[jira] [Commented] (SPARK-19698) Race condition in stale attempt task completion vs current attempt task completion when task is doing persistent state changes
[ https://issues.apache.org/jira/browse/SPARK-19698?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15883331#comment-15883331 ] Charles Allen commented on SPARK-19698: --- [~mridulm80] is there documentation somewhere that describes the output commit best practices? I see a bunch of things that seem to have either the hadoop MR output committer, or some Spark specific output committing stuff, but it is not clear when each should be used. > Race condition in stale attempt task completion vs current attempt task > completion when task is doing persistent state changes > -- > > Key: SPARK-19698 > URL: https://issues.apache.org/jira/browse/SPARK-19698 > Project: Spark > Issue Type: Bug > Components: Mesos, Spark Core >Affects Versions: 2.0.0 >Reporter: Charles Allen > > We have encountered a strange scenario in our production environment. Below > is the best guess we have right now as to what's going on. > Potentially, the final stage of a job has a failure in one of the tasks (such > as OOME on the executor) which can cause tasks for that stage to be > relaunched in a second attempt. > https://github.com/apache/spark/blob/v2.1.0/core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala#L1155 > keeps track of which tasks have been completed, but does NOT keep track of > which attempt those tasks were completed in. As such, we have encountered a > scenario where a particular task gets executed twice in different stage > attempts, and the DAGScheduler does not consider if the second attempt is > still running. This means if the first task attempt succeeded, the second > attempt can be cancelled part-way through its run cycle if all other tasks > (including the prior failed) are completed successfully. > What this means is that if a task is manipulating some state somewhere (for > example: a upload-to-temporary-file-location, then delete-then-move on an > underlying s3n storage implementation) the driver can improperly shutdown the > running (2nd attempt) task between state manipulations, leaving the > persistent state in a bad state since the 2nd attempt never got to complete > its manipulations, and was terminated prematurely at some arbitrary point in > its state change logic (ex: finished the delete but not the move). > This is using the mesos coarse grained executor. It is unclear if this > behavior is limited to the mesos coarse grained executor or not. -- This message was sent by Atlassian JIRA (v6.3.15#6346) - To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org For additional commands, e-mail: issues-h...@spark.apache.org
[jira] [Commented] (SPARK-19698) Race condition in stale attempt task completion vs current attempt task completion when task is doing persistent state changes
[ https://issues.apache.org/jira/browse/SPARK-19698?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15881991#comment-15881991 ] Mridul Muralidharan commented on SPARK-19698: - Depending on ordering and semantics of task resubmission is not a very good design choice. For the usecase described, would be better to use an external synchronization mechanism - and not depend on how spark would (re-)submit tasks : not only is it not an implementation detail, but it is subject to change without an explicit contract - the only explicit contract we have is with OutputCommitter > Race condition in stale attempt task completion vs current attempt task > completion when task is doing persistent state changes > -- > > Key: SPARK-19698 > URL: https://issues.apache.org/jira/browse/SPARK-19698 > Project: Spark > Issue Type: Bug > Components: Mesos, Spark Core >Affects Versions: 2.0.0 >Reporter: Charles Allen > > We have encountered a strange scenario in our production environment. Below > is the best guess we have right now as to what's going on. > Potentially, the final stage of a job has a failure in one of the tasks (such > as OOME on the executor) which can cause tasks for that stage to be > relaunched in a second attempt. > https://github.com/apache/spark/blob/v2.1.0/core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala#L1155 > keeps track of which tasks have been completed, but does NOT keep track of > which attempt those tasks were completed in. As such, we have encountered a > scenario where a particular task gets executed twice in different stage > attempts, and the DAGScheduler does not consider if the second attempt is > still running. This means if the first task attempt succeeded, the second > attempt can be cancelled part-way through its run cycle if all other tasks > (including the prior failed) are completed successfully. > What this means is that if a task is manipulating some state somewhere (for > example: a upload-to-temporary-file-location, then delete-then-move on an > underlying s3n storage implementation) the driver can improperly shutdown the > running (2nd attempt) task between state manipulations, leaving the > persistent state in a bad state since the 2nd attempt never got to complete > its manipulations, and was terminated prematurely at some arbitrary point in > its state change logic (ex: finished the delete but not the move). > This is using the mesos coarse grained executor. It is unclear if this > behavior is limited to the mesos coarse grained executor or not. -- This message was sent by Atlassian JIRA (v6.3.15#6346) - To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org For additional commands, e-mail: issues-h...@spark.apache.org
