feat(oceanbase): add multi-process loader, configurable index/partition params, and HNSW_BQ cosine support #769
Open
wyfanxiao wants to merge 2 commits intozilliztech:mainfrom
Open
feat(oceanbase): add multi-process loader, configurable index/partition params, and HNSW_BQ cosine support #769wyfanxiao wants to merge 2 commits intozilliztech:mainfrom
wyfanxiao wants to merge 2 commits intozilliztech:mainfrom
Conversation
…W_BQ cosine support - Add MultiprocessInsertRunner for parallel data loading across worker processes - OceanBase: declare thread_safe=False, auto-switch to multi-process loader - Add --load-processes CLI option for explicit multi-process control - Add --create-index-parallel CLI option (default 16) - Add --extra-info-max-size CLI option (default 32, set 0 to omit) - Add --partitions CLI option for KEY partitioning (default 0, no partition) - HNSW_BQ: remove forced L2 for cosine, now supports cosine natively - Improve concurrent_runner log message for thread_safe=False fallback - pyproject.toml: add pyyaml dependency, fix packages.find to include all subpackages
|
[APPROVALNOTIFIER] This PR is NOT APPROVED This pull-request has been approved by: wyfanxiao The full list of commands accepted by this bot can be found here. DetailsNeeds approval from an approver in each of these files:Approvers can indicate their approval by writing |
wyfanxiao
changed the title
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Hi team! 👋
This PR enhances the OceanBase client and adds a multi-process data loader to improve load throughput for SQL-based vector DBs.
Summary
MultiprocessInsertRunnerfor parallel data loading across worker processes, bypassing GIL limitation for SQL-based vector DBsthread_safe=False, auto-switch to multi-process loader when--load-concurrency>1--load-processesCLI option for explicit multi-process control--create-index-parallelCLI option (default 16) for configurable index build parallelism--extra-info-max-sizeCLI option (default 32, set 0 to omit) for HNSW index--partitionsCLI option for KEY partitioning (default 0, no partition)concurrent_runnerlog message forthread_safe=Falsefallbackpyproject.toml: addpyyamldependency, fixpackages.findto include all subpackagesWe've been using these changes in our OceanBase benchmark testing and they've been working well. Would love to get this merged so it can benefit other users too. Thanks in advance for taking the time to review! Happy to address any feedback. 🙏