Cassandra 19480 Additional task execution specific instrumentation of job stats #51
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,47 @@ | ||
| /* | ||
| * 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.cassandra.spark; | ||
|
|
||
| import java.util.Map; | ||
|
|
||
| /** | ||
| * Container class for the job metadata associated with a spark listener event. | ||
| */ | ||
| public class JobEventDetail | ||
| { | ||
| private String internalJobID; | ||
| private Map<String, String> jobStats; | ||
|
|
||
| public JobEventDetail(String internalJobID, Map<String, String> jobStats) | ||
| { | ||
| this.internalJobID = internalJobID; | ||
| this.jobStats = jobStats; | ||
| } | ||
|
|
||
| public String internalJobID() | ||
| { | ||
| return internalJobID; | ||
| } | ||
|
|
||
| public Map<String, String> jobStats() | ||
| { | ||
| return jobStats; | ||
| } | ||
| } | ||
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,171 @@ | ||
| /* | ||
| * 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.cassandra.spark.common.stats; | ||
|
|
||
| import java.util.HashMap; | ||
| import java.util.HashSet; | ||
| import java.util.List; | ||
| import java.util.Map; | ||
| import java.util.Set; | ||
| import java.util.concurrent.TimeUnit; | ||
| import java.util.function.Consumer; | ||
| import java.util.stream.Collectors; | ||
|
|
||
| import org.apache.commons.math3.stat.StatUtils; | ||
| import org.slf4j.Logger; | ||
| import org.slf4j.LoggerFactory; | ||
|
|
||
| import org.apache.cassandra.spark.JobEventDetail; | ||
| import org.apache.spark.executor.TaskMetrics; | ||
| import org.apache.spark.scheduler.JobFailed; | ||
| import org.apache.spark.scheduler.SparkListener; | ||
| import org.apache.spark.scheduler.SparkListenerJobEnd; | ||
| import org.apache.spark.scheduler.SparkListenerJobStart; | ||
| import org.apache.spark.scheduler.SparkListenerTaskEnd; | ||
|
|
||
| /** | ||
| * Spark listener implementation to capture stats on completion of jobs and tasks. | ||
| */ | ||
| public class JobStatsListener extends SparkListener | ||
| { | ||
| private final Map<Integer, Integer> jobIdToTaskRetryStats = new HashMap<>(); | ||
| private final Map<Integer, Set<TaskMetrics>> jobIdToTaskMetrics = new HashMap<>(); | ||
| private final Map<Integer, Long> jobIdToStartTimes = new HashMap<>(); | ||
| private final Map<Integer, String> internalJobIdMapping = new HashMap<>(); | ||
|
|
||
| private static int jobId = -1; | ||
| private static final Logger LOGGER = LoggerFactory.getLogger(JobStatsListener.class); | ||
| private final Consumer<JobEventDetail> jobCompletionConsumer; | ||
|
|
||
| public JobStatsListener(Consumer<JobEventDetail> jobCompletionConsumer) | ||
| { | ||
| this.jobCompletionConsumer = jobCompletionConsumer; | ||
| } | ||
|
|
||
| @Override | ||
| public synchronized void onTaskEnd(SparkListenerTaskEnd taskEnd) | ||
| { | ||
| try | ||
| { | ||
| // Calculate max task retries across all tasks in job | ||
| int attempt = taskEnd.taskInfo().attemptNumber(); | ||
| jobIdToTaskRetryStats.compute(jobId, (k, v) -> (v == null || attempt > v) ? attempt : v); | ||
| // Persist all task metrics for the job - across all stages | ||
| jobIdToTaskMetrics.computeIfAbsent(jobId, k -> new HashSet<>()).add(taskEnd.taskMetrics()); | ||
| LOGGER.debug("Task END for jobId:{} task:{} task attempt:{}} Reason:{}", | ||
| jobId, | ||
| taskEnd.taskInfo().taskId(), | ||
| taskEnd.taskInfo().attemptNumber(), | ||
| taskEnd.reason()); | ||
|
|
||
| } | ||
| catch (Exception e) | ||
| { | ||