[jira] [Commented] (SPARK-19698) Race condition in stale attempt task completion vs current attempt task completion when task is doing persistent state changes
[ https://issues.apache.org/jira/browse/SPARK-19698?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15881771#comment-15881771 ] Jisoo Kim commented on SPARK-19698: --- Ah, I see what you mean. I don't use Spark's speculation feature, so I wasn't aware that the running tasks won't be killed when their speculative copies get restarted. What is the reason behind not killing the stale tasks that were overridden? Is that for performance? I found that TaskSetManager will kill all the other attempts for the specific task when one of the attempts succeeds: https://github.com/apache/spark/blob/d9043092caf71d5fa6be18ae8c51a0158bc2218e/core/src/main/scala/org/apache/spark/scheduler/TaskSetManager.scala#L709 However, the above scenario still concerns me in case the task has some other long-running computation after modifying external state. In that case, Attempt 1 can be launched after Attempt 0 finishes modifying external state (but is still doing some computation) and gets partway through its own modification. I think in this case if Attempt 1 gets killed or all other partitions are "finished" before Attempt 1 finishes, the same problem can happen. I wonder if this approach is a viable solution: - Have additional information (task attemptNumber from task info) when adding the task index to speculableTasks (https://github.com/apache/spark/blob/d9043092caf71d5fa6be18ae8c51a0158bc2218e/core/src/main/scala/org/apache/spark/scheduler/TaskSetManager.scala#L937) - Have TaskSetManager to notify the driver only when the completed task is not inside speculableTasks (https://github.com/apache/spark/blob/d9043092caf71d5fa6be18ae8c51a0158bc2218e/core/src/main/scala/org/apache/spark/scheduler/TaskSetManager.scala#L706) > Race condition in stale attempt task completion vs current attempt task > completion when task is doing persistent state changes > -- > > Key: SPARK-19698 > URL: https://issues.apache.org/jira/browse/SPARK-19698 > Project: Spark > Issue Type: Bug > Components: Mesos, Spark Core >Affects Versions: 2.0.0 >Reporter: Charles Allen > > We have encountered a strange scenario in our production environment. Below > is the best guess we have right now as to what's going on. > Potentially, the final stage of a job has a failure in one of the tasks (such > as OOME on the executor) which can cause tasks for that stage to be > relaunched in a second attempt. > https://github.com/apache/spark/blob/v2.1.0/core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala#L1155 > keeps track of which tasks have been completed, but does NOT keep track of > which attempt those tasks were completed in. As such, we have encountered a > scenario where a particular task gets executed twice in different stage > attempts, and the DAGScheduler does not consider if the second attempt is > still running. This means if the first task attempt succeeded, the second > attempt can be cancelled part-way through its run cycle if all other tasks > (including the prior failed) are completed successfully. > What this means is that if a task is manipulating some state somewhere (for > example: a upload-to-temporary-file-location, then delete-then-move on an > underlying s3n storage implementation) the driver can improperly shutdown the > running (2nd attempt) task between state manipulations, leaving the > persistent state in a bad state since the 2nd attempt never got to complete > its manipulations, and was terminated prematurely at some arbitrary point in > its state change logic (ex: finished the delete but not the move). > This is using the mesos coarse grained executor. It is unclear if this > behavior is limited to the mesos coarse grained executor or not. -- This message was sent by Atlassian JIRA (v6.3.15#6346) - To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org For additional commands, e-mail: issues-h...@spark.apache.org
[jira] [Commented] (SPARK-19698) Race condition in stale attempt task completion vs current attempt task completion when task is doing persistent state changes
[ https://issues.apache.org/jira/browse/SPARK-19698?