| From: | Jeff Janes <jeff(dot)janes(at)gmail(dot)com> |
|---|---|
| To: | Vick Khera <vivek(at)khera(dot)org> |
| Cc: | Kevin Grittner <kgrittn(at)ymail(dot)com>, Carlos Henrique Reimer <carlos(dot)reimer(at)opendb(dot)com(dot)br>, "pgsql-general(at)postgresql(dot)org" <pgsql-general(at)postgresql(dot)org> |
| Subject: | Re: Runtime variations during day |
| Date: | 2013-02-14 17:03:21 |
| Message-ID: | CAMkU=1xhoLFYEDdTC5gzJiNNUwevpJOE-GH+Pd_ByG-n73iZ5Q@mail.gmail.com |
| Views: | Raw Message | Whole Thread | Download mbox | Resend email |
| Thread: | |
| Lists: | pgsql-general |
On Thu, Feb 14, 2013 at 5:31 AM, Vick Khera <vivek(at)khera(dot)org> wrote:
>
> On Wed, Feb 13, 2013 at 4:35 PM, Kevin Grittner <kgrittn(at)ymail(dot)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
| From | Date | Subject | |
|---|---|---|---|
| Next Message | François Beausoleil | 2013-02-14 17:09:02 | PGbouncer and batch vs real-time pools |
| Previous Message | Craig Ringer | 2013-02-14 16:57:01 | Re: BUG #7493: Postmaster messages unreadable in a Windows console |