The batch size during external sort will grow up to max 10000, then shrink down to zero, causing infinite loop.
Given the assumption that the items usually have similar size, so we don't need to adjust the batch size after first spill.
cc JoshRosen rxin angelini
Author: Davies Liu <davies@databricks.com>
Closes#6714 from davies/batch_size and squashes the following commits:
b170dfb [Davies Liu] update test
b9be832 [Davies Liu] Merge branch 'batch_size' of github.com:davies/spark into batch_size
6ade745 [Davies Liu] update test
5c21777 [Davies Liu] Update shuffle.py
e746aec [Davies Liu] fix batch size during sort
This PR fixes the sum issue and also adds `emptyRDD` so that it's easy to create a test case.
Author: zsxwing <zsxwing@gmail.com>
Closes#6826 from zsxwing/python-emptyRDD and squashes the following commits:
b36993f [zsxwing] Update the return type to JavaRDD[T]
71df047 [zsxwing] Add emptyRDD to pyspark and fix the issue when calling sum on an empty RDD
(cherry picked from commit 0fc4b96f3e)
Signed-off-by: Andrew Or <andrew@databricks.com>
Author: Holden Karau <holden@pigscanfly.ca>
Closes#6275 from holdenk/SPARK-771-startTime-is-missing-from-pyspark and squashes the following commits:
06662dc [Holden Karau] add mising blank line for style checks
7a87410 [Holden Karau] add back missing newline
7a7876b [Holden Karau] Add a startTime property to match the corresponding one in the Scala SparkContext
(cherry picked from commit 6b18cdc1b1)
Signed-off-by: Josh Rosen <joshrosen@databricks.com>
This PR is based on #6081, thanks adrian-wang.
Closes#6081
Author: Daoyuan Wang <daoyuan.wang@intel.com>
Author: Davies Liu <davies@databricks.com>
Closes#6230 from davies/range and squashes the following commits:
d3ce5fe [Davies Liu] add tests
789eda5 [Davies Liu] add range() in Python
4590208 [Davies Liu] Merge commit 'refs/pull/6081/head' of github.com:apache/spark into range
cbf5200 [Daoyuan Wang] let's add python support in a separate PR
f45e3b2 [Daoyuan Wang] remove redundant toLong
617da76 [Daoyuan Wang] fix safe marge for corner cases
867c417 [Daoyuan Wang] fix
13dbe84 [Daoyuan Wang] update
bd998ba [Daoyuan Wang] update comments
d3a0c1b [Daoyuan Wang] add range api()
(cherry picked from commit c2437de189)
Signed-off-by: Reynold Xin <rxin@databricks.com>
This PR revert #5404, change to pass the version of python in driver into JVM, check it in worker before deserializing closure, then it can works with different major version of Python.
Author: Davies Liu <davies@databricks.com>
Closes#6203 from davies/py_version and squashes the following commits:
b8fb76e [Davies Liu] fix test
6ce5096 [Davies Liu] use string for version
47c6278 [Davies Liu] check python version of worker with driver
(cherry picked from commit 32fbd297dd)
Signed-off-by: Josh Rosen <joshrosen@databricks.com>
Author: Vinod K C <vinod.kc@huawei.com>
Closes#5974 from vinodkc/fix_countApproxDistinct_Validation and squashes the following commits:
3a3d59c [Vinod K C] Reverted removal of validation relativeSD<0.000017
799976e [Vinod K C] Removed testcase to assert IAE when relativeSD>3.7
8ddbfae [Vinod K C] Remove blank line
b1b00a3 [Vinod K C] Removed relativeSD validation from python API,RDD.scala will do validation
122d378 [Vinod K C] Fixed validation of relativeSD in countApproxDistinct
(cherry picked from commit dda6d9f404)
Signed-off-by: Sean Owen <sowen@cloudera.com>
This PR try to speed up some python tests:
```
tests.py 144s -> 103s -41s
mllib/classification.py 24s -> 17s -7s
mllib/regression.py 27s -> 15s -12s
mllib/tree.py 27s -> 13s -14s
mllib/tests.py 64s -> 31s -33s
streaming/tests.py 185s -> 84s -101s
```
Considering python3, the total saving will be 558s (almost 10 minutes) (core, and streaming run three times, mllib runs twice).
During testing, it will show used time for each test file:
```
Run core tests ...
Running test: pyspark/rdd.py ... ok (22s)
Running test: pyspark/context.py ... ok (16s)
Running test: pyspark/conf.py ... ok (4s)
Running test: pyspark/broadcast.py ... ok (4s)
Running test: pyspark/accumulators.py ... ok (4s)
Running test: pyspark/serializers.py ... ok (6s)
Running test: pyspark/profiler.py ... ok (5s)
Running test: pyspark/shuffle.py ... ok (1s)
Running test: pyspark/tests.py ... ok (103s) 144s
```
Author: Reynold Xin <rxin@databricks.com>
Author: Xiangrui Meng <meng@databricks.com>
Closes#5605 from rxin/python-tests-speed and squashes the following commits:
d08542d [Reynold Xin] Merge pull request #14 from mengxr/SPARK-6953
89321ee [Xiangrui Meng] fix seed in tests
3ad2387 [Reynold Xin] Merge pull request #5427 from davies/python_tests
This PR update PySpark to support Python 3 (tested with 3.4).
