Commit message (Collapse) | Author | Age | Files | Lines | |
---|---|---|---|---|---|
* | Adding Sonatype releases to SBT. | Patrick Wendell | 2012-10-07 | 1 | -0/+0 |
| | | | | | | | | | | This does a few things to get this branch ready for release: 1. Upgrades the sbt and Scala version 2. Sets the release number to 0.5.1 3. Adds the Sonatype publishing target 4. Installs the PGP signing plugin 5. Removes the Mesos jar dependency | ||||
* | Make reduce logging less verbose | Matei Zaharia | 2012-10-06 | 1 | -3/+4 |
| | |||||
* | Merge branch 'master' into reduce-logging | Matei Zaharia | 2012-10-05 | 3 | -13/+30 |
|\ | |||||
| * | Merge branch 'master' of github.com:mesos/spark | Matei Zaharia | 2012-10-05 | 2 | -12/+29 |
| |\ | |||||
| | * | Fix SizeEstimator tests to work with String classes in JDK 6 and 7 | Shivaram Venkataraman | 2012-10-04 | 2 | -12/+29 |
| | | | |||||
| * | | Only group elements ten at a time into SequenceFile records in | Matei Zaharia | 2012-10-04 | 1 | -1/+1 |
| |/ | | | | | | | saveAsObjectFile | ||||
* | | Let the reducer retry if a fetch fails before reading all records | Matei Zaharia | 2012-10-04 | 3 | -22/+43 |
| | | |||||
* | | Add more logging for number of records fetched by each reduce | Matei Zaharia | 2012-10-04 | 1 | -1/+6 |
|/ | |||||
* | Backport sampling fixes from dev (suggested by Henry Milner) | Matei Zaharia | 2012-09-29 | 4 | -42/+51 |
| | |||||
* | Make error reporting less scary if we can't look up UseCompressedOops | Matei Zaharia | 2012-09-28 | 1 | -10/+6 |
| | |||||
* | Look for Kryo registrator using context class loader | Matei Zaharia | 2012-09-26 | 1 | -1/+2 |
| | |||||
* | Fixed GrowableAccumulatorParam.zero() to do a copy and to make sure it's | Matei Zaharia | 2012-09-11 | 1 | -3/+13 |
| | | | | empty instead of using the old initialValue | ||||
* | Merge branch 'master' into collection_accumulators | Imran Rashid | 2012-09-11 | 4 | -6/+33 |
|\ | | | | | | | | | Conflicts: core/src/test/scala/spark/AccumulatorSuite.scala | ||||
| * | End runJob with a SparkException when a Mesos task fails too many times | Matei Zaharia | 2012-08-31 | 2 | -0/+4 |
| | | |||||
| * | change tests to show utility of localValue | Imran Rashid | 2012-08-20 | 2 | -4/+5 |
| | | |||||
| * | make accumulator.localValue public, add tests | Imran Rashid | 2012-08-14 | 2 | -1/+24 |
| | | |||||
* | | fix stupid typo and add documentation | Imran Rashid | 2012-09-07 | 1 | -1/+7 |
| | | |||||
* | | add accumulators for mutable collections, with correct typing! | Imran Rashid | 2012-08-17 | 3 | -5/+46 |
|/ | |||||
* | Add test-cases for 32-bit and no-compressed oops scenarios. | Shivaram Venkataraman | 2012-08-12 | 2 | -14/+46 |
| | |||||
* | Move object size and pointer size initialization into a function to enable ↵ | Shivaram Venkataraman | 2012-08-12 | 1 | -21/+31 |
| | | | | unit-testing | ||||
* | Update test cases to match the new size estimates. Uses 64-bit and compressed | Shivaram Venkataraman | 2012-08-11 | 2 | -35/+77 |
| | | | | oops setting to get deterministic results | ||||
* | If spark.test.useCompressedOops is set, use that to infer compressed oops | Shivaram Venkataraman | 2012-08-11 | 1 | -0/+3 |
| | | | | setting. This is useful to get a deterministic test case | ||||
* | Use HotSpotDiagnosticMXBean to get if CompressedOops are in use or not | Shivaram Venkataraman | 2012-08-11 | 1 | -3/+28 |
| | |||||
* | Add link to Java wiki which specifies what changes with compressed oops | Shivaram Venkataraman | 2012-08-11 | 1 | -0/+3 |
| | |||||
* | Changes to make size estimator more accurate. Fixes object size, pointer size | Shivaram Venkataraman | 2012-08-11 | 1 | -4/+38 |
