I'm running a piece of software that forks transient children frequently
on a Quad Xeon running 2.2.12, and after some time (and several tens of
thousands of tasks), the machine complains of running out of tasks. For
example, I have the default 512 procs, and there'll be some 120 tasks
running, and the entire system will be unable to fork.
Does anyone have any ideas on this? I haven't yet determined if the
count correctly corresponds to the number of tasks on the free list, but I
plan on trying that at the next crash.
Here's some info:
[root@chimera /proc]# ps -ef | wc; cat loadavg
151 1352 9993
1.75 1.77 1.84 2/643 25951
[root@chimera /proc]#
Many thanks,
Curtis
P.S. Please CC me on reply or info request.
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/