From: | Scott Marlowe <scott(dot)marlowe(at)gmail(dot)com> |
---|---|
To: | "M(dot) Edward (Ed) Borasky" <znmeb(at)cesmail(dot)net> |
Cc: | pgsql-performance(at)postgresql(dot)org |
Subject: | Re: [PERFORMANCE] Buying hardware |
Date: | 2009-01-28 20:03:25 |
Message-ID: | dcc563d10901281203w50e7346alec09ad75020a6ec5@mail.gmail.com |
Views: | Raw Message | Whole Thread | Download mbox | Resend email |
Thread: | |
Lists: | pgsql-performance |
On Tue, Jan 27, 2009 at 7:03 AM, M. Edward (Ed) Borasky
<znmeb(at)cesmail(dot)net> wrote:
> M. Edward (Ed) Borasky wrote:
>> Given large amounts of RAM and only PostgreSQL running in the server,
>> the interesting trade-offs become
>>
>> a. How little memory can you buy without putting your service level
>> agreements at risk?
>>
>> b. How do you allocate the PostgreSQL-specific memory buffers at the
>> expense of the Linux page cache for optimum performance?
>
> c. What do I do with the idle cores? :)
>
> (or, how can I exploit them by changing my database design or the
> PostgreSQL architecture?)
You run as many queries as you have cores at the same time? If you've
only ever got 1 or 2 queries running at the same time, don't buy so
many extra cores.
From | Date | Subject | |
---|---|---|---|
Next Message | Kevin Traster | 2009-01-29 07:01:34 | NOT IN >2hrs vs EXCEPT < 2 sec. |
Previous Message | Scott Marlowe | 2009-01-28 20:01:50 | Re: [PERFORMANCE] Buying hardware |