Misaligned raid0

Phillip Susi psusi at cfl.rr.com
Thu Dec 8 01:01:54 UTC 2005

I have been using dmraid for a few months now to access my two disk 
raid0 on my VIA SATA Raid controller.  Today I noticed some IO errors 
beyond the end of the disk in my syslog and when I investigated, it 
looks to me like my raid setup is broken.

The dm table that dmraid creates for the main raid volume device looks 
like this:

0 144607678 striped 2 128 8:0 0 8:16 0

Now what I noticed is that 144607678 is NOT an even multiple of the 
stripe width of 256 sectors ( 128 sector stripe factor x 2 disks ). 
Shouldn't the total length of a striped mapper device allways be an even 
multiple of the stripe width?  I think that the last fractional stripe 
at the end of the disk is the problem, because there aren't a full 128 
sectors left on the disk to access before rolling over to the next disk 
in the stripe.

So does this mean that my bios created a broken stripe?  And why does 
dmraid and the kernel device mapper accept such broken values?

Wish me luck with using resizefs.reiserfs to shrink down the volume a 
bit to avoid that broken tail end.

More information about the Ataraid-list mailing list