#84, display parquet metric in Spark UI.

Kyligence · Dec 4, 2019 · 51c2ea0 · 51c2ea0
1 parent 847cdd7
commit 51c2ea0
Show file tree

Hide file tree

Showing 43 changed files with 259 additions and 42 deletions.
diff --git a/assembly/pom.xml b/assembly/pom.xml
@@ -21,7 +21,7 @@
   <parent>
     <groupId>org.apache.spark</groupId>
     <artifactId>spark-parent_2.11</artifactId>
-    <version>2.4.1-kylin-r20</version>
+    <version>2.4.1-kylin-r22</version>
     <relativePath>../pom.xml</relativePath>
   </parent>
 

diff --git a/common/kvstore/pom.xml b/common/kvstore/pom.xml
@@ -22,7 +22,7 @@
   <parent>
     <groupId>org.apache.spark</groupId>
     <artifactId>spark-parent_2.11</artifactId>
-    <version>2.4.1-kylin-r20</version>
+    <version>2.4.1-kylin-r22</version>
     <relativePath>../../pom.xml</relativePath>
   </parent>
 

diff --git a/common/network-common/pom.xml b/common/network-common/pom.xml
@@ -22,7 +22,7 @@
   <parent>
     <groupId>org.apache.spark</groupId>
     <artifactId>spark-parent_2.11</artifactId>
-    <version>2.4.1-kylin-r20</version>
+    <version>2.4.1-kylin-r22</version>
     <relativePath>../../pom.xml</relativePath>
   </parent>
 

diff --git a/common/network-shuffle/pom.xml b/common/network-shuffle/pom.xml
@@ -22,7 +22,7 @@
   <parent>
     <groupId>org.apache.spark</groupId>
     <artifactId>spark-parent_2.11</artifactId>
-    <version>2.4.1-kylin-r20</version>
+    <version>2.4.1-kylin-r22</version>
     <relativePath>../../pom.xml</relativePath>
   </parent>
 

diff --git a/common/network-yarn/pom.xml b/common/network-yarn/pom.xml
@@ -22,7 +22,7 @@
   <parent>
     <groupId>org.apache.spark</groupId>
     <artifactId>spark-parent_2.11</artifactId>
-    <version>2.4.1-kylin-r20</version>
+    <version>2.4.1-kylin-r22</version>
     <relativePath>../../pom.xml</relativePath>
   </parent>
 

diff --git a/common/sketch/pom.xml b/common/sketch/pom.xml
@@ -22,7 +22,7 @@
   <parent>
     <groupId>org.apache.spark</groupId>
     <artifactId>spark-parent_2.11</artifactId>
-    <version>2.4.1-kylin-r20</version>
+    <version>2.4.1-kylin-r22</version>
     <relativePath>../../pom.xml</relativePath>
   </parent>
 

diff --git a/common/tags/pom.xml b/common/tags/pom.xml
@@ -22,7 +22,7 @@
   <parent>
     <groupId>org.apache.spark</groupId>
     <artifactId>spark-parent_2.11</artifactId>
-    <version>2.4.1-kylin-r20</version>
+    <version>2.4.1-kylin-r22</version>
     <relativePath>../../pom.xml</relativePath>
   </parent>
 

diff --git a/common/unsafe/pom.xml b/common/unsafe/pom.xml
@@ -22,7 +22,7 @@
   <parent>
     <groupId>org.apache.spark</groupId>
     <artifactId>spark-parent_2.11</artifactId>
-    <version>2.4.1-kylin-r20</version>
+    <version>2.4.1-kylin-r22</version>
     <relativePath>../../pom.xml</relativePath>
   </parent>
 

diff --git a/core/pom.xml b/core/pom.xml
@@ -21,7 +21,7 @@
   <parent>
     <groupId>org.apache.spark</groupId>
     <artifactId>spark-parent_2.11</artifactId>
-    <version>2.4.1-kylin-r20</version>
+    <version>2.4.1-kylin-r22</version>
     <relativePath>../pom.xml</relativePath>
   </parent>
 

