sparkforensics-server 0.5.1 → 0.6.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/package.json +1 -1
- package/public/assets/AutoscalingChurn-CRA2Mb7F.js +1 -0
- package/public/assets/CacheUtilization-Bh9OY_V9.js +1 -0
- package/public/assets/CachingOpportunity-oCiQwmTJ.js +1 -0
- package/public/assets/{ColdStart-B38OiAOp.js → ColdStart-BJrtjfmn.js} +1 -1
- package/public/assets/ConfigAudit-DMvKxySP.js +1 -0
- package/public/assets/CoreUsageArea-REC2zsKw.js +1 -0
- package/public/assets/Dashboard-BHZ76JCu.js +2 -0
- package/public/assets/DisclosureContext-OO7X1HAx.js +1 -0
- package/public/assets/{DuplicatePlanSubtree-BqS2A2j4.js → DuplicatePlanSubtree-BgG-L-cK.js} +1 -1
- package/public/assets/ExecutorUtilization-D2KhSVbY.js +1 -0
- package/public/assets/{GcPressure-CT1yzR_s.js → GcPressure-D1BTE8qh.js} +1 -1
- package/public/assets/{IncompleteRun-C7Qkjtjn.js → IncompleteRun-DD40xUpy.js} +1 -1
- package/public/assets/{JobFailures-WHl3ELfh.js → JobFailures-YwNzCF19.js} +1 -1
- package/public/assets/MemoryUtilization-9b8ee_3_.js +1 -0
- package/public/assets/{OverBroadcast-6oSSAQ_R.js → OverBroadcast-CfctS8a8.js} +1 -1
- package/public/assets/PartitionSizing-VG8kBgG5.js +1 -0
- package/public/assets/{PlanExplorer-DcxmiQWL.js → PlanExplorer-DmubTAOP.js} +1 -1
- package/public/assets/PlanGraphRoute-DctPZjS0.js +1 -0
- package/public/assets/RetryWaste-CnpM8bB7.js +1 -0
- package/public/assets/{ShuffleIO-CRhrYNE0.js → ShuffleIO-D13vGmas.js} +1 -1
- package/public/assets/Skew-DlagstYP.js +1 -0
- package/public/assets/SlowHost-cSkLRZ_e.js +1 -0
- package/public/assets/{SmallFiles-C082c2rd.js → SmallFiles-B-kERMcq.js} +1 -1
- package/public/assets/{SpeculationWaste-BS2vpadr.js → SpeculationWaste-DaysAzXO.js} +1 -1
- package/public/assets/Spill-H44Gz4US.js +1 -0
- package/public/assets/{StageFailed-D3ac9Sou.js → StageFailed-DCfii9h_.js} +1 -1
- package/public/assets/StageFindingGroup-BXJ0Mj5n.js +1 -0
- package/public/assets/{StageHeader-pI1nTwVf.js → StageHeader--oN2J-oD.js} +1 -1
- package/public/assets/StageShape-IZ80CZiJ.js +1 -0
- package/public/assets/{StageSlowness-BaNyfNvL.js → StageSlowness--BRIaBc1.js} +1 -1
- package/public/assets/Straggler-Ctq0Df_o.js +1 -0
- package/public/assets/TaskFailures-Bks_gqhL.js +1 -0
- package/public/assets/{TinyTask-8_5lpq_2.js → TinyTask-BssfzGFB.js} +1 -1
- package/public/assets/{UnderBroadcast-DJ0XSwth.js → UnderBroadcast-DsScrxc-.js} +1 -1
- package/public/assets/{finding-anchor-Cys8Z6Yn.js → finding-anchor-BYW1oz5R.js} +1 -1
- package/public/assets/{impact-sort-BTQndbof.js → impact-sort-xzy0g-Vh.js} +1 -1
- package/public/assets/index-DhpRGMZc.css +2 -0
- package/public/assets/index-DwqkFUFk.js +14 -0
- package/public/assets/instrument-sans-latin-ext-wdth-normal-C5E2Gvlv.woff2 +0 -0
- package/public/assets/instrument-sans-latin-wdth-normal-BVScPF0l.woff2 +0 -0
- package/public/assets/jetbrains-mono-latin-ext-wght-normal-DBQx-q_a.woff2 +0 -0
- package/public/assets/jetbrains-mono-latin-wght-normal-B9CIFXIH.woff2 +0 -0
- package/public/assets/{parser-worker-DmeCnLWU.js → parser-worker-CA5RxqKc.js} +8 -8
- package/public/assets/react-vendor-DfpuPQZf.js +9 -0
- package/public/assets/{select-DIYN6D3y.js → select-C8edjYTq.js} +1 -1
- package/public/assets/{usePagedRows-BxvdFnPk.js → usePagedRows-CsuUFeYx.js} +1 -1
- package/public/assets/useRecentFiles-BvkKo3JN.js +11 -0
- package/public/assets/{useSortMode-B8SRfAoG.js → useSortMode-joX71BZN.js} +1 -1
- package/public/docs/404.html +3 -7
- package/public/docs/assets/{app.D2GqAkhy.js → app.CnWL6bKV.js} +1 -1
- package/public/docs/assets/chunks/@localSearchIndexroot.tE5pz54z.js +1 -0
- package/public/docs/assets/chunks/{VPLocalSearchBox.BS4cSmtW.js → VPLocalSearchBox.C0IBKeRQ.js} +1 -1
- package/public/docs/assets/chunks/{theme.BuxVpb0H.js → theme.BH-2HuRf.js} +2 -2
- package/public/docs/assets/{contributor-guide_architecture_board-widgets_caching-and-memory.md.8bH1HnZp.js → contributor-guide_architecture_board-widgets_caching-and-memory.md.CQgn1t_M.js} +1 -1
- package/public/docs/assets/contributor-guide_architecture_board-widgets_visual-system-and-templating.md.wulOueeB.js +1 -0
- package/public/docs/assets/{contributor-guide_architecture_detector-contract.md.wj6Et6UD.js → contributor-guide_architecture_detector-contract.md.N4hhenrA.js} +1 -1
- package/public/docs/assets/contributor-guide_architecture_detector-contract_threshold-tables.md.Dp3c40rx.js +1 -0
- package/public/docs/assets/contributor-guide_architecture_impact-estimation.md.DfvbqEUu.js +1 -0
- package/public/docs/assets/{contributor-guide_architecture_impact-estimation.md.CZv_ZGOp.lean.js → contributor-guide_architecture_impact-estimation.md.DfvbqEUu.lean.js} +1 -1
- package/public/docs/assets/{contributor-guide_architecture_impact-estimation_caveats-tuning-and-coverage.md.BUucRc0A.js → contributor-guide_architecture_impact-estimation_caveats-tuning-and-coverage.md.Cwm1jHmn.js} +1 -1
- package/public/docs/assets/{contributor-guide_architecture_impact-estimation_caveats-tuning-and-coverage.md.BUucRc0A.lean.js → contributor-guide_architecture_impact-estimation_caveats-tuning-and-coverage.md.Cwm1jHmn.lean.js} +1 -1
- package/public/docs/assets/contributor-guide_architecture_state-and-history_run-comparison-internals.md.CZA0JLtV.js +1 -0
- package/public/docs/assets/{contributor-guide_architecture_state-and-history_run-comparison-internals.md.uuAKpY0Y.lean.js → contributor-guide_architecture_state-and-history_run-comparison-internals.md.CZA0JLtV.lean.js} +1 -1
- package/public/docs/assets/contributor-guide_architecture_worker-protocol_cli-and-mcp.md.BX1XnFbq.js +1 -0
- package/public/docs/assets/{contributor-guide_architecture_worker-protocol_evidence-report.md.DVGZOWvW.js → contributor-guide_architecture_worker-protocol_evidence-report.md.CiQl1MLb.js} +1 -1
- package/public/docs/assets/{contributor-guide_development-setup.md.D9bu4j_c.js → contributor-guide_development-setup.md.DQdzera7.js} +1 -1
- package/public/docs/assets/instrument-sans-latin-ext-wdth-normal.C5E2Gvlv.woff2 +0 -0
- package/public/docs/assets/instrument-sans-latin-wdth-normal.BVScPF0l.woff2 +0 -0
- package/public/docs/assets/jetbrains-mono-cyrillic-wght-normal.D73BlboJ.woff2 +0 -0
- package/public/docs/assets/jetbrains-mono-greek-wght-normal.Bw9x6K1M.woff2 +0 -0
- package/public/docs/assets/jetbrains-mono-latin-ext-wght-normal.DBQx-q_a.woff2 +0 -0
- package/public/docs/assets/jetbrains-mono-latin-wght-normal.B9CIFXIH.woff2 +0 -0
- package/public/docs/assets/jetbrains-mono-vietnamese-wght-normal.Bt-aOZkq.woff2 +0 -0
- package/public/docs/assets/style.CyK9Ss73.css +1 -0
- package/public/docs/assets/user-guide_getting-started_ci-and-automation.md.BEepbDDL.js +24 -0
- package/public/docs/assets/user-guide_getting-started_ci-and-automation.md.BEepbDDL.lean.js +1 -0
- package/public/docs/assets/{user-guide_mcp-tools_compare-runs.md.CPowlb2q.js → user-guide_mcp-tools_compare-runs.md.Cc_gLoix.js} +3 -2
- package/public/docs/assets/{user-guide_mcp-tools_compare-runs.md.CPowlb2q.lean.js → user-guide_mcp-tools_compare-runs.md.Cc_gLoix.lean.js} +1 -1
- package/public/docs/assets/{user-guide_mcp-tools_evaluate-budgets.md.Dq5Azk8G.js → user-guide_mcp-tools_evaluate-budgets.md.BB0nDY3Z.js} +2 -2
- package/public/docs/assets/{user-guide_mcp-tools_evaluate-budgets.md.Dq5Azk8G.lean.js → user-guide_mcp-tools_evaluate-budgets.md.BB0nDY3Z.lean.js} +1 -1
- package/public/docs/assets/{user-guide_mcp-tools_get-run-summary.md.DpxZ4ZNp.js → user-guide_mcp-tools_get-run-summary.md.EhaIsele.js} +1 -1
- package/public/docs/assets/user-guide_run-comparison.md.BUALkohi.js +1 -0
- package/public/docs/assets/user-guide_run-comparison.md.BUALkohi.lean.js +1 -0
- package/public/docs/assets/user-guide_run-comparison_how-stages-are-matched.md.DSXGu2tA.js +1 -0
- package/public/docs/assets/user-guide_run-comparison_how-stages-are-matched.md.DSXGu2tA.lean.js +1 -0
- package/public/docs/assets/user-guide_understanding-findings.md.3C7KCEZO.js +1 -0
- package/public/docs/assets/user-guide_understanding-findings.md.3C7KCEZO.lean.js +1 -0
- package/public/docs/contributor-guide/architecture/board-widgets/caching-and-memory.html +6 -10
- package/public/docs/contributor-guide/architecture/board-widgets/plan-advisor.html +4 -8
- package/public/docs/contributor-guide/architecture/board-widgets/visual-system-and-templating.html +6 -10
- package/public/docs/contributor-guide/architecture/board-widgets.html +4 -8
- package/public/docs/contributor-guide/architecture/detector-contract/plan-attribution.html +4 -8
- package/public/docs/contributor-guide/architecture/detector-contract/threshold-tables.html +6 -10
- package/public/docs/contributor-guide/architecture/detector-contract.html +6 -10
- package/public/docs/contributor-guide/architecture/drill-down/plan-graph.html +4 -8
- package/public/docs/contributor-guide/architecture/drill-down.html +4 -8
- package/public/docs/contributor-guide/architecture/impact-estimation/caveats-tuning-and-coverage.html +6 -10
- package/public/docs/contributor-guide/architecture/impact-estimation/stage-union-rollup.html +4 -8
- package/public/docs/contributor-guide/architecture/impact-estimation.html +6 -10
- package/public/docs/contributor-guide/architecture/index.html +4 -8
- package/public/docs/contributor-guide/architecture/overview.html +4 -8
- package/public/docs/contributor-guide/architecture/state-and-history/history-server-intake.html +4 -8
- package/public/docs/contributor-guide/architecture/state-and-history/run-comparison-internals.html +6 -10
- package/public/docs/contributor-guide/architecture/state-and-history.html +4 -8
- package/public/docs/contributor-guide/architecture/widget-rendering/findings-tab.html +4 -8
- package/public/docs/contributor-guide/architecture/widget-rendering/investigation-routing.html +4 -8
- package/public/docs/contributor-guide/architecture/widget-rendering/list-sort-mode.html +4 -8
- package/public/docs/contributor-guide/architecture/widget-rendering/reference-section.html +4 -8
- package/public/docs/contributor-guide/architecture/widget-rendering/row-expand-contract.html +4 -8
- package/public/docs/contributor-guide/architecture/widget-rendering.html +4 -8
- package/public/docs/contributor-guide/architecture/worker-protocol/cli-and-mcp.html +6 -10
- package/public/docs/contributor-guide/architecture/worker-protocol/core-and-event-validation.html +4 -8
- package/public/docs/contributor-guide/architecture/worker-protocol/evidence-availability.html +4 -8
- package/public/docs/contributor-guide/architecture/worker-protocol/evidence-report.html +6 -10
- package/public/docs/contributor-guide/architecture/worker-protocol.html +4 -8
- package/public/docs/contributor-guide/contributing.html +4 -8
- package/public/docs/contributor-guide/development-setup.html +6 -10
- package/public/docs/contributor-guide/testing.html +4 -8
- package/public/docs/favicon.svg +2 -2
- package/public/docs/hashmap.json +1 -1
- package/public/docs/index.html +4 -8
- package/public/docs/tuning-reference/anti-patterns.html +4 -8
