develooper Front page | perl.perl5.porters | Postings from March 2007

Re: The performance problem of 30678

Thread Previous | Thread Next
From:
Rafael Garcia-Suarez
Date:
March 24, 2007 00:22
Subject:
Re: The performance problem of 30678
Message ID:
b77c1dce0703240022x2b888500m5a9b0e2bcbca527c@mail.gmail.com
On 23/03/07, Nicholas Clark <nick@ccl4.org> wrote:
> Yes, with PERL_DESTRUCT_LEVEL=2 Solaris now takes 2 hours to run t/op/pat.t
>
> We seem to have hit pathological malloc behaviour. I'm not quite sure how,
> or why, given that Linux copes.

Independently, I've tried google's malloc --
http://code.google.com/p/google-perftools/ -- with bleadperl. It can
be used without recompilation, LD_PRELOAD is sufficient (on Linux) if
your perl is compiled with usemymalloc=n (the default on Linux).

Without any PERL_DESTRUCT_LEVEL, t/op/pat is extremely slow. Another
hint that we hit some malloc pathological case here. strace() shows
that the tests that are slowed down are towards the end...

Thread Previous | Thread Next


nntp.perl.org: Perl Programming lists via nntp and http.
Comments to Ask Bjørn Hansen at ask@perl.org | Group listing | About