Hard Disk’s hard life
I knew that hard disks had a limited time-life park/unpark-wise, but I didn't know that was that bad. I always thought that because of ext3's commit every 5 seconds, disk would never spin out and park the head. I was wrong. It seems that whether or not the disk is accessed, every put here the time it is for your disk minutes, it does park and unpark the head. Well, at least on laptop disks, because it seems this is not the case for desktops.
My 3 year-old vaio, which is now this web server, has a Load_Cycle_Count of 580465 for 9775 Power_On_Hours, which is about 1 load cycle per minute.
My 1 year-old vaio, has a Load_Cycle_Count of 83718 for 4043 Power_On_Hours, which is about 1 load cycle every 3 minutes.
While I managed to actually stop the load cycles to occur on the older vaio, with hdparm -B254, nothing actually stopped it on the newer one. I tried to change some other parameters with hdparm -S but nothing did work. I still have to take a look at the BIOS, though.
Now, the question is : why the fuck are the heads parked/unparked every little while even when accesses occur ? Is it a conspiracy so that laptop disks won't last forever ?
Well, at least, I've never experienced a hard disk failure in 12 years of using computers with hard disks. For how long ?...
[Note: the Dell laptop provided by my company, running Windows XP (which also has a somewhat journalled filesystem and commits the journal every few seconds) has around 24000 load cycles for about 800 hours of use, which is 1 load cycle every 2 minutes, so this is not a Linux issue.]
2005-11-24 18:42:58+0900
Both comments and pings are currently closed.
2005-11-25 03:12:45+0900
Until shortly after you blatantly defy Cthulu and Shub-Disk like that. :)
2005-11-25 07:39:45+0900
Well, I belive laptops park hard disc heads as often as they can to prevent damage in case the laptop is moved, shaken, hit, etc. One of the worst things for desktop disc is to shake/hit them, while reading/writing. I guess parking heads lowers the risk of damage in case of laptops.
2005-11-25 16:33:12+0900
I don’t know about you, but I prefer a laptop with a hard disk that may have a relatively short lifetime than one with a hard disk that crashes instantly when someone bumps into me while I am using it. A head crash may result in instant failure. A shorter lifetime due to parking the heads too frequently is less severe problem.
That being said, it does not make much sense to park the heads all the time if the laptop is used mostly as a desktop and is not moved often.
2005-11-25 18:08:28+0900
[…] Mike Hommey: Hard disk’s life […]
2005-11-25 18:36:03+0900
Raphael: the thing is that the hard disk is _always_ active, having the ext3 journal commit every 5 seconds. Whether it parks/unparks the heads at this time is pointless. Actually, if you take a look at your disk status with hdparm -C, you will _always_ see active (idle or not), which means heads are not parked. And then after some time, it _will_ park and unpark the heads instantly (Load_cycle_count inscreased), and still be active. So what is the point ?
2005-11-26 22:40:31+0900
Very strange. I’m using the smarttools since two years and have never seen a behaviour like that. The laptop I’m writing this on has 3200h power on and 13800 load cycles which is still 99% life left.
It’s all running Debian here, mostly sarge.
2005-11-27 14:12:25+0900
I can confirm that phenomenon. And no, it does not only happen on GNU/Linux, either.
I on my dual boot laptop with a Samsung MP0804H I get ca. 2 load cycles per minute, running either Linux or Windows. Atm with a lifetime of 8900 minutes, I already have a load cycle count of 14750.
Unfortunately, with that model hdparm -Bnnn does not work, doing the command fails with an error. It seems the drive does not support it.
2005-12-24 15:41:41+0900
Similar story here: New hard disk (WDC WD400UE-22HCT0),
already 38739 load cycles after 403 power-on hours.
But hdparm -B254 seems to help. Thanks for the tip.