spark git commit: [SPARK-6636] Use public DNS hostname everywhere in spark_ec2.py
Repository: spark Updated Branches: refs/heads/branch-1.3 1cde04f21 - ab1b8edb8 [SPARK-6636] Use public DNS hostname everywhere in spark_ec2.py The spark_ec2.py script uses public_dns_name everywhere in the script except for testing ssh availability, which is done using the public ip address of the instances. This breaks the script for users who are deploying the cluster with a private-network-only security group. The fix is to use public_dns_name in the remaining place. Author: Matt Aasted aas...@twitch.tv Closes #5302 from aasted/master and squashes the following commits: 60cf6ee [Matt Aasted] [SPARK-6636] Use public DNS hostname everywhere in spark_ec2.py (cherry picked from commit 6f0d55d76f758d217fd18ffa0ccf273d7ab0377b) Signed-off-by: Josh Rosen joshro...@databricks.com Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/ab1b8edb Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/ab1b8edb Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/ab1b8edb Branch: refs/heads/branch-1.3 Commit: ab1b8edb81feb2ad5cd28611f809c57cb61db9fb Parents: 1cde04f Author: Matt Aasted aas...@twitch.tv Authored: Mon Apr 6 23:50:48 2015 -0700 Committer: Josh Rosen joshro...@databricks.com Committed: Mon Apr 6 23:52:46 2015 -0700 -- ec2/spark_ec2.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) -- http://git-wip-us.apache.org/repos/asf/spark/blob/ab1b8edb/ec2/spark_ec2.py -- diff --git a/ec2/spark_ec2.py b/ec2/spark_ec2.py index 95082b5..e121dad 100755 --- a/ec2/spark_ec2.py +++ b/ec2/spark_ec2.py @@ -715,7 +715,7 @@ def is_cluster_ssh_available(cluster_instances, opts): Check if SSH is available on all the instances in a cluster. for i in cluster_instances: -if not is_ssh_available(host=i.ip_address, opts=opts): +if not is_ssh_available(host=i.public_dns_name, opts=opts): return False else: return True - To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org For additional commands, e-mail: commits-h...@spark.apache.org
spark git commit: [SPARK-6636] Use public DNS hostname everywhere in spark_ec2.py
Repository: spark Updated Branches: refs/heads/master a0846c4b6 - 6f0d55d76 [SPARK-6636] Use public DNS hostname everywhere in spark_ec2.py The spark_ec2.py script uses public_dns_name everywhere in the script except for testing ssh availability, which is done using the public ip address of the instances. This breaks the script for users who are deploying the cluster with a private-network-only security group. The fix is to use public_dns_name in the remaining place. Author: Matt Aasted aas...@twitch.tv Closes #5302 from aasted/master and squashes the following commits: 60cf6ee [Matt Aasted] [SPARK-6636] Use public DNS hostname everywhere in spark_ec2.py Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/6f0d55d7 Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/6f0d55d7 Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/6f0d55d7 Branch: refs/heads/master Commit: 6f0d55d76f758d217fd18ffa0ccf273d7ab0377b Parents: a0846c4 Author: Matt Aasted aas...@twitch.tv Authored: Mon Apr 6 23:50:48 2015 -0700 Committer: Josh Rosen joshro...@databricks.com Committed: Mon Apr 6 23:51:47 2015 -0700 -- ec2/spark_ec2.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) -- http://git-wip-us.apache.org/repos/asf/spark/blob/6f0d55d7/ec2/spark_ec2.py -- diff --git a/ec2/spark_ec2.py b/ec2/spark_ec2.py index 5507a9c..879a52c 100755 --- a/ec2/spark_ec2.py +++ b/ec2/spark_ec2.py @@ -809,7 +809,7 @@ def is_cluster_ssh_available(cluster_instances, opts): Check if SSH is available on all the instances in a cluster. for i in cluster_instances: -if not is_ssh_available(host=i.ip_address, opts=opts): +if not is_ssh_available(host=i.public_dns_name, opts=opts): return False else: return True - To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org For additional commands, e-mail: commits-h...@spark.apache.org
spark git commit: [SPARK-6716] Change SparkContext.DRIVER_IDENTIFIER from driver to driver
Repository: spark Updated Branches: refs/heads/master e40ea8742 - a0846c4b6 [SPARK-6716] Change SparkContext.DRIVER_IDENTIFIER from driver to driver Currently, the driver's executorId is set to `driver`. This choice of ID was present in older Spark versions, but it has started to cause problems now that executorIds are used in more contexts, such as Ganglia metric names or driver thread-dump links the web UI. The angle brackets must be escaped when embedding this ID in XML or as part of URLs and this has led to multiple problems: - https://issues.apache.org/jira/browse/SPARK-6484 - https://issues.apache.org/jira/browse/SPARK-4313 The simplest solution seems to be to change this id to something that does not contain any special characters, such as `driver`. I'm not sure whether we can perform this change in a patch release, since this ID may be considered a stable API by metrics users, but it's probably okay to do this in a major release as long as we document it in the release notes. Author: Josh Rosen joshro...@databricks.com Closes #5372 from JoshRosen/driver-id-fix and squashes the following commits: 42d3c10 [Josh Rosen] Clarify comment 0c5d04b [Josh Rosen] Add backwards-compatibility in BlockManagerId.isDriver 7ff12e0 [Josh Rosen] Change SparkContext.DRIVER_IDENTIFIER from driver to driver Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/a0846c4b Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/a0846c4b Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/a0846c4b Branch: refs/heads/master Commit: a0846c4b635eac8d8637c83d490177f881952d27 Parents: e40ea87 Author: Josh Rosen joshro...@databricks.com Authored: Mon Apr 6 23:33:16 2015 -0700 Committer: Josh Rosen joshro...@databricks.com Committed: Mon Apr 6 23:33:16 2015 -0700 -- core/src/main/scala/org/apache/spark/SparkContext.scala | 12 +++- .../scala/org/apache/spark/storage/BlockManagerId.scala | 5 - .../org/apache/spark/storage/BlockManagerSuite.scala| 6 ++ 3 files changed, 21 insertions(+), 2 deletions(-) -- http://git-wip-us.apache.org/repos/asf/spark/blob/a0846c4b/core/src/main/scala/org/apache/spark/SparkContext.scala -- diff --git a/core/src/main/scala/org/apache/spark/SparkContext.scala b/core/src/main/scala/org/apache/spark/SparkContext.scala index 942c597..3f1a7dd 100644 --- a/core/src/main/scala/org/apache/spark/SparkContext.scala +++ b/core/src/main/scala/org/apache/spark/SparkContext.scala @@ -1901,7 +1901,17 @@ object SparkContext extends Logging { private[spark] val SPARK_JOB_INTERRUPT_ON_CANCEL = spark.job.interruptOnCancel - private[spark] val DRIVER_IDENTIFIER = driver + /** + * Executor id for the driver. In earlier versions of Spark, this was `driver`, but this was + * changed to `driver` because the angle brackets caused escaping issues in URLs and XML (see + * SPARK-6716 for more details). + */ + private[spark] val DRIVER_IDENTIFIER = driver + + /** + * Legacy version of DRIVER_IDENTIFIER, retained for backwards-compatibility. + */ + private[spark] val LEGACY_DRIVER_IDENTIFIER = driver // The following deprecated objects have already been copied to `object AccumulatorParam` to // make the compiler find them automatically. They are duplicate codes only for backward http://git-wip-us.apache.org/repos/asf/spark/blob/a0846c4b/core/src/main/scala/org/apache/spark/storage/BlockManagerId.scala -- diff --git a/core/src/main/scala/org/apache/spark/storage/BlockManagerId.scala b/core/src/main/scala/org/apache/spark/storage/BlockManagerId.scala index a6f1ebf..69ac375 100644 --- a/core/src/main/scala/org/apache/spark/storage/BlockManagerId.scala +++ b/core/src/main/scala/org/apache/spark/storage/BlockManagerId.scala @@ -60,7 +60,10 @@ class BlockManagerId private ( def port: Int = port_ - def isDriver: Boolean = { executorId == SparkContext.DRIVER_IDENTIFIER } + def isDriver: Boolean = { +executorId == SparkContext.DRIVER_IDENTIFIER || + executorId == SparkContext.LEGACY_DRIVER_IDENTIFIER + } override def writeExternal(out: ObjectOutput): Unit = Utils.tryOrIOException { out.writeUTF(executorId_) http://git-wip-us.apache.org/repos/asf/spark/blob/a0846c4b/core/src/test/scala/org/apache/spark/storage/BlockManagerSuite.scala -- diff --git a/core/src/test/scala/org/apache/spark/storage/BlockManagerSuite.scala b/core/src/test/scala/org/apache/spark/storage/BlockManagerSuite.scala index 283090e..6dc5bc4 100644 --- a/core/src/test/scala/org/apache/spark/storage/BlockManagerSuite.scala +++