- package/public/docs/tuning-reference/aqe.html +4 -8
- package/public/docs/tuning-reference/bottleneck-broadcast-sizing.html +4 -8
- package/public/docs/tuning-reference/bottleneck-cold-start.html +4 -8
- package/public/docs/tuning-reference/bottleneck-duplicate-plan-subtree.html +4 -8
- package/public/docs/tuning-reference/bottleneck-failures.html +4 -8
- package/public/docs/tuning-reference/bottleneck-gc.html +4 -8
- package/public/docs/tuning-reference/bottleneck-job-failure-rate.html +4 -8
- package/public/docs/tuning-reference/bottleneck-memory-utilization.html +4 -8
- package/public/docs/tuning-reference/bottleneck-retry-waste.html +4 -8
- package/public/docs/tuning-reference/bottleneck-shuffle.html +4 -8
- package/public/docs/tuning-reference/bottleneck-skew.html +4 -8
- package/public/docs/tuning-reference/bottleneck-slow-host.html +4 -8
- package/public/docs/tuning-reference/bottleneck-small-files.html +4 -8
- package/public/docs/tuning-reference/bottleneck-spill.html +4 -8
- package/public/docs/tuning-reference/bottleneck-straggler.html +4 -8
- package/public/docs/tuning-reference/bottleneck-tiny-tasks.html +4 -8
- package/public/docs/tuning-reference/bottleneck-utilization.html +4 -8
- package/public/docs/tuning-reference/caching.html +4 -8
- package/public/docs/tuning-reference/cluster-config.html +4 -8
- package/public/docs/tuning-reference/config.html +4 -8
- package/public/docs/tuning-reference/data-formats.html +4 -8
- package/public/docs/tuning-reference/index.html +5 -9
- package/public/docs/tuning-reference/intro.html +4 -8
- package/public/docs/tuning-reference/joins.html +4 -8
- package/public/docs/tuning-reference/memory-model.html +4 -8
- package/public/docs/tuning-reference/metrics.html +4 -8
- package/public/docs/tuning-reference/partitioning.html +4 -8
- package/public/docs/tuning-reference/pyspark.html +4 -8
- package/public/docs/tuning-reference/shuffle.html +4 -8
- package/public/docs/tuning-reference/spark-architecture.html +4 -8
- package/public/docs/tuning-reference/table-formats.html +4 -8
- package/public/docs/user-guide/alternative-log-retrieval/managed-platforms.html +4 -8
- package/public/docs/user-guide/alternative-log-retrieval/ssh-bastion.html +4 -8
- package/public/docs/user-guide/alternative-log-retrieval.html +4 -8
- package/public/docs/user-guide/getting-started/ci-and-automation.html +11 -13
- package/public/docs/user-guide/getting-started/reading-the-dashboard.html +4 -8
- package/public/docs/user-guide/getting-started/regression-metric-keys.html +4 -8
- package/public/docs/user-guide/getting-started/tuning-thresholds.html +4 -8
- package/public/docs/user-guide/getting-started.html +4 -8
- package/public/docs/user-guide/mcp-tools/compare-runs.html +8 -11
- package/public/docs/user-guide/mcp-tools/diagnose-run.html +4 -8
- package/public/docs/user-guide/mcp-tools/evaluate-budgets.html +6 -10
- package/public/docs/user-guide/mcp-tools/get-finding-documentation.html +4 -8
- package/public/docs/user-guide/mcp-tools/get-finding-evidence.html +4 -8
- package/public/docs/user-guide/mcp-tools/get-reference-doc.html +4 -8
- package/public/docs/user-guide/mcp-tools/get-run-summary.html +6 -10
- package/public/docs/user-guide/mcp-tools/list-runs.html +4 -8
- package/public/docs/user-guide/mcp-tools.html +4 -8
- package/public/docs/user-guide/run-comparison/how-stages-are-matched.html +6 -10
- package/public/docs/user-guide/run-comparison.html +6 -10
- package/public/docs/user-guide/understanding-findings.html +6 -10
- package/public/export-template.html +46 -46
- package/public/favicon.svg +2 -2
- package/public/index.html +4 -7
- package/vendor-core/allocation.js +105 -20
- package/vendor-core/api-merge-writes.js +1 -0
- package/vendor-core/cli/budgets.js +62 -2
- package/vendor-core/cli/regression-budgets.js +35 -0
- package/vendor-core/comparison-output.js +2 -1
- package/vendor-core/core-source-hash.txt +1 -1
- package/vendor-core/delta-log-paths.js +10 -1
- package/vendor-core/detectors.js +290 -92
- package/vendor-core/docs-content/detection/chrn.md +3 -1
- package/vendor-core/docs-content/detection/cold.md +2 -1
- package/vendor-core/docs-content/detection/mem.md +1 -1
- package/vendor-core/docs-content/detection/plan.md +9 -2
- package/vendor-core/docs-content/detection/shfl.md +8 -2
- package/vendor-core/docs-content/detection/skew.md +12 -5
- package/vendor-core/docs-content/detection/slow.md +6 -2
- package/vendor-core/docs-content/detection/spill.md +4 -1
- package/vendor-core/docs-content/detection/strag.md +5 -3
- package/vendor-core/docs-content/detection/tiny.md +3 -2
- package/vendor-core/docs-content/detection/util.md +6 -2
- package/vendor-core/efficiency-model.js +22 -14
- package/vendor-core/evidence-report.js +11 -11
- package/vendor-core/finding-presentation.js +52 -19
- package/vendor-core/finding-types.js +71 -16
- package/vendor-core/impact-model.js +2 -2
- package/vendor-core/mcp-server-factory.js +6 -2
- package/vendor-core/mcp-tools.js +10 -1
- package/vendor-core/median.js +8 -0
- package/vendor-core/remediation.js +10 -5
- package/vendor-core/run-comparison.js +2 -0
- package/vendor-core/run-output.js +14 -3
- package/vendor-core/sequence-alignment.js +83 -0
- package/vendor-core/stage-alignment.js +387 -63
- package/vendor-core/stage-quantiles.js +3 -1
- package/vendor-core/stage-structure.js +83 -0
- package/vendor-core/types.js +12 -2
- package/vendor-core/wall-clock.js +8 -0
- package/vendor-core/wasted-core-hours.js +12 -11
- package/vendor-core/write-targets.js +32 -0
- package/public/assets/AutoscalingChurn-5hDGIXi4.js +0 -1
- package/public/assets/CacheUtilization-CT2SCnJJ.js +0 -1
- package/public/assets/CachingOpportunity-D_O_WkbH.js +0 -1
- package/public/assets/ConfigAudit-BoplryCH.js +0 -1
- package/public/assets/CoreUsageArea-csgwNxkl.js +0 -1
- package/public/assets/Dashboard-BgKodJl2.js +0 -2
- package/public/assets/DisclosureContext-B0siMVdg.js +0 -1
- package/public/assets/ExecutorUtilization-Dp52QGWo.js +0 -1
- package/public/assets/MemoryUtilization-D8IUDHJI.js +0 -1
- package/public/assets/PartitionSizing-BwdFL-mw.js +0 -1
- package/public/assets/PlanGraphRoute-pqnHTt4i.js +0 -1
- package/public/assets/RetryWaste-BTbeHkJc.js +0 -1
- package/public/assets/Skew-DSNXRG9V.js +0 -1
- package/public/assets/SlowHost-B7Lwu2EU.js +0 -1
- package/public/assets/Spill-B4DVKHXx.js +0 -1
- package/public/assets/StageFindingGroup-D9naK109.js +0 -1
- package/public/assets/StageShape-eO5le8iG.js +0 -1
- package/public/assets/Straggler-D5Fnok_y.js +0 -1
- package/public/assets/TaskFailures-BWnC-K_G.js +0 -1
- package/public/assets/index-BcqTLKFp.css +0 -2
- package/public/assets/index-DCeWge12.js +0 -13
- package/public/assets/react-vendor-DEdfrRTJ.js +0 -9
- package/public/assets/useRecentFiles-C3Ov47U7.js +0 -11
- package/public/docs/assets/chunks/@localSearchIndexroot.D4OdkQjy.js +0 -1
- package/public/docs/assets/contributor-guide_architecture_board-widgets_visual-system-and-templating.md.DYgUpIJB.js +0 -1
- package/public/docs/assets/contributor-guide_architecture_detector-contract_threshold-tables.md.fkPBXsU2.js +0 -1
- package/public/docs/assets/contributor-guide_architecture_impact-estimation.md.CZv_ZGOp.js +0 -1
- package/public/docs/assets/contributor-guide_architecture_state-and-history_run-comparison-internals.md.uuAKpY0Y.js +0 -1
- package/public/docs/assets/contributor-guide_architecture_worker-protocol_cli-and-mcp.md.Dk08VS7n.js +0 -1
- package/public/docs/assets/inter-italic-cyrillic-ext.r48I6akx.woff2 +0 -0
- package/public/docs/assets/inter-italic-cyrillic.By2_1cv3.woff2 +0 -0
- package/public/docs/assets/inter-italic-greek-ext.1u6EdAuj.woff2 +0 -0
- package/public/docs/assets/inter-italic-greek.DJ8dCoTZ.woff2 +0 -0
- package/public/docs/assets/inter-italic-latin-ext.CN1xVJS-.woff2 +0 -0
- package/public/docs/assets/inter-italic-latin.C2AdPX0b.woff2 +0 -0
- package/public/docs/assets/inter-italic-vietnamese.BSbpV94h.woff2 +0 -0
- package/public/docs/assets/inter-roman-cyrillic-ext.BBPuwvHQ.woff2 +0 -0
- package/public/docs/assets/inter-roman-cyrillic.C5lxZ8CY.woff2 +0 -0
- package/public/docs/assets/inter-roman-greek-ext.CqjqNYQ-.woff2 +0 -0
- package/public/docs/assets/inter-roman-greek.BBVDIX6e.woff2 +0 -0
- package/public/docs/assets/inter-roman-latin-ext.4ZJIpNVo.woff2 +0 -0
- package/public/docs/assets/inter-roman-latin.Di8DUHzh.woff2 +0 -0
- package/public/docs/assets/inter-roman-vietnamese.BjW4sHH5.woff2 +0 -0
- package/public/docs/assets/style.tmDhD3c8.css +0 -1
- package/public/docs/assets/user-guide_getting-started_ci-and-automation.md.DpnfKz3x.js +0 -22
- package/public/docs/assets/user-guide_getting-started_ci-and-automation.md.DpnfKz3x.lean.js +0 -1
- package/public/docs/assets/user-guide_run-comparison.md.B6aNtDYF.js +0 -1
- package/public/docs/assets/user-guide_run-comparison.md.B6aNtDYF.lean.js +0 -1
- package/public/docs/assets/user-guide_run-comparison_how-stages-are-matched.md.XBzQ1oEU.js +0 -1
- package/public/docs/assets/user-guide_run-comparison_how-stages-are-matched.md.XBzQ1oEU.lean.js +0 -1
- package/public/docs/assets/user-guide_understanding-findings.md.Dqt2H_C1.js +0 -1
- package/public/docs/assets/user-guide_understanding-findings.md.Dqt2H_C1.lean.js +0 -1
- /package/public/docs/assets/{contributor-guide_architecture_board-widgets_caching-and-memory.md.8bH1HnZp.lean.js → contributor-guide_architecture_board-widgets_caching-and-memory.md.CQgn1t_M.lean.js} +0 -0
- /package/public/docs/assets/{contributor-guide_architecture_board-widgets_visual-system-and-templating.md.DYgUpIJB.lean.js → contributor-guide_architecture_board-widgets_visual-system-and-templating.md.wulOueeB.lean.js} +0 -0
- /package/public/docs/assets/{contributor-guide_architecture_detector-contract.md.wj6Et6UD.lean.js → contributor-guide_architecture_detector-contract.md.N4hhenrA.lean.js} +0 -0
- /package/public/docs/assets/{contributor-guide_architecture_detector-contract_threshold-tables.md.fkPBXsU2.lean.js → contributor-guide_architecture_detector-contract_threshold-tables.md.Dp3c40rx.lean.js} +0 -0
- /package/public/docs/assets/{contributor-guide_architecture_worker-protocol_cli-and-mcp.md.Dk08VS7n.lean.js → contributor-guide_architecture_worker-protocol_cli-and-mcp.md.BX1XnFbq.lean.js} +0 -0
- /package/public/docs/assets/{contributor-guide_architecture_worker-protocol_evidence-report.md.DVGZOWvW.lean.js → contributor-guide_architecture_worker-protocol_evidence-report.md.CiQl1MLb.lean.js} +0 -0
- /package/public/docs/assets/{contributor-guide_development-setup.md.D9bu4j_c.lean.js → contributor-guide_development-setup.md.DQdzera7.lean.js} +0 -0
- /package/public/docs/assets/{user-guide_mcp-tools_get-run-summary.md.DpxZ4ZNp.lean.js → user-guide_mcp-tools_get-run-summary.md.EhaIsele.lean.js} +0 -0
|
@@ -6,28 +6,24 @@
|
|
|
6
6
|
<title>CI and automation | SparkForensics</title>
|
|
7
7
|
<meta name="description" content="Docs for using and contributing to SparkForensics">
|
|
8
8
|
<meta name="generator" content="VitePress v1.6.4">
|
|
9
|
-
<link rel="preload stylesheet" href="/docs/assets/style.
