Re: Caching by Postgres

From: Stephen Frost
Subject: Re: Caching by Postgres
Date: ,
Msg-id: 20050824145533.GN6026@ns.snowman.net
(view: Whole thread, Raw)
In response to: Re: Caching by Postgres  (Donald Courtney)
List: pgsql-performance

Tree view

Caching by Postgres  (gokulnathbabu manoharan, )
 Re: Caching by Postgres  (John A Meinel, )
  Re: Caching by Postgres  (Josh Berkus, )
 Re: Caching by Postgres  (Bruno Wolff III, )
 Re: Caching by Postgres  (Frank Wiles, )
  Re: Caching by Postgres  (Donald Courtney, )
   Re: Caching by Postgres  (Tom Lane, )
   Re: Caching by Postgres  (Josh Berkus, )
    Re: Caching by Postgres  (Michael Stone, )
   Re: Caching by Postgres  (, )
   Re: Caching by Postgres  (William Yu, )
    Re: Caching by Postgres  (PFC, )
     Re: Caching by Postgres  (Josh Berkus, )
      Re: Caching by Postgres  (PFC, )
     Re: Caching by Postgres  (Gavin Sherry, )
      Re: Caching by Postgres  (Tom Lane, )
       Re: Caching by Postgres  (Gavin Sherry, )
    Re: Caching by Postgres  (Donald Courtney, )
     Re: Caching by Postgres  (Stephen Frost, )
     Re: Caching by Postgres  (, )
      Re: Caching by Postgres  (Alan Stange, )
       Re: Caching by Postgres  (, )
        Re: Caching by Postgres  (Alan Stange, )
         Re: Caching by Postgres  (, )
        Re: Caching by Postgres  (Michael Stone, )
         Re: Caching by Postgres  (, )
       Re: Caching by Postgres  (PFC, )
      Re: Caching by Postgres  (Thomas Ganss, )
     Re: Caching by Postgres  (William Yu, )
 Re: Caching by Postgres  (Chris Browne, )
 Re: Caching by Postgres  (Chris Browne, )

* Donald Courtney () wrote:
> To be clear -
> I built postgreSQL 8.1 64K bit on solaris 10 a few months ago
> and side by side with the 32 bit postgreSQL build saw no improvement.
> In fact the 64 bit result was slightly lower.

That makes some sense actually.  It really depends on what you're doing
alot of the time.  On a Sparc system you're not likely to get much of a
speed improvment by going to 64bit (unless, maybe, you're doing lots of
intensive 64bit math ops).  You'll have larger pointers and whatnot
though.

> I used  the *same 64 bit S10 OS* for both versions.  I think your
> experience makes sense since your change was from 32 to 64 bit Linux.

32bit to 64bit Linux on a Sparc platform really shouldn't affect
performance all that much (I'd expect it to be similar to 32bit to 64bit
under Solaris actually, at least in terms of the performance
difference).  32bit to 64bit Linux on an amd64 platform is another
matter entirely though, but not because of the number of bits involved.

Under amd64, 32bit is limited to 32bit on i386 which has a limited
number of registers and whatnot.  Under amd64/64bit you get more
registers (and I think some other niceities) which will improve
performance.  That's not a 32bit vs. 64bit thing, that's i386 vs. native
amd64.  It's really mainly an oddity of the platform.  On a mips system
I'd expect the same kind of performance difference between 32bit and
64bit as you'd see on a sparc platform.

    Enjoy,

        Stephen

Attachment

pgsql-performance by date:

From: "Lance Obermeyer"
Date:
Subject: Re: Read/Write block sizes
From: PFC
Date:
Subject: Re: Caching by Postgres