-
Type:
Improvement
-
Resolution: Fixed
-
Priority:
Major - P3
-
Affects Version/s: None
-
Component/s: None
-
Networking & Observability
-
Fully Compatible
-
N&O 2026-03-02, N&O 2026-03-16
-
200
-
None
-
None
-
None
-
None
-
None
-
None
-
None
FTDC includes histograms for reactor thread run/wait times, but the buckets are too large to be usable, and there are potentially too many buckets. For instance, the second largest bucket is 1-50ms, but these tasks are meant to have nearly 0 run and wait times. Even 1ms is major degradation, but 50x that is significantly worse. And beyond 50ms is almost reaching unavailability, so bucketing higher than that is less valuable.
If possible (and it may not be due to the schema change), we should consider realigning these buckets to be more useful in understanding reactor thread execution behavior.
- is related to
-
SERVER-120311 determine if t2 changes are needed due to ExecutorStats changes
-
- Open
-
- related to
-
-
- Closed
-
-
-
- Closed
-