Author: Aaron Staple <astaple@gmail.com>
Closes#1630 from staple/minor and squashes the following commits:
6f295a2 [Aaron Staple] Fix typos in comment about ExprId.
8566467 [Aaron Staple] Fix off by one column indentation in SqlParser.
In `reduce` and `aggregate`, the driver node spends linear time on the number of partitions. It becomes a bottleneck when there are many partitions and the data from each partition is big.
SPARK-1485 (#506) tracks the progress of implementing AllReduce on Spark. I did several implementations including butterfly, reduce + broadcast, and treeReduce + broadcast. treeReduce + BT broadcast seems to be right way to go for Spark. Using binary tree may introduce some overhead in communication, because the driver still need to coordinate on data shuffling. In my experiments, n -> sqrt(n) -> 1 gives the best performance in general, which is why I set "depth = 2" in MLlib algorithms. But it certainly needs more testing.
I left `treeReduce` and `treeAggregate` public for easy testing. Some numbers from a test on 32-node m3.2xlarge cluster.
code:
~~~
import breeze.linalg._
import org.apache.log4j._
Logger.getRootLogger.setLevel(Level.OFF)
for (n <- Seq(1, 10, 100, 1000, 10000, 100000, 1000000)) {
val vv = sc.parallelize(0 until 1024, 1024).map(i => DenseVector.zeros[Double](n))
var start = System.nanoTime(); vv.treeReduce(_ + _, 2); println((System.nanoTime() - start) / 1e9)
start = System.nanoTime(); vv.reduce(_ + _); println((System.nanoTime() - start) / 1e9)
}
~~~
out:
| n | treeReduce(,2) | reduce |
|---|---------------------|-----------|
| 10 | 0.215538731 | 0.204206899 |
| 100 | 0.278405907 | 0.205732582 |
| 1000 | 0.208972182 | 0.214298272 |
| 10000 | 0.194792071 | 0.349353687 |
| 100000 | 0.347683285 | 6.086671892 |
| 1000000 | 2.589350682 | 66.572906702 |
CC: @pwendell
This is clearly more scalable than the default implementation. My question is whether we should use this implementation in `reduce` and `aggregate` or put them as separate methods. The concern is that users may use `reduce` and `aggregate` as collect, where having multiple stages doesn't reduce the data size. However, in this case, `collect` is more appropriate.
Author: Xiangrui Meng <meng@databricks.com>
Closes#1110 from mengxr/tree and squashes the following commits:
c6cd267 [Xiangrui Meng] make depth default to 2
b04b96a [Xiangrui Meng] address comments
9bcc5d3 [Xiangrui Meng] add depth for readability
7495681 [Xiangrui Meng] fix compile error
142a857 [Xiangrui Meng] merge master
d58a087 [Xiangrui Meng] move treeReduce and treeAggregate to mllib
8a2a59c [Xiangrui Meng] Merge branch 'master' into tree
be6a88a [Xiangrui Meng] use treeAggregate in mllib
0f94490 [Xiangrui Meng] add docs
eb71c33 [Xiangrui Meng] add treeReduce
fe42a5e [Xiangrui Meng] add treeAggregate
The pull request includes two changes:
1. Removes SortOrder introduced by SPARK-2125. The key ordering already includes the SortOrder information since an Ordering can be reverse. This is similar to Java's Comparator interface. Rarely does an API accept both a Comparator as well as a SortOrder.
2. Replaces the sortWith call in HashShuffleReader with an in-place quick sort.
Author: Reynold Xin <rxin@apache.org>
Closes#1631 from rxin/sortOrder and squashes the following commits:
c9d37e1 [Reynold Xin] [SPARK-2726] and [SPARK-2727] Remove SortOrder and do in-place sort.
fix the problem with pickle operator.itemgetter with multiple index.
Author: Davies Liu <davies.liu@gmail.com>
Closes#1627 from davies/itemgetter and squashes the following commits:
aabd7fa [Davies Liu] fix pickle itemgetter with cloudpickle
During rdd.take(n), JVM will close the socket if it had got enough data, the Python worker should keep silent in this case.
In the same time, the worker should not print the trackback into stderr if it send the traceback to JVM successfully.
Author: Davies Liu <davies.liu@gmail.com>
Closes#1625 from davies/error and squashes the following commits:
4fbcc6d [Davies Liu] disable log4j during testing when exception is expected.
cc14202 [Davies Liu] keep silent in worker if JVM close the socket
Author: Yadong Qi <qiyadong2010@gmail.com>
Closes#1629 from watermen/bug-fix2 and squashes the following commits:
59b7237 [Yadong Qi] Update HiveQl.scala
Spark only transitively depends on the latter, based on the Hadoop version.
Author: Aaron Davidson <aaron@databricks.com>
Closes#1621 from aarondav/lang3 and squashes the following commits:
93c93bf [Aaron Davidson] Use commons-lang3 in SignalLogger rather than commons-lang
JIRA issue: [SPARK-2410](https://issues.apache.org/jira/browse/SPARK-2410)
Another try for #1399 & #1600. Those two PR breaks Jenkins builds because we made a separate profile `hive-thriftserver` in sub-project `assembly`, but the `hive-thriftserver` module is defined outside the `hive-thriftserver` profile. Thus every time a pull request that doesn't touch SQL code will also execute test suites defined in `hive-thriftserver`, but tests fail because related .class files are not included in the assembly jar.
In the most recent commit, module `hive-thriftserver` is moved into its own profile to fix this problem. All previous commits are squashed for clarity.
