[jira] [Updated] (SPARK-14065) serialize MapStatuses in serial model
[
https://issues.apache.org/jira/browse/SPARK-14065?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
xukun updated SPARK-14065:
--
Description:
the query like this:
{quote}
use tpcds_parquet_30720;
drop table temp;
create table temp as select ws_order_number, sum1, sum2, sum1 * sum2
from (select ws_order_number, count(1) as sum1 from web_sales group by
ws_order_number) x
join (select wr_order_number, count(1) as sum2 from web_returns group by
wr_order_number) y
on x.ws_order_number = y.wr_order_number;
{quote}
Executor log shows 'GetMapOutputStatuses RpcTimeoutException'
{code:borderStyle=solid}
2016-03-22 11:48:48,388 | WARN | [Executor task launch worker-1] | Error
sending message [message = GetMapOutputStatuses(1)] in 1 attempts |
org.apache.spark.Logging$class.logWarning(Logging.scala:92)
org.apache.spark.rpc.RpcTimeoutException: Futures timed out after [120
seconds]. This timeout is controlled by spark.network.timeout
at
org.apache.spark.rpc.RpcTimeout.org$apache$spark$rpc$RpcTimeout$$createRpcTimeoutException(RpcTimeout.scala:48)
at
org.apache.spark.rpc.RpcTimeout$$anonfun$addMessageIfTimeout$1.applyOrElse(RpcTimeout.scala:63)
at
org.apache.spark.rpc.RpcTimeout$$anonfun$addMessageIfTimeout$1.applyOrElse(RpcTimeout.scala:59)
at
scala.runtime.AbstractPartialFunction.apply(AbstractPartialFunction.scala:33)
at org.apache.spark.rpc.RpcTimeout.awaitResult(RpcTimeout.scala:76)
at
org.apache.spark.rpc.RpcEndpointRef.askWithRetry(RpcEndpointRef.scala:101)
at
org.apache.spark.rpc.RpcEndpointRef.askWithRetry(RpcEndpointRef.scala:77)
at
org.apache.spark.MapOutputTracker.askTracker(MapOutputTracker.scala:98)
at
org.apache.spark.MapOutputTracker.getMapSizesByExecutorId(MapOutputTracker.scala:156)
at
org.apache.spark.shuffle.hash.HashShuffleReader.read(HashShuffleReader.scala:47)
at
org.apache.spark.sql.execution.ShuffledRowRDD.compute(ShuffledRowRDD.scala:71)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:301)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:265)
at
org.apache.spark.rdd.MapPartitionsWithPreparationRDD.compute(MapPartitionsWithPreparationRDD.scala:63)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:301)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:265)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:301)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:265)
at
org.apache.spark.rdd.MapPartitionsWithPreparationRDD.compute(MapPartitionsWithPreparationRDD.scala:63)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:301)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:265)
at
org.apache.spark.rdd.ZippedPartitionsRDD2.compute(ZippedPartitionsRDD.scala:99)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:301)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:265)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:301)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:265)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:301)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:265)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:68)
at org.apache.spark.scheduler.Task.run(Task.scala:90)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:229)
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
Caused by: java.util.concurrent.TimeoutException: Futures timed out after [120
seconds]
at scala.concurrent.impl.Promise$DefaultPromise.ready(Promise.scala:219)
at
scala.concurrent.impl.Promise$DefaultPromise.result(Promise.scala:223)
at scala.concurrent.Await$$anonfun$result$1.apply(package.scala:107)
at
scala.concurrent.BlockContext$DefaultBlockContext$.blockOn(BlockContext.scala:53)
at scala.concurrent.Await$.result(package.scala:107)
at org.apache.spark.rpc.RpcTimeout.awaitResult(RpcTimeout.scala:75)
... 32 more
2016-03-22 11:48:52,044 | INFO | [Executor task launch worker-1] | Got the
output locations | org.apache.spark.Logging$class.logInfo(Logging.scala:59)
{code}
Driver log shows serialize mapStatus is serial, the procedure is slow.