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15881688#comment-15881688 ] Kay Ousterhout commented on SPARK-19698: My concern is that there are other cases in Spark where this issue could arise (so Spark tasks need to be very careful about how they modify external state). Here's another scenario: - Attempt 0 of a task starts and takes a long time to run - A second, speculative copy of the task is started (attempt 1) - Attempt 0 finishes successfully, but attempt 1 is still running - Attempt 1 gets partway through modifying the external state, but then gets killed because of an OOM on the machine - Attempt 1 won't get re-started, because a copy of the task already finished successfully This seems like it will have the same issue you mentioned in the JIRA, right? > Race condition in stale attempt task completion vs current attempt task > completion when task is doing persistent state changes > -- > > Key: SPARK-19698 > URL: https://issues.apache.org/jira/browse/SPARK-19698 > Project: Spark > Issue Type: Bug > Components: Mesos, Spark Core >Affects Versions: 2.0.0 >Reporter: Charles Allen > > We have encountered a strange scenario in our production environment. Below > is the best guess we have right now as to what's going on. > Potentially, the final stage of a job has a failure in one of the tasks (such > as OOME on the executor) which can cause tasks for that stage to be > relaunched in a second attempt. > https://github.com/apache/spark/blob/v2.1.0/core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala#L1155 > keeps track of which tasks have been completed, but does NOT keep track of > which attempt those tasks were completed in. As such, we have encountered a > scenario where a particular task gets executed twice in different stage > attempts, and the DAGScheduler does not consider if the second attempt is > still running. This means if the first task attempt succeeded, the second > attempt can be cancelled part-way through its run cycle if all other tasks > (including the prior failed) are completed successfully. > What this means is that if a task is manipulating some state somewhere (for > example: a upload-to-temporary-file-location, then delete-then-move on an > underlying s3n storage implementation) the driver can improperly shutdown the > running (2nd attempt) task between state manipulations, leaving the > persistent state in a bad state since the 2nd attempt never got to complete > its manipulations, and was terminated prematurely at some arbitrary point in > its state change logic (ex: finished the delete but not the move). > This is using the mesos coarse grained executor. It is unclear if this > behavior is limited to the mesos coarse grained executor or not. -- This message was sent by Atlassian JIRA (v6.3.15#6346) - To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org For additional commands, e-mail: issues-h...@spark.apache.org
[jira] [Commented] (SPARK-19698) Race condition in stale attempt task completion vs current attempt task completion when task is doing persistent state changes
[ https://issues.apache.org/jira/browse/SPARK-19698?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15881644#comment-15881644 ] Jisoo Kim commented on SPARK-19698: --- [~kayousterhout] If the failed task gets re-tried, as long as Driver doesn't shut down before the next attempt finishes, it should be ok because the next attempt will upload a file as intended. That's actually similar to what happened in my workload, executor was lost due to OOME and stage was resubmitted eventually. If the driver didn't think that the job was done, things would've been fine. The driver didn't mark the partition that the failed task was responsible for as "finished", so in the next attempt, the task finished successfully (and there were no race condition for this specific task because the executor that was running this task was lost) but one of the other tasks had a such problem. One thing I am not sure about my solution is a possible performance regression, but I think it might be better than having some kind of an "incorrect" external state unless it is not recommended and not a good practice to have a task to modify some external state. > Race condition in stale attempt task completion vs current attempt task > completion when task is doing persistent state changes > -- > > Key: SPARK-19698 > URL: https://issues.apache.org/jira/browse/SPARK-19698 > Project: Spark > Issue Type: Bug > Components: Mesos, Spark Core >Affects Versions: 2.0.0 >Reporter: Charles Allen > > We have encountered a strange scenario in our production environment. Below > is the best guess we have right now as to what's going on. > Potentially, the final stage of a job has a failure in one of the tasks (such > as OOME on the executor) which can cause tasks for that stage to be > relaunched in a second attempt. > https://github.com/apache/spark/blob/v2.1.0/core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala#L1155 > keeps track of which tasks have been completed, but does NOT keep track of > which attempt those tasks were completed in. As such, we have encountered a > scenario where a particular task gets executed twice in different stage > attempts, and the DAGScheduler does not consider if the second attempt is > still running. This means if the first task attempt succeeded, the second > attempt can be cancelled part-way through its run cycle if all other tasks > (including the prior failed) are completed successfully. > What this means is that if a task is manipulating some state somewhere (for > example: a upload-to-temporary-file-location, then delete-then-move on an > underlying s3n storage implementation) the driver can improperly shutdown the > running (2nd attempt) task between state manipulations, leaving the > persistent state in a bad state since the 2nd attempt never got to complete > its manipulations, and was terminated prematurely at some arbitrary point in > its state change logic (ex: finished the delete but not the move). > This is using the mesos coarse grained executor. It is unclear if this > behavior is limited to the mesos coarse grained executor or not. -- This message was sent by Atlassian JIRA (v6.3.15#6346) - To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org For additional commands, e-mail: issues-h...@spark.apache.org
