----- Original Message -----
From: "Xin Li" <delp...@delphij.net>
-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA256
On 8/11/13 12:03 PM, Richard Yao wrote:
Is there any possibility that these quirks could be added to the
upcoming 9.2 release?
I think so but we need to act fast.
Pools composed of affected disks will suffer from performance
issues until they are reformatted with the correct block size. In
addition, a certain benchmarking site, whose benchmarks are often
fodder for trolls, uses the Intel X25-M in its benchmarks. Adding
the quirk to 9.2 would eliminate an unfair handicap on FreeBSD from
their next set of benchmarks.
Actually I'm not 100% sure here: the current FreeBSD ZFS code does not
handle stripesize at all, and thus if you create a pool with the
patch, they will still be ashift=9. Justin (gibbs@) have a patchset
to address this by the way, but since it's not yet in HEAD I wouldn't
expect it be incorporated in 9.2...
Indeed, there is nothing which really makes proper use of QUIRKS that
I'm aware of and ZFS definitely doesn't.
There's a number of patches around which correct that, I've one here
too, but none as yet are a total solution to the ashift issue.
Regards
Steve
================================================
This e.mail is private and confidential between Multiplay (UK) Ltd. and the person or entity to whom it is addressed. In the event of misdirection, the recipient is prohibited from using, copying, printing or otherwise disseminating it or any information contained in it.
In the event of misdirection, illegible or incomplete transmission please
telephone +44 845 868 1337
or return the E.mail to postmas...@multiplay.co.uk.
_______________________________________________
freebsd-hackers@freebsd.org mailing list
http://lists.freebsd.org/mailman/listinfo/freebsd-hackers
To unsubscribe, send any mail to "freebsd-hackers-unsubscr...@freebsd.org"
