Spark 之 HiveStrategies

HiveTableRelation 相关代码

HiveStrategies.scala

当 relation.tableMeta.stats.isEmpty 是, 即调用 hiveTableWithStats

复制代码
class DetermineTableStats(session: SparkSession) extends Rule[LogicalPlan] {
  private def hiveTableWithStats(relation: HiveTableRelation): HiveTableRelation = {
    val table = relation.tableMeta
    val partitionCols = relation.partitionCols
    // For partitioned tables, the partition directory may be outside of the table directory.
    // Which is expensive to get table size. Please see how we implemented it in the AnalyzeTable.
    val sizeInBytes = if (conf.fallBackToHdfsForStatsEnabled && partitionCols.isEmpty) {
      try {
        val hadoopConf = session.sessionState.newHadoopConf()
        val tablePath = new Path(table.location)
        val fs: FileSystem = tablePath.getFileSystem(hadoopConf)
        fs.getContentSummary(tablePath).getLength
      } catch {
        case e: IOException =>
          logWarning("Failed to get table size from HDFS.", e)
          conf.defaultSizeInBytes
      }
    } else {
      conf.defaultSizeInBytes
    }

    val stats = Some(Statistics(sizeInBytes = BigInt(sizeInBytes)))
    relation.copy(tableStats = stats)
  }

  override def apply(plan: LogicalPlan): LogicalPlan = plan resolveOperators {
    case relation: HiveTableRelation
      if DDLUtils.isHiveTable(relation.tableMeta) && relation.tableMeta.stats.isEmpty =>
      hiveTableWithStats(relation)

    // handles InsertIntoStatement specially as the table in InsertIntoStatement is not added in its
    // children, hence not matched directly by previous HiveTableRelation case.
    case i @ InsertIntoStatement(relation: HiveTableRelation, _, _, _, _, _)
      if DDLUtils.isHiveTable(relation.tableMeta) && relation.tableMeta.stats.isEmpty =>
      i.copy(table = hiveTableWithStats(relation))
  }
}
  • HiveTableRelation

    /**

    • A LogicalPlan that represents a hive table.
    • TODO: remove this after we completely make hive as a data source.
      */
      case class HiveTableRelation(
      tableMeta: CatalogTable,
      dataCols: Seq[AttributeReference],
      partitionCols: Seq[AttributeReference],
      tableStats: Option[Statistics] = None,
      @transient prunedPartitions: Option[Seq[CatalogTablePartition]] = None)
相关推荐
阿里云大数据AI技术5 小时前
StarRocks 助力数禾科技构建实时数仓:从数据孤岛到智能决策
大数据
Lx3529 小时前
Hadoop数据处理优化:减少Shuffle阶段的性能损耗
大数据·hadoop
努力的小郑12 小时前
从一次分表实践谈起:我们真的需要复杂的分布式ID吗?
分布式·后端·面试
武子康13 小时前
大数据-99 Spark Streaming 数据源全面总结:原理、应用 文件流、Socket、RDD队列流
大数据·后端·spark
AAA修煤气灶刘哥1 天前
别让Redis「歪脖子」!一次搞定数据倾斜与请求倾斜的捉妖记
redis·分布式·后端
阿里云大数据AI技术1 天前
大数据公有云市场第一,阿里云占比47%!
大数据
Lx3521 天前
Hadoop容错机制深度解析:保障作业稳定运行
大数据·hadoop
Aomnitrix2 天前
知识管理新范式——cpolar+Wiki.js打造企业级分布式知识库
开发语言·javascript·分布式
程序消消乐2 天前
Kafka 入门指南:从 0 到 1 构建你的 Kafka 知识基础入门体系
分布式·kafka