flink 源码调试flinksql的 explain功能

1、因业务需要，需要把查看sql的执行计划，所以在代码里可以添加如下代码来查看相关数据,在  TableEnvironmentITCase测试类添加代码

//todo 查看sql的解析语法
  @Test
  def testExplainAndExecuteSingleSink2(): Unit = {
    val sinkPath = TestTableSourceSinks.createCsvTemporarySinkTable(
      tEnv, new TableSchema(Array("first","totalQuantity"), Array(STRING,DOUBLE)),"MySink1")

    //    val table1 = tEnv.sqlQuery("select first from MyTable")
    val table1 = tEnv.sqlQuery(
      "SELECT first,totalQuantity FROM (  " +
        "SELECT first,totalQuantity,row_number() OVER(PARTITION BY first ORDER BY totalQuantity DESC) AS rownum  FROM (  " +
        "  SELECT first , sum(score) AS totalQuantity " +
        " FROM MyTable GROUP BY first  )" +
        ") WHERE rownum <= 10")
    
    tEnv.insertInto(table1, "MySink1")
    //    todo 打印相关日志信息
    println(tEnv.explain(false))
    tEnv.execute("test1")
  }

 

2、debug日志如下：

 

 

3、ast语法树

== Abstract Syntax Tree ==
LogicalLegacySink(name=[`default_catalog`.`default_database`.`MySink1`], fields=[first, totalQuantity])
+- LogicalProject(first=[$0], totalQuantity=[$1])
   +- LogicalFilter(condition=[<=($2, 10)])
      +- LogicalProject(first=[$0], totalQuantity=[$1], rownum=[ROW_NUMBER() OVER (PARTITION BY $0 ORDER BY $1 DESC NULLS LAST)])
         +- LogicalAggregate(group=[{0}], totalQuantity=[SUM($1)])
            +- LogicalProject(first=[$0], score=[$2])
               +- LogicalTableScan(table=[[default_catalog, default_database, MyTable, source: [CsvTableSource(read fields: first, id, score, last)]]])

== Optimized Logical Plan ==
LegacySink(name=[`default_catalog`.`default_database`.`MySink1`], fields=[first, totalQuantity])
+- Calc(select=[first, totalQuantity], where=[<=(w0$o0, 10)])
   +- OverAggregate(partitionBy=[first], orderBy=[totalQuantity DESC], window#0=[ROW_NUMBER(*) AS w0$o0 ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW], select=[first, totalQuantity, w0$o0])
      +- Sort(orderBy=[first ASC, totalQuantity DESC])
         +- HashAggregate(isMerge=[true], groupBy=[first], select=[first, Final_SUM(sum$0) AS totalQuantity])
            +- Exchange(distribution=[hash[first]])
               +- LocalHashAggregate(groupBy=[first], select=[first, Partial_SUM(score) AS sum$0])
                  +- LegacyTableSourceScan(table=[[default_catalog, default_database, MyTable, source: [CsvTableSource(read fields: first, score)]]], fields=[first, score])

== Physical Execution Plan ==
Stage 14 : Data Source
	content : Source: Custom File source

	Stage 15 : Operator
		content : CsvTableSource(read fields: first, score)
		ship_strategy : REBALANCE

		Stage 16 : Operator
			content : SourceConversion(table=[default_catalog.default_database.MyTable, source: [CsvTableSource(read fields: first, score)]], fields=[first, score])
			ship_strategy : FORWARD

			Stage 17 : Operator
				content : LocalHashAggregate(groupBy=[first], select=[first, Partial_SUM(score) AS sum$0])
				ship_strategy : FORWARD

				Stage 19 : Operator
					content : HashAggregate(isMerge=[true], groupBy=[first], select=[first, Final_SUM(sum$0) AS totalQuantity])
					ship_strategy : HASH[first]

					Stage 20 : Operator
						content : Sort(orderBy=[first ASC, totalQuantity DESC])
						ship_strategy : FORWARD

						Stage 21 : Operator
							content : OverAggregate(partitionBy=[first], orderBy=[totalQuantity DESC], window#0=[ROW_NUMBER(*) AS w0$o0 ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW], select=[first, totalQuantity, w0$o0])
							ship_strategy : FORWARD

							Stage 22 : Operator
								content : Calc(select=[first, totalQuantity], where=[(w0$o0 <= 10)])
								ship_strategy : FORWARD

								Stage 23 : Operator
									content : SinkConversionToRow
									ship_strategy : FORWARD

									Stage 24 : Operator
										content : Map
										ship_strategy : REBALANCE

										Stage 25 : Data Sink
											content : Sink: CsvTableSink(first, totalQuantity)
											ship_strategy : FORWARD

 

4、

VolcanoPlanner优化器

 

 

 

VolcanoCost