Author: Cheng Lian <lian.cs.zju@gmail.com>
Closes#1620 from liancheng/jdbc-with-maven-fix and squashes the following commits:
629988e [Cheng Lian] Moved hive-thriftserver module definition into its own profile
ec3c7a7 [Cheng Lian] Cherry picked the Hive Thrift server
Floating point math is not exact, and most floating-point numbers end up being slightly imprecise due to rounding errors.
Simple values like 0.1 cannot be precisely represented using binary floating point numbers, and the limited precision of floating point numbers means that slight changes in the order of operations or the precision of intermediates can change the result.
That means that comparing two floats to see if they are equal is usually not what we want. As long as this imprecision stays small, it can usually be ignored.
Based on discussion in the community, we have implemented two different APIs for relative tolerance, and absolute tolerance. It makes sense that test writers should know which one they need depending on their circumstances.
Developers also need to explicitly specify the eps, and there is no default value which will sometimes cause confusion.
When comparing against zero using relative tolerance, a exception will be raised to warn users that it's meaningless.
For relative tolerance, users can now write
assert(23.1 ~== 23.52 relTol 0.02)
assert(23.1 ~== 22.74 relTol 0.02)
assert(23.1 ~= 23.52 relTol 0.02)
assert(23.1 ~= 22.74 relTol 0.02)
assert(!(23.1 !~= 23.52 relTol 0.02))
assert(!(23.1 !~= 22.74 relTol 0.02))
// This will throw exception with the following message.
// "Did not expect 23.1 and 23.52 to be within 0.02 using relative tolerance."
assert(23.1 !~== 23.52 relTol 0.02)
// "Expected 23.1 and 22.34 to be within 0.02 using relative tolerance."
assert(23.1 ~== 22.34 relTol 0.02)
For absolute error,
assert(17.8 ~== 17.99 absTol 0.2)
assert(17.8 ~== 17.61 absTol 0.2)
assert(17.8 ~= 17.99 absTol 0.2)
assert(17.8 ~= 17.61 absTol 0.2)
assert(!(17.8 !~= 17.99 absTol 0.2))
assert(!(17.8 !~= 17.61 absTol 0.2))
// This will throw exception with the following message.
// "Did not expect 17.8 and 17.99 to be within 0.2 using absolute error."
assert(17.8 !~== 17.99 absTol 0.2)
// "Expected 17.8 and 17.59 to be within 0.2 using absolute error."
assert(17.8 ~== 17.59 absTol 0.2)
Authors:
DB Tsai <dbtsaialpinenow.com>
Marek Kolodziej <marekalpinenow.com>
Author: DB Tsai <dbtsai@alpinenow.com>
Closes#1425 from dbtsai/SPARK-2479_comparing_floating_point and squashes the following commits:
8c7cbcc [DB Tsai] Alpine Data Labs
In HiveTableScan.scala, ObjectInspector was created for all of the partition based records, which probably causes ClassCastException if the object inspector is not identical among table & partitions.
This is the follow up with:
https://github.com/apache/spark/pull/1408https://github.com/apache/spark/pull/1390
I've run a micro benchmark in my local with 15000000 records totally, and got the result as below:
With This Patch | Partition-Based Table | Non-Partition-Based Table
------------ | ------------- | -------------
No | 1927 ms | 1885 ms
Yes | 1541 ms | 1524 ms
It showed this patch will also improve the performance.
PS: the benchmark code is also attached. (thanks liancheng )
```
package org.apache.spark.sql.hive
import org.apache.spark.SparkContext
import org.apache.spark.SparkConf
import org.apache.spark.sql._
object HiveTableScanPrepare extends App {
case class Record(key: String, value: String)
val sparkContext = new SparkContext(
new SparkConf()
.setMaster("local")
.setAppName(getClass.getSimpleName.stripSuffix("$")))
val hiveContext = new LocalHiveContext(sparkContext)
val rdd = sparkContext.parallelize((1 to 3000000).map(i => Record(s"$i", s"val_$i")))
import hiveContext._
hql("SHOW TABLES")
hql("DROP TABLE if exists part_scan_test")
hql("DROP TABLE if exists scan_test")
hql("DROP TABLE if exists records")
rdd.registerAsTable("records")
hql("""CREATE TABLE part_scan_test (key STRING, value STRING) PARTITIONED BY (part1 string, part2 STRING)
| ROW FORMAT SERDE
| 'org.apache.hadoop.hive.serde2.columnar.LazyBinaryColumnarSerDe'
| STORED AS RCFILE
""".stripMargin)
hql("""CREATE TABLE scan_test (key STRING, value STRING)
| ROW FORMAT SERDE
| 'org.apache.hadoop.hive.serde2.columnar.LazyBinaryColumnarSerDe'
| STORED AS RCFILE
""".stripMargin)
for (part1 <- 2000 until 2001) {
for (part2 <- 1 to 5) {
hql(s"""from records
| insert into table part_scan_test PARTITION (part1='$part1', part2='2010-01-$part2')
| select key, value
""".stripMargin)
hql(s"""from records
| insert into table scan_test select key, value
""".stripMargin)
}
}
}
object HiveTableScanTest extends App {
val sparkContext = new SparkContext(
new SparkConf()
.setMaster("local")
.setAppName(getClass.getSimpleName.stripSuffix("$")))
val hiveContext = new LocalHiveContext(sparkContext)
import hiveContext._
hql("SHOW TABLES")
val part_scan_test = hql("select key, value from part_scan_test")
val scan_test = hql("select key, value from scan_test")
val r_part_scan_test = (0 to 5).map(i => benchmark(part_scan_test))
val r_scan_test = (0 to 5).map(i => benchmark(scan_test))
println("Scanning Partition-Based Table")
r_part_scan_test.foreach(printResult)
println("Scanning Non-Partition-Based Table")
r_scan_test.foreach(printResult)
def printResult(result: (Long, Long)) {
println(s"Duration: ${result._1} ms Result: ${result._2}")
}
def benchmark(srdd: SchemaRDD) = {
val begin = System.currentTimeMillis()
val result = srdd.count()
val end = System.currentTimeMillis()
((end - begin), result)
}
}
```
Author: Cheng Hao <hao.cheng@intel.com>
Closes#1439 from chenghao-intel/hadoop_table_scan and squashes the following commits:
888968f [Cheng Hao] Fix issues in code style
27540ba [Cheng Hao] Fix the TableScan Bug while partition serde differs
40a24a7 [Cheng Hao] Add Unit Test
This addresses a PySpark issue where a failed attempt to construct SparkContext would prevent any future SparkContext creation.
