Made the following traits/interfaces/classes non-public:
Made the following traits/interfaces/classes non-public:
SparkHadoopWriter
SparkHadoopMapRedUtil
SparkHadoopMapReduceUtil
SparkHadoopUtil
PythonAccumulatorParam
BlockManagerSlaveActor
Provide Instrumentation for Shuffle Write Performance
Shuffle write performance can have a major impact on the performance of jobs. This patch adds a few pieces of instrumentation related to shuffle writes. They are:
1. A listing of the time spent performing blocking writes for each task. This is implemented by keeping track of the aggregate delay seen by many individual writes.
2. An undocumented option `spark.shuffle.sync` which forces shuffle data to sync to disk. This is necessary for measuring shuffle performance in the absence of the OS buffer cache.
3. An internal utility which micro-benchmarks write throughput for simulated shuffle outputs.
I'm going to do some performance testing on this to see whether these small timing calls add overhead. From a feature perspective, however, I consider this complete. Any feedback is appreciated.
Don't setup the uncaught exception handler in local mode.
This avoids unit test failures for Spark streaming.
java.util.concurrent.RejectedExecutionException: Task org.apache.spark.streaming.JobManager$JobHandler@38cf728d rejected from java.util.concurrent.ThreadPoolExecutor@3b69a41e[Terminated, pool size = 0, active threads = 0, queued tasks = 0, completed tasks = 14]
at java.util.concurrent.ThreadPoolExecutor$AbortPolicy.rejectedExecution(ThreadPoolExecutor.java:2048)
at java.util.concurrent.ThreadPoolExecutor.reject(ThreadPoolExecutor.java:821)
at java.util.concurrent.ThreadPoolExecutor.execute(ThreadPoolExecutor.java:1372)
at org.apache.spark.streaming.JobManager.runJob(JobManager.scala:54)
at org.apache.spark.streaming.Scheduler$$anonfun$generateJobs$2.apply(Scheduler.scala:108)
at org.apache.spark.streaming.Scheduler$$anonfun$generateJobs$2.apply(Scheduler.scala:108)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:60)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
at org.apache.spark.streaming.Scheduler.generateJobs(Scheduler.scala:108)
at org.apache.spark.streaming.Scheduler$$anonfun$1.apply$mcVJ$sp(Scheduler.scala:41)
at org.apache.spark.streaming.util.RecurringTimer.org$apache$spark$streaming$util$RecurringTimer$$loop(RecurringTimer.scala:66)
at org.apache.spark.streaming.util.RecurringTimer$$anon$1.run(RecurringTimer.scala:34)
Code de-duplication in BlockManager
The BlockManager has a few methods that duplicate most of their code. This pull request extracts the duplicated code into private doPut(), doGetLocal(), and doGetRemote() methods that unify the storing/reading of bytes or objects.
I believe that I preserved the logic of the original code, but I'd appreciate some help in reviewing this.
Add an add() method to pyspark accumulators.
Add a regular method for adding a term to accumulators in
pyspark. Currently if you have a non-global accumulator, adding to it
is awkward. The += operator can't be used for non-global accumulators
captured via closure because it's involves an assignment. The only way
to do it is using __iadd__ directly.
Adding this method lets you write code like this:
def main():
sc = SparkContext()
accum = sc.accumulator(0)
rdd = sc.parallelize([1,2,3])
def f(x):
accum.add(x)
rdd.foreach(f)
print accum.value
where using accum += x instead would have caused UnboundLocalError
exceptions in workers. Currently it would have to be written as
accum.__iadd__(x).
Add a regular method for adding a term to accumulators in
pyspark. Currently if you have a non-global accumulator, adding to it
is awkward. The += operator can't be used for non-global accumulators
captured via closure because it's involves an assignment. The only way
to do it is using __iadd__ directly.
Adding this method lets you write code like this:
def main():
sc = SparkContext()
accum = sc.accumulator(0)
rdd = sc.parallelize([1,2,3])
def f(x):
accum.add(x)
rdd.foreach(f)
print accum.value
where using accum += x instead would have caused UnboundLocalError
exceptions in workers. Currently it would have to be written as
accum.__iadd__(x).
Job cancellation via job group id.
This PR adds a simple API to group together a set of jobs belonging to a thread and threads spawned from it. It also allows the cancellation of all jobs in this group.
An example:
sc.setJobDescription("this_is_the_group_id", "some job description")
sc.parallelize(1 to 10000, 2).map { i => Thread.sleep(10); i }.count()
In a separate thread:
sc.cancelJobGroup("this_is_the_group_id")
Add SBT target to assemble dependencies
This pull request is an attempt to address the long assembly build times during development. Instead of rebuilding the assembly jar for every Spark change, this pull request adds a new SBT target `spark` that packages all the Spark modules and builds an assembly of the dependencies.
So the work flow that should work now would be something like
```
./sbt/sbt spark # Doing this once should suffice
## Make changes
./sbt/sbt compile
./sbt/sbt test or ./spark-shell
```
Faster and stable/reliable broadcast
HttpBroadcast is noticeably slow, but the alternatives (TreeBroadcast or BitTorrentBroadcast) are notoriously unreliable. The main problem with them is they try to manage the memory for the pieces of a broadcast themselves. Right now, the BroadcastManager does not know which machines the tasks reading from a broadcast variable is running and when they have finished. Consequently, we try to guess and often guess wrong, which blows up the memory usage and kills/hangs jobs.
This very simple implementation solves the problem by not trying to manage the intermediate pieces; instead, it offloads that duty to the BlockManager which is quite good at juggling blocks. Otherwise, it is very similar to the BitTorrentBroadcast implementation (without fancy optimizations). And it runs much faster than HttpBroadcast we have right now.
I've been using this for another project for last couple of weeks, and just today did some benchmarking against the Http one. The following shows the improvements for increasing broadcast size for cold runs. Each line represent the number of receivers.
After the first broadcast is over, i.e., after JVM is wormed up and for HttpBroadcast the server is already running (I think), the following are the improvements for warm runs.
The curves are not as nice as the cold runs, but the improvements are obvious, specially for larger broadcasts and more receivers.
Depending on how it goes, we should deprecate and/or remove old TreeBroadcast and BitTorrentBroadcast implementations, and hopefully, SPARK-889 will not be necessary any more.
Spark shell exits if it cannot create SparkContext
Mainly, this occurs if you provide a messed up MASTER url (one that doesn't match one
of our regexes). Previously, we would default to Mesos, fail, and then start the shell
anyway, except that any Spark command would fail. Simply exiting seems clearer.
Mainly, this occurs if you provide a messed up MASTER url (one that doesn't match one
of our regexes). Previously, we would default to Mesos, fail, and then start the shell
anyway, except that any Spark command would fail.
Fix for issue SPARK-627. Implementing --config argument in the scripts.
This code fix is for issue SPARK-627. I added code to consider --config arguments in the scripts. In case the <conf-dir> is not a directory the scripts exit. I removed the --hosts argument. It can be achieved by giving a different config directory. Let me know if an explicit --hosts argument is required.
Removed TaskSchedulerListener interface.
The interface was used only by the DAG scheduler (so it wasn't necessary
to define the additional interface), and the naming makes it very
confusing when reading the code (because "listener" was used
to describe the DAG scheduler, rather than SparkListeners, which
implement a nearly-identical interface but serve a different
function).
@mateiz - is there a reason for this interface that I'm missing?
