Stephen,
you will be glad to hear that the long crashing saga (at least in my
case) turns to the end.
The combination 2.6.18 / skge 1.8 is working well with SMP/IRQ
migration.
The last test which crashed was 2.6.17 / skge 1.6 + PCI posting fixes.
So some fix in 1.7/1.8 seems to make the difference
> possible PCI posting bug?
>
> --- linux-2.6.orig/drivers/net/skge.c
> +++ linux-2.6/drivers/net/skge.c
> @@ -2745,7 +2745,7 @@ static int skge_poll(struct net_device *
> spin_lock_irq(&hw->hw_lock);
> hw->intr_mask |= rxirqmask[skge->port];
> skge_write32(hw, B0_IMSK, hw->intr_
possible PCI posting bug?
--- linux-2.6.orig/drivers/net/skge.c
+++ linux-2.6/drivers/net/skge.c
@@ -2745,7 +2745,7 @@ static int skge_poll(struct net_device *
spin_lock_irq(&hw->hw_lock);
hw->intr_mask |= rxirqmask[skge->port];
skge_write32(hw, B0_IMSK, hw->intr_mask);
-
>> Stephen,
>>
>> the reproducible crashes with all skge versions (where sk98lin works
>> fine) on my box are SMP related.
>> I booted with maxcpus=1 and the box survived my usual crash test, I will
>> keep an eye.
>>
>> Daniel
>>
> Is this P3 SMP?
> What form of IRQ balance are you using?
Ind
On Wed, 16 Aug 2006 19:47:08 +0200
"Beschorner Daniel" <[EMAIL PROTECTED]> wrote:
> Stephen,
>
> the reproducible crashes with all skge versions (where sk98lin works
> fine) on my box are SMP related.
> I booted with maxcpus=1 and the box survived my usual crash test, I will
> keep an eye.
>
> D
Stephen,
the reproducible crashes with all skge versions (where sk98lin works
fine) on my box are SMP related.
I booted with maxcpus=1 and the box survived my usual crash test, I will
keep an eye.
Daniel
-
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message