|
|
9
|
+
<link rel="preload stylesheet" href="/docs/assets/style.CyK9Ss73.css" as="style">
|
|
10
10
|
<link rel="preload stylesheet" href="/docs/vp-icons.css" as="style">
|
|
11
11
|
|
|
12
|
-
<script type="module" src="/docs/assets/app.
|
|
13
|
-
<link rel="
|
|
14
|
-
<link rel="modulepreload" href="/docs/assets/chunks/theme.BuxVpb0H.js">
|
|
12
|
+
<script type="module" src="/docs/assets/app.CnWL6bKV.js"></script>
|
|
13
|
+
<link rel="modulepreload" href="/docs/assets/chunks/theme.BH-2HuRf.js">
|
|
15
14
|
<link rel="modulepreload" href="/docs/assets/chunks/framework.DSg0KOwT.js">
|
|
16
|
-
<link rel="modulepreload" href="/docs/assets/user-guide_getting-started_ci-and-automation.md.
|
|
15
|
+
<link rel="modulepreload" href="/docs/assets/user-guide_getting-started_ci-and-automation.md.BEepbDDL.lean.js">
|
|
17
16
|
<script>(()=>{const c=`${`[${["data","shuffle","product","bar"].join("-")}]`}, .VPNav, .VPLocalNav`,a=24,d=document.documentElement,l=t=>{const e=getComputedStyle(t);return e.display==="none"||t.getClientRects().length===0?0:e.position==="fixed"?t.getBoundingClientRect().bottom:e.position==="sticky"?(parseFloat(e.top)||0)+t.offsetHeight:0},u=()=>{try{return location.hash?document.getElementById(decodeURIComponent(location.hash.slice(1))):null}catch{return null}};let r=null;const s=()=>{const t=Array.from(document.querySelectorAll(c),l),e=Math.ceil(Math.max(0,...t))+a;if(e===r)return;const n=r;r=e,d.style.setProperty("--sf-anchor-offset",`${r}px`);const o=n===null?null:u();if(!o)return;const f=(parseFloat(getComputedStyle(o).paddingTop)||0)+2;Math.abs(o.getBoundingClientRect().top-n)<=f&&o.scrollIntoView()},i=()=>{const t=document.createElement("div");t.setAttribute("data-sf-anchor-offset",""),t.setAttribute("aria-hidden","true"),document.body.appendChild(t);const e=window.ResizeObserver?new ResizeObserver(s):null,n=()=>{e&&document.querySelectorAll(c).forEach(o=>e.observe(o)),s()};n(),new MutationObserver(n).observe(document.body,{childList:!0,subtree:!0}),window.addEventListener("resize",s),window.addEventListener("load",s)};document.readyState==="loading"?document.addEventListener("DOMContentLoaded",i,{once:!0}):i()})();</script>
|
|
18
17
|
<link rel="icon" type="image/svg+xml" href="/docs/favicon.svg">
|
|
19
|
-
<link rel="preconnect" href="https://fonts.googleapis.com">
|
|
20
|
-
<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin="">
|
|
21
|
-
<link rel="stylesheet" href="https://fonts.googleapis.com/css2?family=Recursive:wght,CASL@400..700,0..1&family=JetBrains+Mono:wght@400;500;600&display=swap">
|
|
22
18
|
<script id="check-dark-mode">(()=>{const e=localStorage.getItem("vitepress-theme-appearance")||"auto",a=window.matchMedia("(prefers-color-scheme: dark)").matches;(!e||e==="auto"?a:e==="dark")&&document.documentElement.classList.add("dark")})();</script>
|
|
23
19
|
<script id="check-mac-os">document.documentElement.classList.toggle("mac",/Mac|iPhone|iPod|iPad/i.test(navigator.platform));</script>
|
|
24
20
|
</head>
|
|
25
21
|
<body>
|
|
26
22
|
<div id="app"><div class="Layout" data-v-5d98c3a5><!--[--><!--]--><!--[--><span tabindex="-1" data-v-0b0ada53></span><a href="#VPContent" class="VPSkipLink visually-hidden" data-v-0b0ada53>Skip to content</a><!--]--><!----><header class="VPNav" data-v-5d98c3a5 data-v-ae24b3ad><div class="VPNavBar" data-v-ae24b3ad data-v-6aa21345><div class="wrapper" data-v-6aa21345><div class="container" data-v-6aa21345><div class="title" data-v-6aa21345><div class="VPNavBarTitle has-sidebar" data-v-6aa21345 data-v-1168a8e4><a class="title" href="/docs/" data-v-1168a8e4><!--[--><!--]--><!--[--><img class="VPImage logo" src="/docs/favicon.svg" alt data-v-8426fc1a><!--]--><span data-v-1168a8e4>SparkForensics</span><!--[--><!--]--></a></div></div><div class="content" data-v-6aa21345><div class="content-body" data-v-6aa21345><!--[--><!--]--><div class="VPNavBarSearch search" data-v-6aa21345><!--[--><!----><div id="local-search"><button type="button" class="DocSearch DocSearch-Button" aria-label="Search"><span class="DocSearch-Button-Container"><span class="vp-icon DocSearch-Search-Icon"></span><span class="DocSearch-Button-Placeholder">Search</span></span><span class="DocSearch-Button-Keys"><kbd class="DocSearch-Button-Key"></kbd><kbd class="DocSearch-Button-Key">K</kbd></span></button></div><!--]--></div><nav aria-labelledby="main-nav-aria-label" class="VPNavBarMenu menu" data-v-6aa21345 data-v-dc692963><span id="main-nav-aria-label" class="visually-hidden" data-v-dc692963> Main Navigation </span><!--[--><!--[--><a class="VPLink link VPNavBarMenuLink" href="/docs/user-guide/getting-started.html" tabindex="0" data-v-dc692963 data-v-e56f3d57><!--[--><span data-v-e56f3d57>User Guide</span><!--]--></a><!--]--><!--[--><a class="VPLink link VPNavBarMenuLink" href="/docs/contributor-guide/development-setup.html" tabindex="0" data-v-dc692963 data-v-e56f3d57><!--[--><span data-v-e56f3d57>Contributor Guide</span><!--]--></a><!--]--><!--[--><a class="VPLink link VPNavBarMenuLink" href="/docs/tuning-reference/" tabindex="0" data-v-dc692963 data-v-e56f3d57><!--[--><span data-v-e56f3d57>Tuning Reference</span><!--]--></a><!--]--><!--]--></nav><!----><div class="VPNavBarAppearance appearance" data-v-6aa21345 data-v-6c893767><button class="VPSwitch VPSwitchAppearance" type="button" role="switch" title aria-checked="false" data-v-6c893767 data-v-5337faa4 data-v-1d5665e3><span class="check" data-v-1d5665e3><span class="icon" data-v-1d5665e3><!--[--><span class="vpi-sun sun" data-v-5337faa4></span><span class="vpi-moon moon" data-v-5337faa4></span><!--]--></span></span></button></div><!----><div class="VPFlyout VPNavBarExtra extra" data-v-6aa21345 data-v-bb2aa2f0 data-v-cf11d7a2><button type="button" class="button" aria-haspopup="true" aria-expanded="false" aria-label="extra navigation" data-v-cf11d7a2><span class="vpi-more-horizontal icon" data-v-cf11d7a2></span></button><div class="menu" data-v-cf11d7a2><div class="VPMenu" data-v-cf11d7a2 data-v-b98bc113><!----><!--[--><!--[--><!----><div class="group" data-v-bb2aa2f0><div class="item appearance" data-v-bb2aa2f0><p class="label" data-v-bb2aa2f0>Appearance</p><div class="appearance-action" data-v-bb2aa2f0><button class="VPSwitch VPSwitchAppearance" type="button" role="switch" title aria-checked="false" data-v-bb2aa2f0 data-v-5337faa4 data-v-1d5665e3><span class="check" data-v-1d5665e3><span class="icon" data-v-1d5665e3><!--[--><span class="vpi-sun sun" data-v-5337faa4></span><span class="vpi-moon moon" data-v-5337faa4></span><!--]--></span></span></button></div></div></div><!----><!--]--><!--]--></div></div></div><!--[--><!--]--><button type="button" class="VPNavBarHamburger hamburger" aria-label="mobile navigation" aria-expanded="false" aria-controls="VPNavScreen" data-v-6aa21345 data-v-e5dd9c1c><span class="container" data-v-e5dd9c1c><span class="top" data-v-e5dd9c1c></span><span class="middle" data-v-e5dd9c1c></span><span class="bottom" data-v-e5dd9c1c></span></span></button></div></div></div></div><div class="divider" data-v-6aa21345><div class="divider-line" data-v-6aa21345></div></div></div><!----></header><div class="VPLocalNav has-sidebar empty" data-v-5d98c3a5 data-v-a6f0e41e><div class="container" data-v-a6f0e41e><button class="menu" aria-expanded="false" aria-controls="VPSidebarNav" data-v-a6f0e41e><span class="vpi-align-left menu-icon" data-v-a6f0e41e></span><span class="menu-text" data-v-a6f0e41e>Menu</span></button><div class="VPLocalNavOutlineDropdown" style="--vp-vh:0px;" data-v-a6f0e41e data-v-8a42e2b4><button data-v-8a42e2b4>Return to top</button><!----></div></div></div><aside class="VPSidebar" data-v-5d98c3a5 data-v-319d5ca6><div class="curtain" data-v-319d5ca6></div><nav class="nav" id="VPSidebarNav" aria-labelledby="sidebar-aria-label" tabindex="-1" data-v-319d5ca6><span class="visually-hidden" id="sidebar-aria-label" data-v-319d5ca6> Sidebar Navigation </span><!--[--><!--]--><!--[--><div class="no-transition group" data-v-c40bc020><section class="VPSidebarItem level-0 has-active" data-v-c40bc020 data-v-b3fd67f8><div class="item" role="button" tabindex="0" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><h2 class="text" data-v-b3fd67f8>User Guide</h2><!----></div><div class="items" data-v-b3fd67f8><!--[--><section class="VPSidebarItem level-1 collapsible collapsed is-link has-active" data-v-b3fd67f8><div class="item" tabindex="0" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/user-guide/getting-started.html" data-v-b3fd67f8><!--[--><h3 class="text" data-v-b3fd67f8>Getting started</h3><!--]--></a><div class="caret" role="button" aria-label="toggle section" tabindex="0" data-v-b3fd67f8><span class="vpi-chevron-right caret-icon" data-v-b3fd67f8></span></div></div><div class="items" data-v-b3fd67f8><!--[--><div class="VPSidebarItem level-2 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/user-guide/getting-started/reading-the-dashboard.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Reading the dashboard</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-2 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/user-guide/getting-started/ci-and-automation.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>CI and automation</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-2 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/user-guide/getting-started/tuning-thresholds.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Tuning detector thresholds</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-2 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/user-guide/getting-started/regression-metric-keys.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Regression metric keys</p><!--]--></a><!----></div><!----></div><!--]--></div></section><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/user-guide/understanding-findings.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Understanding findings</p><!--]--></a><!----></div><!----></div><section class="VPSidebarItem level-1 collapsible collapsed is-link" data-v-b3fd67f8><div class="item" tabindex="0" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/user-guide/run-comparison.html" data-v-b3fd67f8><!--[--><h3 class="text" data-v-b3fd67f8>Run comparison mode</h3><!--]--></a><div class="caret" role="button" aria-label="toggle section" tabindex="0" data-v-b3fd67f8><span class="vpi-chevron-right caret-icon" data-v-b3fd67f8></span></div></div><div class="items" data-v-b3fd67f8><!--[--><div class="VPSidebarItem level-2 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/user-guide/run-comparison/how-stages-are-matched.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>How stages are matched</p><!--]--></a><!----></div><!----></div><!--]--></div></section><section class="VPSidebarItem level-1 collapsible collapsed is-link" data-v-b3fd67f8><div class="item" tabindex="0" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/user-guide/mcp-tools.html" data-v-b3fd67f8><!--[--><h3 class="text" data-v-b3fd67f8>MCP tools reference</h3><!--]--></a><div class="caret" role="button" aria-label="toggle section" tabindex="0" data-v-b3fd67f8><span class="vpi-chevron-right caret-icon" data-v-b3fd67f8></span></div></div><div class="items" data-v-b3fd67f8><!--[--><div class="VPSidebarItem level-2 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/user-guide/mcp-tools/diagnose-run.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>diagnose_run</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-2 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/user-guide/mcp-tools/get-run-summary.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>get_run_summary</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-2 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/user-guide/mcp-tools/evaluate-budgets.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>evaluate_budgets</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-2 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/user-guide/mcp-tools/compare-runs.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>compare_runs</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-2 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/user-guide/mcp-tools/get-finding-evidence.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>get_finding_evidence</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-2 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/user-guide/mcp-tools/get-finding-documentation.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>get_finding_documentation</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-2 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/user-guide/mcp-tools/get-reference-doc.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>get_reference_doc</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-2 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/user-guide/mcp-tools/list-runs.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>list_runs</p><!--]--></a><!----></div><!----></div><!--]--></div></section><section class="VPSidebarItem level-1 collapsible collapsed is-link" data-v-b3fd67f8><div class="item" tabindex="0" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/user-guide/alternative-log-retrieval.html" data-v-b3fd67f8><!--[--><h3 class="text" data-v-b3fd67f8>Finding your event log</h3><!--]--></a><div class="caret" role="button" aria-label="toggle section" tabindex="0" data-v-b3fd67f8><span class="vpi-chevron-right caret-icon" data-v-b3fd67f8></span></div></div><div class="items" data-v-b3fd67f8><!--[--><div class="VPSidebarItem level-2 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/user-guide/alternative-log-retrieval/managed-platforms.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Managed platforms</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-2 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/user-guide/alternative-log-retrieval/ssh-bastion.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Behind an SSH bastion</p><!--]--></a><!----></div><!----></div><!--]--></div></section><!--]--></div></section></div><!--]--><!--[--><!--]--></nav></aside><div class="VPContent has-sidebar" id="VPContent" data-v-5d98c3a5 data-v-1428d186><div class="VPDoc has-sidebar has-aside" data-v-1428d186 data-v-39a288b8><!--[--><!--]--><div class="container" data-v-39a288b8><div class="aside" data-v-39a288b8><div class="aside-curtain" data-v-39a288b8></div><div class="aside-container" data-v-39a288b8><div class="aside-content" data-v-39a288b8><div class="VPDocAside" data-v-39a288b8 data-v-3f215769><!--[--><!--]--><!--[--><!--]--><nav aria-labelledby="doc-outline-aria-label" class="VPDocAsideOutline" data-v-3f215769 data-v-a5bbad30><div class="content" data-v-a5bbad30><div class="outline-marker" data-v-a5bbad30></div><div aria-level="2" class="outline-title" id="doc-outline-aria-label" role="heading" data-v-a5bbad30>On this page</div><ul class="VPDocOutlineItem root" data-v-a5bbad30 data-v-b933a997><!--[--><!--]--></ul></div></nav><!--[--><!--]--><div class="spacer" data-v-3f215769></div><!--[--><!--]--><!----><!--[--><!--]--><!--[--><!--]--></div></div></div></div><div class="content" data-v-39a288b8><div class="content-container" data-v-39a288b8><!--[--><!--]--><main class="main" data-v-39a288b8><div style="position:relative;" class="vp-doc _docs_user-guide_getting-started_ci-and-automation" data-v-39a288b8><div><h1 id="ci-and-automation" tabindex="-1">CI and automation <a class="header-anchor" href="#ci-and-automation" aria-label="Permalink to "CI and automation""></a></h1><p>How to run SparkForensics from a pipeline or script with the <code>analyze</code> CLI: its output formats, the extra data in the JSON report, and gating on several budgets and candidates.</p><p>In a pipeline or a script, use the <code>analyze</code> CLI instead of the browser dashboard. It parses the same event logs and exits non-zero when a run crosses a threshold you set, so it can gate a build:</p><div class="language-sh vp-adaptive-theme"><button title="Copy Code" class="copy"></button><span class="lang">sh</span><pre class="shiki shiki-themes github-light github-dark vp-code" tabindex="0"><code><span class="line"><span style="--shiki-light:#6F42C1;--shiki-dark:#B392F0;">npx</span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;"> -p</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;"> sparkforensics-cli</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;"> sparkforensics-analyze</span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583;"> <</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">file</span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583;">|</span><span style="--shiki-light:#6F42C1;--shiki-dark:#B392F0;">dir</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">> [--max-runtime </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">ms]</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> [--max-skew </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">ratio]</span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;"> \</span></span>
