The TaskManagers were nixed by the OOM killer.

  [63896.699500] Out of memory: Kill process 12892 (java) score 910 or
sacrifice child
  [63896.702018] Killed process 12892 (java) total-vm:47398740kB,
anon-rss:28487812kB, file-rss:8kB

The cluster is comprised of AWS c4.8xlarge instances which have 60 GiB of
memory across two NUMA nodes (~32.2 GB each). Pertinent TaskManager
configuration:

  taskmanager.memory.off-heap: true
  taskmanager.memory.segment-size: 16384
  taskmanager.heap.mb: 18000
  taskmanager.network.numberOfBuffers: 414720

This was allocating 18 GB plus up to 6.8 GB for network buffers. As Max
noted in FLINK-2865, "I think the maximum number of network memory can
never exceed 2 * (network memory). In this case all network buffers would
be inside the Netty buffer pool." Doubling the 6.8 GB exceeds the node
memory.

Would disabling off-heap memory cause the network buffers to be re-used by
Netty and save half of the network buffer memory? I created FLINK-3164
which would reduce the number of necessary network buffers.

Greg Hogan

On Fri, Oct 30, 2015 at 12:33 PM, Till Rohrmann <trohrm...@apache.org>
wrote:

> The logging of the TaskManager stops 3 seconds before the JobManager
> detects that the connection to the TaskManager is failed. If the clocks are
> remotely in sync and the TaskManager is still running, then we should also
> see logging statements for the time after the connection has failed.
> Therefore, I would also suspect that something happened to the TaskManager
> JVM.
>
> Cheers,
> Till
>
> On Fri, Oct 30, 2015 at 3:43 AM, Robert Metzger <rmetz...@apache.org>
> wrote:
>
> > So is the TaskManager JVM still running after the JM detected that the TM
> > has gone?
> >
> > If not, can you check the kernel log (dmesg) to see whether Linux OOM
> > killer stopped the process? (if its a kill, the JVM might not be able to
> > log anything anymore)
> >
> > On Thu, Oct 29, 2015 at 9:27 PM, Stephan Ewen <se...@apache.org> wrote:
> >
> > > Thanks for sharing the logs, Greg!
> > >
> > > Okay, so the TaskManager does not crash, but the Remote Failure
> Detector
> > of
> > > Akka marks the connection between JobManager and TaskManager as broken.
> > >
> > > The TaskManager is not doing much GC, so it is not a long JVM freeze
> that
> > > causes hearbeats to time out...
> > >
> > > I am wondering at this point whether this is an issue in Akka,
> > specifically
> > > the remote death watch that we use to let the JobManager recognize
> > > disconnected TaskManagers.
> > >
> > > One thing you could try is actually to comment out the line where the
> > > JobManager starts the death watch for the TaskManager and see if they
> can
> > > still successfully exchange messages (tasks finished, find inputs,
> > > schedule) and the program completes. That would indicate that the Akka
> > > Death Watch is flawed and that we should probably do our own heartbeats
> > > instead.
> > >
> > > Greetings,
> > > Stephan
> > >
> > >
> > > On Thu, Oct 29, 2015 at 11:44 AM, Aljoscha Krettek <
> aljos...@apache.org>
> > > wrote:
> > >
> > > > Could it be a problem that there are two TaskManagers running per
> > > machine?
> > > >
> > > > > On 29 Oct 2015, at 19:04, Greg Hogan <c...@greghogan.com> wrote:
> > > > >
> > > > > I have memory logging enabled. Tail of TaskManager log on
> > 10.0.88.140:
> > > > >
> > > > > 17:35:26,415 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > Garbage
> > > > > collector stats: [PS Scavenge, GC TIME (ms): 341, GC COUNT: 3], [PS
> > > > > MarkSweep, GC TIME (ms): 974, GC COUNT: 1]
> > > > > 17:35:27,415 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > Memory
> > > > > usage stats: [HEAP: 576/1917/1917 MB, NON HEAP: 56/58/-1 MB
> > > > > (used/committed/max)]
> > > > > 17:35:27,415 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > > Off-heap
> > > > > pool stats: [Code Cache: 18/19/240 MB (used/committed/max)],
> > > [Metaspace:
> > > > > 34/34/-1 MB (used/committed/max)], [Compressed Class Space:
> 4/4/1024
> > MB
> > > > > (used/committed/max)]
> > > > > 17:35:27,415 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > Garbage
> > > > > collector stats: [PS Scavenge, GC TIME (ms): 341, GC COUNT: 3], [PS
> > > > > MarkSweep, GC TIME (ms): 974, GC COUNT: 1]
> > > > > 17:35:28,012 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > > Received
> > > > > task CHAIN GroupReduce (Compute scores) -> FlatMap (checksum())
> > > > (938/2322)
> > > > > 17:35:28,015 INFO
> > > > > org.apache.flink.runtime.taskmanager.Task                     -
> > Loading
> > > > JAR
> > > > > files for task CHAIN GroupReduce (Compute scores) -> FlatMap
> > > (checksum())
> > > > > (938/2322)
> > > > > 17:35:28,016 INFO
> > > > > org.apache.flink.runtime.taskmanager.Task                     -
> > > > Registering
> > > > > task at network: CHAIN GroupReduce (Compute scores) -> FlatMap
> > > > (checksum())
> > > > > (938/2322) [DEPLOYING]
> > > > > 17:35:28,065 INFO
> > > > > org.apache.flink.runtime.taskmanager.Task                     -
> CHAIN
> > > > > GroupReduce (Compute scores) -> FlatMap (checksum()) (938/2322)
> > > switched
> > > > to
> > > > > RUNNING
> > > > > 17:35:28,100 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > > Received
> > > > > task CHAIN GroupReduce (Compute scores) -> FlatMap (checksum())
> > > > (2304/2322)
> > > > > 17:35:28,116 INFO
> > > > > org.apache.flink.runtime.taskmanager.Task                     -
> > Loading
> > > > JAR
> > > > > files for task CHAIN GroupReduce (Compute scores) -> FlatMap
> > > (checksum())
> > > > > (2304/2322)
> > > > > 17:35:28,116 INFO
> > > > > org.apache.flink.runtime.taskmanager.Task                     -
> > > > Registering
> > > > > task at network: CHAIN GroupReduce (Compute scores) -> FlatMap
> > > > (checksum())
> > > > > (2304/2322) [DEPLOYING]
> > > > > 17:35:28,132 INFO
> > > > > org.apache.flink.runtime.taskmanager.Task                     -
> CHAIN
> > > > > GroupReduce (Compute scores) -> FlatMap (checksum()) (2304/2322)
> > > switched
> > > > > to RUNNING
> > > > > 17:35:28,255 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > > Received
> > > > > task CHAIN GroupReduce (Compute scores) -> FlatMap (checksum())
> > > > (939/2322)
> > > > > 17:35:28,263 INFO
> > > > > org.apache.flink.runtime.taskmanager.Task                     -
> > Loading
> > > > JAR
> > > > > files for task CHAIN GroupReduce (Compute scores) -> FlatMap
> > > (checksum())
> > > > > (939/2322)
> > > > > 17:35:28,263 INFO
> > > > > org.apache.flink.runtime.taskmanager.Task                     -
> > > > Registering
> > > > > task at network: CHAIN GroupReduce (Compute scores) -> FlatMap
> > > > (checksum())
> > > > > (939/2322) [DEPLOYING]
> > > > > 17:35:28,304 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > > Received
> > > > > task CHAIN GroupReduce (Compute scores) -> FlatMap (checksum())
> > > > (2062/2322)
> > > > > 17:35:28,311 INFO
> > > > > org.apache.flink.runtime.taskmanager.Task                     -
> > Loading
