diff options
author | Andrew Or <andrew@databricks.com> | 2015-05-08 17:15:10 -0700 |
---|---|---|
committer | Andrew Or <andrew@databricks.com> | 2015-05-08 17:15:10 -0700 |
commit | bd61f07039064833108070e19b752d4c46045766 (patch) | |
tree | 439e3f0cca8250101fa4ef74a2e719f6ecd1db19 /sql/hive | |
parent | ffdc40ce7a799f2564f57b958d0f32f1d1636488 (diff) | |
download | spark-bd61f07039064833108070e19b752d4c46045766.tar.gz spark-bd61f07039064833108070e19b752d4c46045766.tar.bz2 spark-bd61f07039064833108070e19b752d4c46045766.zip |
[SPARK-7469] [SQL] DAG visualization: show SQL query operators
The DAG visualization currently displays only low-level Spark primitives (e.g. `map`, `reduceByKey`, `filter` etc.). For SQL, these aren't particularly useful. Instead, we should display higher level physical operators (e.g. `Filter`, `Exchange`, `ShuffleHashJoin`). cc marmbrus
-----------------
**Before**
<img src="https://issues.apache.org/jira/secure/attachment/12731586/before.png" width="600px"/>
-----------------
**After** (Pay attention to the words)
<img src="https://issues.apache.org/jira/secure/attachment/12731587/after.png" width="600px"/>
-----------------
Author: Andrew Or <andrew@databricks.com>
Closes #5999 from andrewor14/dag-viz-sql and squashes the following commits:
0db23a4 [Andrew Or] Merge branch 'master' of github.com:apache/spark into dag-viz-sql
1e211db [Andrew Or] Update comment
0d49fd6 [Andrew Or] Merge branch 'master' of github.com:apache/spark into dag-viz-sql
ffd237a [Andrew Or] Fix style
202dac1 [Andrew Or] Make ignoreParent false by default
e61b1ab [Andrew Or] Visualize SQL operators, not low-level Spark primitives
569034a [Andrew Or] Add a flag to ignore parent settings and scopes
Diffstat (limited to 'sql/hive')
3 files changed, 5 insertions, 3 deletions
diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/HiveTableScan.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/HiveTableScan.scala index 0a5f19eee7..62dc4167b7 100644 --- a/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/HiveTableScan.scala +++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/HiveTableScan.scala @@ -129,7 +129,7 @@ case class HiveTableScan( } } - override def execute(): RDD[Row] = if (!relation.hiveQlTable.isPartitioned) { + protected override def doExecute(): RDD[Row] = if (!relation.hiveQlTable.isPartitioned) { hadoopReader.makeRDDForTable(relation.hiveQlTable) } else { hadoopReader.makeRDDForPartitionedTable(prunePartitions(relation.hiveQlPartitions)) diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/InsertIntoHiveTable.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/InsertIntoHiveTable.scala index de8954d5de..c0b0b104e9 100644 --- a/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/InsertIntoHiveTable.scala +++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/InsertIntoHiveTable.scala @@ -258,5 +258,7 @@ case class InsertIntoHiveTable( override def executeCollect(): Array[Row] = sideEffectResult.toArray - override def execute(): RDD[Row] = sqlContext.sparkContext.parallelize(sideEffectResult, 1) + protected override def doExecute(): RDD[Row] = { + sqlContext.sparkContext.parallelize(sideEffectResult, 1) + } } diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/ScriptTransformation.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/ScriptTransformation.scala index 3eddda3b28..bfd26e0170 100644 --- a/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/ScriptTransformation.scala +++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/ScriptTransformation.scala @@ -54,7 +54,7 @@ case class ScriptTransformation( override def otherCopyArgs: Seq[HiveContext] = sc :: Nil - def execute(): RDD[Row] = { + protected override def doExecute(): RDD[Row] = { child.execute().mapPartitions { iter => val cmd = List("/bin/bash", "-c", script) val builder = new ProcessBuilder(cmd) |