spark git commit: [SPARK-6736][GraphX][Doc]Example of Graph#aggregateMessages has error
Repository: spark Updated Branches: refs/heads/master 6f0d55d76 - ae980eb41 [SPARK-6736][GraphX][Doc]Example of Graph#aggregateMessages has error Example of Graph#aggregateMessages has error. Since aggregateMessages is a method of Graph, It should be written rawGraph.aggregateMessages Author: Sasaki Toru sasaki...@nttdata.co.jp Closes #5388 from sasakitoa/aggregateMessagesExample and squashes the following commits: b1d631b [Sasaki Toru] Example of Graph#aggregateMessages has error Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/ae980eb4 Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/ae980eb4 Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/ae980eb4 Branch: refs/heads/master Commit: ae980eb41c00b5f1f64c650f267b884e864693f0 Parents: 6f0d55d Author: Sasaki Toru sasaki...@nttdata.co.jp Authored: Tue Apr 7 01:55:32 2015 -0700 Committer: Ankur Dave ankurd...@gmail.com Committed: Tue Apr 7 01:55:32 2015 -0700 -- graphx/src/main/scala/org/apache/spark/graphx/Graph.scala | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) -- http://git-wip-us.apache.org/repos/asf/spark/blob/ae980eb4/graphx/src/main/scala/org/apache/spark/graphx/Graph.scala -- diff --git a/graphx/src/main/scala/org/apache/spark/graphx/Graph.scala b/graphx/src/main/scala/org/apache/spark/graphx/Graph.scala index 8494d06..36dc7b0 100644 --- a/graphx/src/main/scala/org/apache/spark/graphx/Graph.scala +++ b/graphx/src/main/scala/org/apache/spark/graphx/Graph.scala @@ -409,7 +409,7 @@ abstract class Graph[VD: ClassTag, ED: ClassTag] protected () extends Serializab * {{{ * val rawGraph: Graph[_, _] = Graph.textFile(twittergraph) * val inDeg: RDD[(VertexId, Int)] = - * aggregateMessages[Int](ctx = ctx.sendToDst(1), _ + _) + * rawGraph.aggregateMessages[Int](ctx = ctx.sendToDst(1), _ + _) * }}} * * @note By expressing computation at the edge level we achieve - To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org For additional commands, e-mail: commits-h...@spark.apache.org
spark git commit: [SPARK-3591][YARN]fire and forget for YARN cluster mode
Repository: spark Updated Branches: refs/heads/master ae980eb41 - b65bad65c [SPARK-3591][YARN]fire and forget for YARN cluster mode https://issues.apache.org/jira/browse/SPARK-3591 The output after this patch: doggie153:/opt/oss/spark-1.3.0-bin-hadoop2.4/bin # ./spark-submit --class org.apache.spark.examples.SparkPi --master yarn-cluster ../lib/spark-examples*.jar 15/03/31 21:15:25 WARN NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable 15/03/31 21:15:25 INFO RMProxy: Connecting to ResourceManager at doggie153/10.177.112.153:8032 15/03/31 21:15:25 INFO Client: Requesting a new application from cluster with 4 NodeManagers 15/03/31 21:15:25 INFO Client: Verifying our application has not requested more than the maximum memory capability of the cluster (8192 MB per container) 15/03/31 21:15:25 INFO Client: Will allocate AM container, with 896 MB memory including 384 MB overhead 15/03/31 21:15:25 INFO Client: Setting up container launch context for our AM 15/03/31 21:15:25 INFO Client: Preparing resources for our AM container 15/03/31 21:15:26 INFO Client: Uploading resource file:/opt/oss/spark-1.3.0-bin-hadoop2.4/lib/spark-assembly-1.4.0-SNAPSHOT-hadoop2.4.1.jar - hdfs://doggie153:9000/user/root/.sparkStaging/application_1427257505534_0016/spark-assembly-1.4.0-SNAPSHOT-hadoop2.4.1.jar 15/03/31 21:15:27 INFO Client: Uploading resource file:/opt/oss/spark-1.3.0-bin-hadoop2.4/lib/spark-examples-1.3.0-hadoop2.4.0.jar - hdfs://doggie153:9000/user/root/.sparkStaging/application_1427257505534_0016/spark-examples-1.3.0-hadoop2.4.0.jar 15/03/31 21:15:28 INFO Client: Setting up the launch environment for our AM container 15/03/31 21:15:28 INFO SecurityManager: Changing view acls to: root 15/03/31 21:15:28 INFO SecurityManager: Changing modify acls to: root 15/03/31 21:15:28 INFO SecurityManager: SecurityManager: authentication disabled; ui acls disabled; users with view permissions: Set(root); users with modify permissions: Set(root) 15/03/31 21:15:28 INFO Client: Submitting application 16 to ResourceManager 15/03/31 21:15:28 INFO YarnClientImpl: Submitted application application_1427257505534_0016 15/03/31 21:15:28 INFO Client: ... waiting before polling ResourceManager for application state 15/03/31 21:15:33 INFO Client: ... polling ResourceManager for application state 15/03/31 21:15:33 INFO Client: Application report for application_1427257505534_0016 (state: RUNNING) 15/03/31 21:15:33 INFO Client: client token: N/A diagnostics: N/A ApplicationMaster host: doggie157 ApplicationMaster RPC port: 0 queue: default start time: 1427807728307 final status: UNDEFINED tracking URL: http://doggie153:8088/proxy/application_1427257505534_0016/ user: root /cc andrewor14 Author: WangTaoTheTonic wangtao...@huawei.com Closes #5297 from WangTaoTheTonic/SPARK-3591 and squashes the following commits: c76d232 [WangTaoTheTonic] wrap lines 16c90a8 [WangTaoTheTonic] move up lines to avoid duplicate fea390d [WangTaoTheTonic] log failed/killed report, style and comment be1cc2e [WangTaoTheTonic] reword f0bc54f [WangTaoTheTonic] minor: expose appid in excepiton messages ba9b22b [WangTaoTheTonic] wrong config name e1a4013 [WangTaoTheTonic] revert to the old version and do some robust 19706c0 [WangTaoTheTonic] add a config to control whether to forget 0cbdce8 [WangTaoTheTonic] fire and forget for YARN cluster mode Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/b65bad65 Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/b65bad65 Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/b65bad65 Branch: refs/heads/master Commit: b65bad65c3500475b974ca0219f218eef296db2c Parents: ae980eb Author: WangTaoTheTonic wangtao...@huawei.com Authored: Tue Apr 7 08:36:25 2015 -0500 Committer: Thomas Graves tgra...@apache.org Committed: Tue Apr 7 08:36:25 2015 -0500 -- .../scala/org/apache/spark/deploy/Client.scala | 2 +- .../deploy/rest/StandaloneRestClient.scala | 2 +- docs/running-on-yarn.md | 9 +++ .../org/apache/spark/deploy/yarn/Client.scala | 83 4 files changed, 61 insertions(+), 35 deletions(-) -- http://git-wip-us.apache.org/repos/asf/spark/blob/b65bad65/core/src/main/scala/org/apache/spark/deploy/Client.scala -- diff --git a/core/src/main/scala/org/apache/spark/deploy/Client.scala b/core/src/main/scala/org/apache/spark/deploy/Client.scala index 65238af..8d13b2a 100644 --- a/core/src/main/scala/org/apache/spark/deploy/Client.scala +++ b/core/src/main/scala/org/apache/spark/deploy/Client.scala @@ -89,7 +89,7 @@ private class
spark git commit: Replace use of .size with .length for Arrays
Repository: spark Updated Branches: refs/heads/master 7162ecf88 - 2c32bef17 Replace use of .size with .length for Arrays Invoking .size on arrays is valid, but requires an implicit conversion to SeqLike. This incurs a compile time overhead and more importantly a runtime overhead, as the Array must be wrapped before the method can be invoked. For example, the difference in generated byte code is: public int withSize(); Code: 0: getstatic #23 // Field scala/Predef$.MODULE$:Lscala/Predef$; 3: aload_0 4: invokevirtual #25 // Method array:()[I 7: invokevirtual #29 // Method scala/Predef$.intArrayOps:([I)Lscala/collection/mutable/ArrayOps; 10: invokeinterface #34, 1 // InterfaceMethod scala/collection/mutable/ArrayOps.size:()I 15: ireturn public int withLength(); Code: 0: aload_0 1: invokevirtual #25 // Method array:()[I 4: arraylength 5: ireturn Author: sksamuel s...@sksamuel.com Closes #5376 from sksamuel/master and squashes the following commits: 77ec261 [sksamuel] Replace use of .size with .length for Arrays. Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/2c32bef1 Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/2c32bef1 Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/2c32bef1 Branch: refs/heads/master Commit: 2c32bef1790dac6f77ef9674f6106c2e24ea0338 Parents: 7162ecf Author: sksamuel s...@sksamuel.com Authored: Tue Apr 7 10:43:22 2015 -0700 Committer: Reynold Xin r...