-
Type:
Task
-
Resolution: Duplicate
-
Priority:
Major - P3
-
None
-
Affects Version/s: None
-
Component/s: None
-
None
-
Catalog and Routing
-
CAR Team 2025-07-07
-
None
-
3
-
TBD
-
None
-
None
-
None
-
None
-
None
-
None
-
None
The main idea is to run stress workloads to determine a baseline for the following metrics when a shard in the cluster is at its limit:
- Read/write throughput
- Read/write latency
- CPU utilization
- I/O rate
Then, we stop the non-critical maintenance operations for that shard, and see the impact of this in the metrics specified above.