On Thu, Feb 14, 2013 at 5:31 AM, Vick Khera <vivek@khera.org> wrote:
>
> On Wed, Feb 13, 2013 at 4:35 PM, Kevin Grittner <kgrittn@ymail.com> wrote:
>>
>> seq_page_cost = 0.1
>> random_page_cost = 0.1
>
>
> Is there any gain in setting these to the same low value, as it would to
> leave them both at 4? I thought they are just relative numbers to each
> other.
They are also relative to all the cpu cost parameters as well to each other.
> And unless you're on SSD, these numbers seem way too low, and
> probably shouldn't be the same.
He said all his data is in RAM. If that is truly the case, these
parameters are basically just more CPU-like parameters--representing
the cost of reading from main memory into on-CPU cache, for example.
Cheers,
Jeff