forked from apache/spark
-
Notifications
You must be signed in to change notification settings - Fork 0
1072 lines (1059 loc) · 46.2 KB
/
build_and_test.yml
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
#
# Licensed to the Apache Software Foundation (ASF) under one
# or more contributor license agreements. See the NOTICE file
# distributed with this work for additional information
# regarding copyright ownership. The ASF licenses this file
# to you under the Apache License, Version 2.0 (the
# "License"); you may not use this file except in compliance
# with the License. You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing,
# software distributed under the License is distributed on an
# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
# KIND, either express or implied. See the License for the
# specific language governing permissions and limitations
# under the License.
#
name: Build and test
on:
workflow_call:
inputs:
java:
required: false
type: string
default: 17
branch:
description: Branch to run the build against
required: false
type: string
# Change 'master' to 'branch-4.0' in branch-4.0 branch after cutting it.
default: master
hadoop:
description: Hadoop version to run with. HADOOP_PROFILE environment variable should accept it.
required: false
type: string
default: hadoop3
envs:
description: Additional environment variables to set when running the tests. Should be in JSON format.
required: false
type: string
default: '{}'
jobs:
description: >-
Jobs to run, and should be in JSON format. The values should be matched with the job's key defined
in this file, e.g., build. See precondition job below.
required: false
type: string
default: ''
jobs:
precondition:
name: Check changes
runs-on: ubuntu-22.04
env:
GITHUB_PREV_SHA: ${{ github.event.before }}
outputs:
required: ${{ steps.set-outputs.outputs.required }}
image_url: >-
${{
(inputs.branch == 'branch-3.3' && 'dongjoon/apache-spark-github-action-image:20220207')
|| steps.infra-image-outputs.outputs.image_url
}}
steps:
- name: Checkout Spark repository
uses: actions/checkout@v3
with:
fetch-depth: 0
repository: apache/spark
ref: ${{ inputs.branch }}
- name: Sync the current branch with the latest in Apache Spark
if: github.repository != 'apache/spark'
run: |
echo "APACHE_SPARK_REF=$(git rev-parse HEAD)" >> $GITHUB_ENV
git fetch https://github.com/$GITHUB_REPOSITORY.git ${GITHUB_REF#refs/heads/}
git -c user.name='Apache Spark Test Account' -c user.email='[email protected]' merge --no-commit --progress --squash FETCH_HEAD
git -c user.name='Apache Spark Test Account' -c user.email='[email protected]' commit -m "Merged commit" --allow-empty
- name: Check all modules
id: set-outputs
run: |
if [ -z "${{ inputs.jobs }}" ]; then
pyspark=true; sparkr=true; tpcds=true; docker=true;
pyspark_modules=`cd dev && python -c "import sparktestsupport.modules as m; print(','.join(m.name for m in m.all_modules if m.name.startswith('pyspark')))"`
pyspark=`./dev/is-changed.py -m $pyspark_modules`
sparkr=`./dev/is-changed.py -m sparkr`
tpcds=`./dev/is-changed.py -m sql`
docker=`./dev/is-changed.py -m docker-integration-tests`
# 'build' and 'java-other-versions' are always true for now.
# It does not save significant time and most of PRs trigger the build.
precondition="
{
\"build\": \"true\",
\"pyspark\": \"$pyspark\",
\"sparkr\": \"$sparkr\",
\"tpcds-1g\": \"$tpcds\",
\"docker-integration-tests\": \"$docker\",
\"java-other-versions\": \"true\",
\"lint\" : \"true\",
\"k8s-integration-tests\" : \"true\",
\"breaking-changes-buf\" : \"true\",
}"
echo $precondition # For debugging
# Remove `\n` to avoid "Invalid format" error
precondition="${precondition//$'\n'/}}"
echo "required=$precondition" >> $GITHUB_OUTPUT
else
# This is usually set by scheduled jobs.
precondition='${{ inputs.jobs }}'
echo $precondition # For debugging
precondition="${precondition//$'\n'/}"
echo "required=$precondition" >> $GITHUB_OUTPUT
fi
- name: Generate infra image URL
id: infra-image-outputs
run: |
# Convert to lowercase to meet Docker repo name requirement
REPO_OWNER=$(echo "${{ github.repository_owner }}" | tr '[:upper:]' '[:lower:]')
IMG_NAME="apache-spark-ci-image:${{ inputs.branch }}-${{ github.run_id }}"
IMG_URL="ghcr.io/$REPO_OWNER/$IMG_NAME"
echo "image_url=$IMG_URL" >> $GITHUB_OUTPUT
# Build: build Spark and run the tests for specified modules.
build:
name: "Build modules: ${{ matrix.modules }} ${{ matrix.comment }}"
needs: precondition
if: fromJson(needs.precondition.outputs.required).build == 'true'
runs-on: ubuntu-22.04
timeout-minutes: 300
strategy:
fail-fast: false
matrix:
java:
- ${{ inputs.java }}
hadoop:
- ${{ inputs.hadoop }}
hive:
