On Thu, Jul 8, 2010 at 12:46 PM, Kevin Grittner <Kevin.Grittner@xxxxxxxxxxxx> wrote:
Thanks for the explanations that makes things clearer. It still amazes me that it would account for a 5x change in IO.Ryan Wexler <ryan@xxxxxxxxxxxxxxxx> wrote:Well, it makes it safe for the controller to consider the write
> One thing I don't understand is why BBU will result in a huge
> performance gain. I thought BBU was all about power failures?
complete as soon as it hits the RAM cache, rather than waiting for
persistence to the disk itself. It can then schedule the writes in
a manner which is efficient based on the physical medium.
Something like this was probably happening on your non-server
machines, but without BBU it was not actually safe. Server class
machines tend to be more conservative about not losing your data,
but without a RAID controller with BBU cache, that slows writes down
to the speed of the rotating disks.
-Kevin
