0472cf8 | Matei Zaharia | 12 June 2012, 18:30:49 UTC | Update version in SBT | 12 June 2012, 18:30:49 UTC |
4971e0f | Matei Zaharia | 12 June 2012, 17:41:57 UTC | Updated version number to 0.5.0 | 12 June 2012, 17:41:57 UTC |
08c50ad | Matei Zaharia | 11 June 2012, 06:06:15 UTC | Added script for launching Spark on EC2 from Mesos, to make it easier for new users to get up and running on EC2. | 11 June 2012, 06:06:15 UTC |
879bc0b | Matei Zaharia | 09 June 2012, 23:24:16 UTC | Merge branch 'master' into mesos-0.9 | 09 June 2012, 23:24:16 UTC |
4b05798 | Matei Zaharia | 09 June 2012, 23:24:03 UTC | Further bug fix to HttpBroadcast | 09 June 2012, 23:24:03 UTC |
587a16a | Matei Zaharia | 09 June 2012, 23:17:07 UTC | Merge branch 'master' into mesos-0.9 | 09 June 2012, 23:17:07 UTC |
8ed6628 | Matei Zaharia | 09 June 2012, 23:16:48 UTC | Bug fix to HttpBroadcast | 09 June 2012, 23:16:55 UTC |
2fd9f99 | Matei Zaharia | 09 June 2012, 22:58:35 UTC | Merge branch 'master' into mesos-0.9 | 09 June 2012, 22:58:35 UTC |
e75b1b5 | Matei Zaharia | 09 June 2012, 22:58:07 UTC | Change the default broadcast implementation to a simple HTTP-based broadcast. Fixes #139. | 09 June 2012, 22:58:07 UTC |
a96558c | Matei Zaharia | 09 June 2012, 21:44:18 UTC | Performance improvements to shuffle operations: in particular, preserve RDD partitioning in more cases where it's possible, and use iterators instead of materializing collections when doing joins. | 09 June 2012, 21:44:18 UTC |
7e1c97f | Matei Zaharia | 06 June 2012, 23:48:59 UTC | Merge branch 'master' into mesos-0.9 | 06 June 2012, 23:48:59 UTC |
0482767 | Matei Zaharia | 06 June 2012, 23:46:53 UTC | Commit task outputs to Hadoop-supported storage systems in parallel on the cluster instead of on the master. Fixes #110. | 06 June 2012, 23:46:53 UTC |
6888bc7 | Matei Zaharia | 06 June 2012, 23:14:19 UTC | Merge branch 'master' into mesos-0.9 | 06 June 2012, 23:14:19 UTC |
6ae2746 | Matei Zaharia | 06 June 2012, 23:13:02 UTC | Handle arrays that contain the same element many times better in SizeEstimator. Also added a test for SizeEstimator. Fixes #136. | 06 June 2012, 23:13:02 UTC |
0a61795 | Matei Zaharia | 06 June 2012, 23:12:08 UTC | Some refactoring to make BoundedMemoryCache test similar to others | 06 June 2012, 23:12:08 UTC |
1fa0da5 | Matei Zaharia | 06 June 2012, 06:31:46 UTC | Merge branch 'master' into mesos-0.9 | 06 June 2012, 06:31:46 UTC |
28fed4c | Matei Zaharia | 06 June 2012, 06:31:28 UTC | Add System.exit(0) at the end of all the example programs. | 06 June 2012, 06:31:28 UTC |
dbc3c86 | Matei Zaharia | 04 June 2012, 00:44:04 UTC | Merge branch 'master' into mesos-0.9 Conflicts: core/src/main/scala/spark/Executor.scala | 04 June 2012, 00:44:04 UTC |
1dd7d3d | Reynold Xin | 31 May 2012, 01:41:07 UTC | Merge branch 'master' of github.com:mesos/spark | 31 May 2012, 01:41:07 UTC |
d176422 | Reynold Xin | 31 May 2012, 01:40:10 UTC | Make spark.repl.Main.interp_ publicly accessible (so Shark can get rid of a weird file dediated to accessing this variable). | 31 May 2012, 01:40:10 UTC |
