docs: define app performance metrics for monitoring collection (issue #518)#519
Draft
Chulhee1Lee with Copilot wants to merge 4 commits into
Draft
docs: define app performance metrics for monitoring collection (issue #518)#519Chulhee1Lee with Copilot wants to merge 4 commits into
Chulhee1Lee with Copilot wants to merge 4 commits into
Conversation
10 tasks
Copilot
AI
changed the title
[WIP] Design app performance metrics for monitoring collection
docs: define app performance metrics for monitoring collection (issue #518)
Jul 8, 2026
Contributor
|
@copilot 연결된 Issue에서 언급한 모든 항목이 다 커버되고 있는지 확인해줘. |
… performance metrics design (issue #518)
Contributor
Author
이슈 #518의 모든 항목을 다시 점검하고, 누락된 부분을 추가하였습니다 (커밋: 최신 커밋). 이슈 Tasks 대비 커버리지:
Acceptance Criteria 모두 충족:
|
Contributor
|
@copilot Architecture 및 Document는 항상 한글과 영문을 병기해줘. 업데이트하도록. |
…h) per project convention
Contributor
Author
두 문서( |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
MonitoringServer already delivers node-level metrics to PolicyManager via
ReportNodeMetricsgRPC, but app-level metrics (StressMonitoringMetric: FPS, latency, per-core CPU load) have no forwarding path to PolicyManager — confirming the core gap identified in #518.Changes
Both documents are fully bilingual, with each section written in Korean and English side by side.
doc/architecture/EN/HLD/app_performance_metrics.md— Bilingual design document (English primary, Korean alongside) defining:doc/architecture/KR/HLD/app_performance_metrics.md— Bilingual counterpart (Korean primary, English alongside) with identical contentKey findings
ReportNodeMetricsgRPC + threshold-based offloading)SendStressMonitoringMetricgRPC)App-level metrics confirmed for collection (High feasibility):
Metrics with Medium or Low feasibility (GPU Utilization, Throughput, Error Rate, Temperature, Power Consumption, Context Switch Rate, Real-time Deadline Violation) are deferred to future iterations.