mit-pdos/noria

Dynamic load profiling

Open

#90 opened on 2018年9月19日

GitHub で見る
 (0 comments) (0 reactions) (0 assignees)Rust (4,576 stars) (229 forks)batch import
enhancementhelp wantedm-debugging

説明

It'd be really cool if the system kept stats about how "busy" different parts of the graphs were. For example, how many records they're processing per second or how long they spend idle between every time they're woken up. This might help to identify performance regressions and opportunities for optimization, but could also have a wider impact by allowing the controller to re-shard or replicate nodes in response to increase/decreased load.

コントリビューターガイド

技術スタック
rust
領域
performance
Issue 種別
feature
難度新しい貢献者にとっての実装難度です。1 は非常に小さな変更、5 は専門的な作業です。
4
推定時間経験ある貢献者が調査、実装、テスト、pull request 準備にかけるおおよその時間範囲です。
over 1 week
活動状況Issue が今どれだけ取り組みやすいかを示します。新しい、活発、古い、ブロック中、またはメンテナー入力待ちなどです。
stale
明確さ期待される変更、受け入れ条件、次の手順がどれだけ明確かを示します。
mostly clear
前提条件
Rust programmingDataflow system conceptsPerformance profiling basicsNoria architecture knowledge
初心者向け度初回貢献者にどれだけ取り組みやすいかを 1-100 で推定したスコアです。
15
調査方針
To implement this feature, first study the Noria architecture, especially the graph execution engine and handling of internal state. Explore existing profiling infrastructure in the codebase (e.g., metrics or logging) and propose a set of metrics to collect. Since no prior discussion exists, open a design issue or ask maintainers for guidance on preferred approach and integration points. The main challenge is deciding where to insert profiling hooks without significant performance overhead.