spark-reviews mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From gatorsmile <...@git.apache.org>
Subject [GitHub] spark pull request #15090: [SPARK-17073] [SQL] generate column-level statist...
Date Tue, 20 Sep 2016 07:11:55 GMT
Github user gatorsmile commented on a diff in the pull request:

    https://github.com/apache/spark/pull/15090#discussion_r79547634
  
    --- Diff: sql/core/src/main/scala/org/apache/spark/sql/execution/command/AnalyzeColumnCommand.scala
---
    @@ -0,0 +1,168 @@
    +/*
    + * 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.command
    +
    +import scala.collection.mutable
    +
    +import org.apache.spark.sql._
    +import org.apache.spark.sql.catalyst.{InternalRow, TableIdentifier}
    +import org.apache.spark.sql.catalyst.analysis.EliminateSubqueryAliases
    +import org.apache.spark.sql.catalyst.catalog.{CatalogRelation, CatalogTable}
    +import org.apache.spark.sql.catalyst.expressions._
    +import org.apache.spark.sql.catalyst.expressions.aggregate._
    +import org.apache.spark.sql.catalyst.plans.logical.{Aggregate, ColumnStats, Statistics}
    +import org.apache.spark.sql.execution.datasources.LogicalRelation
    +import org.apache.spark.sql.types._
    +
    +
    +/**
    + * Analyzes the given columns of the given table in the current database to generate
statistics,
    + * which will be used in query optimizations.
    + */
    +case class AnalyzeColumnCommand(
    +    tableIdent: TableIdentifier,
    +    columnNames: Seq[String]) extends RunnableCommand {
    +
    +  override def run(sparkSession: SparkSession): Seq[Row] = {
    +    val sessionState = sparkSession.sessionState
    +    val relation = EliminateSubqueryAliases(sessionState.catalog.lookupRelation(tableIdent))
    +
    +    // check correctness of column names
    +    val attributesToAnalyze = mutable.MutableList[Attribute]()
    +    val caseSensitive = sessionState.conf.caseSensitiveAnalysis
    +    columnNames.foreach { col =>
    +      val exprOption = relation.output.find { attr =>
    +        if (caseSensitive) attr.name == col else attr.name.equalsIgnoreCase(col)
    +      }
    +      val expr = exprOption.getOrElse(throw new AnalysisException(s"Invalid column name:
$col."))
    +      // do deduplication
    +      if (!attributesToAnalyze.contains(expr)) {
    +        attributesToAnalyze += expr
    +      }
    +    }
    +
    +    relation match {
    +      case catalogRel: CatalogRelation =>
    +        updateStats(catalogRel.catalogTable,
    +          AnalyzeTableCommand.calculateTotalSize(sparkSession, catalogRel.catalogTable))
    +
    +      case logicalRel: LogicalRelation if logicalRel.catalogTable.isDefined =>
    +        updateStats(logicalRel.catalogTable.get, logicalRel.relation.sizeInBytes)
    +
    +      case otherRelation =>
    +        throw new AnalysisException("ANALYZE TABLE is not supported for " +
    +          s"${otherRelation.nodeName}.")
    +    }
    +
    +    def updateStats(catalogTable: CatalogTable, newTotalSize: Long): Unit = {
    +      // Collect statistics per column.
    +      // The first element in the result will be the overall row count, the following
elements
    +      // will be structs containing all column stats.
    +      // The layout of each struct follows the layout of the ColumnStats.
    +      val ndvMaxErr = sessionState.conf.ndvMaxError
    +      val expressions = Count(Literal(1)).toAggregateExpression() +:
    +        attributesToAnalyze.map(ColumnStatsStruct(_, ndvMaxErr))
    +      val namedExpressions = expressions.map(e => Alias(e, e.toString)())
    +      val statsRow = Dataset.ofRows(sparkSession, Aggregate(Nil, namedExpressions, relation))
    +        .queryExecution.toRdd.collect().head
    +
    +      // unwrap the result
    +      val rowCount = statsRow.getLong(0)
    +      val columnStats = attributesToAnalyze.zipWithIndex.map { case (expr, i) =>
    +        (expr.name, ColumnStatsStruct.unwrapStruct(statsRow, i + 1, expr))
    +      }.toMap
    +
    +      val statistics = Statistics(
    +        sizeInBytes = newTotalSize,
    +        rowCount = Some(rowCount),
    +        colStats = columnStats ++ catalogTable.stats.map(_.colStats).getOrElse(Map()))
    +      sessionState.catalog.alterTable(catalogTable.copy(stats = Some(statistics)))
    +      // Refresh the cached data source table in the catalog.
    +      sessionState.catalog.refreshTable(tableIdent)
    +    }
    +
    +    Seq.empty[Row]
    --- End diff --
    
    This is a design decision. Should we output the outcomes of this command? cc @hvanhovell



---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastructure@apache.org or file a JIRA ticket
with INFRA.
---

---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org


Mime
View raw message