| From: | Andres Freund <andres(at)anarazel(dot)de> |
|---|---|
| To: | Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us> |
| Cc: | Jeff Janes <jeff(dot)janes(at)gmail(dot)com>, Robert Haas <robertmhaas(at)gmail(dot)com>, Bruce Momjian <bruce(at)momjian(dot)us>, pgsql-hackers(at)postgresql(dot)org, Heikki Linnakangas <heikki(dot)linnakangas(at)enterprisedb(dot)com> |
| Subject: | Re: profiling connection overhead |
| Date: | 2010-11-30 07:21:29 |
| Message-ID: | 201011300821.30383.andres@anarazel.de |
| Views: | Raw Message | Whole Thread | Download mbox | Resend email |
| Thread: | |
| Lists: | pgsql-hackers |
On Monday 29 November 2010 19:10:07 Tom Lane wrote:
> Jeff Janes <jeff(dot)janes(at)gmail(dot)com> writes:
> > Are you sure you haven't just moved the page-fault time to a part of
> > the code where it still exists, but just isn't being captured and
> > reported?
>
> I'm a bit suspicious about that too. Another thing to keep in mind
> is that Robert's original program doesn't guarantee that the char
> array is maxaligned; though reasonable implementations of memset
> should be able to use the same inner loop anyway for most of the
> array.
Yes, I measured the time including mmap itself. I don't find it surprising its
taking measurably shorter as it can just put up the mappings without
explicitly faulting for each and every page. The benefit is too small to worry
though, so ...
The answer to Robert includes the timings + test program.
Andres
| From | Date | Subject | |
|---|---|---|---|
| Next Message | Heikki Linnakangas | 2010-11-30 07:34:04 | Re: crash-safe visibility map, take three |
| Previous Message | Marti Raudsepp | 2010-11-30 05:50:55 | Re: DELETE with LIMIT (or my first hack) |