[CentOS] Software RAID resync

John R Pierce pierce at hogranch.com
Fri May 8 04:58:22 UTC 2009


Rajagopal Swaminathan wrote:
> This list never ceases to amaze me with very very quick and educating responses
>
>
> John R Pierce <pierce at ...> writes:
>
>   
>> Rajagopal Swaminathan wrote:
>>
>> depends on  your disk controllers.    whats `iostat -x 5` say the IO on 
>> hdb3 and hda3 is doing? (ignore the first sample, its average since 
>>     
>
> avg-cpu:  %user   %nice %system %iowait  %steal   %idle
>            0.13    0.00   31.98    0.00    0.00   67.89
>
> Device:         rrqm/s   wrqm/s   r/s   w/s   rsec/s   wsec/s avgrq-sz avgqu-sz
>   await  svctm  %util
> hda              26.40     0.40  4.20  2.20  3660.80    20.80   575.25     2.74
>  386.97 148.44  95.00
> hdb               0.00    24.80  0.00  6.60     0.00  3988.80   604.36     1.43
>  217.45 143.24  94.54
> ...
>   

> I won't claim I understand everyone of the above columns. 
> I am in the process of reading man pages.
>   

the import wants there are rsec/s and wsec/s which are read/write 
sectors/sec, and %util which is %utilization.  your disks are 100% busy, 
and one is reading 3600 sector/sec which is 1.8MB/sec and the other is 
writing that much.


there's no way in h*** a SATA disk should be that slow, my guess is the 
SATA controller is runnign in IDE PIO mode.    you also have 32% CPU 
utilization, which is real high for just doing this.







More information about the CentOS mailing list