- hive2.3
# TODO(SPARK-32246): We don't test 'streaming-kinesis-asl' for now.
# Kinesis tests depends on external Amazon kinesis service.
# Note that the modules below are from sparktestsupport/modules.py.
modules:
- >-
core, unsafe, kvstore, avro,
network-common, network-shuffle, repl, launcher,
examples, sketch, graphx
- >-
catalyst, hive-thriftserver
- >-
streaming, sql-kafka-0-10, streaming-kafka-0-10,
mllib-local, mllib,
yarn, kubernetes, hadoop-cloud, spark-ganglia-lgpl,
connect, protobuf
# Here, we split Hive and SQL tests into some of slow ones and the rest of them.
included-tags: [""]
excluded-tags: [""]
comment: [""]
include:
# Hive tests
- modules: hive
java: ${{ inputs.java }}
hadoop: ${{ inputs.hadoop }}
hive: hive2.3
included-tags: org.apache.spark.tags.SlowHiveTest
comment: "- slow tests"
- modules: hive
java: ${{ inputs.java }}
hadoop: ${{ inputs.hadoop }}
hive: hive2.3
excluded-tags: org.apache.spark.tags.SlowHiveTest
comment: "- other tests"
# SQL tests
- modules: sql
java: ${{ inputs.java }}
hadoop: ${{ inputs.hadoop }}
hive: hive2.3
included-tags: org.apache.spark.tags.ExtendedSQLTest
comment: "- extended tests"
- modules: sql
java: ${{ inputs.java }}
hadoop: ${{ inputs.hadoop }}
hive: hive2.3
included-tags: org.apache.spark.tags.SlowSQLTest
comment: "- slow tests"
- modules: sql
java: ${{ inputs.java }}
hadoop: ${{ inputs.hadoop }}
hive: hive2.3
excluded-tags: org.apache.spark.tags.ExtendedSQLTest,org.apache.spark.tags.SlowSQLTest
comment: "- other tests"
env:
MODULES_TO_TEST: ${{ matrix.modules }}
EXCLUDED_TAGS: ${{ matrix.excluded-tags }}
INCLUDED_TAGS: ${{ matrix.included-tags }}
HADOOP_PROFILE: ${{ matrix.hadoop }}
HIVE_PROFILE: ${{ matrix.hive }}
GITHUB_PREV_SHA: ${{ github.event.before }}
SPARK_LOCAL_IP: localhost
SKIP_UNIDOC: true
SKIP_MIMA: true
SKIP_PACKAGING: true
steps:
- name: Checkout Spark repository
uses: actions/checkout@v3
# In order to fetch changed files
with:
fetch-depth: 0
repository: apache/spark
ref: ${{ inputs.branch }}
- name: Sync the current branch with the latest in Apache Spark
if: github.repository != 'apache/spark'
run: |
echo "APACHE_SPARK_REF=$(git rev-parse HEAD)" >> $GITHUB_ENV
git fetch https://github.com/$GITHUB_REPOSITORY.git ${GITHUB_REF#refs/heads/}
git -c user.name='Apache Spark Test Account' -c user.email='[email protected]' merge --no-commit --progress --squash FETCH_HEAD
git -c user.name='Apache Spark Test Account' -c user.email='[email protected]' commit -m "Merged commit" --allow-empty
# Cache local repositories. Note that GitHub Actions cache has a 2G limit.
- name: Cache Scala, SBT and Maven
uses: actions/cache@v3
with:
path: |
build/apache-maven-*
build/scala-*
build/*.jar
~/.sbt
key: build-${{ hashFiles('**/pom.xml', 'project/build.properties', 'build/mvn', 'build/sbt', 'build/sbt-launch-lib.bash', 'build/spark-build-info') }}
restore-keys: |
build-
- name: Cache Coursier local repository
uses: actions/cache@v3
with:
path: ~/.cache/coursier
key: ${{ matrix.java }}-${{ matrix.hadoop }}-coursier-${{ hashFiles('**/pom.xml', '**/plugins.sbt') }}
restore-keys: |
${{ matrix.java }}-${{ matrix.hadoop }}-coursier-
- name: Free up disk space
run: |
if [ -f ./dev/free_disk_space ]; then
./dev/free_disk_space
fi
- name: Install Java ${{ matrix.java }}
uses: actions/setup-java@v3
with:
distribution: zulu
java-version: ${{ matrix.java }}
- name: Install Python 3.8
uses: actions/setup-python@v4
# We should install one Python that is higher then 3+ for SQL and Yarn because:
# - SQL component also has Python related tests, for example, IntegratedUDFTestUtils.
# - Yarn has a Python specific test too, for example, YarnClusterSuite.
if: contains(matrix.modules, 'yarn') || (contains(matrix.modules, 'sql') && !contains(matrix.modules, 'sql-')) || contains(matrix.modules, 'connect')
with:
python-version: 3.8
architecture: x64
- name: Install Python packages (Python 3.8)
if: (contains(matrix.modules, 'sql') && !contains(matrix.modules, 'sql-')) || contains(matrix.modules, 'connect')
run: |
python3.8 -m pip install 'numpy>=1.20.0' pyarrow pandas scipy unittest-xml-reporting 'grpcio>=1.48,<1.57' 'grpcio-status>=1.48,<1.57' 'protobuf==3.20.3'
python3.8 -m pip list
# Run the tests.
- name: Run tests
env: ${{ fromJSON(inputs.envs) }}
shell: 'script -q -e -c "bash {0}"'