> > > > JAR
> > > > > files for task CHAIN GroupReduce (Compute scores) -> FlatMap
> > > (checksum())
> > > > > (2062/2322)
> > > > > 17:35:28,311 INFO
> > > > > org.apache.flink.runtime.taskmanager.Task                     -
> > > > Registering
> > > > > task at network: CHAIN GroupReduce (Compute scores) -> FlatMap
> > > > (checksum())
> > > > > (2062/2322) [DEPLOYING]
> > > > > 17:35:28,323 INFO
> > > > > org.apache.flink.runtime.taskmanager.Task                     -
> CHAIN
> > > > > GroupReduce (Compute scores) -> FlatMap (checksum()) (939/2322)
> > > switched
> > > > to
> > > > > RUNNING
> > > > > 17:35:28,386 INFO
> > > > > org.apache.flink.runtime.taskmanager.Task                     -
> CHAIN
> > > > > GroupReduce (Compute scores) -> FlatMap (checksum()) (2062/2322)
> > > switched
> > > > > to RUNNING
> > > > > 17:35:28,396 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > > Received
> > > > > task CHAIN GroupReduce (Compute scores) -> FlatMap (checksum())
> > > > (1775/2322)
> > > > > 17:35:28,401 INFO
> > > > > org.apache.flink.runtime.taskmanager.Task                     -
> > Loading
> > > > JAR
> > > > > files for task CHAIN GroupReduce (Compute scores) -> FlatMap
> > > (checksum())
> > > > > (1775/2322)
> > > > > 17:35:28,402 INFO
> > > > > org.apache.flink.runtime.taskmanager.Task                     -
> > > > Registering
> > > > > task at network: CHAIN GroupReduce (Compute scores) -> FlatMap
> > > > (checksum())
> > > > > (1775/2322) [DEPLOYING]
> > > > > 17:35:28,416 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > Memory
> > > > > usage stats: [HEAP: 747/1917/1917 MB, NON HEAP: 56/58/-1 MB
> > > > > (used/committed/max)]
> > > > > 17:35:28,416 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > > Off-heap
> > > > > pool stats: [Code Cache: 18/19/240 MB (used/committed/max)],
> > > [Metaspace:
> > > > > 34/34/-1 MB (used/committed/max)], [Compressed Class Space:
> 4/4/1024
> > MB
> > > > > (used/committed/max)]
> > > > > 17:35:28,416 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > Garbage
> > > > > collector stats: [PS Scavenge, GC TIME (ms): 341, GC COUNT: 3], [PS
> > > > > MarkSweep, GC TIME (ms): 974, GC COUNT: 1]
> > > > > 17:35:28,419 INFO
> > > > > org.apache.flink.runtime.taskmanager.Task                     -
> CHAIN
> > > > > GroupReduce (Compute scores) -> FlatMap (checksum()) (1775/2322)
> > > switched
> > > > > to RUNNING
> > > > > 17:35:28,475 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > > Received
> > > > > task CHAIN GroupReduce (Compute scores) -> FlatMap (checksum())
> > > > (2158/2322)
> > > > > 17:35:28,475 INFO
> > > > > org.apache.flink.runtime.taskmanager.Task                     -
> > Loading
> > > > JAR
> > > > > files for task CHAIN GroupReduce (Compute scores) -> FlatMap
> > > (checksum())
> > > > > (2158/2322)
> > > > > 17:35:28,476 INFO
> > > > > org.apache.flink.runtime.taskmanager.Task                     -
> > > > Registering
> > > > > task at network: CHAIN GroupReduce (Compute scores) -> FlatMap
> > > > (checksum())
> > > > > (2158/2322) [DEPLOYING]
> > > > > 17:35:28,509 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > > Received
> > > > > task CHAIN GroupReduce (Compute scores) -> FlatMap (checksum())
> > > > (1463/2322)
> > > > > 17:35:28,860 INFO
> > > > > org.apache.flink.runtime.taskmanager.Task                     -
> > Loading
> > > > JAR
> > > > > files for task CHAIN GroupReduce (Compute scores) -> FlatMap
> > > (checksum())
> > > > > (1463/2322)
> > > > > 17:35:28,861 INFO
> > > > > org.apache.flink.runtime.taskmanager.Task                     -
> > > > Registering
> > > > > task at network: CHAIN GroupReduce (Compute scores) -> FlatMap
> > > > (checksum())
> > > > > (1463/2322) [DEPLOYING]
> > > > > 17:35:28,862 INFO
> > > > > org.apache.flink.runtime.taskmanager.Task                     -
> CHAIN
> > > > > GroupReduce (Compute scores) -> FlatMap (checksum()) (2158/2322)
> > > switched
> > > > > to RUNNING
> > > > > 17:35:28,878 INFO
> > > > > org.apache.flink.runtime.taskmanager.Task                     -
> CHAIN
> > > > > GroupReduce (Compute scores) -> FlatMap (checksum()) (1463/2322)
> > > switched
> > > > > to RUNNING
> > > > > 17:35:28,892 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > > Received
> > > > > task CHAIN GroupReduce (Compute scores) -> FlatMap (checksum())
> > > > (1154/2322)
> > > > > 17:35:28,893 INFO
> > > > > org.apache.flink.runtime.taskmanager.Task                     -
> > Loading
> > > > JAR
> > > > > files for task CHAIN GroupReduce (Compute scores) -> FlatMap
> > > (checksum())
> > > > > (1154/2322)
> > > > > 17:35:28,893 INFO
> > > > > org.apache.flink.runtime.taskmanager.Task                     -
> > > > Registering
> > > > > task at network: CHAIN GroupReduce (Compute scores) -> FlatMap
> > > > (checksum())
> > > > > (1154/2322) [DEPLOYING]
> > > > > 17:35:28,914 INFO
> > > > > org.apache.flink.runtime.taskmanager.Task                     -
> CHAIN
> > > > > GroupReduce (Compute scores) -> FlatMap (checksum()) (1154/2322)
> > > switched
> > > > > to RUNNING
> > > > > 17:35:28,916 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > > Received
> > > > > task CHAIN GroupReduce (Compute scores) -> FlatMap (checksum())
> > > > (1429/2322)
> > > > > 17:35:28,917 INFO
> > > > > org.apache.flink.runtime.taskmanager.Task                     -
> > Loading
> > > > JAR
> > > > > files for task CHAIN GroupReduce (Compute scores) -> FlatMap
> > > (checksum())
> > > > > (1429/2322)
> > > > > 17:35:28,917 INFO
> > > > > org.apache.flink.runtime.taskmanager.Task                     -
> > > > Registering
> > > > > task at network: CHAIN GroupReduce (Compute scores) -> FlatMap
> > > > (checksum())
> > > > > (1429/2322) [DEPLOYING]
> > > > > 17:35:28,942 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > > Received
> > > > > task CHAIN GroupReduce (Compute scores) -> FlatMap (checksum())
> > > > (1078/2322)
> > > > > 17:35:28,942 INFO
> > > > > org.apache.flink.runtime.taskmanager.Task                     -
> > Loading
> > > > JAR
> > > > > files for task CHAIN GroupReduce (Compute scores) -> FlatMap
> > > (checksum())
> > > > > (1078/2322)
> > > > > 17:35:28,942 INFO
> > > > > org.apache.flink.runtime.taskmanager.Task                     -
> > > > Registering
> > > > > task at network: CHAIN GroupReduce (Compute scores) -> FlatMap
> > > > (checksum())
> > > > > (1078/2322) [DEPLOYING]
> > > > > 17:35:28,943 INFO
> > > > > org.apache.flink.runtime.taskmanager.Task                     -
> CHAIN
> > > > > GroupReduce (Compute scores) -> FlatMap (checksum()) (1429/2322)
> > > switched
> > > > > to RUNNING
> > > > > 17:35:28,955 INFO
> > > > > org.apache.flink.runtime.taskmanager.Task                     -
> CHAIN
> > > > > GroupReduce (Compute scores) -> FlatMap (checksum()) (1078/2322)
> > > switched
> > > > > to RUNNING
> > > > > 17:35:28,959 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > > Received
> > > > > task CHAIN GroupReduce (Compute scores) -> FlatMap (checksum())