Known issue: unpickle array from Pyrolite is broken in Python 3, those tests are skipped.
TODO: ec2/spark-ec2.py is not fully tested with python3.
Author: Davies Liu <davies@databricks.com>
Author: twneale <twneale@gmail.com>
Author: Josh Rosen <joshrosen@databricks.com>
Closes#5173 from davies/python3 and squashes the following commits:
d7d6323 [Davies Liu] fix tests
6c52a98 [Davies Liu] fix mllib test
99e334f [Davies Liu] update timeout
b716610 [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3
cafd5ec [Davies Liu] adddress comments from @mengxr
bf225d7 [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3
179fc8d [Davies Liu] tuning flaky tests
8c8b957 [Davies Liu] fix ResourceWarning in Python 3
5c57c95 [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3
4006829 [Davies Liu] fix test
2fc0066 [Davies Liu] add python3 path
71535e9 [Davies Liu] fix xrange and divide
5a55ab4 [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3
125f12c [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3
ed498c8 [Davies Liu] fix compatibility with python 3
820e649 [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3
e8ce8c9 [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3
ad7c374 [Davies Liu] fix mllib test and warning
ef1fc2f [Davies Liu] fix tests
4eee14a [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3
20112ff [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3
59bb492 [Davies Liu] fix tests
1da268c [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3
ca0fdd3 [Davies Liu] fix code style
9563a15 [Davies Liu] add imap back for python 2
0b1ec04 [Davies Liu] make python examples work with Python 3
d2fd566 [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3
a716d34 [Davies Liu] test with python 3.4
f1700e8 [Davies Liu] fix test in python3
671b1db [Davies Liu] fix test in python3
692ff47 [Davies Liu] fix flaky test
7b9699f [Davies Liu] invalidate import cache for Python 3.3+
9c58497 [Davies Liu] fix kill worker
309bfbf [Davies Liu] keep compatibility
5707476 [Davies Liu] cleanup, fix hash of string in 3.3+
8662d5b [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3
f53e1f0 [Davies Liu] fix tests
70b6b73 [Davies Liu] compile ec2/spark_ec2.py in python 3
a39167e [Davies Liu] support customize class in __main__
814c77b [Davies Liu] run unittests with python 3
7f4476e [Davies Liu] mllib tests passed
d737924 [Davies Liu] pass ml tests
375ea17 [Davies Liu] SQL tests pass
6cc42a9 [Davies Liu] rename
431a8de [Davies Liu] streaming tests pass
78901a7 [Davies Liu] fix hash of serializer in Python 3
24b2f2e [Davies Liu] pass all RDD tests
35f48fe [Davies Liu] run future again
1eebac2 [Davies Liu] fix conflict in ec2/spark_ec2.py
6e3c21d [Davies Liu] make cloudpickle work with Python3
2fb2db3 [Josh Rosen] Guard more changes behind sys.version; still doesn't run
1aa5e8f [twneale] Turned out `pickle.DictionaryType is dict` == True, so swapped it out
7354371 [twneale] buffer --> memoryview I'm not super sure if this a valid change, but the 2.7 docs recommend using memoryview over buffer where possible, so hoping it'll work.
b69ccdf [twneale] Uses the pure python pickle._Pickler instead of c-extension _pickle.Pickler. It appears pyspark 2.7 uses the pure python pickler as well, so this shouldn't degrade pickling performance (?).
f40d925 [twneale] xrange --> range
e104215 [twneale] Replaces 2.7 types.InstsanceType with 3.4 `object`....could be horribly wrong depending on how types.InstanceType is used elsewhere in the package--see http://bugs.python.org/issue8206
79de9d0 [twneale] Replaces python2.7 `file` with 3.4 _io.TextIOWrapper
2adb42d [Josh Rosen] Fix up some import differences between Python 2 and 3
854be27 [Josh Rosen] Run `futurize` on Python code:
7c5b4ce [Josh Rosen] Remove Python 3 check in shell.py.
Currently, the created broadcast object will have same life cycle as RDD in Python. For multistage jobs, an PythonRDD will be created in JVM and the RDD in Python may be GCed, then the broadcast will be destroyed in JVM before the PythonRDD.
This PR change to use PythonRDD to track the lifecycle of the broadcast object. It also have a refactor about getNumPartitions() to avoid unnecessary creation of PythonRDD, which could be heavy.
cc JoshRosen
Author: Davies Liu <davies@databricks.com>
Closes#5496 from davies/big_closure and squashes the following commits:
9a0ea4c [Davies Liu] fix big closure with shuffle
Author: Davies Liu <davies@databricks.com>
Closes#5404 from davies/check_version and squashes the following commits:
e559248 [Davies Liu] add tests
ec33b5f [Davies Liu] check the python version in worker
The samples should always be sorted in ascending order, because bisect.bisect_left is used on it. The reverse order of the result is already achieved in rangePartitioner by reversing the found index.
