[olug] IO Performance

[Christopher Cashell]

On Thu, Sep 15, 2011 at 9:52 AM, jay swackhamer <reboottheuser at gmail.com> wrote:
> It appears that a code-level on the IBM XIV disk array that relates to
> replication has more to do with IO performance than Linux Tuning.
>
> Now we are running batch schedules through Oracle faster than previously, so
> there was some benefit, and now I can tweak/tune these some more,
> to get to the best numbers for the workload.

At a previous job, we had some very positive results with Oracle when
we switched to the deadline IO scheduler.  That was a few years ago,
so I don't remember much in the way of specifics or numbers, but it
was enough of an improvement that we made the change on all of our
Oracle servers.

-- 
Christopher