[jira] [Commented] (SPARK-19698) Race condition in stale attempt task completion vs current attempt task completion when task is doing persistent state changes
[ https://issues.apache.org/jira/browse/SPARK-19698?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15881564#comment-15881564 ] Kay Ousterhout commented on SPARK-19698: I see -- I agree that everything in your description is correct. The driver will allow all tasks to finish if it's still running (e.g., if other tasks are being submitted), but you're right it will shut down the workers while some tasks are still in progress if the Driver shuts down. To think about how to fix this, let me ask you a question about your workload: suppose a task is in the middle of manipulating some external state (as you described in the JIRA description) and it gets killed suddenly because the JVM runs out of memory (e.g., because another concurrently running task used up all of the memory). In that case, the job listener won't be told about the failed task, and it will be re-tried. Does that pose a problem in the same way that the behavior described in the PR is problematic? > Race condition in stale attempt task completion vs current attempt task > completion when task is doing persistent state changes > -- > > Key: SPARK-19698 > URL: https://issues.apache.org/jira/browse/SPARK-19698 > Project: Spark > Issue Type: Bug > Components: Mesos, Spark Core >Affects Versions: 2.0.0 >Reporter: Charles Allen > > We have encountered a strange scenario in our production environment. Below > is the best guess we have right now as to what's going on. > Potentially, the final stage of a job has a failure in one of the tasks (such > as OOME on the executor) which can cause tasks for that stage to be > relaunched in a second attempt. > https://github.com/apache/spark/blob/v2.1.0/core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala#L1155 > keeps track of which tasks have been completed, but does NOT keep track of > which attempt those tasks were completed in. As such, we have encountered a > scenario where a particular task gets executed twice in different stage > attempts, and the DAGScheduler does not consider if the second attempt is > still running. This means if the first task attempt succeeded, the second > attempt can be cancelled part-way through its run cycle if all other tasks > (including the prior failed) are completed successfully. > What this means is that if a task is manipulating some state somewhere (for > example: a upload-to-temporary-file-location, then delete-then-move on an > underlying s3n storage implementation) the driver can improperly shutdown the > running (2nd attempt) task between state manipulations, leaving the > persistent state in a bad state since the 2nd attempt never got to complete > its manipulations, and was terminated prematurely at some arbitrary point in > its state change logic (ex: finished the delete but not the move). > This is using the mesos coarse grained executor. It is unclear if this > behavior is limited to the mesos coarse grained executor or not. -- This message was sent by Atlassian JIRA (v6.3.15#6346) - To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org For additional commands, e-mail: issues-h...@spark.apache.org
[jira] [Commented] (SPARK-19698) Race condition in stale attempt task completion vs current attempt task completion when task is doing persistent state changes
[ https://issues.apache.org/jira/browse/SPARK-19698?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15881525#comment-15881525 ] Jisoo Kim commented on SPARK-19698: --- [~kayousterhout] Thanks for linking the JIRA ticket, I agree that the ticket describes a very similar problem that I had. However, I don't think that fixes the problem because the PR only deals with a problem in ShuffleMapStage and doesn't check the attempt Id in case of ResultStage. In my case, it was ResultStage that had the problem. I had run my test with a fix from (https://github.com/apache/spark/pull/16620) but it still failed. Could you point me to where driver will wait until all tasks finish? I tried finding the part but wasn't successful. I don't think Driver shuts down all tasks when a job is done, however, DAGScheduler signals the JobWaiter every time it receives completion event for a task that is responsible for unfinished partition (https://github.com/apache/spark/blob/ba8912e5f3d5c5a366cb3d1f6be91f2471d048d2/core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala#L1171). As a result, JobWaiter will call success() on the job promise (https://github.com/jinxing64/spark/blob/6809d1ff5d09693e961087da35c8f6b3b50fe53c/core/src/main/scala/org/apache/spark/scheduler/JobWaiter.scala#L61) before the 2nd task attempt finishes. This could not be of a problem if Driver waits until all tasks finish and SparkContext doesn't return results before all tasks finish, but I haven't found that it does yet (please correct me if I am missing something). I call