In-Reply-To: <20061124005528.GF11034@xxxxxxxxxxxxxxxxx>
On Fri, 24 Nov 2006 11:55:28 +1100, David Chinner wrote:
> Also, that means that while XFS is apparently only using <1500 bytes
> of stack through this path according to the static stack checker
> tool, there's more than 2k of extra stack usage that the tool is not
> telling me about. i.e. XFS and whatever is above/below it should
> have a full 4k to work with. I'd really like to know where that
> extra stack space is being used....
You could try applying the (untested) patch below and booting with
the parameter "kstack=2048", then regenerate the problem stack
traces. This should give you a complete raw stack dump in addition
to the call trace for each overflow.
(Output could get very large, so maybe adding a counter and stopping
after ~100 events might also be a good idea.)
--- 2.6.19-rc6-32smp.orig/arch/i386/kernel/irq.c
+++ 2.6.19-rc6-32smp/arch/i386/kernel/irq.c
@@ -80,7 +80,7 @@ fastcall unsigned int do_IRQ(struct pt_r
if (unlikely(esp < (sizeof(struct thread_info) + STACK_WARN))) {
printk("do_IRQ: stack overflow: %ld\n",
esp - sizeof(struct thread_info));
- dump_stack();
+ show_stack();
}
}
#endif
--
Chuck
"Even supernovas have their duller moments."
|