I have a server with Debian 6 and software RAID1. There is a problem: every few seconds the jbd2/md2-8 process loads all the HDD IO. It was detected by iotop. And for the md2_raid1 process 99% of IO displays.
The flush-9:2 process every few seconds loads 99% of CPU in top.
What can I do to optimize this system? Can transition to hardware RAID help in this situation?
This is cat /proc/mdstat
Personalities : [raid0] [raid1] [raid6] [raid5] [raid4] [raid10] md3 : active raid1 sda4 sdb4 1822442815 blocks super 1.2 [2/2] [UU] md2 : active raid1 sda3 sdb3 1073740664 blocks super 1.2 [2/2] [UU] md1 : active raid1 sda2 sdb2 524276 blocks super 1.2 [2/2] [UU] md0 : active raid1 sda1 sdb1 33553336 blocks super 1.2 [2/2] [UU] unused devices: <none>