 400GB SATA Drive In Constant Smart Testing?

WD 400GB SATA Drive In Constant Smart Testing?

[Justin Piszcz]

When I write to this disk for a while, I see this in dmesg (only once so 
far):

[31230.223504] ata6: translated ATA stat/err 0x51/04 to SCSI SK/ASC/ASCQ 
0xb/00/00
[31230.223511] ata6: status=0x51 { DriveReady SeekComplete Error }
[31230.223515] ata6: error=0x04 { DriveStatusError }


Is there some sort of smart testing going on constantly?  I only get 
26-27MB/s on this 400GB/SATA/16MB/7200RPM drive.  I use smartmontools to 
do a daily test.  However, even with smart disabled, I get:

# hdparm -t /dev/sde
/dev/sde:
  Timing buffered disk reads:   78 MB in  3.06 seconds =  25.46 MB/sec

Does anyone know if this drive has problems in Linux or something?

[    6.895914]   Vendor: ATA       Model: WDC WD4000KD-00N  Rev: 01.0


It just seems to be that drive that has issues.

Here is a 400GB seagate ata/100:
/dev/hde:
  Timing buffered disk reads:  172 MB in  3.02 seconds =  56.91 MB/sec

Here is a 74GB raptor SATA/150:
/dev/sda:
  Timing buffered disk reads:  204 MB in  3.03 seconds =  67.38 MB/sec

Both drives above are on the same system, so my question is what exactly 
is wrong with the WD drive?  Is it a Linux issue, a drive issue, or?

Does anyone else use this drive, what rates do they get?

What is up with the error in dmesg?


# smartctl -d ata -l selftest /dev/sde
smartctl version 5.34 [i686-pc-linux-gnu] Copyright (C) 2002-5 Bruce Allen
Home page is http://smartmontools.sourceforge.net/

=== START OF READ SMART DATA SECTION ===
SMART Self-test log structure revision number 1
Num  Test_Description    Status                  Remaining 
LifeTime(hours)  LBA
_of_first_error
# 1  Short offline       Completed without error       00%      1094 
-
# 2  Offline             Completed without error       00%         0 
-
# 3  Offline             Completed without error       00%         0 
-
# 4  Offline             Completed without error       00%         0 
-
# 5  Offline             Completed without error       00%         0 
-
# 6  Offline             Completed without error       00%         0 
-
# 7  Offline             Completed without error       00%         0 
-
# 8  Offline             Completed without error       00%         1 
-
# 9  Short offline       Completed without error       00%       810 
-
#10  Vendor offline      Completed without error       30%     65280 
-
#11  Offline             Self-test routine in progress 150%     65535 
-
#12  Vendor offline      Self-test routine in progress 150%       255 
-
#13  Vendor offline      Completed without error       00%         0 
-
#14  Offline             Completed without error       00%         0 
-
#15  Offline             Completed without error       00%         0 
-
#16  Offline             Completed without error       00%         0 
-
#17  Offline             Completed without error       00%         0 
-
#18  Offline             Completed without error       00%         0 
-
#19  Offline             Completed without error       00%         0 
-
#20  Offline             Completed without error       00%         0 
-
#21  Offline             Completed without error       00%         1 
-

default hdparms? readahead=256? Re: WD 400GB xATA Drives

[Linda Walsh]

I've seen similar errors soon after bootup on a 400GB PATA Seagate
drive, but they have mysteriously disappeared so I haven't tracked
them down.

Have you checked if there is a difference in the hard disk parameters?
hdparm -i <drive>.

For some insane reason I haven't tracked down, drives not explicitly
set to known values may not contain "great values".  My "readahead"
value seems to boot with a value of "256" for all of my drives.

