Excessive load cycle counts on WD drives

[Riot]

 

Here's a summary of what the problem is.

- starting with kernel 3.5 developers decided to get rid of a system kernel thread that wakes up periodically (5 sec default) to call the "sync_fs" method of each registered file system.  In it's place, each file system is responsible for syncing when it deems it needs to.  For reiserfs, this means scheduling "work" on a "work queue" when necessary to execute sync_fs.  (They wanted to avoid unnecessarily waking a thread up to do nothing among other things).

 

From this thread http://lime-technology.com/forum/index.php?topic=28142.45

 

This may be off topic but does anyone know if that wake up thread they got rid of is the same one that causes all the load cycle count increases on the Western Digital drives?

[limetech]

This may be off topic but does anyone know if that wake up thread they got rid of is the same one that causes all the load cycle count increases on the Western Digital drives?

Don't know what you mean, links?

[Hoopster]

This may be off topic but does anyone know if that wake up thread they got rid of is the same one that causes all the load cycle count increases on the Western Digital drives?

 

Excessive load cycle counts on WD drives has been around for awhile. I don't believe it has anything to do with the Linux kernel patch.  I have a WD30EZRX drive in my array that is already well over 18,000 on the LCC value after a few months of use.  I had the same problem in a 2TB WD Black drive that I fixed by running WDIDLE3 and setting it to the maximum 300 second value before it parked the heads.

 

Most consumer WD drives are rated at 300,000 load cycle count and some users were seeing excessive values over 100,000 in less than a year.  I have yet to "fix" my WD30EZRX, but, I will probably pull it out as a spare run WDIDLE3 on it and replace it with a 3TB WD Red I am preclearing now.  The Red drives seem less susceptible to this issue.

 

See http://www.storagereview.com/how_to_stop_excessive_load_cycles_on_the_western_digital_2tb_caviar_green_wd20ears_with_wdidle3 for more info.

[Riot]

This may be off topic but does anyone know if that wake up thread they got rid of is the same one that causes all the load cycle count increases on the Western Digital drives?

Don't know what you mean, links?

 

What Hoopster said and..

Googling pulls mainly fixes for the issue rather than the specific issue in Linux other than it wakes the drives up every five secs.

This link is about a specific as I've found saying it relates to pdflush.

http://jeanbruenn.info/2011/01/23/wd-green-discs-and-the-problem-in-linux-load-cycle-count/

 

also

http://lime-technology.com/forum/index.php?topic=5223.0

http://translate.google.com/translate?hl=en&sl=de&u=http://wiki.ubuntuusers.de/WD_IntelliPark&prev=/search%3Fq%3DLoad%2BCycle%2Bwd%2Blinux%2Bpdflush%26safe%3Doff%26client%3Dfirefox-a%26sa%3DX%26rls%3Dorg.mozilla:en-US:official%26biw%3D1540%26bih%3D796

 

Was mainly just curious because it sounded similar.

[Interstellar]

 

Here's a summary of what the problem is.

- starting with kernel 3.5 developers decided to get rid of a system kernel thread that wakes up periodically (5 sec default) to call the "sync_fs" method of each registered file system.  In it's place, each file system is responsible for syncing when it deems it needs to.  For reiserfs, this means scheduling "work" on a "work queue" when necessary to execute sync_fs.  (They wanted to avoid unnecessarily waking a thread up to do nothing among other things).

 

From this thread http://lime-technology.com/forum/index.php?topic=28142.45

 

This may be off topic but does anyone know if that wake up thread they got rid of is the same one that causes all the load cycle count increases on the Western Digital drives?

 

No.

 

This is something that is set in the firmware of the drive.

 

I've personally turned it off on all of my WD Green drives. Called WDidle3 I think.