> > > > (524/2322)
> > > > > 17:35:28,995 INFO
> > > > > org.apache.flink.runtime.taskmanager.Task                     -
> > Loading
> > > > JAR
> > > > > files for task CHAIN GroupReduce (Compute scores) -> FlatMap
> > > (checksum())
> > > > > (524/2322)
> > > > > 17:35:28,995 INFO
> > > > > org.apache.flink.runtime.taskmanager.Task                     -
> > > > Registering
> > > > > task at network: CHAIN GroupReduce (Compute scores) -> FlatMap
> > > > (checksum())
> > > > > (524/2322) [DEPLOYING]
> > > > > 17:35:29,000 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > > Received
> > > > > task CHAIN GroupReduce (Compute scores) -> FlatMap (checksum())
> > > > (2021/2322)
> > > > > 17:35:29,000 INFO
> > > > > org.apache.flink.runtime.taskmanager.Task                     -
> > Loading
> > > > JAR
> > > > > files for task CHAIN GroupReduce (Compute scores) -> FlatMap
> > > (checksum())
> > > > > (2021/2322)
> > > > > 17:35:29,000 INFO
> > > > > org.apache.flink.runtime.taskmanager.Task                     -
> > > > Registering
> > > > > task at network: CHAIN GroupReduce (Compute scores) -> FlatMap
> > > > (checksum())
> > > > > (2021/2322) [DEPLOYING]
> > > > > 17:35:29,012 INFO
> > > > > org.apache.flink.runtime.taskmanager.Task                     -
> CHAIN
> > > > > GroupReduce (Compute scores) -> FlatMap (checksum()) (524/2322)
> > > switched
> > > > to
> > > > > RUNNING
> > > > > 17:35:29,039 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > > Received
> > > > > task CHAIN GroupReduce (Compute scores) -> FlatMap (checksum())
> > > > (2022/2322)
> > > > > 17:35:29,039 INFO
> > > > > org.apache.flink.runtime.taskmanager.Task                     -
> CHAIN
> > > > > GroupReduce (Compute scores) -> FlatMap (checksum()) (2021/2322)
> > > switched
> > > > > to RUNNING
> > > > > 17:35:29,043 INFO
> > > > > org.apache.flink.runtime.taskmanager.Task                     -
> > Loading
> > > > JAR
> > > > > files for task CHAIN GroupReduce (Compute scores) -> FlatMap
> > > (checksum())
> > > > > (2022/2322)
> > > > > 17:35:29,043 INFO
> > > > > org.apache.flink.runtime.taskmanager.Task                     -
> > > > Registering
> > > > > task at network: CHAIN GroupReduce (Compute scores) -> FlatMap
> > > > (checksum())
> > > > > (2022/2322) [DEPLOYING]
> > > > > 17:35:29,076 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > > Received
> > > > > task CHAIN GroupReduce (Compute scores) -> FlatMap (checksum())
> > > > (1464/2322)
> > > > > 17:35:29,081 INFO
> > > > > org.apache.flink.runtime.taskmanager.Task                     -
> > Loading
> > > > JAR
> > > > > files for task CHAIN GroupReduce (Compute scores) -> FlatMap
> > > (checksum())
> > > > > (1464/2322)
> > > > > 17:35:29,081 INFO
> > > > > org.apache.flink.runtime.taskmanager.Task                     -
> > > > Registering
> > > > > task at network: CHAIN GroupReduce (Compute scores) -> FlatMap
> > > > (checksum())
> > > > > (1464/2322) [DEPLOYING]
> > > > > 17:35:29,095 INFO
> > > > > org.apache.flink.runtime.taskmanager.Task                     -
> CHAIN
> > > > > GroupReduce (Compute scores) -> FlatMap (checksum()) (2022/2322)
> > > switched
> > > > > to RUNNING
> > > > > 17:35:29,108 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > > Received
> > > > > task CHAIN GroupReduce (Compute scores) -> FlatMap (checksum())
> > > > (1095/2322)
> > > > > 17:35:29,110 INFO
> > > > > org.apache.flink.runtime.taskmanager.Task                     -
> CHAIN
> > > > > GroupReduce (Compute scores) -> FlatMap (checksum()) (1464/2322)
> > > switched
> > > > > to RUNNING
> > > > > 17:35:29,112 INFO
> > > > > org.apache.flink.runtime.taskmanager.Task                     -
> > Loading
> > > > JAR
> > > > > files for task CHAIN GroupReduce (Compute scores) -> FlatMap
> > > (checksum())
> > > > > (1095/2322)
> > > > > 17:35:29,112 INFO
> > > > > org.apache.flink.runtime.taskmanager.Task                     -
> > > > Registering
> > > > > task at network: CHAIN GroupReduce (Compute scores) -> FlatMap
> > > > (checksum())
> > > > > (1095/2322) [DEPLOYING]
> > > > > 17:35:29,140 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > > Received
> > > > > task CHAIN GroupReduce (Compute scores) -> FlatMap (checksum())
> > > > (2306/2322)
> > > > > 17:35:29,142 INFO
> > > > > org.apache.flink.runtime.taskmanager.Task                     -
> > Loading
> > > > JAR
> > > > > files for task CHAIN GroupReduce (Compute scores) -> FlatMap
> > > (checksum())
> > > > > (2306/2322)
> > > > > 17:35:29,142 INFO
> > > > > org.apache.flink.runtime.taskmanager.Task                     -
> > > > Registering
> > > > > task at network: CHAIN GroupReduce (Compute scores) -> FlatMap
> > > > (checksum())
> > > > > (2306/2322) [DEPLOYING]
> > > > > 17:35:29,147 INFO
> > > > > org.apache.flink.runtime.taskmanager.Task                     -
> CHAIN
> > > > > GroupReduce (Compute scores) -> FlatMap (checksum()) (1095/2322)
> > > switched
> > > > > to RUNNING
> > > > > 17:35:29,152 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > > Received
> > > > > task CHAIN GroupReduce (Compute scores) -> FlatMap (checksum())
> > > > (974/2322)
> > > > > 17:35:29,153 INFO
> > > > > org.apache.flink.runtime.taskmanager.Task                     -
> CHAIN
> > > > > GroupReduce (Compute scores) -> FlatMap (checksum()) (2306/2322)
> > > switched
> > > > > to RUNNING
> > > > > 17:35:29,155 INFO
> > > > > org.apache.flink.runtime.taskmanager.Task                     -
> > Loading
> > > > JAR
> > > > > files for task CHAIN GroupReduce (Compute scores) -> FlatMap
> > > (checksum())
> > > > > (974/2322)
> > > > > 17:35:29,155 INFO
> > > > > org.apache.flink.runtime.taskmanager.Task                     -
> > > > Registering
> > > > > task at network: CHAIN GroupReduce (Compute scores) -> FlatMap
> > > > (checksum())
> > > > > (974/2322) [DEPLOYING]
> > > > > 17:35:29,166 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > > Received
> > > > > task CHAIN GroupReduce (Compute scores) -> FlatMap (checksum())
> > > > (2305/2322)
> > > > > 17:35:29,167 INFO
> > > > > org.apache.flink.runtime.taskmanager.Task                     -
> > Loading
> > > > JAR
> > > > > files for task CHAIN GroupReduce (Compute scores) -> FlatMap
> > > (checksum())
> > > > > (2305/2322)
> > > > > 17:35:29,167 INFO
> > > > > org.apache.flink.runtime.taskmanager.Task                     -
> > > > Registering
> > > > > task at network: CHAIN GroupReduce (Compute scores) -> FlatMap
> > > > (checksum())
> > > > > (2305/2322) [DEPLOYING]
> > > > > 17:35:29,176 INFO
> > > > > org.apache.flink.runtime.taskmanager.Task                     -
> CHAIN
> > > > > GroupReduce (Compute scores) -> FlatMap (checksum()) (974/2322)
> > > switched
> > > > to
> > > > > RUNNING
> > > > > 17:35:29,205 INFO
> > > > > org.apache.flink.runtime.taskmanager.Task                     -
> CHAIN
> > > > > GroupReduce (Compute scores) -> FlatMap (checksum()) (2305/2322)
> > > switched
> > > > > to RUNNING
