Date: Thu, 16 Dec 1999 09:14:07 -0500 (EST)
From: Ingo Molnar <[EMAIL PROTECTED]>
the 4-CPU box is up and running ever since removing those
printk's. 3 weeks uptime and no SMP-specific problems. Any
suggestion/patch to debug the printk problem is welcome.
What you could do is somehow trace to the exact thing which
causes the secondary processor to hang. You could do something
clever like print dots on the serial console or real graphics
console at strategic places, and keep jumbling them around until
you determine the precise place.
Also Ingo, could you send me 'prtconf -pv' from the machine?
I can use that to obtain CPU revision numbers and figure out
if there is some hardware bug which needs a workaround which
we have not implemented (some SuperSparc cpus have corrupted
L2 cache contents when booted as secondary processors, we never
have had opportunity to test a workaround so we never implemented
it, so it might what we're hitting here).
Later,
David S. Miller
[EMAIL PROTECTED]
-
To unsubscribe from this list: send the line "unsubscribe sparclinux" in
the body of the message to [EMAIL PROTECTED]
