[GitHub] [spark] pgandhi999 opened a new pull request #24035: [SPARK-27112] : Spark Scheduler encounters two independent Deadlocks …

[GitBox]

pgandhi999 opened a new pull request #24035: [SPARK-27112] : Spark Scheduler 
encounters two independent Deadlocks …
URL: https://github.com/apache/spark/pull/24035
 
 
   …when trying to kill executors either due to dynamic allocation or 
blacklisting
   
   Recently, a few spark users in the organization have reported that their 
jobs were getting stuck. On further analysis, it was found out that there exist 
two independent deadlocks and either of them occur under different 
circumstances. The screenshots for these two deadlocks are attached here. 
   
   We were able to reproduce the deadlocks with the following piece of code:
   
   `import org.apache.hadoop.conf.Configuration
   import org.apache.hadoop.fs.{FileSystem, Path}
   
   import org.apache.spark._
   import org.apache.spark.TaskContext
   
   // Simple example of Word Count in Scala
   object ScalaWordCount {
   def main(args: Array[String]) {
   
   if (args.length < 2) {
   System.err.println("Usage: ScalaWordCount <inputFilesURI> <outputFilesUri>")
   System.exit(1)
   }
   
   val conf = new SparkConf().setAppName("Scala Word Count")
   val sc = new SparkContext(conf)
   
   // get the input file uri
   val inputFilesUri = args(0)
   
   // get the output file uri
   val outputFilesUri = args(1)
   
   while (true) {
   val textFile = sc.textFile(inputFilesUri)
   val counts = textFile.flatMap(line => line.split(" "))
   .map(word => {if (TaskContext.get.partitionId == 5 && 
TaskContext.get.attemptNumber == 0) throw new Exception("Fail for 
blacklisting") else (word, 1)})
   .reduceByKey(_ + _)
   counts.saveAsTextFile(outputFilesUri)
   val conf: Configuration = new Configuration()
   val path: Path = new Path(outputFilesUri)
   val hdfs: FileSystem = FileSystem.get(conf)
   hdfs.delete(path, true)
   }
   
   sc.stop()
   }
   }`
   
   Additionally, to ensure that the deadlock surfaces up soon enough, I also 
added a small delay in the Spark code here:
   
   
https://github.com/apache/spark/blob/master/core/src/main/scala/org/apache/spark/scheduler/BlacklistTracker.scala#L256
   
   `executorIdToFailureList.remove(exec)
   updateNextExpiryTime()
   Thread.sleep(2000)
   killBlacklistedExecutor(exec)`
   
   Screenshots for deadlock between task-result-getter-thread and 
spark-dynamic-executor-allocation thread:
   <img width="1417" alt="Screen Shot 2019-02-26 at 4 10 26 PM" 
src="https://user-images.githubusercontent.com/22228190/54062129-de943e80-41c9-11e9-8c62-cc810b7be74d.png";>
   
   <img width="1416" alt="Screen Shot 2019-02-26 at 4 10 48 PM" 
src="https://user-images.githubusercontent.com/22228190/54062135-e653e300-41c9-11e9-99a2-7569045487bd.png";>
   
   Screenshots for deadlock between task-result-getter-thread and 
dispatcher-event-loop thread:
   
   <img width="1417" alt="Screen Shot 2019-02-26 at 4 11 11 PM" 
src="https://user-images.githubusercontent.com/22228190/54062148-fc61a380-41c9-11e9-9014-9199b46863d8.png";>
   
   <img width="1417" alt="Screen Shot 2019-02-26 at 4 11 26 PM" 
src="https://user-images.githubusercontent.com/22228190/54062150-01beee00-41ca-11e9-8d0b-a7a1836a4e11.png";>
   
   
   
   ## What changes were proposed in this pull request?
   
   There are two deadlocks as a result of the interplay between three different 
threads:
   
   task-result-getter thread
   
   spark-dynamic-executor-allocation thread
   
   dispatcher-event-loop thread(makeOffers())
   
   The fix for the deadlock between dynamic allocation thread and result getter 
thread involves moving the method isExecutorBusy outside of the lock 
CoarseGrainedSchedulerBackend.this.
   
   The fix for the deadlock between event loop thread and result getter thread 
involves removing synchronized on CoarseGrainedSchedulerBackend.this. The same 
synchronization has been replaced by a dummy lock to ensure synchronization 
between dynamic allocation thread and event loop thread.
   
   
   ## How was this patch tested?
   
   The code used to reproduce the deadlock issue is documented above.
   

----------------------------------------------------------------
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:
us...@infra.apache.org


With regards,
Apache Git Services

---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org