Event Timeline
Comment Actions
Follow up after fixing the description part (D1683:
ition(topic='swh.journal.objects.origin_visit', partition=31), TopicPartition(topic='swh.journal.objects.origin_visit', partition=96), TopicPartition(topic='swh.journal.objects.origin_visit', partition=46), TopicPartition(topic='swh.journ$ l.objects.origin_visit', partition=117), TopicPartition(topic='swh.journal.objects.origin_visit', partition=51), TopicPartition(topic='swh.journal.objects.origin_visit', partition=70)} for group swh.indexer.journal_client Jul 03 14:25:26 getty swh[3294]: INFO:kafka.conn:<BrokerConnection node_id=13 host=esnode3.internal.softwareheritage.org/192.168.100.63 port=9092>: connecting to 192.168.100.63:9092 Jul 03 14:25:36 getty swh[3294]: Processed 0 messages. Jul 03 14:25:36 getty swh[3294]: Traceback (most recent call last): Jul 03 14:25:36 getty swh[3294]: File "/usr/bin/swh", line 11, in <module> Jul 03 14:25:36 getty swh[3294]: load_entry_point('swh.core==0.0.63', 'console_scripts', 'swh')() Jul 03 14:25:36 getty swh[3294]: File "/usr/lib/python3/dist-packages/swh/core/cli/__init__.py", line 56, in main Jul 03 14:25:36 getty swh[3294]: return swh(auto_envvar_prefix='SWH') Jul 03 14:25:36 getty swh[3294]: File "/usr/lib/python3/dist-packages/click/core.py", line 716, in __call__ Jul 03 14:25:36 getty swh[3294]: return self.main(*args, **kwargs) Jul 03 14:25:36 getty swh[3294]: File "/usr/lib/python3/dist-packages/click/core.py", line 696, in main Jul 03 14:25:36 getty swh[3294]: rv = self.invoke(ctx) Jul 03 14:25:36 getty swh[3294]: File "/usr/lib/python3/dist-packages/click/core.py", line 1060, in invoke Jul 03 14:25:36 getty swh[3294]: return _process_result(sub_ctx.command.invoke(sub_ctx)) Jul 03 14:25:36 getty swh[3294]: File "/usr/lib/python3/dist-packages/click/core.py", line 1060, in invoke Jul 03 14:25:36 getty swh[3294]: return _process_result(sub_ctx.command.invoke(sub_ctx)) Jul 03 14:25:36 getty swh[3294]: File "/usr/lib/python3/dist-packages/click/core.py", line 889, in invoke Jul 03 14:25:36 getty swh[3294]: return ctx.invoke(self.callback, **ctx.params) Jul 03 14:25:36 getty swh[3294]: File "/usr/lib/python3/dist-packages/click/core.py", line 534, in invoke Jul 03 14:25:36 getty swh[3294]: return callback(*args, **kwargs) Jul 03 14:25:36 getty swh[3294]: File "/usr/lib/python3/dist-packages/click/decorators.py", line 17, in new_func Jul 03 14:25:36 getty swh[3294]: return f(get_current_context(), *args, **kwargs) Jul 03 14:25:36 getty swh[3294]: File "/usr/lib/python3/dist-packages/swh/indexer/cli.py", line 211, in journal_client Jul 03 14:25:36 getty swh[3294]: nb_messages += client.process(worker_fn) Jul 03 14:25:36 getty swh[3294]: File "/usr/lib/python3/dist-packages/swh/journal/client.py", line 103, in process Jul 03 14:25:36 getty swh[3294]: worker_fn({object_type: [msg.value for msg in messages]}) Jul 03 14:25:36 getty swh[3294]: File "/usr/lib/python3/dist-packages/swh/indexer/journal_client.py", line 19, in process_journal_objects Jul 03 14:25:36 getty swh[3294]: process_origin_visits(messages['origin_visit'], scheduler, task_names) Jul 03 14:25:36 getty swh[3294]: File "/usr/lib/python3/dist-packages/swh/indexer/journal_client.py", line 26, in process_origin_visits Jul 03 14:25:36 getty swh[3294]: visits = [visit for visit in visits if visit[b'status'] == b'full'] Jul 03 14:25:36 getty swh[3294]: File "/usr/lib/python3/dist-packages/swh/indexer/journal_client.py", line 26, in <listcomp> Jul 03 14:25:36 getty swh[3294]: visits = [visit for visit in visits if visit[b'status'] == b'full'] Jul 03 14:25:36 getty swh[3294]: KeyError: b'status' Jul 03 14:25:38 getty systemd[1]: swh-indexer-journal-client.service: Main process exited, code=exited, status=1/FAILURE Jul 03 14:25:38 getty systemd[1]: swh-indexer-journal-client.service: Unit entered failed state. Jul 03 14:25:38 getty systemd[1]: swh-indexer-journal-client.service: Failed with result 'exit-code'.
