This is an automated email from the ASF dual-hosted git repository. github-bot pushed a change to branch nightly-refs/heads/master in repository https://gitbox.apache.org/repos/asf/beam.git
from 71c8459633e [Blog Post] Apache Beam for a content discovery platform (#28734) add 1c5982567b3 Bump cloud.google.com/go/bigtable from 1.19.0 to 1.20.0 in /sdks (#28789) add 25024064ed2 Bump github.com/aws/aws-sdk-go-v2/config in /sdks (#28790) add b556aee9177 Bump urllib3 from 1.26.16 to 1.26.17 in /sdks/python/container/py38 (#28787) add c7d7896533b Github Workflow Replacement for Jenkins Jobs, beam_LoadTests_Java_GBK_Dataflow_Batch_* (#28738) add 2e0521162f6 [Java BQ] Storage API streaming load test (#28264) add 3655b1ea3fb Update dyi-content-discovery-platform-genai-beam.md add f3df03d8fa9 Merge pull request #28788 from apache/aaltay-patch-1 add 12b07140203 Add notebook for per key models (#28327) add c01b41f9758 Bump urllib3 from 1.26.16 to 1.26.17 in /sdks/python/container/py310 (#28785) add be805372238 BigQuery testing suite that runs against BQ's day 0 region (#28397) add f6b43ce1736 Revert "assign highmem runner to beam_PostCommit_Python and to beam_PreCommit_Java_GCP_IO_Direct (#28719)" (#28804) No new revisions were added by this update. Summary of changes: .../beam_LoadTests_Java_GBK_Dataflow_Batch.yml | 141 +++++ .../beam_LoadTests_Java_GBK_Dataflow_Streaming.yml | 141 +++++ ...LoadTests_Java_GBK_Dataflow_V2_Batch_Java11.yml | 166 ++++++ ...LoadTests_Java_GBK_Dataflow_V2_Batch_Java17.yml | 168 ++++++ ...Tests_Java_GBK_Dataflow_V2_Streaming_Java11.yml | 166 ++++++ ...Tests_Java_GBK_Dataflow_V2_Streaming_Java17.yml | 168 ++++++ ... beam_PostCommit_Java_BigQueryEarlyRollout.yml} | 68 +-- .../beam_PostCommit_Java_IO_Performance_Tests.yml | 2 +- .github/workflows/beam_PostCommit_Python.yml | 2 +- .../beam_PreCommit_Java_GCP_IO_Direct.yml | 2 +- ...java_GBK_Dataflow_Batch_2GB_of_100B_records.txt | 28 + ...ava_GBK_Dataflow_Batch_2GB_of_100kB_records.txt | 28 + .../java_GBK_Dataflow_Batch_2GB_of_10B_records.txt | 28 + ...nout_4_times_with_2GB_10-byte_records_total.txt | 28 + ...nout_8_times_with_2GB_10-byte_records_total.txt | 28 + ...ataflow_Batch_reiterate_4_times_10kB_values.txt | 28 + ...Dataflow_Batch_reiterate_4_times_2MB_values.txt | 28 + ..._GBK_Dataflow_Streaming_2GB_of_100B_records.txt | 29 + ...GBK_Dataflow_Streaming_2GB_of_100kB_records.txt | 29 + ...a_GBK_Dataflow_Streaming_2GB_of_10B_records.txt | 29 + ...nout_4_times_with_2GB_10-byte_records_total.txt | 29 + ...nout_8_times_with_2GB_10-byte_records_total.txt | 29 + ...low_Streaming_reiterate_4_times_10kB_values.txt | 29 + ...flow_Streaming_reiterate_4_times_2MB_values.txt | 29 + ...ataflow_V2_Batch_Java11_2GB_of_100B_records.txt | 29 + ...taflow_V2_Batch_Java11_2GB_of_100kB_records.txt | 29 + ...Dataflow_V2_Batch_Java11_2GB_of_10B_records.txt | 29 + ...nout_4_times_with_2GB_10-byte_records_total.txt | 29 + ...nout_8_times_with_2GB_10-byte_records_total.txt | 29 + ..._Batch_Java11_reiterate_4_times_10kB_values.txt | 29 + ...2_Batch_Java11_reiterate_4_times_2MB_values.txt | 29 + ...ataflow_V2_Batch_Java17_2GB_of_100B_records.txt | 29 + ...taflow_V2_Batch_Java17_2GB_of_100kB_records.txt | 29 + ...Dataflow_V2_Batch_Java17_2GB_of_10B_records.txt | 29 + ...nout_4_times_with_2GB_10-byte_records_total.txt | 29 + ...nout_8_times_with_2GB_10-byte_records_total.txt | 29 + ..._Batch_Java17_reiterate_4_times_10kB_values.txt | 29 + ...2_Batch_Java17_reiterate_4_times_2MB_values.txt | 29 + ...low_V2_Streaming_Java11_2GB_of_100B_records.txt | 30 + ...ow_V2_Streaming_Java11_2GB_of_100kB_records.txt | 30 + ...flow_V2_Streaming_Java11_2GB_of_10B_records.txt | 30 + ...nout_4_times_with_2GB_10-byte_records_total.txt | 30 + ...nout_8_times_with_2GB_10-byte_records_total.txt | 30 + ...eaming_Java11_reiterate_4_times_10kB_values.txt | 30 + ...reaming_Java11_reiterate_4_times_2MB_values.txt | 30 + ...low_V2_Streaming_Java17_2GB_of_100B_records.txt | 30 + ...ow_V2_Streaming_Java17_2GB_of_100kB_records.txt | 30 + ...flow_V2_Streaming_Java17_2GB_of_10B_records.txt | 30 + ...nout_4_times_with_2GB_10-byte_records_total.txt | 30 + ...nout_8_times_with_2GB_10-byte_records_total.txt | 30 + ...eaming_Java17_reiterate_4_times_10kB_values.txt | 30 + ...reaming_Java17_reiterate_4_times_2MB_values.txt | 30 + examples/notebooks/beam-ml/README.md | 1 + examples/notebooks/beam-ml/per_key_models.ipynb | 608 +++++++++++++++++++ it/build.gradle | 4 + it/google-cloud-platform/build.gradle | 5 +- .../beam/it/gcp/bigquery/BigQueryStreamingLT.java | 643 +++++++++++++++++++++ sdks/go.mod | 10 +- sdks/go.sum | 16 +- sdks/java/io/google-cloud-platform/build.gradle | 44 +- .../beam/sdk/io/gcp/bigquery/BigQueryIO.java | 6 +- .../sdk/io/gcp/bigquery/BigQueryServicesImpl.java | 6 +- .../beam/sdk/io/gcp/bigquery/BigQueryUtils.java | 29 +- .../sdk/io/gcp/bigquery/TestBigQueryOptions.java | 7 + .../gcp/common/GcpIoPipelineOptionsRegistrar.java | 2 + .../beam/sdk/io/gcp/testing/BigqueryClient.java | 37 +- .../io/gcp/bigquery/BigQueryIOStorageQueryIT.java | 10 +- .../io/gcp/bigquery/BigQueryIOStorageReadIT.java | 9 +- .../bigquery/BigQueryIOStorageReadTableRowIT.java | 43 +- .../io/gcp/bigquery/BigQueryIOStorageWriteIT.java | 31 +- .../bigquery/BigQuerySchemaUpdateOptionsIT.java | 6 +- .../BigQueryTimePartitioningClusteringIT.java | 42 +- .../sdk/io/gcp/bigquery/BigQueryToTableIT.java | 9 +- .../sdk/io/gcp/bigquery/BigQueryUtilsTest.java | 37 +- .../sdk/io/gcp/bigquery/FileLoadsStreamingIT.java | 9 +- .../bigquery/StorageApiDirectWriteProtosIT.java | 9 +- .../gcp/bigquery/StorageApiSinkFailedRowsIT.java | 13 +- .../io/gcp/bigquery/StorageApiSinkRowUpdateIT.java | 9 +- .../gcp/bigquery/StorageApiSinkSchemaUpdateIT.java | 17 +- .../gcp/bigquery/TableRowToStorageApiProtoIT.java | 11 +- .../container/py310/base_image_requirements.txt | 2 +- .../container/py38/base_image_requirements.txt | 2 +- .../dyi-content-discovery-platform-genai-beam.md | 2 +- 83 files changed, 3802 insertions(+), 126 deletions(-) create mode 100644 .github/workflows/beam_LoadTests_Java_GBK_Dataflow_Batch.yml