run: |
# Fix for TTY related issues when launching the Ammonite REPL in tests.
export TERM=vt100
# Hive "other tests" test needs larger metaspace size based on experiment.
if [[ "$MODULES_TO_TEST" == "hive" ]] && [[ "$EXCLUDED_TAGS" == "org.apache.spark.tags.SlowHiveTest" ]]; then export METASPACE_SIZE=2g; fi
export SERIAL_SBT_TESTS=1
./dev/run-tests --parallelism 1 --modules "$MODULES_TO_TEST" --included-tags "$INCLUDED_TAGS" --excluded-tags "$EXCLUDED_TAGS"
- name: Upload test results to report
if: always()
uses: actions/upload-artifact@v3
with:
name: test-results-${{ matrix.modules }}-${{ matrix.comment }}-${{ matrix.java }}-${{ matrix.hadoop }}-${{ matrix.hive }}
path: "**/target/test-reports/*.xml"
- name: Upload unit tests log files
if: ${{ !success() }}
uses: actions/upload-artifact@v3
with:
name: unit-tests-log-${{ matrix.modules }}-${{ matrix.comment }}-${{ matrix.java }}-${{ matrix.hadoop }}-${{ matrix.hive }}
path: "**/target/unit-tests.log"
infra-image:
name: "Base image build"
needs: precondition
# Currently, enable docker build from cache for `master` and branch (since 3.4) jobs
if: >-
(fromJson(needs.precondition.outputs.required).pyspark == 'true' ||
fromJson(needs.precondition.outputs.required).lint == 'true' ||
fromJson(needs.precondition.outputs.required).sparkr == 'true') &&
(inputs.branch != 'branch-3.3')
runs-on: ubuntu-latest
permissions:
packages: write
steps:
- name: Login to GitHub Container Registry
uses: docker/login-action@v2
with:
registry: ghcr.io
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
- name: Checkout Spark repository
uses: actions/checkout@v3
# In order to fetch changed files
with:
fetch-depth: 0
repository: apache/spark
ref: ${{ inputs.branch }}
- name: Sync the current branch with the latest in Apache Spark
if: github.repository != 'apache/spark'
run: |
echo "APACHE_SPARK_REF=$(git rev-parse HEAD)" >> $GITHUB_ENV
git fetch https://github.com/$GITHUB_REPOSITORY.git ${GITHUB_REF#refs/heads/}
git -c user.name='Apache Spark Test Account' -c user.email='[email protected]' merge --no-commit --progress --squash FETCH_HEAD
git -c user.name='Apache Spark Test Account' -c user.email='[email protected]' commit -m "Merged commit" --allow-empty
- name: Set up QEMU
uses: docker/setup-qemu-action@v2
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@v2
- name: Build and push
id: docker_build
uses: docker/build-push-action@v3
with:
context: ./dev/infra/
push: true
tags: |
${{ needs.precondition.outputs.image_url }}
# Use the infra image cache to speed up
cache-from: type=registry,ref=ghcr.io/apache/spark/apache-spark-github-action-image-cache:${{ inputs.branch }}
pyspark:
needs: [precondition, infra-image]
# always run if pyspark == 'true', even infra-image is skip (such as non-master job)
if: (!cancelled()) && fromJson(needs.precondition.outputs.required).pyspark == 'true'
name: "Build modules: ${{ matrix.modules }}"
runs-on: ubuntu-22.04
timeout-minutes: 300
container:
image: ${{ needs.precondition.outputs.image_url }}
strategy:
fail-fast: false
matrix:
java:
- ${{ inputs.java }}
modules:
- >-
pyspark-errors
- >-
pyspark-sql, pyspark-resource, pyspark-testing
- >-
pyspark-core, pyspark-streaming
- >-
pyspark-mllib, pyspark-ml, pyspark-ml-connect
- >-
pyspark-pandas
- >-
pyspark-pandas-slow
- >-
pyspark-connect
- >-
pyspark-pandas-connect-part0
- >-
pyspark-pandas-connect-part1
- >-
pyspark-pandas-connect-part2
- >-
pyspark-pandas-connect-part3
env:
MODULES_TO_TEST: ${{ matrix.modules }}
PYTHON_TO_TEST: 'python3.9'
HADOOP_PROFILE: ${{ inputs.hadoop }}
HIVE_PROFILE: hive2.3
GITHUB_PREV_SHA: ${{ github.event.before }}
SPARK_LOCAL_IP: localhost
SKIP_UNIDOC: true
SKIP_MIMA: true
SKIP_PACKAGING: true
METASPACE_SIZE: 1g
BRANCH: ${{ inputs.branch }}
steps:
- name: Checkout Spark repository
uses: actions/checkout@v3
# In order to fetch changed files
with:
fetch-depth: 0
repository: apache/spark
ref: ${{ inputs.branch }}
- name: Add GITHUB_WORKSPACE to git trust safe.directory
run: |
git config --global --add safe.directory ${GITHUB_WORKSPACE}
- name: Sync the current branch with the latest in Apache Spark
if: github.repository != 'apache/spark'
run: |
echo "APACHE_SPARK_REF=$(git rev-parse HEAD)" >> $GITHUB_ENV
git fetch https://github.com/$GITHUB_REPOSITORY.git ${GITHUB_REF#refs/heads/}
git -c user.name='Apache Spark Test Account' -c user.email='[email protected]' merge --no-commit --progress --squash FETCH_HEAD
git -c user.name='Apache Spark Test Account' -c user.email='[email protected]' commit -m "Merged commit" --allow-empty
# Cache local repositories. Note that GitHub Actions cache has a 2G limit.
- name: Cache Scala, SBT and Maven
uses: actions/cache@v3
with:
path: |
build/apache-maven-*
build/scala-*
build/*.jar
~/.sbt
key: build-${{ hashFiles('**/pom.xml', 'project/build.properties', 'build/mvn', 'build/sbt', 'build/sbt-launch-lib.bash', 'build/spark-build-info') }}
restore-keys: |
build-
- name: Cache Coursier local repository
uses: actions/cache@v3
with:
path: ~/.cache/coursier
key: pyspark-coursier-${{ hashFiles('**/pom.xml', '**/plugins.sbt') }}
restore-keys: |
pyspark-coursier-
- name: Free up disk space
shell: 'script -q -e -c "bash {0}"'
run: |
if [[ "$MODULES_TO_TEST" != *"pyspark-ml"* ]] && [[ "$BRANCH" != "branch-3.5" ]]; then
# uninstall libraries dedicated for ML testing
python3.9 -m pip uninstall -y torch torchvision torcheval torchtnt tensorboard mlflow deepspeed
fi
if [ -f ./dev/free_disk_space_container ]; then
./dev/free_disk_space_container
fi
- name: Install Java ${{ matrix.java }}
uses: actions/setup-java@v3
with:
distribution: zulu
java-version: ${{ matrix.java }}
- name: List Python packages (Python 3.9, PyPy3)
run: |
python3.9 -m pip list
pypy3 -m pip list
- name: Install Conda for pip packaging test
if: ${{ matrix.modules == 'pyspark-errors' }}
run: |
curl -s https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh > miniconda.sh
