Hi,
I'm having bad luck with the AMD Quartet machines currently. Due to the 4 memory controllers I had to take out quite some debug messages from auto.c to get it compile, but I don't really get to that point anyways..
all I get is the following:
LinuxBIOS-1.1.0Fallback Do Aug 7 16:05:24 CEST 2003 starting... setting up resource map.... done. Enabling routing table for node 00000000 done. Enabling SMP settings setup_remote_node setup_remote_done Renaming current temp node to 00000001 done. Enabling routing table for node 00000001 done. [long delay here] Renaming current temp node to 00000002 [long delay here] done. Enabling routing table for node 00000002 [long delay here, then reset:]
LinuxBIOS-1.1.0Fallback Do Aug 7 16:05:24 CEST 2003 starting... setting up resource map.... done. Enabling routing table for node 00000000 done. Enabling SMP settings [complete hang]
this worked some time ago in CVS, but I don't know when it stopped.
Can the resource map cause these problems? I dumped the resource map I am using from a different quartet machine, and now I get the same problems than I had before with the default resource map.
It looks to me like it's a bad idea[tm] to set the resource map at all before knowing anything about the machine's resources.
debugging... Stefan
* Stefan Reinauer stepan@suse.de [030807 16:19]:
Can the resource map cause these problems? I dumped the resource map I am using from a different quartet machine, and now I get the same problems than I had before with the default resource map.
This time it's different trouble. Seems some changes in coherent_ht.c did not like the quartet too well...
Stefan
On Thu, 7 Aug 2003, Stefan Reinauer wrote:
It looks to me like it's a bad idea[tm] to set the resource map at all before knowing anything about the machine's resources.
Is this the right time to fill out the "probe" and "present" stuff that Greg mentioned for the static cpu map?
ron
-
ron minnich -
Stefan Reinauer