Is this not a bit "excessive"?
(

Justin Piszcz wrote:
> When I write to this disk for a while, I see this in dmesg (only once 
> so far):
>
> [31230.223504] ata6: translated ATA stat/err 0x51/04 to SCSI 
> SK/ASC/ASCQ 0xb/00/00
> [31230.223511] ata6: status=0x51 { DriveReady SeekComplete Error }
> [31230.223515] ata6: error=0x04 { DriveStatusError }
>
>
> Is there some sort of smart testing going on constantly?  I only get 
> 26-27MB/s on this 400GB/SATA/16MB/7200RPM drive.  I use smartmontools 
> to do a daily test.  However, even with smart disabled, I get:
>
> # hdparm -t /dev/sde
> /dev/sde:
>  Timing buffered disk reads:   78 MB in  3.06 seconds =  25.46 MB/sec
>
> Does anyone know if this drive has problems in Linux or something?
>
> [    6.895914]   Vendor: ATA       Model: WDC WD4000KD-00N  Rev: 01.0
>
>
> It just seems to be that drive that has issues.
>
> Here is a 400GB seagate ata/100:
> /dev/hde:
>  Timing buffered disk reads:  172 MB in  3.02 seconds =  56.91 MB/sec
>
> Here is a 74GB raptor SATA/150:
> /dev/sda:
>  Timing buffered disk reads:  204 MB in  3.03 seconds =  67.38 MB/sec
>
> Both drives above are on the same system, so my question is what 
> exactly is wrong with the WD drive?  Is it a Linux issue, a drive 
> issue, or?
>
> Does anyone else use this drive, what rates do they get?
>
> What is up with the error in dmesg?
>
>
> # smartctl -d ata -l selftest /dev/sde
> smartctl version 5.34 [i686-pc-linux-gnu] Copyright (C) 2002-5 Bruce 
> Allen
> Home page is http://smartmontools.sourceforge.net/
>
> === START OF READ SMART DATA SECTION ===
> SMART Self-test log structure revision number 1
> Num  Test_Description    Status                  Remaining 
> LifeTime(hours)  LBA
> _of_first_error
> # 1  Short offline       Completed without error       00%      1094 -
> # 2  Offline             Completed without error       00%         0 -
> # 3  Offline             Completed without error       00%         0 -
> # 4  Offline             Completed without error       00%         0 -
> # 5  Offline             Completed without error       00%         0 -
> # 6  Offline             Completed without error       00%         0 -
> # 7  Offline             Completed without error       00%         0 -
> # 8  Offline             Completed without error       00%         1 -
> # 9  Short offline       Completed without error       00%       810 -
> #10  Vendor offline      Completed without error       30%     65280 -
> #11  Offline             Self-test routine in progress 150%     65535 -
> #12  Vendor offline      Self-test routine in progress 150%       255 -
> #13  Vendor offline      Completed without error       00%         0 -
> #14  Offline             Completed without error       00%         0 -
> #15  Offline             Completed without error       00%         0 -
> #16  Offline             Completed without error       00%         0 -
> #17  Offline             Completed without error       00%         0 -
> #18  Offline             Completed without error       00%         0 -
> #19  Offline             Completed without error       00%         0 -
> #20  Offline             Completed without error       00%         0 -
> #21  Offline             Completed without error       00%         1 -
>
>
> -
> 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/

Re: default hdparms? readahead=256? Re: WD 400GB xATA Drives

[Mark Lord]

Linda Walsh wrote:
>..
> set to known values may not contain "great values".  My "readahead"
> value seems to boot with a value of "256" for all of my drives.
> 
> Is this not a bit "excessive"?

Wow.. that does look a bit HUGE.  Thanks for pointing it out,
I'm resetting mine back to 128 for now.

> Justin Piszcz wrote:
>> When I write to this disk for a while, I see this in dmesg (only once 
>> so far):
>>
>> [31230.223504] ata6: translated ATA stat/err 0x51/04 to SCSI 
>> SK/ASC/ASCQ 0xb/00/00
>> [31230.223511] ata6: status=0x51 { DriveReady SeekComplete Error }
>> [31230.223515] ata6: error=0x04 { DriveStatusError }
>>
>> Is there some sort of smart testing going on constantly?  I only get 
>> 26-27MB/s on this 400GB/SATA/16MB/7200RPM drive.  I use smartmontools 
>> to do a daily test.  However, even with smart disabled, I get:
>>
>> # hdparm -t /dev/sde
>> /dev/sde:
>>  Timing buffered disk reads:   78 MB in  3.06 seconds =  25.46 MB/sec
>>
>> Does anyone know if this drive has problems in Linux or something?
>>
>> [    6.895914]   Vendor: ATA       Model: WDC WD4000KD-00N  Rev: 01.0
...