create mode 100644 .github/workflows/beam_LoadTests_Java_GBK_Dataflow_Streaming.yml create mode 100644 .github/workflows/beam_LoadTests_Java_GBK_Dataflow_V2_Batch_Java11.yml create mode 100644 .github/workflows/beam_LoadTests_Java_GBK_Dataflow_V2_Batch_Java17.yml create mode 100644 .github/workflows/beam_LoadTests_Java_GBK_Dataflow_V2_Streaming_Java11.yml create mode 100644 .github/workflows/beam_LoadTests_Java_GBK_Dataflow_V2_Streaming_Java17.yml copy .github/workflows/{beam_PostCommit_Python.yml => beam_PostCommit_Java_BigQueryEarlyRollout.yml} (57%) create mode 100644 .github/workflows/load-tests-job-configs/java_GBK_Dataflow_Batch_2GB_of_100B_records.txt create mode 100644 .github/workflows/load-tests-job-configs/java_GBK_Dataflow_Batch_2GB_of_100kB_records.txt create mode 100644 .github/workflows/load-tests-job-configs/java_GBK_Dataflow_Batch_2GB_of_10B_records.txt create mode 100644 .github/workflows/load-tests-job-configs/java_GBK_Dataflow_Batch_fanout_4_times_with_2GB_10-byte_records_total.txt create mode 100644 .github/workflows/load-tests-job-configs/java_GBK_Dataflow_Batch_fanout_8_times_with_2GB_10-byte_records_total.txt create mode 100644 .github/workflows/load-tests-job-configs/java_GBK_Dataflow_Batch_reiterate_4_times_10kB_values.txt create mode 100644 .github/workflows/load-tests-job-configs/java_GBK_Dataflow_Batch_reiterate_4_times_2MB_values.txt create mode 100644 .github/workflows/load-tests-job-configs/java_GBK_Dataflow_Streaming_2GB_of_100B_records.txt create mode 100644 .github/workflows/load-tests-job-configs/java_GBK_Dataflow_Streaming_2GB_of_100kB_records.txt create mode 100644 .github/workflows/load-tests-job-configs/java_GBK_Dataflow_Streaming_2GB_of_10B_records.txt create mode 100644 .github/workflows/load-tests-job-configs/java_GBK_Dataflow_Streaming_fanout_4_times_with_2GB_10-byte_records_total.txt create mode 100644 .github/workflows/load-tests-job-configs/java_GBK_Dataflow_Streaming_fanout_8_times_with_2GB_10-byte_records_total.txt create mode 100644 .github/workflows/load-tests-job-configs/java_GBK_Dataflow_Streaming_reiterate_4_times_10kB_values.txt create mode 100644 .github/workflows/load-tests-job-configs/java_GBK_Dataflow_Streaming_reiterate_4_times_2MB_values.txt create mode 100644 .github/workflows/load-tests-job-configs/java_GBK_Dataflow_V2_Batch_Java11_2GB_of_100B_records.txt create mode 100644 .github/workflows/load-tests-job-configs/java_GBK_Dataflow_V2_Batch_Java11_2GB_of_100kB_records.txt create mode 100644 .github/workflows/load-tests-job-configs/java_GBK_Dataflow_V2_Batch_Java11_2GB_of_10B_records.txt create mode 100644 .github/workflows/load-tests-job-configs/java_GBK_Dataflow_V2_Batch_Java11_fanout_4_times_with_2GB_10-byte_records_total.txt create mode 100644 .github/workflows/load-tests-job-configs/java_GBK_Dataflow_V2_Batch_Java11_fanout_8_times_with_2GB_10-byte_records_total.txt create mode 100644 .github/workflows/load-tests-job-configs/java_GBK_Dataflow_V2_Batch_Java11_reiterate_4_times_10kB_values.txt create mode 