@databricks.com Committed: Tue Apr 7 10:43:22 2015 -0700 -- .../apache/spark/network/nio/Connection.scala | 2 +- .../org/apache/spark/rdd/AsyncRDDActions.scala | 10 - .../scala/org/apache/spark/rdd/BlockRDD.scala | 2 +- .../org/apache/spark/rdd/CartesianRDD.scala | 4 ++-- .../org/apache/spark/rdd/CheckpointRDD.scala| 2 +- .../org/apache/spark/rdd/CoGroupedRDD.scala | 4 ++-- .../org/apache/spark/rdd/CoalescedRDD.scala | 2 +- .../apache/spark/rdd/DoubleRDDFunctions.scala | 4 ++-- .../apache/spark/rdd/OrderedRDDFunctions.scala | 2 +- .../org/apache/spark/rdd/PairRDDFunctions.scala | 2 +- .../main/scala/org/apache/spark/rdd/RDD.scala | 22 ++-- .../apache/spark/rdd/RDDCheckpointData.scala| 6 +++--- .../org/apache/spark/rdd/SubtractedRDD.scala| 2 +- .../scala/org/apache/spark/rdd/UnionRDD.scala | 6 +++--- .../apache/spark/rdd/ZippedPartitionsRDD.scala | 4 ++-- .../apache/spark/rdd/ZippedWithIndexRDD.scala | 2 +- .../org/apache/spark/storage/RDDInfo.scala | 2 +- .../apache/spark/ui/ConsoleProgressBar.scala| 4 ++-- .../apache/spark/util/collection/BitSet.scala | 2 +- 19 files changed, 42 insertions(+), 42 deletions(-) -- http://git-wip-us.apache.org/repos/asf/spark/blob/2c32bef1/core/src/main/scala/org/apache/spark/network/nio/Connection.scala -- diff --git a/core/src/main/scala/org/apache/spark/network/nio/Connection.scala b/core/src/main/scala/org/apache/spark/network/nio/Connection.scala index 04eb2bf..6b898bd 100644 --- a/core/src/main/scala/org/apache/spark/network/nio/Connection.scala +++ b/core/src/main/scala/org/apache/spark/network/nio/Connection.scala @@ -181,7 +181,7 @@ abstract class Connection(val channel: SocketChannel, val selector: Selector, buffer.get(bytes) bytes.foreach(x = print(x + )) buffer.position(curPosition) -print( ( + bytes.size + )) +print( ( + bytes.length + )) } def printBuffer(buffer: ByteBuffer, position: Int, length: Int) { http://git-wip-us.apache.org/repos/asf/spark/blob/2c32bef1/core/src/main/scala/org/apache/spark/rdd/AsyncRDDActions.scala -- diff --git a/core/src/main/scala/org/apache/spark/rdd/AsyncRDDActions.scala b/core/src/main/scala/org/apache/spark/rdd/AsyncRDDActions.scala index 646df28..3406a7e 100644 --- a/core/src/main/scala/org/apache/spark/rdd/AsyncRDDActions.scala +++ b/core/src/main/scala/org/apache/spark/rdd/AsyncRDDActions.scala @@ -45,7 +45,7 @@ class AsyncRDDActions[T: ClassTag](self: RDD[T]) extends Serializable with Loggi } result }, - Range(0, self.partitions.size), + Range(0, self.partitions.length), (index: Int, data: Long) = totalCount.addAndGet(data), totalCount.get()) } @@ -54,8 +54,8 @@ class AsyncRDDActions[T: ClassTag](self: RDD[T]) extends Serializable with Loggi * Returns a future for retrieving all elements of this RDD. */ def collectAsync(): FutureAction[Seq[T]] = { -val results = new Array[Array[T]](self.partitions.size) -
spark git commit: [SPARK-6733][ Scheduler]Added scala.language.existentials
Repository: spark Updated Branches: refs/heads/master b65bad65c - 7162ecf88 [SPARK-6733][ Scheduler]Added scala.language.existentials Author: Vinod K C vinod...@huawei.com Closes #5384 from vinodkc/Suppression_Scala_existential_code and squashes the following commits: 82a3a1f [Vinod K C] Added scala.language.existentials Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/7162ecf8 Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/7162ecf8 Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/7162ecf8 Branch: refs/heads/master Commit: 7162ecf88624615c78a332de482f5defd297e415 Parents: b65bad6 Author: Vinod K C vinod...@huawei.com Authored: Tue Apr 7 10:42:08 2015 -0700 Committer: Reynold Xin r...@databricks.com Committed: Tue Apr 7 10:42:08 2015 -0700 -- core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala | 1 + .../test/scala/org/apache/spark/ml/recommendation/ALSSuite.scala| 1 + 2 files changed, 2 insertions(+) -- http://git-wip-us.apache.org/repos/asf/spark/blob/7162ecf8/core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala -- diff --git a/core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala b/core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala index 917cce1..c82ae4b 100644 --- a/core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala +++ b/core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala @@ -24,6 +24,7 @@ import java.util.concurrent.atomic.AtomicInteger import scala.collection.mutable.{ArrayBuffer, HashMap, HashSet, Map, Stack} import scala.concurrent.duration._ +import scala.language.existentials import scala.language.postfixOps import scala.util.control.NonFatal http://git-wip-us.apache.org/repos/asf/spark/blob/7162ecf8/mllib/src/test/scala/org/apache/spark/ml/recommendation/ALSSuite.scala -- diff --git a/mllib/src/test/scala/org/apache/spark/ml/recommendation/ALSSuite.scala b/mllib/src/test/scala/org/apache/spark/ml/recommendation/ALSSuite.scala index 29d4ec5..fc73493 100644 --- a/mllib/src/test/scala/org/apache/spark/ml/recommendation/ALSSuite.scala +++ b/mllib/src/test/scala/org/apache/spark/ml/recommendation/ALSSuite.scala @@ -22,6 +22,7 @@ import java.util.Random import scala.collection.mutable import scala.collection.mutable.ArrayBuffer +import scala.language.existentials import com.github.fommil.netlib.BLAS.{getInstance = blas} import org.scalatest.FunSuite - To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org For additional commands, e-mail: commits-h...@spark.apache.org
spark git commit: [SPARK-6750] Upgrade ScalaStyle to 0.7.
Repository: spark Updated Branches: refs/heads/master 2c32bef17 - 123221591 [SPARK-6750] Upgrade ScalaStyle to 0.7. 0.7 fixes a bug that's pretty useful, i.e. inline functions no longer return explicit type definition. Author: Reynold Xin r...@databricks.com Closes #5399 from rxin/style0.7 and squashes the following commits: 54c41b2 [Reynold Xin] Actually update the version. 09c759c [Reynold Xin] [SPARK-6750] Upgrade ScalaStyle to 0.7. Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/12322159 Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/12322159 Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/12322159 Branch: refs/heads/master Commit: 12322159147581602978f7f5a6b33b887ef781a1 Parents: 2c32bef Author: Reynold Xin r...@databricks.com Authored: Tue Apr 7 12:37:33 2015 -0700 Committer: Reynold Xin r...@databricks.com Committed: Tue Apr 7 12:37:33 2015 -0700 -- project/plugins.sbt | 2 +- project/project/SparkPluginBuild.scala | 16 +--- .../scalastyle/NonASCIICharacterChecker.scala | 39 3 files changed, 2 insertions(+), 55 deletions(-) -- http://git-wip-us.apache.org/repos/asf/spark/blob/12322159/project/plugins.sbt -- diff --git a/project/plugins.sbt b/project/plugins.sbt index ee45b6a..7096b0d 100644 --- a/project/plugins.sbt +++ b/project/plugins.sbt @@ -19,7 +19,7 @@ addSbtPlugin(com.github.mpeltonen % sbt-idea % 1.6.0) addSbtPlugin(net.virtual-void % sbt-dependency-graph % 0.7.4) -addSbtPlugin(org.scalastyle %% scalastyle-sbt-plugin % 0.6.0) +addSbtPlugin(org.scalastyle %% scalastyle-sbt-plugin % 0.7.0) addSbtPlugin(com.typesafe % sbt-mima-plugin % 0.1.6) http://git-wip-us.apache.org/repos/asf/spark/blob/12322159/project/project/SparkPluginBuild.scala -- diff --git a/project/project/SparkPluginBuild.scala b/project/project/SparkPluginBuild.scala index 8863f27..471d00b 100644 --- a/project/project/SparkPluginBuild.scala +++ b/project/project/SparkPluginBuild.scala @@ -24,20 +24,6 @@ import sbt.Keys._ * becomes available for scalastyle sbt plugin. */ object SparkPluginDef extends Build { - lazy val root = Project(plugins, file(.)) dependsOn(sparkStyle, sbtPomReader) - lazy val sparkStyle = Project(spark-style, file(spark-style), settings = styleSettings) + lazy val root = Project(plugins, file(.)) dependsOn(sbtPomReader) lazy val sbtPomReader = uri(https://github.com/ScrapCodes/sbt-pom-reader.git#ignore_artifact_id;) - - // There is actually no need to publish this artifact. - def styleSettings = Defaults.defaultSettings ++ Seq ( -name := spark-style, -organization := org.apache.spark, -scalaVersion := 2.10.4, -scalacOptions:= Seq(-unchecked, -deprecation), -libraryDependencies ++= Dependencies.scalaStyle - ) - - object Dependencies { -val scalaStyle = Seq(org.scalastyle %% scalastyle % 0.4.0) - } } http://git-wip-us.apache.org/repos/asf/spark/blob/12322159/project/spark-style/src/main/scala/org/apache/spark/scalastyle/NonASCIICharacterChecker.scala -- diff --git a/project/spark-style/src/main/scala/org/apache/spark/scalastyle/NonASCIICharacterChecker.scala b/project/spark-style/src/main/scala/org/apache/spark/scalastyle/NonASCIICharacterChecker.scala deleted file mode 100644 index 3d43c35..000 --- a/project/spark-style/src/main/scala/org/apache/spark/scalastyle/NonASCIICharacterChecker.scala +++ /dev/null @@ -1,39 +0,0 @@ -/* - * Licensed to the Apache Software Foundation (ASF) under one or more - * contributor license agreements. See the NOTICE file distributed with - * this work for additional information regarding copyright ownership. - * The ASF licenses this file to You under the Apache License, Version 2.0 - * (the License); you may not use this file except in compliance with - * the License. You may obtain a copy of the License at - * - *http://www.apache.org/licenses/LICENSE-2.0 - * - * Unless required by applicable law or agreed to in writing, software - * distributed under the License is distributed on an AS IS BASIS, - * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. - * See the License for the specific language governing permissions and - * limitations under the License. - */ - - -package org.apache.spark.scalastyle - -import java.util.regex.Pattern - -import org.scalastyle.{PositionError, ScalariformChecker, ScalastyleError} - -import scalariform.lexer.Token -import scalariform.parser.CompilationUnit - -class NonASCIICharacterChecker extends
