Having an empty NumaNode but with CPUs attached to it (IOW they are all
offline) causes kcompile.py to raise the following exception:
calc_jobs_per_cpu():
ratio = float(mem) / float(len(self.node))
ZeroDivisionError: float division by zero
Remove nodes that do have CPUs but none of which are online.
Signed-off-by: Valentin Schneider <vschneid@xxxxxxxxxx>
---
rteval/modules/loads/kcompile.py | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/rteval/modules/loads/kcompile.py b/rteval/modules/loads/kcompile.py
index 367f8dc..ac99964 100644
--- a/rteval/modules/loads/kcompile.py
+++ b/rteval/modules/loads/kcompile.py
@@ -211,7 +211,10 @@ class Kcompile(CommandLineLoad):
# remove nodes with no cpus available for running
for node, cpus in self.cpus.items():
- if not cpus:
+ # If the intersection between the node CPUs and the cpulist is empty
+ # then either the cpulist exludes that node, or the CPUs allowed by
+ # the cpulist are actually offline
+ if not set(self.topology.nodes[node].cpus.cpulist) & set(cpus):
self.nodes.remove(node)
self._log(Log.DEBUG, "node %s has no available cpus, removing" % node)
--
2.27.0
