[GitHub] [incubator-iceberg] aokolnychyi commented on a change in pull request #900: Spark: Add ORC JMH tests for IcebergSource

[GitBox <gi...@apache.org>]

aokolnychyi commented on a change in pull request #900: Spark: Add ORC JMH tests for IcebergSource
URL: https://github.com/apache/incubator-iceberg/pull/900#discussion_r406515860
 
 

 ##########
 File path: spark/src/jmh/java/org/apache/iceberg/spark/source/orc/IcebergSourceFlatORCDataBenchmark.java
 ##########
 @@ -0,0 +1,67 @@
+/*
+ * 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.iceberg.spark.source.orc;
+
+import com.google.common.collect.Maps;
+import java.util.Map;
+import org.apache.hadoop.conf.Configuration;
+import org.apache.iceberg.PartitionSpec;
+import org.apache.iceberg.Schema;
+import org.apache.iceberg.Table;
+import org.apache.iceberg.TableProperties;
+import org.apache.iceberg.hadoop.HadoopTables;
+import org.apache.iceberg.spark.source.IcebergSourceBenchmark;
+import org.apache.iceberg.types.Types;
+
+import static org.apache.iceberg.types.Types.NestedField.optional;
+import static org.apache.iceberg.types.Types.NestedField.required;
+
+
+/**
+ * Same as {@link org.apache.iceberg.spark.source.IcebergSourceFlatDataBenchmark} but we disable the Timestamp with
+ * zone type for ORC performance tests as Spark native reader does not support ORC's TIMESTAMP_INSTANT type
+ */
+public abstract class IcebergSourceFlatORCDataBenchmark extends IcebergSourceBenchmark {
+
+  @Override
+  protected Configuration initHadoopConf() {
+    return new Configuration();
+  }
+
+  @Override
+  protected final Table initTable() {
+    Schema schema = new Schema(
+        required(1, "longCol", Types.LongType.get()),
+        required(2, "intCol", Types.IntegerType.get()),
+        required(3, "floatCol", Types.FloatType.get()),
+        optional(4, "doubleCol", Types.DoubleType.get()),
+        optional(5, "decimalCol", Types.DecimalType.of(20, 5)),
+        optional(6, "dateCol", Types.DateType.get()),
+        // Disable timestamp column for ORC performance tests as Spark native reader does not support ORC's
 
 Review comment:
   Will switching to `TimestampType.withoutZone()` in `IcebergSourceFlatDataBenchmark` help?

----------------------------------------------------------------
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:
users@infra.apache.org


With regards,
Apache Git Services

---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@iceberg.apache.org
For additional commands, e-mail: issues-help@iceberg.apache.org