On Tue, Oct 30, 2012 at 02:16:57PM +0100, Albe Laurenz wrote:
> ktm@rice.edu wrote:
> >>> If you do not have good random io performance log replay is nearly
> >>> unbearable.
> >>>
> >>> also, what io scheduler are you using? if it is cfq change that to
> >>> deadline or noop.
> >>> that can make a huge difference.
> >>
> >> We use the noop scheduler.
> >> As I said, an identical system performed well in load tests.
>
> > The load tests probably had the "important" data already cached.
> Processing
> > a WAL file would involve bringing all the data back into memory using
> a
> > random I/O pattern.
>
> The database is way too big (1 TB) to fit into cache.
>
> What are "all the data" that have to be brought back?
> Surely only the database blocks that are modified by the WAL,
> right?
>
> Yours,
> Laurenz Albe
>
Right, it would only read the blocks that are modified.
Regards,
Ken