| From: | Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us> |
|---|---|
| To: | Chris Travers <chris(at)metatrontech(dot)com> |
| Cc: | pgsql-general <pgsql-general(at)postgresql(dot)org> |
| Subject: | Re: Thousands of parallel connections |
| Date: | 2004-08-17 00:32:08 |
| Message-ID: | 24083.1092702728@sss.pgh.pa.us |
| Views: | Raw Message | Whole Thread | Download mbox | Resend email |
| Thread: | |
| Lists: | pgsql-general |
Chris Travers <chris(at)metatrontech(dot)com> writes:
> Tom Lane wrote:
>> That does not add up: the graph can't have a negative y-intercept.
>> There should be a substantial cost to run the postmaster at all,
>> and then an essentially fixed cost per connection --- assuming
>> that all the connections are running similar queries, of course.
>> You're telling us the first 40 connections require zero RAM.
> That is strange. Is it really linear or does the cost go up somewhat
> after the first few?
Well, if you have significant contention problems then the speed could
be worse than linear --- but he was talking about memory usage. AFAICS,
a backend doing a particular query should need X amount of RAM pretty
much independently of how many others there are. The only data structure
I can think of that would be impacted at all is QuerySnapshot, and at
4 bytes per sibling backend it's *way* down in the noise...
regards, tom lane
| From | Date | Subject | |
|---|---|---|---|
| Next Message | Chris Travers | 2004-08-17 00:42:17 | Re: Thousands of parallel connections |
| Previous Message | Glen Parker | 2004-08-17 00:30:00 | pg_clog and pg_xlog empty, postgresql refuses to start |