e141f64 | Matei Zaharia | 26 May 2012, 20:15:06 UTC | Merge pull request #132 from Benky/rb-first-iteration Little refactoring and unit tests for CacheTrackerActor | 26 May 2012, 20:15:06 UTC |
69372b4 | Matei Zaharia | 26 May 2012, 19:59:39 UTC | Merge pull request #133 from Benky/565245871f666c22aebb2c534f4fb7e947fca9f5 BoundedMemoryCache.put should fail when estimated size of 'value' is larger than cache capacity | 26 May 2012, 19:59:39 UTC |
ae64920 | Richard Benkovsky | 20 May 2012, 09:14:12 UTC | MesosScheduler refactoring | 22 May 2012, 09:04:54 UTC |
3a1bcd4 | Richard Benkovsky | 20 May 2012, 08:05:43 UTC | Added tests for CacheTrackerActor | 22 May 2012, 09:04:54 UTC |
8f2f736 | Richard Benkovsky | 20 May 2012, 06:02:30 UTC | Little refactoring | 22 May 2012, 09:04:54 UTC |
518506a | Richard Benkovsky | 19 May 2012, 13:42:54 UTC | Added tests for Utils.copyStream | 22 May 2012, 09:04:51 UTC |
f162fc2 | Richard Benkovsky | 19 May 2012, 13:14:37 UTC | Formating fixed | 22 May 2012, 07:45:38 UTC |
5652458 | Richard Benkovsky | 20 May 2012, 16:33:07 UTC | BoundedMemoryCache.put fails when estimated size of 'value' is larger than cache capacity | 20 May 2012, 20:13:35 UTC |
822a4be | Richard Benkovsky | 19 May 2012, 13:13:20 UTC | Utils.memoryBytesToString fixed | 19 May 2012, 13:13:20 UTC |
10716b1 | Matei Zaharia | 18 May 2012, 22:21:30 UTC | Merge pull request #131 from rxin/master Return size estimation, cache usage, and cache capacity from slave nodes to CacheTracker | 18 May 2012, 22:21:30 UTC |
d0c6e9f | Reynold Xin | 16 May 2012, 21:16:55 UTC | Made some RDD dependencies transient to reduce the amount of data needed to be serialized in closure serialization. This can significantly reduce the task setup time in Shark when the query involves a large number of (Hive) partitions. | 16 May 2012, 21:16:55 UTC |
16461e2 | Reynold Xin | 15 May 2012, 07:31:52 UTC | Updated Cache's put method to use a case class for response. Previously it was pretty ugly that put() should return -1 for failures. | 15 May 2012, 07:31:52 UTC |
019e488 | Reynold Xin | 15 May 2012, 01:39:04 UTC | Added the capacity to report cache usage status back to the cache trackor. This is essential for building a dashboard to see the status of caches on all slaves. | 15 May 2012, 01:39:04 UTC |
f487426 | Matei Zaharia | 07 May 2012, 03:14:40 UTC | Made caches dataset-aware so that they won't cyclically evict partitions from the same dataset. | 07 May 2012, 03:14:40 UTC |
bd2ab63 | Matei Zaharia | 06 May 2012, 03:05:15 UTC | Fixed the way the JAR server is created after finding issue at Twitter | 06 May 2012, 03:05:15 UTC |
32a4f46 | Matei Zaharia | 24 April 2012, 23:18:39 UTC | Merge pull request #129 from mesos/rxin Force serialize/deserialize task results in local execution mode. | 24 April 2012, 23:18:39 UTC |
0b70dae | Matei Zaharia | 24 April 2012, 23:18:02 UTC | Merge pull request #127 from alupher/master End task instead of just exiting in LocalScheduler for tasks that throw exceptions | 24 April 2012, 23:18:02 UTC |
761ea65 | Reynold Xin | 24 April 2012, 22:14:35 UTC | Added a test for the previous commit (failing to serialize task results would throw an exception for local tasks). | 24 April 2012, 22:14:35 UTC |
