Denovo1998 opened a new pull request, #24739:
URL: https://github.com/apache/pulsar/pull/24739
<!--
### Contribution Checklist
- PR title format should be *[type][component] summary*. For details, see
*[Guideline - Pulsar PR Naming
Convention](https://pulsar.apache.org/contribute/develop-semantic-title/)*.
- Fill out the template below to describe the changes contributed by the
pull request. That will give reviewers the context they need to do the review.
- Each pull request should address only one issue, not mix up code from
multiple issues.
- Each commit in the pull request has a meaningful commit message
- Once all items of the checklist are addressed, remove the above text and
this checklist, leaving only the filled out template below.
-->
<!-- Either this PR fixes an issue, -->
Fixes #xyz
<!-- or this PR is one task of an issue -->
Main Issue: #24600
<!-- If the PR belongs to a PIP, please add the PIP link here -->
PIP: #xyz
<!-- Details of when a PIP is required and how the PIP process work, please
see: https://github.com/apache/pulsar/blob/master/pip/README.md -->
### Motivation
The current concurrent control model of `BucketDelayedDeliveryTracker` has
serious performance bottlenecks and thread safety issues. It mainly relies on
coarse-grained synchronized keywords to protect its internal state, which leads
to several key problems:
1. **High lock contention**
`All operations, whether simple read-only checks (like containsMessage) or
complex I/O-intensive operations (like creating a Bucket snapshot), contend for
the same object lock. This leads to operations being unnecessarily serialized,
limiting overall throughput.
2. **Read-write operations mutually block**
- Write operations block read operations: An executing `addMessage` or
`getScheduledMessages` will block all `containsMessage` and `nextDeliveryTime`
and other read-only checks.
- Read-write mixed operations block all other operations: for example, the
`getScheduledMessages` method, which appears to be reading messages but
actually includes multiple write operations such as modifying the queue,
updating the bitmap, and removing mappings. When executed within a synchronized
block, it holds the lock for a long time, blocking the addition of all new
messages.
3. I/O operations block the critical path
Within the synchronized block of `addMessage`, the creation and persistence
of Bucket snapshots are executed synchronously. This is a time-consuming I/O
operation that blocks all subsequent message addition and read requests until
the snapshot is completed, significantly increasing the message publishing
delay.
This PR is the first step in optimizing and enhancing the
`BucketDelayedDeliveryTracker`, aiming to address the above performance
bottlenecks by introducing more refined concurrency control mechanisms and
asynchronizing I/O operations.
### Modifications
This change is mainly focused on the `addMessage` method, because it is one
of the most critical bottlenecks under high throughput scenarios. Subsequent
PRs will continue to optimize other methods based on this foundation, such as
`getScheduledMessages`.
1. **Introducing fine-grained locks (`ReentrantReadWriteLock`)**:
* Removed `StampedLock` and the `synchronized` keyword on multiple methods,
unifying the use of `ReentrantReadWriteLock` as the core concurrency control
mechanism.
* This implements read-write separation:
* **Read operations** (`containsMessage`, `nextDeliveryTime`) now use a
**read lock**, allowing multiple threads to execute concurrently without
blocking each other.
* **Write operations** (`addMessage`, `asyncMergeBucketSnapshot`) use a
**write lock**, ensuring atomicity and consistency of data modifications.
* `addMessage` internally adopts an optimized pattern of "read lock check ->
write lock modification" to reduce the holding time of the write lock.
2. **Asynchronous Bucket Snapshot Creation**:
* Introduced a dedicated single-threaded `ExecutorService`
(`bucketSnapshotExecutor`) to handle time-consuming Bucket snapshot persistence
tasks.
* Refactored the snapshot creation logic in `addMessage`:
* When a snapshot needs to be created, no longer wait synchronously.
Instead, mark the current `MutableBucket` as `bucketBeingSealed`.
* Immediately create a new `lastMutableBucket` to handle subsequent
incoming messages, ensuring that `addMessage` calls can return quickly.
* Submit the actual snapshot creation and persistence task to the
background `bucketSnapshotExecutor` for asynchronous execution.
* This change removes I/O operations from the critical path of message
publishing, greatly reducing publish latency and increasing throughput.
### Verifying this change
- [x] Make sure that the change passes the CI checks.
*(Please pick either of the following options)*
This change is a trivial rework / code cleanup without any test coverage.
*(or)*
This change is already covered by existing tests, such as *(please describe
tests)*.
*(or)*
This change added tests and can be verified as follows:
*(example:)*
- *Added integration tests for end-to-end deployment with large payloads
(10MB)*
- *Extended integration test for recovery after broker failure*
### Does this pull request potentially affect one of the following parts:
<!-- DO NOT REMOVE THIS SECTION. CHECK THE PROPER BOX ONLY. -->
*If the box was checked, please highlight the changes*
- [ ] Dependencies (add or upgrade a dependency)
- [ ] The public API
- [ ] The schema
- [ ] The default values of configurations
- [ ] The threading model
- [ ] The binary protocol
- [ ] The REST endpoints
- [ ] The admin CLI options
- [ ] The metrics
- [ ] Anything that affects deployment
### Documentation
<!-- DO NOT REMOVE THIS SECTION. CHECK THE PROPER BOX ONLY. -->
- [ ] `doc` <!-- Your PR contains doc changes. -->
- [ ] `doc-required` <!-- Your PR changes impact docs and you will update
later -->
- [x] `doc-not-needed` <!-- Your PR changes do not impact docs -->
- [ ] `doc-complete` <!-- Docs have been already added -->
### Matching PR in forked repository
PR in forked repository: https://github.com/Denovo1998/pulsar/pull/10
<!--
After opening this PR, the build in apache/pulsar will fail and instructions
will
be provided for opening a PR in the PR author's forked repository.
apache/pulsar pull requests should be first tested in your own fork since
the
apache/pulsar CI based on GitHub Actions has constrained resources and quota.
GitHub Actions provides separate quota for pull requests that are executed
in
a forked repository.
The tests will be run in the forked repository until all PR review comments
have
been handled, the tests pass and the PR is approved by a reviewer.
-->
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