{code:borderStyle=solid}
Line 192882: 16/03/22 11:46:54 INFO [dispatcher-event-loop-25]
MapOutputTrackerMaster: Size of output statuses for shuffle 1 is
[jira] [Updated] (SPARK-14065) serialize MapStatuses in serial model
[
https://issues.apache.org/jira/browse/SPARK-14065?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
xukun updated SPARK-14065:
--
Description:
the query like this:
{quote}
use tpcds_parquet_30720;
drop table temp;
create table temp as select ws_order_number, sum1, sum2, sum1 * sum2
from (select ws_order_number, count(1) as sum1 from web_sales group by
ws_order_number) x
join (select wr_order_number, count(1) as sum2 from web_returns group by
wr_order_number) y
on x.ws_order_number = y.wr_order_number;
{quote}
Executor log shows 'GetMapOutputStatuses RpcTimeoutException'
{code:borderStyle=solid}
2016-03-22 11:48:48,388 | WARN | [Executor task launch worker-1] | Error
sending message [message = GetMapOutputStatuses(1)] in 1 attempts |
org.apache.spark.Logging$class.logWarning(Logging.scala:92)
org.apache.spark.rpc.RpcTimeoutException: Futures timed out after [120
seconds]. This timeout is controlled by spark.network.timeout
at
org.apache.spark.rpc.RpcTimeout.org$apache$spark$rpc$RpcTimeout$$createRpcTimeoutException(RpcTimeout.scala:48)
at
org.apache.spark.rpc.RpcTimeout$$anonfun$addMessageIfTimeout$1.applyOrElse(RpcTimeout.scala:63)
at
org.apache.spark.rpc.RpcTimeout$$anonfun$addMessageIfTimeout$1.applyOrElse(RpcTimeout.scala:59)
at
scala.runtime.AbstractPartialFunction.apply(AbstractPartialFunction.scala:33)
at org.apache.spark.rpc.RpcTimeout.awaitResult(RpcTimeout.scala:76)
at
org.apache.spark.rpc.RpcEndpointRef.askWithRetry(RpcEndpointRef.scala:101)
at
org.apache.spark.rpc.RpcEndpointRef.askWithRetry(RpcEndpointRef.scala:77)
at
org.apache.spark.MapOutputTracker.askTracker(MapOutputTracker.scala:98)
at
org.apache.spark.MapOutputTracker.getMapSizesByExecutorId(MapOutputTracker.scala:156)
at
org.apache.spark.shuffle.hash.HashShuffleReader.read(HashShuffleReader.scala:47)
at
org.apache.spark.sql.execution.ShuffledRowRDD.compute(ShuffledRowRDD.scala:71)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:301)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:265)
at
org.apache.spark.rdd.MapPartitionsWithPreparationRDD.compute(MapPartitionsWithPreparationRDD.scala:63)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:301)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:265)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:301)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:265)
at
org.apache.spark.rdd.MapPartitionsWithPreparationRDD.compute(MapPartitionsWithPreparationRDD.scala:63)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:301)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:265)
at
org.apache.spark.rdd.ZippedPartitionsRDD2.compute(ZippedPartitionsRDD.scala:99)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:301)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:265)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:301)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:265)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:301)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:265)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:68)
at org.apache.spark.scheduler.Task.run(Task.scala:90)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:229)
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
Caused by: java.util.concurrent.TimeoutException: Futures timed out after [120
seconds]
at scala.concurrent.impl.Promise$DefaultPromise.ready(Promise.scala:219)
at
scala.concurrent.impl.Promise$DefaultPromise.result(Promise.scala:223)
at scala.concurrent.Await$$anonfun$result$1.apply(package.scala:107)
at
scala.concurrent.BlockContext$DefaultBlockContext$.blockOn(BlockContext.scala:53)
at scala.concurrent.Await$.result(package.scala:107)
at org.apache.spark.rpc.RpcTimeout.awaitResult(RpcTimeout.scala:75)
... 32 more
2016-03-22 11:48:52,044 | INFO | [Executor task launch worker-1] | Got the
output locations | org.apache.spark.Logging$class.logInfo(Logging.scala:59)
{code}
Driver log shows serialize mapStatus is serial
{code:borderStyle=solid}
