[BBLISA] ZFS Anyone?

Edward Ned Harvey bblisa3 at nedharvey.com
Sat Apr 4 00:28:22 EDT 2009


> Yes, I meant that ZFS scales linearly with the number of spindles,
> essentially being able to drive them at their max throughput.  I'm not
> sure
> on your RAID 6 calculation. For reads certainly you'd scale with number
> of
> spindles (basically a striped read).  For writes, without cache, you
> would
> certainly see a large decrease from that in general. ZFS, for
> asynchronous

I'm really not sure why anyone uses raid5, raid6, raidDP, raidz, or raidz2
anymore.  I suppose it is a little cheaper ... Get the capacity of 7 or 8
disks when you purchased 10 ...  I'm heavily gravitated toward mirroring.
What many people (not quite accurately) call raid 10 ... Also not accurately
called stripe of mirrors ... More accurately, a concatenation of mirrors.
Get the capacity of 5 disks when you bought 11 (assuming you dedicate a
hotspare).

Yes, it's less GB per dollar, but much higher speed per dollar.  With much
more flexibility as well.  Wanna expand?  Just buy 2 more disks.  The new
disks don't match the size of the old disks?  No big deal.




More information about the bblisa mailing list