bash miniconda.sh -b -p $HOME/miniconda
rm miniconda.sh
# Run the tests.
- name: Run tests
env: ${{ fromJSON(inputs.envs) }}
shell: 'script -q -e -c "bash {0}"'
run: |
if [[ "$MODULES_TO_TEST" == "pyspark-errors" ]]; then
export PATH=$PATH:$HOME/miniconda/bin
export SKIP_PACKAGING=false
echo "Python Packaging Tests Enabled!"
fi
if [ ! -z "$PYTHON_TO_TEST" ]; then
./dev/run-tests --parallelism 1 --modules "$MODULES_TO_TEST" --python-executables "$PYTHON_TO_TEST"
else
# For branch-3.5 and below, it uses the default Python versions.
./dev/run-tests --parallelism 1 --modules "$MODULES_TO_TEST"
fi
- name: Upload coverage to Codecov
if: fromJSON(inputs.envs).PYSPARK_CODECOV == 'true'
uses: codecov/codecov-action@v2
with:
files: ./python/coverage.xml
flags: unittests
name: PySpark
- name: Upload test results to report
if: always()
uses: actions/upload-artifact@v3
with:
name: test-results-${{ matrix.modules }}--${{ matrix.java }}-${{ inputs.hadoop }}-hive2.3
path: "**/target/test-reports/*.xml"
- name: Upload unit tests log files
if: ${{ !success() }}
uses: actions/upload-artifact@v3
with:
name: unit-tests-log-${{ matrix.modules }}--${{ matrix.java }}-${{ inputs.hadoop }}-hive2.3
path: "**/target/unit-tests.log"
sparkr:
needs: [precondition, infra-image]
# always run if sparkr == 'true', even infra-image is skip (such as non-master job)
if: (!cancelled()) && fromJson(needs.precondition.outputs.required).sparkr == 'true'
name: "Build modules: sparkr"
runs-on: ubuntu-22.04
timeout-minutes: 300
container:
image: ${{ needs.precondition.outputs.image_url }}
env:
HADOOP_PROFILE: ${{ inputs.hadoop }}
HIVE_PROFILE: hive2.3
GITHUB_PREV_SHA: ${{ github.event.before }}
SPARK_LOCAL_IP: localhost
SKIP_UNIDOC: true
SKIP_MIMA: true
SKIP_PACKAGING: true
steps:
- name: Checkout Spark repository
uses: actions/checkout@v3
# In order to fetch changed files
with:
fetch-depth: 0
repository: apache/spark
ref: ${{ inputs.branch }}
- name: Add GITHUB_WORKSPACE to git trust safe.directory
run: |
git config --global --add safe.directory ${GITHUB_WORKSPACE}
- name: Sync the current branch with the latest in Apache Spark
if: github.repository != 'apache/spark'
run: |
echo "APACHE_SPARK_REF=$(git rev-parse HEAD)" >> $GITHUB_ENV
git fetch https://github.com/$GITHUB_REPOSITORY.git ${GITHUB_REF#refs/heads/}
git -c user.name='Apache Spark Test Account' -c user.email='[email protected]' merge --no-commit --progress --squash FETCH_HEAD
git -c user.name='Apache Spark Test Account' -c user.email='[email protected]' commit -m "Merged commit" --allow-empty
# Cache local repositories. Note that GitHub Actions cache has a 2G limit.
- name: Cache Scala, SBT and Maven
uses: actions/cache@v3
with:
path: |
build/apache-maven-*
build/scala-*
build/*.jar
~/.sbt
key: build-${{ hashFiles('**/pom.xml', 'project/build.properties', 'build/mvn', 'build/sbt', 'build/sbt-launch-lib.bash', 'build/spark-build-info') }}
restore-keys: |
build-
- name: Cache Coursier local repository
uses: actions/cache@v3
with:
path: ~/.cache/coursier
key: sparkr-coursier-${{ hashFiles('**/pom.xml', '**/plugins.sbt') }}
restore-keys: |
sparkr-coursier-
- name: Free up disk space
run: |
if [ -f ./dev/free_disk_space_container ]; then
./dev/free_disk_space_container
fi
- name: Install Java ${{ inputs.java }}
uses: actions/setup-java@v3
with:
distribution: zulu
java-version: ${{ inputs.java }}
- name: Run tests
env: ${{ fromJSON(inputs.envs) }}
run: |
# The followings are also used by `r-lib/actions/setup-r` to avoid
# R issues at docker environment
export TZ=UTC
export _R_CHECK_SYSTEM_CLOCK_=FALSE
./dev/run-tests --parallelism 1 --modules sparkr
- name: Upload test results to report
if: always()
uses: actions/upload-artifact@v3
with:
name: test-results-sparkr--${{ inputs.java }}-${{ inputs.hadoop }}-hive2.3
path: "**/target/test-reports/*.xml"
breaking-changes-buf:
needs: [precondition]
if: (!cancelled()) && fromJson(needs.precondition.outputs.required).breaking-changes-buf == 'true'