> > > > > 17:35:29,417 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > Memory
> > > > > usage stats: [HEAP: 590/1917/1917 MB, NON HEAP: 57/59/-1 MB
> > > > > (used/committed/max)]
> > > > > 17:35:29,417 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > > Off-heap
> > > > > pool stats: [Code Cache: 18/19/240 MB (used/committed/max)],
> > > [Metaspace:
> > > > > 34/34/-1 MB (used/committed/max)], [Compressed Class Space:
> 4/4/1024
> > MB
> > > > > (used/committed/max)]
> > > > > 17:35:29,417 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > Garbage
> > > > > collector stats: [PS Scavenge, GC TIME (ms): 689, GC COUNT: 4], [PS
> > > > > MarkSweep, GC TIME (ms): 974, GC COUNT: 1]
> > > > > 17:35:30,418 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > Memory
> > > > > usage stats: [HEAP: 614/1917/1917 MB, NON HEAP: 57/59/-1 MB
> > > > > (used/committed/max)]
> > > > > 17:35:30,418 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > > Off-heap
> > > > > pool stats: [Code Cache: 18/19/240 MB (used/committed/max)],
> > > [Metaspace:
> > > > > 34/34/-1 MB (used/committed/max)], [Compressed Class Space:
> 4/4/1024
> > MB
> > > > > (used/committed/max)]
> > > > > 17:35:30,418 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > Garbage
> > > > > collector stats: [PS Scavenge, GC TIME (ms): 689, GC COUNT: 4], [PS
> > > > > MarkSweep, GC TIME (ms): 974, GC COUNT: 1]
> > > > > 17:35:31,418 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > Memory
> > > > > usage stats: [HEAP: 634/1917/1917 MB, NON HEAP: 57/59/-1 MB
> > > > > (used/committed/max)]
> > > > > 17:35:31,418 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > > Off-heap
> > > > > pool stats: [Code Cache: 19/19/240 MB (used/committed/max)],
> > > [Metaspace:
> > > > > 34/34/-1 MB (used/committed/max)], [Compressed Class Space:
> 4/4/1024
> > MB
> > > > > (used/committed/max)]
> > > > > 17:35:31,419 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > Garbage
> > > > > collector stats: [PS Scavenge, GC TIME (ms): 689, GC COUNT: 4], [PS
> > > > > MarkSweep, GC TIME (ms): 974, GC COUNT: 1]
> > > > > 17:35:32,419 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > Memory
> > > > > usage stats: [HEAP: 638/1917/1917 MB, NON HEAP: 57/59/-1 MB
> > > > > (used/committed/max)]
> > > > > 17:35:32,419 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > > Off-heap
> > > > > pool stats: [Code Cache: 19/19/240 MB (used/committed/max)],
> > > [Metaspace:
> > > > > 34/34/-1 MB (used/committed/max)], [Compressed Class Space:
> 4/4/1024
> > MB
> > > > > (used/committed/max)]
> > > > > 17:35:32,419 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > Garbage
> > > > > collector stats: [PS Scavenge, GC TIME (ms): 689, GC COUNT: 4], [PS
> > > > > MarkSweep, GC TIME (ms): 974, GC COUNT: 1]
> > > > > 17:35:33,487 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > Memory
> > > > > usage stats: [HEAP: 648/1917/1917 MB, NON HEAP: 58/59/-1 MB
> > > > > (used/committed/max)]
> > > > > 17:35:33,494 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > > Off-heap
> > > > > pool stats: [Code Cache: 19/19/240 MB (used/committed/max)],
> > > [Metaspace:
> > > > > 34/34/-1 MB (used/committed/max)], [Compressed Class Space:
> 4/4/1024
> > MB
> > > > > (used/committed/max)]
> > > > > 17:35:33,522 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > Garbage
> > > > > collector stats: [PS Scavenge, GC TIME (ms): 689, GC COUNT: 4], [PS
> > > > > MarkSweep, GC TIME (ms): 974, GC COUNT: 1]
> > > > > 17:35:34,523 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > Memory
> > > > > usage stats: [HEAP: 662/1917/1917 MB, NON HEAP: 58/59/-1 MB
> > > > > (used/committed/max)]
> > > > > 17:35:34,523 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > > Off-heap
> > > > > pool stats: [Code Cache: 19/19/240 MB (used/committed/max)],
> > > [Metaspace:
> > > > > 34/34/-1 MB (used/committed/max)], [Compressed Class Space:
> 4/4/1024
> > MB
> > > > > (used/committed/max)]
> > > > > 17:35:34,523 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > Garbage
> > > > > collector stats: [PS Scavenge, GC TIME (ms): 689, GC COUNT: 4], [PS
> > > > > MarkSweep, GC TIME (ms): 974, GC COUNT: 1]
> > > > > 17:35:35,523 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > Memory
> > > > > usage stats: [HEAP: 670/1917/1917 MB, NON HEAP: 58/59/-1 MB
> > > > > (used/committed/max)]
> > > > > 17:35:35,524 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > > Off-heap
> > > > > pool stats: [Code Cache: 19/19/240 MB (used/committed/max)],
> > > [Metaspace:
> > > > > 34/34/-1 MB (used/committed/max)], [Compressed Class Space:
> 4/4/1024
> > MB
> > > > > (used/committed/max)]
> > > > > 17:35:35,524 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > Garbage
> > > > > collector stats: [PS Scavenge, GC TIME (ms): 689, GC COUNT: 4], [PS
> > > > > MarkSweep, GC TIME (ms): 974, GC COUNT: 1]
> > > > > 17:35:36,525 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > Memory
> > > > > usage stats: [HEAP: 717/1917/1917 MB, NON HEAP: 58/59/-1 MB
> > > > > (used/committed/max)]
> > > > > 17:35:36,525 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > > Off-heap
> > > > > pool stats: [Code Cache: 19/19/240 MB (used/committed/max)],
> > > [Metaspace:
> > > > > 34/34/-1 MB (used/committed/max)], [Compressed Class Space:
> 4/4/1024
> > MB
> > > > > (used/committed/max)]
> > > > > 17:35:36,525 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > Garbage
> > > > > collector stats: [PS Scavenge, GC TIME (ms): 689, GC COUNT: 4], [PS
> > > > > MarkSweep, GC TIME (ms): 974, GC COUNT: 1]
> > > > > 17:35:37,525 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > Memory
> > > > > usage stats: [HEAP: 737/1917/1917 MB, NON HEAP: 58/59/-1 MB
> > > > > (used/committed/max)]
> > > > > 17:35:37,525 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > > Off-heap
> > > > > pool stats: [Code Cache: 19/19/240 MB (used/committed/max)],
> > > [Metaspace:
> > > > > 34/34/-1 MB (used/committed/max)], [Compressed Class Space:
> 4/4/1024
> > MB
> > > > > (used/committed/max)]
> > > > > 17:35:37,525 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > Garbage
> > > > > collector stats: [PS Scavenge, GC TIME (ms): 689, GC COUNT: 4], [PS
> > > > > MarkSweep, GC TIME (ms): 974, GC COUNT: 1]
> > > > > 17:35:38,525 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > Memory
> > > > > usage stats: [HEAP: 747/1917/1917 MB, NON HEAP: 58/59/-1 MB
> > > > > (used/committed/max)]
> > > > > 17:35:38,525 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > > Off-heap
> > > > > pool stats: [Code Cache: 19/20/240 MB (used/committed/max)],
> > > [Metaspace:
> > > > > 34/34/-1 MB (used/committed/max)], [Compressed Class Space:
> 4/4/1024
> > MB
> > > > > (used/committed/max)]
> > > > > 17:35:38,525 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > Garbage
> > > > > collector stats: [PS Scavenge, GC TIME (ms): 689, GC COUNT: 4], [PS
> > > > > MarkSweep, GC TIME (ms): 974, GC COUNT: 1]
