spark MetricsReporter 源码

2022-10-20
浏览 (247)

spark MetricsReporter 代码

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

import java.text.SimpleDateFormat

import com.codahale.metrics.{Gauge, MetricRegistry}

import org.apache.spark.internal.Logging
import org.apache.spark.metrics.source.{Source => CodahaleSource}
import org.apache.spark.sql.catalyst.util.DateTimeUtils
import org.apache.spark.sql.streaming.StreamingQueryProgress

/**
 * Serves metrics from a [[org.apache.spark.sql.streaming.StreamingQuery]] to
 * Codahale/DropWizard metrics
 */
class MetricsReporter(
    stream: StreamExecution,
    override val sourceName: String) extends CodahaleSource with Logging {

  override val metricRegistry: MetricRegistry = new MetricRegistry

  // Metric names should not have . in them, so that all the metrics of a query are identified
  // together in Ganglia as a single metric group
  registerGauge("inputRate-total", _.inputRowsPerSecond, 0.0)
  registerGauge("processingRate-total", _.processedRowsPerSecond, 0.0)
  registerGauge("latency", _.durationMs.getOrDefault("triggerExecution", 0L).longValue(), 0L)

  private val timestampFormat = new SimpleDateFormat("yyyy-MM-dd'T'HH:mm:ss.SSS'Z'") // ISO8601
  timestampFormat.setTimeZone(DateTimeUtils.getTimeZone("UTC"))

  registerGauge("eventTime-watermark",
    progress => convertStringDateToMillis(progress.eventTime.get("watermark")), 0L)

  registerGauge("states-rowsTotal", _.stateOperators.map(_.numRowsTotal).sum, 0L)
  registerGauge("states-usedBytes", _.stateOperators.map(_.memoryUsedBytes).sum, 0L)

  private def convertStringDateToMillis(isoUtcDateStr: String) = {
    if (isoUtcDateStr != null) {
      timestampFormat.parse(isoUtcDateStr).getTime
    } else {
      0L
    }
  }

  private def registerGauge[T](
      name: String,
      f: StreamingQueryProgress => T,
      default: T): Unit = {
    synchronized {
      metricRegistry.register(name, new Gauge[T] {
        override def getValue: T = Option(stream.lastProgress).map(f).getOrElse(default)
      })
    }
  }
}

相关信息

spark 源码目录

相关文章

spark AvailableNowDataStreamWrapper 源码

spark AvailableNowMicroBatchStreamWrapper 源码

spark AvailableNowSourceWrapper 源码

spark CheckpointFileManager 源码

spark CommitLog 源码

spark CompactibleFileStreamLog 源码

spark ContinuousRecordEndpoint 源码

spark EventTimeWatermarkExec 源码

spark FileStreamOptions 源码

spark FileStreamSink 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/6455684be4004ee7bf4d1325d93de96b

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...