-
Type: Improvement
-
Resolution: Won't Fix
-
Priority: Major - P3
-
None
-
Affects Version/s: None
-
Component/s: Logging
-
None
-
(copied to CRM)
-
Storage 2017-09-11, Storage 2017-10-02
MongoDB 3.4 had an optimization when tracking commits that avoided flushing the log if transactions committed in order. To get the same behavior in 3.6, we need to track whether transactions are committing in order and use that information to optionally sync the log to disk.
- related to
-
SERVER-31679 Increase in disk i/o for writes to replica set
- Closed
-
WT-3567 Add a test case that measures oplog throughput
- Closed
- links to