You can test it using LD_PRELOAD just fine. Since most of the allocations use mmap() anyway (so reclamation is possible) it really isn't used enough to cause contention between cores.
-- Christian On Oct 14, 2009, at 3:47 AM, [email protected] wrote: > Very interesting Christian. Wouldn't it be worth to have it > available as > a compilation switch or something? Maybe performance varies > depending on > the test. I'm thinking on our own load tests. > > pablo > > Christian Hergert wrote: >> I've tested it in the past (extensibly during 2.4 cycle) with >> negligible >> changes in performance on 2, 4, and 8 core boxes. >> >> -- Christian >> >> On Oct 13, 2009, at 2:10 PM, Zoltan Varga wrote: >> >>> Hi, >>> >>> We use malloc for allocating runtime memory structures etc., but in >>> a server app, that >>> all happens during startup, so it doesn't help much. >>> >>> Zoltan >>> >>> On Tue, Oct 13, 2009 at 11:05 PM, [email protected] >>> <[email protected]> wrote: >>> Hi there, >>> >>> Dick and I were talking about it today and most likely it wouldn't >>> have >>> a big impact since Mono does use mmap instead but.. do you guys >>> think >>> using tcmalloc would be worth? >>> >>> http://goog-perftools.sourceforge.net/doc/tcmalloc.html >>> >>> It's not new, but I've just found it reading the MySql 5.4 release >>> notes, and it seems it helps boosting its performance >>> >>> http://mysqlha.blogspot.com/2009/01/double-sysbench-throughput-with_18.html >>> >>> >>> Would it help? >>> >>> pablo >>> _______________________________________________ >>> Mono-devel-list mailing list >>> [email protected] >>> http://lists.ximian.com/mailman/listinfo/mono-devel-list >>> >>> _______________________________________________ >>> Mono-devel-list mailing list >>> [email protected] >>> http://lists.ximian.com/mailman/listinfo/mono-devel-list >> >> _______________________________________________ Mono-devel-list mailing list [email protected] http://lists.ximian.com/mailman/listinfo/mono-devel-list