# Change 'branch-3.5' to 'branch-4.0' in master branch after cutting branch-4.0 branch.
name: Breaking change detection with Buf (branch-3.5)
runs-on: ubuntu-22.04
steps:
- name: Checkout Spark repository
uses: actions/checkout@v3
with:
fetch-depth: 0
repository: apache/spark
ref: ${{ inputs.branch }}
- name: Sync the current branch with the latest in Apache Spark
if: github.repository != 'apache/spark'
run: |
git fetch https://github.com/$GITHUB_REPOSITORY.git ${GITHUB_REF#refs/heads/}
git -c user.name='Apache Spark Test Account' -c user.email='[email protected]' merge --no-commit --progress --squash FETCH_HEAD
git -c user.name='Apache Spark Test Account' -c user.email='[email protected]' commit -m "Merged commit" --allow-empty
- name: Install Buf
uses: bufbuild/buf-setup-action@v1
with:
github_token: ${{ secrets.GITHUB_TOKEN }}
- name: Detect breaking changes
uses: bufbuild/buf-breaking-action@v1
with:
input: connector/connect/common/src/main
against: 'https://github.com/apache/spark.git#branch=branch-3.5,subdir=connector/connect/common/src/main'
# Static analysis, and documentation build
lint:
needs: [precondition, infra-image]
# always run if lint == 'true', even infra-image is skip (such as non-master job)
if: (!cancelled()) && fromJson(needs.precondition.outputs.required).lint == 'true'
name: Linters, licenses, dependencies and documentation generation
runs-on: ubuntu-22.04
timeout-minutes: 300
env:
LC_ALL: C.UTF-8
LANG: C.UTF-8
PYSPARK_DRIVER_PYTHON: python3.9
PYSPARK_PYTHON: python3.9
GITHUB_PREV_SHA: ${{ github.event.before }}
container:
image: ${{ needs.precondition.outputs.image_url }}
steps:
- name: Checkout Spark repository
uses: actions/checkout@v3
with:
fetch-depth: 0
repository: apache/spark
ref: ${{ inputs.branch }}
- name: Add GITHUB_WORKSPACE to git trust safe.directory
run: |
git config --global --add safe.directory ${GITHUB_WORKSPACE}
- name: Sync the current branch with the latest in Apache Spark
if: github.repository != 'apache/spark'
run: |
echo "APACHE_SPARK_REF=$(git rev-parse HEAD)" >> $GITHUB_ENV
git fetch https://github.com/$GITHUB_REPOSITORY.git ${GITHUB_REF#refs/heads/}
git -c user.name='Apache Spark Test Account' -c user.email='[email protected]' merge --no-commit --progress --squash FETCH_HEAD
git -c user.name='Apache Spark Test Account' -c user.email='[email protected]' commit -m "Merged commit" --allow-empty
# Cache local repositories. Note that GitHub Actions cache has a 2G limit.
- name: Cache Scala, SBT and Maven
uses: actions/cache@v3
with:
path: |
build/apache-maven-*
build/scala-*
build/*.jar
~/.sbt
key: build-${{ hashFiles('**/pom.xml', 'project/build.properties', 'build/mvn', 'build/sbt', 'build/sbt-launch-lib.bash', 'build/spark-build-info') }}
restore-keys: |
build-
- name: Cache Coursier local repository
uses: actions/cache@v3
with:
path: ~/.cache/coursier
key: docs-coursier-${{ hashFiles('**/pom.xml', '**/plugins.sbt') }}
restore-keys: |
docs-coursier-
- name: Cache Maven local repository
uses: actions/cache@v3
with:
path: ~/.m2/repository
key: docs-maven-${{ hashFiles('**/pom.xml') }}
restore-keys: |
docs-maven-
- name: Free up disk space
run: |
if [ -f ./dev/free_disk_space_container ]; then
./dev/free_disk_space_container
fi
- name: Install Java ${{ inputs.java }}
uses: actions/setup-java@v3
with:
distribution: zulu
java-version: ${{ inputs.java }}
- name: License test
run: ./dev/check-license
- name: Dependencies test
run: ./dev/test-dependencies.sh
- name: MIMA test
run: ./dev/mima
- name: Scala linter
run: ./dev/lint-scala
- name: Java linter
run: ./dev/lint-java
- name: Spark connect jvm client mima check
if: inputs.branch != 'branch-3.3'
run: ./dev/connect-jvm-client-mima-check
- name: Install Python linter dependencies for branch-3.3
if: inputs.branch == 'branch-3.3'
run: |
# SPARK-44554: Copy from https://github.com/apache/spark/blob/073d0b60d31bf68ebacdc005f59b928a5902670f/.github/workflows/build_and_test.yml#L501-L508
# Should delete this section after SPARK 3.3 EOL.
python3.9 -m pip install 'flake8==3.9.0' pydata_sphinx_theme 'mypy==0.920' 'pytest==7.1.3' 'pytest-mypy-plugins==1.9.3' numpydoc 'jinja2<3.0.0' 'black==21.12b0'
python3.9 -m pip install 'pandas-stubs==1.2.0.53' ipython
- name: Install Python linter dependencies for branch-3.4
if: inputs.branch == 'branch-3.4'
run: |
# SPARK-44554: Copy from https://github.com/apache/spark/blob/a05c27e85829fe742c1828507a1fd180cdc84b54/.github/workflows/build_and_test.yml#L571-L578
