On Mon, Sep 25, 2006 at 08:37:23AM -0700, Neelakanth Nadgir wrote:
> We did an experiment where we placed the logs on UFS+DIO and the
> rest on ZFS. This was a write heavy benchmark. We did not see
> much gain in performance by doing that (around 5%). I suspect
> you would be willing to trade 5% fo
We did an experiment where we placed the logs on UFS+DIO and the
rest on ZFS. This was a write heavy benchmark. We did not see
much gain in performance by doing that (around 5%). I suspect
you would be willing to trade 5% for all the benefits of ZFS.
Moreover this penalty is for the current versio
[EMAIL PROTECTED] writes:
> On Fri, Sep 22, 2006 at 03:38:05PM +0200, Roch wrote:
> >
> >
> >http://blogs.sun.com/roch/entry/zfs_and_oltp
>
> After reading this page and taking into consideration my (not so big)
> knowledge
> of ZFS it came to my mind that putting e.g. Oracle on bo
On Fri, Sep 22, 2006 at 03:38:05PM +0200, Roch wrote:
>
>
> http://blogs.sun.com/roch/entry/zfs_and_oltp
After reading this page and taking into consideration my (not so big) knowledge
of ZFS it came to my mind that putting e.g. Oracle on both UFS+DIO _and_
ZFS would be the best solution _
http://blogs.sun.com/roch/entry/zfs_and_oltp
Performance, Availability & Architecture Engineering
Roch BourbonnaisSun Microsystems, Icnc-Grenoble
Senior Performance An
