{
  "schema_version": "0.1.0",
  "record_type": "research-topic",
  "topic_id": "latency-analysis",
  "label": "Latency Analysis",
  "title": "Latency Analysis Research",
  "description": "Research papers on latency outliers, intermittent delays, critical paths, and performance diagnosis.",
  "introduction": "This topic focuses on explaining latency rather than only measuring end-to-end response time. The records study outlier detection, dependency and critical-path analysis, blocking or preemption, resource contention, distributed request behavior, and methods for ranking likely causes of intermittent delay.",
  "aliases": [
    "latency outlier analysis",
    "response-time diagnosis",
    "tail-latency analysis"
  ],
  "search_terms": [
    "latency analysis",
    "latency outliers",
    "tail latency",
    "intermittent latency",
    "critical path"
  ],
  "related_topics": [
    "performance-analysis",
    "root-cause-analysis",
    "dependency-graphs",
    "microservices",
    "system-tracing"
  ],
  "canonical_url": "https://threadslab.org/research-publications/topics/latency-analysis.html",
  "paper_count": 7,
  "papers": [
    {
      "paper_id": "care-context-aware-root-cause-identification",
      "title": "CARE: Context Aware Root Cause Identification Using Distributed Traces and Profiling Metrics",
      "year": 2026,
      "authors": [
        "Mahsa Panahandeh",
        "Naser Ezzati-Jivan",
        "Abdelwahab Hamou-Lhadj",
        "James Miller"
      ],
      "page_url": "https://threadslab.org/research-publications/papers/care-context-aware-root-cause-identification/",
      "canonical_source_url": "https://doi.org/10.1109/TSE.2025.3645143",
      "core_contribution": "CARE combines distributed traces and profiling metrics with graph- and spectrum-based analysis to localize performance root causes in microservices.",
      "tags": [
        "system-tracing",
        "microservices",
        "root-cause-analysis",
        "latency-analysis"
      ],
      "keywords": [
        "distributed traces",
        "profiling metrics",
        "context-aware RCA",
        "microservice diagnosis",
        "TrainTicket",
        "spectrum-based fault localization",
        "PageRank",
        "China Mobile Zhejiang"
      ]
    },
    {
      "paper_id": "dtracomp-distributed-trace-comparison",
      "title": "DTraComp: Comparing distributed execution traces for understanding intermittent latency sources",
      "year": 2026,
      "authors": [
        "Maryam Ekhlasi",
        "Fatemeh Faraji Daneshgar",
        "Michel Dagenais",
        "Maxime Lamothe",
        "Naser Ezzati-Jivan",
        "Matthew Khouzam"
      ],
      "page_url": "https://threadslab.org/research-publications/papers/dtracomp-distributed-trace-comparison/",
      "canonical_source_url": "https://doi.org/10.1016/j.jss.2026.112990",
      "core_contribution": "DTraComp is an open-source Eclipse Trace Compass framework that compares groups of distributed requests and attributes span time to user-space, kernel, thread-state, and system-call evidence.",
      "tags": [
        "system-tracing",
        "kernel-tracing",
        "trace-analysis",
        "trace-visualization",
        "latency-analysis",
        "root-cause-analysis",
        "microservices",
        "lttng"
      ],
      "keywords": [
        "DTraComp",
        "distributed trace comparison",
        "OpenTracing",
        "LTTng",
        "LTTng-UST",
        "Eclipse Trace Compass",
        "differential flame graph",
        "span-state attribution",
        "system-call attribution",
        "Waited CPU",
        "Waited Blocked",
        "HotROD",
        "TiDB",
        "Apache Cassandra",
        "Eclipse Theia",
        "JFreeChart",
        "Jaeger",
        "microservice performance"
      ]
    },
    {
      "paper_id": "hybridrca-critical-path-aware-tracing",
      "title": "HybridRCA: Lightweight Critical-Path-Aware Hybrid Tracing for Root-Cause Analysis in Production Microservices",
      "year": 2025,
      "authors": [
        "Maryam Ekhlasi",
        "Arnaud Fiorini",
        "Michel R. Dagenais",
        "Naser Ezzati-Jivan",
        "Maxime Lamothe"
      ],
      "page_url": "https://threadslab.org/research-publications/papers/hybridrca-critical-path-aware-tracing/",
      "canonical_source_url": "https://doi.org/10.1109/icsme64153.2025.00056",
      "core_contribution": "HybridRCA combines critical-path-aware span analysis with targeted kernel metrics to reduce production trace volume while preserving root-cause localization evidence.",
      "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"
      ]
    },
