Description
I've been profiling a complex streams job, and found two major hotspots when writing metrics, which take up about 60% of the CPU time of the job. A PR is attached.
Attachments
Issue Links
- relates to
-
KAFKA-3826 Sampling on throughput / latency metrics recording in Streams
- Resolved
-
KAFKA-3785 Fetcher spending unnecessary time during metrics recording
- Resolved
- links to