Author: Josh Rosen <joshrosen@apache.org>
Closes#1606 from JoshRosen/SPARK-1550 and squashes the following commits:
ec7fadc [Josh Rosen] [SPARK-1550] [PySpark] Allow SparkContext creation after failed attempts
Can be run as: "mvn scalastyle:check"
Author: Rahul Singhal <rahul.singhal@guavus.com>
Closes#1550 from rahulsinghaliitd/SPARK-2651 and squashes the following commits:
53748dd [Rahul Singhal] SPARK-2651: Add maven scalastyle plugin
Utilities for generating random RDDs.
RandomRDD and RandomVectorRDD are created instead of using `sc.parallelize(range:Range)` because `Range` objects in Scala can only have `size <= Int.MaxValue`.
The object `RandomRDDGenerators` can be transformed into a generator class to reduce the number of auxiliary methods for optional arguments.
Author: Doris Xin <doris.s.xin@gmail.com>
Closes#1520 from dorx/randomRDD and squashes the following commits:
01121ac [Doris Xin] reviewer comments
6bf27d8 [Doris Xin] Merge branch 'master' into randomRDD
a8ea92d [Doris Xin] Reviewer comments
063ea0b [Doris Xin] Merge branch 'master' into randomRDD
aec68eb [Doris Xin] newline
bc90234 [Doris Xin] units passed.
d56cacb [Doris Xin] impl with RandomRDD
92d6f1c [Doris Xin] solution for Cloneable
df5bcff [Doris Xin] Merge branch 'generator' into randomRDD
f46d928 [Doris Xin] WIP
49ed20d [Doris Xin] alternative poisson distribution generator
7cb0e40 [Doris Xin] fix for data inconsistency
8881444 [Doris Xin] RandomRDDGenerator: initial design
**Problem.** When caching, we currently unroll the entire RDD partition before making sure we have enough free memory. This is a common cause for OOMs especially when (1) the BlockManager has little free space left in memory, and (2) the partition is large.
**Solution.** We maintain a global memory pool of `M` bytes shared across all threads, similar to the way we currently manage memory for shuffle aggregation. Then, while we unroll each partition, periodically check if there is enough space to continue. If not, drop enough RDD blocks to ensure we have at least `M` bytes to work with, then try again. If we still don't have enough space to unroll the partition, give up and drop the block to disk directly if applicable.
**New configurations.**
- `spark.storage.bufferFraction` - the value of `M` as a fraction of the storage memory. (default: 0.2)
- `spark.storage.safetyFraction` - a margin of safety in case size estimation is slightly off. This is the equivalent of the existing `spark.shuffle.safetyFraction`. (default 0.9)
For more detail, see the [design document](https://issues.apache.org/jira/secure/attachment/12651793/spark-1777-design-doc.pdf). Tests pending for performance and memory usage patterns.
Author: Andrew Or <andrewor14@gmail.com>
Closes#1165 from andrewor14/them-rdd-memories and squashes the following commits:
e77f451 [Andrew Or] Merge branch 'master' of github.com:apache/spark into them-rdd-memories
c7c8832 [Andrew Or] Simplify logic + update a few comments
269d07b [Andrew Or] Very minor changes to tests
6645a8a [Andrew Or] Merge branch 'master' of github.com:apache/spark into them-rdd-memories
b7e165c [Andrew Or] Add new tests for unrolling blocks
f12916d [Andrew Or] Slightly clean up tests
71672a7 [Andrew Or] Update unrollSafely tests
369ad07 [Andrew Or] Correct ensureFreeSpace and requestMemory behavior
f4d035c [Andrew Or] Allow one thread to unroll multiple blocks
a66fbd2 [Andrew Or] Rename a few things + update comments
68730b3 [Andrew Or] Fix weird scalatest behavior
e40c60d [Andrew Or] Fix MIMA excludes
ff77aa1 [Andrew Or] Fix tests
1a43c06 [Andrew Or] Merge branch 'master' of github.com:apache/spark into them-rdd-memories
b9a6eee [Andrew Or] Simplify locking behavior on unrollMemoryMap
ed6cda4 [Andrew Or] Formatting fix (super minor)
f9ff82e [Andrew Or] putValues -> putIterator + putArray
beb368f [Andrew Or] Merge branch 'master' of github.com:apache/spark into them-rdd-memories
8448c9b [Andrew Or] Fix tests
a49ba4d [Andrew Or] Do not expose unroll memory check period
69bc0a5 [Andrew Or] Always synchronize on putLock before unrollMemoryMap
3f5a083 [Andrew Or] Simplify signature of ensureFreeSpace
dce55c8 [Andrew Or] Merge branch 'master' of github.com:apache/spark into them-rdd-memories
8288228 [Andrew Or] Synchronize put and unroll properly
4f18a3d [Andrew Or] bufferFraction -> unrollFraction
28edfa3 [Andrew Or] Update a few comments / log messages
728323b [Andrew Or] Do not synchronize every 1000 elements
5ab2329 [Andrew Or] Merge branch 'master' of github.com:apache/spark into them-rdd-memories
129c441 [Andrew Or] Fix bug: Use toArray rather than array
9a65245 [Andrew Or] Update a few comments + minor control flow changes
57f8d85 [Andrew Or] Merge branch 'master' of github.com:apache/spark into them-rdd-memories
abeae4f [Andrew Or] Add comment clarifying the MEMORY_AND_DISK case