| LOGGER.warn("Failed to process job stats for the task completion event with jobId: {}", | ||
| internalJobIdMapping.get(jobId), e); | ||
| } | ||
| } | ||
|
|
||
| @Override | ||
| public void onJobStart(SparkListenerJobStart jobStart) | ||
| { | ||
| String internalJobId = (String) jobStart.properties().get("spark.jobGroup.id"); | ||
| try | ||
| { | ||
|
|
||
| jobId = Integer.valueOf(jobStart.jobId()); | ||
| internalJobIdMapping.put(jobId, internalJobId); | ||
| jobIdToStartTimes.put(jobId, System.nanoTime()); | ||
| } | ||
| catch (Exception e) | ||
| { | ||
| LOGGER.warn("Failed to process job stats for the job start event with jobId: {}", internalJobId, e); | ||
| } | ||
| } | ||
|
|
||
| @Override | ||
| public void onJobEnd(SparkListenerJobEnd jobEnd) | ||
| { | ||
| try | ||
| { | ||
| boolean jobFailed = false; | ||
| String reason = "null"; | ||
| if (jobEnd.jobResult() instanceof JobFailed) | ||
| { | ||
| jobFailed = true; | ||
| JobFailed result = (JobFailed) jobEnd.jobResult(); | ||
| reason = result.exception().getCause().getMessage(); | ||
| } | ||
|
|
||
| long elapsedTimeMillis = TimeUnit.NANOSECONDS.toMillis(System.nanoTime() - jobIdToStartTimes.get(jobId)); | ||
| String internalJobId = internalJobIdMapping.get(jobId); | ||
| String jobStatus = (jobFailed) ? "Failed" : "Succeeded"; | ||
| Map<String, String> jobStats = new HashMap<>(); | ||
| jobStats.put("jobId", internalJobId); | ||
| jobStats.put("jobStatus", jobStatus); | ||
| jobStats.put("failureReason", reason); | ||
| jobStats.put("jobElapsedTimeMillis", String.valueOf(elapsedTimeMillis)); | ||
|
|
||
| LOGGER.debug("Job END for jobId:{} status:{} Reason:{} ElapsedTime: {}", | ||
|
There was a problem hiding this comment. There is an extra space after ElapsedTime |
||
| jobId, | ||
| jobStatus, | ||
| reason, | ||
| elapsedTimeMillis); | ||
|
|
||
| jobStats.putAll(getJobMetrics(jobId)); | ||
| jobCompletionConsumer.accept(new JobEventDetail(internalJobId, jobStats)); | ||
| cleanup(jobId); | ||
| } | ||
| catch (Exception e) | ||
| { | ||
| LOGGER.warn("Failed to process job stats for the job completion event with jobId: {}", | ||
| internalJobIdMapping.get(jobId), e); | ||
| } | ||
|
|
||
| } | ||
|
|
||
| public synchronized Map<String, String> getJobMetrics(int jobId) | ||
| { | ||
| Map<String, String> jobMetrics = new HashMap<>(); | ||
| if (jobIdToTaskMetrics.containsKey(jobId)) | ||
| { | ||
| List<Long> runTimes = jobIdToTaskMetrics.get(jobId) | ||
| .stream() | ||
| .map(TaskMetrics::executorRunTime) | ||
| .collect(Collectors.toList()); | ||
|
|
||
| double[] runTimesArray = runTimes.stream().mapToDouble(Long::doubleValue).toArray(); | ||
| jobMetrics.put("maxTaskRuntimeMillis", String.valueOf(StatUtils.max(runTimesArray))); | ||
| jobMetrics.put("meanTaskRuntimeMillis", String.valueOf(StatUtils.mean(runTimesArray))); | ||
| jobMetrics.put("p50TaskRuntimeMillis", String.valueOf(StatUtils.percentile(runTimesArray, 50))); | ||
| jobMetrics.put("p95TaskRuntimeMillis", String.valueOf(StatUtils.percentile(runTimesArray, 95))); | ||
| jobMetrics.put("maxTaskRetriesMillis", String.valueOf(jobIdToTaskRetryStats.get(jobId))); | ||
| } | ||
| return jobMetrics; | ||
| } | ||
|
|
||
| private void cleanup(int jobId) | ||
| { | ||
| jobIdToStartTimes.remove(jobId); | ||
| internalJobIdMapping.remove(jobId); | ||
| jobIdToTaskMetrics.remove(jobId); | ||
| jobIdToTaskRetryStats.remove(jobId); | ||
| } | ||
| } | ||
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
can we add a javadoc here?