spark git commit: [SPARK-6568] spark-shell.cmd --jars option does not accept the jar that has space in its path
Repository: spark Updated Branches: refs/heads/master 123221591 - 596ba77c5 [SPARK-6568] spark-shell.cmd --jars option does not accept the jar that has space in its path escape spaces in the arguments. Author: Masayoshi TSUZUKI tsudu...@oss.nttdata.co.jp Closes #5347 from tsudukim/feature/SPARK-6568 and squashes the following commits: 9180aaf [Masayoshi TSUZUKI] [SPARK-6568] spark-shell.cmd --jars option does not accept the jar that has space in its path Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/596ba77c Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/596ba77c Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/596ba77c Branch: refs/heads/master Commit: 596ba77c5fdca79486396989e549632153055caf Parents: 1232215 Author: Masayoshi TSUZUKI tsudu...@oss.nttdata.co.jp Authored: Tue Apr 7 14:29:53 2015 -0700 Committer: Xiangrui Meng m...@databricks.com Committed: Tue Apr 7 14:29:53 2015 -0700 -- core/src/main/scala/org/apache/spark/util/Utils.scala | 2 +- core/src/test/scala/org/apache/spark/util/UtilsSuite.scala | 6 -- 2 files changed, 5 insertions(+), 3 deletions(-) -- http://git-wip-us.apache.org/repos/asf/spark/blob/596ba77c/core/src/main/scala/org/apache/spark/util/Utils.scala -- diff --git a/core/src/main/scala/org/apache/spark/util/Utils.scala b/core/src/main/scala/org/apache/spark/util/Utils.scala index 0fdfaf3..25ae6ee 100644 --- a/core/src/main/scala/org/apache/spark/util/Utils.scala +++ b/core/src/main/scala/org/apache/spark/util/Utils.scala @@ -1661,7 +1661,7 @@ private[spark] object Utils extends Logging { /** * Format a Windows path such that it can be safely passed to a URI. */ - def formatWindowsPath(path: String): String = path.replace(\\, /) + def formatWindowsPath(path: String): String = path.replace(\\, /).replace( , %20) /** * Indicates whether Spark is currently running unit tests. http://git-wip-us.apache.org/repos/asf/spark/blob/596ba77c/core/src/test/scala/org/apache/spark/util/UtilsSuite.scala -- diff --git a/core/src/test/scala/org/apache/spark/util/UtilsSuite.scala b/core/src/test/scala/org/apache/spark/util/UtilsSuite.scala index 5d93086..b7cc840 100644 --- a/core/src/test/scala/org/apache/spark/util/UtilsSuite.scala +++ b/core/src/test/scala/org/apache/spark/util/UtilsSuite.scala @@ -241,6 +241,7 @@ class UtilsSuite extends FunSuite with ResetSystemProperties { assertResolves(C:/path/to/file.txt, file:/C:/path/to/file.txt, testWindows = true) assertResolves(C:\\path\\to\\file.txt, file:/C:/path/to/file.txt, testWindows = true) assertResolves(file:/C:/path/to/file.txt, file:/C:/path/to/file.txt, testWindows = true) +assertResolves(file:/C:/path to/file.txt, file:/C:/path%20to/file.txt, testWindows = true) assertResolves(file:///C:/path/to/file.txt, file:/C:/path/to/file.txt, testWindows = true) assertResolves(file:/C:/file.txt#alias.txt, file:/C:/file.txt#alias.txt, testWindows = true) intercept[IllegalArgumentException] { Utils.resolveURI(file:foo) } @@ -264,8 +265,9 @@ class UtilsSuite extends FunSuite with ResetSystemProperties { assertResolves(hdfs:/jar1,file:/jar2,jar3, shdfs:/jar1,file:/jar2,file:$cwd/jar3) assertResolves(hdfs:/jar1,file:/jar2,jar3,jar4#jar5, shdfs:/jar1,file:/jar2,file:$cwd/jar3,file:$cwd/jar4#jar5) -assertResolves(hdfs:/jar1,file:/jar2,jar3,C:\\pi.py#py.pi, - shdfs:/jar1,file:/jar2,file:$cwd/jar3,file:/C:/pi.py#py.pi, testWindows = true) +assertResolves(hdfs:/jar1,file:/jar2,jar3,C:\pi.py#py.pi,C:\path to\jar4.jar, + shdfs:/jar1,file:/jar2,file:$cwd/jar3,file:/C:/pi.py#py.pi,file:/C:/path%20to/jar4.jar, + testWindows = true) } test(nonLocalPaths) { - To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org For additional commands, e-mail: commits-h...@spark.apache.org
spark git commit: Revert [SPARK-6568] spark-shell.cmd --jars option does not accept the jar that has space in its path
Repository: spark Updated Branches: refs/heads/master 596ba77c5 - e6f08fb42 Revert [SPARK-6568] spark-shell.cmd --jars option does not accept the jar that has space in its path This reverts commit 596ba77c5fdca79486396989e549632153055caf. Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/e6f08fb4 Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/e6f08fb4 Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/e6f08fb4 Branch: refs/heads/master Commit: e6f08fb42fda35952ea8b005170750ae551dc7d9 Parents: 596ba77 Author: Xiangrui Meng m...@databricks.com Authored: Tue Apr 7 14:34:15 2015 -0700 Committer: Xiangrui Meng m...@databricks.com Committed: Tue Apr 7 14:34:15 2015 -0700 -- core/src/main/scala/org/apache/spark/util/Utils.scala | 2 +- core/src/test/scala/org/apache/spark/util/UtilsSuite.scala | 6 ++ 2 files changed, 3 insertions(+), 5 deletions(-) -- http://git-wip-us.apache.org/repos/asf/spark/blob/e6f08fb4/core/src/main/scala/org/apache/spark/util/Utils.scala -- diff --git a/core/src/main/scala/org/apache/spark/util/Utils.scala b/core/src/main/scala/org/apache/spark/util/Utils.scala index 25ae6ee..0fdfaf3 100644 --- a/core/src/main/scala/org/apache/spark/util/Utils.scala +++ b/core/src/main/scala/org/apache/spark/util/Utils.scala @@ -1661,7 +1661,7 @@ private[spark] object Utils extends Logging { /** * Format a Windows path such that it can be safely passed to a URI. */ - def formatWindowsPath(path: String): String = path.replace(\\, /).replace( , %20) + def formatWindowsPath(path: String): String = path.replace(\\, /) /** * Indicates whether Spark is currently running unit tests. http://git-wip-us.apache.org/repos/asf/spark/blob/e6f08fb4/core/src/test/scala/org/apache/spark/util/UtilsSuite.scala -- diff --git a/core/src/test/scala/org/apache/spark/util/UtilsSuite.scala b/core/src/test/scala/org/apache/spark/util/UtilsSuite.scala index b7cc840..5d93086 100644 --- a/core/src/test/scala/org/apache/spark/util/UtilsSuite.scala +++ b/core/src/test/scala/org/apache/spark/util/UtilsSuite.scala @@ -241,7 +241,6 @@ class UtilsSuite extends FunSuite with ResetSystemProperties { assertResolves(C:/path/to/file.txt, file:/C:/path/to/file.txt, testWindows = true) assertResolves(C:\\path\\to\\file.txt, file:/C:/path/to/file.txt, testWindows = true) assertResolves(file:/C:/path/to/file.txt, file:/C:/path/to/file.txt, testWindows = true) -assertResolves(file:/C:/path to/file.txt, file:/C:/path%20to/file.txt, testWindows = true) assertResolves(file:///C:/path/to/file.txt, file:/C:/path/to/file.txt, testWindows = true) assertResolves(file:/C:/file.txt#alias.txt, file:/C:/file.txt#alias.txt, testWindows = true) intercept[IllegalArgumentException] { Utils.resolveURI(file:foo) } @@ -265,9 +264,8 @@ class UtilsSuite extends FunSuite with ResetSystemProperties { assertResolves(hdfs:/jar1,file:/jar2,jar3, shdfs:/jar1,file:/jar2,file:$cwd/jar3) assertResolves(hdfs:/jar1,file:/jar2,jar3,jar4#jar5, shdfs:/jar1,file:/jar2,file:$cwd/jar3,file:$cwd/jar4#jar5) -assertResolves(hdfs:/jar1,file:/jar2,jar3,C:\pi.py#py.pi,C:\path to\jar4.jar, - shdfs:/jar1,file:/jar2,file:$cwd/jar3,file:/C:/pi.py#py.pi,file:/C:/path%20to/jar4.jar, - testWindows = true) +assertResolves(hdfs:/jar1,file:/jar2,jar3,C:\\pi.py#py.pi, + shdfs:/jar1,file:/jar2,file:$cwd/jar3,file:/C:/pi.py#py.pi, testWindows = true) } test(nonLocalPaths) { - To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org For additional commands, e-mail: commits-h...@spark.apache.org
spark git commit: [SPARK-6720][MLLIB] PySpark MultivariateStatisticalSummary unit test for normL1...
