For the archives...
On Apr 16, 2012, at 3:37 PM, Peter Jeremy wrote:
> On 2012-Apr-14 02:30:54 +1000, Tim Cook <t...@cook.ms> wrote:
>> You will however have an issue replacing them if one should fail. You need
>> to have the same block count to replace a device, which is why I asked for a
>> "right-sizing" years ago.
> The "traditional" approach this is to slice the disk yourself so you have a
> slice size with a known area and a dummy slice of a couple of GB in case a
> replacement is a bit smaller. Unfortunately, ZFS on Solaris disables the
> drive cache if you don't give it a complete disk so this approach incurs as
> significant performance overhead there. FreeBSD leaves the drive cache
> enabled in either situation. I'm not sure how OI or Linux behave.
Write-back cache enablement is toxic for file systems that do not issue cache
flush commands, such as Solaris' UFS. In the early days of ZFS, on Solaris 10 or
before ZFS was bootable on OpenSolaris, it was not uncommon to have ZFS and
UFS on the same system.
NB, there are a number of consumer-grade IDE/*ATA disks that ignore disabling
the write buffer. Hence, it is not always a win to enable the write buffer that
ZFS Performance and Training
zfs-discuss mailing list