diff --git a/examples/pom.xml b/examples/pom.xml
@@ -21,7 +21,7 @@
   <parent>
     <groupId>org.apache.spark</groupId>
     <artifactId>spark-parent_2.11</artifactId>
-    <version>2.4.1-kylin-r20</version>
+    <version>2.4.1-kylin-r22</version>
     <relativePath>../pom.xml</relativePath>
   </parent>
 

diff --git a/external/avro/pom.xml b/external/avro/pom.xml
@@ -21,7 +21,7 @@
   <parent>
     <groupId>org.apache.spark</groupId>
     <artifactId>spark-parent_2.11</artifactId>
-    <version>2.4.1-kylin-r20</version>
+    <version>2.4.1-kylin-r22</version>
     <relativePath>../../pom.xml</relativePath>
   </parent>
 

diff --git a/external/docker-integration-tests/pom.xml b/external/docker-integration-tests/pom.xml
@@ -22,7 +22,7 @@
   <parent>
     <groupId>org.apache.spark</groupId>
     <artifactId>spark-parent_2.11</artifactId>
-    <version>2.4.1-kylin-r20</version>
+    <version>2.4.1-kylin-r22</version>
     <relativePath>../../pom.xml</relativePath>
   </parent>
 

diff --git a/external/flume-assembly/pom.xml b/external/flume-assembly/pom.xml
@@ -21,7 +21,7 @@
   <parent>
     <groupId>org.apache.spark</groupId>
     <artifactId>spark-parent_2.11</artifactId>
-    <version>2.4.1-kylin-r20</version>
+    <version>2.4.1-kylin-r22</version>
     <relativePath>../../pom.xml</relativePath>
   </parent>
 

diff --git a/external/flume-sink/pom.xml b/external/flume-sink/pom.xml
@@ -21,7 +21,7 @@
   <parent>
     <groupId>org.apache.spark</groupId>
     <artifactId>spark-parent_2.11</artifactId>
-    <version>2.4.1-kylin-r20</version>
+    <version>2.4.1-kylin-r22</version>
     <relativePath>../../pom.xml</relativePath>
   </parent>
 

diff --git a/external/flume/pom.xml b/external/flume/pom.xml
@@ -21,7 +21,7 @@
   <parent>
     <groupId>org.apache.spark</groupId>
     <artifactId>spark-parent_2.11</artifactId>
-    <version>2.4.1-kylin-r20</version>
+    <version>2.4.1-kylin-r22</version>
     <relativePath>../../pom.xml</relativePath>
   </parent>
 

diff --git a/external/kafka-0-10-assembly/pom.xml b/external/kafka-0-10-assembly/pom.xml
@@ -21,7 +21,7 @@
   <parent>
     <groupId>org.apache.spark</groupId>
     <artifactId>spark-parent_2.11</artifactId>
-    <version>2.4.1-kylin-r20</version>
+    <version>2.4.1-kylin-r22</version>
     <relativePath>../../pom.xml</relativePath>
   </parent>
 

diff --git a/external/kafka-0-10-sql/pom.xml b/external/kafka-0-10-sql/pom.xml
@@ -21,7 +21,7 @@
   <parent>
     <groupId>org.apache.spark</groupId>
     <artifactId>spark-parent_2.11</artifactId>
-    <version>2.4.1-kylin-r20</version>
+    <version>2.4.1-kylin-r22</version>
     <relativePath>../../pom.xml</relativePath>
   </parent>
 

diff --git a/external/kafka-0-10/pom.xml b/external/kafka-0-10/pom.xml
@@ -21,7 +21,7 @@
   <parent>
     <groupId>org.apache.spark</groupId>
     <artifactId>spark-parent_2.11</artifactId>
-    <version>2.4.1-kylin-r20</version>
+    <version>2.4.1-kylin-r22</version>
     <relativePath>../../pom.xml</relativePath>
   </parent>
 