> > > > > 17:35:39,526 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > Memory
> > > > > usage stats: [HEAP: 817/1917/1917 MB, NON HEAP: 58/59/-1 MB
> > > > > (used/committed/max)]
> > > > > 17:35:39,526 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > > Off-heap
> > > > > pool stats: [Code Cache: 19/20/240 MB (used/committed/max)],
> > > [Metaspace:
> > > > > 34/34/-1 MB (used/committed/max)], [Compressed Class Space:
> 4/4/1024
> > MB
> > > > > (used/committed/max)]
> > > > > 17:35:39,526 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > Garbage
> > > > > collector stats: [PS Scavenge, GC TIME (ms): 689, GC COUNT: 4], [PS
> > > > > MarkSweep, GC TIME (ms): 974, GC COUNT: 1]
> > > > > 17:35:40,526 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > Memory
> > > > > usage stats: [HEAP: 832/1917/1917 MB, NON HEAP: 58/59/-1 MB
> > > > > (used/committed/max)]
> > > > > 17:35:40,526 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > > Off-heap
> > > > > pool stats: [Code Cache: 19/20/240 MB (used/committed/max)],
> > > [Metaspace:
> > > > > 34/34/-1 MB (used/committed/max)], [Compressed Class Space:
> 4/4/1024
> > MB
> > > > > (used/committed/max)]
> > > > > 17:35:40,526 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > Garbage
> > > > > collector stats: [PS Scavenge, GC TIME (ms): 689, GC COUNT: 4], [PS
> > > > > MarkSweep, GC TIME (ms): 974, GC COUNT: 1]
> > > > > 17:35:41,527 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > Memory
> > > > > usage stats: [HEAP: 840/1917/1917 MB, NON HEAP: 58/59/-1 MB
> > > > > (used/committed/max)]
> > > > > 17:35:41,527 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > > Off-heap
> > > > > pool stats: [Code Cache: 19/20/240 MB (used/committed/max)],
> > > [Metaspace:
> > > > > 34/34/-1 MB (used/committed/max)], [Compressed Class Space:
> 4/4/1024
> > MB
> > > > > (used/committed/max)]
> > > > > 17:35:41,527 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > Garbage
> > > > > collector stats: [PS Scavenge, GC TIME (ms): 689, GC COUNT: 4], [PS
> > > > > MarkSweep, GC TIME (ms): 974, GC COUNT: 1]
> > > > > 17:35:42,527 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > Memory
> > > > > usage stats: [HEAP: 847/1917/1917 MB, NON HEAP: 58/59/-1 MB
> > > > > (used/committed/max)]
> > > > > 17:35:42,527 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > > Off-heap
> > > > > pool stats: [Code Cache: 19/20/240 MB (used/committed/max)],
> > > [Metaspace:
> > > > > 34/34/-1 MB (used/committed/max)], [Compressed Class Space:
> 4/4/1024
> > MB
> > > > > (used/committed/max)]
> > > > > 17:35:42,527 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > Garbage
> > > > > collector stats: [PS Scavenge, GC TIME (ms): 689, GC COUNT: 4], [PS
> > > > > MarkSweep, GC TIME (ms): 974, GC COUNT: 1]
> > > > > 17:35:43,599 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > Memory
> > > > > usage stats: [HEAP: 450/1917/1917 MB, NON HEAP: 58/59/-1 MB
> > > > > (used/committed/max)]
> > > > > 17:35:43,599 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > > Off-heap
> > > > > pool stats: [Code Cache: 19/20/240 MB (used/committed/max)],
> > > [Metaspace:
> > > > > 34/34/-1 MB (used/committed/max)], [Compressed Class Space:
> 4/4/1024
> > MB
> > > > > (used/committed/max)]
> > > > > 17:35:43,599 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > Garbage
> > > > > collector stats: [PS Scavenge, GC TIME (ms): 797, GC COUNT: 5], [PS
> > > > > MarkSweep, GC TIME (ms): 974, GC COUNT: 1]
> > > > > 17:35:44,599 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > Memory
> > > > > usage stats: [HEAP: 508/1917/1917 MB, NON HEAP: 58/59/-1 MB
> > > > > (used/committed/max)]
> > > > > 17:35:44,599 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > > Off-heap
> > > > > pool stats: [Code Cache: 19/20/240 MB (used/committed/max)],
> > > [Metaspace:
> > > > > 34/34/-1 MB (used/committed/max)], [Compressed Class Space:
> 4/4/1024
> > MB
> > > > > (used/committed/max)]
> > > > > 17:35:44,599 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > Garbage
> > > > > collector stats: [PS Scavenge, GC TIME (ms): 797, GC COUNT: 5], [PS
> > > > > MarkSweep, GC TIME (ms): 974, GC COUNT: 1]
> > > > > 17:35:45,600 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > Memory
> > > > > usage stats: [HEAP: 517/1917/1917 MB, NON HEAP: 58/59/-1 MB
> > > > > (used/committed/max)]
> > > > > 17:35:45,600 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > > Off-heap
> > > > > pool stats: [Code Cache: 19/20/240 MB (used/committed/max)],
> > > [Metaspace:
> > > > > 34/34/-1 MB (used/committed/max)], [Compressed Class Space:
> 4/4/1024
> > MB
> > > > > (used/committed/max)]
> > > > > 17:35:45,600 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > Garbage
> > > > > collector stats: [PS Scavenge, GC TIME (ms): 797, GC COUNT: 5], [PS
> > > > > MarkSweep, GC TIME (ms): 974, GC COUNT: 1]
> > > > > 17:35:46,600 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > Memory
> > > > > usage stats: [HEAP: 528/1917/1917 MB, NON HEAP: 58/59/-1 MB
> > > > > (used/committed/max)]
> > > > > 17:35:46,600 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > > Off-heap
> > > > > pool stats: [Code Cache: 19/20/240 MB (used/committed/max)],
> > > [Metaspace:
> > > > > 34/34/-1 MB (used/committed/max)], [Compressed Class Space:
> 4/4/1024
> > MB
> > > > > (used/committed/max)]
> > > > > 17:35:46,600 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > Garbage
> > > > > collector stats: [PS Scavenge, GC TIME (ms): 797, GC COUNT: 5], [PS
> > > > > MarkSweep, GC TIME (ms): 974, GC COUNT: 1]
> > > > > 17:35:47,663 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > Memory
> > > > > usage stats: [HEAP: 541/1917/1917 MB, NON HEAP: 58/59/-1 MB
> > > > > (used/committed/max)]
> > > > > 17:35:47,664 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > > Off-heap
> > > > > pool stats: [Code Cache: 19/20/240 MB (used/committed/max)],
> > > [Metaspace:
> > > > > 34/34/-1 MB (used/committed/max)], [Compressed Class Space:
> 4/4/1024
> > MB
> > > > > (used/committed/max)]
> > > > > 17:35:47,664 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > Garbage
> > > > > collector stats: [PS Scavenge, GC TIME (ms): 797, GC COUNT: 5], [PS
> > > > > MarkSweep, GC TIME (ms): 974, GC COUNT: 1]
> > > > > 17:35:48,791 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > Memory
> > > > > usage stats: [HEAP: 554/1917/1917 MB, NON HEAP: 58/59/-1 MB
> > > > > (used/committed/max)]
> > > > > 17:35:48,791 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > > Off-heap
> > > > > pool stats: [Code Cache: 19/20/240 MB (used/committed/max)],
> > > [Metaspace:
> > > > > 34/34/-1 MB (used/committed/max)], [Compressed Class Space:
> 4/4/1024
> > MB
> > > > > (used/committed/max)]
> > > > > 17:35:48,791 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > Garbage
> > > > > collector stats: [PS Scavenge, GC TIME (ms): 797, GC COUNT: 5], [PS
> > > > > MarkSweep, GC TIME (ms): 974, GC COUNT: 1]
