High disk I/O rate
I am wondering how I can tell what is using up all the disk I/O on my linode. I have been receiving emails about a high I/O rate and can't figure out why.
> has exceeded the notification threshold (1000) for disk io rate by averaging 6776.14 for the last 2 hours
It seems way to high for the time period these occur (overnight during slow usage hours).
Is there any command I could run to tell what is using the current disk I/O? I could easily set that up to run as a cron during these problematic hours and see if I can capture anything useful.
5 Replies
By the way, do you have any disk-intensive cron jobs scheduled in the night? Such as backups, log analysis, etc.?
iotop looks like it may do the job. I should be able to setup a task to run for an entire hour every second and dump the I/O usage.
As for running crons, it is default for a ubuntu 10.4 server.
> root@server:~# ls /etc/cron.*/
/etc/cron.d/:
nsd3 php5
/etc/cron.daily/:
apache2 apt aptitude bsdmainutils dpkg locate logrotate man-db ntp popularity-contest standard
/etc/cron.hourly/:
/etc/cron.monthly/:
standard
/etc/cron.weekly/:
man-db