diff --git a/external/kafka-0-8-assembly/pom.xml b/external/kafka-0-8-assembly/pom.xml
@@ -21,7 +21,7 @@
   <parent>
     <groupId>org.apache.spark</groupId>
     <artifactId>spark-parent_2.11</artifactId>
-    <version>2.4.1-kylin-r20</version>
+    <version>2.4.1-kylin-r22</version>
     <relativePath>../../pom.xml</relativePath>
   </parent>
 

diff --git a/external/kafka-0-8/pom.xml b/external/kafka-0-8/pom.xml
@@ -21,7 +21,7 @@
   <parent>
     <groupId>org.apache.spark</groupId>
     <artifactId>spark-parent_2.11</artifactId>
-    <version>2.4.1-kylin-r20</version>
+    <version>2.4.1-kylin-r22</version>
     <relativePath>../../pom.xml</relativePath>
   </parent>
 

diff --git a/external/kinesis-asl-assembly/pom.xml b/external/kinesis-asl-assembly/pom.xml
@@ -21,7 +21,7 @@
   <parent>
     <groupId>org.apache.spark</groupId>
     <artifactId>spark-parent_2.11</artifactId>
-    <version>2.4.1-kylin-r20</version>
+    <version>2.4.1-kylin-r22</version>
     <relativePath>../../pom.xml</relativePath>
   </parent>
 

diff --git a/external/kinesis-asl/pom.xml b/external/kinesis-asl/pom.xml
@@ -20,7 +20,7 @@
   <parent>
     <groupId>org.apache.spark</groupId>
     <artifactId>spark-parent_2.11</artifactId>
-    <version>2.4.1-kylin-r20</version>
+    <version>2.4.1-kylin-r22</version>
     <relativePath>../../pom.xml</relativePath>
   </parent>
 

diff --git a/external/spark-ganglia-lgpl/pom.xml b/external/spark-ganglia-lgpl/pom.xml
@@ -20,7 +20,7 @@
   <parent>
     <groupId>org.apache.spark</groupId>
     <artifactId>spark-parent_2.11</artifactId>
-    <version>2.4.1-kylin-r20</version>
+    <version>2.4.1-kylin-r22</version>
     <relativePath>../../pom.xml</relativePath>
   </parent>
 

diff --git a/graphx/pom.xml b/graphx/pom.xml
@@ -21,7 +21,7 @@
   <parent>
     <groupId>org.apache.spark</groupId>
     <artifactId>spark-parent_2.11</artifactId>
-    <version>2.4.1-kylin-r20</version>
+    <version>2.4.1-kylin-r22</version>
     <relativePath>../pom.xml</relativePath>
   </parent>
 

diff --git a/hadoop-cloud/pom.xml b/hadoop-cloud/pom.xml
@@ -22,7 +22,7 @@
   <parent>
     <groupId>org.apache.spark</groupId>
     <artifactId>spark-parent_2.11</artifactId>
-    <version>2.4.1-kylin-r20</version>
+    <version>2.4.1-kylin-r22</version>
     <relativePath>../pom.xml</relativePath>
   </parent>
 

diff --git a/launcher/pom.xml b/launcher/pom.xml
@@ -22,7 +22,7 @@
   <parent>
     <groupId>org.apache.spark</groupId>
     <artifactId>spark-parent_2.11</artifactId>
-    <version>2.4.1-kylin-r20</version>
+    <version>2.4.1-kylin-r22</version>
     <relativePath>../pom.xml</relativePath>
   </parent>
 

diff --git a/mllib-local/pom.xml b/mllib-local/pom.xml
@@ -21,7 +21,7 @@
   <parent>
     <groupId>org.apache.spark</groupId>
     <artifactId>spark-parent_2.11</artifactId>
-    <version>2.4.1-kylin-r20</version>
+    <version>2.4.1-kylin-r22</version>
     <relativePath>../pom.xml</relativePath>
   </parent>
 

