Re: [PATCH] Re: Negative scalability by removal of lock_kernel()?(Was: Strange performance behavior of 2.4.0-test9)

From: kumon@flab.fujitsu.co.jp
Date: Thu Nov 02 2000 - 07:50:08 EST

kumon@flab.fujitsu.co.jp writes:
> Your last patch makes the problem very clear.
>
> 2.4.0-test10-pre5 with the LIFO patch (P3), we can't get the values.

It dies at the following line in kernel/sched.c:schedule()

move_rr_back:

        switch (prev->state & ~TASK_EXCLUSIVE) {
                case TASK_INTERRUPTIBLE:
                        if (signal_pending(prev)) {
                                prev->state = TASK_RUNNING;
                                break;
                        }
                default:
here==> del_from_runqueue(prev);
                case TASK_RUNNING:
        }

"prev" contains a run_list structure and prev->run_list.next pointed
to NULL. This caused the bus-error in __list_del().

# actually the CPU accesses address 0x4 (4 is offset to prev within
# run_list).

BTW, why this switch statement has less breaks at everywhere. 

--
Computer Systems Laboratory, Fujitsu Labs.
kumon@flab.fujitsu.co.jp
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
Please read the FAQ at http://www.tux.org/lkml/

This archive was generated by hypermail 2b29 : Tue Nov 07 2000 - 21:00:11 EST