[CentOS] Software RAID1 Disk I/O

Wed Jan 6 00:00:15 UTC 2010
Les Mikesell <lesmikesell at gmail.com>

On 1/5/2010 5:29 PM, Matt wrote:
>>> I just installed CentOS 5.4 64 bit release on a 1.9ghz CPU with 8gB of
>>> RAM.  It has 2 Western Digital 1.5TB SATA2 drives in RAID1.
>>>
>>> [root at server ~]# df -h
>>> Filesystem            Size  Used Avail Use% Mounted on
>>> /dev/md2              1.4T  1.4G  1.3T   1% /
>>> /dev/md0               99M   19M   76M  20% /boot
>>> tmpfs                 4.0G     0  4.0G   0% /dev/shm
>>> [root at server ~]#

>>
>> Did you just create the RAIDs?  It will something that size a few hours to
>> complete the initial sync.  Try 'cat /proc/mdstat' to see when the sync
>> completes.  Until then, expect to have head contention with anything else
>> that might be trying to use the drives.
>
> Here is what I got there.  Md1 is swap I beleive:
>
> [root at server ~]# uptime
>   17:20:54 up 7 days,  3:26,  2 users,  load average: 3.41, 2.93, 2.89
> [root at server ~]#
> [root at server ~]#
> [root at server ~]# cat /proc/mdstat
> Personalities : [raid1]
> md0 : active raid1 sdb1[1] sda1[0]
>        104320 blocks [2/2] [UU]
>
> md1 : active raid1 sdb2[1] sda2[0]
>        8385856 blocks [2/2] [UU]
>
> md2 : active raid1 sdb3[1] sda3[0]
>        1456645568 blocks [2/2] [UU]

That's working normally with the sync completed.  Mirrors should run at 
close to the speed of a single drive.  Maybe you are just expecting too 
much from SATA or you have something like an updatedb running.  An 
'hdparm -tT' against the partitions and md devices should give you an 
idea of what the drives can do.  And top might show what's causing the 
load (but maybe not if it is mostly waiting on disk seeks).

-- 
   Les Mikesell
    lesmikesell at gmail.com