> > > > > 17:35:49,794 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > Memory
> > > > > usage stats: [HEAP: 562/1917/1917 MB, NON HEAP: 58/59/-1 MB
> > > > > (used/committed/max)]
> > > > > 17:35:49,795 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > > Off-heap
> > > > > pool stats: [Code Cache: 19/20/240 MB (used/committed/max)],
> > > [Metaspace:
> > > > > 34/34/-1 MB (used/committed/max)], [Compressed Class Space:
> 4/4/1024
> > MB
> > > > > (used/committed/max)]
> > > > > 17:35:49,795 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > Garbage
> > > > > collector stats: [PS Scavenge, GC TIME (ms): 797, GC COUNT: 5], [PS
> > > > > MarkSweep, GC TIME (ms): 974, GC COUNT: 1]
> > > > > 17:35:50,795 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > Memory
> > > > > usage stats: [HEAP: 569/1917/1917 MB, NON HEAP: 58/59/-1 MB
> > > > > (used/committed/max)]
> > > > > 17:35:50,795 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > > Off-heap
> > > > > pool stats: [Code Cache: 19/20/240 MB (used/committed/max)],
> > > [Metaspace:
> > > > > 34/34/-1 MB (used/committed/max)], [Compressed Class Space:
> 4/4/1024
> > MB
> > > > > (used/committed/max)]
> > > > > 17:35:50,795 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > Garbage
> > > > > collector stats: [PS Scavenge, GC TIME (ms): 797, GC COUNT: 5], [PS
> > > > > MarkSweep, GC TIME (ms): 974, GC COUNT: 1]
> > > > > 17:35:51,795 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > Memory
> > > > > usage stats: [HEAP: 582/1917/1917 MB, NON HEAP: 58/59/-1 MB
> > > > > (used/committed/max)]
> > > > > 17:35:51,795 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > > Off-heap
> > > > > pool stats: [Code Cache: 19/20/240 MB (used/committed/max)],
> > > [Metaspace:
> > > > > 34/34/-1 MB (used/committed/max)], [Compressed Class Space:
> 4/4/1024
> > MB
> > > > > (used/committed/max)]
> > > > > 17:35:51,795 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > Garbage
> > > > > collector stats: [PS Scavenge, GC TIME (ms): 797, GC COUNT: 5], [PS
> > > > > MarkSweep, GC TIME (ms): 974, GC COUNT: 1]
> > > > > 17:35:52,796 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > Memory
> > > > > usage stats: [HEAP: 593/1917/1917 MB, NON HEAP: 58/59/-1 MB
> > > > > (used/committed/max)]
> > > > > 17:35:52,796 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > > Off-heap
> > > > > pool stats: [Code Cache: 19/20/240 MB (used/committed/max)],
> > > [Metaspace:
> > > > > 34/34/-1 MB (used/committed/max)], [Compressed Class Space:
> 4/4/1024
> > MB
> > > > > (used/committed/max)]
> > > > > 17:35:52,796 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > Garbage
> > > > > collector stats: [PS Scavenge, GC TIME (ms): 797, GC COUNT: 5], [PS
> > > > > MarkSweep, GC TIME (ms): 974, GC COUNT: 1]
> > > > > 17:35:53,796 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > Memory
> > > > > usage stats: [HEAP: 600/1917/1917 MB, NON HEAP: 58/59/-1 MB
> > > > > (used/committed/max)]
> > > > > 17:35:53,796 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > > Off-heap
> > > > > pool stats: [Code Cache: 19/20/240 MB (used/committed/max)],
> > > [Metaspace:
> > > > > 34/34/-1 MB (used/committed/max)], [Compressed Class Space:
> 4/4/1024
> > MB
> > > > > (used/committed/max)]
> > > > > 17:35:53,796 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > Garbage
> > > > > collector stats: [PS Scavenge, GC TIME (ms): 797, GC COUNT: 5], [PS
> > > > > MarkSweep, GC TIME (ms): 974, GC COUNT: 1]
> > > > > 17:35:54,797 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > Memory
> > > > > usage stats: [HEAP: 604/1917/1917 MB, NON HEAP: 58/59/-1 MB
> > > > > (used/committed/max)]
> > > > > 17:35:54,797 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > > Off-heap
> > > > > pool stats: [Code Cache: 19/20/240 MB (used/committed/max)],
> > > [Metaspace:
> > > > > 34/34/-1 MB (used/committed/max)], [Compressed Class Space:
> 4/4/1024
> > MB
> > > > > (used/committed/max)]
> > > > > 17:35:54,797 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > Garbage
> > > > > collector stats: [PS Scavenge, GC TIME (ms): 797, GC COUNT: 5], [PS
> > > > > MarkSweep, GC TIME (ms): 974, GC COUNT: 1]
> > > > > 17:35:55,797 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > Memory
> > > > > usage stats: [HEAP: 610/1917/1917 MB, NON HEAP: 58/59/-1 MB
> > > > > (used/committed/max)]
> > > > > 17:35:55,797 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > > Off-heap
> > > > > pool stats: [Code Cache: 19/20/240 MB (used/committed/max)],
> > > [Metaspace:
> > > > > 34/34/-1 MB (used/committed/max)], [Compressed Class Space:
> 4/4/1024
> > MB
> > > > > (used/committed/max)]
> > > > > 17:35:55,797 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > Garbage
> > > > > collector stats: [PS Scavenge, GC TIME (ms): 797, GC COUNT: 5], [PS
> > > > > MarkSweep, GC TIME (ms): 974, GC COUNT: 1]
> > > > > 17:35:56,797 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > Memory
> > > > > usage stats: [HEAP: 615/1917/1917 MB, NON HEAP: 58/59/-1 MB
> > > > > (used/committed/max)]
> > > > > 17:35:56,798 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > > Off-heap
> > > > > pool stats: [Code Cache: 19/20/240 MB (used/committed/max)],
> > > [Metaspace:
> > > > > 34/34/-1 MB (used/committed/max)], [Compressed Class Space:
> 4/4/1024
> > MB
> > > > > (used/committed/max)]
> > > > > 17:35:56,798 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > Garbage
> > > > > collector stats: [PS Scavenge, GC TIME (ms): 797, GC COUNT: 5], [PS
> > > > > MarkSweep, GC TIME (ms): 974, GC COUNT: 1]
> > > > > 17:35:57,798 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > Memory
> > > > > usage stats: [HEAP: 624/1917/1917 MB, NON HEAP: 58/59/-1 MB
> > > > > (used/committed/max)]
> > > > > 17:35:57,798 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > > Off-heap
> > > > > pool stats: [Code Cache: 19/20/240 MB (used/committed/max)],
> > > [Metaspace:
> > > > > 34/34/-1 MB (used/committed/max)], [Compressed Class Space:
> 4/4/1024
> > MB
> > > > > (used/committed/max)]
> > > > > 17:35:57,798 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > Garbage
> > > > > collector stats: [PS Scavenge, GC TIME (ms): 797, GC COUNT: 5], [PS
> > > > > MarkSweep, GC TIME (ms): 974, GC COUNT: 1]
> > > > > 17:35:58,798 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > Memory
> > > > > usage stats: [HEAP: 636/1917/1917 MB, NON HEAP: 58/59/-1 MB
> > > > > (used/committed/max)]
> > > > > 17:35:58,798 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > > Off-heap
> > > > > pool stats: [Code Cache: 19/20/240 MB (used/committed/max)],
> > > [Metaspace:
> > > > > 34/34/-1 MB (used/committed/max)], [Compressed Class Space:
> 4/4/1024
> > MB
> > > > > (used/committed/max)]
> > > > > 17:35:58,798 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > Garbage
> > > > > collector stats: [PS Scavenge, GC TIME (ms): 797, GC COUNT: 5], [PS
> > > > > MarkSweep, GC TIME (ms): 974, GC COUNT: 1]