diff --git a/mllib/pom.xml b/mllib/pom.xml
@@ -21,7 +21,7 @@
   <parent>
     <groupId>org.apache.spark</groupId>
     <artifactId>spark-parent_2.11</artifactId>
-    <version>2.4.1-kylin-r20</version>
+    <version>2.4.1-kylin-r22</version>
     <relativePath>../pom.xml</relativePath>
   </parent>
 

diff --git a/pom.xml b/pom.xml
@@ -26,7 +26,7 @@
   </parent>
   <groupId>org.apache.spark</groupId>
   <artifactId>spark-parent_2.11</artifactId>
-  <version>2.4.1-kylin-r20</version>
+  <version>2.4.1-kylin-r22</version>
   <packaging>pom</packaging>
   <name>Spark Project Parent POM</name>
   <url>http://spark.apache.org/</url>

diff --git a/repl/pom.xml b/repl/pom.xml
@@ -21,7 +21,7 @@
   <parent>
     <groupId>org.apache.spark</groupId>
     <artifactId>spark-parent_2.11</artifactId>
-    <version>2.4.1-kylin-r20</version>
+    <version>2.4.1-kylin-r22</version>
     <relativePath>../pom.xml</relativePath>
   </parent>
 

diff --git a/resource-managers/kubernetes/core/pom.xml b/resource-managers/kubernetes/core/pom.xml
@@ -20,7 +20,7 @@
   <parent>
     <groupId>org.apache.spark</groupId>
     <artifactId>spark-parent_2.11</artifactId>
-    <version>2.4.1-kylin-r20</version>
+    <version>2.4.1-kylin-r22</version>
     <relativePath>../../../pom.xml</relativePath>
   </parent>
 

diff --git a/resource-managers/kubernetes/integration-tests/pom.xml b/resource-managers/kubernetes/integration-tests/pom.xml
@@ -20,7 +20,7 @@
   <parent>
     <groupId>org.apache.spark</groupId>
     <artifactId>spark-parent_2.11</artifactId>
-    <version>2.4.1-kylin-r20</version>
+    <version>2.4.1-kylin-r22</version>
     <relativePath>../../../pom.xml</relativePath>
   </parent>
 

diff --git a/resource-managers/mesos/pom.xml b/resource-managers/mesos/pom.xml
@@ -20,7 +20,7 @@
   <parent>
     <groupId>org.apache.spark</groupId>
     <artifactId>spark-parent_2.11</artifactId>
-    <version>2.4.1-kylin-r20</version>
+    <version>2.4.1-kylin-r22</version>
     <relativePath>../../pom.xml</relativePath>
   </parent>
 

diff --git a/resource-managers/yarn/pom.xml b/resource-managers/yarn/pom.xml
@@ -20,7 +20,7 @@
   <parent>
     <groupId>org.apache.spark</groupId>
     <artifactId>spark-parent_2.11</artifactId>
-    <version>2.4.1-kylin-r20</version>
+    <version>2.4.1-kylin-r22</version>
     <relativePath>../../pom.xml</relativePath>
   </parent>
 

diff --git a/sql/catalyst/pom.xml b/sql/catalyst/pom.xml
@@ -22,7 +22,7 @@
   <parent>
     <groupId>org.apache.spark</groupId>
     <artifactId>spark-parent_2.11</artifactId>
-    <version>2.4.1-kylin-r20</version>
+    <version>2.4.1-kylin-r22</version>
     <relativePath>../../pom.xml</relativePath>
   </parent>
 

diff --git a/sql/core/pom.xml b/sql/core/pom.xml
@@ -22,7 +22,7 @@
   <parent>
     <groupId>org.apache.spark</groupId>
     <artifactId>spark-parent_2.11</artifactId>
-    <version>2.4.1-kylin-r20</version>
+    <version>2.4.1-kylin-r22</version>
     <relativePath>../../pom.xml</relativePath>
   </parent>
 