# Should delete this section after SPARK 3.4 EOL.
python3.9 -m pip install 'flake8==3.9.0' pydata_sphinx_theme 'mypy==0.920' 'pytest==7.1.3' 'pytest-mypy-plugins==1.9.3' numpydoc 'jinja2<3.0.0' 'black==22.6.0'
python3.9 -m pip install 'pandas-stubs==1.2.0.53' ipython 'grpcio==1.48.1' 'grpc-stubs==1.24.11' 'googleapis-common-protos-stubs==2.2.0'
- name: Install Python linter dependencies for branch-3.5
if: inputs.branch == 'branch-3.5'
run: |
# SPARK-45212: Copy from https://github.com/apache/spark/blob/555c8def51e5951c7bf5165a332795e9e330ec9d/.github/workflows/build_and_test.yml#L631-L638
# Should delete this section after SPARK 3.5 EOL.
python3.9 -m pip install 'flake8==3.9.0' pydata_sphinx_theme 'mypy==0.982' 'pytest==7.1.3' 'pytest-mypy-plugins==1.9.3' numpydoc 'jinja2<3.0.0' 'black==22.6.0'
python3.9 -m pip install 'pandas-stubs==1.2.0.53' ipython 'grpcio==1.56.0' 'grpc-stubs==1.24.11' 'googleapis-common-protos-stubs==2.2.0'
- name: Install Python linter dependencies
if: inputs.branch != 'branch-3.3' && inputs.branch != 'branch-3.4' && inputs.branch != 'branch-3.5'
run: |
# TODO(SPARK-32407): Sphinx 3.1+ does not correctly index nested classes.
# See also https://github.com/sphinx-doc/sphinx/issues/7551.
# Jinja2 3.0.0+ causes error when building with Sphinx.
# See also https://issues.apache.org/jira/browse/SPARK-35375.
python3.9 -m pip install 'flake8==3.9.0' pydata_sphinx_theme 'mypy==0.982' 'pytest==7.1.3' 'pytest-mypy-plugins==1.9.3' numpydoc 'jinja2<3.0.0' 'black==23.9.1'
python3.9 -m pip install 'pandas-stubs==1.2.0.53' ipython 'grpcio==1.56.0' 'grpc-stubs==1.24.11' 'googleapis-common-protos-stubs==2.2.0'
- name: Python linter
run: PYTHON_EXECUTABLE=python3.9 ./dev/lint-python
- name: Install dependencies for Python code generation check
if: inputs.branch != 'branch-3.3' && inputs.branch != 'branch-3.4'
run: |
# See more in "Installation" https://docs.buf.build/installation#tarball
curl -LO https://github.com/bufbuild/buf/releases/download/v1.26.1/buf-Linux-x86_64.tar.gz
mkdir -p $HOME/buf
tar -xvzf buf-Linux-x86_64.tar.gz -C $HOME/buf --strip-components 1
rm buf-Linux-x86_64.tar.gz
python3.9 -m pip install 'protobuf==3.20.3' 'mypy-protobuf==3.3.0'
- name: Python code generation check
if: inputs.branch != 'branch-3.3' && inputs.branch != 'branch-3.4'
run: if test -f ./dev/connect-check-protos.py; then PATH=$PATH:$HOME/buf/bin PYTHON_EXECUTABLE=python3.9 ./dev/connect-check-protos.py; fi
- name: Install JavaScript linter dependencies
run: |
apt update
apt-get install -y nodejs npm
- name: JS linter
run: ./dev/lint-js
- name: Install R linter dependencies and SparkR
run: |
apt update
apt-get install -y libcurl4-openssl-dev libgit2-dev libssl-dev libxml2-dev \
libfontconfig1-dev libharfbuzz-dev libfribidi-dev libfreetype6-dev libpng-dev \
libtiff5-dev libjpeg-dev
Rscript -e "install.packages(c('devtools'), repos='https://cloud.r-project.org/')"
Rscript -e "devtools::install_version('lintr', version='2.0.1', repos='https://cloud.r-project.org')"