3dd96aa [Andrew Or] AppendOnlyBuffer -> Vector (+ a few small changes)
f920531 [Andrew Or] Merge branch 'master' of github.com:apache/spark into them-rdd-memories
0871835 [Andrew Or] Add an effective storage level interface to BlockManager
64e7d4c [Andrew Or] Add/modify a few comments (minor)
8af2f35 [Andrew Or] Merge branch 'master' of github.com:apache/spark into them-rdd-memories
4f4834e [Andrew Or] Use original storage level for blocks dropped to disk
ecc8c2d [Andrew Or] Fix binary incompatibility
24185ea [Andrew Or] Avoid dropping a block back to disk if reading from disk
2b7ee66 [Andrew Or] Fix bug in SizeTracking*
9b9a273 [Andrew Or] Fix tests
20eb3e5 [Andrew Or] Merge branch 'master' of github.com:apache/spark into them-rdd-memories
649bdb3 [Andrew Or] Document spark.storage.bufferFraction
a10b0e7 [Andrew Or] Add initial memory request threshold + rename a few things
e9c3cb0 [Andrew Or] cacheMemoryMap -> unrollMemoryMap
198e374 [Andrew Or] Unfold -> unroll
0d50155 [Andrew Or] Merge branch 'master' of github.com:apache/spark into them-rdd-memories
d9d02a8 [Andrew Or] Remove unused param in unfoldSafely
ec728d8 [Andrew Or] Add tests for safe unfolding of blocks
22b2209 [Andrew Or] Merge branch 'master' of github.com:apache/spark into them-rdd-memories
078eb83 [Andrew Or] Add check for hasNext in PrimitiveVector.iterator
0871535 [Andrew Or] Fix tests in BlockManagerSuite
d68f31e [Andrew Or] Safely unfold blocks for all memory puts
5961f50 [Andrew Or] Fix tests
195abd7 [Andrew Or] Refactor: move unfold logic to MemoryStore
1e82d00 [Andrew Or] Merge branch 'master' of github.com:apache/spark into them-rdd-memories
3ce413e [Andrew Or] Merge branch 'master' of github.com:apache/spark into them-rdd-memories
d5dd3b4 [Andrew Or] Free buffer memory in finally
ea02eec [Andrew Or] Fix tests
b8e1d9c [Andrew Or] Merge branch 'master' of github.com:apache/spark into them-rdd-memories
a8704c1 [Andrew Or] Merge branch 'master' of github.com:apache/spark into them-rdd-memories
e1b8b25 [Andrew Or] Merge branch 'master' of github.com:apache/spark into them-rdd-memories
87aa75c [Andrew Or] Fix mima excludes again (typo)
11eb921 [Andrew Or] Clarify comment (minor)
50cae44 [Andrew Or] Remove now duplicate mima exclude
7de5ef9 [Andrew Or] Merge branch 'master' of github.com:apache/spark into them-rdd-memories
df47265 [Andrew Or] Fix binary incompatibility
6d05a81 [Andrew Or] Merge branch 'master' of github.com:apache/spark into them-rdd-memories
f94f5af [Andrew Or] Update a few comments (minor)
776aec9 [Andrew Or] Prevent OOM if a single RDD partition is too large
bbd3eea [Andrew Or] Fix CacheManagerSuite to use Array
97ea499 [Andrew Or] Change BlockManager interface to use Arrays
c12f093 [Andrew Or] Add SizeTrackingAppendOnlyBuffer and tests
(This is a replacement of #1399, trying to fix potential `HiveThriftServer2` port collision between parallel builds. Please refer to [these comments](https://github.com/apache/spark/pull/1399#issuecomment-50212572) for details.)
JIRA issue: [SPARK-2410](https://issues.apache.org/jira/browse/SPARK-2410)
Merging the Hive Thrift/JDBC server from [branch-1.0-jdbc](https://github.com/apache/spark/tree/branch-1.0-jdbc).
Thanks chenghao-intel for his initial contribution of the Spark SQL CLI.
Author: Cheng Lian <lian.cs.zju@gmail.com>
Closes#1600 from liancheng/jdbc and squashes the following commits:
ac4618b [Cheng Lian] Uses random port for HiveThriftServer2 to avoid collision with parallel builds
090beea [Cheng Lian] Revert changes related to SPARK-2678, decided to move them to another PR
21c6cf4 [Cheng Lian] Updated Spark SQL programming guide docs
fe0af31 [Cheng Lian] Reordered spark-submit options in spark-shell[.cmd]
199e3fb [Cheng Lian] Disabled MIMA for hive-thriftserver
1083e9d [Cheng Lian] Fixed failed test suites
7db82a1 [Cheng Lian] Fixed spark-submit application options handling logic
9cc0f06 [Cheng Lian] Starts beeline with spark-submit
cfcf461 [Cheng Lian] Updated documents and build scripts for the newly added hive-thriftserver profile
061880f [Cheng Lian] Addressed all comments by @pwendell
7755062 [Cheng Lian] Adapts test suites to spark-submit settings
40bafef [Cheng Lian] Fixed more license header issues
e214aab [Cheng Lian] Added missing license headers
b8905ba [Cheng Lian] Fixed minor issues in spark-sql and start-thriftserver.sh
f975d22 [Cheng Lian] Updated docs for Hive compatibility and Shark migration guide draft
3ad4e75 [Cheng Lian] Starts spark-sql shell with spark-submit
a5310d1 [Cheng Lian] Make HiveThriftServer2 play well with spark-submit
61f39f4 [Cheng Lian] Starts Hive Thrift server via spark-submit
2c4c539 [Cheng Lian] Cherry picked the Hive Thrift server
This will decrease object allocation from the "update" closure used in map.changeValue.
