Commit message (Collapse) | Author | Age | Files | Lines | |
---|---|---|---|---|---|
* | Further simplify checking for Nil. | Stephen Haberman | 2013-02-02 | 1 | -3/+1 |
| | |||||
* | Once we find a split with no block, we don't have to look for more. | Stephen Haberman | 2013-01-31 | 1 | -12/+11 |
| | |||||
* | Merge pull request #430 from pwendell/pyspark-guide | Matei Zaharia | 2013-01-30 | 2 | -2/+10 |
|\ | | | | | Minor improvements to PySpark docs | ||||
| * | Make module help available in python shell. | Patrick Wendell | 2013-01-30 | 2 | -0/+2 |
| | | | | | | | | Also, adds a line in doc explaining how to use. | ||||
| * | Inclue packaging and launching pyspark in guide. | Patrick Wendell | 2013-01-30 | 1 | -2/+8 |
| | | | | | | | | It's nicer if all the commands you need are made explicit. | ||||
* | | Merge pull request #426 from woggling/conn-manager-ips | Matei Zaharia | 2013-01-30 | 2 | -5/+13 |
|\ \ | | | | | | | Remember ConnectionManagerId used to initiate SendingConnections | ||||
| * | | Remember ConnectionManagerId used to initiate SendingConnections. | Charles Reiss | 2013-01-29 | 2 | -5/+13 |
| | | | | | | | | | | | | | | | | | | This prevents ConnectionManager from getting confused if a machine has multiple host names and the one getHostName() finds happens not to be the one that was passed from, e.g., the BlockManagerMaster. | ||||
* | | | Merge pull request #428 from woggling/mesos-exec-id | Matei Zaharia | 2013-01-30 | 2 | -15/+21 |
|\ \ \ | | | | | | | | | Make ExecutorIDs include SlaveIDs when running Mesos | ||||
| * | | | Remove remants of attempt to use slaveId-executorId in MesosExecutorBackend | Charles Reiss | 2013-01-30 | 1 | -1/+1 |
| | | | | |||||
| * | | | Use Mesos ExecutorIDs to hold SlaveIDs. Then we can safely use | Charles Reiss | 2013-01-30 | 2 | -15/+21 |
| |/ / | | | | | | | | | | the Mesos ExecutorID as a Spark ExecutorID. | ||||
* | | | Merge pull request #429 from stephenh/includemessage | Matei Zaharia | 2013-01-30 | 1 | -1/+3 |
|\ \ \ | | | | | | | | | Include message and exitStatus if availalbe. | ||||
| * | | | Include message and exitStatus if availalbe. | Stephen Haberman | 2013-01-30 | 1 | -1/+3 |
|/ / / | |||||
* | | | Merge remote-tracking branch 'stephenh/removefailedjob' | Matei Zaharia | 2013-01-29 | 2 | -7/+9 |
|\ \ \ | | | | | | | | | | | | | | | | | Conflicts: core/src/main/scala/spark/deploy/master/Master.scala | ||||
| * | | | Fix Worker logInfo about unknown executor. | Stephen Haberman | 2013-01-22 | 1 | -1/+1 |
| | | | | |||||
| * | | | Don't bother creating an exception. | Stephen Haberman | 2013-01-22 | 1 | -2/+1 |
| | | | | |||||
| * | | | Handle Master telling the Worker to kill an already-dead executor. | Stephen Haberman | 2013-01-22 | 1 | -3/+7 |
| | | | | |||||
| * | | | Call removeJob instead of killing the cluster. | Stephen Haberman | 2013-01-22 | 1 | -2/+1 |
| | | | | |||||
* | | | | Merge pull request #425 from stephenh/toDebugString | Matei Zaharia | 2013-01-29 | 2 | -0/+21 |
|\ \ \ \ | | | | | | | | | | | Add RDD.toDebugString. | ||||
| * | | | | Include name, if set, in RDD.toString(). | Stephen Haberman | 2013-01-29 | 1 | -1/+6 |
| | | | | | |||||
| * | | | | Add number of splits. | Stephen Haberman | 2013-01-29 | 1 | -1/+2 |
| | | | | | |||||
| * | | | | Add JavaRDDLike.toDebugString(). | Stephen Haberman | 2013-01-29 | 1 | -0/+5 |
| | | | | | |||||
| * | | | | Add RDD.toDebugString. | Stephen Haberman | 2013-01-28 | 1 | -0/+10 |
| | | | | | | | | | | | | | | | | | | | | Original idea by Nathan Kronenfeld. | ||||
* | | | | | Merge pull request #415 from stephenh/driver | Matei Zaharia | 2013-01-29 | 34 | -216/+214 |
|\ \ \ \ \ | |_|_|/ / |/| | | | | Replace old 'master' term with 'driver'. | ||||
| * | | | | Merge branch 'master' into driver | Stephen Haberman | 2013-01-28 | 57 | -390/+938 |
| |\| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Conflicts: core/src/main/scala/spark/SparkContext.scala core/src/main/scala/spark/SparkEnv.scala core/src/main/scala/spark/deploy/LocalSparkCluster.scala core/src/main/scala/spark/executor/StandaloneExecutorBackend.scala core/src/main/scala/spark/scheduler/cluster/SparkDeploySchedulerBackend.scala core/src/main/scala/spark/scheduler/cluster/StandaloneClusterMessage.scala core/src/main/scala/spark/scheduler/cluster/StandaloneSchedulerBackend.scala core/src/main/scala/spark/storage/BlockManagerMaster.scala core/src/main/scala/spark/storage/ThreadingTest.scala core/src/test/scala/spark/MapOutputTrackerSuite.scala | ||||
| * | | | | Replace old 'master' term with 'driver'. | Stephen Haberman | 2013-01-25 | 34 | -251/+248 |
| | | | | | |||||
* | | | | | Simplify checkpointing code and RDD class a little: | Matei Zaharia | 2013-01-28 | 15 | -168/+153 |
