spark FileBatchWrite 源码

2022-10-20
浏览 (170)

spark FileBatchWrite 代码

文件路径：/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/FileBatchWrite.scala

/*
 * 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.sql.execution.datasources.v2

import org.apache.hadoop.mapreduce.Job

import org.apache.spark.internal.Logging
import org.apache.spark.internal.io.FileCommitProtocol
import org.apache.spark.sql.connector.write.{BatchWrite, DataWriterFactory, PhysicalWriteInfo, WriterCommitMessage}
import org.apache.spark.sql.execution.datasources.{WriteJobDescription, WriteTaskResult}
import org.apache.spark.sql.execution.datasources.FileFormatWriter.processStats
import org.apache.spark.util.Utils

class FileBatchWrite(
    job: Job,
    description: WriteJobDescription,
    committer: FileCommitProtocol)
  extends BatchWrite with Logging {
  override def commit(messages: Array[WriterCommitMessage]): Unit = {
    val results = messages.map(_.asInstanceOf[WriteTaskResult])
    logInfo(s"Start to commit write Job ${description.uuid}.")
    val (_, duration) = Utils.timeTakenMs { committer.commitJob(job, results.map(_.commitMsg)) }
    logInfo(s"Write Job ${description.uuid} committed. Elapsed time: $duration ms.")

    processStats(description.statsTrackers, results.map(_.summary.stats), duration)
    logInfo(s"Finished processing stats for write job ${description.uuid}.")
  }

  override def useCommitCoordinator(): Boolean = false

  override def abort(messages: Array[WriterCommitMessage]): Unit = {
    committer.abortJob(job)
  }

  override def createBatchWriterFactory(info: PhysicalWriteInfo): DataWriterFactory = {
    FileWriterFactory(description, committer)
  }
}

相关信息

spark 源码目录

相关文章

spark AddPartitionExec 源码

spark AlterNamespaceSetPropertiesExec 源码

spark AlterTableExec 源码

spark BatchScanExec 源码

spark CacheTableExec 源码

spark ContinuousScanExec 源码

spark CreateIndexExec 源码

spark CreateNamespaceExec 源码

spark CreateTableExec 源码

spark DataSourceRDD 源码

0 赞

所属分类： 前端技术
本文标签：
版权声明： 原创文章如转载，请注明本文链接: https://www.seaxiang.com/blog/1b0944a3f96d4c118ec04c5f33c78436

热门推荐

1、直接访问google.com
2、 - 优质文章
3、 gate.io
4、 harmony 鸿蒙hdc使用指导
5、 harmony 鸿蒙初识ArkTS语言
6、 flink kafka connector scan.startup.mode 的几个选项
7、 harmony 鸿蒙ArkUI组件（ArkTS）开发常见问题
8、 golang
9、 openharmony
10、 Vue中input框自动聚焦

Loading...