Repository: spark Updated Branches: refs/heads/master e6f08fb42 - fc957dc78 [SPARK-6720][MLLIB] PySpark MultivariateStatisticalSummary unit test for normL1... ... and normL2. Add test cases to insufficient unit test for `normL1` and `normL2`. Ref: https://github.com/apache/spark/pull/5359 Author: lewuathe lewua...@me.com Closes #5374 from Lewuathe/SPARK-6720 and squashes the following commits: 5541b24 [lewuathe] More accurate tests dc5718c [lewuathe] [SPARK-6720] PySpark MultivariateStatisticalSummary unit test for normL1 and normL2 Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/fc957dc7 Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/fc957dc7 Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/fc957dc7 Branch: refs/heads/master Commit: fc957dc78138e72036dbbadc9a54f155d318c038 Parents: e6f08fb Author: lewuathe lewua...@me.com Authored: Tue Apr 7 14:36:57 2015 -0700 Committer: Xiangrui Meng m...@databricks.com Committed: Tue Apr 7 14:36:57 2015 -0700 -- python/pyspark/mllib/tests.py | 7 +++ 1 file changed, 7 insertions(+) -- http://git-wip-us.apache.org/repos/asf/spark/blob/fc957dc7/python/pyspark/mllib/tests.py -- diff --git a/python/pyspark/mllib/tests.py b/python/pyspark/mllib/tests.py index 47dad7d..61ef398 100644 --- a/python/pyspark/mllib/tests.py +++ b/python/pyspark/mllib/tests.py @@ -363,6 +363,13 @@ class StatTests(PySparkTestCase): self.assertEqual(10, len(summary.normL1())) self.assertEqual(10, len(summary.normL2())) +data2 = self.sc.parallelize(xrange(10)).map(lambda x: Vectors.dense(x)) +summary2 = Statistics.colStats(data2) +self.assertEqual(array([45.0]), summary2.normL1()) +import math +expectedNormL2 = math.sqrt(sum(map(lambda x: x*x, xrange(10 +self.assertTrue(math.fabs(summary2.normL2()[0] - expectedNormL2) 1e-14) + class VectorUDTTests(PySparkTestCase): - To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org For additional commands, e-mail: commits-h...@spark.apache.org
spark git commit: [SPARK-6748] [SQL] Makes QueryPlan.schema a lazy val
Repository: spark Updated Branches: refs/heads/master fc957dc78 - 77bcceb9f [SPARK-6748] [SQL] Makes QueryPlan.schema a lazy val `DataFrame.collect()` calls `SparkPlan.executeCollect()`, which consists of a single line: ```scala execute().map(ScalaReflection.convertRowToScala(_, schema)).collect() ``` The problem is that, `QueryPlan.schema` is a function. And since 1.3.0, `convertRowToScala` starts returning a `GenericRowWithSchema`. Thus, every `GenericRowWithSchema` instance holds a separate copy of the schema object. Also, YJP profiling result of the following simple micro benchmark (executed in Spark shell) shows that constructing the schema object takes up to ~35% CPU time. ```scala sc.parallelize(1 to 1000). map(i = (i, sval_$i)). toDF(key, value). saveAsParquetFile(file:///tmp/src.parquet) // Profiling started from this line sqlContext.parquetFile(file:///tmp/src.parquet).collect() ``` !-- Reviewable:start -- [img src=https://reviewable.io/review_button.png; height=40 alt=Review on Reviewable/](https://reviewable.io/reviews/apache/spark/5398) !-- Reviewable:end -- Author: Cheng Lian l...@databricks.com Closes #5398 from liancheng/spark-6748 and squashes the following commits: 3159469 [Cheng Lian] Makes QueryPlan.schema a lazy val Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/77bcceb9 Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/77bcceb9 Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/77bcceb9 Branch: refs/heads/master Commit: 77bcceb9f01e97cb6f41791f2167b40c4311f701 Parents: fc957dc Author: Cheng Lian l...@databricks.com Authored: Wed Apr 8 07:00:56 2015 +0800 Committer: Cheng Lian l...@databricks.com Committed: Wed Apr 8 07:00:56 2015 +0800 -- .../main/scala/org/apache/spark/sql/catalyst/plans/QueryPlan.scala | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) -- http://git-wip-us.apache.org/repos/asf/spark/blob/77bcceb9/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/QueryPlan.scala -- diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/QueryPlan.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/QueryPlan.scala index 02f7c26..7967189 100644 --- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/QueryPlan.scala +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/QueryPlan.scala @@ -150,7 +150,7 @@ abstract class QueryPlan[PlanType : TreeNode[PlanType]] extends TreeNode[PlanTy }.toSeq } - def schema: StructType = StructType.fromAttributes(output) + lazy val schema: StructType = StructType.fromAttributes(output) /** Returns the output schema in the tree format. */ def schemaString: String = schema.treeString - To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org For additional commands, e-mail: commits-h...@spark.apache.org
spark git commit: [SPARK-6737] Fix memory leak in OutputCommitCoordinator
Repository: spark Updated Branches: refs/heads/master 77bcceb9f - c83e03948 [SPARK-6737] Fix memory leak in OutputCommitCoordinator This patch fixes a memory leak in the DAGScheduler, which caused us to leak a map entry per submitted stage. The problem is that the OutputCommitCoordinator needs to be informed when stages end in order to remove entries from its `authorizedCommitters` map, but the DAGScheduler only called it in one of the four code paths that are used to mark stages as completed. This patch fixes this issue by consolidating the processing of stage completion into a new `markStageAsFinished` method and updates DAGSchedulerSuite's `assertDataStructuresEmpty` assertion to also check the OutputCommitCoordinator data structures. I've also added a comment at the top of DAGScheduler so that we remember to update this test when adding new data structures. Author: Josh Rosen joshro...@databricks.com Closes #5397 from JoshRosen/SPARK-6737 and squashes the following commits: af3b02f [Josh Rosen] Consolidate stage completion handling code in a single method. e96ce3a [Josh Rosen] Consolidate stage completion handling code in a single method. 3052aea [Josh Rosen] Comment update 7896899 [Josh Rosen] Fix SPARK-6737 by informing OutputCommitCoordinator of all stage end events. 4ead1dc [Josh Rosen] Add regression tests for SPARK-6737 Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/c83e0394 Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/c83e0394 Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/c83e0394 Branch: refs/heads/master Commit: c83e03948b184ffb3a9418fecc4d2c26ae33b057 Parents: 77bcceb Author: Josh Rosen joshro...@databricks.com Authored: Tue Apr 7 16:18:55 2015 -0700 Committer: Josh Rosen joshro...@databricks.com Committed: Tue Apr 7 16:18:55 2015 -0700 -- .../apache/spark/scheduler/DAGScheduler.scala | 63 +++- .../scheduler/OutputCommitCoordinator.scala | 7 +++ .../spark/scheduler/DAGSchedulerSuite.scala | 1 + 3 files changed, 42 insertions(+), 29 deletions(-) -- http://git-wip-us.apache.org/repos/asf/spark/blob/c83e0394/core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala -- diff --git a/core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala b/core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala index c82ae4b..c912520 100644 --- a/core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala +++ b/core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala @@ -50,6 +50,10 @@ import org.apache.spark.storage.BlockManagerMessages.BlockManagerHeartbeat * not caused by shuffle file loss are handled by the TaskScheduler, which will retry each task * a small number of times before cancelling the whole stage. * + * Here's a checklist to use when making or reviewing changes to this class: + * + * - When adding a new data structure, update `DAGSchedulerSuite.assertDataStructuresEmpty` to + *include the new structure. This will help to catch memory leaks. */ private[spark] class DAGScheduler( @@ -111,6 +115,8 @@ class DAGScheduler( // stray messages to detect. private val failedEpoch = new HashMap[String, Long] + private [scheduler] val outputCommitCoordinator = env.outputCommitCoordinator + // A closure serializer that we reuse. // This is only safe because DAGScheduler runs in a single thread. private val closureSerializer = SparkEnv.get.closureSerializer.newInstance() @@ -128,8 +134,6 @@ class DAGScheduler( private[scheduler] val eventProcessLoop = new DAGSchedulerEventProcessLoop(this) taskScheduler.setDAGScheduler(this) - private val outputCommitCoordinator = env.outputCommitCoordinator - // Called by TaskScheduler to report task's starting. def taskStarted(task: Task[_], taskInfo: TaskInfo) { eventProcessLoop.post(BeginEvent(task, taskInfo)) @@ -710,9 +714,10 @@ class DAGScheduler( // cancelling the stages because if the DAG scheduler is stopped, the entire application // is in the process of getting stopped. val stageFailedMessage = Stage cancelled because SparkContext was shut down - runningStages.foreach { stage = -stage.latestInfo.stageFailed(stageFailedMessage) -listenerBus.post(SparkListenerStageCompleted(stage.latestInfo)) + // The `toArray` here is necessary so that we don't iterate over `runningStages` while + // mutating it. + runningStages.toArray.foreach { stage = +markStageAsFinished(stage, Some(stageFailedMessage)) } listenerBus.post(SparkListenerJobEnd(job.jobId, clock.getTimeMillis(), JobFailed(error))) } @@ -887,10 +892,9 @@ class DAGScheduler(
spark git commit: [SPARK-6737] Fix memory leak in OutputCommitCoordinator