The current implementation also work, but always uses only two partitions -- the first one and the last one (because the bisect_left return returns either "beginning" or "end" for a descending sequence).
Author: Milan Straka <fox@ucw.cz>
This patch had conflicts when merged, resolved by
Committer: Josh Rosen <joshrosen@databricks.com>
Closes#4761 from foxik/fix-descending-sort and squashes the following commits:
95896b5 [Milan Straka] Add regression test for SPARK-5969.
5757490 [Milan Straka] Fix descending pyspark.rdd.sortByKey.
This patch change groupByKey() to use external sort based approach, so it can support single huge key.
For example, it can group by a dataset including one hot key with 40 millions values (strings), using 500M memory for Python worker, finished in about 2 minutes. (it will need 6G memory in hash based approach).
During groupByKey(), it will do in-memory groupBy first. If the dataset can not fit in memory, then data will be partitioned by hash. If one partition still can not fit in memory, it will switch to sort based groupBy().
Author: Davies Liu <davies.liu@gmail.com>
Author: Davies Liu <davies@databricks.com>
Closes#1977 from davies/groupby and squashes the following commits:
af3713a [Davies Liu] make sure it's iterator
67772dd [Davies Liu] fix tests
e78c15c [Davies Liu] address comments
0b0fde8 [Davies Liu] address comments
0dcf320 [Davies Liu] address comments, rollback changes in ResultIterable
e3b8eab [Davies Liu] fix narrow dependency
2a1857a [Davies Liu] typo
d2f053b [Davies Liu] add repr for FlattedValuesSerializer
c6a2f8d [Davies Liu] address comments
9e2df24 [Davies Liu] Merge branch 'master' of github.com:apache/spark into groupby
2b9c261 [Davies Liu] fix typo in comments
70aadcd [Davies Liu] Merge branch 'master' of github.com:apache/spark into groupby
a14b4bd [Davies Liu] Merge branch 'master' of github.com:apache/spark into groupby
ab5515b [Davies Liu] Merge branch 'master' into groupby
651f891 [Davies Liu] simplify GroupByKey
1578f2e [Davies Liu] Merge branch 'master' of github.com:apache/spark into groupby
1f69f93 [Davies Liu] fix tests
0d3395f [Davies Liu] Merge branch 'master' of github.com:apache/spark into groupby
341f1e0 [Davies Liu] add comments, refactor
47918b8 [Davies Liu] remove unused code
6540948 [Davies Liu] address comments:
17f4ec6 [Davies Liu] Merge branch 'master' of github.com:apache/spark into groupby
4d4bc86 [Davies Liu] bugfix
8ef965e [Davies Liu] Merge branch 'master' into groupby
fbc504a [Davies Liu] Merge branch 'master' into groupby
779ed03 [Davies Liu] fix merge conflict
2c1d05b [Davies Liu] refactor, minor turning
b48cda5 [Davies Liu] Merge branch 'master' into groupby
85138e6 [Davies Liu] Merge branch 'master' into groupby
acd8e1b [Davies Liu] fix memory when groupByKey().count()
905b233 [Davies Liu] Merge branch 'sort' into groupby
1f075ed [Davies Liu] Merge branch 'master' into sort
4b07d39 [Davies Liu] compress the data while spilling
0a081c6 [Davies Liu] Merge branch 'master' into groupby
f157fe7 [Davies Liu] Merge branch 'sort' into groupby
eb53ca6 [Davies Liu] Merge branch 'master' into sort
b2dc3bf [Davies Liu] Merge branch 'sort' into groupby
644abaf [Davies Liu] add license in LICENSE
19f7873 [Davies Liu] improve tests
11ba318 [Davies Liu] typo
085aef8 [Davies Liu] Merge branch 'master' into groupby
3ee58e5 [Davies Liu] switch to sort based groupBy, based on size of data
1ea0669 [Davies Liu] choose sort based groupByKey() automatically
b40bae7 [Davies Liu] bugfix
efa23df [Davies Liu] refactor, add spark.shuffle.sort=False
250be4e [Davies Liu] flatten the combined values when dumping into disks
d05060d [Davies Liu] group the same key before shuffle, reduce the comparison during sorting
083d842 [Davies Liu] sorted based groupByKey()
55602ee [Davies Liu] use external sort in sortBy() and sortByKey()
The Thread.interrupt() can not terminate the thread in some cases, so we should not wait for the writerThread of PythonRDD.