Comment Actions
Follow up:
Jul 03 16:11:11 getty swh[15355]: igin_visit', partition=23), TopicPartition(topic='swh.journal.objects.origin_visit', partition=92), TopicPartition(topic='swh.journal.objects.origin_visit', partition=26), TopicPartition(topic='swh.journal.objects.origin_visit', partition=79), TopicPartition(topic='swh.journal.objects.origin_visit', partition=13), TopicPartition(topic='swh.journal .objects.origin_visit', partition=112), TopicPartition(topic='swh.journal.objects.origin_visit', partition=62), TopicPartition(topic='swh.journal.objects.origin_visit', partition=99), TopicPartition(topic='swh.journal.objects.origin_visit', partition=33), TopicPartition(topic='swh.journal.objects.origin_visit', partition=86), TopicPartition(topic='swh.journal.objects.origin_visit' , partition=20), TopicPartition(topic='swh.journal.objects.origin_visit', partition=89), TopicPartition(topic='swh.journal.objects.origin_visit', partition=7), TopicPartition(topic='swh.journal.objects.origin_visit', partition=76), TopicPartition(topic='swh.journal.objects.origin_visit', partition=10), TopicPartition(topic='swh.journal.objects.origin_visit', partition=125)} for gr oup swh.indexer.journal_client Jul 03 16:11:11 getty swh[15355]: INFO:kafka.conn:<BrokerConnection node_id=11 host=esnode1.internal.softwareheritage.org/192.168.100.61 port=9092>: connecting to 192.168.100.61:9092 Jul 03 16:11:18 getty swh[15355]: Processed 0 messages. Jul 03 16:11:18 getty swh[15355]: Traceback (most recent call last): Jul 03 16:11:18 getty swh[15355]: File "/usr/bin/swh", line 11, in <module> Jul 03 16:11:18 getty swh[15355]: load_entry_point('swh.core==0.0.63', 'console_scripts', 'swh')() Jul 03 16:11:18 getty swh[15355]: File "/usr/lib/python3/dist-packages/swh/core/cli/__init__.py", line 56, in main Jul 03 16:11:18 getty swh[15355]: return swh(auto_envvar_prefix='SWH') Jul 03 16:11:18 getty swh[15355]: File "/usr/lib/python3/dist-packages/click/core.py", line 716, in __call__ Jul 03 16:11:18 getty swh[15355]: return self.main(*args, **kwargs) Jul 03 16:11:18 getty swh[15355]: File "/usr/lib/python3/dist-packages/click/core.py", line 696, in main Jul 03 16:11:18 getty swh[15355]: rv = self.invoke(ctx) Jul 03 16:11:18 getty swh[15355]: File "/usr/lib/python3/dist-packages/click/core.py", line 1060, in invoke Jul 03 16:11:18 getty swh[15355]: return _process_result(sub_ctx.command.invoke(sub_ctx)) Jul 03 16:11:18 getty swh[15355]: File "/usr/lib/python3/dist-packages/click/core.py", line 1060, in invoke Jul 03 16:11:18 getty swh[15355]: return _process_result(sub_ctx.command.invoke(sub_ctx)) Jul 03 16:11:18 getty swh[15355]: File "/usr/lib/python3/dist-packages/click/core.py", line 889, in invoke Jul 03 16:11:18 getty swh[15355]: return ctx.invoke(self.callback, **ctx.params) Jul 03 16:11:18 getty swh[15355]: File "/usr/lib/python3/dist-packages/click/core.py", line 534, in invoke Jul 03 16:11:18 getty swh[15355]: return callback(*args, **kwargs) Jul 03 16:11:18 getty swh[15355]: File "/usr/lib/python3/dist-packages/click/decorators.py", line 17, in new_func Jul 03 16:11:18 getty swh[15355]: return f(get_current_context(), *args, **kwargs) Jul 03 16:11:18 getty swh[15355]: File "/usr/lib/python3/dist-packages/swh/indexer/cli.py", line 211, in journal_client Jul 03 