That's a scary low bar for comparison.
OpenSolaris (or even Solaris 11), ZFS, Stable. Pick one. Maybe two. Three? Yeah right. Anyone who's used it hard, under heavy load, should understand.
Hey guys, I am running it on freeBSD. (nas4free)
It's my understanding that when a resilver happens in a zpool, only the
data that has actually been written to the disks gets used, not the whole
array like traditional raid5 does, reading even empty blocks. I know I
should be using RAIDZ2 for this size array, but I have daily backups off of
this array and also this is a lab, not a production environment. In a
production environment I would use raidz2 or raidz3. The bottom line is
even just Raidz1 is way better than any RAID5 hardware/software solution I
have come across. 1 disk with ZFS can survive 1/8 of the disk becoming
destroyed apparently. ZFS itself has many protections against data
corruption. Also I have scheduled a zpool scrub to run twice a week (to
detect bitrot before it happens.)
Anyway. I have been using linux raid since it has been available and I ask
myself, why haven't I used ZFS seriously before now.
- J
Jon Lewis <jlewis@lewis.org> writes:
OpenSolaris (or even Solaris 11), ZFS, Stable. Pick one. Maybe
two. Three? Yeah right. Anyone who's used it hard, under heavy load,
should understand.
The most recent release of OpenSolaris was over 5 years ago. You're
working from (extremely) dated information.
The current FOSS Solaris ecosystem forked when Oracle brought stuff
back in-house. Significant development has happened over the
intervening half-decade.
Anyone who's using Nexentastor (or hosted in Joyent Cloud) is getting
all three (supra).
-r
That might be close enough. I need to set up a test system and play
around with zfs and btrfs.
Thanks.