SparkContext.stop() after I get the result from the application to clean up and upload event logs so I can view the spark history from the history server. And when SparkContext stops, AFAIK, it stops the Driver as well, which will shut down the task scheduler and executors, and I don't think executors will wait until it finishes its task before it shuts down. Hence, if this happens, the 2nd task attempt will get shut down as well I think. > Race condition in stale attempt task completion vs current attempt task > completion when task is doing persistent state changes > -- > > Key: SPARK-19698 > URL: https://issues.apache.org/jira/browse/SPARK-19698 > Project: Spark > Issue Type: Bug > Components: Mesos, Spark Core >Affects Versions: 2.0.0 >Reporter: Charles Allen > > We have encountered a strange scenario in our production environment. Below > is the best guess we have right now as to what's going on. > Potentially, the final stage of a job has a failure in one of the tasks (such > as OOME on the executor) which can cause tasks for that stage to be > relaunched in a second attempt. > https://github.com/apache/spark/blob/v2.1.0/core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala#L1155 > keeps track of which tasks have been completed, but does NOT keep track of > which attempt those tasks were completed in. As such, we have encountered a > scenario where a particular task gets executed twice in different stage > attempts, and the DAGScheduler does not consider if the second attempt is > still running. This means if the first task attempt succeeded, the second > attempt can be cancelled part-way through its run cycle if all other tasks > (including the prior failed) are completed successfully. > What this means is that if a task is manipulating some state somewhere (for > example: a upload-to-temporary-file-location, then delete-then-move on an > underlying s3n storage implementation) the driver can improperly shutdown the > running (2nd attempt) task between state manipulations, leaving the > persistent state in a bad state since the 2nd attempt never got to complete > its manipulations, and was terminated prematurely at some arbitrary point in > its state change logic (ex: finished the delete but not the move). > This is using the mesos coarse grained executor. It is unclear if this > behavior is limited to the mesos coarse grained executor or not. -- This message was sent by Atlassian JIRA (v6.3.15#6346) - To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org For additional commands, e-mail: issues-h...@spark.apache.org
[jira] [Commented] (SPARK-19698) Race condition in stale attempt task completion vs current attempt task completion when task is doing persistent state changes
[ https://issues.apache.org/jira/browse/SPARK-19698?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15881358#comment-15881358 ] Kay Ousterhout commented on SPARK-19698: I think this is the same issue as SPARK-19263 -- can you check to see if that fixes the problem / have you looked at that JIRA? I wrote a super long description of the problem towards the end of the associated PR. > Race condition in stale attempt task completion vs current attempt task > completion when task is doing persistent state changes > -- > > Key: SPARK-19698 > URL: https://issues.apache.org/jira/browse/SPARK-19698 > Project: Spark > Issue Type: Bug > Components: Mesos, Spark Core >Affects Versions: 2.0.0 >Reporter: Charles Allen > > We have encountered a strange scenario in our production environment. Below > is the best guess we have right now as to what's going on. > Potentially, the final stage of a job has a failure in one of the tasks (such > as OOME on the executor) which can cause tasks for that stage to be > relaunched in a second attempt. > https://github.com/apache/spark/blob/v2.1.0/core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala#L1155 > keeps track of which tasks have been completed, but does NOT keep track of > which attempt those tasks were completed in. As such, we have encountered a > scenario where a particular task gets executed twice in different stage > attempts, and the DAGScheduler does not consider if the second attempt is > still running. This means if the first task attempt succeeded, the second > attempt can be cancelled part-way through its run cycle if all other tasks > (including the prior failed) are completed successfully. > What this means is that if a task is manipulating some state somewhere (for > example: a upload-to-temporary-file-location, then delete-then-move on an > underlying s3n storage implementation) the driver can improperly shutdown the > running (2nd attempt) task between state manipulations, leaving the > persistent state in a bad state since the 2nd attempt never got to complete > its manipulations, and was terminated prematurely at some arbitrary point in > its state change logic (ex: finished the delete but not the move). > This is using the mesos coarse grained executor. It is unclear if this > behavior is limited to the mesos coarse grained executor or not. -- This message was sent by Atlassian JIRA (v6.3.15#6346) - To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org For additional commands, e-mail: issues-h...@spark.apache.org