Line 192882: 16/03/22 11:46:54 INFO [dispatcher-event-loop-25]
MapOutputTrackerMaster: Size of output statuses for shuffle 1 is 10298063 bytes
[jira] [Updated] (SPARK-14065) serialize MapStatuses in serial model
[
https://issues.apache.org/jira/browse/SPARK-14065?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
xukun updated SPARK-14065:
--
Description:
the query like this:
_
use tpcds_parquet_30720;
drop table temp;
create table temp as select ws_order_number, sum1, sum2, sum1 * sum2
from (select ws_order_number, count(1) as sum1 from web_sales group by
ws_order_number) x
join (select wr_order_number, count(1) as sum2 from web_returns group by
wr_order_number) y
on x.ws_order_number = y.wr_order_number;
_
Executor log shows GetMapOutputStatuses timeout:
{code:borderStyle=solid}
2016-03-22 11:48:48,388 | WARN | [Executor task launch worker-1] | Error
sending message [message = GetMapOutputStatuses(1)] in 1 attempts |
org.apache.spark.Logging$class.logWarning(Logging.scala:92)
org.apache.spark.rpc.RpcTimeoutException: Futures timed out after [120
seconds]. This timeout is controlled by spark.network.timeout
at
org.apache.spark.rpc.RpcTimeout.org$apache$spark$rpc$RpcTimeout$$createRpcTimeoutException(RpcTimeout.scala:48)
at
org.apache.spark.rpc.RpcTimeout$$anonfun$addMessageIfTimeout$1.applyOrElse(RpcTimeout.scala:63)
at
org.apache.spark.rpc.RpcTimeout$$anonfun$addMessageIfTimeout$1.applyOrElse(RpcTimeout.scala:59)
at
scala.runtime.AbstractPartialFunction.apply(AbstractPartialFunction.scala:33)
at org.apache.spark.rpc.RpcTimeout.awaitResult(RpcTimeout.scala:76)
at
org.apache.spark.rpc.RpcEndpointRef.askWithRetry(RpcEndpointRef.scala:101)
at
org.apache.spark.rpc.RpcEndpointRef.askWithRetry(RpcEndpointRef.scala:77)
at
org.apache.spark.MapOutputTracker.askTracker(MapOutputTracker.scala:98)
at
org.apache.spark.MapOutputTracker.getMapSizesByExecutorId(MapOutputTracker.scala:156)
at
org.apache.spark.shuffle.hash.HashShuffleReader.read(HashShuffleReader.scala:47)
at
org.apache.spark.sql.execution.ShuffledRowRDD.compute(ShuffledRowRDD.scala:71)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:301)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:265)
at
org.apache.spark.rdd.MapPartitionsWithPreparationRDD.compute(MapPartitionsWithPreparationRDD.scala:63)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:301)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:265)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:301)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:265)
at
org.apache.spark.rdd.MapPartitionsWithPreparationRDD.compute(MapPartitionsWithPreparationRDD.scala:63)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:301)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:265)
at
org.apache.spark.rdd.ZippedPartitionsRDD2.compute(ZippedPartitionsRDD.scala:99)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:301)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:265)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:301)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:265)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:301)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:265)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:68)
at org.apache.spark.scheduler.Task.run(Task.scala:90)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:229)
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
Caused by: java.util.concurrent.TimeoutException: Futures timed out after [120
seconds]
at scala.concurrent.impl.Promise$DefaultPromise.ready(Promise.scala:219)
at
scala.concurrent.impl.Promise$DefaultPromise.result(Promise.scala:223)
at scala.concurrent.Await$$anonfun$result$1.apply(package.scala:107)
at
scala.concurrent.BlockContext$DefaultBlockContext$.blockOn(BlockContext.scala:53)
at scala.concurrent.Await$.result(package.scala:107)
at org.apache.spark.rpc.RpcTimeout.awaitResult(RpcTimeout.scala:75)
... 32 more
2016-03-22 11:48:52,044 | INFO | [Executor task launch worker-1] | Got the
output locations | org.apache.spark.Logging$class.logInfo(Logging.scala:59)
{code}
Driver log shows serialize mapStatus is serial
{code:borderStyle=solid}
Line 192882: 16/03/22 11:46:54 INFO [dispatcher-event-loop-25]