    {
      "paper_id": "analyzing-performance-variability-in-alibaba-s-microservice-architecture-a-critical-path-based-p",
      "title": "Analyzing Performance Variability in Alibaba's Microservice Architecture: A Critical-Path-Based Perspective",
      "year": 2024,
      "authors": [
        "Alireza Ezaz",
        "Ghazal Khodabandeh",
        "Naser Ezzati-Jivan"
      ],
      "page_url": "https://threadslab.org/research-publications/papers/analyzing-performance-variability-in-alibaba-s-microservice-architecture-a-critical-path-based-p/",
      "canonical_source_url": "https://doi.org/10.1145/3629527.3651845",
      "core_contribution": "The paper identifies response-time variability in Alibaba microservice traces through critical-path extraction and variability analysis of service interactions.",
      "tags": [
        "microservices",
        "performance-analysis",
        "latency-analysis",
        "observability",
        "performance-engineering"
      ],
      "keywords": [
        "Alibaba microservice architecture",
        "critical path",
        "distributed traces",
        "response-time variability",
        "critical interactions",
        "microservice performance",
        "adaptive tracing",
        "cluster-trace-microservices-v2022",
        "mean response time",
        "standard deviation"
      ]
    },
    {
      "paper_id": "efficient-unsupervised-latency-culprit-ranking",
      "title": "Efficient Unsupervised Latency Culprit Ranking in Distributed Traces with GNN and Critical Path Analysis",
      "year": 2024,
      "authors": [
        "Mahsa Panahandeh",
        "Naser Ezzati-Jivan",
        "Abdelwahab Hamou-Lhadj",
        "James Miller"
      ],
      "page_url": "https://threadslab.org/research-publications/papers/efficient-unsupervised-latency-culprit-ranking/",
      "canonical_source_url": "https://doi.org/10.1145/3629527.3651841",
      "core_contribution": "The paper combines an unsupervised GraphSAGE model with critical-path-specific latency profiles to detect anomalous requests and rank likely microservice culprits without labelled training data.",
      "tags": [
        "microservices",
        "graph-neural-networks",
        "latency-analysis",
        "root-cause-analysis",
        "trace-analysis"
      ],
      "keywords": [
        "latency culprit ranking",
        "distributed traces",
        "GraphSAGE",
        "graph neural networks",
        "critical path",
        "FIRM dataset",
        "service invocation graph",
        "unsupervised anomaly detection",
        "Top-k ranking"
      ]
    },
    {
      "paper_id": "automated-cause-analysis-latency-outliers",
      "title": "Automated Cause Analysis of Latency Outliers Using System-Level Dependency Graphs",
      "year": 2021,
      "authors": [
        "Sneh Patel",
        "Brendan Park",
        "Naser Ezzati-Jivan",
        "Quentin Fournier"
      ],
      "page_url": "https://threadslab.org/research-publications/papers/automated-cause-analysis-latency-outliers/",
      "canonical_source_url": "https://doi.org/10.1109/QRS54544.2021.00054",
      "core_contribution": "The paper combines system-level dependency graphs with automated outlier detection to localize likely causes of latency anomalies.",
      "tags": [
        "system-tracing",
        "latency-analysis",
        "root-cause-analysis",
        "dependency-graphs"
      ],
      "keywords": [
        "latency outliers",
        "system-level traces",
        "dependency graphs",
        "density-based models",
        "z-score",
        "production diagnosis"
      ]
    },
    {
      "paper_id": "high-latency-cause-detection-multilevel-analysis",
      "title": "High latency cause detection using multilevel dynamic analysis",
      "year": 2018,
      "authors": [
        "Naser Ezzati-Jivan",
        "Genevieve Bastien",
        "Michel R. Dagenais"
      ],
      "page_url": "https://threadslab.org/research-publications/papers/high-latency-cause-detection-multilevel-analysis/",
      "canonical_source_url": "https://doi.org/10.1109/SYSCON.2018.8369613",
      "core_contribution": "The paper correlates PHP user-space events with LTTng kernel events in a unified multilevel model to explain high-latency web requests.",
      "tags": [
        "system-tracing",
        "latency-analysis",
        "root-cause-analysis",
        "performance-analysis"
      ],
      "keywords": [
        "high latency",
        "dynamic analysis",
        "multilevel analysis",
        "latency causes",
        "LTTng",
        "LTTng-UST",
        "Trace Compass",
        "OPcache contention"
      ]
    }
  ]
}