| | | | | | according to architecture and also aligns objects and arrays when computing instance sizes. Verified using Eclipse Memory Analysis Tool (MAT) | ||||
* | Made range partition balance tests more aggressive. | Matei Zaharia | 2012-08-03 | 1 | -8/+8 |
| | | | | | | This is because we pull out such a large sample (10x the number of partitions) that we should expect pretty good balance. The tests are also deterministic so there's no worry about them failing irreproducibly. | ||||
* | Added a unit test for cross-partition balancing in sort, and changes to | Matei Zaharia | 2012-08-03 | 3 | -41/+84 |
| | | | | | RangePartitioner to make it pass. It turns out that the first partition was always kind of small due to how we picked partition boundaries. | ||||
* | Fix to #154 (CacheTracker trying to cast a broadcast variable's ID to int) | Matei Zaharia | 2012-08-03 | 1 | -3/+4 |
| | |||||
* | Fix for partitioning when sorting in descending order | Harvey | 2012-08-03 | 1 | -2/+1 |
| | |||||
* | Logging Throwables in Info and Debug | Paul Cavallaro | 2012-07-30 | 1 | -2/+2 |
| | | | | Logging Throwables in logInfo and logDebug instead of swallowing them. | ||||
* | Merge pull request #145 from squito/exp_accum | Matei Zaharia | 2012-07-26 | 4 | -13/+277 |
|\ | | | | | add Accumulatable, add corresponding docs & tests for accumulators | ||||
| * | tasks cannot access value of accumulator | Imran Rashid | 2012-07-26 | 2 | -56/+21 |
| | | |||||
| * | one more minor cleanup to scaladoc | Imran Rashid | 2012-07-16 | 1 | -2/+2 |
| | | |||||
| * | fix up scaladoc, naming of type parameters | Imran Rashid | 2012-07-16 | 2 | -15/+12 |
| | | |||||
| * | rename addToAccum to addAccumulator | Imran Rashid | 2012-07-16 | 2 | -4/+4 |
| | | |||||
| * | add some functionality to Vector, delete copy in AccumulatorSuite | Imran Rashid | 2012-07-12 | 2 | -113/+33 |
| | | |||||
| * | move Vector class into core and spark.util package | Imran Rashid | 2012-07-12 | 1 | -0/+84 |
| | | |||||
| * | Accumulator now inherits from Accumulable, whcih simplifies a bunch of other ↵ | Imran Rashid | 2012-07-12 | 3 | -34/+56 |
| | | | | | | | | things (eg., no +:=) | ||||
| * | improve scaladoc | Imran Rashid | 2012-07-12 | 1 | -1/+1 |
| | | |||||
| * | add Accumulatable, add corresponding docs & tests for accumulators | Imran Rashid | 2012-07-12 | 3 | -0/+276 |
| | | |||||
* | | Merge pull request #152 from dennybritz/fix/testbeforeafter | Matei Zaharia | 2012-07-23 | 12 | -109/+153 |
|\ \ | | | | | | | Always destroy SparkContext in after block for the unit tests. | ||||
| * | | Stlystic changes | Denny | 2012-07-23 | 11 | -22/+22 |
| | | | |||||
| * | | Always destroy SparkContext in after block for the unit tests. | Denny | 2012-07-18 | 10 | -107/+151 |
| |/ | |||||
* | | Merge branch 'master' of github.com:mesos/spark | Matei Zaharia | 2012-07-21 | 2 | -6/+6 |
|\ \ | |||||
| * \ | Merge pull request #149 from dennybritz/serfix | Matei Zaharia | 2012-07-21 | 2 | -6/+6 |
| |\ \ | | | | | | | | | Instantiating custom serializer using user's classpath | ||||
| | * | | Create the ClassLoader before creating a SparkEnv - SparkEnv must use the ↵ | Denny | 2012-07-17 | 1 | -5/+5 |
| | | | | | | | | | | | | | | | | loader. | ||||
| | * | | Use Context classloader for Serializer class | Denny | 2012-07-17 | 1 | -1/+1 |
| | |/ | |||||
* | | | Fix a bug where an input path was added to a Hadoop job configuration twice | Matei Zaharia | 2012-07-21 | 1 | -4/+1 |
| | | | |||||
* | | | Use full package name in import | Matei Zaharia | 2012-07-21 | 1 | -1/+1 |
|/ / | |||||
* | | Merge branch 'master' of github.com:mesos/spark | Matei Zaharia | 2012-07-12 | 2 | -5/+31 |
|\| |