[Linux-PowerEdge] Extremely poor performance with LVM vs. RAW disc

Linda A. Walsh dell at tlinx.org
Mon Nov 5 16:30:34 CST 2012


Bond Masuda wrote:
> The other thing to consider is the hardware architecture and how you
> make use of it. The MD1000 and PERC6/E setup has 4 lanes from the
> controller to the MD1000 head unit, which uses multipliers to make those
> 4 lanes into 4x4=16 lanes, of which only 15 are used. Let's call them
> drives 0 thru 14. If you try to access drives 0-3, or 4-7, or 8-11, or
> 12-14 within those sets, you'll have contention at the lane multiplier.
> A RAID-0 over 0,4,8,12 is going to be faster than a RAID-0 over 0,1,2,3.
> These results I've verified and tested before, so it's not just
> theoretical. 

----
I'd call that a bug.

why is it not using all the lanes?

Also why wouldn't only one of {0-3},{4-7},{8-11}{12-14} get the
hit if only 1 out of 16 lines is dead?   That's just poopy!

I use LSI containers -- only 12 disks in each... each take 8 channels,
but you can daisy chain them.  Something to consider if you have 6Mb
SAS2 cards.



More information about the Linux-PowerEdge mailing list