|
|
27
23
|
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> [--max-spill </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">gb]</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> [--max-failed-task-rate </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">pct]</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> [--min-efficiency </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">pct]</span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;"> \</span></span>
|
|
28
|
-
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> [--out </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">path]</span></span></code></pre></div><p>Output is JSON by default; <code>--format md</code> writes the Markdown report instead. Budget violations and inconclusive budgets print to stderr as <code>[violation] ...</code> and <code>[inconclusive] ...</code> lines. The exit code is 0 when every budget passes, 1 when one is violated, 3 when none is violated but one is inconclusive, 2 for a usage error (bad flags or arguments, an invalid <code>--thresholds</code> or <code>--budgets</code> file), 4 when the candidate log can't be read or parsed or its History Server fetch fails, 5 when the <code>--baseline</code> log can't be read or parsed, and 6 for an internal error, including a failed <code>--export-html</code>. When several of these apply, the worst wins in this order: 6, 5, 4, 1, 3, 0. A usage error exits 2 before any log is read.</p><p><code>--min-efficiency</code> checks busy core time, the share of executor core time that ran tasks (100 minus the dashboard's Unused core time). It is not the dashboard's Efficiency tile, which is the share of wall-clock with a stage running, so the two can differ widely on the same run.</p><p>The command ships in the <code>sparkforensics-cli</code> package. To install it once: <code>npm i -g sparkforensics-cli</code>, then run <code>sparkforensics-analyze</code> directly. <code>npx sparkforensics-analyze <file></code> is a shorter way to run the same command.</p><p>Point it at a single event-log file, or at one run's <code>eventlog_v2_*</code> rolling-log directory; any other directory is rejected. Output goes to stdout; pass <code>--out <path></code> to write it to that file instead.</p><p>Pass <code>--export-html <dir></code> to write a self-contained HTML dashboard for the run into <code><dir></code> (which must not already exist or must be empty). Open <code><dir>/index.html</code> directly in a browser over <code>file://</code>, with no server, to get the same interactive dashboard offline, without the docs links. This makes it easy to archive or share a run. <code>--redact</code> applies to the exported report too.</p><h2 id="machine-readable-fixes-and-costs" tabindex="-1">Machine-readable fixes and costs <a class="header-anchor" href="#machine-readable-fixes-and-costs" aria-label="Permalink to "Machine-readable fixes and costs""></a></h2><p>Each row of the JSON report's <code>findings</code> array carries two fields for a script or tuning loop that acts on the output without reading prose.</p><p><code>remediation</code> is an array of the
|
|
24
|
+
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> [--out </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">path]</span></span></code></pre></div><p>Output is JSON by default; <code>--format md</code> writes the Markdown report instead. Budget violations and inconclusive budgets print to stderr as <code>[violation] ...</code> and <code>[inconclusive] ...</code> lines. The exit code is 0 when every budget passes, 1 when one is violated, 3 when none is violated but one is inconclusive, 2 for a usage error (bad flags or arguments, an invalid <code>--thresholds</code> or <code>--budgets</code> file), 4 when the candidate log can't be read or parsed or its History Server fetch fails, 5 when the <code>--baseline</code> log can't be read or parsed, and 6 for an internal error, including a failed <code>--export-html</code>. When several of these apply, the worst wins in this order: 6, 5, 4, 1, 3, 0. A usage error exits 2 before any log is read.</p><p><code>--min-efficiency</code> checks busy core time, the share of executor core time that ran tasks (100 minus the dashboard's Unused core time). It is not the dashboard's Efficiency tile, which is the share of wall-clock with a stage running, so the two can differ widely on the same run.</p><p>The command ships in the <code>sparkforensics-cli</code> package. To install it once: <code>npm i -g sparkforensics-cli</code>, then run <code>sparkforensics-analyze</code> directly. <code>npx sparkforensics-analyze <file></code> is a shorter way to run the same command.</p><p>Point it at a single event-log file, or at one run's <code>eventlog_v2_*</code> rolling-log directory; any other directory is rejected. Output goes to stdout; pass <code>--out <path></code> to write it to that file instead.</p><p>Pass <code>--export-html <dir></code> to write a self-contained HTML dashboard for the run into <code><dir></code> (which must not already exist or must be empty). Open <code><dir>/index.html</code> directly in a browser over <code>file://</code>, with no server, to get the same interactive dashboard offline, without the docs links. This makes it easy to archive or share a run. <code>--redact</code> applies to the exported report too.</p><h2 id="machine-readable-fixes-and-costs" tabindex="-1">Machine-readable fixes and costs <a class="header-anchor" href="#machine-readable-fixes-and-costs" aria-label="Permalink to "Machine-readable fixes and costs""></a></h2><p>Each row of the JSON report's <code>findings</code> array carries two fields for a script or tuning loop that acts on the output without reading prose.</p><p><code>remediation</code> is an array of the changes the row's <code>recommendation</code> names, in structured form. It is empty when the recommendation names no Spark property and no change to the job.</p><div class="language-json vp-adaptive-theme"><button title="Copy Code" class="copy"></button><span class="lang">json</span><pre class="shiki shiki-themes github-light github-dark vp-code" tabindex="0"><code><span class="line"><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">"remediation"</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: [</span></span>
|
|
29
25
|
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> { </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">"kind"</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">"conf"</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">, </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">"key"</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">"spark.sql.shuffle.partitions"</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">, </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">"direction"</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">"increase"</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">, </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">"suggested"</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">800</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> }</span></span>
|
|
30
|
-
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">]</span></span></code></pre></div><ul><li><code>kind</code> is always <code>"conf"</code>: a Spark property.</li><li><code>direction</code> is <code>"increase"</code> or <code>"decrease"</code> (move the current value that way) or <code>"set"</code> (take the <code>suggested</code> value, for a switch or a class name).</li><li><code>suggested</code> is the value the detector computed, or <code>null</code> when it computes none. Counts are numbers, switches are booleans, sizes carry a Spark unit suffix (<code>"1024m"</code>).</li></ul><p><code>impactEstimate.coreTimeMs</code> is the busy core time the fix removes: the executor task time, in core-milliseconds, next to the <code>wallClock</code> range (elapsed time). It is a <code>{ "low": ..., "high": ... }</code> range with <code>low</code> equal to <code>high</code>, or <code>null</code> when the detector measures no such figure: <code>null</code> means unknown, never zero. Only figures read from the log count: GC time, the executor time of retried and discarded speculative attempts, and for skew and straggler findings the task time the fix removes from the slow tasks. These are set even when the log has no executor core data. A finding with only a wall-clock claim has <code>coreTimeMs: null</code>: its elapsed time is not converted to core time. Task run time is used, not <code>executorCpuTime</code>, so Python worker CPU is not missed.</p><p>Findings whose only figure is bytes or memory-time have <code>coreTimeMs: null</code>, as do findings whose core figure rests on an assumed constant: <code>coreLocality</code>'s per-task fetch penalty and the executor-hours or job-hours of <code>autoscalingChurn</code> and <code>jobFailureRate</code>. Their <code>rawWaste</code> is unchanged.</p><p><code>coreTimeMs</code> never includes idle capacity. A finding whose waste is allocated cores that ran no task (<code>utilization</code>, <code>stageShape</code>'s low parallelism and task/stage skew rows) has <code>coreTimeMs: null</code> and keeps its figure in <code>impactEstimate.rawWaste</code> with <code>"idle": true</code>; every surface labels it "of idle core capacity", not "of core time". A stage's slow tail is counted once: when <code>skew</code> and <code>straggler</code> both flag the same stage, <code>skew</code> carries the removed task time and <code>straggler</code> has <code>null</code>.</p><p>When the logged <code>spark.sql.shuffle.partitions</code> is already at or above the count a low-parallelism shuffle stage needs, the property is not what limits that stage: the recommendation points at the stage's own partitioning (<code>repartition(n)</code> or RDD parallelism) and <code>remediation</code> is empty.</p><p>A <code>remediation</code> that sets a property to a fixed value (for example <code>spark.sql.adaptive.skewJoin.enabled</code>, <code>spark.speculation</code> or <code>spark.dynamicAllocation.enabled</code>) is left out when the run's logged conf already has that value; booleans compare case-insensitively. The recommendation then stops naming that property and points at the remedy left (for example "AQE skew-join handling is already on, so salt the key or repartition on a better key"), so the text and <code>remediation</code> never disagree. The dashboard's one-line fix for a group of such findings follows the same logged conf. Only properties the event log records count: Spark's unlogged version defaults (such as skew-join handling being on by default with AQE in Spark 3.2+) are not modeled, so such a run can still get the suggestion.</p><p>Two logged settings change which fix is offered. Skew-join handling counts as already on only when <code>spark.sql.adaptive.enabled</code> is not logged <code>false</code>; with AQE logged off, the skew findings suggest setting <code>spark.sql.adaptive.enabled</code> to <code>true</code> instead. When <code>spark.sql.autoBroadcastJoinThreshold</code> is logged <code>-1</code> (auto-broadcast disabled), an over-broadcast finding has an empty <code>remediation</code> and points at removing the <code>broadcast()</code> hint.</p><p>The CLI also supports fetching a run directly from a reachable Spark History Server (<code>--shs-base-url</code>/<code>--app-id</code>/<code>--attempt-id</code>) instead of a local file, comparing a candidate run against a baseline with regression gating (<code>--baseline</code>/<code>--max-regression-pct</code>/<code>--regression-metric</code>/ <code>--fail-on-introduced</code>; the baseline is a local file or rolling-log directory, no History Server), several regression budgets and several candidates in one call (<code>--regression-budget</code>/<code>--budgets</code>, see <a href="#several-budgets-and-several-candidates">Several budgets and several candidates</a>), rewriting run-specific text before stages are paired (<code>--normalize-path</code>, see <a href="#pairing-stages-across-runs">Pairing stages across runs</a>), redacting the app id, the app name and any host/IP tokens before sharing output (<code>--redact</code>), and narrowing the findings to certain impact bands, types, or a stage (<code>--impact</code>/<code>--type</code>/<code>--stage</code>), and tuning detector thresholds from a file (<code>--thresholds</code>, below). Run it with <code>--help</code> for the full flag list.</p><p>Same caveat as above: if the History Server is only reachable through an SSH bastion, <code>--shs-base-url</code> can't reach it either: see <a href="./../alternative-log-retrieval/ssh-bastion.html#behind-an-ssh-bastion">Behind an SSH bastion</a>.</p><p>Running in Airflow instead of a plain CI pipeline? See <a href="https://github.com/shuffle-works/sparkforensics-operator" target="_blank" rel="noreferrer">sparkforensics-operator</a>, an Airflow operator that wraps the CLI and acts on the result after each Spark job, so you don't have to wire up the call yourself.</p><p>Want an AI assistant to diagnose a run directly, without the dashboard or a CI gate? See <a href="./../mcp-tools.html">MCP tools reference</a>.</p><h2 id="write-targets" tabindex="-1">Write targets <a class="header-anchor" href="#write-targets" aria-label="Permalink to "Write targets {#write-targets}""></a></h2><p>The JSON report has a top-level <code>writeTargets</code> object listing every SQL write in the run, so a script can check where a job wrote without reading the plan. It has no Markdown counterpart. The MCP <code>diagnose_run</code> tool returns it too.</p><div class="language-json vp-adaptive-theme"><button title="Copy Code" class="copy"></button><span class="lang">json</span><pre class="shiki shiki-themes github-light github-dark vp-code" tabindex="0"><code><span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">{</span></span>
