1

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.

3
  • 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, 2012 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, 2012 at 18:51
  • 1
    I'll share with you end of story: hard drive died! It was probably the problem.
    – Federico
    Dec 12, 2012 at 17:47

0

You must log in to answer this question.

Browse other questions tagged .