[zfs-discuss] Improving read IOPS on RAIDZ

Gordan Bobic gordan.bobic at gmail.com
Thu Apr 28 09:08:53 EDT 2016


On Thu, Apr 28, 2016 at 2:01 PM, Edward Ned Harvey (zfsonlinux) via
zfs-discuss <zfs-discuss at list.zfsonlinux.org> wrote:

> > From: zfs-discuss [mailto:zfs-discuss-bounces at list.zfsonlinux.org] On
> Behalf
> > Of Hans Henrik Happe via zfs-discuss
> >
> > I had hoped that turning off checksumming would make RAIDZ give similar
> > read IOPS as traditional RAID,
>
> Why would you believe raidz has lower read iops than hardware raid? I
> believe your presumption is false.
>


Because hardware RAID uses per-disk blocks. ZFS blocks are the equivalent
of RAID stripes (block size * number of data bearing disks). So reading a
ZFS block is equivalent of reading the entire RAID stripe, which consumes
I/O of all disks involved.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://list.zfsonlinux.org/pipermail/zfs-discuss/attachments/20160428/50abc4d3/attachment.html>


More information about the zfs-discuss mailing list