Repository: spark Updated Branches: refs/heads/branch-1.3 ab1b8edb8 - 277733b1d [SPARK-6737] Fix memory leak in OutputCommitCoordinator This patch fixes a memory leak in the DAGScheduler, which caused us to leak a map entry per submitted stage. The problem is that the OutputCommitCoordinator needs to be informed when stages end in order to remove entries from its `authorizedCommitters` map, but the DAGScheduler only called it in one of the four code paths that are used to mark stages as completed. This patch fixes this issue by consolidating the processing of stage completion into a new `markStageAsFinished` method and updates DAGSchedulerSuite's `assertDataStructuresEmpty` assertion to also check the OutputCommitCoordinator data structures. I've also added a comment at the top of DAGScheduler so that we remember to update this test when adding new data structures. Author: Josh Rosen joshro...@databricks.com Closes #5397 from JoshRosen/SPARK-6737 and squashes the following commits: af3b02f [Josh Rosen] Consolidate stage completion handling code in a single method. e96ce3a [Josh Rosen] Consolidate stage completion handling code in a single method. 3052aea [Josh Rosen] Comment update 7896899 [Josh Rosen] Fix SPARK-6737 by informing OutputCommitCoordinator of all stage end events. 4ead1dc [Josh Rosen] Add regression tests for SPARK-6737 (cherry picked from commit c83e03948b184ffb3a9418fecc4d2c26ae33b057) Signed-off-by: Josh Rosen joshro...@databricks.com Conflicts: core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/277733b1 Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/277733b1 Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/277733b1 Branch: refs/heads/branch-1.3 Commit: 277733b1daa16fcd39e1ab30ba73b040affc3810 Parents: ab1b8ed Author: Josh Rosen joshro...@databricks.com Authored: Tue Apr 7 16:18:55 2015 -0700 Committer: Josh Rosen joshro...@databricks.com Committed: Tue Apr 7 16:26:07 2015 -0700 -- .../apache/spark/scheduler/DAGScheduler.scala | 63 +++- .../scheduler/OutputCommitCoordinator.scala | 7 +++ .../spark/scheduler/DAGSchedulerSuite.scala | 1 + 3 files changed, 42 insertions(+), 29 deletions(-) -- http://git-wip-us.apache.org/repos/asf/spark/blob/277733b1/core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala -- diff --git a/core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala b/core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala index c10873e..4a79eba 100644 --- a/core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala +++ b/core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala @@ -54,6 +54,10 @@ import org.apache.spark.storage.BlockManagerMessages.BlockManagerHeartbeat * not caused by shuffle file loss are handled by the TaskScheduler, which will retry each task * a small number of times before cancelling the whole stage. * + * Here's a checklist to use when making or reviewing changes to this class: + * + * - When adding a new data structure, update `DAGSchedulerSuite.assertDataStructuresEmpty` to + *include the new structure. This will help to catch memory leaks. */ private[spark] class DAGScheduler( @@ -115,6 +119,8 @@ class DAGScheduler( // stray messages to detect. private val failedEpoch = new HashMap[String, Long] + private [scheduler] val outputCommitCoordinator = env.outputCommitCoordinator + // A closure serializer that we reuse. // This is only safe because DAGScheduler runs in a single thread. private val closureSerializer = SparkEnv.get.closureSerializer.newInstance() @@ -132,8 +138,6 @@ class DAGScheduler( private[scheduler] val eventProcessLoop = new DAGSchedulerEventProcessLoop(this) taskScheduler.setDAGScheduler(this) - private val outputCommitCoordinator = env.outputCommitCoordinator - // Called by TaskScheduler to report task's starting. def taskStarted(task: Task[_], taskInfo: TaskInfo) { eventProcessLoop.post(BeginEvent(task, taskInfo)) @@ -698,9 +702,10 @@ class DAGScheduler( // cancelling the stages because if the DAG scheduler is stopped, the entire application // is in the process of getting stopped. val stageFailedMessage = Stage cancelled because SparkContext was shut down - runningStages.foreach { stage = -stage.latestInfo.stageFailed(stageFailedMessage) -listenerBus.post(SparkListenerStageCompleted(stage.latestInfo)) + // The `toArray` here is necessary so that we don't iterate over `runningStages` while + // mutating it. + runningStages.toArray.foreach { stage = +
spark git commit: [SPARK-6754] Remove unnecessary TaskContextHelper
Repository: spark Updated Branches: refs/heads/master d138aa8ee - 8d2a36c0f [SPARK-6754] Remove unnecessary TaskContextHelper The TaskContextHelper was originally necessary because TaskContext was written in Java, which does not have a way to specify that classes are package-private, so TaskContextHelper existed to work around this. Now that TaskContext has been re-written in Scala, this class is no longer necessary. rxin can you look at this? It looks like you missed this bit of cleanup when you moved TaskContext from Java to Scala in #4324 cc ScrapCodes and pwendell who added this originally. Author: Kay Ousterhout kayousterh...@gmail.com Closes #5402 from kayousterhout/SPARK-6754 and squashes the following commits: f089800 [Kay Ousterhout] [SPARK-6754] Remove unnecessary TaskContextHelper Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/8d2a36c0 Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/8d2a36c0 Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/8d2a36c0 Branch: refs/heads/master Commit: 8d2a36c0fdfbea9f58271ef6aeb89bb79b22cf62 Parents: d138aa8 Author: Kay Ousterhout kayousterh...@gmail.com Authored: Tue Apr 7 22:40:42 2015 -0700 Committer: Reynold Xin r...@databricks.com Committed: Tue Apr 7 22:40:42 2015 -0700 -- .../org/apache/spark/TaskContextHelper.scala| 29 .../apache/spark/scheduler/DAGScheduler.scala | 4 +-- .../scala/org/apache/spark/scheduler/Task.scala | 6 ++-- 3 files changed, 5 insertions(+), 34 deletions(-) -- http://git-wip-us.apache.org/repos/asf/spark/blob/8d2a36c0/core/src/main/scala/org/apache/spark/TaskContextHelper.scala -- diff --git a/core/src/main/scala/org/apache/spark/TaskContextHelper.scala b/core/src/main/scala/org/apache/spark/TaskContextHelper.scala deleted file mode 100644 index 4636c46..000 --- a/core/src/main/scala/org/apache/spark/TaskContextHelper.scala +++ /dev/null @@ -1,29 +0,0 @@ -/* - * Licensed to the Apache Software Foundation (ASF) under one or more - * contributor license agreements. See the NOTICE file distributed with - * this work for additional information regarding copyright ownership. - * The ASF licenses this file to You under the Apache License, Version 2.0 - * (the License); you may not use this file except in compliance with - * the License. You may obtain a copy of the License at - * - *http://www.apache.org/licenses/LICENSE-2.0 - * - * Unless required by applicable law or agreed to in writing, software - * distributed under the License is distributed on an AS IS BASIS, - * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. - * See the License for the specific language governing permissions and - * limitations under the License. - */ - -package org.apache.spark - -/** - * This class exists to restrict the visibility of TaskContext setters. - */ -private [spark] object TaskContextHelper { - - def setTaskContext(tc: TaskContext): Unit = TaskContext.setTaskContext(tc) - - def unset(): Unit = TaskContext.unset() - -} http://git-wip-us.apache.org/repos/asf/spark/blob/8d2a36c0/core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala -- diff --git a/core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala b/core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala index c912520..508fe7b 100644 --- a/core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala +++ b/core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala @@ -645,13 +645,13 @@ class DAGScheduler( val split = rdd.partitions(job.partitions(0)) val taskContext = new TaskContextImpl(job.finalStage.id, job.partitions(0), taskAttemptId = 0, attemptNumber = 0, runningLocally = true) - TaskContextHelper.setTaskContext(taskContext) + TaskContext.setTaskContext(taskContext) try { val result = job.func(taskContext, rdd.iterator(split, taskContext)) job.listener.taskSucceeded(0, result) } finally { taskContext.markTaskCompleted() -TaskContextHelper.unset() +TaskContext.unset() } } catch { case e: Exception = http://git-wip-us.apache.org/repos/asf/spark/blob/8d2a36c0/core/src/main/scala/org/apache/spark/scheduler/Task.scala -- diff --git a/core/src/main/scala/org/apache/spark/scheduler/Task.scala b/core/src/main/scala/org/apache/spark/scheduler/Task.scala index 4d9f940..8b59286 100644 --- a/core/src/main/scala/org/apache/spark/scheduler/Task.scala +++ b/core/src/main/scala/org/apache/spark/scheduler/Task.scala @@ -22,7 +22,7 @@ import
spark git commit: [SPARK-6705][MLLIB] Add fit intercept api to ml logisticregression