./R/install-dev.sh
- name: Install dependencies for documentation generation
run: |
# pandoc is required to generate PySpark APIs as well in nbsphinx.
apt-get install -y libcurl4-openssl-dev pandoc
# TODO(SPARK-32407): Sphinx 3.1+ does not correctly index nested classes.
# See also https://github.com/sphinx-doc/sphinx/issues/7551.
# Jinja2 3.0.0+ causes error when building with Sphinx.
# See also https://issues.apache.org/jira/browse/SPARK-35375.
# Pin the MarkupSafe to 2.0.1 to resolve the CI error.
# See also https://issues.apache.org/jira/browse/SPARK-38279.
python3.9 -m pip install 'sphinx<3.1.0' mkdocs pydata_sphinx_theme nbsphinx numpydoc 'jinja2<3.0.0' 'markupsafe==2.0.1' 'pyzmq<24.0.0'
python3.9 -m pip install ipython_genutils # See SPARK-38517
python3.9 -m pip install sphinx_plotly_directive 'numpy>=1.20.0' pyarrow pandas 'plotly>=4.8'
python3.9 -m pip install 'docutils<0.18.0' # See SPARK-39421
apt-get update -y
apt-get install -y ruby ruby-dev
Rscript -e "install.packages(c('devtools', 'testthat', 'knitr', 'rmarkdown', 'markdown', 'e1071', 'roxygen2', 'ggplot2', 'mvtnorm', 'statmod'), repos='https://cloud.r-project.org/')"
Rscript -e "devtools::install_version('pkgdown', version='2.0.1', repos='https://cloud.r-project.org')"
Rscript -e "devtools::install_version('preferably', version='0.4', repos='https://cloud.r-project.org')"
gem install bundler
cd docs
bundle install
- name: R linter
run: ./dev/lint-r
- name: Run documentation build
run: |
if [ -f "./dev/is-changed.py" ]; then
# Skip PySpark and SparkR docs while keeping Scala/Java/SQL docs
pyspark_modules=`cd dev && python3.9 -c "import sparktestsupport.modules as m; print(','.join(m.name for m in m.all_modules if m.name.startswith('pyspark')))"`
if [ `./dev/is-changed.py -m $pyspark_modules` = false ]; then export SKIP_PYTHONDOC=1; fi
if [ `./dev/is-changed.py -m sparkr` = false ]; then export SKIP_RDOC=1; fi
fi
cd docs
bundle exec jekyll build
- name: Tar documentation
if: github.repository != 'apache/spark'
run: tar cjf site.tar.bz2 docs/_site
- name: Upload documentation
if: github.repository != 'apache/spark'
uses: actions/upload-artifact@v3
with:
name: site
path: site.tar.bz2
retention-days: 1
java-other-versions:
needs: precondition
if: fromJson(needs.precondition.outputs.required).java-other-versions == 'true'
name: Java ${{ matrix.java }} build with Maven
strategy:
fail-fast: false
matrix:
java:
- 17
- 21
runs-on: ubuntu-22.04
timeout-minutes: 300
steps:
- name: Checkout Spark repository
uses: actions/checkout@v3
with:
fetch-depth: 0
repository: apache/spark
ref: ${{ inputs.branch }}
- name: Sync the current branch with the latest in Apache Spark
if: github.repository != 'apache/spark'
run: |
git fetch https://github.com/$GITHUB_REPOSITORY.git ${GITHUB_REF#refs/heads/}
git -c user.name='Apache Spark Test Account' -c user.email='[email protected]' merge --no-commit --progress --squash FETCH_HEAD
git -c user.name='Apache Spark Test Account' -c user.email='[email protected]' commit -m "Merged commit" --allow-empty
- name: Cache Scala, SBT and Maven
uses: actions/cache@v3
with:
path: |
build/apache-maven-*
build/scala-*
build/*.jar
~/.sbt
key: build-${{ hashFiles('**/pom.xml', 'project/build.properties', 'build/mvn', 'build/sbt', 'build/sbt-launch-lib.bash', 'build/spark-build-info') }}
restore-keys: |
build-
- name: Cache Maven local repository
uses: actions/cache@v3
with:
path: ~/.m2/repository
key: java${{ matrix.java }}-maven-${{ hashFiles('**/pom.xml') }}
restore-keys: |
java${{ matrix.java }}-maven-
- name: Install Java ${{ matrix.java }}
uses: actions/setup-java@v3
with:
distribution: zulu
java-version: ${{ matrix.java }}
- name: Build with Maven
run: |
export MAVEN_OPTS="-Xss64m -Xmx2g -XX:ReservedCodeCacheSize=1g -Dorg.slf4j.simpleLogger.defaultLogLevel=WARN"
export MAVEN_CLI_OPTS="--no-transfer-progress"
export JAVA_VERSION=${{ matrix.java }}
# It uses Maven's 'install' intentionally, see https://github.com/apache/spark/pull/26414.
./build/mvn $MAVEN_CLI_OPTS -DskipTests -Pyarn -Pkubernetes -Pvolcano -Phive -Phive-thriftserver -Phadoop-cloud -Djava.version=${JAVA_VERSION/-ea} install
rm -rf ~/.m2/repository/org/apache/spark
# Any TPC-DS related updates on this job need to be applied to tpcds-1g-gen job of benchmark.yml as well
tpcds-1g:
needs: precondition
if: fromJson(needs.precondition.outputs.required).tpcds-1g == 'true'
name: Run TPC-DS queries with SF=1
# Pin to 'Ubuntu 20.04' due to 'databricks/tpcds-kit' compilation
runs-on: ubuntu-20.04
timeout-minutes: 300
env:
SPARK_LOCAL_IP: localhost
steps:
- name: Checkout Spark repository
uses: actions/checkout@v3
with:
fetch-depth: 0
repository: apache/spark
ref: ${{ inputs.branch }}
- name: Sync the current branch with the latest in Apache Spark
if: github.repository != 'apache/spark'
run: |
git fetch https://github.com/$GITHUB_REPOSITORY.git ${GITHUB_REF#refs/heads/}
git -c user.name='Apache Spark Test Account' -c user.email='[email protected]' merge --no-commit --progress --squash FETCH_HEAD
git -c user.name='Apache Spark Test Account' -c user.email='[email protected]' commit -m "Merged commit" --allow-empty
- name: Cache Scala, SBT and Maven
