On Sun, Jan 03, 2010 at 08:26:47PM -0800, Richard Elling wrote:
> On Jan 3, 2010, at 4:05 PM, Jack Kielsmeier wrote:
> >
> >With L2arc, no such redundancy is needed. So, with a $100 SSD, if
> >you can get 8x the performance out of your dedup'd dataset, and you
> >don't have to worry about "what if the device fails", I'd call that
> >an awesome investment.
>
> AFAIK, the L2ARC is not persistent.
Correct, until this CR is fixed:
6662467 L2ARC content to survive reboots
http://bugs.opensolaris.org/bugdatabase/view_bug.do?bug_id=6662467
Please don't ask for a specific ETA - I can't give one yet.
Brendan
> This is not much of a problem for
> servers,
> which tend to stay up for long periods of time.
>
> Upon reboot, there will be a lot of random reads as the DTT is reloaded.
> -- richard
>
> _______________________________________________
> zfs-discuss mailing list
> zfs-discuss@opensolaris.org
> http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
--
Brendan Gregg, Sun Microsystems Fishworks. http://blogs.sun.com/brendan
_______________________________________________
zfs-discuss mailing list
zfs-discuss@opensolaris.org
http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