[jira] [Commented] (SPARK-19698) Race condition in stale attempt task completion vs current attempt task completion when task is doing persistent state changes
[ https://issues.apache.org/jira/browse/SPARK-19698?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15879068#comment-15879068 ] Jisoo Kim commented on SPARK-19698: --- I don't think it's only limited to Mesos coarse-grained executor. https://github.com/metamx/spark/pull/25 this might be a solution, and we're doing more investigating/testing. > Race condition in stale attempt task completion vs current attempt task > completion when task is doing persistent state changes > -- > > Key: SPARK-19698 > URL: https://issues.apache.org/jira/browse/SPARK-19698 > Project: Spark > Issue Type: Bug > Components: Mesos, Spark Core >Affects Versions: 2.0.0 >Reporter: Charles Allen > > We have encountered a strange scenario in our production environment. Below > is the best guess we have right now as to what's going on. > Potentially, the final stage of a job has a failure in one of the tasks (such > as OOME on the executor) which can cause tasks for that stage to be > relaunched in a second attempt. > https://github.com/apache/spark/blob/v2.1.0/core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala#L1155 > keeps track of which tasks have been completed, but does NOT keep track of > which attempt those tasks were completed in. As such, we have encountered a > scenario where a particular task gets executed twice in different stage > attempts, and the DAGScheduler does not consider if the second attempt is > still running. This means if the first task attempt succeeded, the second > attempt can be cancelled part-way through its run cycle if all other tasks > (including the prior failed) are completed successfully. > What this means is that if a task is manipulating some state somewhere (for > example: a upload-to-temporary-file-location, then delete-then-move on an > underlying s3n storage implementation) the driver can improperly shutdown the > running (2nd attempt) task between state manipulations, leaving the > persistent state in a bad state since the 2nd attempt never got to complete > its manipulations, and was terminated prematurely at some arbitrary point in > its state change logic (ex: finished the delete but not the move). > This is using the mesos coarse grained executor. It is unclear if this > behavior is limited to the mesos coarse grained executor or not. -- This message was sent by Atlassian JIRA (v6.3.15#6346) - To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org For additional commands, e-mail: issues-h...@spark.apache.org
[jira] [Commented] (SPARK-19698) Race condition in stale attempt task completion vs current attempt task completion when task is doing persistent state changes
[ https://issues.apache.org/jira/browse/SPARK-19698?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15878959#comment-15878959 ] Charles Allen commented on SPARK-19698: --- I *think* this is due to the driver not having the concept of a "critical section" for code being executed, meaning that you can't declare a portion of the code being run as "I'm in a non-idempotent command region, please let me finish" > Race condition in stale attempt task completion vs current attempt task > completion when task is doing persistent state changes > -- > > Key: SPARK-19698 > URL: https://issues.apache.org/jira/browse/SPARK-19698 > Project: Spark > Issue Type: Bug > Components: Mesos, Spark Core >Affects Versions: 2.0.0 >Reporter: Charles Allen > > We have encountered a strange scenario in our production environment. Below > is the best guess we have right now as to what's going on. > Potentially, the final stage of a job has a failure in one of the tasks (such > as OOME on the executor) which can cause tasks for that stage to be > relaunched in a second attempt. > https://github.com/apache/spark/blob/v2.1.0/core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala#L1155 > keeps track of which tasks have been completed, but does NOT keep track of > which attempt those tasks were completed in. As such, we have encountered a > scenario where a particular task gets executed twice in different stage > attempts, and the DAGScheduler does not consider if the second attempt is > still running. This means if the first task attempt succeeded, the second > attempt can be cancelled part-way through its run cycle if all other tasks > (including the prior failed) are completed successfully. > What this means is that if a task is manipulating some state somewhere (for > example: a upload-to-temporary-file-location, then delete-then-move on an > underlying s3n storage implementation) the driver can improperly shutdown the > running (2nd attempt) task between state manipulations, leaving the > persistent state in a bad state since the 2nd attempt never got to complete > its manipulations, and was terminated prematurely at some arbitrary point in > its state change logic (ex: finished the delete but not the move). > This is using the mesos coarse grained executor. It is unclear if this > behavior is limited to the mesos coarse grained executor or not. -- This message was sent by Atlassian JIRA (v6.3.15#6346) - To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org For additional commands, e-mail: issues-h...@spark.apache.org