spark WriteToContinuousDataSourceExec 源码

2022-10-20
浏览 (283)

spark WriteToContinuousDataSourceExec 代码

文件路径：/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/continuous/WriteToContinuousDataSourceExec.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.streaming.continuous

import org.apache.spark.internal.Logging
import org.apache.spark.rdd.RDD
import org.apache.spark.sql.catalyst.InternalRow
import org.apache.spark.sql.catalyst.expressions.Attribute
import org.apache.spark.sql.connector.metric.CustomMetric
import org.apache.spark.sql.connector.write.PhysicalWriteInfoImpl
import org.apache.spark.sql.connector.write.streaming.StreamingWrite
import org.apache.spark.sql.execution.{SparkPlan, UnaryExecNode}
import org.apache.spark.sql.execution.metric.SQLMetrics

/**
 * The physical plan for writing data into a continuous processing [[StreamingWrite]].
 */
case class WriteToContinuousDataSourceExec(write: StreamingWrite, query: SparkPlan,
    customMetrics: Seq[CustomMetric])
  extends UnaryExecNode with Logging {

  override def child: SparkPlan = query
  override def output: Seq[Attribute] = Nil

  override lazy val metrics = customMetrics.map { customMetric =>
    customMetric.name() -> SQLMetrics.createV2CustomMetric(sparkContext, customMetric)
  }.toMap

  override protected def doExecute(): RDD[InternalRow] = {
    val queryRdd = query.execute()
    val writerFactory = write.createStreamingWriterFactory(
      PhysicalWriteInfoImpl(queryRdd.getNumPartitions))
    val rdd = new ContinuousWriteRDD(queryRdd, writerFactory, metrics)

    logInfo(s"Start processing data source write support: $write. " +
      s"The input RDD has ${rdd.partitions.length} partitions.")
    EpochCoordinatorRef.get(
      sparkContext.getLocalProperty(ContinuousExecution.EPOCH_COORDINATOR_ID_KEY),
      sparkContext.env)
      .askSync[Unit](SetWriterPartitions(rdd.getNumPartitions))

    try {
      // Force the RDD to run so continuous processing starts; no data is actually being collected
      // to the driver, as ContinuousWriteRDD outputs nothing.
      rdd.collect()
    } catch {
      case _: InterruptedException =>
        // Interruption is how continuous queries are ended, so accept and ignore the exception.
    }

    sparkContext.emptyRDD
  }

  override protected def withNewChildInternal(
    newChild: SparkPlan): WriteToContinuousDataSourceExec = copy(query = newChild)
}

相关信息

spark 源码目录

相关文章

spark ContinuousDataSourceRDD 源码

spark ContinuousExecution 源码

spark ContinuousQueuedDataReader 源码

spark ContinuousRateStreamSource 源码

spark ContinuousTaskRetryException 源码

spark ContinuousTextSocketSource 源码

spark ContinuousWriteRDD 源码

spark EpochCoordinator 源码

spark EpochTracker 源码

spark WriteToContinuousDataSource 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://m.seaxiang.com/blog/93b8acb7ef6b4b07998d8b05e151ed88

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ArkUI组件（ArkTS）开发常见问题
6、 harmony 鸿蒙初识ArkTS语言
7、 golang
8、 flink kafka connector scan.startup.mode 的几个选项
9、 openharmony
10、 Vue中input框自动聚焦

Loading...