100644 .github/workflows/load-tests-job-configs/java_GBK_Dataflow_V2_Batch_Java11_reiterate_4_times_2MB_values.txt create mode 100644 .github/workflows/load-tests-job-configs/java_GBK_Dataflow_V2_Batch_Java17_2GB_of_100B_records.txt create mode 100644 .github/workflows/load-tests-job-configs/java_GBK_Dataflow_V2_Batch_Java17_2GB_of_100kB_records.txt create mode 100644 .github/workflows/load-tests-job-configs/java_GBK_Dataflow_V2_Batch_Java17_2GB_of_10B_records.txt create mode 100644 .github/workflows/load-tests-job-configs/java_GBK_Dataflow_V2_Batch_Java17_fanout_4_times_with_2GB_10-byte_records_total.txt create mode 100644 .github/workflows/load-tests-job-configs/java_GBK_Dataflow_V2_Batch_Java17_fanout_8_times_with_2GB_10-byte_records_total.txt create mode 100644 .github/workflows/load-tests-job-configs/java_GBK_Dataflow_V2_Batch_Java17_reiterate_4_times_10kB_values.txt create mode 100644 .github/workflows/load-tests-job-configs/java_GBK_Dataflow_V2_Batch_Java17_reiterate_4_times_2MB_values.txt create mode 100644 .github/workflows/load-tests-job-configs/java_GBK_Dataflow_V2_Streaming_Java11_2GB_of_100B_records.txt create mode 100644 .github/workflows/load-tests-job-configs/java_GBK_Dataflow_V2_Streaming_Java11_2GB_of_100kB_records.txt create mode 100644 .github/workflows/load-tests-job-configs/java_GBK_Dataflow_V2_Streaming_Java11_2GB_of_10B_records.txt create mode 100644 .github/workflows/load-tests-job-configs/java_GBK_Dataflow_V2_Streaming_Java11_fanout_4_times_with_2GB_10-byte_records_total.txt create mode 100644 .github/workflows/load-tests-job-configs/java_GBK_Dataflow_V2_Streaming_Java11_fanout_8_times_with_2GB_10-byte_records_total.txt create mode 100644 .github/workflows/load-tests-job-configs/java_GBK_Dataflow_V2_Streaming_Java11_reiterate_4_times_10kB_values.txt create mode 100644 .github/workflows/load-tests-job-configs/java_GBK_Dataflow_V2_Streaming_Java11_reiterate_4_times_2MB_values.txt create mode 100644 .github/workflows/load-tests-job-configs/java_GBK_Dataflow_V2_Streaming_Java17_2GB_of_100B_records.txt create mode 100644 .github/workflows/load-tests-job-configs/java_GBK_Dataflow_V2_Streaming_Java17_2GB_of_100kB_records.txt create mode 100644 .github/workflows/load-tests-job-configs/java_GBK_Dataflow_V2_Streaming_Java17_2GB_of_10B_records.txt create mode 100644 .github/workflows/load-tests-job-configs/java_GBK_Dataflow_V2_Streaming_Java17_fanout_4_times_with_2GB_10-byte_records_total.txt create mode 100644 .github/workflows/load-tests-job-configs/java_GBK_Dataflow_V2_Streaming_Java17_fanout_8_times_with_2GB_10-byte_records_total.txt create mode 100644 .github/workflows/load-tests-job-configs/java_GBK_Dataflow_V2_Streaming_Java17_reiterate_4_times_10kB_values.txt create mode 100644 .github/workflows/load-tests-job-configs/java_GBK_Dataflow_V2_Streaming_Java17_reiterate_4_times_2MB_values.txt create mode 100644 examples/notebooks/beam-ml/per_key_models.ipynb create mode 100644 it/google-cloud-platform/src/test/java/org/apache/beam/it/gcp/bigquery/BigQueryStreamingLT.java