[OpenIndiana-discuss] Very slow write performance on a 3 disk raidz1-0 zpool

[Jan Owoc]

Hi,


On Thu, Aug 23, 2012 at 10:32 PM, Julius Roberts
<hooliowobbits at gmail.com> wrote:
> as per the subject, I'm getting very slow write performance on a 3
> disk raidz1-0 zpool.  IIRC the disks are early 1tb WD green drives.
> Not sure what i should tell you, but during copies of large 10gb+
> files rsync is showing around 2MB/s, which is terribly poor i think.
> Sorry if this is a common question, not sure what to do.
>
> twsadmin at darling:~/mdbackup$ zpool iostat Backups 5
>                capacity     operations    bandwidth
> pool        alloc   free   read  write   read  write
> ----------  -----  -----  -----  -----  -----  -----
> Backups     2.04T   694G     97    330  2.72M  1.95M
> Backups     2.04T   694G    170    248  3.98M  1019K

How are you generating these writes? Are they maybe small files over a
wireless network? If so, what if you generated the I/O using:
dd if=/dev/zero of=/Backups/zero.file

Is this behaviour new, or did you change anything recently? (Did you
really copy over all those GBs at 2MB/s?) I'm going to rule out
underpowered system, since even an Atom should be able to do sha256
checksums and parity calculations faster than 2 MB/s.


> twsadmin at darling:~/mdbackup$ zpool status
>   pool: Backups
>  state: ONLINE
>   scan: scrub repaired 0 in 12h56m with 0 errors on Sat Aug 18 20:56:44 2012
> config:
>
>         NAME        STATE     READ WRITE CKSUM
>         Backups     ONLINE       0     0     0
>           raidz1-0  ONLINE       0     0     0
>             c3t0d0  ONLINE       0     0     0
>             c3t1d0  ONLINE       0     0     0
>             c4t1d0  ONLINE       0     0     0

This looks fine. Reading 2TB in 13h is about 45 MB/s, so about the
order of magnitude we'd expect.


Jan