-
Type: Improvement
-
Resolution: Fixed
-
Priority: Critical - P2
-
Affects Version/s: None
-
Component/s: Performance
-
None
-
Fully Compatible
-
Not Needed
We observed a significant regression in the ycsb_100read benchmark (see ycsb-mongodb/workloads/workloadc and dsi/configurations/test_control/test_control.ycsb.yml). Just to give a perspective, the throughput dropped from 55k for 4.2.0, to 36k for 4.3.0, to 19k for 4.4.0 when the ycsb_100read benchmark is run against a single-node MongoDB replica set.
- causes
-
JAVA-4462 Introduce a benchmark that could have sensed JAVA-4452
- Backlog
- depends on
-
JAVA-4451 Fix the await condition in OpenConcurrencyLimiter.acquirePermitOrGetAvailableOpenedConnection
- Closed
- is caused by
-
JAVA-3927 Rate limit new connection creations (maxConnecting)
- Closed
-
JAVA-3928 Connection pool paused state
- Closed
- related to
-
JAVA-4454 Introduce checking benchmark results as part of the release process
- Closed
-
JAVA-5680 Investigate connection pool scaling limitation
- Investigating
- links to