diff options
author | Matei Zaharia <matei@eecs.berkeley.edu> | 2013-01-29 18:12:29 -0800 |
---|---|---|
committer | Matei Zaharia <matei@eecs.berkeley.edu> | 2013-01-29 18:12:29 -0800 |
commit | d54b10b6ad25ebf29f8ca7f438131ed6a9af24ab (patch) | |
tree | 90e585f81fc8e0f56f76f29d81e393f819fe6cd0 | |
parent | ccb67ff2cae366973a1a2e7eac57db4e861a4ca7 (diff) | |
parent | 98d0b7747d7539db009a9bbc261f899955871524 (diff) | |
download | spark-d54b10b6ad25ebf29f8ca7f438131ed6a9af24ab.tar.gz spark-d54b10b6ad25ebf29f8ca7f438131ed6a9af24ab.tar.bz2 spark-d54b10b6ad25ebf29f8ca7f438131ed6a9af24ab.zip |
Merge remote-tracking branch 'stephenh/removefailedjob'
Conflicts:
core/src/main/scala/spark/deploy/master/Master.scala
-rw-r--r-- | core/src/main/scala/spark/deploy/master/Master.scala | 6 | ||||
-rw-r--r-- | core/src/main/scala/spark/deploy/worker/Worker.scala | 10 |
2 files changed, 9 insertions, 7 deletions
diff --git a/core/src/main/scala/spark/deploy/master/Master.scala b/core/src/main/scala/spark/deploy/master/Master.scala index bc53b70015..c618e87cdd 100644 --- a/core/src/main/scala/spark/deploy/master/Master.scala +++ b/core/src/main/scala/spark/deploy/master/Master.scala @@ -100,11 +100,9 @@ private[spark] class Master(ip: String, port: Int, webUiPort: Int) extends Actor if (jobInfo.incrementRetryCount < JobState.MAX_NUM_RETRY) { schedule() } else { - val e = new SparkException("Job %s with ID %s failed %d times.".format( + logError("Job %s with ID %s failed %d times, removing it".format( jobInfo.desc.name, jobInfo.id, jobInfo.retryCount)) - logError(e.getMessage, e) - throw e - //System.exit(1) + removeJob(jobInfo) } } } diff --git a/core/src/main/scala/spark/deploy/worker/Worker.scala b/core/src/main/scala/spark/deploy/worker/Worker.scala index 19bf2be118..5a83a42daf 100644 --- a/core/src/main/scala/spark/deploy/worker/Worker.scala +++ b/core/src/main/scala/spark/deploy/worker/Worker.scala @@ -143,9 +143,13 @@ private[spark] class Worker( case KillExecutor(jobId, execId) => val fullId = jobId + "/" + execId - val executor = executors(fullId) - logInfo("Asked to kill executor " + fullId) - executor.kill() + executors.get(fullId) match { + case Some(executor) => + logInfo("Asked to kill executor " + fullId) + executor.kill() + case None => + logInfo("Asked to kill unknown executor " + fullId) + } case Terminated(_) | RemoteClientDisconnected(_, _) | RemoteClientShutdown(_, _) => masterDisconnected() |