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | - RDD's getDependencies and getSplits methods are now guaranteed to be called only once, so subclasses can safely do computation in there without worrying about caching the results. - The management of a "splits_" variable that is cleared out when we checkpoint an RDD is now done in the RDD class. - A few of the RDD subclasses are simpler. - CheckpointRDD's compute() method no longer assumes that it is given a CheckpointRDDSplit -- it can work just as well on a split from the original RDD, because it only looks at its index. This is important because things like UnionRDD and ZippedRDD remember the parent's splits as part of their own and wouldn't work on checkpointed parents. - RDD.iterator can now reuse cached data if an RDD is computed before it is checkpointed. It seems like it wouldn't do this before (it always called iterator() on the CheckpointRDD, which read from HDFS). | ||||
* | | | | | Fix code that depended on metadata cleaner interval being in minutes | Matei Zaharia | 2013-01-28 | 2 | -5/+5 |
| | | | | | |||||
* | | | | | Merge branch 'master' of github.com:mesos/spark | Matei Zaharia | 2013-01-28 | 6 | -16/+47 |
|\ \ \ \ \ | |||||
| * \ \ \ \ | Merge pull request #413 from pwendell/stage-logging | Matei Zaharia | 2013-01-28 | 2 | -4/+19 |
| |\ \ \ \ \ | | | | | | | | | | | | | | | SPARK-658: Adding logging of stage duration | ||||
| | * | | | | | Units from ms -> s | Patrick Wendell | 2013-01-28 | 1 | -2/+2 |
| | | | | | | | |||||
| | * | | | | | Making submission time a field | Patrick Wendell | 2013-01-28 | 2 | -4/+6 |
| | | | | | | | |||||
| | * | | | | | Renaming stage finished function | Patrick Wendell | 2013-01-28 | 1 | -3/+3 |
| | | | | | | | |||||
| | * | | | | | SPARK-658: Adding logging of stage duration | Patrick Wendell | 2013-01-28 | 1 | -4/+17 |
| | | |/ / / | | |/| | | | |||||
| * | | | | | Merge pull request #424 from pwendell/logging-cleanup | Matei Zaharia | 2013-01-28 | 3 | -12/+12 |
| |\ \ \ \ \ | | | | | | | | | | | | | | | Some DEBUG-level log cleanup. | ||||
| | * | | | | | Some DEBUG-level log cleanup. | Patrick Wendell | 2013-01-28 | 3 | -12/+12 |
| | |/ / / / | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | A few changes to make the DEBUG-level logs less noisy and more readable. - Moved a few very frequent messages to Trace - Changed some BlockManger log messages to make them more understandable SPARK-666 #resolve | ||||
| * | | | | | Merge pull request #423 from squito/long_float_accums | Matei Zaharia | 2013-01-28 | 2 | -0/+16 |
| |\ \ \ \ \ | | |/ / / / | |/| | | | | add long and float accumulatorparams | ||||
| | * | | | | add long and float accumulatorparams | Imran Rashid | 2013-01-28 | 2 | -0/+16 |
| |/ / / / | |||||
* / / / / | Change time unit in MetadataCleaner to seconds | Matei Zaharia | 2013-01-28 | 1 | -3/+2 |
|/ / / / | |||||
* | | | | Clean up BlockManagerUI a little (make it not be an object, merge with | Matei Zaharia | 2013-01-27 | 7 | -74/+91 |
| | | | | | | | | | | | | | | | | Directives, and bind to a random port) | ||||
* | | | | Rename more things from slave to executor | Matei Zaharia | 2013-01-27 | 8 | -60/+50 |
| | | | | |||||
* | | | | Track workers by executor ID instead of hostname to allow multiple | Matei Zaharia | 2013-01-27 | 35 | -314/+343 |
| | | | | | | | | | | | | | | | | | | | | executors per machine and remove the need for multiple IP addresses in unit tests. | ||||
* | | | | Merge pull request #419 from shivaram/ec2-ip-change | Matei Zaharia | 2013-01-27 | 1 | -1/+2 |
|\ \ \ \ | | | | | | | | | | | Detect whether we run on EC2 using ec2-metadata as well | ||||
| * | | | | Detect whether we run on EC2 using ec2-metadata as well | Shivaram Venkataraman | 2013-01-26 | 1 | -1/+2 |
| | | | | | |||||
* | | | | | Merge pull request #401 from squito/blockmanager_ui | Matei Zaharia | 2013-01-27 | 17 | -8/+401 |
|\ \ \ \ \ | | | | | | | | | | | | | Blockmanager ui | ||||
| * | | | | | add metadatacleaner for persisentRdd map | Imran Rashid | 2013-01-25 | 1 | -1/+11 |
| | | | | | | |||||
| * | | | | | fixup 1cadaa1, changed api of map | Imran Rashid | 2013-01-25 | 1 | -2/+2 |
| | | | | | | |||||
| * | | | | | switch to TimeStampedHashMap for storing persistent Rdds | Imran Rashid | 2013-01-25 | 1 | -1/+2 |
| | | | | | | |||||
| * | | | | | code reformatting | Imran Rashid | 2013-01-25 | 2 | -5/+7 |
| | | | | | | |||||
| * | | | | | Merge branch 'master' into blockmanager_ui | Imran Rashid | 2013-01-22 | 159 | -469/+11630 |
| |\ \ \ \ \ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Conflicts: core/src/main/scala/spark/RDD.scala | ||||
| * | | | | | | Fix up some problems from the merge | Imran Rashid | 2013-01-22 | 3 | -4/+18 |
| | | | | | | |