MapOutputTrackerMaster: Size of output statuses for shuffle 1 is 10298063 bytes
Line 192914: 16/03/22
[jira] [Updated] (SPARK-14065) serialize MapStatuses in serial model
[
https://issues.apache.org/jira/browse/SPARK-14065?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
xukun updated SPARK-14065:
--
Description:
the query like this:
{quote}
use tpcds_parquet_30720;
drop table temp;
create table temp as select ws_order_number, sum1, sum2, sum1 * sum2
from (select ws_order_number, count(1) as sum1 from web_sales group by
ws_order_number) x
join (select wr_order_number, count(1) as sum2 from web_returns group by
wr_order_number) y
on x.ws_order_number = y.wr_order_number;
{quote}
Executor log shows GetMapOutputStatuses timeout:
{code:borderStyle=solid}
2016-03-22 11:48:48,388 | WARN | [Executor task launch worker-1] | Error
sending message [message = GetMapOutputStatuses(1)] in 1 attempts |
org.apache.spark.Logging$class.logWarning(Logging.scala:92)
org.apache.spark.rpc.RpcTimeoutException: Futures timed out after [120
seconds]. This timeout is controlled by spark.network.timeout
at
org.apache.spark.rpc.RpcTimeout.org$apache$spark$rpc$RpcTimeout$$createRpcTimeoutException(RpcTimeout.scala:48)
at
org.apache.spark.rpc.RpcTimeout$$anonfun$addMessageIfTimeout$1.applyOrElse(RpcTimeout.scala:63)
at
org.apache.spark.rpc.RpcTimeout$$anonfun$addMessageIfTimeout$1.applyOrElse(RpcTimeout.scala:59)
at
scala.runtime.AbstractPartialFunction.apply(AbstractPartialFunction.scala:33)
at org.apache.spark.rpc.RpcTimeout.awaitResult(RpcTimeout.scala:76)
at
org.apache.spark.rpc.RpcEndpointRef.askWithRetry(RpcEndpointRef.scala:101)
at
org.apache.spark.rpc.RpcEndpointRef.askWithRetry(RpcEndpointRef.scala:77)
at
org.apache.spark.MapOutputTracker.askTracker(MapOutputTracker.scala:98)
at
org.apache.spark.MapOutputTracker.getMapSizesByExecutorId(MapOutputTracker.scala:156)
at
org.apache.spark.shuffle.hash.HashShuffleReader.read(HashShuffleReader.scala:47)
at
org.apache.spark.sql.execution.ShuffledRowRDD.compute(ShuffledRowRDD.scala:71)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:301)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:265)
at
org.apache.spark.rdd.MapPartitionsWithPreparationRDD.compute(MapPartitionsWithPreparationRDD.scala:63)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:301)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:265)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:301)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:265)
at
org.apache.spark.rdd.MapPartitionsWithPreparationRDD.compute(MapPartitionsWithPreparationRDD.scala:63)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:301)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:265)
at
org.apache.spark.rdd.ZippedPartitionsRDD2.compute(ZippedPartitionsRDD.scala:99)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:301)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:265)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:301)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:265)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:301)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:265)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:68)
at org.apache.spark.scheduler.Task.run(Task.scala:90)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:229)
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
Caused by: java.util.concurrent.TimeoutException: Futures timed out after [120
seconds]
at scala.concurrent.impl.Promise$DefaultPromise.ready(Promise.scala:219)
at
scala.concurrent.impl.Promise$DefaultPromise.result(Promise.scala:223)
at scala.concurrent.Await$$anonfun$result$1.apply(package.scala:107)
at
scala.concurrent.BlockContext$DefaultBlockContext$.blockOn(BlockContext.scala:53)
at scala.concurrent.Await$.result(package.scala:107)
at org.apache.spark.rpc.RpcTimeout.awaitResult(RpcTimeout.scala:75)
... 32 more
2016-03-22 11:48:52,044 | INFO | [Executor task launch worker-1] | Got the
output locations | org.apache.spark.Logging$class.logInfo(Logging.scala:59)
{code}
Driver log shows serialize mapStatus is serial
{code:borderStyle=solid}
Line 192882: 16/03/22 11:46:54 INFO [dispatcher-event-loop-25]
