{
  "schema_version": "0.6.0",
  "paper_id": "a-framework-to-compute-statistics-of-system-parameters-from-very-large-trace-files",
  "page_url": "https://naser.github.io/research-publications/papers/a-framework-to-compute-statistics-of-system-parameters-from-very-large-trace-files/",
  "title": "A Framework to Compute Statistics of System Parameters from Very Large Trace Files",
  "title_variants": [],
  "authors": [
    "Naser Ezzati-Jivan",
    "Michel R. Dagenais"
  ],
  "author_details": [
    {
      "name": "Naser Ezzati-Jivan",
      "orcid": "https://orcid.org/0000-0003-1435-6297",
      "profile_url": "https://naser.github.io/"
    },
    {
      "name": "Michel R. Dagenais",
      "orcid": null,
      "profile_url": "https://dblp.org/pid/60/309.html"
    }
  ],
  "publication": {
    "year": 2013,
    "venue": "ACM SIGOPS Operating Systems Review",
    "type": "journal article",
    "publication_date": "2013-01-29",
    "online_date": "2013-01-29",
    "print_date": "2013-01-29",
    "volume": "47",
    "issue": "1",
    "pages": "43-54",
    "article_number": null,
    "publisher": "Association for Computing Machinery (ACM)",
    "issn": [
      "0163-5980"
    ],
    "isbn": [],
    "crossref_type": "journal-article"
  },
  "publication_type": "journal article",
  "status": "published_with_public_full_text",
  "canonical_source_url": "https://doi.org/10.1145/2433140.2433151",
  "source_record_id": "a-framework-to-compute-statistics-of-system-parameters-from-very-large-trace-files-23edcf281c",
  "identifiers": {
    "doi": "10.1145/2433140.2433151"
  },
  "abstract": null,
  "abstract_source": "Institutional accepted-version PDF reviewed; abstract paraphrased for this catalog.",
  "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": "The framework computes system-parameter statistics for arbitrary intervals and resource hierarchies from very large traces using a disk-resident history structure and controlled granularity.",
  "evidence_level": "full-text-reviewed",
  "evidence": {
    "source_basis": "full-text-reviewed",
    "coverage": "material paper sections",
    "summary_origin": "AI-assisted catalog editorial summary",
    "review_status": "catalog-reviewed; paper-author approval pending",
    "verified_on": "2026-08-09",
    "sources": [
      {
        "note": "Statistics framework PDF: LTTng/Linux 2.6.38.6, Java history/resource trees, granularity degree, interpolation, and query bounds"
      },
      {
        "note": "Statistics framework PDF: 1-40 GB traces, GD 1/100/500/1000, 20-run/100-interval query experiment, disk-size comparison, and hierarchy analysis"
      },
      {
        "note": "Statistics framework PDF: interpolation/precision, storage, online-construction limitations, and future work"
      },
      {
        "note": "Local PDF hash verified in pdf-evidence/extraction-manifest.json"
      }
    ]
  },
  "summary": {
    "core_contribution": "The framework computes system-parameter statistics for arbitrary intervals and resource hierarchies from very large traces using a disk-resident history structure and controlled granularity.",
    "problem": "Re-reading large traces for every interval query is slow, while storing every metric change can consume storage comparable to the source trace. The framework targets scalable, compact, interactive metric statistics (pp. 2-4).",
    "method": "A Java/LTTng prototype builds a disk-resident interval history in one trace pass. A granularity degree controls persistence frequency; intermediate values are linearly interpolated. Stabbing queries answer point values, endpoint subtraction answers interval statistics, and a resource/metric hierarchy supports roll-up/drill-down queries (pp. 5-11).",
    "findings": "Tests use Linux kernel 2.6.38.6, a 2.8 GHz/6 GB machine, metrics including CPU usage, I/O throughput, HTTP/FTP/DNS connection counts, and event counts. Traces span 1-40 GB; GD=1 creates a store about 2.5-4.5x the source size, while coarser GD values reduce storage/construction cost. Twenty runs use 100 random intervals; GD=1000 is the best tested query case in the figures (pp. 11-13).",
    "limitations": "Interpolation accuracy depends on metric behavior and granularity degree; coarse degrees trade precision for space and construction time. Online construction is described as possible but was not investigated in this phase (pp. 7-8, 12-13).",
    "future_work": "Relate granularity to metrics and trace size; study interpolation effects; support other tracing systems; connect the framework to kernel fault/attack detection; and evaluate online construction (pp. 12-13)."
  },
  "tags": [
    "kernel-tracing",
    "trace-analysis",
    "performance-analysis",
    "resource-analysis",
    "performance-engineering"
  ],
  "keywords": [
    "trace statistics",
    "LTTng",
    "Linux kernel 2.6.38.6",
    "disk-resident interval tree",
    "history tree",
    "granularity degree",
    "linear interpolation",
    "hierarchical query",
    "large-scale tracing",
    "online analysis",
    "CPU usage",
    "I/O throughput"
  ],
  "versions": [
    {
      "id": "published-version",
      "label": "Published version",
      "relation": "version-of-record",
      "title": "A Framework to Compute Statistics of System Parameters from Very Large Trace Files",
      "url": "https://doi.org/10.1145/2433140.2433151",
      "pdf_url": null,
      "status": "published",
      "canonical_for_citation": true
    },
    {
      "id": "institutional-full-text",
      "label": "Institutional full text",
      "relation": "source-record",
      "title": "A Framework to Compute Statistics of System Parameters from Very Large Trace Files",
      "url": "https://publications.polymtl.ca/2954/1/2013_Ezzati-Jivan_Framework_compute_statistics_system_parameters.pdf",
      "pdf_url": "https://publications.polymtl.ca/2954/1/2013_Ezzati-Jivan_Framework_compute_statistics_system_parameters.pdf",
      "status": "public_full_text",
      "canonical_for_citation": false
    }
  ],
  "access": {
    "status": "published_with_public_full_text",
    "note": "The DOI is the canonical citation target; the institutional source link is external and the PDF is not redistributed here.",
    "license": null
  },
  "resources": {
    "code": null,
    "data": null,
    "slides": null,
    "demo": null
  },
  "citation_guidance": {
    "when_to_cite": "Cite this paper when your work uses or compares granularity-degree-controlled, disk-resident trace-statistics computation with interpolation.",
    "points": [
      "Granularity-degree-controlled, disk-resident trace-statistics computation with interpolation.",
      "Endpoint/stabbing-query construction for interval statistics without re-reading the queried trace range.",
      "Resource-hierarchy aggregation with `O(log n + K)` reported query work.",
      "The 1-40 GB LTTng scalability study and the storage/precision trade-off across GD values."
    ],
    "canonical_version_id": "published-version"
  },
  "provenance": {
    "metadata_verified_on": "2026-08-09",
    "metadata_source": [
      "Statistics framework PDF: LTTng/Linux 2.6.38.6, Java history/resource trees, granularity degree, interpolation, and query bounds",
      "Statistics framework PDF: 1-40 GB traces, GD 1/100/500/1000, 20-run/100-interval query experiment, disk-size comparison, and hierarchy analysis",
      "Statistics framework PDF: interpolation/precision, storage, online-construction limitations, and future work",
      "Local PDF hash verified in pdf-evidence/extraction-manifest.json"
    ],
    "summary_written_by": "AI-assisted",
    "summary_verified_by": "full-text-grounded catalog review; 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"
  }
}