nzw921rx opened a new pull request, #12026: URL: https://github.com/apache/seatunnel/pull/12026
## Purpose of this pull request Add a JMH benchmark for regular Zeta checkpoint completion time without backpressure. ## Does this PR introduce any user-facing change? No. ## How was this patch tested? - ./mvnw -Pbenchmark -pl seatunnel-benchmarks spotless:apply package - java -jar seatunnel-benchmarks/target/benchmarks.jar CheckpointingTimeBenchmark -f 1 -wi 1 -w 1s -i 1 -r 1s - ./mvnw spotless:apply ## What changed - Add a dedicated two-node master/worker checkpoint benchmark environment. - Keep master and worker Hazelcast configurations separate, enable master IMap MapStore with local HDFS storage, and set backup count to zero. - Persist checkpoints through the HDFS checkpoint plugin in local mode and verify checkpoint and MapStore files after each trial. - Trigger checkpoints through a benchmark-only reflection bridge without changing core APIs. - Cover 1-byte and 1-KiB records and report average completion time in seconds. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