> > > > > 17:35:59,799 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > Memory
> > > > > usage stats: [HEAP: 641/1917/1917 MB, NON HEAP: 58/59/-1 MB
> > > > > (used/committed/max)]
> > > > > 17:35:59,799 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > > Off-heap
> > > > > pool stats: [Code Cache: 19/20/240 MB (used/committed/max)],
> > > [Metaspace:
> > > > > 34/34/-1 MB (used/committed/max)], [Compressed Class Space:
> 4/4/1024
> > MB
> > > > > (used/committed/max)]
> > > > > 17:35:59,799 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > Garbage
> > > > > collector stats: [PS Scavenge, GC TIME (ms): 797, GC COUNT: 5], [PS
> > > > > MarkSweep, GC TIME (ms): 974, GC COUNT: 1]
> > > > > 17:36:00,799 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > Memory
> > > > > usage stats: [HEAP: 648/1917/1917 MB, NON HEAP: 58/59/-1 MB
> > > > > (used/committed/max)]
> > > > > 17:36:00,799 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > > Off-heap
> > > > > pool stats: [Code Cache: 19/20/240 MB (used/committed/max)],
> > > [Metaspace:
> > > > > 34/34/-1 MB (used/committed/max)], [Compressed Class Space:
> 4/4/1024
> > MB
> > > > > (used/committed/max)]
> > > > > 17:36:00,799 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > Garbage
> > > > > collector stats: [PS Scavenge, GC TIME (ms): 797, GC COUNT: 5], [PS
> > > > > MarkSweep, GC TIME (ms): 974, GC COUNT: 1]
> > > > > 17:36:01,821 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > Memory
> > > > > usage stats: [HEAP: 655/1917/1917 MB, NON HEAP: 58/60/-1 MB
> > > > > (used/committed/max)]
> > > > > 17:36:01,936 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > > Off-heap
> > > > > pool stats: [Code Cache: 19/20/240 MB (used/committed/max)],
> > > [Metaspace:
> > > > > 34/35/-1 MB (used/committed/max)], [Compressed Class Space:
> 4/4/1024
> > MB
> > > > > (used/committed/max)]
> > > > > 17:36:01,936 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > Garbage
> > > > > collector stats: [PS Scavenge, GC TIME (ms): 797, GC COUNT: 5], [PS
> > > > > MarkSweep, GC TIME (ms): 974, GC COUNT: 1]
> > > > > 17:36:02,937 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > Memory
> > > > > usage stats: [HEAP: 665/1917/1917 MB, NON HEAP: 58/60/-1 MB
> > > > > (used/committed/max)]
> > > > > 17:36:02,937 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > > Off-heap
> > > > > pool stats: [Code Cache: 19/20/240 MB (used/committed/max)],
> > > [Metaspace:
> > > > > 34/35/-1 MB (used/committed/max)], [Compressed Class Space:
> 4/4/1024
> > MB
> > > > > (used/committed/max)]
> > > > > 17:36:02,937 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > Garbage
> > > > > collector stats: [PS Scavenge, GC TIME (ms): 797, GC COUNT: 5], [PS
> > > > > MarkSweep, GC TIME (ms): 974, GC COUNT: 1]
> > > > > 17:36:03,944 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > Memory
> > > > > usage stats: [HEAP: 666/1917/1917 MB, NON HEAP: 58/60/-1 MB
> > > > > (used/committed/max)]
> > > > > 17:36:03,950 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > > Off-heap
> > > > > pool stats: [Code Cache: 19/20/240 MB (used/committed/max)],
> > > [Metaspace:
> > > > > 34/35/-1 MB (used/committed/max)], [Compressed Class Space:
> 4/4/1024
> > MB
> > > > > (used/committed/max)]
> > > > > 17:36:03,951 INFO
> > > > > org.apache.flink.runtime.taskmanager.TaskManager              -
> > Garbage
> > > > > collector stats: [PS Scavenge, GC TIME (ms): 797, GC COUNT: 5], [PS
> > > > > MarkSweep, GC TIME (ms): 974, GC COUNT: 1]
> > > > >
> > > > > On Thu, Oct 29, 2015 at 1:55 PM, Till Rohrmann <
> trohrm...@apache.org
> > >
> > > > wrote:
> > > > >
> > > > >> What does the log of the failed TaskManager 10.0.88.140 say?
> > > > >>
> > > > >> On Thu, Oct 29, 2015 at 6:44 PM, Greg Hogan <c...@greghogan.com>
> > > wrote:
> > > > >>
> > > > >>> I removed the use of numactl but left in starting two
> TaskManagers
> > > and
> > > > am
> > > > >>> still seeing TaskManagers crash.
> > > > >>> From the JobManager log:
> > > > >>>
> > > > >>> 17:36:06,412 WARN
> > > > >>> akka.remote.ReliableDeliverySupervisor                        -
> > > > >> Association
> > > > >>> with remote system [akka.tcp://flink@10.0.88.140:45742] has
> > failed,
> > > > >>> address
> > > > >>> is now gated for [5000] ms. Reason is: [Disassociated].
> > > > >>> 17:36:06,567 INFO
> > > > >>> org.apache.flink.runtime.executiongraph.ExecutionGraph        -
> > CHAIN
> > > > >>> GroupReduce (Compute scores) -> FlatMap (checksum()) (370/2322)
> > > > >>> (cac9927a8568c2ad79439262a91478af) switched from RUNNING to
> FAILED
> > > > >>> 17:36:06,572 INFO
> > > > >>> org.apache.flink.runtime.jobmanager.JobManager                -
> > > Status
> > > > of
> > > > >>> job 14d946015fd7b35eb801ea6fee5af9e4 (Flink Java Job at Thu Oct
> 29
> > > > >> 17:34:48
> > > > >>> UTC 2015) changed to FAILING.
> > > > >>> java.lang.Exception: The data preparation for task 'CHAIN
> > GroupReduce
> > > > >>> (Compute scores) -> FlatMap (checksum())' , caused an error:
> Error
> > > > >>> obtaining the sorted input: Thread 'SortMerger Reading Thread'
> > > > terminated
> > > > >>> due to an exception: Connection unexpectedly closed by remote
> task
> > > > >> manager
> > > > >>> 'ip-10-0-88-140/10.0.88.140:58558'. This might indicate that the
> > > > remote
> > > > >>> task manager was lost.
> > > > >>>        at
> > > > >>>
> > org.apache.flink.runtime.operators.BatchTask.run(BatchTask.java:465)
> > > > >>>        at
> > > > >>>
> > > org.apache.flink.runtime.operators.BatchTask.invoke(BatchTask.java:354)
> > > > >>>        at
> > > org.apache.flink.runtime.taskmanager.Task.run(Task.java:584)
> > > > >>>        at java.lang.Thread.run(Thread.java:745)
> > > > >>> Caused by: java.lang.RuntimeException: Error obtaining the sorted
> > > > input:
> > > > >>> Thread 'SortMerger Reading Thread' terminated due to an
> exception:
> > > > >>> Connection unexpectedly closed by remote task manager
> > > 'ip-10-0-88-140/
> > > > >>> 10.0.88.140:58558'. This might indicate that the remote task
> > manager
> > > > was
> > > > >>> lost.
> > > > >>>        at
> > > > >>>
> > > > >>>
> > > > >>
> > > >
> > >
> >
> org.apache.flink.runtime.operators.sort.UnilateralSortMerger.getIterator(UnilateralSortMerger.java:619)
> > > > >>>        at
> > > > >>>
> > > > >>
> > > >
> > >
> >
> org.apache.flink.runtime.operators.BatchTask.getInput(BatchTask.java:1089)
> > > > >>>        at
> > > > >>>
> > > > >>>
> > > > >>
> > > >
> > >
> >
> org.apache.flink.runtime.operators.GroupReduceDriver.prepare(GroupReduceDriver.java:94)
> > > > >>>        at
> > > > >>>
> > org.apache.flink.runtime.operators.BatchTask.run(BatchTask.java:459)
> > > > >>>        ... 3 more
> > > > >>> Caused by: java.io.IOException: Thread 'SortMerger Reading
> Thread'
> > > > >>> terminated due to an exception: Connection unexpectedly closed by
> > > > remote
> > > > >>> task manager 'ip-10-0-88-140/10.0.88.140:58558'. This might
> > indicate
> > > > >> that
> > > > >>> the remote task manager was lost.