9821cd4 | Reynold Xin | 24 April 2012, 21:55:28 UTC | Force serialize/deserialize task results in local execution mode. | 24 April 2012, 21:55:28 UTC |
3e48818 | Antonio | 23 April 2012, 18:42:58 UTC | Removed commented-out System.exit call | 23 April 2012, 18:42:58 UTC |
39d9916 | Antonio | 20 April 2012, 21:46:43 UTC | Added exception handling instead of just exiting in LocalScheduler for tasks that throw exceptions | 20 April 2012, 21:46:43 UTC |
f709b3a | Matei Zaharia | 20 April 2012, 19:58:26 UTC | Merge pull request #124 from mesos/rxin Added the ability to set environmental variables in piped rdd. | 20 April 2012, 19:58:26 UTC |
e601b3b | Reynold Xin | 17 April 2012, 23:40:56 UTC | Added the ability to set environmental variables in piped rdd. | 17 April 2012, 23:40:56 UTC |
3b74517 | Matei Zaharia | 12 April 2012, 17:53:02 UTC | Bug fix to pluggable closure serialization change | 12 April 2012, 17:53:02 UTC |
112655f | Matei Zaharia | 10 April 2012, 21:21:02 UTC | Merge pull request #121 from rxin/kryo-closure Added an option (spark.closure.serializer) to specify the serializer for closures. | 10 April 2012, 21:21:02 UTC |
d295ccb | Reynold Xin | 10 April 2012, 20:29:46 UTC | Added a closureSerializer field in SparkEnv and use it to serialize tasks. | 10 April 2012, 20:29:46 UTC |
968f75f | Reynold Xin | 10 April 2012, 04:59:56 UTC | Added an option (spark.closure.serializer) to specify the serializer for closures. This enables using Kryo as the closure serializer. | 10 April 2012, 04:59:56 UTC |
a69c073 | Matei Zaharia | 09 April 2012, 06:41:36 UTC | Merge branch 'master' into mesos-0.9 | 09 April 2012, 06:41:36 UTC |
a633974 | Matei Zaharia | 09 April 2012, 06:41:25 UTC | Merge branch 'master' of github.com:mesos/spark | 09 April 2012, 06:41:25 UTC |
0229d53 | Matei Zaharia | 09 April 2012, 06:39:37 UTC | Merge branch 'master' into mesos-0.9 | 09 April 2012, 06:39:37 UTC |
d401e1b | Matei Zaharia | 09 April 2012, 06:38:49 UTC | Fix a possible deadlock in MesosScheduler | 09 April 2012, 06:38:49 UTC |
a7d6ffc | Matei Zaharia | 06 April 2012, 22:59:29 UTC | Merge pull request #119 from mesos/report-cache-events Report entry dropping in BoundedMemoryCache | 06 April 2012, 22:59:29 UTC |
7be1c7b | Ankur Dave | 06 April 2012, 22:48:36 UTC | Report entry dropping in BoundedMemoryCache | 06 April 2012, 22:49:32 UTC |
a8bb324 | Matei Zaharia | 05 April 2012, 21:53:22 UTC | Merge branch 'master' into mesos-0.9 | 05 April 2012, 21:53:22 UTC |
816d4e5 | Matei Zaharia | 05 April 2012, 21:53:17 UTC | Pass local IP address instead of hostname in spark.master.host. Fixes #117. | 05 April 2012, 21:53:17 UTC |
335a603 | Matei Zaharia | 05 April 2012, 18:57:41 UTC | Converted some tabs to spaces | 05 April 2012, 18:58:01 UTC |
acaf99c | Matei Zaharia | 30 March 2012, 17:39:47 UTC | Merge branch 'master' into mesos-0.9 | 30 March 2012, 17:39:47 UTC |
8c95a85 | Matei Zaharia | 30 March 2012, 17:38:19 UTC | Use Runtime.maxMemory instead of Runtime.totalMemory in BoundedMemoryCache, in case the JVM was not started with its initial heap size equaling its maximum one (-Xms == -Xmx). | 30 March 2012, 17:39:35 UTC |
