Remove replication prioritization

Code Issues Proposed changes

Turns out this prioritization causes stampedes right after capacity
additions (especially on smaller clusters), which means the things it
prioritizes don't get done for several passes anyway, which means the
prioritization isn't solving the problem it was designed to do, and
it causes non-productive load spikes instead. :/
Getting rid of the prioritization doesn't make things go any slower
overall, could make things actually go faster since there are less
collisions, and evens out the load.
Change-Id: I4938bcd12d9a21fad635cfe772897e4c151f8a95

This commit is contained in:

gholt

2012年10月19日 00:50:25 +00:00

parent 4c76f3dc3c

commit 25ee63a943

1 changed files with 0 additions and 2 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

2
swift/obj/replicator.py

View File

@@ -589,8 +589,6 @@ class ObjectReplicator(Daemon):

except ValueError, OSError:

continue

random.shuffle(jobs)

# Partititons that need to be deleted take priority

jobs.sort(key=lambda job: not job['delete'])

self.job_count = len(jobs)

return jobs

Remove replication prioritization

2 swift/obj/replicator.py Unescape Escape View File

2
swift/obj/replicator.py

View File