Re: profiling connection overhead - Mailing list pgsql-hackers

From Peter Eisentraut
Subject Re: profiling connection overhead
Date
Msg-id 1291180496.601.1.camel@vanquo.pezone.net
Whole thread Raw
In response to Re: profiling connection overhead  (Tom Lane <tgl@sss.pgh.pa.us>)
List pgsql-hackers
On tis, 2010-11-30 at 15:49 -0500, Tom Lane wrote:
> Peter Eisentraut <peter_e@gmx.net> writes:
> > On mån, 2010-11-29 at 13:10 -0500, Tom Lane wrote:
> >> Rolling in calloc in place of
> >> malloc/memset made no particular difference either, which says that
> >> Fedora 13's glibc does not have any optimization for that case as I'd
> >> hoped.
> 
> > glibc's calloc is either mmap of /dev/zero or malloc followed by memset.
> 
> Hmm.  I would have expected to see a difference then.  Do you know what
> conditions are needed to cause the mmap to be used?

Check out the mallopt(3) man page.  It contains a few tunable malloc
options that may be useful for your investigation.



pgsql-hackers by date:

Previous
From: Itagaki Takahiro
Date:
Subject: Re: SQL/MED - core functionality
Next
From: Hitoshi Harada
Date:
Subject: Re: SQL/MED - core functionality