MapOutputTrackerMaster: Size of output statuses for shuffle 1 is 10298063 bytes
Line 192914:
[jira] [Updated] (SPARK-14065) serialize MapStatuses in serial model
[
https://issues.apache.org/jira/browse/SPARK-14065?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
xukun updated SPARK-14065:
--
Description:
the query like this:
use tpcds_parquet_30720;
drop table temp;
create table temp as select ws_order_number, sum1, sum2, sum1 * sum2
from (select ws_order_number, count(1) as sum1 from web_sales group by
ws_order_number) x
join (select wr_order_number, count(1) as sum2 from web_returns group by
wr_order_number) y
on x.ws_order_number = y.wr_order_number;
Executor log shows GetMapOutputStatuses timeout:
{code:borderStyle=solid}
2016-03-22 11:48:48,388 | WARN | [Executor task launch worker-1] | Error
sending message [message = GetMapOutputStatuses(1)] in 1 attempts |
org.apache.spark.Logging$class.logWarning(Logging.scala:92)
org.apache.spark.rpc.RpcTimeoutException: Futures timed out after [120
seconds]. This timeout is controlled by spark.network.timeout
at
org.apache.spark.rpc.RpcTimeout.org$apache$spark$rpc$RpcTimeout$$createRpcTimeoutException(RpcTimeout.scala:48)
at
org.apache.spark.rpc.RpcTimeout$$anonfun$addMessageIfTimeout$1.applyOrElse(RpcTimeout.scala:63)
at
org.apache.spark.rpc.RpcTimeout$$anonfun$addMessageIfTimeout$1.applyOrElse(RpcTimeout.scala:59)
at
scala.runtime.AbstractPartialFunction.apply(AbstractPartialFunction.scala:33)
at org.apache.spark.rpc.RpcTimeout.awaitResult(RpcTimeout.scala:76)
at
org.apache.spark.rpc.RpcEndpointRef.askWithRetry(RpcEndpointRef.scala:101)
at
org.apache.spark.rpc.RpcEndpointRef.askWithRetry(RpcEndpointRef.scala:77)
at
org.apache.spark.MapOutputTracker.askTracker(MapOutputTracker.scala:98)
at
org.apache.spark.MapOutputTracker.getMapSizesByExecutorId(MapOutputTracker.scala:156)
at
org.apache.spark.shuffle.hash.HashShuffleReader.read(HashShuffleReader.scala:47)
at
org.apache.spark.sql.execution.ShuffledRowRDD.compute(ShuffledRowRDD.scala:71)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:301)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:265)
at
org.apache.spark.rdd.MapPartitionsWithPreparationRDD.compute(MapPartitionsWithPreparationRDD.scala:63)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:301)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:265)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:301)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:265)
at
org.apache.spark.rdd.MapPartitionsWithPreparationRDD.compute(MapPartitionsWithPreparationRDD.scala:63)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:301)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:265)
at
org.apache.spark.rdd.ZippedPartitionsRDD2.compute(ZippedPartitionsRDD.scala:99)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:301)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:265)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:301)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:265)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:301)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:265)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:68)
at org.apache.spark.scheduler.Task.run(Task.scala:90)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:229)
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
Caused by: java.util.concurrent.TimeoutException: Futures timed out after [120
seconds]
at scala.concurrent.impl.Promise$DefaultPromise.ready(Promise.scala:219)
at
scala.concurrent.impl.Promise$DefaultPromise.result(Promise.scala:223)
at scala.concurrent.Await$$anonfun$result$1.apply(package.scala:107)
at
scala.concurrent.BlockContext$DefaultBlockContext$.blockOn(BlockContext.scala:53)
at scala.concurrent.Await$.result(package.scala:107)
at org.apache.spark.rpc.RpcTimeout.awaitResult(RpcTimeout.scala:75)
... 32 more
2016-03-22 11:48:52,044 | INFO | [Executor task launch worker-1] | Got the
output locations | org.apache.spark.Logging$class.logInfo(Logging.scala:59)
{code}
Driver log shows serialize mapStatus is serial
{code:borderStyle=solid}
Line 192882: 16/03/22 11:46:54 INFO [dispatcher-event-loop-25]
MapOutputTrackerMaster: Size of output statuses for shuffle 1 is 10298063 bytes
