On Thu, Jan 28, 2010 at 2:06 AM, Gabor Gombas [off-list ref] wrote:

On Wed, Jan 27, 2010 at 10:16:12PM -0500, Yuehai Xu wrote:

quoted

md0 : active raid5 sdh1[7] sdg1[5] sdf1[4] sde1[3] sdd1[2] sdc1[1] sdb1[0]
      631353600 blocks level 5, 64k chunk, algorithm 2 [7/6] [UUUUUU_]

[...]

Do you mean there is something wrong when I setup my RAID5? The
command I use to setup RAID5 is:
mdadm --create /dev/md0 --level=5 --raid-devices=7 /dev/sdb1 /dev/sdc1
/dev/sdd1 /dev/sde1 /dev/sdf1 /dev/sdg1 /dev/sdh1

I don't think any of my drive fail because there is no "F" in my
/proc/mdstat output

quoted

Then I start IOZONE which starts 10 processes to do the sequential
read(iozone -i 1). Each process read 640M file on each partition. The
throughput of RAID0 is about 180M/s, while the throughput of RAID5 is
just 43M/s. Why the performance between RAID0 and RAID5 is so
different?

You have a degraded RAID5 array with one drive missing, meaning the data
has to be recalculated from parity all the time. That obviously kills
performance.

Gabor

How do you know my RAID5 array has one drive missing? I tried to setup
RAID5 with 5 disks, 3 disks, after each setup, recovery has always
been done. However, if I format my md0 with such command:
mkfs.ext3 -b 4096 -E stride=16 -E stripe-width=*** /dev/XXXX, the
performance for RAID5 becomes usual, at about 200~300M/s.

--
    ---------------------------------------------------------
    MTA SZTAKI Computer and Automation Research Institute
               Hungarian Academy of Sciences
    ---------------------------------------------------------

--
To unsubscribe from this list: send the line "unsubscribe linux-raid" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html