feat(uptime): Add ability to use queues to manage parallelism#8
Open
akshayutture-augment wants to merge 1 commit into
Open
feat(uptime): Add ability to use queues to manage parallelism#8akshayutture-augment wants to merge 1 commit into
akshayutture-augment wants to merge 1 commit into
Conversation
One potential problem we have with batch processing is that any one slow item will clog up the whole batch. This pr implements a queueing method instead, where we keep N queues that each have their own workers. There's still a chance of individual items backlogging a queue, but we can try increased concurrency here to reduce the chances of that happening <!-- Describe your PR here. -->
There was a problem hiding this comment.
Pull Request Overview
Copilot reviewed 5 out of 7 changed files in this pull request and generated 3 comments.
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
| """Process items from the queue in order.""" | ||
| while not self.shutdown: | ||
| try: | ||
| work_item = self.work_queue.get() |
There was a problem hiding this comment.
The get() call will block indefinitely when the queue is empty. This prevents the worker thread from shutting down gracefully when self.shutdown is set to True. Use get(timeout=1) with appropriate exception handling to allow periodic shutdown checks.
Suggested change
| work_item = self.work_queue.get() | |
| work_item = self.work_queue.get(timeout=1) | |
| except queue.Empty: | |
| continue |
| ) -> None: | ||
| self.mode = mode | ||
| metric_tags = {"identifier": self.identifier, "mode": self.mode} | ||
| self.result_processor = self.result_processor_cls() |
There was a problem hiding this comment.
The result_processor is now instantiated before checking the mode, but previously it was created after all mode-specific setup. This changes the initialization order which could affect mode-specific configurations that might depend on the processor's state. Consider whether this reordering is intentional and document why it's necessary.
Comment on lines
+2081
to
+2106
| factory.create_with_partitions = create_with_partitions_tracking # type: ignore[method-assign] | ||
| consumer_config = build_kafka_consumer_configuration( | ||
| settings.KAFKA_CLUSTERS["default"]["common"], | ||
| group_id=consumer_group, | ||
| auto_offset_reset="earliest", | ||
| ) | ||
|
|
||
| consumer = KafkaConsumer(consumer_config) | ||
| processor = StreamProcessor( | ||
| consumer=consumer, | ||
| topic=Topic(test_topic), | ||
| processor_factory=factory, | ||
| commit_policy=ONCE_PER_SECOND, | ||
| ) | ||
|
|
||
| with mock.patch.object( | ||
| type(factory.result_processor), "__call__" | ||
| ) as mock_processor: | ||
| mock_processor.return_value = None | ||
|
|
||
| start_time = time.time() | ||
| while time.time() - start_time < 5: | ||
| processor._run_once() | ||
| time.sleep(0.1) | ||
|
|
||
| processor._shutdown() |
There was a problem hiding this comment.
Directly assigning to a method bypasses Python's descriptor protocol and can lead to unexpected behavior. Consider using unittest.mock.patch.object() or wrapping the factory in a test subclass that overrides the method properly.
Suggested change
| factory.create_with_partitions = create_with_partitions_tracking # type: ignore[method-assign] | |
| consumer_config = build_kafka_consumer_configuration( | |
| settings.KAFKA_CLUSTERS["default"]["common"], | |
| group_id=consumer_group, | |
| auto_offset_reset="earliest", | |
| ) | |
| consumer = KafkaConsumer(consumer_config) | |
| processor = StreamProcessor( | |
| consumer=consumer, | |
| topic=Topic(test_topic), | |
| processor_factory=factory, | |
| commit_policy=ONCE_PER_SECOND, | |
| ) | |
| with mock.patch.object( | |
| type(factory.result_processor), "__call__" | |
| ) as mock_processor: | |
| mock_processor.return_value = None | |
| start_time = time.time() | |
| while time.time() - start_time < 5: | |
| processor._run_once() | |
| time.sleep(0.1) | |
| processor._shutdown() | |
| with mock.patch.object(factory, "create_with_partitions", create_with_partitions_tracking): | |
| consumer_config = build_kafka_consumer_configuration( | |
| settings.KAFKA_CLUSTERS["default"]["common"], | |
| group_id=consumer_group, | |
| auto_offset_reset="earliest", | |
| ) | |
| consumer = KafkaConsumer(consumer_config) | |
| processor = StreamProcessor( | |
| consumer=consumer, | |
| topic=Topic(test_topic), | |
| processor_factory=factory, | |
| commit_policy=ONCE_PER_SECOND, | |
| ) | |
| with mock.patch.object( | |
| type(factory.result_processor), "__call__" | |
| ) as mock_processor: | |
| mock_processor.return_value = None | |
| start_time = time.time() | |
| while time.time() - start_time < 5: | |
| processor._run_once() | |
| time.sleep(0.1) | |
| processor._shutdown() |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Test 9
Replicated from ai-code-review-evaluation/sentry-copilot#8