|
|
26
|
+
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">]</span></span></code></pre></div><ul><li><code>kind</code> is <code>"conf"</code> (a Spark property) or <code>"code"</code> (a change to the job's code or data). A consumer that reads <code>key</code> checks <code>kind</code> first.</li><li><code>direction</code> is <code>"increase"</code> or <code>"decrease"</code> (move the current value that way) or <code>"set"</code> (take the <code>suggested</code> value, for a switch or a class name).</li><li>Entries apply together unless the <code>recommendation</code> words them as alternatives ("either ... or"). An idle-capacity finding (<code>utilization</code>, <code>memoryUtilization</code> with <code>variant: "idleCores"</code>) does this with dynamic allocation off or unset: <code>set spark.dynamicAllocation.enabled</code> and <code>decrease spark.executor.instances</code> are alternatives, so apply one. With dynamic allocation on, it lowers <code>spark.dynamicAllocation.maxExecutors</code>, and also <code>spark.dynamicAllocation.minExecutors</code> when the run logs a value above 0.</li><li><code>suggested</code> is the value the detector computed, or <code>null</code> when it computes none. Counts are numbers, switches are booleans, sizes carry a Spark unit suffix (<code>"1024m"</code>).</li></ul><p>A <code>code</code> entry has no <code>key</code>, <code>direction</code> or <code>suggested</code>, only a <code>hint</code>:</p><div class="language-json vp-adaptive-theme"><button title="Copy Code" class="copy"></button><span class="lang">json</span><pre class="shiki shiki-themes github-light github-dark vp-code" tabindex="0"><code><span class="line"><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">"remediation"</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: [{ </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">"kind"</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">"code"</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">, </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">"hint"</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">"salt the key or repartition on a better key"</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> }]</span></span></code></pre></div><p>Skew and straggler findings carry one when no property can fix them: the stage's <code>evidence.origin</code> is <code>other</code>, or AQE skew-join handling is already on. The <code>hint</code> is the remedy the <code>recommendation</code> gives.</p><p><code>impactEstimate.coreTimeMs</code> is the busy core time the fix removes: the executor task time, in core-milliseconds, next to the <code>wallClock</code> range (elapsed time). It is a <code>{ "low": ..., "high": ... }</code> range with <code>low</code> equal to <code>high</code>, or <code>null</code> when the detector measures no such figure: <code>null</code> means unknown, never zero. Only figures read from the log count: GC time, the executor time of retried and discarded speculative attempts, and for skew and straggler findings the task time the fix removes from the slow tasks. These are set even when the log has no executor core data. A finding with only a wall-clock claim has <code>coreTimeMs: null</code>: its elapsed time is not converted to core time. Task run time is used, not <code>executorCpuTime</code>, so Python worker CPU is not missed.</p><p>Findings whose only figure is bytes or memory-time have <code>coreTimeMs: null</code>, as do findings whose core figure rests on an assumed constant: <code>coreLocality</code>'s per-task fetch penalty and the executor-hours or job-hours of <code>autoscalingChurn</code> and <code>jobFailureRate</code>. Their <code>rawWaste</code> is unchanged.</p><p><code>coreTimeMs</code> never includes idle capacity. A finding whose waste is allocated cores that ran no task (<code>utilization</code>, <code>stageShape</code>'s low parallelism and task/stage skew rows) has <code>coreTimeMs: null</code> and keeps its figure in <code>impactEstimate.rawWaste</code> with <code>"idle": true</code>; every surface labels it "of idle core capacity", not "of core time". A stage's slow tail is counted once: when <code>skew</code> and <code>straggler</code> both flag the same stage, <code>skew</code> carries the removed task time and <code>straggler</code> has <code>null</code>.</p><p><code>impactEstimate.idleCoreTimeMs</code> is the idle capacity as a number a script can rank by: the <code>utilization</code> finding's allocated core time that ran no task, in core-milliseconds, as a <code>{ "low": ..., "high": ... }</code> range with <code>low</code> equal to <code>high</code>. It is the run's allocated core-milliseconds (<code>allocation.coreHours</code>) minus the busy core-milliseconds, never below zero and never above the allocation. It is the same quantity as the finding's <code>rawWaste</code>, kept apart from <code>coreTimeMs</code>, which is busy time a fix removes. The field is absent on every other finding, and on a <code>utilization</code> finding the log gives no executor cores to allocate. The <code>memoryUtilization</code> finding with <code>variant: "idleCores"</code> is the memory view of the same condition and carries no <code>idleCoreTimeMs</code>.</p><p>A finding on a serial basis whose figure is modeled has no core time either. <code>partitionSizing</code>'s <code>lowShuffleParallelism</code> reports <code>rawWaste</code> in <code>ms</code>: stage wall-clock that more partitions shorten, not task work they remove. It has <code>coreTimeMs: null</code> and is ranked on <code>wallClock</code>, which models the stage with its longest task split evenly across the partition count the stage needs.</p><p>When the effective <code>spark.sql.shuffle.partitions</code> (logged, else Spark's 200) is already at or above the count a low-parallelism shuffle stage needs, the property is not what limits that stage: the recommendation points at the stage's own partitioning (<code>repartition(n)</code> or RDD parallelism) and <code>remediation</code> is empty. When AQE coalescing is on and the stage ran fewer tasks than the property, AQE merged the partitions and the recommendation points at <code>spark.sql.adaptive.advisoryPartitionSizeInBytes</code> instead. <code>shuffle</code> and <code>partitionSizing</code> (<code>lowShuffleParallelism</code>) findings carry <code>evidence.partitions</code> (<code>raise</code>, <code>sufficient</code>, <code>aqeCoalesced</code> or <code>ownPartitioning</code>) for the case.</p><p>A <code>remediation</code> that sets a property to a fixed value (for example <code>spark.sql.adaptive.skewJoin.enabled</code>, <code>spark.speculation</code> or <code>spark.dynamicAllocation.enabled</code>) is left out when the run's effective conf already has that value. The effective value is the logged property, else Spark's default for the run's <code>sparkVersion</code>; the defaults modeled are <code>spark.sql.adaptive.enabled</code> (off before Spark 3.2, on from 3.2), <code>spark.sql.adaptive.skewJoin.enabled</code> and <code>spark.sql.adaptive.coalescePartitions.enabled</code> (both on from 3.0), and, for every version, <code>spark.sql.shuffle.partitions</code> (200) and <code>spark.sql.autoBroadcastJoinThreshold</code> (10 MiB). Spark before 3.0 has no AQE skew-join handling, so a skew finding on such a run suggests no conf. Booleans compare case-insensitively. The recommendation then stops naming that property and points at the remedy left (for example "AQE skew-join handling is already on, so salt the key or repartition on a better key"), so the text and <code>remediation</code> never disagree. The dashboard's one-line fix for a group of such findings follows the same effective conf.</p><p>Two effective settings change which fix is offered. Skew-join handling counts as already on only when <code>spark.sql.adaptive.enabled</code> is not effectively <code>false</code>; with AQE off (logged, or the default on Spark 3.0 and 3.1), the skew findings suggest setting <code>spark.sql.adaptive.enabled</code> to <code>true</code> instead. When <code>spark.sql.autoBroadcastJoinThreshold</code> is logged <code>-1</code> (auto-broadcast disabled), an over-broadcast finding has an empty <code>remediation</code> and points at removing the <code>broadcast()</code> hint.</p><p>Skew-join handling is only suggested for a stage that reads a shuffle in a SQL execution whose plan has a sort-merge or shuffled-hash join. Skew findings carry <code>evidence.origin</code>: <code>shuffleJoin</code> (the conf above applies), <code>inputScan</code> (a stage reading uneven input files: the remediation lowers <code>spark.sql.files.maxPartitionBytes</code>) or <code>other</code> (no conf is suggested; the <code>remediation</code> holds a <code>code</code> entry). <code>shufflePartitionSkew</code> carries the same field but is judged on shuffle-read sizes, so it is only ever <code>shuffleJoin</code> or <code>other</code>. A <code>stageSlowness</code> finding carries <code>evidence.reads</code> (<code>shuffle</code>, <code>input</code> or <code>other</code>) and suggests shuffle partitions only for <code>shuffle</code>; <code>spill</code> and <code>tinyTask</code> carry the same <code>reads</code> key and gate their shuffle-partition advice the same way. <code>straggler</code> carries <code>evidence.origin</code> and the same skew advice as a skew finding on that stage. <code>coldStart</code> and <code>autoscalingChurn</code> carry <code>evidence.dynamicAllocation</code> (<code>on</code> or <code>off</code>) and suggest no dynamic-allocation property when it is <code>off</code>. <code>underBroadcast</code> and <code>overBroadcast</code> carry <code>evidence.broadcastThreshold</code> (<code>limits</code>, <code>notLimiting</code> or <code>disabled</code>) and suggest changing the threshold only when it limits the join.</p><p>The CLI also supports fetching a run directly from a reachable Spark History Server (<code>--shs-base-url</code>/<code>--app-id</code>/<code>--attempt-id</code>) instead of a local file, comparing a candidate run against a baseline with regression gating (<code>--baseline</code>/<code>--max-regression-pct</code>/<code>--regression-metric</code>/ <code>--fail-on-introduced</code>; the baseline is a local file or rolling-log directory, no History Server), several regression budgets and several candidates in one call (<code>--regression-budget</code>/<code>--budgets</code>, see <a href="#several-budgets-and-several-candidates">Several budgets and several candidates</a>), rewriting run-specific text before stages are paired (<code>--normalize-path</code>, see <a href="#pairing-stages-across-runs">Pairing stages across runs</a>), redacting the app id, the app name and any host/IP tokens before sharing output (<code>--redact</code>), and narrowing the findings to certain impact bands, types, or a stage (<code>--impact</code>/<code>--type</code>/<code>--stage</code>), and tuning detector thresholds from a file (<code>--thresholds</code>, below). Run it with <code>--help</code> for the full flag list.</p><p>Same caveat as above: if the History Server is only reachable through an SSH bastion, <code>--shs-base-url</code> can't reach it either: see <a href="./../alternative-log-retrieval/ssh-bastion.html#behind-an-ssh-bastion">Behind an SSH bastion</a>.</p><p>Running in Airflow instead of a plain CI pipeline? See <a href="https://github.com/shuffle-works/sparkforensics-operator" target="_blank" rel="noreferrer">sparkforensics-operator</a>, an Airflow operator that wraps the CLI and acts on the result after each Spark job, so you don't have to wire up the call yourself.</p><p>Want an AI assistant to diagnose a run directly, without the dashboard or a CI gate? See <a href="./../mcp-tools.html">MCP tools reference</a>.</p><h2 id="write-targets" tabindex="-1">Write targets <a class="header-anchor" href="#write-targets" aria-label="Permalink to "Write targets {#write-targets}""></a></h2><p>The JSON report has a top-level <code>writeTargets</code> object listing every SQL write in the run, so a script can check where a job wrote without reading the plan. It has no Markdown counterpart. The MCP <code>diagnose_run</code> tool returns it too.</p><div class="language-json vp-adaptive-theme"><button title="Copy Code" class="copy"></button><span class="lang">json</span><pre class="shiki shiki-themes github-light github-dark vp-code" tabindex="0"><code><span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">{</span></span>
|
|
31
27
|
<span class="line"><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;"> "writes"</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: [</span></span>
|
|
32
28
|
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> {</span></span>
|
|
33
29
|
<span class="line"><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;"> "sqlExecutionId"</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">3</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">,</span></span>
|
|
@@ -37,15 +33,17 @@
|
|
|
37
33
|
<span class="line"><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;"> "kind"</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">"path"</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">,</span></span>
|
|
38
34
|
<span class="line"><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;"> "target"</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">"hdfs://nn/sandbox/out/t1"</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">,</span></span>
|
|
39
35
|
<span class="line"><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;"> "outputRows"</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">5000000</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">,</span></span>
|
|
36
|
+
<span class="line"><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;"> "mergeRows"</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">null</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">,</span></span>
|
|
40
37
|
<span class="line"><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;"> "raw"</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">"Execute InsertIntoHadoopFsRelationCommand hdfs://nn/sandbox/out/t1, false, Parquet, ..."</span></span>
|
|
41
38
|
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> }</span></span>
