Scyld - Weird Beostatus bit here
Dean.Carpenter at pharma.com
Tue Apr 3 15:31:56 PDT 2001
This is a little odd. A while ago I had some problems with getting the SMP
kernel running properly on a test cluster here - you may recall :) One of
the dual-cpu boxes I borrowed was in the cluster as node 10, and sort of
showed up in beostatus.
That is, cpu0 and cpu1 both had % figures that would change slightly.
Because of the problems with the kernel modules, it was really a viable
situation, and so was left. That dual-cpu box was returned to its original
duty, and I deleted the MAC address (along with a couple of others also
returned) from beosetup.
Note - beostatus seems to retain the last known values for the various items
it tracks, so node 10 still showed a greyed out 5% cpu0 and 4.1% cpu1 value
Today I snagged a couple of new single-cpu machines to play with for a
couple of days, so booted them with a node diskette and watched them come up
just fine. First one popped in as the new node 10, second one as node 11,
What was not expected was that the cpu0 counter doesn't seem to track
properly. I started up an instance of distributed.net client on both nodes,
and node 11 shot to 100%, like it should. Node 10 though seems stuck at 5%,
but the other counters (mem, disk etc) all change normally.
The process is definitely running - I have it logging to the local ramdisk,
and can watch the packets gets crunched and so forth. loadavg also shows
the correct amount of utilization.
So what got left behind (and where) in beostatus' config ? How can it be
reset or cleared out ? This problem (pretty minor actually) stays around
even after a reboot of master and slaves.
dean.carpenter at pharma.com
deano at areyes.com
More information about the Beowulf