Repository: spark Updated Branches: refs/heads/master c83e03948 - d138aa8ee [SPARK-6705][MLLIB] Add fit intercept api to ml logisticregression I have the fit intercept enabled by default for logistic regression, I wonder what others think here. I understand that it enables allocation by default which is undesirable, but one needs to have a very strong reason for not having an intercept term enabled so it is the safer default from a statistical sense. Explicitly modeling the intercept by adding a column of all 1s does not work. I believe the reason is that since the API for LogisticRegressionWithLBFGS forces column normalization, and a column of all 1s has 0 variance so dividing by 0 kills it. Author: Omede Firouz ofir...@palantir.com Closes #5301 from oefirouz/addIntercept and squashes the following commits: 9f1286b [Omede Firouz] [SPARK-6705][MLLIB] Add fitInterceptTerm to LogisticRegression 1d6bd6f [Omede Firouz] [SPARK-6705][MLLIB] Add a fit intercept term to ML LogisticRegression 9963509 [Omede Firouz] [MLLIB] Add fitIntercept to LogisticRegression 2257fca [Omede Firouz] [MLLIB] Add fitIntercept param to logistic regression 329c1e2 [Omede Firouz] [MLLIB] Add fit intercept term bd9663c [Omede Firouz] [MLLIB] Add fit intercept api to ml logisticregression Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/d138aa8e Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/d138aa8e Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/d138aa8e Branch: refs/heads/master Commit: d138aa8ee23f4450242da3ac70a493229a90c76b Parents: c83e039 Author: Omede Firouz ofir...@palantir.com Authored: Tue Apr 7 23:36:31 2015 -0400 Committer: Joseph K. Bradley jos...@databricks.com Committed: Tue Apr 7 23:36:31 2015 -0400 -- .../spark/ml/classification/LogisticRegression.scala| 8 ++-- .../scala/org/apache/spark/ml/param/sharedParams.scala | 12 .../ml/classification/LogisticRegressionSuite.scala | 9 + 3 files changed, 27 insertions(+), 2 deletions(-) -- http://git-wip-us.apache.org/repos/asf/spark/blob/d138aa8e/mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala -- diff --git a/mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala b/mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala index 49c00f7..3462574 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala @@ -31,7 +31,7 @@ import org.apache.spark.storage.StorageLevel * Params for logistic regression. */ private[classification] trait LogisticRegressionParams extends ProbabilisticClassifierParams - with HasRegParam with HasMaxIter with HasThreshold + with HasRegParam with HasMaxIter with HasFitIntercept with HasThreshold /** @@ -56,6 +56,9 @@ class LogisticRegression def setMaxIter(value: Int): this.type = set(maxIter, value) /** @group setParam */ + def setFitIntercept(value: Boolean): this.type = set(fitIntercept, value) + + /** @group setParam */ def setThreshold(value: Double): this.type = set(threshold, value) override protected def train(dataset: DataFrame, paramMap: ParamMap): LogisticRegressionModel = { @@ -67,7 +70,8 @@ class LogisticRegression } // Train model -val lr = new LogisticRegressionWithLBFGS +val lr = new LogisticRegressionWithLBFGS() + .setIntercept(paramMap(fitIntercept)) lr.optimizer .setRegParam(paramMap(regParam)) .setNumIterations(paramMap(maxIter)) http://git-wip-us.apache.org/repos/asf/spark/blob/d138aa8e/mllib/src/main/scala/org/apache/spark/ml/param/sharedParams.scala -- diff --git a/mllib/src/main/scala/org/apache/spark/ml/param/sharedParams.scala b/mllib/src/main/scala/org/apache/spark/ml/param/sharedParams.scala index 5d660d1..0739fdb 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/param/sharedParams.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/param/sharedParams.scala @@ -106,6 +106,18 @@ private[ml] trait HasProbabilityCol extends Params { def getProbabilityCol: String = get(probabilityCol) } +private[ml] trait HasFitIntercept extends Params { + /** + * param for fitting the intercept term, defaults to true + * @group param + */ + val fitIntercept: BooleanParam = +new BooleanParam(this, fitIntercept, indicates whether to fit an intercept term, Some(true)) + + /** @group getParam */ + def getFitIntercept: Boolean = get(fitIntercept) +} + private[ml] trait HasThreshold extends Params { /** * param for threshold in
[2/2] spark git commit: Revert Preparing Spark release v1.3.1-rc1
Revert Preparing Spark release v1.3.1-rc1 This reverts commit 0dcb5d9f31b713ed90bcec63ebc4e530cbb69851. Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/00837ccd Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/00837ccd Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/00837ccd Branch: refs/heads/branch-1.3 Commit: 00837ccd02000b6bb5994a0d7ab8a41d11efe5a3 Parents: 333b473 Author: Patrick Wendell patr...@databricks.com Authored: Tue Apr 7 22:31:25 2015 -0400 Committer: Patrick Wendell patr...@databricks.com Committed: Tue Apr 7 22:31:25 2015 -0400 -- assembly/pom.xml | 2 +- bagel/pom.xml | 2 +- core/pom.xml | 2 +- examples/pom.xml | 2 +- external/flume-sink/pom.xml | 2 +- external/flume/pom.xml| 2 +- external/kafka-assembly/pom.xml | 2 +- external/kafka/pom.xml| 2 +- external/mqtt/pom.xml | 2 +- external/twitter/pom.xml | 2 +- external/zeromq/pom.xml | 2 +- extras/java8-tests/pom.xml| 2 +- extras/kinesis-asl/pom.xml| 2 +- extras/spark-ganglia-lgpl/pom.xml | 2 +- graphx/pom.xml| 2 +- mllib/pom.xml | 2 +- network/common/pom.xml| 2 +- network/shuffle/pom.xml | 2 +- network/yarn/pom.xml | 2 +- pom.xml | 2 +- repl/pom.xml | 2 +- sql/catalyst/pom.xml | 2 +- sql/core/pom.xml | 2 +- sql/hive-thriftserver/pom.xml | 2 +- sql/hive/pom.xml | 2 +- streaming/pom.xml | 2 +- tools/pom.xml | 2 +- yarn/pom.xml | 2 +- 28 files changed, 28 insertions(+), 28 deletions(-) -- http://git-wip-us.apache.org/repos/asf/spark/blob/00837ccd/assembly/pom.xml -- diff --git a/assembly/pom.xml b/assembly/pom.xml index 67bebfc..114dde7 100644 --- a/assembly/pom.xml +++ b/assembly/pom.xml @@ -21,7 +21,7 @@ parent groupIdorg.apache.spark/groupId artifactIdspark-parent_2.10/artifactId -version1.3.1/version +version1.3.1-SNAPSHOT/version relativePath../pom.xml/relativePath /parent http://git-wip-us.apache.org/repos/asf/spark/blob/00837ccd/bagel/pom.xml -- diff --git a/bagel/pom.xml b/bagel/pom.xml index c7750a2..dea41f8 100644 --- a/bagel/pom.xml +++ b/bagel/pom.xml @@ -21,7 +21,7 @@ parent groupIdorg.apache.spark/groupId artifactIdspark-parent_2.10/artifactId -version1.3.1/version +version1.3.1-SNAPSHOT/version relativePath../pom.xml/relativePath /parent http://git-wip-us.apache.org/repos/asf/spark/blob/00837ccd/core/pom.xml -- diff --git a/core/pom.xml b/core/pom.xml index a3dc28f..9a79d70 100644 --- a/core/pom.xml +++ b/core/pom.xml @@ -21,7 +21,7 @@ parent groupIdorg.apache.spark/groupId artifactIdspark-parent_2.10/artifactId -version1.3.1/version +version1.3.1-SNAPSHOT/version relativePath../pom.xml/relativePath /parent http://git-wip-us.apache.org/repos/asf/spark/blob/00837ccd/examples/pom.xml -- diff --git a/examples/pom.xml b/examples/pom.xml index 9f03cbd..73ab234 100644 --- a/examples/pom.xml +++ b/examples/pom.xml @@ -21,7 +21,7 @@ parent groupIdorg.apache.spark/groupId artifactIdspark-parent_2.10/artifactId -version1.3.1/version +version1.3.1-SNAPSHOT/version relativePath../pom.xml/relativePath /parent http://git-wip-us.apache.org/repos/asf/spark/blob/00837ccd/external/flume-sink/pom.xml -- diff --git a/external/flume-sink/pom.xml b/external/flume-sink/pom.xml index 46adbe2..1a5aaf5 100644 --- a/external/flume-sink/pom.xml +++ b/external/flume-sink/pom.xml @@ -21,7 +21,7 @@ parent groupIdorg.apache.spark/groupId artifactIdspark-parent_2.10/artifactId -version1.3.1/version +version1.3.1-SNAPSHOT/version relativePath../../pom.xml/relativePath /parent http://git-wip-us.apache.org/repos/asf/spark/blob/00837ccd/external/flume/pom.xml -- diff --git a/external/flume/pom.xml b/external/flume/pom.xml index 5fc589f..d5539d9 100644 --- a/external/flume/pom.xml +++ b/external/flume/pom.xml @@ -21,7 +21,7 @@ parent groupIdorg.apache.spark/groupId artifactIdspark-parent_2.10/artifactId -version1.3.1/version +version1.3.1-SNAPSHOT/version
[1/2] spark git commit: Revert Preparing development version 1.3.2-SNAPSHOT
Repository: spark Updated Branches: refs/heads/branch-1.3 277733b1d - 00837ccd0 Revert Preparing development version 1.3.2-SNAPSHOT This reverts commit 728c1f927822eb6b12f04dc47109feb6fbe02ec2. Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/333b4732 Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/333b4732 Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/333b4732 Branch: refs/heads/branch-1.3 Commit: 333b47325ce22dbc7670f0499e43f02b82c0c797 Parents: 277733b Author: Patrick Wendell patr...@databricks.com Authored: Tue Apr 7 22:31:22 2015 -0400 Committer: Patrick Wendell patr...@databricks.com Committed: Tue Apr 7 22:31:22 2015 -0400 -- assembly/pom.xml | 2 +- bagel/pom.xml | 2 +- core/pom.xml | 2 +- examples/pom.xml | 2 +- external/flume-sink/pom.xml | 2 +- external/flume/pom.xml| 2 +- external/kafka-assembly/pom.xml | 2 +- external/kafka/pom.xml| 2 +- external/mqtt/pom.xml | 2 +- external/twitter/pom.xml | 2 +- external/zeromq/pom.xml | 2 +- extras/java8-tests/pom.xml| 2 +- extras/kinesis-asl/pom.xml| 2 +- extras/spark-ganglia-lgpl/pom.xml | 2 +- graphx/pom.xml| 2 +- mllib/pom.xml | 2 +- network/common/pom.xml| 2 +- network/shuffle/pom.xml | 2 +- network/yarn/pom.xml | 2 +- pom.xml | 2 +- repl/pom.xml | 2 +- sql/catalyst/pom.xml | 2 +- sql/core/pom.xml | 2 +- sql/hive-thriftserver/pom.xml | 2 +- sql/hive/pom.xml | 2 +- streaming/pom.xml | 2 +- tools/pom.xml | 2 +- yarn/pom.xml | 2 +- 28 files changed, 28 insertions(+), 28 deletions(-) -- http://git-wip-us.apache.org/repos/asf/spark/blob/333b4732/assembly/pom.xml -- diff --git a/assembly/pom.xml b/assembly/pom.xml index 0952cd2..67bebfc 100644 --- a/assembly/pom.xml +++ b/assembly/pom.xml @@ -21,7 +21,7 @@ parent groupIdorg.apache.spark/groupId artifactIdspark-parent_2.10/artifactId -version1.3.2-SNAPSHOT/version +version1.3.1/version relativePath../pom.xml/relativePath /parent http://git-wip-us.apache.org/repos/asf/spark/blob/333b4732/bagel/pom.xml -- diff --git a/bagel/pom.xml b/bagel/pom.xml index 602cc7b..c7750a2 100644 --- a/bagel/pom.xml +++ b/bagel/pom.xml @@ -21,7 +21,7 @@ parent