Support advanced format drives, i.e. ashift=xx

[GoogleCodeExporter]

Current large capacity hard disk tend to lie about their true physical sector 
size, claiming 512 byte sector while in fact using 4096 bytes.  This forces 
simple writes into expensive read-modify-write cycles, causing significant 
slowdown [1].

A technical clean solution (aside the drives stopping to lie) is difficult, as 
the blocksize should really be a per top-level vdev option, but that breaks the 
way properties are handled in ZFS.  While technically not fully correct, the 
approach taken by ZFSonLinux looks the least bad to me.  

I have started to port the ZFSonLinux approach to our much older code base.

[1] ZFSonLinux has performance data here: 
https://github.com/zfsonlinux/zfs/pull/280#issuecomment-1381910 

Original issue reported on code.google.com by googlelogin@bjoern-kahl.de on 5 Aug 2012 at 8:19

[GoogleCodeExporter]

I have ported the ZFSonLinux approach to our untested branch (upcoming next 
release, will move on pool version and significantly advance the code).  The 
patch is here: https://github.com/BjoKaSH/mac-zfs/tree/untested_ashift pull 
request: https://github.com/alblue/mac-zfs/pull/3

Bringing an ashift to maczfs_74, possibly as a service release maczfs_74_x, is 
much harder, since _74 misses most of the needed infrastructure.  a proposed 
solution, also besed in the ZFSonLinux approach, is here: 
https://github.com/BjoKaSH/mac-zfs/tree/ashift12 (and for the new build system: 
https://github.com/BjoKaSH/mac-zfs/tree/mfb_ashift12), the pull request is at 
https://github.com/alblue/mac-zfs/pull/2

The patch for untested should be fine, the patch for maczfs_74 needs review.

Original comment by googlelogin@bjoern-kahl.de on 11 Aug 2012 at 12:17

[GoogleCodeExporter]

Supported since MacZFS-74.3.0, released April 2, 2013.

Original comment by googlelogin@bjoern-kahl.de on 28 Jul 2015 at 9:53

• Changed state: Fixed