03d5b3b | Matei Zaharia | 30 March 2012, 17:38:19 UTC | Use Runtime.maxMemory instead of Runtime.totalMemory in BoundedMemoryCache, in case the JVM was not started with its initial heap size equaling its maximum one (-Xms == -Xmx). | 30 March 2012, 17:38:19 UTC |
95fb1a1 | Matei Zaharia | 30 March 2012, 15:38:49 UTC | Use Mesos 0.9 RC3 JAR and protobuf 2.4.1 | 30 March 2012, 15:38:49 UTC |
dfa3b6b | Matei Zaharia | 30 March 2012, 02:12:35 UTC | Fixes to work with the very latest Mesos 0.9 API | 30 March 2012, 02:12:35 UTC |
4d52cc6 | Matei Zaharia | 30 March 2012, 01:29:39 UTC | Merge branch 'master' into mesos-0.9 | 30 March 2012, 01:29:39 UTC |
d46f662 | Reynold Xin | 29 March 2012, 22:22:17 UTC | Merge branch 'master' of github.com:mesos/spark | 29 March 2012, 22:22:17 UTC |
42dcdbc | Reynold Xin | 29 March 2012, 22:21:57 UTC | Removed the extra spaces in OrderedRDDFunctions and SortedRDD. | 29 March 2012, 22:21:57 UTC |
ca5c19c | Matei Zaharia | 29 March 2012, 05:03:34 UTC | Remove dependency on Akka | 29 March 2012, 05:03:34 UTC |
90418b7 | Reynold Xin | 23 March 2012, 01:46:31 UTC | Added sbt-assembly for spark-repl project so we can generate an assembled jar for Shark. | 23 March 2012, 01:46:31 UTC |
ca64a7a | Matei Zaharia | 17 March 2012, 20:51:29 UTC | Documentation | 17 March 2012, 20:51:29 UTC |
36c7db7 | Matei Zaharia | 17 March 2012, 20:49:55 UTC | Documentation | 17 March 2012, 20:49:55 UTC |
08cda89 | Matei Zaharia | 17 March 2012, 20:39:14 UTC | Further fixes to how Mesos is found and used | 17 March 2012, 20:39:14 UTC |
3c3fdf6 | Matei Zaharia | 17 March 2012, 20:09:21 UTC | Merge branch 'master' into mesos-0.9 | 17 March 2012, 20:09:21 UTC |
c7af538 | Matei Zaharia | 17 March 2012, 20:08:36 UTC | Some fixes to sorting for when the RDD has fewer elements than the number of partitions we ask to partition it into. Also, removed a test that was taking way too long to run. | 17 March 2012, 20:08:36 UTC |
a099a63 | Matei Zaharia | 17 March 2012, 19:31:34 UTC | Initial work to make Spark compile with Mesos 0.9 and Hadoop 1.0 | 17 March 2012, 19:31:34 UTC |
a5e2b6a | Matei Zaharia | 06 March 2012, 21:38:32 UTC | Merge pull request #112 from cengle/master Changed HadoopRDD to get key and value containers from the RecordReader instead of through reflection | 06 March 2012, 21:38:32 UTC |
97eee50 | Matei Zaharia | 01 March 2012, 21:43:17 UTC | Fixes a nasty bug that could happen when tasks fail, because calling wait() with a timeout of 0 on a Java object means "wait forever". | 01 March 2012, 21:43:17 UTC |
dd68cb6 | Cliff Engle | 01 March 2012, 00:33:23 UTC | Get key and value container from RecordReader | 01 March 2012, 00:33:23 UTC |
1e10df0 | Matei Zaharia | 24 February 2012, 23:50:14 UTC | Merge pull request #111 from alupher/master Adding sorting to RDDs | 24 February 2012, 23:50:14 UTC |
0d93d95 | Antonio | 22 February 2012, 03:57:12 UTC | Removed unnecessary import | 22 February 2012, 03:57:12 UTC |
2990298 | Antonio | 22 February 2012, 03:54:21 UTC | Added sorting testing suite | 22 February 2012, 03:54:21 UTC |