Line 192914: 16/03/22 11:47:01
[jira] [Updated] (SPARK-14065) serialize MapStatuses in serial model
[
https://issues.apache.org/jira/browse/SPARK-14065?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
xukun updated SPARK-14065:
--
Description:
the query like this:
{code:title=Bar.java|borderStyle=solid}
use tpcds_parquet_30720;
drop table temp;
create table temp as select ws_order_number, sum1, sum2, sum1 * sum2
from (select ws_order_number, count(1) as sum1 from web_sales group by
ws_order_number) x
join (select wr_order_number, count(1) as sum2 from web_returns group by
wr_order_number) y
on x.ws_order_number = y.wr_order_number;
{code}
Executor log shows GetMapOutputStatuses timeout:
```
2016-03-22 11:48:48,388 | WARN | [Executor task launch worker-1] | Error
sending message [message = GetMapOutputStatuses(1)] in 1 attempts |
org.apache.spark.Logging$class.logWarning(Logging.scala:92)
org.apache.spark.rpc.RpcTimeoutException: Futures timed out after [120
seconds]. This timeout is controlled by spark.network.timeout
at
org.apache.spark.rpc.RpcTimeout.org$apache$spark$rpc$RpcTimeout$$createRpcTimeoutException(RpcTimeout.scala:48)
at
org.apache.spark.rpc.RpcTimeout$$anonfun$addMessageIfTimeout$1.applyOrElse(RpcTimeout.scala:63)
at
org.apache.spark.rpc.RpcTimeout$$anonfun$addMessageIfTimeout$1.applyOrElse(RpcTimeout.scala:59)
at
scala.runtime.AbstractPartialFunction.apply(AbstractPartialFunction.scala:33)
at org.apache.spark.rpc.RpcTimeout.awaitResult(RpcTimeout.scala:76)
at
org.apache.spark.rpc.RpcEndpointRef.askWithRetry(RpcEndpointRef.scala:101)
at
org.apache.spark.rpc.RpcEndpointRef.askWithRetry(RpcEndpointRef.scala:77)
at
org.apache.spark.MapOutputTracker.askTracker(MapOutputTracker.scala:98)
at
org.apache.spark.MapOutputTracker.getMapSizesByExecutorId(MapOutputTracker.scala:156)
at
org.apache.spark.shuffle.hash.HashShuffleReader.read(HashShuffleReader.scala:47)
at
org.apache.spark.sql.execution.ShuffledRowRDD.compute(ShuffledRowRDD.scala:71)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:301)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:265)
at
org.apache.spark.rdd.MapPartitionsWithPreparationRDD.compute(MapPartitionsWithPreparationRDD.scala:63)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:301)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:265)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:301)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:265)
at
org.apache.spark.rdd.MapPartitionsWithPreparationRDD.compute(MapPartitionsWithPreparationRDD.scala:63)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:301)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:265)
at
org.apache.spark.rdd.ZippedPartitionsRDD2.compute(ZippedPartitionsRDD.scala:99)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:301)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:265)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:301)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:265)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:301)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:265)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:68)
at org.apache.spark.scheduler.Task.run(Task.scala:90)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:229)
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
Caused by: java.util.concurrent.TimeoutException: Futures timed out after [120
seconds]
at scala.concurrent.impl.Promise$DefaultPromise.ready(Promise.scala:219)
at
scala.concurrent.impl.Promise$DefaultPromise.result(Promise.scala:223)
at scala.concurrent.Await$$anonfun$result$1.apply(package.scala:107)
at
scala.concurrent.BlockContext$DefaultBlockContext$.blockOn(BlockContext.scala:53)
at scala.concurrent.Await$.result(package.scala:107)
at org.apache.spark.rpc.RpcTimeout.awaitResult(RpcTimeout.scala:75)
... 32 more
2016-03-22 11:48:52,044 | INFO | [Executor task launch worker-1] | Got the
output locations | org.apache.spark.Logging$class.logInfo(Logging.scala:59)
```
Driver log shows serialize mapStatus is serial
```
Line 192882: 16/03/22 11:46:54 INFO [dispatcher-event-loop-25]
MapOutputTrackerMaster: Size of output statuses for shuffle 1 is 10298063 bytes
