{
  "schema_version": "0.6.0",
  "paper_id": "container-workload-characterization-host-tracing",
  "page_url": "https://naser.github.io/research-publications/papers/container-workload-characterization-host-tracing/",
  "title": "Container Workload Characterization Through Host System Tracing",
  "title_variants": [],
  "authors": [
    "Madeline Janecek",
    "Naser Ezzati-Jivan",
    "Seyed Vahid Azhari"
  ],
  "author_details": [
    {
      "name": "Madeline Janecek",
      "orcid": "https://orcid.org/0000-0002-7182-3958",
      "profile_url": "https://dblp.org/pid/307/5913.html"
    },
    {
      "name": "Naser Ezzati-Jivan",
      "orcid": "https://orcid.org/0000-0003-1435-6297",
      "profile_url": "https://naser.github.io/"
    },
    {
      "name": "Seyed Vahid Azhari",
      "orcid": null,
      "profile_url": "https://dblp.org/pid/42/2821.html"
    }
  ],
  "publication": {
    "year": 2021,
    "venue": "IEEE International Conference on Cloud Computing Technology and Science (CloudCom)",
    "type": "conference paper",
    "publication_date": "2021-10",
    "online_date": null,
    "print_date": "2021-10",
    "volume": null,
    "issue": null,
    "pages": "9-19",
    "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/ic2e52221.2021.00015",
  "source_record_id": "container-workload-characterization-through-host-system-tracing-8afdc8b21d",
  "identifiers": {
    "doi": "10.1109/ic2e52221.2021.00015"
  },
  "abstract": null,
  "abstract_source": "Container workload 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": "The paper characterizes container workloads from host-level LTTng traces by selecting important threads and clustering execution-state behavior without instrumenting the containers internally.",
  "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/ic2e52221.2021.00015"
      },
      {
        "note": "author identity matched to Naser Ezzati-Jivan in the local research catalog"
      },
      {
        "note": "Container workload PDF pp. 1-4: host-only motivation, LTTng, pid_ns/tid attribution, and state extraction"
      },
      {
        "note": "Container workload PDF pp. 4-9: PageRank feature selection, vectorization, two-stage K-Means, workloads, and silhouette result"
      },
      {
        "note": "Container workload PDF pp. 9-10: required tracepoints, 21.62% versus 3.6% overhead, limitations, and future work"
      },
      {
        "note": "local container-workload PDF hash verified in pdf-evidence/notes/container-workload-characterization-host-tracing.md and pdf-evidence/extraction-manifest.json"
      }
    ]
  },
  "summary": {
    "core_contribution": "The paper characterizes container workloads from host-level LTTng traces by selecting important threads and clustering execution-state behavior without instrumenting the containers internally.",
    "problem": "Cloud users may not control internal container agents, and coarse CPU, disk, and network metrics do not reveal enough execution detail for workload characterization.",
    "method": "LTTng kernel tracing records host events with pid_ns and tid context so events can be attributed to containers. Per-thread states such as user mode, system-call mode, preempted, interrupted, blocked, and waiting are aggregated into normalized container vectors; an adapted PageRank selects important threads and two-stage K-Means produces coarse and fine workload groups. Trace Compass and JavaScript scripting support extraction.",
    "findings": "The Ubuntu 20.04.1/Linux 5.8.0/Docker 20.10.4 evaluation covers network-intensive, CPU-intensive, disk-I/O-intensive, and idle workloads. The CPU-intensive group has about 97.3% running/preempted time, the overall silhouette score is 0.6527, and the second clustering stage yields five finer groups. Average tracing overhead is 21.62% with all kernel events and 3.6% with the minimal necessary event set.",
    "limitations": "The evaluation covers four workload classes on one Linux/Docker configuration and depends on the selected execution-state features and clustering choices; it does not establish cross-runtime or multi-tenant generalization.",
    "future_work": "Use the clusters for resource allocation and configuration, test other inputs and tasks, distinguish interrupt types, and explore richer or deep-learning-based characterization."
  },
  "tags": [
    "kernel-tracing",
    "system-tracing",
    "performance-analysis",
    "resource-analysis"
  ],
  "keywords": [
    "container workloads",
    "host tracing",
    "LTTng",
    "pid_ns",
    "tid",
    "Trace Compass",
    "PageRank",
    "K-Means",
    "Docker",
    "Ubuntu 20.04.1",
    "Linux 5.8.0",
    "silhouette score",
    "tracing overhead"
  ],
  "versions": [
    {
      "id": "published-version",
      "label": "Published version",
      "relation": "version-of-record",
      "title": "Container Workload Characterization Through Host System Tracing",
      "url": "https://doi.org/10.1109/ic2e52221.2021.00015",
      "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 characterizing container workloads from host-level tracing without internal container agents.",
    "points": [
      "LTTng pid_ns/tid context for attributing host events to containers.",
      "PageRank thread selection, execution-state vectors, and two-stage K-Means clustering.",
      "Docker workload groups, silhouette score, and minimal-versus-all-kernel-event overhead comparison."
    ],
    "canonical_version_id": "published-version"
  },
  "provenance": {
    "metadata_verified_on": "2026-08-09",
    "metadata_source": [
      "DBLP/DOI bibliographic record for 10.1109/ic2e52221.2021.00015",
      "author identity matched to Naser Ezzati-Jivan in the local research catalog",
      "Container workload PDF pp. 1-4: host-only motivation, LTTng, pid_ns/tid attribution, and state extraction",
      "Container workload PDF pp. 4-9: PageRank feature selection, vectorization, two-stage K-Means, workloads, and silhouette result",
      "Container workload PDF pp. 9-10: required tracepoints, 21.62% versus 3.6% overhead, limitations, and future work",
      "local container-workload PDF hash verified in pdf-evidence/notes/container-workload-characterization-host-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"
  }
}