16:11:18 getty swh[15355]: nb_messages += client.process(worker_fn) Jul 03 16:11:18 getty swh[15355]: File "/usr/lib/python3/dist-packages/swh/journal/client.py", line 103, in process Jul 03 16:11:18 getty swh[15355]: worker_fn({object_type: [msg.value for msg in messages]}) Jul 03 16:11:18 getty swh[15355]: File "/usr/lib/python3/dist-packages/swh/indexer/journal_client.py", line 19, in process_journal_objects Jul 03 16:11:18 getty swh[15355]: process_origin_visits(messages['origin_visit'], scheduler, task_names) Jul 03 16:11:18 getty swh[15355]: File "/usr/lib/python3/dist-packages/swh/indexer/journal_client.py", line 37, in process_origin_visits Jul 03 16:11:18 getty swh[15355]: scheduler.create_tasks(task_dicts) Jul 03 16:11:18 getty swh[15355]: File "/usr/lib/python3/dist-packages/swh/scheduler/api/client.py", line 31, in create_tasks Jul 03 16:11:18 getty swh[15355]: return self.post('create_tasks', {'tasks': tasks}) Jul 03 16:11:18 getty swh[15355]: File "/usr/lib/python3/dist-packages/swh/core/api/__init__.py", line 198, in post Jul 03 16:11:18 getty swh[15355]: return self._decode_response(response) Jul 03 16:11:18 getty swh[15355]: File "/usr/lib/python3/dist-packages/swh/core/api/__init__.py", line 230, in _decode_response Jul 03 16:11:18 getty swh[15355]: raise pickle.loads(decode_response(response)) Jul 03 16:11:18 getty swh[15355]: psycopg2.OperationalError: index row size 2808 exceeds maximum 2712 for index "task_args" Jul 03 16:11:18 getty swh[15355]: HINT: Values larger than 1/3 of a buffer page cannot be indexed. Jul 03 16:11:18 getty swh[15355]: Consider a function index of an MD5 hash of the value, or use full text indexing. Jul 03 16:11:18 getty swh[15355]: CONTEXT: SQL statement "insert into task (type, arguments, next_run, status, current_interval, policy, Jul 03 16:11:18 getty swh[15355]: retries_left, priority) Jul 03 16:11:18 getty swh[15355]: select type, arguments, next_run, status, current_interval, policy, Jul 03 16:11:18 getty swh[15355]: retries_left, priority Jul 03 16:11:18 getty swh[15355]: from tmp_task t Jul 03 16:11:18 getty swh[15355]: where not exists(select 1 Jul 03 16:11:18 getty swh[15355]: from task Jul 03 16:11:18 getty swh[15355]: where type = t.type and Jul 03 16:11:18 getty swh[15355]: arguments->'args' = t.arguments->'args' and Jul 03 16:11:18 getty swh[15355]: arguments->'kwargs' = t.arguments->'kwargs' and Jul 03 16:11:18 getty swh[15355]: policy = t.policy and Jul 03 16:11:18 getty swh[15355]: priority is not distinct from t.priority and Jul 03 16:11:18 getty swh[15355]: status = t.status)" Jul 03 16:11:18 getty swh[15355]: PL/pgSQL function swh_scheduler_create_tasks_from_temp() line 12 at SQL statement Jul 03 16:11:19 getty systemd[1]: swh-indexer-journal-client.service: Main process exited, code=exited, status=1/FAILURE Jul 03 16:11:19 getty systemd[1]: swh-indexer-journal-client.service: Unit entered failed state. Jul 03 16:11:19 getty systemd[1]: swh-indexer-journal-client.service: Failed with result 'exit-code'. Jul 03 16:11:29 getty systemd[1]: swh-indexer-journal-client.service: Service hold-off time over, scheduling restart. Jul 03 16:11:29 getty systemd[1]: Stopped Software Heritage Indexer Journal Client. -- Subject: Unit swh-indexer-journal-client.service has finished shutting down