This is NOT a kernel bug, it was my fault:
the file handle was created before the fork(),
so the flock()-locks were shared by all child processes.
Result: 100 processes to get one flock():
- loadavg ~ 90
- (in another console): "ls /proc" takes nearly 7 seconds.
Thanks for you quick reply,
Manfred
-
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/