|
|
42
39
|
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> ],</span></span>
|
|
43
40
|
<span class="line"><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;"> "executionsWithoutPlan"</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: [{ </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">"sqlExecutionId"</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">4</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">, </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">"reason"</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">"noPlan"</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> }],</span></span>
|
|
44
41
|
<span class="line"><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;"> "skippedLines"</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">0</span></span>
|
|
45
|
-
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">}</span></span></code></pre></div><ul><li><p><code>writes</code> holds one row per write node, ordered by SQL execution id and then by position in the plan. A <code>DeltaTable</code> API merge has no write node: it is one extra row per merge, see <a href="#delta-writes">Delta writes</a>. <code>command</code> is the plan node's name without the <code>Execute </code> prefix or an <code>Exec</code> suffix, <code>nodeId</code> is the plan node's id, and <code>raw</code> is the node's full plan string as the log recorded it.</p></li><li><p><code>kind</code> says how to read <code>target</code>:</p><ul><li><code>path</code> is a filesystem location.</li><li><code>table</code> is a table name whose catalog the command states or implies: a Hive or V1 command's <code>database.table</code>, a DataSource V2 name with a catalog part (<code>catalog.namespace.table</code>), or a Delta command's table as <code>database.table</code> (a table in the session catalog) or <code>catalog.database.table</code>.</li><li><code>unqualifiedTable</code> is a DataSource V2 name with no catalog part, such as <code>default.events</code> or <code>events</code>. The log does not say which catalog it lives in, so a check on its database part alone can match the wrong catalog.</li><li><code>jdbcTable</code> is a <code>dbtable</code> of a JDBC write. It names a table in an external database, not in a Spark catalog, and the database itself (the JDBC url) is not reported.</li></ul><p>Every target is copied verbatim from the plan string: nothing is resolved, so a relative path, an unexpanded <code>${var}</code> placeholder or a bare table name appears exactly as the log states it. Backticks around table name parts are dropped.</p></li><li><p><code>target</code> and <code>kind</code> are <code>null</code> when the target cannot be determined. That covers a node whose plan string has no target (Spark omits it for some commands, and Delta command nodes carry none on real logs, which <a href="#delta-writes">Delta writes</a> covers), a redacted option value, a plan string that names more than one candidate target, and a plan string Spark cut short. A target is reported only when its whole text is followed by a delimiter in the plan string: a path cut by <code>spark.sql.maxMetadataStringLength</code> or a name with a <code>...</code> marker in it is <code>null</code>, never a partial path. A trailing <code>... N more fields</code> after the target, such as the column list of <code>InsertIntoHadoopFsRelationCommand</code>, does not affect the target before it. Treat a <code>null</code> target as unknown, not as inside or outside any location.</p></li><li><p><code>outputRows</code> is the node's own <code>number of output rows</code> SQL metric. It is <code>null</code> when the log has no such metric for that node, which is the case for the DataSource V2 and Delta write nodes that report other metrics.</p></li><li><p><code>recognized</code> is <code>true</code> for the commands below and <code>false</code> for a write-like node that is not in that list. An unrecognized write always has <code>target</code> and <code>kind</code> <code>null</code>, and <code>raw</code> is the only information about it.</p></li><li><p><code>executionsWithoutPlan</code> lists the SQL executions whose writes the report cannot see, each with a <code>reason</code>. <code>noPlan</code> means the execution started but the log has no plan for it, such as an execution still running when the log was cut off (a plan is read when its execution ends). <code>unreadableStart</code> means the execution's start event was skipped because it could not be read, for example a plan nested deeper than 500 nodes or a start line cut off at the end of the log. A write in one of these executions is not in <code>writes</code>, so a non-empty list means the report may be incomplete.</p></li><li><p><code>skippedLines</code> is the number of log lines the parser could not read. A line cut off before its execution id is not in <code>executionsWithoutPlan</code>, so a non-zero count means a write may be missing even when that list is empty. It is <code>null</code> when the count is unknown.</p></li></ul><p>Recognized commands and where their target comes from:</p><table tabindex="0"><thead><tr><th>Command</th><th>Target</th></tr></thead><tbody><tr><td><code>InsertIntoHadoopFsRelationCommand</code></td><td><code>path</code>: the first argument, including for an <code>INSERT OVERWRITE ... PARTITION</code> that prints a static-partition map after it</td></tr><tr><td><code>InsertIntoHiveTable</code>, <code>CreateDataSourceTableAsSelectCommand</code>, <code>CreateHiveTableAsSelectCommand</code>, <code>OptimizedCreateHiveTableAsSelectCommand</code></td><td><code>table</code>: the first argument</td></tr><tr><td><code>SaveIntoDataSourceCommand</code></td><td><code>path</code> from the <code>path</code> option, or <code>jdbcTable</code> from the JDBC <code>dbtable</code>/<code>table</code> option</td></tr><tr><td><code>AppendData</code>, <code>OverwriteByExpression</code>, <code>OverwritePartitionsDynamic</code>, <code>ReplaceData</code>, <code>WriteDelta</code>, <code>WriteToDataSourceV2</code>, <code>AppendDataExecV1</code>, <code>OverwriteByExpressionExecV1</code></td><td><code>table</code> or <code>unqualifiedTable</code>: the <code>table=</code> of the connector's write object, for example Iceberg's <code>IcebergWrite(table=..., ...)</code>. For a Delta table, see <a href="#delta-writes">Delta writes</a></td></tr><tr><td><code>CreateTableAsSelect</code>, <code>AtomicCreateTableAsSelect</code>, <code>ReplaceTableAsSelect</code>, <code>AtomicReplaceTableAsSelect</code></td><td><code>table</code> or <code>unqualifiedTable</code>: the identifier after the catalog object, which does not name the catalog</td></tr><tr><td><code>WriteIntoDelta</code>, <code>WriteIntoDeltaCommand</code>, <code>UpdateCommand</code>, <code>DeleteCommand</code>, <code>MergeIntoCommand</code></td><td><code>path</code>: the first argument when it is a <code>delta.</code> path table (never for <code>MergeIntoCommand</code>, whose plan string also prints the source); otherwise as in <a href="#delta-writes">Delta writes</a></td></tr><tr><td><code>CreateDeltaTableCommand</code>, <code>OptimizeTableCommand</code>, <code>RestoreTableCommand</code>, <code>DeltaReorgTableCommand</code></td><td><code>path</code>: the first argument when it is a <code>delta.</code> path table, otherwise <code>null</code></td></tr><tr><td><code>DeltaMerge</code></td><td>not a plan node: one row per <code>DeltaTable</code> API merge, see <a href="#delta-writes">Delta writes</a></td></tr></tbody></table><p>A plan node not in the table is a write when its operator name (the first word of the node name after any leading <code>Execute</code>, so not the relation or table a scan prints after it), split into CamelCase words, contains <code>Write</code>, <code>Insert</code>, <code>Save</code>, <code>Overwrite</code>, <code>Append</code>, <code>Merge</code>, <code>Update</code>, <code>Delete</code>, <code>Truncate</code>, <code>Replace</code>, <code>Drop</code>, <code>Load</code>, <code>Vacuum</code>, <code>Convert</code>, <code>Clone</code>, <code>Restore</code>, <code>Optimize</code>, <code>Alter</code>, <code>Reorg</code>, <code>Rename</code> or <code>Call</code>, or contains <code>TableAsSelect</code>, <code>AddPartition</code>, <code>DropPartition</code>, <code>RenamePartition</code> or <code>RecoverPartitions</code>. That covers table DDL and <code>ADD PARTITION ... LOCATION</code>, and an Iceberg procedure call (<code>Call</code>), whose target is a procedure argument and not a path, so it is reported with a <code>null</code> target. A name containing <code>Join</code> (<code>SortMergeJoin</code>) and these operators that share a word with a write but write nothing are not: <code>WriteFiles</code> (the child of a write command), <code>AppendColumns</code>, <code>AppendColumnsWithObject</code>, <code>MergeRows</code>, <code>StateStoreSave</code>, <code>StateStoreRestore</code>, <code>SessionWindowStateStoreSave</code>, <code>SessionWindowStateStoreRestore</code> and <code>UpdateEventTimeWatermarkColumn</code>. The classification leans toward reporting too much: a node that matches by name is listed with a <code>null</code> target rather than dropped.</p><h3 id="delta-writes" tabindex="-1">Delta writes <a class="header-anchor" href="#delta-writes" aria-label="Permalink to "Delta writes {#delta-writes}""></a></h3><p>On a real log a Delta command node (<code>MergeIntoCommand</code>, <code>UpdateCommand</code>, <code>DeleteCommand</code>, <code>WriteIntoDelta</code>, <code>SaveIntoDataSourceCommand</code>) is a bare name: its plan string has no target. The target is read from up to two other places, in this order, and is <code>null</code> when neither names exactly one target.</p><ol><li>The command's <code>Arguments:</code> line in Spark's physical plan description. The parser drops the rest of that text to save memory, but keeps this one line for these commands. A quoted table name that appears once on the line is the target, as <code>kind: "table"</code> (<code>spark_catalog</code> is dropped, so it reads <code>database.table</code>). A <code>SaveIntoDataSourceCommand</code> is read this way only when the line shows a Delta source, and its target is the <code>path</code> option. A description that spans two read chunks is not kept for a <code>SaveIntoDataSourceCommand</code>, which prints its whole query plan under it; its target is then <code>null</code>.</li><li>For <code>MergeIntoCommand</code>, <code>UpdateCommand</code> and <code>DeleteCommand</code> only, the <code>_delta_log</code> path in the plans of the executions that share the command's root execution, as <code>kind: "path"</code>. Exactly one distinct path must appear. It applies only when the command is its own root execution, and a source that is itself a Delta table adds a second path and leaves the target <code>null</code>. The write commands (<code>WriteIntoDelta</code>, <code>WriteIntoDeltaCommand</code>, <code>SaveIntoDataSourceCommand</code>) never take this step, because a write may read another Delta table as its source: with no table or <code>path</code> option on the arguments line, their target is <code>null</code>.</li></ol><p>An append or overwrite of an existing Delta table (<code>saveAsTable</code> in <code>append</code> or <code>overwrite</code> mode on an existing table, <code>INSERT INTO</code>, <code>INSERT OVERWRITE</code>) prints the table object as its first argument, and that names the table: <code>kind: "table"</code> as <code>database.table</code> (<code>catalog.database.table</code> outside the session catalog), or <code>kind: "path"</code> for a path-based table. A <code>CREATE TABLE ... AS SELECT</code>, <code>CREATE OR REPLACE TABLE</code> or <code>saveAsTable</code> that creates or replaces a table runs two executions under one root: the create or replace node, which names the table as <code>unqualifiedTable</code> because Delta's catalog object does not state its catalog name, and an <code>AppendDataExecV1</code> whose staged table has no name. That append takes the table its root's create or replace node names, and is <code>null</code> when the root has no single such node.</p><p>A merge made with <code>DeltaTable.merge(...).execute()</code> normally runs a <code>MergeIntoCommand</code> too (its description is <code>toDataset$ at DeltaMergeBuilder</code>), and is reported like a SQL MERGE, including two merges run from threads of one session, whose sub-queries are told apart by their root execution. Some logs have no such command execution for an API merge. Its queries are then separate root executions, and the only things tying them together are a <code>MERGE operation</code> description and adjacent execution ids. Each run of consecutive ids with such a description is reported as one write with the synthetic command <code>DeltaMerge</code>, <code>kind: "path"</code> and the table path from the <code>_delta_log</code> of the plans in the run. The log holds no table name for these merges. The run must hold a write phase (a description containing <code>writing</code> or <code>rewriting</code>), because a run that only scanned may have read the merge's source. The target is <code>null</code> when the run has no write phase, names zero or several paths, has a plan or start time missing, or has start times that overlap another run's (merges on concurrent threads); <code>raw</code> says which. Two merges whose executions have consecutive ids are one run and name two paths, so they get no target. A description a user sets that starts with <code>MERGE operation</code> is indistinguishable from Delta's and is reported the same way. <code>raw</code> reads <code>Delta MERGE operation, executions 10-17</code>.</p><p>Only SQL writes are covered. Writes made outside Spark SQL, such as an RDD <code>saveAsTextFile</code> or a direct filesystem call from the driver, do not appear in the event log and are not in <code>writeTargets</code>.</p><h2 id="metrics-block" tabindex="-1">Metrics block <a class="header-anchor" href="#metrics-block" aria-label="Permalink to "Metrics block""></a></h2><p>The CLI's JSON output carries a <code>metrics</code> block next to the report, for scripts that act on a run without reading the report. With <code>--baseline</code> it is inside <code>candidate</code>. The MCP <code>diagnose_run</code> tool returns the same block. It has its own <code>schemaVersion</code>, separate from the report's. A figure the log cannot provide is <code>null</code>, never <code>0</code>: a log from a Spark version that records no CPU time has <code>executorCpuTimeMs: null</code>, and a log cut off before any executor joined has null allocation. The time, data and task figures, run-level and per row, include the work of every attempt of a resubmitted stage, failed attempts too, and the tasks of a failed attempt that end after it (killed or still running when it failed); skew describes the latest attempt.</p><table tabindex="0"><thead><tr><th>Field</th><th>Meaning</th></tr></thead><tbody><tr><td><code>runComplete</code></td><td><code>true</code> when the log has an application-end record. <code>false</code> means the log was cut off and every total covers only what it recorded.