Author: Matei Zaharia <matei@databricks.com>
Closes#1607 from mateiz/spark-2684 and squashes the following commits:
b7d89e6 [Matei Zaharia] Add insertAll for Iterables too, and fix some code style
561fc97 [Matei Zaharia] Update ExternalAppendOnlyMap to take an iterator as input
Added a set of serializer/deserializer for Double in _common.py and PythonMLLibAPI in MLLib.
Author: Doris Xin <doris.s.xin@gmail.com>
Closes#1581 from dorx/doubleSerDe and squashes the following commits:
86a85b3 [Doris Xin] Merge branch 'master' into doubleSerDe
2bfe7a4 [Doris Xin] Removed magic byte
ad4d0d9 [Doris Xin] removed a space in unit
a9020bc [Doris Xin] units passed
7dad9af [Doris Xin] WIP
We saw task serialization problems with large feature dimension, which could be avoid if we don't serialize data directly into task but use broadcast variables. This PR uses broadcast in both training and prediction and adds tests to make sure the task size is small.
Author: Xiangrui Meng <meng@databricks.com>
Closes#1427 from mengxr/broadcast-new and squashes the following commits:
b9a1228 [Xiangrui Meng] style update
b97c184 [Xiangrui Meng] minimal change to LBFGS
9ebadcc [Xiangrui Meng] add task size test to RowMatrix
9427bf0 [Xiangrui Meng] add task size tests to linear methods
e0a5cf2 [Xiangrui Meng] add task size test to GD
28a8411 [Xiangrui Meng] add test for NaiveBayes
380778c [Xiangrui Meng] update KMeans test
bccab92 [Xiangrui Meng] add task size test to LBFGS
02103ba [Xiangrui Meng] remove print
e73d68e [Xiangrui Meng] update tests for k-means
174cb15 [Xiangrui Meng] use local-cluster for test with a small akka.frameSize
1928a5a [Xiangrui Meng] add test for KMeans task size
e00c2da [Xiangrui Meng] use broadcast in GD, KMeans
010d076 [Xiangrui Meng] modify NaiveBayesModel and GLM to use broadcast
Author: Matei Zaharia <matei@databricks.com>
Closes#1593 from mateiz/spark-2680 and squashes the following commits:
3c949c4 [Matei Zaharia] Lower spark.shuffle.memoryFraction to 0.2 by default
Similar to SPARK-1034, the problem was that Py4J didn’t cope well with the fake ClassTags used in the Java API. It doesn’t look like there’s any reason why PythonRDD needs to take a ClassTag, since it just ignores the type of the previous RDD, so I removed the type parameter and we no longer pass ClassTags from Python.
Author: Josh Rosen <joshrosen@apache.org>
Closes#1605 from JoshRosen/spark-2601 and squashes the following commits:
b68e118 [Josh Rosen] Fix Py4J error when transforming pickleFiles [SPARK-2601]
handleMessageExecutor, handleReadWriteExecutor, and handleConnectExecutor are not marked as daemon and not named. I think there exists some condition in which Spark programs won't terminate because of this.
Stack dump attached in https://issues.apache.org/jira/browse/SPARK-2704
Author: Reynold Xin <rxin@apache.org>
Closes#1604 from rxin/daemon and squashes the following commits:
98d6a6c [Reynold Xin] [SPARK-2704] Name threads in ConnectionManager and mark them as daemon.
Added emptyRDD method to Java API with tests.
Author: bpaulin <bob@bobpaulin.com>
Closes#1597 from bobpaulin/SPARK-2279 and squashes the following commits:
5ad57c2 [bpaulin] [SPARK-2279] Added emptyRDD method to Java API
Add several default configs for PySpark, related to serialization in JVM.
spark.serializer = org.apache.spark.serializer.KryoSerializer
spark.serializer.objectStreamReset = 100
spark.rdd.compress = True
This will help to reduce the memory usage during RDD.partitionBy()
Author: Davies Liu <davies.liu@gmail.com>
Closes#1568 from davies/conf and squashes the following commits:
cd316f1 [Davies Liu] remove duplicated line
f71a355 [Davies Liu] rebase to master, add spark.rdd.compress = True
8f63f45 [Davies Liu] Merge branch 'master' into conf
8bc9f08 [Davies Liu] fix unittest
c04a83d [Davies Liu] some default configs for PySpark
The current default value of spark.serializer.objectStreamReset is 10,000.
When trying to re-partition (e.g., to 64 partitions) a large file (e.g., 500MB), containing 1MB records, the serializer will cache 10000 x 1MB x 64 ~= 640 GB which will cause out of memory errors.
This patch sets the default value to a more reasonable default value (100).
