Michael Stone wrote:
> Is it possible to tweak the size of a block that postgres tries to read
> when doing a sequential scan? It looks like it reads in fairly small
> blocks, and I'd expect a fairly significant boost in i/o performance
> when doing a large (multi-gig) sequential scan if larger blocks were
> Mike Stone
I believe postgres reads in one database page at a time, which defaults
to 8k IIRC. If you want bigger, you could recompile and set the default
page size to something else.
There has been discussion about changing the reading/writing code to be
able to handle multiple pages at once, (using something like vread())
but I don't know that it has been implemented.
Also, this would hurt cases where you can terminate as sequential scan
early. And if the OS is doing it's job right, it will already do some
read-ahead for you.
In response to
pgsql-performance by date
|Next:||From: PFC||Date: 2005-06-28 17:10:05|
|Subject: Re: Too slow querying a table of 15 million records|
|Previous:||From: John A Meinel||Date: 2005-06-28 16:25:56|
|Subject: Re: tricky query|