Server Fault is a question and answer site for system and network administrators. Join them; it only takes a minute:

Sign up
Here's how it works:
  1. Anybody can ask a question
  2. Anybody can answer
  3. The best answers are voted up and rise to the top

some days ago I discovered (using Munin) that my server had high iowait times. The reason was that write cache was disabled. I enabled it using hdparm -W1 /dev/sda but after some time (ramdonly) it got disable again.

No information about this event in system logs. I updated kernel to 2.6.18-308.20.1.el5 #1 SMP, it seems to be better but the problem continues.

I turned off every service but problem still continues.

Do you know where can I get some information or log to know why write cache turns off?

Some hardware information:

Hard drive: Western Digital WDC WD5000AAKX-00ERMA0 Mother Board: Intel D945GCPE

Any help is appreciated.

share|improve this question
Is that the only drive in the configuration? What storage configuration is it? file system, LVM/mdadm, etc. And does dmesg / /var/log/messages show any indication of that change? It may help you track down the source. Please be aware that write back cache could be a cause for data loss some time later if your machine encounters a power loss. – gertvdijk Dec 5 '12 at 14:41
Thanks for your comment, yes it is the only drive un the configuration. It is ext3. Theres no RAID. dmesg doesnt show anything when drive cache turns off but dmesg logs "EXT3-fs: mounted filesystem with writeback data mode". Nothing in /var/log/messages. – Federico Dec 5 '12 at 18:51
I'll share with you end of story: hard drive died! It was probably the problem. – Federico Dec 12 '12 at 17:47

Your Answer


By posting your answer, you agree to the privacy policy and terms of service.

Browse other questions tagged or ask your own question.