This PR also ignore some exception during clean up.
cc JoshRosen mengxr
Author: Davies Liu <davies@databricks.com>
Closes#4987 from davies/fix_take and squashes the following commits:
4488f1a [Davies Liu] fix hang when call take() in JVM on PythonRDD
Author: Davies Liu <davies@databricks.com>
Closes#4745 from davies/fix_zip and squashes the following commits:
2124b2c [Davies Liu] Update tests.py
b5c828f [Davies Liu] increase the number of records
c1e40fd [Davies Liu] fix zip with two RDDs with AutoBatchedSerializer
Currently, PySpark does not support narrow dependency during cogroup/join when the two RDDs have the partitioner, another unnecessary shuffle stage will come in.
The Python implementation of cogroup/join is different than Scala one, it depends on union() and partitionBy(). This patch will try to use PartitionerAwareUnionRDD() in union(), when all the RDDs have the same partitioner. It also fix `reservePartitioner` in all the map() or mapPartitions(), then partitionBy() can skip the unnecessary shuffle stage.
Author: Davies Liu <davies@databricks.com>
Closes#4629 from davies/narrow and squashes the following commits:
dffe34e [Davies Liu] improve test, check number of stages for join/cogroup
1ed3ba2 [Davies Liu] Merge branch 'master' of github.com:apache/spark into narrow
4d29932 [Davies Liu] address comment
cc28d97 [Davies Liu] add unit tests
940245e [Davies Liu] address comments
ff5a0a6 [Davies Liu] skip the partitionBy() on Python side
eb26c62 [Davies Liu] narrow dependency in PySpark
This patch bring the pull based progress API into Python, also a example in Python.
Author: Davies Liu <davies@databricks.com>
Closes#3027 from davies/progress_api and squashes the following commits:
b1ba984 [Davies Liu] fix style
d3b9253 [Davies Liu] add tests, mute the exception after stop
4297327 [Davies Liu] Merge branch 'master' of github.com:apache/spark into progress_api
969fa9d [Davies Liu] Merge branch 'master' of github.com:apache/spark into progress_api
25590c9 [Davies Liu] update with Java API
360de2d [Davies Liu] Merge branch 'master' of github.com:apache/spark into progress_api
c0f1021 [Davies Liu] Merge branch 'master' of github.com:apache/spark into progress_api
023afb3 [Davies Liu] add Python API and example for progress API
This PR brings the Python API for Spark Streaming Kafka data source.
```
class KafkaUtils(__builtin__.object)
| Static methods defined here:
|
| createStream(ssc, zkQuorum, groupId, topics, storageLevel=StorageLevel(True, True, False, False,
2), keyDecoder=<function utf8_decoder>, valueDecoder=<function utf8_decoder>)
| Create an input stream that pulls messages from a Kafka Broker.
|
| :param ssc: StreamingContext object
| :param zkQuorum: Zookeeper quorum (hostname:port,hostname:port,..).
| :param groupId: The group id for this consumer.
| :param topics: Dict of (topic_name -> numPartitions) to consume.
| Each partition is consumed in its own thread.
| :param storageLevel: RDD storage level.
| :param keyDecoder: A function used to decode key
| :param valueDecoder: A function used to decode value
| :return: A DStream object
```
run the example:
```
bin/spark-submit --driver-class-path external/kafka-assembly/target/scala-*/spark-streaming-kafka-assembly-*.jar examples/src/main/python/streaming/kafka_wordcount.py localhost:2181 test
```
Author: Davies Liu <davies@databricks.com>
Author: Tathagata Das <tdas@databricks.com>
Closes#3715 from davies/kafka and squashes the following commits:
d93bfe0 [Davies Liu] Update make-distribution.sh
4280d04 [Davies Liu] address comments
e6d0427 [Davies Liu] Merge branch 'master' of github.com:apache/spark into kafka
f257071 [Davies Liu] add tests for null in RDD
23b039a [Davies Liu] address comments
9af51c4 [Davies Liu] Merge branch 'kafka' of github.com:davies/spark into kafka
a74da87 [Davies Liu] address comments
dc1eed0 [Davies Liu] Update kafka_wordcount.py
31e2317 [Davies Liu] Update kafka_wordcount.py
370ba61 [Davies Liu] Update kafka.py
97386b3 [Davies Liu] address comment
2c567a5 [Davies Liu] update logging and comment
33730d1 [Davies Liu] Merge branch 'master' of github.com:apache/spark into kafka
adeeb38 [Davies Liu] Merge pull request #3 from tdas/kafka-python-api
aea8953 [Tathagata Das] Kafka-assembly for Python API
eea16a7 [Davies Liu] refactor
f6ce899 [Davies Liu] add example and fix bugs
98c8d17 [Davies Liu] fix python style
5697a01 [Davies Liu] bypass decoder in scala
048dbe6 [Davies Liu] fix python style
75d485e [Davies Liu] add mqtt
07923c4 [Davies Liu] support kafka in Python
1. Throw UnsupportedOperationException if a Column is not computable.
2. Perform eager analysis on DataFrame so we can catch errors when they happen (not when an action is run).
Author: Reynold Xin <rxin@databricks.com>
Author: Davies Liu <davies@databricks.com>
Closes#4296 from rxin/col-computability and squashes the following commits:
6527b86 [Reynold Xin] Merge pull request #8 from davies/col-computability
fd92bc7 [Reynold Xin] Merge branch 'master' into col-computability
f79034c [Davies Liu] fix python tests
5afe1ff [Reynold Xin] Fix scala test.
