50% speed penalty for LVM on mdraid

David Nielsen david at lovesunix.net
Sun Mar 18 17:31:47 UTC 2007


søn, 18 03 2007 kl. 16:34 +0000, skrev Andy Burns:
> I have an F7/rawhide machine with 6x400GB SATA II disks all
> partitioned as 100MB + 399.9GB
> 
> /boot is on /dev/sda1 (would be RAID1 across /dev/sd[abc]1 partitions
> except for mkinitrd raid1.ko breakage) with /dev/md1 as RAID5 on
> /dev/sd[abcdef]2
> 
> Then a single LVM vg00 on top of /dev/md1
> 
> root and swap as LVs within vg00 and plenty of spare space.
> 
> Doing some timings of the various block devices (so far just roughly
> with hdparm, bonnie installed for more detail later). Results of
> "hdparm -Tt" averaged over a few runs, showing cached and buffered
> speeds
> 
> /dev/sda1 gives 1995MB/s and 72MB/s which seems quite good for a single spindle
> /dev/md1 gives 2040MB/s and 260MB/s also fairly good (I had hoped with
> six spindles and parity to get closer to 5x performance than 3.5x)
> /dev/mapper/vg00-lv01 (my root fs) gives 2100MB/s and 135MB/s which is
> a little disappointing
> 
> Nearly a 50% speed penalty seems a heavy price to pay for LVM, is
> there any slow debug code currently in rawhide that might explain it?
> Could I have some bad choices of block sizes between RAID/LVM layers
> which are reducing throughput by splitting reads? Anything  else?

Wow that explains a lot.. performance on Development has be awful for me
lately and I have been unable to figure out why, this might be related.

My setup is 2 400GB drives in RAID0 using dmraid with LVM ontop.

- David Nielsen

-- 
"Ridicule is the only weapon that can be used against unintelligible
propositions. Ideas must be distinct before reason can act upon them.” 
-Thomas Jefferson 
-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 189 bytes
Desc: Dette er en digitalt underskrevet brevdel
URL: <http://listman.redhat.com/archives/fedora-devel-list/attachments/20070318/eabb054b/attachment.sig>


More information about the fedora-devel-list mailing list