Github user jiangxb1987 commented on a diff in the pull request:
https://github.com/apache/spark/pull/17617#discussion_r118830572
--- Diff:
core/src/test/scala/org/apache/spark/metrics/InputOutputMetricsSuite.scala ---
@@ -319,6 +319,45 @@ class InputOutputMetricsSuite extends SparkFunSuite
with SharedSparkContext
}
assert(bytesRead >= tmpFile.length())
}
+
+ test("input metrics with old Hadoop API in different thread") {
+ val bytesRead = runAndReturnBytesRead {
+ sc.textFile(tmpFilePath, 4).mapPartitions { iter =>
+ val buf = new ArrayBuffer[String]()
+ val thread = new Thread() {
+ override def run(): Unit = {
+ iter.flatMap(_.split(" ")).foreach(buf.append(_))
+ }
+ }
+ thread.start()
+ thread.join()
+
+ buf.iterator
+ }.count()
+ }
+ assert(bytesRead != 0)
+ assert(bytesRead >= tmpFile.length())
+ }
+
+ test("input metrics with new Hadoop API in different thread") {
+ val bytesRead = runAndReturnBytesRead {
+ sc.newAPIHadoopFile(tmpFilePath, classOf[NewTextInputFormat],
classOf[LongWritable],
+ classOf[Text]).mapPartitions { iter =>
+ val buf = new ArrayBuffer[String]()
+ val thread = new Thread() {
--- End diff --
nit: Same as above, we could rewrite to:
```
ThreadUtils.runInNewThread("TestThread") {
iter.map(_._2.toString).flatMap(_.split("
")).foreach(buf.append(_))
}
```
---
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 [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