17f6bae [Reynold Xin] Various fixes.
b932e86 [Reynold Xin] Added eager analysis for error reporting.
e6f00b8 [Reynold Xin] [SQL][API] ComputableColumn vs IncomputableColumn
This fixes an exception that prevented users from calling `help()` on Python DataFrame instances.
Author: Josh Rosen <joshrosen@databricks.com>
Closes#4278 from JoshRosen/SPARK-5464-python-dataframe-help-command and squashes the following commits:
08f95f7 [Josh Rosen] Fix exception when calling help() on Python DataFrame instances
This PR is based on #3255 , fix conflicts and code style.
Closes#3255.
Author: Yandu Oppacher <yandu.oppacher@jadedpixel.com>
Author: Davies Liu <davies@databricks.com>
Closes#3901 from davies/refactor-python-profile-code and squashes the following commits:
b4a9306 [Davies Liu] fix tests
4b79ce8 [Davies Liu] add docstring for profiler_cls
2700e47 [Davies Liu] use BasicProfiler as default
349e341 [Davies Liu] more refactor
6a5d4df [Davies Liu] refactor and fix tests
31bf6b6 [Davies Liu] fix code style
0864b5d [Yandu Oppacher] Remove unused method
76a6c37 [Yandu Oppacher] Added a profile collector to accumulate the profilers per stage
9eefc36 [Yandu Oppacher] Fix doc
9ace076 [Yandu Oppacher] Refactor of profiler, and moved tests around
8739aff [Yandu Oppacher] Code review fixes
9bda3ec [Yandu Oppacher] Refactor profiler code
This is found through reading RDD from `sc.newAPIHadoopRDD` and writing it back using `rdd.saveAsNewAPIHadoopFile` in pyspark.
It turns out that whenever there are multiple RDD conversions from JavaRDD to PythonRDD then back to JavaRDD, the exception below happens:
```
15/01/16 10:28:31 ERROR Executor: Exception in task 0.0 in stage 3.0 (TID 7)
java.lang.ClassCastException: [Ljava.lang.Object; cannot be cast to java.util.ArrayList
at org.apache.spark.api.python.SerDeUtil$$anonfun$pythonToJava$1$$anonfun$apply$1.apply(SerDeUtil.scala:157)
at org.apache.spark.api.python.SerDeUtil$$anonfun$pythonToJava$1$$anonfun$apply$1.apply(SerDeUtil.scala:153)
at scala.collection.Iterator$$anon$13.hasNext(Iterator.scala:371)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:308)
```
The test case code below reproduces it:
```
from pyspark.rdd import RDD
dl = [
(u'2', {u'director': u'David Lean'}),
(u'7', {u'director': u'Andrew Dominik'})
]
dl_rdd = sc.parallelize(dl)
tmp = dl_rdd._to_java_object_rdd()
tmp2 = sc._jvm.SerDe.javaToPython(tmp)
t = RDD(tmp2, sc)
t.count()
tmp = t._to_java_object_rdd()
tmp2 = sc._jvm.SerDe.javaToPython(tmp)
t = RDD(tmp2, sc)
t.count() # it blows up here during the 2nd time of conversion
```
Author: Winston Chen <wchen@quid.com>
Closes#4146 from wingchen/master and squashes the following commits:
903df7d [Winston Chen] SPARK-5361, update to toSeq based on the PR
5d90a83 [Winston Chen] SPARK-5361, make python pretty, so to pass PEP 8 checks
126be6b [Winston Chen] SPARK-5361, add in test case
4cf1187 [Winston Chen] SPARK-5361, add in test case
9f1a097 [Winston Chen] add in tuple handling while converting form python RDD back to JavaRDD
This PR brings support of using StructType(and other hashable types) as key in MapType.
Author: Davies Liu <davies@databricks.com>
Closes#3714 from davies/fix_struct_in_map and squashes the following commits:
68585d7 [Davies Liu] fix primitive types in MapType
9601534 [Davies Liu] support StructType as key in MapType
UTF8Deserializer can not be used in BatchedSerializer, so always use PickleSerializer() when change batchSize in zip().
Also, if two RDD have the same batch size already, they did not need re-serialize any more.
Author: Davies Liu <davies@databricks.com>
Closes#3706 from davies/fix_4841 and squashes the following commits:
20ce3a3 [Davies Liu] fix bug in _reserialize()
e3ebf7c [Davies Liu] add comment
379d2c8 [Davies Liu] fix zip with textFile()
Re-implement the Python broadcast using file:
1) serialize the python object using cPickle, write into disks.
