Commit 7fbe0a4b authored by Paul Rich's avatar Paul Rich
Browse files

Merge branch '98-fix-forker-LOC' into 'develop'

fix for bug where commuincation interruption to a forker would kill its tasks

Closes #98

See merge request !59
parents 89376c7f f03d4acb
......@@ -159,7 +159,6 @@ class ProcessGroupManager(object): #degenerate with ProcessMonitor.
completed_pgs = []
now = int(time.time())
for forker in self.forkers:
completed[forker] = []
try:
child_data = ComponentProxy(forker).get_children("process group", None)
except ComponentLookupError, e:
......@@ -168,11 +167,13 @@ class ProcessGroupManager(object): #degenerate with ProcessMonitor.
_logger.error("unexpected exception while getting a list of children from the %s component",
forker, exc_info=True)
else:
completed[forker] = []
for child in child_data:
children[(forker, child['id'])] = child
#clean up orphaned process groups
for pg in self.process_groups.values():
if pg.forker in completed:
if now < pg.startup_timeout:
#wait for startup timeout. We don't want any hasty kills
continue
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment