Updated ashift optimization patch

[Justin T. Gibbs]

On Aug 19, 2013, at 2:48 PM, Richard Yao <ryao at gentoo.org> wrote:

> On 08/18/2013 10:26 PM, Justin T. Gibbs wrote:>> One thing we did here,
> which would be good to see in this patch, is to add
>>> an overall min system ashift as thie enables admins to configure pools
>>> to be compatible with future disks they are likely to use e.g. min ashift
>>> 12 (4k compatible). This could be left at 9 by default for max
> compatibility
>>> but personally I'd suggest 12.
>> 
>> it would be nice to hear more consensus come out of the recent zpool
> ashift discussions before doing something here.  Whatever that is, I
> agree that the default should be 9 until someone fixes the RAIDZ space
> penalty for going to 4k on 512N drives.
>> 
>> --
>> Justin
>> 
> 
> The default ashift is determined dynamically per top-level vdev by the
> highest block_size reported by any member at creation time. There is no
> fixed default ashift. However, many drives lie, so it could appear that way.

The change Steven is proposing would set a system wide *minimum* ashift for new pools.  This would only come into play on devices reporting an ashift smaller than the set minimum.

--
Justin
-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 495 bytes
Desc: Message signed with OpenPGP using GPGMail
URL: <http://lists.freebsd.org/pipermail/zfs-devel/attachments/20130820/5f76513c/attachment.sig>