</td></tr><tr><td><code>time.wallClockMs</code></td><td>Application start to end; null without both.</td></tr><tr><td><code>time.executorCpuTimeMs</code></td><td>Summed CPU time of every task attempt, including failed attempts, retries and speculative copies that lost. Null when no task recorded any. Misses Python worker CPU, see <code>python</code>.</td></tr><tr><td><code>time.executorRunTimeMs</code>, <code>time.gcTimeMs</code></td><td>Summed run time and JVM GC time of every task attempt, counted like the CPU time.</td></tr><tr><td><code>data.memorySpillBytes</code>, <code>data.diskSpillBytes</code></td><td>Summed spill.</td></tr><tr><td><code>data.shuffleReadBytes</code>, <code>data.shuffleWriteBytes</code></td><td>Summed shuffle bytes, local plus remote on the read side.</td></tr><tr><td><code>data.inputBytes</code>, <code>data.outputBytes</code>, <code>data.outputRows</code></td><td>Summed input, output and rows written. <code>outputRows</code> is null when no task reported rows.</td></tr><tr><td><code>data.peakExecutionMemoryBytes</code></td><td>The largest per-task peak execution memory. Null when every task reports 0.</td></tr><tr><td><code>shape.taskCount</code>, <code>shape.stageCount</code></td><td>Distinct task records and stages.</td></tr><tr><td><code>shape.failedStageAttempts</code></td><td>Stage attempts that ended with a failure reason, including an attempt Spark then resubmitted (a fetch failure, for example).</td></tr><tr><td><code>shape.retriedStages</code></td><td>Stages submitted more than once.</td></tr><tr><td><code>shape.failedTasks</code>, <code>shape.retriedTasks</code></td><td>Task-level counts: tasks whose final attempt failed, and task attempts superseded by a retry.</td></tr><tr><td><code>shape.maxSkew</code></td><td>The largest stage skew ratio, the figure <code>--max-skew</code> checks (P95 over median, or max over median for a stage with few tasks; <code>skew.minTasksForP95</code> from <code>--thresholds</code> applies).</td></tr><tr><td><code>allocation.coreHours</code>, <code>allocation.memoryGbHours</code></td><td>See <a href="#allocation">Allocation</a>.</td></tr><tr><td><code>python.shareOfTaskRunTime</code></td><td>See <a href="#python-share">Python share</a>.</td></tr><tr><td><code>stages</code></td><td>The per-stage rows.</td></tr></tbody></table><p><code>stages</code> holds one row per stage fingerprint, keyed by the same fingerprint the run comparison matches stages on (the normalized stage name plus the stage's plan nodes), so the same stage has the same key in a baseline and a candidate run. A stage repeated in a loop shares one key: its row sums the repeats and lists them in <code>stageIds</code>. A row carries <code>durationMs</code>, <code>executorCpuTimeMs</code>, <code>executorRunTimeMs</code>, <code>gcTimeMs</code>, the spill, shuffle, input and output figures, <code>outputRows</code>, <code>peakExecutionMemoryBytes</code>, <code>taskCount</code>, <code>failedTasks</code>, <code>retriedTasks</code> and <code>skew</code> (the largest skew ratio among the repeats) as above, plus <code>failed</code> (an attempt of the stage failed), <code>retried</code> (the stage was submitted more than once) and <code>python</code> flags. The stage-attempt figures, run-level and per row, are null for a stage record that carries no attempt count. With <code>--redact</code> the <code>metrics</code> and <code>effectiveConf</code> blocks are built from the redacted run the report uses, so they carry the same <code>host-N</code> and <code>app-N</code> pseudonyms: the keys come from redacted stage names.</p><h3 id="allocation" tabindex="-1">Allocation <a class="header-anchor" href="#allocation" aria-label="Permalink to "Allocation""></a></h3><p><code>allocation.coreHours</code> is the sum over executors of cores times hours alive. <code>allocation.memoryGbHours</code> is the sum of memory times hours alive, in GiB (1024 MiB). An executor is alive from its executor-added event to its first later executor-removed event. One with no removal event closes at the application end when the log has one. In a cut-off log (<code>runComplete</code> false) it closes at the last timestamp the log records (the latest application, stage or executor event), so the figure is a lower bound.</p><p>Cores per executor are the executor-added event's total cores. Under dynamic allocation or YARN defaults, where <code>spark.executor.cores</code> is not set, that is the core count the cluster manager actually granted; when the event carries none, <code>spark.executor.cores</code> is used. If neither exists the core-hours are null.</p><p>Memory per executor is the container size Spark requests: <code>spark.executor.memory</code> (1g when unset), plus the overhead, plus <code>spark.memory.offHeap.size</code> when <code>spark.memory.offHeap.enabled</code> is <code>true</code>, plus <code>spark.executor.pyspark.memory</code>. The overhead is <code>spark.executor.memoryOverhead</code>, else the legacy <code>spark.yarn.executor.memoryOverhead</code>, else the larger of 384 MiB and <code>spark.executor.memoryOverheadFactor</code> (default 0.1) times the executor memory. Memory GB-hours are null when the log records no Spark properties at all, or a memory property cannot be read. Driver resources are not included.</p><h3 id="python-share" tabindex="-1">Python share <a class="header-anchor" href="#python-share" aria-label="Permalink to "Python share""></a></h3><p><code>python.shareOfTaskRunTime</code> is the summed task run time of Python stages divided by the summed task run time of all stages; null when no task run time was recorded. It is <code>0</code> for a run with task time and no Python stage. Executor CPU time counts only the JVM task thread, so on a run with a high share it misses the CPU of the Python worker processes; treat <code>executorCpuTimeMs</code> as unreliable there.</p><p>A stage is a Python stage when either signal holds:</p><ul><li>a plan node attributed to it is a Python operator (<code>PythonRDD</code>, <code>BatchEvalPython</code>, <code>ArrowEvalPython</code>, <code>PythonMapInArrow</code>, or a pandas/Arrow grouped or map operator such as <code>FlatMapGroupsInPandas</code>, including suffixed variants such as <code>BatchEvalPythonUDTF</code> and <code>FlatMapGroupsInPandasWithState</code> and the Spark 4.1 <code>ArrowAggregatePython</code> and <code>ArrowWindowPython</code>), which catches Python UDFs and UDTFs inside SQL;</li><li>its name or call site names <code>PythonRDD</code> or <code>org.apache.spark.api.python</code>, which catches RDD lambdas that have no plan and stages that cannot be matched to one.</li></ul><p>The "tasks mostly idle" check that keeps a low-CPU stage from being treated as waiting on an external system uses the same test.</p><h3 id="other-surfaces" tabindex="-1">Other surfaces <a class="header-anchor" href="#other-surfaces" aria-label="Permalink to "Other surfaces""></a></h3><p>Every figure the metrics block shares with another surface reads the same core code as that surface. The run comparison (the dashboard's comparison view, the CLI's <code>--baseline</code> and the MCP <code>compare_runs</code> tool) uses the same sums for run time, CPU time, GC time, spill, input, output and task count, so a comparison metric equals the matching <code>metrics</code> field for the same run, including the work of failed and speculative task attempts. Per-stage views in the dashboard (the stage table and stage detail) describe the stage's latest attempt and the task attempts that won, so a stage's own figures can be smaller than its row in <code>metrics.stages</code>. The dashboard's Efficiency card reports available capacity (peak concurrent cores times run time), which differs from <code>allocation.coreHours</code> (cores times the hours each executor was alive) under dynamic allocation. The utilization finding's <code>cpuUtilizationPct</code> is null, as <code>time.executorCpuTimeMs</code> is, when the log recorded no CPU time.</p><h2 id="effective-conf" tabindex="-1">Effective conf <a class="header-anchor" href="#effective-conf" aria-label="Permalink to "Effective conf""></a></h2><p>The JSON output also carries <code>effectiveConf</code> (with its own <code>schemaVersion</code>), the Spark properties the run started with, so a script can check that a <code>--conf</code> overlay took effect. It is null when the log records no Spark properties. With <code>--baseline</code> it is inside <code>candidate</code>. The MCP <code>diagnose_run</code> tool returns the same block.</p><ul><li><code>values</code>: property to value, for every property that is not withheld.</li><li><code>maskedKeys</code>: properties present in the log whose value is withheld.</li><li><code>absentKeys</code>: with <code>--conf-keys</code>, the requested properties the log does not contain.</li></ul><p>A value is withheld when its key or value matches Spark's default secret pattern (<code>(?i)secret|password|token|access[.]?key</code>), as Spark's own redaction does, when its key names another credential form (<code>passwd</code>, <code>pwd</code>, <code>pass</code>, <code>apiKey</code>, <code>accountKey</code> as in <code>fs.azure.account.key.*</code>, <code>privateKey</code>, <code>sas</code>, <code>sig</code>, <code>credential</code>), when the key or value matches the job's own <code>spark.redaction.regex</code> (when the log records one; if that pattern uses syntax JavaScript cannot evaluate, every value is withheld), or when the key or value matches <code>--conf-redact-regex <pattern></code>. A withheld property shows that it is present, not what it is set to, so the output cannot tell you whether a masked property has the value you expected. No hash or other derivative of a withheld value is emitted.</p><p>In every other value, credentials are replaced with <code>[redacted]</code>: in a value that looks like a URL, <code>user:password@host</code> userinfo and the Oracle thin <code>user/password@host</code> form; in any value, <code>name=value</code> parameters named <code>password</code>, <code>passwd</code>, <code>pwd</code>, <code>pass</code>, <code>apikey</code>, <code>accountkey</code>, <code>sas</code>, <code>sig</code>, <code>signature</code> and similar (JDBC and ODBC strings, query strings, JVM options), including signature parameters such as Azure SAS <code>sig=</code> and <code>X-Amz-Signature=</code>. <code>--conf-keys a,b</code> narrows <code>values</code> and <code>maskedKeys</code> to the named properties.</p><p>With <code>--redact</code>, the host names the report pseudonymizes become <code>host-N</code> in every value: the values of <code>*.host</code> and <code>*.hostname</code> properties, executor hosts, and IP or EC2-style addresses. <code>spark.app.name</code> becomes the application's <code>app-N</code> pseudonym. A host name that appears only in some other property, such as <code>spark.yarn.historyServer.address</code>, is left as is; withhold it with <code>--conf-redact-regex</code> or leave it out with <code>--conf-keys</code>.</p><h2 id="pairing-stages-across-runs" tabindex="-1">Pairing stages across runs <a class="header-anchor" href="#pairing-stages-across-runs" aria-label="Permalink to "Pairing stages across runs {#pairing-stages-across-runs}""></a></h2><p>With <code>--baseline</code>, the <code>comparison</code> object pairs the stages of the two runs (<code>stagePairs</code>, with each pair's <code>deltas</code>) and reports <code>runtimeCoverage</code>, the share of both runs' executor run time that sits in paired stages. <code>confidence</code> is <code>ok</code>, <code>low</code> or <code>insufficient</code>: <code>low</code> when the application names differ or <code>runtimeCoverage</code> is under 0.9, <code>insufficient</code> when neither run recorded any executor run time. <code>confidence</code> does not change an exit code. The fields and the matching rules are in <a href="./../mcp-tools/compare-runs.html"><code>compare_runs</code></a> and <a href="./../run-comparison/how-stages-are-matched.html">How stages are matched</a>.</p><p>When a stage writes to a path that differs per run, for example <code>{sandbox_root}/{session}/{variant}/{batch}</code> where the variant is <code>baseline</code> in one run and <code>c07b</code> in the other, the write stage cannot pair, and it is often the heaviest. Pass <code>--normalize-path <regex></code>, repeatable, to rewrite what the patterns match, in every plan node's text, before stages are paired:</p><div class="language-bash vp-adaptive-theme"><button title="Copy Code" class="copy"></button><span class="lang">bash</span><pre class="shiki shiki-themes github-light github-dark vp-code" tabindex="0"><code><span class="line"><span style="--shiki-light:#6F42C1;--shiki-dark:#B392F0;">sparkforensics-analyze</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;"> candidate</span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;"> --baseline</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;"> baseline</span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;"> \</span></span>
|
|
42
|
+