2) Create a wrapper in JVM (for the dumped file), it read data from during serialization
3) Using TorrentBroadcast or HttpBroadcast to transfer the data (compressed) into executors
4) During deserialization, writing the data into disk.
5) Passing the path into Python worker, read data from disk and unpickle it into python object, until the first access.
It fixes the performance regression introduced in #2659, has similar performance as 1.1, but support object larger than 2G, also improve the memory efficiency (only one compressed copy in driver and executor).
Testing with a 500M broadcast and 4 tasks (excluding the benefit from reused worker in 1.2):
name | 1.1 | 1.2 with this patch | improvement
---------|--------|---------|--------
python-broadcast-w-bytes | 25.20 | 9.33 | 170.13% |
python-broadcast-w-set | 4.13 | 4.50 | -8.35% |
Testing with 100 tasks (16 CPUs):
name | 1.1 | 1.2 with this patch | improvement
---------|--------|---------|--------
python-broadcast-w-bytes | 38.16 | 8.40 | 353.98%
python-broadcast-w-set | 23.29 | 9.59 | 142.80%
Author: Davies Liu <davies@databricks.com>
Closes#3417 from davies/pybroadcast and squashes the following commits:
50a58e0 [Davies Liu] address comments
b98de1d [Davies Liu] disable gc while unpickle
e5ee6b9 [Davies Liu] support large string
09303b8 [Davies Liu] read all data into memory
dde02dd [Davies Liu] improve performance of python broadcast
The Row object is created on the fly once the field is accessed, so we should access them by getattr() in asDict(0
Author: Davies Liu <davies@databricks.com>
Closes#3434 from davies/fix_asDict and squashes the following commits:
b20f1e7 [Davies Liu] fix asDict() with nested Row()
This patch will bring support for broadcasting objects larger than 2G.
pickle, zlib, FrameSerializer and Array[Byte] all can not support objects larger than 2G, so this patch introduce LargeObjectSerializer to serialize broadcast objects, the object will be serialized and compressed into small chunks, it also change the type of Broadcast[Array[Byte]]] into Broadcast[Array[Array[Byte]]]].
Testing for support broadcast objects larger than 2G is slow and memory hungry, so this is tested manually, could be added into SparkPerf.
Author: Davies Liu <davies@databricks.com>
Author: Davies Liu <davies.liu@gmail.com>
Closes#2659 from davies/huge and squashes the following commits:
7b57a14 [Davies Liu] add more tests for broadcast
28acff9 [Davies Liu] Merge branch 'master' of github.com:apache/spark into huge
a2f6a02 [Davies Liu] bug fix
4820613 [Davies Liu] Merge branch 'master' of github.com:apache/spark into huge
5875c73 [Davies Liu] address comments
10a349b [Davies Liu] address comments
0c33016 [Davies Liu] Merge branch 'master' of github.com:apache/spark into huge
6182c8f [Davies Liu] Merge branch 'master' into huge
d94b68f [Davies Liu] Merge branch 'master' of github.com:apache/spark into huge
2514848 [Davies Liu] address comments
fda395b [Davies Liu] Merge branch 'master' of github.com:apache/spark into huge
1c2d928 [Davies Liu] fix scala style
091b107 [Davies Liu] broadcast objects larger than 2G
This PR fix sortBy()/sortByKey() on empty RDD.
This should be back ported into 1.1/1.2
Author: Davies Liu <davies@databricks.com>
Closes#3162 from davies/fix_sort and squashes the following commits:
84f64b7 [Davies Liu] add tests
52995b5 [Davies Liu] fix sortByKey() on empty RDD
add binaryFiles() and binaryRecords() in Python
```
binaryFiles(self, path, minPartitions=None):
:: Developer API ::
Read a directory of binary files from HDFS, a local file system
(available on all nodes), or any Hadoop-supported file system URI
as a byte array. Each file is read as a single record and returned
in a key-value pair, where the key is the path of each file, the
value is the content of each file.
Note: Small files are preferred, large file is also allowable, but
may cause bad performance.
binaryRecords(self, path, recordLength):
Load data from a flat binary file, assuming each record is a set of numbers
with the specified numerical format (see ByteBuffer), and the number of
bytes per record is constant.
:param path: Directory to the input data files
:param recordLength: The length at which to split the records
```
Author: Davies Liu <davies@databricks.com>
Closes#3078 from davies/binary and squashes the following commits:
cd0bdbd [Davies Liu] Merge branch 'master' of github.com:apache/spark into binary
3aa349b [Davies Liu] add experimental notes
24e84b6 [Davies Liu] Merge branch 'master' of github.com:apache/spark into binary
5ceaa8a [Davies Liu] Merge branch 'master' of github.com:apache/spark into binary
1900085 [Davies Liu] bugfix
bb22442 [Davies Liu] add binaryFiles and binaryRecords in Python
This PR simplify serializer, always use batched serializer (AutoBatchedSerializer as default), even batch size is 1.