Some drives suck at sequential reads, in favour of doing random seeks
very very well.  Basically, the on-drive seek algorithm may not favour
doing much read-ahead.  Try "hdparm -A1" and see if that helps.

Re: WD 400GB SATA Drive In Constant Smart Testing?

[Jan Engelhardt]

>
> Is there some sort of smart testing going on constantly?  I only get 26-27MB/s

You can find out using `smartctl -data -a /dev/hdX`; if there is a SMART 
test going on, there should be info about its status.

> #13  Vendor offline      Completed without error       00%         0 -
> #14  Offline             Completed without error       00%         0 -
> #15  Offline             Completed without error       00%         0 -
> #16  Offline             Completed without error       00%         0 -
> #17  Offline             Completed without error       00%         0 -
> #18  Offline             Completed without error       00%         0 -
> #19  Offline             Completed without error       00%         0 -
> #20  Offline             Completed without error       00%         0 -
> #21  Offline             Completed without error       00%         1 -
>
A little bit more below the values, usually.



Jan Engelhardt
-- 

Re: default hdparms? readahead=256? Re: WD 400GB xATA Drives

[Justin Piszcz]

Turned out I had too many devices in the box, I have removed them now, 
still getting those pesky drive errors though, I will try the hdparm soon, 
thanks.


On Mon, 13 Feb 2006, Mark Lord wrote:

> Linda Walsh wrote:
>> ..
>> set to known values may not contain "great values".  My "readahead"
>> value seems to boot with a value of "256" for all of my drives.
>> 
>> Is this not a bit "excessive"?
>
> Wow.. that does look a bit HUGE.  Thanks for pointing it out,
> I'm resetting mine back to 128 for now.
>
>> Justin Piszcz wrote:
>>> When I write to this disk for a while, I see this in dmesg (only once so 
>>> far):
>>> 
>>> [31230.223504] ata6: translated ATA stat/err 0x51/04 to SCSI SK/ASC/ASCQ 
>>> 0xb/00/00
>>> [31230.223511] ata6: status=0x51 { DriveReady SeekComplete Error }
>>> [31230.223515] ata6: error=0x04 { DriveStatusError }
>>> 
>>> Is there some sort of smart testing going on constantly?  I only get 
>>> 26-27MB/s on this 400GB/SATA/16MB/7200RPM drive.  I use smartmontools to 
>>> do a daily test.  However, even with smart disabled, I get:
>>> 
>>> # hdparm -t /dev/sde
>>> /dev/sde:
>>>  Timing buffered disk reads:   78 MB in  3.06 seconds =  25.46 MB/sec
>>> 
>>> Does anyone know if this drive has problems in Linux or something?
>>> 
>>> [    6.895914]   Vendor: ATA       Model: WDC WD4000KD-00N  Rev: 01.0
> ...
>
> Some drives suck at sequential reads, in favour of doing random seeks
> very very well.  Basically, the on-drive seek algorithm may not favour
> doing much read-ahead.  Try "hdparm -A1" and see if that helps.
>

Re: [smartmontools-support]Re: WD 400GB SATA Drive In Constant Smart Testing?

[Michael Mansour]

Hi,

> > Is there some sort of smart testing going on constantly?  I only get 26-27MB/s
> 
> You can find out using `smartctl -data -a /dev/hdX`; if there is a 
> SMART test going on, there should be info about its status.
> 
> > #13  Vendor offline      Completed without error       00%         0 -
> > #14  Offline             Completed without error       00%         0 -
> > #15  Offline             Completed without error       00%         0 -
> > #16  Offline             Completed without error       00%         0 -
> > #17  Offline             Completed without error       00%         0 -
> > #18  Offline             Completed without error       00%         0 -
> > #19  Offline             Completed without error       00%         0 -
> > #20  Offline             Completed without error       00%         0 -
> > #21  Offline             Completed without error       00%         1 -
> >
> A little bit more below the values, usually.

Also, you may have to monitor this for a while as I've seen when a drive is
not recognised in the smartctl database, then it doesn't show it's progress,
only when it finishes checking does it show something in the selftest log.

Michael.