summaryrefslogtreecommitdiff
path: root/kafka/coordinator
Commit message (Collapse)AuthorAgeFilesLines
* Fix KafkaConsumer autocommit for 0.8 brokers (#756 / #706)Dana Powers2016-07-162-20/+25
| | | | * Dont wait for group join to enable AutoCommitTask if broker version < 0.9 * For zookeeper offset storage, set a "coordinator" with least_loaded_node
* Avoid some exceptions in Coordinator.__del__ (#668)Dana Powers2016-04-252-2/+4
|
* Changing some commented out metrics to avoid future gotchas.Zack Dever2016-04-131-3/+3
|
* Beginnings of metrics instrumentation in kafka consumer.Zack Dever2016-04-131-41/+30
| | | | | | This adds the parent metrics instance to kafka consumer, which will eventually be used to instrument everything under consumer. To start I ported the java consumer coordinator metrics.
* Default sleep=True in client.pollDana Powers2016-04-081-1/+1
|
* Can no longer have coordinator_id if coordinator_unknown()Dana Powers2016-04-081-6/+0
|
* Use version-indexed lists for request/response protocol structsprotocol_versionsDana Powers2016-04-052-24/+21
|
* Remove unused importskafka-3318Dana Powers2016-04-051-2/+0
|
* KAFKA-3318: clean up consumer logging and error messagesDana Powers2016-04-052-78/+103
|
* Update imports from kafka.common -> kafka.errors / kafka.structsDana Powers2016-04-054-5/+5
|
* Merge pull request #589 from dpkp/node_not_readyDana Powers2016-04-041-8/+14
|\ | | | | Refactor NodeNotReadyError handling
| * Improve Coordinator Error handlingDana Powers2016-04-041-8/+14
| | | | | | | | | | | | | | - coordinator_unknown() should not check ready(node_id) - dont mark coordinator dead on not-ready or inflight-requests errors - improve coordinator and heartbeat logging - dont gate group metadata requests on ready() check [conn handles now]
* | Improve auto-commit task handling when group_id is Noneissue_619Dana Powers2016-04-031-20/+22
|/
* Check for None returned from least_loaded_node when no brokers are availablenone_least_loaded_nodeDana Powers2016-03-131-0/+4
|
* Log successful heartbeat as INFO; improve heartbeat response loggingDana Powers2016-03-121-11/+12
|
* HeartbeatTask should reschedule heartbeat on coordinator_unknown()Dana Powers2016-03-121-2/+6
|
* Mock client.ready() call to test coordinator offset fetch requestDana Powers2016-02-191-1/+2
|
* Some attributes may not exist in __del__ if we failed assertionsDana Powers2016-02-181-1/+1
|
* More friendly warning when offset fetch request returns unknown topic / ↵Dana Powers2016-02-181-1/+2
| | | | partition
* Verify node ready before sending offset fetch request from coordinatorDana Powers2016-02-181-0/+5
|
* break up some circular references and close client wake pipe on __del__aisch2016-02-162-6/+21
|
* Add RangePartitionAssignor (and use as default); add assignor testsrange_assignorDana Powers2016-02-164-4/+98
|
* Fixup: _send_offset_commit_request future should succeed w/ True, not NoneDana Powers2016-02-021-1/+2
|
* Ok to sleep in blocking poll for metadata updateDana Powers2016-01-251-1/+1
|
* Disable offset commits and auto-partition-assignment when group_id is NoneDana Powers2016-01-241-8/+17
|
* Dont need to refresh metadata on GroupCoordinatorNotAvailableErrorsDana Powers2016-01-241-1/+4
|
* KAFKA-2978: consumer stops fetching when consumed and fetch positions get ↵Dana Powers2016-01-101-1/+2
| | | | out of sync
* ConsumerCoordinator cleanupsDana Powers2016-01-102-13/+36
| | | | | | | | | | | | | | - default assignors to RoundRobinPartitionAssignor - check offsets types in commit_offsets_* methods - succeed future in _send_offset_commit_request when no offsets - raise exception if no subscribed topics in group_protocols() - fix _subscription typo in metadata listener callbacks - short circuit if no partitions passed to fetch_committed_offsets - line-wrap comments - return future from commit_offsets_async - return future value from commit_offsets_sync - fix self._failed_request callback partial args - comment out metrics class for now
* Move ConsumerProtocol definition to kafka.coordinator.protocolDana Powers2016-01-103-35/+44
|
* Fix future redefine bug in client.pollDana Powers2016-01-041-0/+1
|
* Drop unused method from ConsumerCoordinatorDana Powers2016-01-031-5/+0
|
* Check api_version in ConsumerCoordinatorDana Powers2016-01-031-32/+94
| | | | | | | - Full group support in 0.9 - Kafka-storage offsets w/ GroupCoordinator in 0.8.2 - Zookeeper-storage offsets in 0.8.1 - Assign all partitions locally if < 0.9
* Use python3 compatible next() in roundrobin assignorDana Powers2016-01-011-2/+2
|
* Fixup heartbeat config assertionDana Powers2015-12-311-1/+1
|
* Rename AbstractCoordinator -> BaseCoordinator, log as kafka.coordinatorDana Powers2015-12-302-5/+5
|
* Prefer assert or more-specific error to IllegalState / IllegalArgumentDana Powers2015-12-303-21/+8
|
* Catch GroupCoordinatorNotAvailableError in GroupCoordinatorResponse handlerDana Powers2015-12-301-0/+3
|
* More Docstring ImprovementsDana Powers2015-12-303-30/+106
|
* Rename KafkaClient.connection_failed -> is_disconnectedDana Powers2015-12-301-1/+1
|
* Make group_id a Coordinator kwarg (not arg) for consistencyDana Powers2015-12-302-7/+5
|
* Switch configs from attributes to dict to make passing / inspecting easierDana Powers2015-12-293-55/+63
|
* Fix log statement bug (via pylint)Dana Powers2015-12-291-1/+1
|
* Clean more ConsumerCoordinator docstringsDana Powers2015-12-291-16/+19
|
* Dont warn in AutoCommitTask.disable if not previously scheduledDana Powers2015-12-291-1/+1
|
* Improve OffsetCommit error loggingDana Powers2015-12-291-23/+33
| | | | | | Avoid printing full errors because they currently include long descriptions that are generally duplicative of our local error message.
* Log request failures in AbstractCoordinator._failed_requestDana Powers2015-12-291-5/+10
|
* _handle_group_coordinator_response should resolve future with the coordinator idDana Powers2015-12-291-1/+1
|
* Improve heartbeat loggingDana Powers2015-12-291-14/+13
|
* Log as INFO: group join, leader election, partition assignmentsDana Powers2015-12-291-1/+4
|
* Improve various docstringsDana Powers2015-12-292-19/+33
|
View Lorry Controller Status