Author: Hossein <hossein@databricks.com>
Closes#1595 from falaki/objectStreamReset and squashes the following commits:
650a935 [Hossein] Updated documentation
1aa0df8 [Hossein] Reduce default value of spark.serializer.objectStreamReset
Author: Josh Rosen <joshrosen@apache.org>
Closes#1596 from JoshRosen/spark-1458 and squashes the following commits:
fdbb0bf [Josh Rosen] Add SparkContext.version to Python & Java [SPARK-1458]
Author: Michael Armbrust <michael@databricks.com>
Closes#1557 from marmbrus/fixDivision and squashes the following commits:
b85077f [Michael Armbrust] Fix unit tests.
af98f29 [Michael Armbrust] Change DIV to long type
0c29ae8 [Michael Armbrust] Fix division semantics for hive
This is part of the scheduler cleanup/refactoring effort to make the scheduler code easier to maintain.
@kayousterhout @markhamstra please take a look ...
Author: Reynold Xin <rxin@apache.org>
Closes#1561 from rxin/dagSchedulerHashMaps and squashes the following commits:
1c44e15 [Reynold Xin] Clear pending tasks in submitMissingTasks.
620a0d1 [Reynold Xin] Use filterKeys.
5b54404 [Reynold Xin] Code review feedback.
c1e9a1c [Reynold Xin] Removed some HashMaps from DAGScheduler by storing information in Stage.
This reverts commit 06dc0d2c6b.
#1399 is making Jenkins fail. We should investigate and put this back after its passing tests.
Author: Michael Armbrust <michael@databricks.com>
Closes#1594 from marmbrus/revertJDBC and squashes the following commits:
59748da [Michael Armbrust] Revert "[SPARK-2410][SQL] Merging Hive Thrift/JDBC server"
Due to problems with when we update runningStages (in DAGScheduler.scala)
and how we decide to send a SparkListenerStageCompleted message to
SparkListeners, sometimes stages can be shown as "running" in the UI forever
(even after they have failed). This issue can manifest when stages are
resubmitted with 0 tasks, or when the DAGScheduler catches non-serializable
tasks. The problem also resulted in a (small) memory leak in the DAGScheduler,
where stages can stay in runningStages forever. This commit fixes
that problem and adds a unit test.
Thanks tsudukim for helping to look into this issue!
cc markhamstra rxin
Author: Kay Ousterhout <kayousterhout@gmail.com>
Closes#1566 from kayousterhout/dag_fix and squashes the following commits:
217d74b [Kay Ousterhout] [SPARK-1726] [SPARK-2567] Eliminate zombie stages in UI.
This patch adds a sort flag into ShuffleDependecy and moves sort into hash shuffle implementation.
Moving sort into shuffle implementation can give space for other shuffle implementations (like sort-based shuffle) to better optimize sort through shuffle.
Author: jerryshao <saisai.shao@intel.com>
Closes#1210 from jerryshao/SPARK-2125 and squashes the following commits:
2feaf7b [jerryshao] revert MimaExcludes
ceddf75 [jerryshao] add MimaExeclude
f674ff4 [jerryshao] Add missing Scope restriction
b9fe0dd [jerryshao] Fix some style issues according to comments
ef6b729 [jerryshao] Change sort flag into Option
3f6eeed [jerryshao] Fix issues related to unit test
2f552a5 [jerryshao] Minor changes about naming and order
c92a281 [jerryshao] Move sort into shuffle implementations
I think it's better to defined hiveQlTable as a val
Author: baishuo(白硕) <vc_java@hotmail.com>
Closes#1569 from baishuo/patch-1 and squashes the following commits:
dc2f895 [baishuo(白硕)] Update HiveMetastoreCatalog.scala
a7b32a2 [baishuo(白硕)] Update HiveMetastoreCatalog.scala
Add genjavadocSettings back to SparkBuild. It requires #1585 .
https://issues.apache.org/jira/browse/SPARK-2682
Author: Yin Huai <huai@cse.ohio-state.edu>
Closes#1584 from yhuai/SPARK-2682 and squashes the following commits:
2e89461 [Yin Huai] Merge remote-tracking branch 'upstream/master' into SPARK-2682
54e3b66 [Yin Huai] Add genjavadocSettings back.
JIRA issue:
- Main: [SPARK-2410](https://issues.apache.org/jira/browse/SPARK-2410)
- Related: [SPARK-2678](https://issues.apache.org/jira/browse/SPARK-2678)
Cherry picked the Hive Thrift/JDBC server from [branch-1.0-jdbc](https://github.com/apache/spark/tree/branch-1.0-jdbc).
(Thanks chenghao-intel for his initial contribution of the Spark SQL CLI.)
TODO
- [x] Use `spark-submit` to launch the server, the CLI and beeline
- [x] Migration guideline draft for Shark users
----
Hit by a bug in `SparkSubmitArguments` while working on this PR: all application options that are recognized by `SparkSubmitArguments` are stolen as `SparkSubmit` options. For example:
```bash
$ spark-submit --class org.apache.hive.beeline.BeeLine spark-internal --help
```
This actually shows usage information of `SparkSubmit` rather than `BeeLine`.
~~Fixed this bug here since the `spark-internal` related stuff also touches `SparkSubmitArguments` and I'd like to avoid conflict.~~
**UPDATE** The bug mentioned above is now tracked by [SPARK-2678](https://issues.apache.org/jira/browse/SPARK-2678). Decided to revert changes to this bug since it involves more subtle considerations and worth a separate PR.