aa04f87 | Matei Zaharia | 20 February 2012, 06:50:23 UTC | Added support for parallel execution of jobs in DAGScheduler. | 20 February 2012, 06:50:23 UTC |
6207981 | Antonio | 13 February 2012, 08:07:39 UTC | Added fixes to sorting | 13 February 2012, 08:07:39 UTC |
2587ce1 | Matei Zaharia | 12 February 2012, 05:22:45 UTC | Fixed a deadlock that occured with MesosScheduler due to an earlier synchronization change | 12 February 2012, 05:22:45 UTC |
e93f622 | Antonio | 11 February 2012, 08:56:28 UTC | Added sorting by key for pair RDDs | 11 February 2012, 08:56:28 UTC |
98f008b | Matei Zaharia | 10 February 2012, 18:52:03 UTC | Formatting fixes | 10 February 2012, 18:52:03 UTC |
7660a8b | Matei Zaharia | 10 February 2012, 18:42:14 UTC | Merge branch 'formatting' Conflicts: core/src/main/scala/spark/DAGScheduler.scala core/src/main/scala/spark/SimpleShuffleFetcher.scala core/src/main/scala/spark/SparkContext.scala | 10 February 2012, 18:42:14 UTC |
194c42a | haoyuan | 10 February 2012, 16:19:53 UTC | Code format. | 10 February 2012, 16:19:53 UTC |
8f5ed51 | Matei Zaharia | 10 February 2012, 06:58:24 UTC | Delete Spark's temporary directories when the JVM exits. | 10 February 2012, 06:58:24 UTC |
c0a0df3 | Matei Zaharia | 10 February 2012, 06:32:02 UTC | Made the default cache BoundedMemoryCache, and reduced its default size | 10 February 2012, 06:32:02 UTC |
a766780 | Matei Zaharia | 10 February 2012, 06:27:53 UTC | Added some tests for multithreaded access to Spark. | 10 February 2012, 06:27:53 UTC |
0e93891 | Matei Zaharia | 10 February 2012, 06:14:19 UTC | Replaced LocalFileShuffle with a non-singleton ShuffleManager class and made DAGScheduler automatically set SparkEnv. | 10 February 2012, 06:14:56 UTC |
445e0bb | haoyuan | 09 February 2012, 23:50:26 UTC | Format the code a bit mroe. | 09 February 2012, 23:50:26 UTC |
651932e | haoyuan | 09 February 2012, 21:26:23 UTC | Format the code as coding style agreed by Matei/TD/Haoyuan | 09 February 2012, 21:26:23 UTC |
e02dc83 | Matei Zaharia | 07 February 2012, 04:40:39 UTC | IO optimizations | 07 February 2012, 04:40:39 UTC |
c40e766 | Matei Zaharia | 07 February 2012, 03:20:25 UTC | Use java.util.HashMap in shuffles | 07 February 2012, 03:20:25 UTC |
d6ec664 | Matei Zaharia | 06 February 2012, 23:37:27 UTC | Add dependency on fastutil and update Guava | 06 February 2012, 23:37:27 UTC |
b267175 | Matei Zaharia | 06 February 2012, 22:28:18 UTC | Synchronization fix in case SparkContext is used from multiple threads. | 06 February 2012, 22:28:18 UTC |
b72d93a | haoyuan | 06 February 2012, 17:58:06 UTC | Test commit | 06 February 2012, 17:58:06 UTC |
43a3335 | Matei Zaharia | 06 February 2012, 06:46:51 UTC | Simplifying test | 06 February 2012, 06:46:51 UTC |
7449ecf | Matei Zaharia | 31 January 2012, 08:33:24 UTC | Merge branch 'master' of github.com:mesos/spark | 31 January 2012, 08:33:24 UTC |
100e800 | Matei Zaharia | 31 January 2012, 08:33:18 UTC | Some fixes to the examples (mostly to use functional API) | 31 January 2012, 08:33:18 UTC |
72d2489 | Matei Zaharia | 31 January 2012, 00:31:12 UTC | Merge pull request #108 from patelh/master Added immutable map registration in kryo serializer | 31 January 2012, 00:31:12 UTC |