~~~~ Execution Summary - RUN_INGEST ~~~~ Execution finished with errors. {'exec_id': 'd922c8b8-69eb-491c-be00-5d9238b771e0', 'infos': ['2023-09-22 20:17:23.935573 INFO: Starting execution for task with name=RUN_INGEST', "2023-09-22 20:17:25.973386 INFO: Failed to execute 'datahub ingest'", '2023-09-22 20:17:25.973514 INFO: Caught exception EXECUTING task_id=d922c8b8-69eb-491c-be00-5d9238b771e0, name=RUN_INGEST, ' 'stacktrace=Traceback (most recent call last):\n' ' File "/usr/local/lib/python3.10/site-packages/acryl/executor/execution/default_executor.py", line 122, in execute_task\n' ' task_event_loop.run_until_complete(task_future)\n' ' File "/usr/local/lib/python3.10/asyncio/base_events.py", line 649, in run_until_complete\n' ' return future.result()\n' ' File "/usr/local/lib/python3.10/site-packages/acryl/executor/execution/sub_process_ingestion_task.py", line 231, in execute\n' ' raise TaskError("Failed to execute \'datahub ingest\'")\n' "acryl.executor.execution.task.TaskError: Failed to execute 'datahub ingest'\n"], 'errors': []} ~~~~ Ingestion Report ~~~~ { "cli": { "cli_version": "0.10.4", "cli_entry_location": "/tmp/datahub/ingest/venv-mongodb-0.10.4/lib/python3.10/site-packages/datahub/__init__.py", "py_version": "3.10.10 (main, Mar 14 2023, 02:37:11) [GCC 10.2.1 20210110]", "py_exec_path": "/tmp/datahub/ingest/venv-mongodb-0.10.4/bin/python3", "os_details": "Linux-5.10.186-179.751.amzn2.x86_64-x86_64-with-glibc2.31", "peak_memory_usage": "65.02 MB", "mem_info": "65.02 MB", "peak_disk_usage": "63.05 GB", "disk_info": { "total": "107.36 GB", "used": "63.05 GB", "free": "44.31 GB" } }, "source": { "type": "mongodb", "report": { "events_produced": 0, "events_produced_per_sec": 0, "entities": {}, "aspects": {}, "warnings": {}, "failures": {}, "filtered": [], "start_time": "2023-09-22 20:17:25.006667 (now)", "running_time": "0.09 seconds" } }, "sink": { "type": "datahub-rest", "report": { "total_records_written": 0, "records_written_per_second": 0, "warnings": [], "failures": [], "start_time": "2023-09-22 20:17:24.951561 (now)", "current_time": "2023-09-22 20:17:25.098149 (now)", "total_duration_in_seconds": 0.15, "gms_version": "v0.10.4", "pending_requests": 0 } } } ~~~~ Ingestion Logs ~~~~ Obtaining venv creation lock... Acquired venv creation lock venv setup time = 0 This version of datahub supports report-to functionality datahub ingest run -c /tmp/datahub/ingest/d922c8b8-69eb-491c-be00-5d9238b771e0/recipe.yml --report-to /tmp/datahub/ingest/d922c8b8-69eb-491c-be00-5d9238b771e0/ingestion_report.json [2023-09-22 20:17:24,925] INFO {datahub.cli.ingest_cli:173} - DataHub CLI version: 0.10.4 [2023-09-22 20:17:24,955] INFO {datahub.ingestion.run.pipeline:210} - Sink configured successfully. DataHubRestEmitter: configured to talk to http://datahub-datahub-gms:8080 [2023-09-22 20:17:25,056] INFO {datahub.ingestion.run.pipeline:227} - Source configured successfully. [2023-09-22 20:17:25,057] INFO {datahub.cli.ingest_cli:129} - Starting metadata ingestion [2023-09-22 20:17:25,061] INFO {datahub.ingestion.source.mongodb:425} - Mongodb version for current connection - [4, 4, 24, 0] [2023-09-22 20:17:25,098] INFO {datahub.ingestion.reporting.file_reporter:52} - Wrote UNKNOWN report successfully to <_io.TextIOWrapper name='/tmp/datahub/ingest/d922c8b8-69eb-491c-be00-5d9238b771e0/ingestion_report.json' mode='w' encoding='UTF-8'> [2023-09-22 20:17:25,099] INFO {datahub.cli.ingest_cli:134} - Source (mongodb) report: {'events_produced': 0, 'events_produced_per_sec': 0, 'entities': {}, 'aspects': {}, 'warnings': {}, 'failures': {}, 'filtered': [], 'start_time': '2023-09-22 20:17:25.006667 (now)', 'running_time': '0.09 seconds'} [2023-09-22 20:17:25,100] INFO {datahub.cli.ingest_cli:137} - Sink (datahub-rest) report: {'total_records_written': 0, 'records_written_per_second': 0, 'warnings': [], 'failures': [], 'start_time': '2023-09-22 20:17:24.951561 (now)', 'current_time': '2023-09-22 20:17:25.100318 (now)', 'total_duration_in_seconds': 0.15, 'gms_version': 'v0.10.4', 'pending_requests': 0} [2023-09-22 20:17:25,261] ERROR {datahub.entrypoints:199} - Command failed: not authorized on core to execute command { aggregate: "system.profile", pipeline: [ { $addFields: { temporary_doc_size_field: { $bsonSize: "$$ROOT" } } }, { $match: { temporary_doc_size_field: { $lt: 16793600 } } }, { $project: { temporary_doc_size_field: 0 } }, { $sample: { size: 1000 } } ], allowDiskUse: true, cursor: {}, lsid: { id: UUID("ce68e6bf-9724-4e57-9ef8-34ec26bd9799") }, $clusterTime: { clusterTime: Timestamp(1695413844, 22), signature: { hash: BinData(0, 071E3F7B144A832572237F77C70358EB3B192C1F), keyId: 7267723820390154244 } }, $db: "core", $readPreference: { mode: "secondary" } }, full error: {'operationTime': Timestamp(1695413844, 22), 'ok': 0.0, 'errmsg': 'not authorized on core to execute command { aggregate: "system.profile", pipeline: [ { $addFields: { temporary_doc_size_field: { $bsonSize: "$$ROOT" } } }, { $match: { temporary_doc_size_field: { $lt: 16793600 } } }, { $project: { temporary_doc_size_field: 0 } }, { $sample: { size: 1000 } } ], allowDiskUse: true, cursor: {}, lsid: { id: UUID("ce68e6bf-9724-4e57-9ef8-34ec26bd9799") }, $clusterTime: { clusterTime: Timestamp(1695413844, 22), signature: { hash: BinData(0, 071E3F7B144A832572237F77C70358EB3B192C1F), keyId: 7267723820390154244 } }, $db: "core", $readPreference: { mode: "secondary" } }', 'code': 13, 'codeName': 'Unauthorized', '$clusterTime': {'clusterTime': Timestamp(1695413844, 22), 'signature': {'hash': b'\x07\x1e?{\x14J\x83%r#\x7fw\xc7\x03X\xeb;\x19,\x1f', 'keyId': 7267723820390154244}}} Traceback (most recent call last): File "/tmp/datahub/ingest/venv-mongodb-0.10.4/lib/python3.10/site-packages/datahub/entrypoints.py", line 186, in main sys.exit(datahub(standalone_mode=False, **kwargs)) File "/tmp/datahub/ingest/venv-mongodb-0.10.4/lib/python3.10/site-packages/click/core.py", line 1157, in __call__ return self.main(*args, **kwargs) File "/tmp/datahub/ingest/venv-mongodb-0.10.4/lib/python3.10/site-packages/click/core.py", line 1078, in main rv = self.invoke(ctx) File "/tmp/datahub/ingest/venv-mongodb-0.10.4/lib/python3.10/site-packages/click/core.py", line 1688, in invoke return _process_result(sub_ctx.command.invoke(sub_ctx)) File "/tmp/datahub/ingest/venv-mongodb-0.10.4/lib/python3.10/site-packages/click/core.py", line 1688, in invoke return _process_result(sub_ctx.command.invoke(sub_ctx)) File "/tmp/datahub/ingest/venv-mongodb-0.10.4/lib/python3.10/site-packages/click/core.py", line 1434, in invoke return ctx.invoke(self.callback, **ctx.params) File "/tmp/datahub/ingest/venv-mongodb-0.10.4/lib/python3.10/site-packages/click/core.py", line 783, in invoke return __callback(*args, **kwargs) File "/tmp/datahub/ingest/venv-mongodb-0.10.4/lib/python3.10/site-packages/click/decorators.py", line 33, in new_func return f(get_current_context(), *args, **kwargs) File "/tmp/datahub/ingest/venv-mongodb-0.10.4/lib/python3.10/site-packages/datahub/telemetry/telemetry.py", line 379, in wrapper raise e File "/tmp/datahub/ingest/venv-mongodb-0.10.4/lib/python3.10/site-packages/datahub/telemetry/telemetry.py", line 334, in wrapper res = func(*args, **kwargs) File "/tmp/datahub/ingest/venv-mongodb-0.10.4/lib/python3.10/site-packages/datahub/utilities/memory_leak_detector.py", line 95, in wrapper return func(ctx, *args, **kwargs) File "/tmp/datahub/ingest/venv-mongodb-0.10.4/lib/python3.10/site-packages/datahub/cli/ingest_cli.py", line 198, in run loop.run_until_complete(run_func_check_upgrade(pipeline)) File "/usr/local/lib/python3.10/asyncio/base_events.py", line 649, in run_until_complete return future.result() File "/tmp/datahub/ingest/venv-mongodb-0.10.4/lib/python3.10/site-packages/datahub/cli/ingest_cli.py", line 158, in run_func_check_upgrade ret = await the_one_future File "/tmp/datahub/ingest/venv-mongodb-0.10.4/lib/python3.10/site-packages/datahub/cli/ingest_cli.py", line 149, in run_pipeline_async return await loop.run_in_executor( File "/usr/local/lib/python3.10/concurrent/futures/thread.py", line 58, in run result = self.fn(*self.args, **self.kwargs) File "/tmp/datahub/ingest/venv-mongodb-0.10.4/lib/python3.10/site-packages/datahub/cli/ingest_cli.py", line 140, in run_pipeline_to_completion raise e File "/tmp/datahub/ingest/venv-mongodb-0.10.4/lib/python3.10/site-packages/datahub/cli/ingest_cli.py", line 132, in run_pipeline_to_completion pipeline.run() File "/tmp/datahub/ingest/venv-mongodb-0.10.4/lib/python3.10/site-packages/datahub/ingestion/run/pipeline.py", line 364, in run for wu in itertools.islice( File "/tmp/datahub/ingest/venv-mongodb-0.10.4/lib/python3.10/site-packages/datahub/ingestion/api/source_helpers.py", line 138, in auto_workunit_reporter for wu in stream: File "/tmp/datahub/ingest/venv-mongodb-0.10.4/lib/python3.10/site-packages/datahub/ingestion/source/mongodb.py", line 346, in get_workunits_internal collection_schema = construct_schema_pymongo( File "/tmp/datahub/ingest/venv-mongodb-0.10.4/lib/python3.10/site-packages/datahub/ingestion/source/mongodb.py", line 193, in construct_schema_pymongo documents = collection.aggregate( File "/tmp/datahub/ingest/venv-mongodb-0.10.4/lib/python3.10/site-packages/pymongo/collection.py", line 2722, in aggregate return self._aggregate( File "/tmp/datahub/ingest/venv-mongodb-0.10.4/lib/python3.10/site-packages/pymongo/_csot.py", line 108, in csot_wrapper return func(self, *args, **kwargs) File "/tmp/datahub/ingest/venv-mongodb-0.10.4/lib/python3.10/site-packages/pymongo/collection.py", line 2629, in _aggregate return self.__database.client._retryable_read( File "/tmp/datahub/ingest/venv-mongodb-0.10.4/lib/python3.10/site-packages/pymongo/_csot.py", line 108, in csot_wrapper return func(self, *args, **kwargs) File "/tmp/datahub/ingest/venv-mongodb-0.10.4/lib/python3.10/site-packages/pymongo/mongo_client.py", line 1535, in _retryable_read return func(session, server, conn, read_pref) File "/tmp/datahub/ingest/venv-mongodb-0.10.4/lib/python3.10/site-packages/pymongo/aggregation.py", line 164, in get_cursor result = conn.command( File "/tmp/datahub/ingest/venv-mongodb-0.10.4/lib/python3.10/site-packages/pymongo/helpers.py", line 315, in inner return func(*args, **kwargs) File "/tmp/datahub/ingest/venv-mongodb-0.10.4/lib/python3.10/site-packages/pymongo/pool.py", line 932, in command return command( File "/tmp/datahub/ingest/venv-mongodb-0.10.4/lib/python3.10/site-packages/pymongo/network.py", line 191, in command helpers._check_command_response( File "/tmp/datahub/ingest/venv-mongodb-0.10.4/lib/python3.10/site-packages/pymongo/helpers.py", line 223, in _check_command_response raise OperationFailure(errmsg, code, response, max_wire_version) pymongo.errors.OperationFailure: not authorized on core to execute command { aggregate: "system.profile", pipeline: [ { $addFields: { temporary_doc_size_field: { $bsonSize: "$$ROOT" } } }, { $match: { temporary_doc_size_field: { $lt: 16793600 } } }, { $project: { temporary_doc_size_field: 0 } }, { $sample: { size: 1000 } } ], allowDiskUse: true, cursor: {}, lsid: { id: UUID("ce68e6bf-9724-4e57-9ef8-34ec26bd9799") }, $clusterTime: { clusterTime: Timestamp(1695413844, 22), signature: { hash: BinData(0, 071E3F7B144A832572237F77C70358EB3B192C1F), keyId: 7267723820390154244 } }, $db: "core", $readPreference: { mode: "secondary" } }, full error: {'operationTime': Timestamp(1695413844, 22), 'ok': 0.0, 'errmsg': 'not authorized on core to execute command { aggregate: "system.profile", pipeline: [ { $addFields: { temporary_doc_size_field: { $bsonSize: "$$ROOT" } } }, { $match: { temporary_doc_size_field: { $lt: 16793600 } } }, { $project: { temporary_doc_size_field: 0 } }, { $sample: { size: 1000 } } ], allowDiskUse: true, cursor: {}, lsid: { id: UUID("ce68e6bf-9724-4e57-9ef8-34ec26bd9799") }, $clusterTime: { clusterTime: Timestamp(1695413844, 22), signature: { hash: BinData(0, 071E3F7B144A832572237F77C70358EB3B192C1F), keyId: 7267723820390154244 } }, $db: "core", $readPreference: { mode: "secondary" } }', 'code': 13, 'codeName': 'Unauthorized', '$clusterTime': {'clusterTime': Timestamp(1695413844, 22), 'signature': {'hash': b'\x07\x1e?{\x14J\x83%r#\x7fw\xc7\x03X\xeb;\x19,\x1f', 'keyId': 7267723820390154244}}}