jeffkbkim commented on code in PR #14417: URL: https://github.com/apache/kafka/pull/14417#discussion_r1350893216
########## group-coordinator/src/main/java/org/apache/kafka/coordinator/group/metrics/CoordinatorRuntimeMetrics.java: ########## @@ -0,0 +1,100 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ +package org.apache.kafka.coordinator.group.metrics; + +import org.apache.kafka.coordinator.group.runtime.CoordinatorRuntime.CoordinatorState; + +import java.util.function.Supplier; + +/** + * Used by the group and transaction coordinator runtimes, the metrics suite holds partition state gauges and sensors. + */ +public interface CoordinatorRuntimeMetrics extends AutoCloseable { + /** + * Returns the metrics group. + */ + String metricsGroup(); + + /** + * Called when the partition state changes. + * @param oldState The old state. + * @param newState The new state to transition to. + */ + void onPartitionStateChange(CoordinatorState oldState, CoordinatorState newState); + + /** + * Record the partition load metric. + * @param startTimeMs The partition load start time. + * @param endTimeMs The partition load end time. + */ + void recordPartitionLoadSensor(long startTimeMs, long endTimeMs); + + /** + * Get the counter for partitions in Loading state. + * Only used for testing. + */ + long numPartitionsLoading(); + + /** + * Get the counter for partitions in Active state. + * Only used for testing. + */ + long numPartitionsActive(); + + /** + * Get the counter for partitions in Failed state. + * Only used for testing. + */ + long numPartitionsFailed(); + + /** + * Update the event queue time. + * + * @param durationMs The queue time. + */ + void updateEventQueueTime(long durationMs); + + /** + * Update the event queue processing time. + * + * @param durationMs The event processing time. + */ + void updateEventQueueProcessingTime(long durationMs); + + /** + * Record the failed event. + */ + void recordFailedEvent(); + + /** + * Record the successful event. + */ + void recordSuccessfulEvent(); + + /** + * Record the thread idle ratio. + * @param ratio The idle ratio. + */ + void recordThreadIdleRatio(double ratio); Review Comment: Right, we won't be able to differentiate the idle ratio for each individual thread. Is this something we should have? > So we have an average an min for idle ratio. Is the minimum value just the lowest recorded at a given time frame? Yes, that's right -- 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: jira-unsubscr...@kafka.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org