Author: Cheng Lian <lian.cs.zju@gmail.com>
Closes#1399 from liancheng/thriftserver and squashes the following commits:
090beea [Cheng Lian] Revert changes related to SPARK-2678, decided to move them to another PR
21c6cf4 [Cheng Lian] Updated Spark SQL programming guide docs
fe0af31 [Cheng Lian] Reordered spark-submit options in spark-shell[.cmd]
199e3fb [Cheng Lian] Disabled MIMA for hive-thriftserver
1083e9d [Cheng Lian] Fixed failed test suites
7db82a1 [Cheng Lian] Fixed spark-submit application options handling logic
9cc0f06 [Cheng Lian] Starts beeline with spark-submit
cfcf461 [Cheng Lian] Updated documents and build scripts for the newly added hive-thriftserver profile
061880f [Cheng Lian] Addressed all comments by @pwendell
7755062 [Cheng Lian] Adapts test suites to spark-submit settings
40bafef [Cheng Lian] Fixed more license header issues
e214aab [Cheng Lian] Added missing license headers
b8905ba [Cheng Lian] Fixed minor issues in spark-sql and start-thriftserver.sh
f975d22 [Cheng Lian] Updated docs for Hive compatibility and Shark migration guide draft
3ad4e75 [Cheng Lian] Starts spark-sql shell with spark-submit
a5310d1 [Cheng Lian] Make HiveThriftServer2 play well with spark-submit
61f39f4 [Cheng Lian] Starts Hive Thrift server via spark-submit
2c4c539 [Cheng Lian] Cherry picked the Hive Thrift server
Renaming `short` to `shortForm` and `long` to `longForm`.
JIRA: https://issues.apache.org/jira/browse/SPARK-2683
Author: Yin Huai <huai@cse.ohio-state.edu>
Closes#1585 from yhuai/SPARK-2683 and squashes the following commits:
5ddb843 [Yin Huai] "short" and "long" are Java keyworks. In order to generate javadoc, renaming "short" to "shortForm" and "long" to "longForm".
Our program needs to receive a large amount of data and run for a long
time.
We set the log level to WARN but "Storing iterator" "received single"
as such message written to the log file. (over yarn)
Author: fireflyc <fireflyc@126.com>
Closes#1372 from fireflyc/fix-replace-stdout-log and squashes the following commits:
e684140 [fireflyc] 'info' modified into the 'debug'
fa22a38 [fireflyc] replace println to log4j
Hive Supports the operator "<=>", which returns same result with EQUAL(=) operator for non-null operands, but returns TRUE if both are NULL, FALSE if one of the them is NULL.
Author: Cheng Hao <hao.cheng@intel.com>
Closes#1570 from chenghao-intel/equalns and squashes the following commits:
8d6c789 [Cheng Hao] Remove the test case orc_predicate_pushdown
5b2ca88 [Cheng Hao] Add cases into whitelist
8e66cdd [Cheng Hao] Rename the EqualNSTo ==> EqualNullSafe
7af4b0b [Cheng Hao] Add EqualNS & Unit Tests
Author: Reynold Xin <rxin@apache.org>
Closes#1583 from rxin/closureClean and squashes the following commits:
8982fe6 [Reynold Xin] [SPARK-2529] Clean closures in foreach and foreachPartition.
JIRA: https://issues.apache.org/jira/browse/SPARK-2657
Our current code uses ArrayBuffers for each group of values in groupBy, as well as for the key's elements in CoGroupedRDD. ArrayBuffers have a lot of overhead if there are few values in them, which is likely to happen in cases such as join. In particular, they have a pointer to an Object[] of size 16 by default, which is 24 bytes for the array header + 128 for the pointers in there, plus at least 32 for the ArrayBuffer data structure. This patch replaces the per-group buffers with a CompactBuffer class that can store up to 2 elements more efficiently (in fields of itself) and acts like an ArrayBuffer beyond that. For a key's elements in CoGroupedRDD, we use an Array of CompactBuffers instead of an ArrayBuffer of ArrayBuffers.
There are some changes throughout the code to deal with CoGroupedRDD returning Array instead. We can also decide not to do that but CoGroupedRDD is a `DeveloperAPI` so I think it's okay to change it here.
Author: Matei Zaharia <matei@databricks.com>
Closes#1555 from mateiz/compact-groupby and squashes the following commits:
845a356 [Matei Zaharia] Lower initial size of CompactBuffer's vector to 8
07621a7 [Matei Zaharia] Review comments
0c1cd12 [Matei Zaharia] Don't use varargs in CompactBuffer.apply
bdc8a39 [Matei Zaharia] Small tweak to +=, and typos
f61f040 [Matei Zaharia] Fix line lengths
59da88b0 [Matei Zaharia] Fix line lengths
197cde8 [Matei Zaharia] Make CompactBuffer extend Seq to make its toSeq more efficient
775110f [Matei Zaharia] Change CoGroupedRDD to give (K, Array[Iterable[_]]) to avoid wrappers
9b4c6e8 [Matei Zaharia] Use CompactBuffer in CoGroupedRDD
ed577ab [Matei Zaharia] Use CompactBuffer in groupByKey
10f0de1 [Matei Zaharia] A CompactBuffer that's more memory-efficient than ArrayBuffer for small buffers
exact sample size not supported for now.
Author: Doris Xin <doris.s.xin@gmail.com>
Closes#1554 from dorx/pystratified and squashes the following commits:
4ba927a [Doris Xin] use rel diff (+- 50%) instead of abs diff (+- 50)
bdc3f8b [Doris Xin] updated unit to check sample holistically
7713c7b [Doris Xin] Python version of stratified sampling
During aggregation in Python worker, if the memory usage is above spark.executor.memory, it will do disk spilling aggregation.
It will split the aggregation into multiple stage, in each stage, it will partition the aggregated data by hash and dump them into disks. After all the data are aggregated, it will merge all the stages together (partition by partition).