Author: Davies Liu <davies@databricks.com>
This patch had conflicts when merged, resolved by
Committer: Josh Rosen <joshrosen@databricks.com>
Closes#2920 from davies/fix_autobatch and squashes the following commits:
e544ef9 [Davies Liu] revert unrelated change
6880b14 [Davies Liu] Merge branch 'master' of github.com:apache/spark into fix_autobatch
1d557fc [Davies Liu] fix tests
8180907 [Davies Liu] Merge branch 'master' of github.com:apache/spark into fix_autobatch
76abdce [Davies Liu] clean up
53fa60b [Davies Liu] Merge branch 'master' of github.com:apache/spark into fix_autobatch
d7ac751 [Davies Liu] Merge branch 'master' of github.com:apache/spark into fix_autobatch
2cc2497 [Davies Liu] Merge branch 'master' of github.com:apache/spark into fix_autobatch
b4292ce [Davies Liu] fix bug in master
d79744c [Davies Liu] recover hive tests
be37ece [Davies Liu] refactor
eb3938d [Davies Liu] refactor serializer in scala
8d77ef2 [Davies Liu] simplify serializer, use AutoBatchedSerializer by default.
Following #2919, this PR adds Python UDT (for internal use only) with tests under "pyspark.tests". Before `SQLContext.applySchema`, we check whether we need to convert user-type instances into SQL recognizable data. In the current implementation, a Python UDT must be paired with a Scala UDT for serialization on the JVM side. A following PR will add VectorUDT in MLlib for both Scala and Python.
marmbrus jkbradley davies
Author: Xiangrui Meng <meng@databricks.com>
Closes#3068 from mengxr/SPARK-4192-sql and squashes the following commits:
acff637 [Xiangrui Meng] merge master
dba5ea7 [Xiangrui Meng] only use pyClass for Python UDT output sqlType as well
2c9d7e4 [Xiangrui Meng] move import to global setup; update needsConversion
7c4a6a9 [Xiangrui Meng] address comments
75223db [Xiangrui Meng] minor update
f740379 [Xiangrui Meng] remove UDT from default imports
e98d9d0 [Xiangrui Meng] fix py style
4e84fce [Xiangrui Meng] remove local hive tests and add more tests
39f19e0 [Xiangrui Meng] add tests
b7f666d [Xiangrui Meng] add Python UDT
This patch will try to infer schema for RDD which has empty value (None, [], {}) in the first row. It will try first 100 rows and merge the types into schema, also merge fields of StructType together. If there is still NullType in schema, then it will show an warning, tell user to try with sampling.
If sampling is presented, it will infer schema from all the rows after sampling.
Also, add samplingRatio for jsonFile() and jsonRDD()
Author: Davies Liu <davies.liu@gmail.com>
Author: Davies Liu <davies@databricks.com>
Closes#2716 from davies/infer and squashes the following commits:
e678f6d [Davies Liu] Merge branch 'master' of github.com:apache/spark into infer
34b5c63 [Davies Liu] Merge branch 'master' of github.com:apache/spark into infer
567dc60 [Davies Liu] update docs
9767b27 [Davies Liu] Merge branch 'master' into infer
e48d7fb [Davies Liu] fix tests
29e94d5 [Davies Liu] let NullType inherit from PrimitiveType
ee5d524 [Davies Liu] Merge branch 'master' of github.com:apache/spark into infer
540d1d5 [Davies Liu] merge fields for StructType
f93fd84 [Davies Liu] add more tests
3603e00 [Davies Liu] take more rows to infer schema, or infer the schema by sampling the RDD
The current way of seed distribution makes the random sequences from partition i and i+1 offset by 1.
~~~
In [14]: import random
In [15]: r1 = random.Random(10)
In [16]: r1.randint(0, 1)
Out[16]: 1
In [17]: r1.random()
Out[17]: 0.4288890546751146
In [18]: r1.random()
Out[18]: 0.5780913011344704
In [19]: r2 = random.Random(10)
In [20]: r2.randint(0, 1)
Out[20]: 1
In [21]: r2.randint(0, 1)
Out[21]: 0
In [22]: r2.random()
Out[22]: 0.5780913011344704
~~~
Note: The new tests are not for this bug fix.
Author: Xiangrui Meng <meng@databricks.com>
Closes#3010 from mengxr/SPARK-4148 and squashes the following commits:
869ae4b [Xiangrui Meng] move tests tests.py
c1bacd9 [Xiangrui Meng] fix seed distribution and add some tests for rdd.sample
Call Python UDF on ArrayType/MapType/PrimitiveType, the returnType can also be ArrayType/MapType/PrimitiveType.
For StructType, it will act as tuple (without attributes). If returnType is StructType, it also should be tuple.
