> I have a similar proble, but it's caused after a kernel oops (possibly due
> to a bug in DMSDOS, not the kernel but its definately started in 2.2.1),
> after that, any program which accesses the directory the 'oopsed' program
> was accessing hangs, and slowly but surely my load av creeps up and
> eventually (after about 9 hours) my load average was at 56, and when I
> tried to start X everything ran out of memory...
Well, that's a different story. The first oops left the
semaphore on directory inode held. All processes that tried to access it
after that tried to grab the same semaphore and slept down
(uninterruptably). The rest is obvious.
-
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/