Line 192914: 16/03/22 11:47:01
[jira] [Updated] (SPARK-14065) serialize MapStatuses in serial model
[ https://issues.apache.org/jira/browse/SPARK-14065?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] xukun updated SPARK-14065: -- Description: the query like this: ```shell use tpcds_parquet_30720; drop table temp; create table temp as select ws_order_number, sum1, sum2, sum1 * sum2 from (select ws_order_number, count(1) as sum1 from web_sales group by ws_order_number) x join (select wr_order_number, count(1) as sum2 from web_returns group by wr_order_number) y on x.ws_order_number = y.wr_order_number; ``` Executor log shows GetMapOutputStatuses timeout: ``` 2016-03-22 11:48:48,388 | WARN | [Executor task launch worker-1] | Error sending message [message = GetMapOutputStatuses(1)] in 1 attempts | org.apache.spark.Logging$class.logWarning(Logging.scala:92) org.apache.spark.rpc.RpcTimeoutException: Futures timed out after [120 seconds]. This timeout is controlled by spark.network.timeout at org.apache.spark.rpc.RpcTimeout.org$apache$spark$rpc$RpcTimeout$$createRpcTimeoutException(RpcTimeout.scala:48) at org.apache.spark.rpc.RpcTimeout$$anonfun$addMessageIfTimeout$1.applyOrElse(RpcTimeout.scala:63) at org.apache.spark.rpc.RpcTimeout$$anonfun$addMessageIfTimeout$1.applyOrElse(RpcTimeout.scala:59) at scala.runtime.AbstractPartialFunction.apply(AbstractPartialFunction.scala:33) at org.apache.spark.rpc.RpcTimeout.awaitResult(RpcTimeout.scala:76) at org.apache.spark.rpc.RpcEndpointRef.askWithRetry(RpcEndpointRef.scala:101) at org.apache.spark.rpc.RpcEndpointRef.askWithRetry(RpcEndpointRef.scala:77) at org.apache.spark.MapOutputTracker.askTracker(MapOutputTracker.scala:98) at org.apache.spark.MapOutputTracker.getMapSizesByExecutorId(MapOutputTracker.scala:156) at org.apache.spark.shuffle.hash.HashShuffleReader.read(HashShuffleReader.scala:47) at org.apache.spark.sql.execution.ShuffledRowRDD.compute(ShuffledRowRDD.scala:71) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:301) at org.apache.spark.rdd.RDD.iterator(RDD.scala:265) at org.apache.spark.rdd.MapPartitionsWithPreparationRDD.compute(MapPartitionsWithPreparationRDD.scala:63) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:301) at org.apache.spark.rdd.RDD.iterator(RDD.scala:265) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:301) at org.apache.spark.rdd.RDD.iterator(RDD.scala:265) at org.apache.spark.rdd.MapPartitionsWithPreparationRDD.compute(MapPartitionsWithPreparationRDD.scala:63) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:301) at org.apache.spark.rdd.RDD.iterator(RDD.scala:265) at org.apache.spark.rdd.ZippedPartitionsRDD2.compute(ZippedPartitionsRDD.scala:99) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:301) at org.apache.spark.rdd.RDD.iterator(RDD.scala:265) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:301) at org.apache.spark.rdd.RDD.iterator(RDD.scala:265) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:301) at org.apache.spark.rdd.RDD.iterator(RDD.scala:265) at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:68) at org.apache.spark.scheduler.Task.run(Task.scala:90) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:229) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617) at java.lang.Thread.run(Thread.java:745) Caused by: java.util.concurrent.TimeoutException: Futures timed out after [120 seconds] at scala.concurrent.impl.Promise$DefaultPromise.ready(Promise.scala:219) at scala.concurrent.impl.Promise$DefaultPromise.result(Promise.scala:223) at scala.concurrent.Await$$anonfun$result$1.apply(package.scala:107) at scala.concurrent.BlockContext$DefaultBlockContext$.blockOn(BlockContext.scala:53) at scala.concurrent.Await$.result(package.scala:107) at org.apache.spark.rpc.RpcTimeout.awaitResult(RpcTimeout.scala:75) ... 32 more 2016-03-22 11:48:52,044 | INFO | [Executor task launch worker-1] | Got the output locations | org.apache.spark.Logging$class.logInfo(Logging.scala:59) ``` Driver log shows serialize mapStatus is serial ``` Line 192882: 16/03/22 11:46:54 INFO [dispatcher-event-loop-25] MapOutputTrackerMaster: Size of output statuses for shuffle 1 is 10298063 bytes Line 192914: 16/03/22 11:47:01 INFO [dispatcher-event-loop-7]
