Page 2 of 2

Re: 1.5.2 usage impact

PostPosted: Wed Jun 08, 2016 10:39 am
by haer22
I'm going for skein when I will re-create my quirky 15TB pool this evening. So I will use your config

tangles wrote:so, should we suggest a "speed" config/option in the documentation of:
Code: Select all
 sudo zpool create -f -o ashift=12 -O compression=skein -O casesensitivity=insensitive -O atime=off -O normalization=formD tank mirror disk3 disk4


I saw that edon-R has some issues...
https://www.listbox.com/member/archive/ ... FD97918BF/

Mr Lundy? yr expertise please... :geek: :D

Re: 1.5.2 usage impact

PostPosted: Wed Jun 08, 2016 10:40 pm
by lundman
First comment about SIMD, we are somewhat lucky that in XNU kernel we can mix SIMD with regular without any hoop-jumping, so we can vectorise our algorithms at any time. None of them are at the moment though. I was looking at the fletcher avx2 code from ZOL, but realised my hardware does not have AVX2 so I am unable to test it anyway.

As for EDON-R, the cryptographical concerns are probably valid, but it is only used as checksum in ZFS, so worries about collisions are probably not as drastic. But who knows.

Re: 1.5.2 usage impact

PostPosted: Thu Jun 09, 2016 1:45 pm
by haer22
And i guess you meant "checksum=skein" instead of "compression=skein".

tangles wrote:so, should we suggest a "speed" config/option in the documentation of:
Code: Select all
 sudo zpool create -f -o ashift=12 -O compression=skein -O casesensitivity=insensitive -O atime=off -O normalization=formD tank mirror disk3 disk4


I saw that edon-R has some issues...
https://www.listbox.com/member/archive/ ... FD97918BF/

Mr Lundy? yr expertise please... :geek: :D

Re: 1.5.2 usage impact

PostPosted: Tue Jun 14, 2016 4:57 am
by tangles
ah... yep... :oops:

Did have a pint in my hand at the time when I hit the submit button.

Might have something to do with it :roll: