AF (4096 byte sector) drives: Can you mix/match in a ZFS pool?

[Bob Friesenhahn]

On Thu, 13 Oct 2011, Tom Evans wrote:

> On Thu, Oct 13, 2011 at 3:27 PM, Larry Rosenman <ler at lerctr.org> wrote:
>> I think something(tm) should be put in the handbook about this.
>
> TBH I think that ZFS should just move it's default ashift to 11 and
> have 4k blocks by default. Saves all this messing around with
> temporary gnop devices.

There is a cost to using 4k blocks becaus zfs metadata will then 
consume 4k bytes (each copy) rather than 512 bytes.  As someone posted 
to the zfs-discuss list a few days ago, this consumes quite a lot of 
space when the zfs block size is set to 8K.  This results in almost 2X 
the disk space consumption when using 8K zfs block size.

There is additional performance cost because the drive will be doing 
I/O in 4K chunks rather than 512 byte chunks.

Typical SAS enterprise drives (not near-line drives) are surely still 
all using small sectors because their storage size is not very high 
and to get more IOPS.

Bob
-- 
Bob Friesenhahn
bfriesen at simple.dallas.tx.us, http://www.simplesystems.org/users/bfriesen/
GraphicsMagick Maintainer,    http://www.GraphicsMagick.org/