> > > > >>>        at
> > > > >>>
> > > > >>>
> > > > >>
> > > >
> > >
> >
> org.apache.flink.runtime.operators.sort.UnilateralSortMerger$ThreadBase.run(UnilateralSortMerger.java:800)
> > > > >>> Caused by:
> > > > >>>
> > > > >>>
> > > > >>
> > > >
> > >
> >
> org.apache.flink.runtime.io.network.netty.exception.RemoteTransportException:
> > > > >>> Connection unexpectedly closed by remote task manager
> > > 'ip-10-0-88-140/
> > > > >>> 10.0.88.140:58558'. This might indicate that the remote task
> > manager
> > > > was
> > > > >>> lost.
> > > > >>>        at
> > > > >>>
> > > > >>>
> > > > >>
> > > >
> > >
> >
> org.apache.flink.runtime.io.network.netty.PartitionRequestClientHandler.channelInactive(PartitionRequestClientHandler.java:119)
> > > > >>>        at
> > > > >>>
> > > > >>>
> > > > >>
> > > >
> > >
> >
> io.netty.channel.AbstractChannelHandlerContext.invokeChannelInactive(AbstractChannelHandlerContext.java:208)
> > > > >>>        at
> > > > >>>
> > > > >>>
> > > > >>
> > > >
> > >
> >
> io.netty.channel.AbstractChannelHandlerContext.fireChannelInactive(AbstractChannelHandlerContext.java:194)
> > > > >>>        at
> > > > >>>
> > > > >>>
> > > > >>
> > > >
> > >
> >
> io.netty.channel.ChannelInboundHandlerAdapter.channelInactive(ChannelInboundHandlerAdapter.java:75)
> > > > >>>        at
> > > > >>>
> > > > >>>
> > > > >>
> > > >
> > >
> >
> io.netty.channel.AbstractChannelHandlerContext.invokeChannelInactive(AbstractChannelHandlerContext.java:208)
> > > > >>>        at
> > > > >>>
> > > > >>>
> > > > >>
> > > >
> > >
> >
> io.netty.channel.AbstractChannelHandlerContext.fireChannelInactive(AbstractChannelHandlerContext.java:194)
> > > > >>>        at
> > > > >>>
> > > > >>>
> > > > >>
> > > >
> > >
> >
> io.netty.handler.codec.ByteToMessageDecoder.channelInactive(ByteToMessageDecoder.java:306)
> > > > >>>        at
> > > > >>>
> > > > >>>
> > > > >>
> > > >
> > >
> >
> io.netty.channel.AbstractChannelHandlerContext.invokeChannelInactive(AbstractChannelHandlerContext.java:208)
> > > > >>>        at
> > > > >>>
> > > > >>>
> > > > >>
> > > >
> > >
> >
> io.netty.channel.AbstractChannelHandlerContext.fireChannelInactive(AbstractChannelHandlerContext.java:194)
> > > > >>>        at
> > > > >>>
> > > > >>>
> > > > >>
> > > >
> > >
> >
> io.netty.channel.DefaultChannelPipeline.fireChannelInactive(DefaultChannelPipeline.java:828)
> > > > >>>        at
> > > > >>>
> > > > >>>
> > > > >>
> > > >
> > >
> >
> io.netty.channel.AbstractChannel$AbstractUnsafe$7.run(AbstractChannel.java:621)
> > > > >>>        at
> > > > >>>
> > > > >>>
> > > > >>
> > > >
> > >
> >
> io.netty.util.concurrent.SingleThreadEventExecutor.runAllTasks(SingleThreadEventExecutor.java:358)
> > > > >>>        at
> > > io.netty.channel.nio.NioEventLoop.run(NioEventLoop.java:357)
> > > > >>>        at
> > > > >>>
> > > > >>>
> > > > >>
> > > >
> > >
> >
> io.netty.util.concurrent.SingleThreadEventExecutor$2.run(SingleThreadEventExecutor.java:112)
> > > > >>>        at java.lang.Thread.run(Thread.java:745)
> > > > >>> 17:36:06,587 INFO
> > > > >>> org.apache.flink.runtime.executiongraph.ExecutionGraph        -
> > CHAIN
> > > > >>> GroupReduce (Compute scores) -> FlatMap (checksum()) (367/2322)
> > > > >>> (d63c681a18b8164bc24936df1ecb159b) switched from RUNNING to
> FAILED
> > > > >>>
> > > > >>>
> > > > >>> On Thu, Oct 29, 2015 at 1:00 PM, Stephan Ewen <se...@apache.org>
> > > > wrote:
> > > > >>>
> > > > >>>> Hi Greg!
> > > > >>>>
> > > > >>>> Interesting... When you say the TaskManagers are dropping, are
> the
> > > > >>>> TaskManager processes crashing, or are they loosing connection
> to
> > > the
> > > > >>>> JobManager?
> > > > >>>>
> > > > >>>> Greetings,
> > > > >>>> Stephan
> > > > >>>>
> > > > >>>>
> > > > >>>> On Thu, Oct 29, 2015 at 9:56 AM, Greg Hogan <c...@greghogan.com
> >
> > > > >> wrote:
> > > > >>>>
> > > > >>>>> I recently discovered that AWS uses NUMA for its largest nodes.
> > An
> > > > >>>> example
> > > > >>>>> c4.8xlarge:
> > > > >>>>>
> > > > >>>>> $ numactl --hardware
> > > > >>>>> available: 2 nodes (0-1)
> > > > >>>>> node 0 cpus: 0 1 2 3 4 5 6 7 8 18 19 20 21 22 23 24 25 26
> > > > >>>>> node 0 size: 29813 MB
> > > > >>>>> node 0 free: 24537 MB
> > > > >>>>> node 1 cpus: 9 10 11 12 13 14 15 16 17 27 28 29 30 31 32 33 34
> 35
> > > > >>>>> node 1 size: 30574 MB
> > > > >>>>> node 1 free: 22757 MB
> > > > >>>>> node distances:
> > > > >>>>> node   0   1
> > > > >>>>>  0:  10  20
> > > > >>>>>  1:  20  10
> > > > >>>>>
> > > > >>>>> I discovered yesterday that Flink performed ~20-30% faster on
> > large
> > > > >>>>> datasets by running two NUMA-constrained TaskManagers per node.
> > The
> > > > >>>>> JobManager node ran a single TaskManager. Resources were
> divided
> > in
> > > > >>> half
> > > > >>>>> relative to running a single TaskManager.
> > > > >>>>>
> > > > >>>>> The changes from the tail of /bin/taskmanager.sh:
> > > > >>>>>
> > > > >>>>> -"${FLINK_BIN_DIR}"/flink-daemon.sh $STARTSTOP taskmanager
> > > > >> "${args[@]}"
> > > > >>>>> +numactl --membind=0 --cpunodebind=0
> > > > >> "${FLINK_BIN_DIR}"/flink-daemon.sh
> > > > >>>>> $STARTSTOP taskmanager "${args[@]}"
> > > > >>>>> +numactl --membind=1 --cpunodebind=1
> > > > >> "${FLINK_BIN_DIR}"/flink-daemon.sh
> > > > >>>>> $STARTSTOP taskmanager "${args[@]}"
> > > > >>>>>
> > > > >>>>> After reverting this change the system is again stable. I had
> not
> > > > >>>>> experienced issues using numactl when running 16 nodes.
> > > > >>>>>
> > > > >>>>> Greg
> > > > >>>>>
> > > > >>>>
> > > > >>>
> > > > >>
> > > >
> > > >
> > >
> >
>

Reply via email to