steveloughran commented on a change in pull request #24970: [SPARK-23977][SQL] Support High Performance S3A committers [test-hadoop3.2] URL: https://github.com/apache/spark/pull/24970#discussion_r310214013
########## File path: hadoop-cloud/src/hadoop-3/test/scala/org/apache/spark/internal/io/cloud/CommitterBindingSuite.scala ########## @@ -0,0 +1,147 @@ +/* + * 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.spark.internal.io.cloud + +import java.io.{File, FileInputStream, FileOutputStream, IOException, ObjectInputStream, ObjectOutputStream} +import java.lang.reflect.InvocationTargetException + +import org.apache.hadoop.conf.Configuration +import org.apache.hadoop.fs.Path +import org.apache.hadoop.io.IOUtils +import org.apache.hadoop.mapreduce.{Job, JobStatus, MRJobConfig, TaskAttemptID} +import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat +import org.apache.hadoop.mapreduce.task.TaskAttemptContextImpl + +import org.apache.spark.SparkFunSuite +import org.apache.spark.internal.io.{cloud, FileCommitProtocol} + +/** + * Test committer binding logic. + */ +class CommitterBindingSuite extends SparkFunSuite { + + private val jobId = "2007071202143_0101" + private val taskAttempt0 = "attempt_" + jobId + "_m_000000_0" + private val taskAttemptId0 = TaskAttemptID.forName(taskAttempt0) + + /** hadoop-mapreduce option to enable the _SUCCESS marker. */ + private val successMarker = "mapreduce.fileoutputcommitter.marksuccessfuljobs" + /** + * Does the + * [[BindingParquetOutputCommitter]] committer bind to the schema-specific + * committer declared for the destination path? + */ + test("BindingParquetOutputCommitter lifecycle") { + val path = new Path("http://example/data";) + val job = newJob(path) + val conf = job.getConfiguration + conf.set(MRJobConfig.TASK_ATTEMPT_ID, taskAttempt0) + conf.setInt(MRJobConfig.APPLICATION_ATTEMPT_ID, 1) + + StubPathOutputCommitterFactory.bind(conf, "http") + val tContext = new TaskAttemptContextImpl(conf, taskAttemptId0) + val parquet = new BindingParquetOutputCommitter(path, tContext) + val inner = parquet.boundCommitter.asInstanceOf[StubPathOutputCommitter] + parquet.setupJob(tContext) + assert(inner.jobSetup, s"$inner job not setup") + parquet.setupTask(tContext) + assert(inner.taskSetup, s"$inner task not setup") + assert(parquet.needsTaskCommit(tContext), "needsTaskCommit false") + inner.needsTaskCommit = false + assert(!parquet.needsTaskCommit(tContext), "needsTaskCommit true") + parquet.commitTask(tContext) + assert(inner.taskCommitted, s"$inner task not committed") + parquet.abortTask(tContext) + assert(inner.taskAborted, s"$inner task not aborted") + parquet.commitJob(tContext) + assert(inner.jobCommitted, s"$inner job not committed") + parquet.abortJob(tContext, JobStatus.State.RUNNING) + assert(inner.jobAborted, s"$inner job not aborted") + } + + /** + * Create a a new job. Sets the task attempt ID. + * + * @return the new job + */ + def newJob(outDir: Path): Job = { + val job = Job.getInstance(new Configuration()) + val conf = job.getConfiguration + conf.set(MRJobConfig.TASK_ATTEMPT_ID, taskAttempt0) + conf.setBoolean(successMarker, true) + FileOutputFormat.setOutputPath(job, outDir) + job + } + + /** + * Verify that the committer protocol can be serialized and that Review comment: moved the text down; removed the comment. ---------------------------------------------------------------- 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. For queries about this service, please contact Infrastructure at: [email protected] With regards, Apache Git Services --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
