{ "schema_version": "0.6.0", "paper_id": "hybridrca-critical-path-aware-tracing", "page_url": "https://naser.github.io/research-publications/papers/hybridrca-critical-path-aware-tracing/", "title": "HybridRCA: Lightweight Critical-Path-Aware Hybrid Tracing for Root-Cause Analysis in Production Microservices", "title_variants": [], "authors": [ "Maryam Ekhlasi", "Arnaud Fiorini", "Michel R. Dagenais", "Naser Ezzati-Jivan", "Maxime Lamothe" ], "author_details": [ { "name": "Maryam Ekhlasi", "orcid": null, "profile_url": "https://dblp.org/pid/409/3420.html" }, { "name": "Arnaud Fiorini", "orcid": null, "profile_url": "https://dblp.org/pid/330/2202.html" }, { "name": "Michel R. Dagenais", "orcid": null, "profile_url": "https://dblp.org/pid/60/309.html" }, { "name": "Naser Ezzati-Jivan", "orcid": "https://orcid.org/0000-0003-1435-6297", "profile_url": "https://naser.github.io/" }, { "name": "Maxime Lamothe", "orcid": null, "profile_url": "https://dblp.org/pid/223/4602.html" } ], "publication": { "year": 2025, "venue": "IEEE International Conference on Software Maintenance and Evolution (ICSME)", "type": "conference paper", "publication_date": "2025-09-07", "online_date": null, "print_date": "2025-09-07", "volume": null, "issue": null, "pages": "553-564", "article_number": null, "publisher": "IEEE", "issn": [], "isbn": [], "crossref_type": "proceedings-article" }, "publication_type": "research paper", "status": "published_metadata_record", "canonical_source_url": "https://doi.org/10.1109/icsme64153.2025.00056", "source_record_id": "hybridrca-lightweight-critical-path-aware-hybrid-tracing-for-root-cause-analysis-in-production-m-af256da8ce", "identifiers": { "doi": "10.1109/icsme64153.2025.00056" }, "abstract": null, "abstract_source": "HybridRCA published-paper PDF reviewed on 2026-08-06; abstract not reproduced because reuse permission for the publisher version was not established.", "abstract_available": false, "scholar_eligibility": { "eligible": false, "basis": "not-eligible", "note": "The page is a discovery record; it does not claim Google Scholar article-host eligibility." }, "description": "HybridRCA combines critical-path-aware span analysis with targeted kernel metrics to reduce production trace volume while preserving root-cause localization evidence.", "evidence_level": "metadata-or-abstract-reviewed", "evidence": { "source_basis": "metadata-only", "coverage": "bibliographic metadata", "summary_origin": "AI-assisted catalog editorial summary", "review_status": "catalog-reviewed; paper-author approval pending", "verified_on": "2026-08-09", "sources": [ { "note": "DBLP/DOI bibliographic record for 10.1109/icsme64153.2025.00056" }, { "note": "author identity matched to Naser Ezzati-Jivan in the local research catalog" }, { "note": "HybridRCA PDF pp. 1-6: critical-path extraction, Personalized PageRank, weighted spectrum analysis, targeted metrics, and clock synchronization" }, { "note": "HybridRCA PDF pp. 7-10: LTTng 2.13.9-1 environment, HotROD/TrainTicket/OnlineBoutique/TiDB workloads, injected faults, accuracy, trace-volume, and storage results" }, { "note": "HybridRCA PDF p. 10: limitations and future-work boundary" }, { "note": "local HybridRCA PDF hash verified in pdf-evidence/notes/hybridrca-critical-path-aware-tracing.md and pdf-evidence/extraction-manifest.json" } ] }, "summary": { "core_contribution": "HybridRCA combines critical-path-aware span analysis with targeted kernel metrics to reduce production trace volume while preserving root-cause localization evidence.", "problem": "Production microservices generate too many spans and low-level events for full-granularity storage and diagnosis, yet root-cause analysis still needs evidence about the execution context that causes latency.", "method": "The pipeline groups similar traces, structures requests, extracts each request's critical path, builds a critical-path span graph, applies Personalized PageRank and weighted