Thread: Shared Buffers

Siddharth Shah wrote:
>
> Hello All,
> How Postgres Maintains data in Shared Buffer
>
> Does It maintains queried data in memory or table data and Next time
> how postgres fetch data from memory
> rather than disk
> Which algorithm is used for storing data how data is indexed in shared
> buffers
>
> Thanks
> Siddharth
Take a look at

http://www.westnet.com/~gsmith/content/postgresql/InsideBufferCache.pdf

http://postgresql.mirrors-r-us.net/files/documentation/books/aw_pgsql/hw_performance/node3.html

--Ashish

On Mon, Mar 2, 2009 at 1:31 PM, Ashish Karalkar <ashishka@synechron.com> wrote:

> Take a look at
>
> http://www.westnet.com/~gsmith/content/postgresql/InsideBufferCache.pdf
>
> http://postgresql.mirrors-r-us.net/files/documentation/books/aw_pgsql/hw_performance/node3.html

Wouldn't it be nice, to have any presentation's like that one made by
Greg, in wiki, or part of devel docs ?


--
GJ

On Mon, Mar 2, 2009 at 7:40 AM, Gauthier, Dave <dave.gauthier@intel.com> wrote:
> I believe that op system side buffering can play a role too.  I our case,
> the DB server (machine & op sys) caches data that it pulled from disk (not
> necessarily from a DB) and also the disk servers do the same.  If a block
> was removed from the DB buffer cache to accommodate more recently requested
> data, but the evicted block is live in memory on the DB server or the disk
> server, it can pull from there instead of performing an expensive disk-IO.

This is very true for certain workloads.  If your db is bigger than
memory, and you only work on a tiny bit at a time, the kernel is often
better at caching than pgsql.  Run something like pgbench on a machine
with say 4 Gig of memory and a 40 Gig pgbench db dir, and you're
better off with 128M or something for shared_buffers than 1G often
times.  Truly random small access, has, for me, worked better with
moderate to smaller shared_buffers.  Plus if you need to run a few
memory hog queries, the kernel can flush out some free memory from
cache quickly, but shared_buffers is static.  So, the kernel file
cache is self tuning.

But you'll have to test it with your application to really see.