diff --git a/...src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetFileFormat.scala b/...src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetFileFormat.scala
@@ -31,6 +31,7 @@ import org.apache.hadoop.mapreduce.lib.input.FileSplit
 import org.apache.hadoop.mapreduce.task.TaskAttemptContextImpl
 import org.apache.parquet.filter2.compat.FilterCompat
 import org.apache.parquet.filter2.predicate.FilterApi
+import org.apache.parquet.format.ParquetMetrics
 import org.apache.parquet.format.converter.ParquetMetadataConverter.SKIP_ROW_GROUPS
 import org.apache.parquet.hadoop._
 import org.apache.parquet.hadoop.ParquetOutputFormat.JobSummaryLevel
@@ -64,6 +65,8 @@ class ParquetFileFormat
   // here.
   private val parquetLogRedirector = ParquetLogRedirector.INSTANCE
 
+  private val metric = new ParquetMetric
+
   override def shortName(): String = "parquet"
 
   override def toString: String = "Parquet"
@@ -326,7 +329,9 @@ class ParquetFileFormat
 
     val broadcastedHadoopConf =
       sparkSession.sparkContext.broadcast(new SerializableConfiguration(hadoopConf))
-
+    if (!metric.isRegistered()) {
+      metric.register(sparkSession.sparkContext)
+    }
     // TODO: if you move this into the closure it reverts to the default values.
     // If true, enable using the custom RecordReader for parquet. This only works for
     // a subset of the types (no complex types).
@@ -409,7 +414,7 @@ class ParquetFileFormat
         ParquetInputFormat.setFilterPredicate(hadoopAttemptContext.getConfiguration, pushed.get)
       }
       val taskContext = Option(TaskContext.get())
-      if (enableVectorizedReader) {
+      val iter = if (enableVectorizedReader) {
         val vectorizedReader = new VectorizedParquetRecordReader(
           convertTz.orNull, enableOffHeapColumnVector && taskContext.isDefined, capacity)
         val iter = new RecordReaderIterator(vectorizedReader)
@@ -453,6 +458,36 @@ class ParquetFileFormat
             .map(d => appendPartitionColumns(joinedRow(d, file.partitionValues)))
         }
       }
+      val metrics = ParquetMetrics.get()
+      metric._pageReadHeaderTime.setValue(metrics.getPageReadHeaderTime)
+      metric._pageReadHeaderCnt.setValue(metrics.getPageReadHeaderCnt)
+
+      metric._footerReadTime.setValue(metrics.getFooterReadTime)
+      metric._footerReadCnt.setValue(metrics.getFooterReadCnt)
+
+      metric._groupReadTime.setValue(metrics.getGroupReadTime)
+      metric._groupReadCnt.setValue(metrics.getGroupReadCnt)
+
+      metric._pageReadTime.setValue(metrics.getPageReadTime)
+      metric._pageReadCnt.setValue(metrics.getPageReadCnt)
+
+      metric._filteredGroupReadTime.setValue(metrics.getFilteredGroupReadTime)
+      metric._filteredGroupReadCnt.setValue(metrics.getFilteredGroupReadTime)
+
+      metric._pageReadDecompressTime.setValue(metrics.getPageReadDecompressTime)
+      metric._pageReadUncompressBytes.setValue(metrics.getPageReadUncompressBytes)
+      metric._pageReadDecompressBytes.setValue(metrics.getPageReadDecompressBytes)
+
+      metric._totalPages.setValue(metrics.getTotalPages)
+
+      metric._colPageIndexReadTime.setValue(metrics.getColPageIndexReadTime)
+      metric._colPageIndexReadCnt.setValue(metrics.getColPageIndexReadCnt)
+
+      metric._offsetPageIndexReadTime.setValue(metrics.getOffsetPageIndexReadTime)
+      metric._offsetPageIndexReadCnt.setValue(metrics.getOffsetPageIndexReadCnt)
+
+      metric._totalTime.setValue(metrics.getTotalTime)
+      iter
     }
   }