uses: actions/cache@v3
with:
path: |
build/apache-maven-*
build/scala-*
build/*.jar
~/.sbt
key: build-${{ hashFiles('**/pom.xml', 'project/build.properties', 'build/mvn', 'build/sbt', 'build/sbt-launch-lib.bash', 'build/spark-build-info') }}
restore-keys: |
build-
- name: Cache Coursier local repository
uses: actions/cache@v3
with:
path: ~/.cache/coursier
key: tpcds-coursier-${{ hashFiles('**/pom.xml', '**/plugins.sbt') }}
restore-keys: |
tpcds-coursier-
- name: Install Java ${{ inputs.java }}
uses: actions/setup-java@v3
with:
distribution: zulu
java-version: ${{ inputs.java }}
- name: Cache TPC-DS generated data
id: cache-tpcds-sf-1
uses: actions/cache@v3
with:
path: ./tpcds-sf-1
key: tpcds-${{ hashFiles('.github/workflows/build_and_test.yml', 'sql/core/src/test/scala/org/apache/spark/sql/TPCDSSchema.scala') }}
- name: Checkout tpcds-kit repository
if: steps.cache-tpcds-sf-1.outputs.cache-hit != 'true'
uses: actions/checkout@v3
with:
repository: databricks/tpcds-kit
ref: 2a5078a782192ddb6efbcead8de9973d6ab4f069
path: ./tpcds-kit
- name: Build tpcds-kit
if: steps.cache-tpcds-sf-1.outputs.cache-hit != 'true'
run: cd tpcds-kit/tools && make OS=LINUX
- name: Generate TPC-DS (SF=1) table data
if: steps.cache-tpcds-sf-1.outputs.cache-hit != 'true'
run: build/sbt "sql/Test/runMain org.apache.spark.sql.GenTPCDSData --dsdgenDir `pwd`/tpcds-kit/tools --location `pwd`/tpcds-sf-1 --scaleFactor 1 --numPartitions 1 --overwrite"
- name: Run TPC-DS queries (Sort merge join)
run: |
SPARK_TPCDS_DATA=`pwd`/tpcds-sf-1 build/sbt "sql/testOnly org.apache.spark.sql.TPCDSQueryTestSuite"
env:
SPARK_ANSI_SQL_MODE: ${{ fromJSON(inputs.envs).SPARK_ANSI_SQL_MODE }}
SPARK_TPCDS_JOIN_CONF: |
spark.sql.autoBroadcastJoinThreshold=-1
spark.sql.join.preferSortMergeJoin=true
- name: Run TPC-DS queries (Broadcast hash join)
run: |
SPARK_TPCDS_DATA=`pwd`/tpcds-sf-1 build/sbt "sql/testOnly org.apache.spark.sql.TPCDSQueryTestSuite"
env:
SPARK_ANSI_SQL_MODE: ${{ fromJSON(inputs.envs).SPARK_ANSI_SQL_MODE }}
SPARK_TPCDS_JOIN_CONF: |
spark.sql.autoBroadcastJoinThreshold=10485760
- name: Run TPC-DS queries (Shuffled hash join)
run: |
SPARK_TPCDS_DATA=`pwd`/tpcds-sf-1 build/sbt "sql/testOnly org.apache.spark.sql.TPCDSQueryTestSuite"
env:
SPARK_ANSI_SQL_MODE: ${{ fromJSON(inputs.envs).SPARK_ANSI_SQL_MODE }}
SPARK_TPCDS_JOIN_CONF: |
spark.sql.autoBroadcastJoinThreshold=-1
spark.sql.join.forceApplyShuffledHashJoin=true
- name: Upload test results to report
if: always()
uses: actions/upload-artifact@v3
with:
name: test-results-tpcds--${{ inputs.java }}-${{ inputs.hadoop }}-hive2.3
path: "**/target/test-reports/*.xml"
- name: Upload unit tests log files
if: ${{ !success() }}
uses: actions/upload-artifact@v3
with:
name: unit-tests-log-tpcds--${{ inputs.java }}-${{ inputs.hadoop }}-hive2.3
path: "**/target/unit-tests.log"
docker-integration-tests:
needs: precondition
if: fromJson(needs.precondition.outputs.required).docker-integration-tests == 'true'
name: Run Docker integration tests
runs-on: ubuntu-22.04
timeout-minutes: 300
env:
HADOOP_PROFILE: ${{ inputs.hadoop }}
HIVE_PROFILE: hive2.3
GITHUB_PREV_SHA: ${{ github.event.before }}
SPARK_LOCAL_IP: localhost
ORACLE_DOCKER_IMAGE_NAME: gvenzl/oracle-free:23.3
SKIP_MIMA: true
SKIP_PACKAGING: true
steps:
- name: Checkout Spark repository
uses: actions/checkout@v3
with:
fetch-depth: 0
repository: apache/spark
ref: ${{ inputs.branch }}
- name: Sync the current branch with the latest in Apache Spark
if: github.repository != 'apache/spark'
run: |
echo "APACHE_SPARK_REF=$(git rev-parse HEAD)" >> $GITHUB_ENV
git fetch https://github.com/$GITHUB_REPOSITORY.git ${GITHUB_REF#refs/heads/}
git -c user.name='Apache Spark Test Account' -c user.email='[email protected]' merge --no-commit --progress --squash FETCH_HEAD
git -c user.name='Apache Spark Test Account' -c user.email='[email protected]' commit -m "Merged commit" --allow-empty
- name: Cache Scala, SBT and Maven
uses: actions/cache@v3
with:
path: |
build/apache-maven-*
build/scala-*
build/*.jar
~/.sbt
key: build-${{ hashFiles('**/pom.xml', 'project/build.properties', 'build/mvn', 'build/sbt', 'build/sbt-launch-lib.bash', 'build/spark-build-info') }}
restore-keys: |
build-
- name: Cache Coursier local repository
uses: actions/cache@v3
with:
path: ~/.cache/coursier
key: docker-integration-coursier-${{ hashFiles('**/pom.xml', '**/plugins.sbt') }}
restore-keys: |
docker-integration-coursier-
- name: Install Java ${{ inputs.java }}
uses: actions/setup-java@v3
with:
distribution: zulu
java-version: ${{ inputs.java }}
- name: Run tests
run: |
./dev/run-tests --parallelism 1 --modules docker-integration-tests --included-tags org.apache.spark.tags.DockerTest
- name: Upload test results to report
if: always()
uses: actions/upload-artifact@v3
with:
name: test-results-docker-integration--${{ inputs.java }}-${{ inputs.hadoop }}-hive2.3
path: "**/target/test-reports/*.xml"
- name: Upload unit tests log files
if: ${{ !success() }}
uses: actions/upload-artifact@v3
with:
name: unit-tests-log-docker-integration--${{ inputs.java }}-${{ inputs.hadoop }}-hive2.3
path: "**/target/unit-tests.log"
k8s-integration-tests:
needs: precondition