Author: Davies Liu <davies@databricks.com>
Closes#2973 from davies/udf_array and squashes the following commits:
306956e [Davies Liu] Merge branch 'master' of github.com:apache/spark into udf_array
2c00e43 [Davies Liu] fix merge
11395fa [Davies Liu] Merge branch 'master' of github.com:apache/spark into udf_array
9df50a2 [Davies Liu] address comments
79afb4e [Davies Liu] type conversionfor python udf
Added a method to Row to turn row into dict:
```
>>> row = Row(a=1)
>>> row.asDict()
{'a': 1}
```
Author: Davies Liu <davies@databricks.com>
Closes#2896 from davies/dict and squashes the following commits:
8d97366 [Davies Liu] convert Row into dict
After take(), maybe there are some garbage left in the socket, then next task assigned to this worker will hang because of corrupted data.
We should make sure the socket is clean before reuse it, write END_OF_STREAM at the end, and check it after read out all result from python.
Author: Davies Liu <davies.liu@gmail.com>
Author: Davies Liu <davies@databricks.com>
Closes#2838 from davies/fix_reuse and squashes the following commits:
8872914 [Davies Liu] fix tests
660875b [Davies Liu] fix bug while reuse worker after take()
Change maximum value for default seed during RDD sampling so that it is strictly less than 2 ** 32. This prevents a bug in the most recent version of NumPy, which cannot accept random seeds above this bound.
Adds an extra test that uses the default seed (instead of setting it manually, as in the docstrings).
mengxr
Author: freeman <the.freeman.lab@gmail.com>
Closes#2889 from freeman-lab/pyspark-sampling and squashes the following commits:
dc385ef [freeman] Change maximum value for default seed
In the current implementation it was possible for the reference to change after analysis.
Author: Michael Armbrust <michael@databricks.com>
Closes#2717 from marmbrus/pythonUdfResults and squashes the following commits:
da14879 [Michael Armbrust] Fix test
6343bcb [Michael Armbrust] add test
9533286 [Michael Armbrust] Correctly preserve the result attribute of python UDFs though transformations
./python/run-tests search a Python 2.6 executable on PATH and use it if available.
When using Python 2.6, it is going to import unittest2 module which is not a standard library in Python 2.6, so it fails with ImportError.
Author: cocoatomo <cocoatomo77@gmail.com>
Closes#2759 from cocoatomo/issues/3867-unittest2-import-error and squashes the following commits:
f068eb5 [cocoatomo] [SPARK-3867] ./python/run-tests failed when it run with Python 2.6 and unittest2 is not installed
This patch try to speed up tests of PySpark, re-use the SparkContext in tests.py and mllib/tests.py to reduce the overhead of create SparkContext, remove some test cases, which did not make sense. It also improve the performance of some cases, such as MergerTests and SortTests.
before this patch:
real 21m27.320s
user 4m42.967s
sys 0m17.343s
after this patch:
real 9m47.541s
user 2m12.947s
sys 0m14.543s
It almost cut the time by half.
Author: Davies Liu <davies.liu@gmail.com>
Closes#2646 from davies/tests and squashes the following commits:
c54de60 [Davies Liu] revert change about memory limit
6a2a4b0 [Davies Liu] refactor of tests, speedup 100%
1. broadcast is triggle unexpected
2. fd is leaked in JVM (also leak in parallelize())
3. broadcast is not unpersisted in JVM after RDD is not be used any more.
cc JoshRosen , sorry for these stupid bugs.
Author: Davies Liu <davies.liu@gmail.com>
Closes#2603 from davies/fix_broadcast and squashes the following commits:
080a743 [Davies Liu] fix bugs in broadcast large closure of RDD
Currently, the schema of object in ArrayType or MapType is attached lazily, it will have better performance but introduce issues while serialization or accessing nested objects.
This patch will apply schema to the objects of ArrayType or MapType immediately when accessing them, will be a little bit slower, but much robust.
Author: Davies Liu <davies.liu@gmail.com>
Closes#2526 from davies/nested and squashes the following commits:
2399ae5 [Davies Liu] fix serialization of List and Map in SchemaRDD
function.func_code.co_names has all the names used in the function, including name of attributes. It will pickle some unnecessary globals if there is a global having the same name with attribute (in co_names).
There is a regression introduced by #2144, revert part of changes in that PR.
cc JoshRosen
Author: Davies Liu <davies.liu@gmail.com>
Closes#2522 from davies/globals and squashes the following commits:
dfbccf5 [Davies Liu] fix bug while pickle globals of function
Python modules added through addPyFile should take precedence over system modules.
This patch put the path for user added module in the front of sys.path (just after '').
Author: Davies Liu <davies.liu@gmail.com>
Closes#2492 from davies/path and squashes the following commits:
4a2af78 [Davies Liu] fix tests
f7ff4da [Davies Liu] ad license header
6b0002f [Davies Liu] add tests
c16c392 [Davies Liu] put addPyFile in front of sys.path
Author: Matthew Farrellee <matt@redhat.com>
Closes#2467 from mattf/master-pyspark-remove-numslices-from-tests and squashes the following commits:
c49a87b [Matthew Farrellee] [PySpark] remove unnecessary use of numSlices from pyspark tests