Github user zsxwing commented on a diff in the pull request: https://github.com/apache/spark/pull/18199#discussion_r120200602 --- Diff: sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/RateSourceProvider.scala --- @@ -0,0 +1,229 @@ +/* + * 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.streaming + +import java.io._ +import java.nio.charset.StandardCharsets +import java.util.concurrent.TimeUnit + +import org.apache.commons.io.IOUtils + +import org.apache.spark.internal.Logging +import org.apache.spark.sql.{DataFrame, SQLContext} +import org.apache.spark.sql.catalyst.InternalRow +import org.apache.spark.sql.catalyst.util.{CaseInsensitiveMap, DateTimeUtils} +import org.apache.spark.sql.sources.{DataSourceRegister, StreamSourceProvider} +import org.apache.spark.sql.types._ +import org.apache.spark.util.{ManualClock, SystemClock} + +/** + * A source that generates increment long values with timestamps. Each generated row has two + * columns: a timestamp column for the generated time and an auto increment long column starting + * with 0L. + * + * This source supports the following options: + * - `tuplesPerSecond` (default: 1): How many tuples should be generated per second. + * - `rampUpTimeSeconds` (default: 0): How many seconds to ramp up before the generating speed + * becomes `tuplesPerSecond`. + * - `numPartitions` (default: Spark's default parallelism): The partition number for the generated + * tuples. + */ +class RateSourceProvider extends StreamSourceProvider with DataSourceRegister { + + override def sourceSchema( + sqlContext: SQLContext, + schema: Option[StructType], + providerName: String, + parameters: Map[String, String]): (String, StructType) = + (shortName(), RateSourceProvider.SCHEMA) + + override def createSource( + sqlContext: SQLContext, + metadataPath: String, + schema: Option[StructType], + providerName: String, + parameters: Map[String, String]): Source = { + val params = CaseInsensitiveMap(parameters) + + val tuplesPerSecond = params.get("tuplesPerSecond").map(_.toLong).getOrElse(1L) + if (tuplesPerSecond <= 0) { + throw new IllegalArgumentException( + s"Invalid value '${params("tuplesPerSecond")}' for option 'tuplesPerSecond', " + + "must be positive") + } + + val rampUpTimeSeconds = params.get("rampUpTimeSeconds").map(_.toLong).getOrElse(0L) + if (rampUpTimeSeconds < 0) { + throw new IllegalArgumentException( + s"Invalid value '${params("rampUpTimeSeconds")}' for option 'rampUpTimeSeconds', " + + "must not be negative") + } + + val numPartitions = params.get("numPartitions").map(_.toInt).getOrElse( + sqlContext.sparkContext.defaultParallelism) + if (numPartitions <= 0) { + throw new IllegalArgumentException( + s"Invalid value '${params("numPartitions")}' for option 'numPartitions', " + + "must be positive") + } + + new RateStreamSource( + sqlContext, + metadataPath, + tuplesPerSecond, + rampUpTimeSeconds, + numPartitions, + params.get("useManualClock").map(_.toBoolean).getOrElse(false) // Only for testing + ) + } + override def shortName(): String = "rate" +} + +object RateSourceProvider { + val SCHEMA = + StructType(StructField("timestamp", TimestampType) :: StructField("value", LongType) :: Nil) + + val VERSION = 1 +} + +class RateStreamSource( + sqlContext: SQLContext, + metadataPath: String, + tuplesPerSecond: Long, + rampUpTimeSeconds: Long, + numPartitions: Int, + useManualClock: Boolean) extends Source with Logging { + + import RateSourceProvider._ + import RateStreamSource._ + + val clock = if (useManualClock) new ManualClock else new SystemClock + + private val maxSeconds = Long.MaxValue / tuplesPerSecond --- End diff -- This will be <= the real max allowed seconds because it doesn't take `rampUpTimeSeconds` into consideration. I don't find a simple way to detect overflow quickly with `rampUpTimeSeconds`. However, this should be fine because the user usually won't hit this problem. The overflow detection is just to not surprise people because `range` will return an empty RDD if overflow happens (See the below codes). ``` scala> sc.range(Long.MaxValue, -2, 1).count() res0: Long = 0 ```
--- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org