[OpenIndiana-discuss] Fileserver performance with log and cache devices?

[Gary Mills]

On Fri, Dec 02, 2011 at 09:34:17PM +0100, Per Sjoholm wrote:
> On 12/02/2011 07:44 PM, Gary Mills wrote:
> >On Thu, Dec 01, 2011 at 08:59:48AM -0600, Gary Mills wrote:
> >>I'm in the process of setting up a fileserver running oi_151a.  How
> >>can I determine the performance improvement from adding log and cache
> >>devices?  I'm using filebench with the fileserver personality.  Is
> >>that my best choice?  So far, I've tried filebench directly on the
> >>server and also on an NFS client.  What statistics should I be
> >>watching?
> >So, can nobody answer my questions?
> >
> http://constantin.glez.de/blog/2011/02/frequently-asked-questions-about-flash-memory-ssds-and-zfs
> # How Do I Know if an SSD Will Really Help My Write Performance? <http://constantin.glez.de/blog/2011/02/frequently-asked-questions-about-flash-memory-ssds-and-zfs#write>
> # How Do I Know if an SSD Will Really Help My Read Performance? <http://constantin.glez.de/blog/2011/02/frequently-asked-questions-about-flash-memory-ssds-and-zfs#read>

Thanks.  That article provides me with plenty of leads.  It looks as
if I should use filebench only a load generator, ignoring the
statistics that it produces.  Then I should use Richard Elling's
zilstat to evaluate synchronous write performance and Ben Rockwood's
arc_summary to evaluate read performance.  I can certainly do that.

-- 
-Gary Mills-		-refurb-		-Winnipeg, Manitoba, Canada-