Github user HyukjinKwon commented on a diff in the pull request:
https://github.com/apache/spark/pull/20937#discussion_r184851188
--- Diff:
sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/json/JsonBenchmarks.scala
---
@@ -0,0 +1,179 @@
+/*
+ * 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.datasources.json
+
+import java.io.File
+
+import org.apache.spark.SparkConf
+import org.apache.spark.sql.SparkSession
+import org.apache.spark.sql.types.{LongType, StringType, StructType}
+import org.apache.spark.util.{Benchmark, Utils}
+
+/**
+ * Benchmark to measure JSON read/write performance.
+ * To run this:
+ * spark-submit --class <this class> --jars <spark sql test jar>
+ */
+object JSONBenchmarks {
+ val conf = new SparkConf()
+
+ val spark = SparkSession.builder
+ .master("local[1]")
+ .appName("benchmark-json-datasource")
+ .config(conf)
+ .getOrCreate()
+ import spark.implicits._
+
+ def withTempPath(f: File => Unit): Unit = {
+ val path = Utils.createTempDir()
+ path.delete()
+ try f(path) finally Utils.deleteRecursively(path)
+ }
+
+
+ def schemaInferring(rowsNum: Int): Unit = {
+ val benchmark = new Benchmark("JSON schema inferring", rowsNum)
+
+ withTempPath { path =>
+ // scalastyle:off
+ benchmark.out.println("Preparing data for benchmarking ...")
+ // scalastyle:on
+
+ spark.sparkContext.range(0, rowsNum, 1)
+ .map(_ => "a")
+ .toDF("fieldA")
+ .write
+ .option("encoding", "UTF-8")
+ .json(path.getAbsolutePath)
+
+ benchmark.addCase("No encoding", 3) { _ =>
+ spark.read.json(path.getAbsolutePath)
+ }
+
+ benchmark.addCase("UTF-8 is set", 3) { _ =>
+ spark.read
+ .option("encoding", "UTF-8")
+ .json(path.getAbsolutePath)
+ }
+
+ /*
+ Intel(R) Core(TM) i7-7920HQ CPU @ 3.10GHz
+
+ JSON schema inferring: Best/Avg Time(ms) Rate(M/s)
Per Row(ns) Relative
+
--------------------------------------------------------------------------------------------
+ No encoding 38902 / 39282 2.6
389.0 1.0X
+ UTF-8 is set 56959 / 57261 1.8
569.6 0.7X
+ */
+ benchmark.run()
+ }
+ }
+
+ def perlineParsing(rowsNum: Int): Unit = {
+ val benchmark = new Benchmark("JSON per-line parsing", rowsNum)
+
+ withTempPath { path =>
+ // scalastyle:off
--- End diff --
ditto
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