spectrum-based fault localization, and triggers LTTng collection of CPU, memory, and I/O-wait metrics only for targeted processes or threads. The evaluation uses OpenTracing-instrumented applications and LTTng 2.13.9-1; Perf is mentioned as a low-level tracing tool but is not the reported primary collector.", "findings": "The paper evaluates HotROD, TrainTicket, OnlineBoutique, and a reproduced TiDB scenario. The abstract reports average recall improvement of 0.45%, up to 22.6% fewer spans, and more than 99% kernel-level storage reduction; the conclusion separately reports 5.7% average top-1 recall improvement, up to 0.45% precision improvement, 22.3% fewer spans, and more than 99% storage reduction. The evaluation includes 56 injected faults across TrainTicket and OnlineBoutique and reports single- and two-root-cause precision/recall/F1 results.", "limitations": "Critical-path-only collection can miss local latency that does not affect end-to-end latency; the anomaly detector assumes most behavior is normal; and the baselines were reimplemented. The evidence is still a benchmark and reproduced-case evaluation rather than a broad live-traffic deployment.", "future_work": "Extend validation to live traffic, streaming alerts, container and network metadata, long-running asynchronous requests, and multi-tenant noise." }, "tags": [ "system-tracing", "microservices", "root-cause-analysis", "latency-analysis" ], "keywords": [ "critical path", "hybrid tracing", "production microservices", "LTTng", "OpenTracing", "Personalized PageRank", "weighted spectrum-based fault localization", "HotROD", "TrainTicket", "OnlineBoutique", "TiDB", "SysBench", "kernel-level storage" ], "versions": [ { "id": "published-version", "label": "Published version", "relation": "version-of-record", "title": "HybridRCA: Lightweight Critical-Path-Aware Hybrid Tracing for Root-Cause Analysis in Production Microservices", "url": "https://doi.org/10.1109/icsme64153.2025.00056", "pdf_url": null, "status": "published", "canonical_for_citation": true } ], "access": { "status": "published_metadata_record", "note": "The DOI is the canonical citation target; this catalog does not redistribute the publisher PDF.", "license": null }, "resources": { "code": null, "data": null, "slides": null, "demo": null }, "citation_guidance": { "when_to_cite": "Cite this paper when reducing production microservice tracing while retaining critical-path evidence for root-cause analysis.", "points": [ "Critical-path extraction with Personalized PageRank and weighted spectrum-based localization.", "LTTng-triggered collection of targeted CPU, memory, and I/O-wait metrics for suspicious processes or spans.", "HotROD, TrainTicket, OnlineBoutique, and TiDB evaluations with trace-volume and kernel-storage reductions." ], "canonical_version_id": "published-version" }, "provenance": { "metadata_verified_on": "2026-08-09", "metadata_source": [ "DBLP/DOI bibliographic record for 10.1109/icsme64153.2025.00056", "author identity matched to Naser Ezzati-Jivan in the local research catalog", "HybridRCA PDF pp. 1-6: critical-path extraction, Personalized PageRank, weighted spectrum analysis, targeted metrics, and clock synchronization", "HybridRCA PDF pp. 7-10: LTTng 2.13.9-1 environment, HotROD/TrainTicket/OnlineBoutique/TiDB workloads, injected faults, accuracy, trace-volume, and storage results", "HybridRCA PDF p. 10: limitations and future-work boundary", "local HybridRCA PDF hash verified in pdf-evidence/notes/hybridrca-critical-path-aware-tracing.md and pdf-evidence/extraction-manifest.json" ], "summary_written_by": "AI-assisted", "summary_verified_by": "metadata/abstract-grounded catalog review; full-text review and author approval pending", "linked_preprint_record": null, "author_order_note": null }, "batch": { "phase": 2, "batch_label": "expanded forty-paper release", "status": "included_in_expanded_catalog", "selected_at": "2026-08-09" } }