kunal642 commented on a change in pull request #3308: [CARBONDATA-3454] optimized index server output for count(*)
URL:
https://github.com/apache/carbondata/pull/3308#discussion_r312337684
##########
File path: integration/spark2/src/main/scala/org/apache/carbondata/indexserver/DistributedCountRDD.scala
##########
@@ -0,0 +1,126 @@
+/*
+ * 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.carbondata.indexserver
+
+import java.text.SimpleDateFormat
+import java.util.Date
+import java.util.concurrent.Executors
+
+import scala.collection.JavaConverters._
+import scala.concurrent.{Await, ExecutionContext, ExecutionContextExecutor, Future}
+import scala.concurrent.duration.Duration
+
+import org.apache.hadoop.mapred.TaskAttemptID
+import org.apache.hadoop.mapreduce.{InputSplit, TaskType}
+import org.apache.hadoop.mapreduce.task.TaskAttemptContextImpl
+import org.apache.spark.{Partition, SparkEnv, TaskContext}
+import org.apache.spark.sql.SparkSession
+
+import org.apache.carbondata.common.logging.LogServiceFactory
+import org.apache.carbondata.core.cache.CacheProvider
+import org.apache.carbondata.core.datamap.{DataMapStoreManager, DistributableDataMapFormat}
+import org.apache.carbondata.core.datamap.dev.expr.DataMapDistributableWrapper
+import org.apache.carbondata.core.datastore.impl.FileFactory
+import org.apache.carbondata.core.util.{CarbonProperties, CarbonThreadFactory}
+import org.apache.carbondata.spark.rdd.CarbonRDD
+
+class DistributedCountRDD(@transient ss: SparkSession, dataMapFormat: DistributableDataMapFormat)
+ extends CarbonRDD[(String, String)](ss, Nil) {
+
+ @transient private val LOGGER = LogServiceFactory.getLogService(classOf[DistributedPruneRDD]
+ .getName)
+
+ private val jobTrackerId: String = {
+ val formatter = new SimpleDateFormat("yyyyMMddHHmm")
+ formatter.format(new Date())
+ }
+
+ override protected def getPreferredLocations(split: Partition): Seq[String] = {
+ if (split.asInstanceOf[DataMapRDDPartition].getLocations != null) {
+ split.asInstanceOf[DataMapRDDPartition].getLocations.toSeq
+ } else {
+ Seq()
+ }
+ }
+
+ private def groupSplits(xs: Seq[InputSplit], n: Int) = {
+ val (quot, rem) = (xs.size / n, xs.size % n)
+ val (smaller, bigger) = xs.splitAt(xs.size - rem * (quot + 1))
+ (smaller.grouped(quot) ++ bigger.grouped(quot + 1)).toList
+ }
+
+ override def internalCompute(split: Partition,
+ context: TaskContext): Iterator[(String, String)] = {
+ val attemptId = new TaskAttemptID(jobTrackerId, id, TaskType.MAP, split.index, 0)
Review comment:
extracted some parts but internalCompute logic is different
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[hidden email]
With regards,
Apache Git Services
Locked
