no longer get the size of the gather set

* Before, we would get the min and max pk of the set we are to gather.
This changeset removes that.
* Before, we would, basically, know the size of the set we are to gather
and would query 100,000 of those job event records at a time. That logic
is now gone.
* Now, for unpartitioned job events we gather 4 hours at a time by
created time.
* Now, for partitioned job events we gather 4 hours at a time by
modified time.
This commit is contained in:
Chris Meyers
2021-05-06 14:50:49 -04:00
committed by Jim Ladd
parent 137111351c
commit 1c97b9a046
2 changed files with 14 additions and 41 deletions

View File

@@ -270,7 +270,8 @@ def gather(dest=None, module=None, subset=None, since=None, until=None, collecti
if not files:
if collection_type != 'dry-run':
with disable_activity_stream():
last_entries[key] = max(last_entries[key], end) if last_entries.get(key) else end
entry = last_entries.get(key)
last_entries[key] = max(entry, end) if entry and type(entry) == type(end) else end
settings.AUTOMATION_ANALYTICS_LAST_ENTRIES = json.dumps(last_entries, cls=DjangoJSONEncoder)
continue
@@ -293,7 +294,8 @@ def gather(dest=None, module=None, subset=None, since=None, until=None, collecti
if slice_succeeded and collection_type != 'dry-run':
with disable_activity_stream():
last_entries[key] = max(last_entries[key], end) if last_entries.get(key) else end
entry = last_entries.get(key)
last_entries[key] = max(entry, end) if entry and type(entry) == type(end) else end
settings.AUTOMATION_ANALYTICS_LAST_ENTRIES = json.dumps(last_entries, cls=DjangoJSONEncoder)
except Exception:
succeeded = False