groupIdorg.apache.spark/groupId artifactIdspark-parent_2.10/artifactId -version1.3.2-SNAPSHOT/version +version1.3.1/version relativePath../pom.xml/relativePath /parent http://git-wip-us.apache.org/repos/asf/spark/blob/333b4732/core/pom.xml -- diff --git a/core/pom.xml b/core/pom.xml index 5971d05..a3dc28f 100644 --- a/core/pom.xml +++ b/core/pom.xml @@ -21,7 +21,7 @@ parent groupIdorg.apache.spark/groupId artifactIdspark-parent_2.10/artifactId -version1.3.2-SNAPSHOT/version +version1.3.1/version relativePath../pom.xml/relativePath /parent http://git-wip-us.apache.org/repos/asf/spark/blob/333b4732/examples/pom.xml -- diff --git a/examples/pom.xml b/examples/pom.xml index e1a3ecc..9f03cbd 100644 --- a/examples/pom.xml +++ b/examples/pom.xml @@ -21,7 +21,7 @@ parent groupIdorg.apache.spark/groupId artifactIdspark-parent_2.10/artifactId -version1.3.2-SNAPSHOT/version +version1.3.1/version relativePath../pom.xml/relativePath /parent http://git-wip-us.apache.org/repos/asf/spark/blob/333b4732/external/flume-sink/pom.xml -- diff --git a/external/flume-sink/pom.xml b/external/flume-sink/pom.xml index f46a2a0..46adbe2 100644 --- a/external/flume-sink/pom.xml +++ b/external/flume-sink/pom.xml @@ -21,7 +21,7 @@ parent groupIdorg.apache.spark/groupId artifactIdspark-parent_2.10/artifactId -version1.3.2-SNAPSHOT/version +version1.3.1/version relativePath../../pom.xml/relativePath /parent http://git-wip-us.apache.org/repos/asf/spark/blob/333b4732/external/flume/pom.xml -- diff --git a/external/flume/pom.xml b/external/flume/pom.xml index 02331e8..5fc589f 100644 --- a/external/flume/pom.xml +++ b/external/flume/pom.xml @@ -21,7 +21,7 @@ parent groupIdorg.apache.spark/groupId
[1/2] spark git commit: Preparing Spark release v1.3.1-rc2
Repository: spark Updated Branches: refs/heads/branch-1.3 00837ccd0 - cdef7d080 Preparing Spark release v1.3.1-rc2 Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/7c4473aa Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/7c4473aa Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/7c4473aa Branch: refs/heads/branch-1.3 Commit: 7c4473aa5a7f5de0323394aaedeefbf9738e8eb5 Parents: 00837cc Author: Patrick Wendell patr...@databricks.com Authored: Wed Apr 8 02:30:52 2015 + Committer: Patrick Wendell patr...@databricks.com Committed: Wed Apr 8 02:30:52 2015 + -- assembly/pom.xml | 2 +- bagel/pom.xml | 2 +- core/pom.xml | 2 +- examples/pom.xml | 2 +- external/flume-sink/pom.xml | 2 +- external/flume/pom.xml| 2 +- external/kafka-assembly/pom.xml | 2 +- external/kafka/pom.xml| 2 +- external/mqtt/pom.xml | 2 +- external/twitter/pom.xml | 2 +- external/zeromq/pom.xml | 2 +- extras/java8-tests/pom.xml| 2 +- extras/kinesis-asl/pom.xml| 2 +- extras/spark-ganglia-lgpl/pom.xml | 2 +- graphx/pom.xml| 2 +- mllib/pom.xml | 2 +- network/common/pom.xml| 2 +- network/shuffle/pom.xml | 2 +- network/yarn/pom.xml | 2 +- pom.xml | 2 +- repl/pom.xml | 2 +- sql/catalyst/pom.xml | 2 +- sql/core/pom.xml | 2 +- sql/hive-thriftserver/pom.xml | 2 +- sql/hive/pom.xml | 2 +- streaming/pom.xml | 2 +- tools/pom.xml | 2 +- yarn/pom.xml | 2 +- 28 files changed, 28 insertions(+), 28 deletions(-) -- http://git-wip-us.apache.org/repos/asf/spark/blob/7c4473aa/assembly/pom.xml -- diff --git a/assembly/pom.xml b/assembly/pom.xml index 114dde7..67bebfc 100644 --- a/assembly/pom.xml +++ b/assembly/pom.xml @@ -21,7 +21,7 @@ parent groupIdorg.apache.spark/groupId artifactIdspark-parent_2.10/artifactId -version1.3.1-SNAPSHOT/version +version1.3.1/version relativePath../pom.xml/relativePath /parent http://git-wip-us.apache.org/repos/asf/spark/blob/7c4473aa/bagel/pom.xml -- diff --git a/bagel/pom.xml b/bagel/pom.xml index dea41f8..c7750a2 100644 --- a/bagel/pom.xml +++ b/bagel/pom.xml @@ -21,7 +21,7 @@ parent groupIdorg.apache.spark/groupId artifactIdspark-parent_2.10/artifactId -version1.3.1-SNAPSHOT/version +version1.3.1/version relativePath../pom.xml/relativePath /parent http://git-wip-us.apache.org/repos/asf/spark/blob/7c4473aa/core/pom.xml -- diff --git a/core/pom.xml b/core/pom.xml index 9a79d70..a3dc28f 100644 --- a/core/pom.xml +++ b/core/pom.xml @@ -21,7 +21,7 @@ parent groupIdorg.apache.spark/groupId artifactIdspark-parent_2.10/artifactId -version1.3.1-SNAPSHOT/version +version1.3.1/version relativePath../pom.xml/relativePath /parent http://git-wip-us.apache.org/repos/asf/spark/blob/7c4473aa/examples/pom.xml -- diff --git a/examples/pom.xml b/examples/pom.xml index 73ab234..9f03cbd 100644 --- a/examples/pom.xml +++ b/examples/pom.xml @@ -21,7 +21,7 @@ parent groupIdorg.apache.spark/groupId artifactIdspark-parent_2.10/artifactId -version1.3.1-SNAPSHOT/version +version1.3.1/version relativePath../pom.xml/relativePath /parent http://git-wip-us.apache.org/repos/asf/spark/blob/7c4473aa/external/flume-sink/pom.xml -- diff --git a/external/flume-sink/pom.xml b/external/flume-sink/pom.xml index 1a5aaf5..46adbe2 100644 --- a/external/flume-sink/pom.xml +++ b/external/flume-sink/pom.xml @@ -21,7 +21,7 @@ parent groupIdorg.apache.spark/groupId artifactIdspark-parent_2.10/artifactId -version1.3.1-SNAPSHOT/version +version1.3.1/version relativePath../../pom.xml/relativePath /parent http://git-wip-us.apache.org/repos/asf/spark/blob/7c4473aa/external/flume/pom.xml -- diff --git a/external/flume/pom.xml b/external/flume/pom.xml index d5539d9..5fc589f 100644 --- a/external/flume/pom.xml +++ b/external/flume/pom.xml @@ -21,7 +21,7 @@ parent groupIdorg.apache.spark/groupId artifactIdspark-parent_2.10/artifactId -version1.3.1-SNAPSHOT/version +
Git Push Summary
Repository: spark Updated Tags: refs/tags/v1.3.1-rc2 [created] 7c4473aa5 - To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org For additional commands, e-mail: commits-h...@spark.apache.org
[2/2] spark git commit: Preparing development version 1.3.2-SNAPSHOT
Preparing development version 1.3.2-SNAPSHOT Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/cdef7d08 Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/cdef7d08 Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/cdef7d08 Branch: refs/heads/branch-1.3 Commit: cdef7d080aa3f473f5ea06ba816c01b41a0239eb Parents: 7c4473a Author: Patrick Wendell patr...@databricks.com Authored: Wed Apr 8 02:30:53 2015 + Committer: Patrick Wendell patr...@databricks.com Committed: Wed Apr 8 02:30:53 2015 + -- assembly/pom.xml | 2 +- bagel/pom.xml | 2 +- core/pom.xml | 2 +- examples/pom.xml | 2 +- external/flume-sink/pom.xml | 2 +- external/flume/pom.xml| 2 +- external/kafka-assembly/pom.xml | 2 +- external/kafka/pom.xml| 2 +- external/mqtt/pom.xml | 2 +- external/twitter/pom.xml | 2 +- external/zeromq/pom.xml | 2 +- extras/java8-tests/pom.xml| 2 +- extras/kinesis-asl/pom.xml| 2 +- extras/spark-ganglia-lgpl/pom.xml | 2 +- graphx/pom.xml| 2 +- mllib/pom.xml | 2 +- network/common/pom.xml| 2 +- network/shuffle/pom.xml | 2 +- network/yarn/pom.xml | 2 +- pom.xml | 2 +- repl/pom.xml | 2 +- sql/catalyst/pom.xml | 2 +- sql/core/pom.xml | 2 +- sql/hive-thriftserver/pom.xml | 2 +- sql/hive/pom.xml | 2 +- streaming/pom.xml | 2 +- tools/pom.xml | 2 +- yarn/pom.xml | 2 +- 28 files changed, 28 insertions(+), 28 deletions(-) -- http://git-wip-us.apache.org/repos/asf/spark/blob/cdef7d08/assembly/pom.xml -- diff --git a/assembly/pom.xml b/assembly/pom.xml index 67bebfc..0952cd2 100644 --- a/assembly/pom.xml +++ b/assembly/pom.xml @@ -21,7 +21,7 @@ parent groupIdorg.apache.spark/groupId artifactIdspark-parent_2.10/artifactId -version1.3.1/version +version1.3.2-SNAPSHOT/version relativePath../pom.xml/relativePath /parent http://git-wip-us.apache.org/repos/asf/spark/blob/cdef7d08/bagel/pom.xml -- diff --git a/bagel/pom.xml b/bagel/pom.xml index c7750a2..602cc7b 100644 --- a/bagel/pom.xml +++ b/bagel/pom.xml @@ -21,7 +21,7 @@ parent groupIdorg.apache.spark/groupId artifactIdspark-parent_2.10/artifactId -version1.3.1/version +version1.3.2-SNAPSHOT/version relativePath../pom.xml/relativePath /parent http://git-wip-us.apache.org/repos/asf/spark/blob/cdef7d08/core/pom.xml -- diff --git a/core/pom.xml b/core/pom.xml index a3dc28f..5971d05 100644 --- a/core/pom.xml +++ b/core/pom.xml @@ -21,7 +21,7 @@ parent groupIdorg.apache.spark/groupId artifactIdspark-parent_2.10/artifactId -version1.3.1/version +version1.3.2-SNAPSHOT/version relativePath../pom.xml/relativePath /parent http://git-wip-us.apache.org/repos/asf/spark/blob/cdef7d08/examples/pom.xml -- diff --git a/examples/pom.xml b/examples/pom.xml index 9f03cbd..e1a3ecc 100644 --- a/examples/pom.xml +++ b/examples/pom.xml @@ -21,7 +21,7 @@ parent groupIdorg.apache.spark/groupId artifactIdspark-parent_2.10/artifactId -version1.3.1/version +version1.3.2-SNAPSHOT/version relativePath../pom.xml/relativePath /parent http://git-wip-us.apache.org/repos/asf/spark/blob/cdef7d08/external/flume-sink/pom.xml -- diff --git a/external/flume-sink/pom.xml b/external/flume-sink/pom.xml index 46adbe2..f46a2a0 100644 --- a/external/flume-sink/pom.xml +++ b/external/flume-sink/pom.xml @@ -21,7 +21,7 @@ parent groupIdorg.apache.spark/groupId artifactIdspark-parent_2.10/artifactId -version1.3.1/version +version1.3.2-SNAPSHOT/version relativePath../../pom.xml/relativePath /parent http://git-wip-us.apache.org/repos/asf/spark/blob/cdef7d08/external/flume/pom.xml -- diff --git a/external/flume/pom.xml b/external/flume/pom.xml index 5fc589f..02331e8 100644 --- a/external/flume/pom.xml +++ b/external/flume/pom.xml @@ -21,7 +21,7 @@ parent groupIdorg.apache.spark/groupId artifactIdspark-parent_2.10/artifactId -version1.3.1/version +version1.3.2-SNAPSHOT/version relativePath../../pom.xml/relativePath /parent