[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index][Old Index]
Re: Possible pthreads memory leak
On Sun, 17 Jan 2010 09:47:03 +0000 (UTC)
mlelstv%serpens.de@localhost (Michael van Elst) wrote:
> and the pullup to netbsd-5 branch occured 6 days ago...
> 2010-01-11 01:47 snj
> * pthread.c (22.214.171.124): Pull up following revision(s) (requested
> by christos in ticket #1235): lib/libpthread/pthread.c:
> revision 1.113 Don't just look only at the first element in the
> deadqueue to find lwp's to reuse, because if we lose the race
> with the kernel we are never going to reuse any elements. Look in
> the whole list instead.
ident(1) shows that I have 126.96.36.199, so my tests were done with the
fix applied. This probably explains the more serious leaks Zach
experiences on 5.0.1. Is it still expected that without inserting a
syscall to cause a context switch a small leak still occurs over time
with the fix?
I realize that in real world scenarios this probably does not matter
very much, however. An application would need to be totally CPU-bound
and to at the same time need to always create new threads without
making any voluntary context switches, while such number-crunching
applications probably initially allocate a number of threads and keep
them alive for optimal performance...
Main Index |
Thread Index |