Re^3 : Solaris Performance - 64 bit puzzle
Re^3 : Solaris Performance - 64 bit puzzle
От:
Mark kirkwood <markir@slingshot.co.nz>
Дата:
>What I'm now puzzled about is why just exercising the right kind of >sort didn't exhibit the slowdown. I wonder if the size of your sorted dataset ( i.e. all 1000000 rows) is the reason - too big to fit into sort_mem, so that temporary files are needed. The resulting file management *may* have obscured the difference in sort speed - although that does not explain how your resuts were consistently *faster* for the Solaris qsort. regards Mark
Re: Re^3 : Solaris Performance - 64 bit puzzle
От:
Andrew Sullivan <andrew@libertyrms.info>
Дата:
On Wed, Jun 05, 2002 at 08:50:09PM +1200, Mark kirkwood wrote:
>
> >What I'm now puzzled about is why just exercising the right kind of
> >sort didn't exhibit the slowdown.
>
> I wonder if the size of your sorted dataset ( i.e. all 1000000 rows) is
> the reason - too big to fit into sort_mem, so that temporary files are
Good point. That's probably it. I should think harder when
doing one-off tests, because I didn't tune the system at all.
> in sort speed - although that does not explain how your resuts were
> consistently *faster* for the Solaris qsort.
True.
A
--
----
Andrew Sullivan 87 Mowat Avenue
Liberty RMS Toronto, Ontario Canada
M6K 3E3
+1 416 646 3304 x110