Author: Davies Liu <davies.liu@gmail.com>
Closes#1460 from davies/spill and squashes the following commits:
cad91bf [Davies Liu] call gc.collect() after data.clear() to release memory as much as possible.
37d71f7 [Davies Liu] balance the partitions
902f036 [Davies Liu] add shuffle.py into run-tests
dcf03a9 [Davies Liu] fix memory_info() of psutil
67e6eba [Davies Liu] comment for MAX_TOTAL_PARTITIONS
f6bd5d6 [Davies Liu] rollback next_limit() again, the performance difference is huge:
e74b785 [Davies Liu] fix code style and change next_limit to memory_limit
400be01 [Davies Liu] address all the comments
6178844 [Davies Liu] refactor and improve docs
fdd0a49 [Davies Liu] add long doc string for ExternalMerger
1a97ce4 [Davies Liu] limit used memory and size of objects in partitionBy()
e6cc7f9 [Davies Liu] Merge branch 'master' into spill
3652583 [Davies Liu] address comments
e78a0a0 [Davies Liu] fix style
24cec6a [Davies Liu] get local directory by SPARK_LOCAL_DIR
57ee7ef [Davies Liu] update docs
286aaff [Davies Liu] let spilled aggregation in Python configurable
e9a40f6 [Davies Liu] recursive merger
6edbd1f [Davies Liu] Hash based disk spilling aggregation
Author: Prashant Sharma <prashant.s@imaginea.com>
Closes#1051 from ScrapCodes/SPARK-2014/pyspark-cache and squashes the following commits:
f192df7 [Prashant Sharma] Code Review
2a2f43f [Prashant Sharma] [SPARK-2014] Make PySpark store RDDs in MEMORY_ONLY_SER with compression by default
Stopping the Twitter Receiver would call twitter4j's TwitterStream.shutdown, which in turn causes an Exception to be thrown to the listener. This exception caused the Receiver to be restarted. This patch check whether the receiver was stopped or not, and accordingly restarts on exception.
Author: Tathagata Das <tathagata.das1565@gmail.com>
Closes#1577 from tdas/twitter-stop and squashes the following commits:
011b525 [Tathagata Das] Fixed Twitter stream stopping bug.
Author: Neville Li <neville@spotify.com>
Closes#1188 from nevillelyh/neville/ui and squashes the following commits:
d3ac425 [Neville Li] SPARK-2250: show persisted RDD in stage UI
f075db9 [Neville Li] SPARK-2035: show call stack even when description is available
Allow small errors in comparison.
@dbtsai , this unit test blocks https://github.com/apache/spark/pull/1562 . I may need to merge this one first. We can change it to use the tools in https://github.com/apache/spark/pull/1425 after that PR gets merged.
Author: Xiangrui Meng <meng@databricks.com>
Closes#1576 from mengxr/fix-binary-metrics-unit-tests and squashes the following commits:
5076a7f [Xiangrui Meng] fix binary metrics unit tests
In JsonRDD.scalafy, we are using toMap/toList to convert a Java Map/List to a Scala one. These two operations are pretty expensive because they read elements from a Java Map/List and then load to a Scala Map/List. We can use Scala wrappers to wrap those Java collections instead of using toMap/toList.
I did a quick test to see the performance. I had a 2.9GB cached RDD[String] storing one JSON object per record (twitter dataset). My simple test program is attached below.
```scala
val sqlContext = new org.apache.spark.sql.SQLContext(sc)
import sqlContext._
val jsonData = sc.textFile("...")
jsonData.cache.count
val jsonSchemaRDD = sqlContext.jsonRDD(jsonData)
jsonSchemaRDD.registerAsTable("jt")
sqlContext.sql("select count(*) from jt").collect
```
Stages for the schema inference and the table scan both had 48 tasks. These tasks were executed sequentially. For the current implementation, scanning the JSON dataset will materialize values of all fields of a record. The inferred schema of the dataset can be accessed at https://gist.github.com/yhuai/05fe8a57c638c6666f8d.
From the result, there was no significant difference on running `jsonRDD`. For the simple aggregation query, results are attached below.
```
Original:
Run 1: 26.1s
Run 2: 27.03s
Run 3: 27.035s
With this change:
Run 1: 21.086s
Run 2: 21.035s
Run 3: 21.029s
```
JIRA: https://issues.apache.org/jira/browse/SPARK-2603
Author: Yin Huai <huai@cse.ohio-state.edu>
Closes#1504 from yhuai/removeToMapToList and squashes the following commits:
6831b77 [Yin Huai] Fix failed tests.
09b9bca [Yin Huai] Merge remote-tracking branch 'upstream/master' into removeToMapToList
d1abdb8 [Yin Huai] Remove unnecessary toMap and toList.
Add a `<deb.bin.filemode>744</deb.bin.filemode>` property to the `assembly/pom.xml` that defaults to `744`.
Use this property for ../bin folder <filemode>.
This patch doesn't change the current default modes but allows one override the modes at build time:
`-Ddeb.bin.filemode=<new mode>`
Author: tzolov <christian.tzolov@gmail.com>
Closes#1531 from tzolov/SPARK-2619 and squashes the following commits:
6d95343 [tzolov] [Build] SPARK-2619: Configurable filemode for the spark/bin folder in the .deb package
...rce manager UI
Use the event logger directory to provide a direct link to finished
application UI in yarn resourcemanager UI.
Author: Rahul Singhal <rahul.singhal@guavus.com>
Closes#1094 from rahulsinghaliitd/SPARK-2150 and squashes the following commits:
95f230c [Rahul Singhal] SPARK-2150: Provide direct link to finished application UI in yarn resource manager UI