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">}</span></span></code></pre></div><ul><li><p><code>writes</code> holds one row per write node, ordered by SQL execution id and then by position in the plan. A <code>DeltaTable</code> API merge has no write node: it is one extra row per merge, see <a href="#delta-writes">Delta writes</a>. <code>command</code> is the plan node's name without the <code>Execute </code> prefix or an <code>Exec</code> suffix, <code>nodeId</code> is the plan node's id, and <code>raw</code> is the node's full plan string as the log recorded it.</p></li><li><p><code>kind</code> says how to read <code>target</code>:</p><ul><li><code>path</code> is a filesystem location.</li><li><code>table</code> is a table name whose catalog the command states or implies: a Hive or V1 command's <code>database.table</code>, a DataSource V2 name with a catalog part (<code>catalog.namespace.table</code>), or a Delta command's table as <code>database.table</code> (a table in the session catalog) or <code>catalog.database.table</code>.</li><li><code>unqualifiedTable</code> is a DataSource V2 name with no catalog part, such as <code>default.events</code> or <code>events</code>. The log does not say which catalog it lives in, so a check on its database part alone can match the wrong catalog.</li><li><code>jdbcTable</code> is a <code>dbtable</code> of a JDBC write. It names a table in an external database, not in a Spark catalog, and the database itself (the JDBC url) is not reported.</li></ul><p>Every target is copied verbatim from the plan string: nothing is resolved, so a relative path, an unexpanded <code>${var}</code> placeholder or a bare table name appears exactly as the log states it. Backticks around table name parts are dropped.</p></li><li><p><code>target</code> and <code>kind</code> are <code>null</code> when the target cannot be determined. That covers a node whose plan string has no target (Spark omits it for some commands, and Delta command nodes carry none on real logs, which <a href="#delta-writes">Delta writes</a> covers), a redacted option value, a plan string that names more than one candidate target, and a plan string Spark cut short. A target is reported only when its whole text is followed by a delimiter in the plan string: a path cut by <code>spark.sql.maxMetadataStringLength</code> or a name with a <code>...</code> marker in it is <code>null</code>, never a partial path. A trailing <code>... N more fields</code> after the target, such as the column list of <code>InsertIntoHadoopFsRelationCommand</code>, does not affect the target before it. Treat a <code>null</code> target as unknown, not as inside or outside any location.</p></li><li><p><code>outputRows</code> is the node's own <code>number of output rows</code> SQL metric. It is <code>null</code> when the log has no such metric for that node, which is the case for the DataSource V2 and Delta write nodes that report other metrics.</p></li><li><p><code>mergeRows</code> holds the row counts of a Delta MERGE: <code>inserted</code>, <code>updated</code>, <code>deleted</code> and <code>copied</code>, read from the <code>MergeIntoCommand</code> node's SQL metrics (<code>number of inserted rows</code>, <code>number of updated rows</code>, <code>number of deleted rows</code> and <code>number of target rows rewritten unmodified</code>; older Delta releases name the last one <code>number of rows copied</code>). It is <code>null</code> for every other command, for a MERGE node that reports none of the four, and for a <code>DeltaMerge</code> row (see <a href="#delta-writes">Delta writes</a>). To check that two runs merged the same rows, compare <code>inserted + updated + deleted</code>. <code>copied</code> counts target rows Delta rewrote unchanged, which depends on how the table's files are laid out.</p></li><li><p><code>recognized</code> is <code>true</code> for the commands below and <code>false</code> for a write-like node that is not in that list. An unrecognized write always has <code>target</code> and <code>kind</code> <code>null</code>, and <code>raw</code> is the only information about it.</p></li><li><p><code>executionsWithoutPlan</code> lists the SQL executions whose writes the report cannot see, each with a <code>reason</code>. <code>noPlan</code> means the execution started but the log has no plan for it, such as an execution still running when the log was cut off (a plan is read when its execution ends). <code>unreadableStart</code> means the execution's start event was skipped because it could not be read, for example a plan nested deeper than 500 nodes or a start line cut off at the end of the log. A write in one of these executions is not in <code>writes</code>, so a non-empty list means the report may be incomplete.</p></li><li><p><code>skippedLines</code> is the number of log lines the parser could not read. A line cut off before its execution id is not in <code>executionsWithoutPlan</code>, so a non-zero count means a write may be missing even when that list is empty. It is <code>null</code> when the count is unknown.</p></li></ul><p>Recognized commands and where their target comes from:</p><table tabindex="0"><thead><tr><th>Command</th><th>Target</th></tr></thead><tbody><tr><td><code>InsertIntoHadoopFsRelationCommand</code></td><td><code>path</code>: the first argument, including for an <code>INSERT OVERWRITE ... PARTITION</code> that prints a static-partition map after it</td></tr><tr><td><code>InsertIntoHiveTable</code>, <code>CreateDataSourceTableAsSelectCommand</code>, <code>CreateHiveTableAsSelectCommand</code>, <code>OptimizedCreateHiveTableAsSelectCommand</code></td><td><code>table</code>: the first argument</td></tr><tr><td><code>SaveIntoDataSourceCommand</code></td><td><code>path</code> from the <code>path</code> option, or <code>jdbcTable</code> from the JDBC <code>dbtable</code>/<code>table</code> option</td></tr><tr><td><code>AppendData</code>, <code>OverwriteByExpression</code>, <code>OverwritePartitionsDynamic</code>, <code>ReplaceData</code>, <code>WriteDelta</code>, <code>WriteToDataSourceV2</code>, <code>AppendDataExecV1</code>, <code>OverwriteByExpressionExecV1</code></td><td><code>table</code> or <code>unqualifiedTable</code>: the <code>table=</code> of the connector's write object, for example Iceberg's <code>IcebergWrite(table=..., ...)</code>. For a Delta table, see <a href="#delta-writes">Delta writes</a></td></tr><tr><td><code>CreateTableAsSelect</code>, <code>AtomicCreateTableAsSelect</code>, <code>ReplaceTableAsSelect</code>, <code>AtomicReplaceTableAsSelect</code></td><td><code>table</code> or <code>unqualifiedTable</code>: the identifier after the catalog object, which does not name the catalog</td></tr><tr><td><code>WriteIntoDelta</code>, <code>WriteIntoDeltaCommand</code>, <code>UpdateCommand</code>, <code>DeleteCommand</code>, <code>MergeIntoCommand</code></td><td><code>path</code>: the first argument when it is a <code>delta.</code> path table (never for <code>MergeIntoCommand</code>, whose plan string also prints the source); otherwise as in <a href="#delta-writes">Delta writes</a></td></tr><tr><td><code>CreateDeltaTableCommand</code>, <code>OptimizeTableCommand</code>, <code>RestoreTableCommand</code>, <code>DeltaReorgTableCommand</code></td><td><code>path</code>: the first argument when it is a <code>delta.</code> path table, otherwise <code>null</code></td></tr><tr><td><code>DeltaMerge</code></td><td>not a plan node: one row per <code>DeltaTable</code> API merge, see <a href="#delta-writes">Delta writes</a></td></tr></tbody></table><p>A plan node not in the table is a write when its operator name (the first word of the node name after any leading <code>Execute</code>, so not the relation or table a scan prints after it), split into CamelCase words, contains <code>Write</code>, <code>Insert</code>, <code>Save</code>, <code>Overwrite</code>, <code>Append</code>, <code>Merge</code>, <code>Update</code>, <code>Delete</code>, <code>Truncate</code>, <code>Replace</code>, <code>Drop</code>, <code>Load</code>, <code>Vacuum</code>, <code>Convert</code>, <code>Clone</code>, <code>Restore</code>, <code>Optimize</code>, <code>Alter</code>, <code>Reorg</code>, <code>Rename</code> or <code>Call</code>, or contains <code>TableAsSelect</code>, <code>AddPartition</code>, <code>DropPartition</code>, <code>RenamePartition</code> or <code>RecoverPartitions</code>. That covers table DDL and <code>ADD PARTITION ... LOCATION</code>, and an Iceberg procedure call (<code>Call</code>), whose target is a procedure argument and not a path, so it is reported with a <code>null</code> target. A name containing <code>Join</code> (<code>SortMergeJoin</code>) and these operators that share a word with a write but write nothing are not: <code>WriteFiles</code> (the child of a write command), <code>AppendColumns</code>, <code>AppendColumnsWithObject</code>, <code>MergeRows</code>, <code>StateStoreSave</code>, <code>StateStoreRestore</code>, <code>SessionWindowStateStoreSave</code>, <code>SessionWindowStateStoreRestore</code> and <code>UpdateEventTimeWatermarkColumn</code>. The classification leans toward reporting too much: a node that matches by name is listed with a <code>null</code> target rather than dropped.</p><h3 id="delta-writes" tabindex="-1">Delta writes <a class="header-anchor" href="#delta-writes" aria-label="Permalink to "Delta writes {#delta-writes}""></a></h3><p>On a real log a Delta command node (<code>MergeIntoCommand</code>, <code>UpdateCommand</code>, <code>DeleteCommand</code>, <code>WriteIntoDelta</code>, <code>SaveIntoDataSourceCommand</code>) is a bare name: its plan string has no target. The target is read from up to two other places, in this order, and is <code>null</code> when neither names exactly one target.</p><ol><li>The command's <code>Arguments:</code> line in Spark's physical plan description. The parser drops the rest of that text to save memory, but keeps this one line for these commands. A quoted table name that appears once on the line is the target, as <code>kind: "table"</code> (<code>spark_catalog</code> is dropped, so it reads <code>database.table</code>). A <code>SaveIntoDataSourceCommand</code> is read this way only when the line shows a Delta source, and its target is the <code>path</code> option. A description that spans two read chunks is not kept for a <code>SaveIntoDataSourceCommand</code>, which prints its whole query plan under it; its target is then <code>null</code>.</li><li>For <code>MergeIntoCommand</code>, <code>UpdateCommand</code> and <code>DeleteCommand</code> only, the <code>_delta_log</code> path in the plans of the executions that share the command's root execution, as <code>kind: "path"</code>. Exactly one distinct path must appear. It applies only when the command is its own root execution, and a source that is itself a Delta table adds a second path and leaves the target <code>null</code>. The write commands (<code>WriteIntoDelta</code>, <code>WriteIntoDeltaCommand</code>, <code>SaveIntoDataSourceCommand</code>) never take this step, because a write may read another Delta table as its source: with no table or <code>path</code> option on the arguments line, their target is <code>null</code>.</li></ol><p>An append or overwrite of an existing Delta table (<code>saveAsTable</code> in <code>append</code> or <code>overwrite</code> mode on an existing table, <code>INSERT INTO</code>, <code>INSERT OVERWRITE</code>) prints the table object as its first argument, and that names the table: <code>kind: "table"</code> as <code>database.table</code> (<code>catalog.database.table</code> outside the session catalog), or <code>kind: "path"</code> for a path-based table. A <code>CREATE TABLE ... AS SELECT</code>, <code>CREATE OR REPLACE TABLE</code> or <code>saveAsTable</code> that creates or replaces a table runs two executions under one root: the create or replace node, which names the table as <code>unqualifiedTable</code> because Delta's catalog object does not state its catalog name, and an <code>AppendDataExecV1</code> whose staged table has no name. That append takes the table its root's create or replace node names, and is <code>null</code> when the root has no single such node.</p><p>A merge made with <code>DeltaTable.merge(...).execute()</code> normally runs a <code>MergeIntoCommand</code> too (its description is <code>toDataset$ at DeltaMergeBuilder</code>), and is reported like a SQL MERGE, including two merges run from threads of one session, whose sub-queries are told apart by their root execution. Some logs have no such command execution for an API merge. Its queries are then separate root executions, and the only things tying them together are a <code>MERGE operation</code> description and adjacent execution ids. Each run of consecutive ids with such a description is reported as one write with the synthetic command <code>DeltaMerge</code>, <code>kind: "path"</code> and the table path from the <code>_delta_log</code> of the plans in the run. The log holds no table name for these merges. The run must hold a write phase (a description containing <code>writing</code> or <code>rewriting</code>), because a run that only scanned may have read the merge's source. The target is <code>null</code> when the run has no write phase, names zero or several paths, has a plan or start time missing, or has start times that overlap another run's (merges on concurrent threads); <code>raw</code> says which. Two merges whose executions have consecutive ids are one run and name two paths, so they get no target. A description a user sets that starts with <code>MERGE operation</code> is indistinguishable from Delta's and is reported the same way. <code>raw</code> reads <code>Delta MERGE operation, executions 10-17</code>.</p><p>Only SQL writes are covered. Writes made outside Spark SQL, such as an RDD <code>saveAsTextFile</code> or a direct filesystem call from the driver, do not appear in the event log and are not in <code>writeTargets</code>.</p><h2 id="generator" tabindex="-1">Generator <a class="header-anchor" href="#generator" aria-label="Permalink to "Generator""></a></h2><p>The CLI's JSON output carries a <code>generator</code> block naming the build that wrote it: <code>name</code> and <code>version</code> of the CLI package, and <code>buildId</code>, the build id of the analysis core the CLI loaded. Equal build ids mean equal analysis code. With <code>--baseline</code> the block is inside <code>candidate</code>. The MCP <code>diagnose_run</code> tool does not return it. The block holds no run identifiers, so <code>--redact</code> leaves it as is.</p><div class="language-json vp-adaptive-theme"><button title="Copy Code" class="copy"></button><span class="lang">json</span><pre class="shiki shiki-themes github-light github-dark vp-code" tabindex="0"><code><span class="line"><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">"generator"</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: { </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">"name"</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">"sparkforensics-cli"</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">, </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">"version"</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">"0.7.0"</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">, </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">"buildId"</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">"9c1f3a7e2b4d"</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> }</span></span></code></pre></div><h2 id="metrics-block" tabindex="-1">Metrics block <a class="header-anchor" href="#metrics-block" aria-label="Permalink to "Metrics block""></a></h2><p>The CLI's JSON output carries a <code>metrics</code> block next to the report, for scripts that act on a run without reading the report. With <code>--baseline</code> it is inside <code>candidate</code>. The MCP <code>diagnose_run</code> tool returns the same block. It has its own <code>schemaVersion</code>, separate from the report's. A figure the log cannot provide is <code>null</code>, never <code>0</code>: a log from a Spark version that records no CPU time has <code>executorCpuTimeMs: null</code>, and a log cut off before any executor joined has null allocation. The time, data and task figures, run-level and per row, include the work of every attempt of a resubmitted stage, failed attempts too, and the tasks of a failed attempt that end after it (killed or still running when it failed); skew describes the latest attempt.</p><table tabindex="0"><thead><tr><th>Field</th><th>Meaning</th></tr></thead><tbody><tr><td><code>runComplete</code></td><td><code>true</code> when the log has an application-end record. <code>false</code> means the log was cut off and every total covers only what it recorded.</td></tr><tr><td><code>time.wallClockMs</code></td><td>Application start to end; null without both.</td></tr><tr><td><code>time.executorCpuTimeMs</code></td><td>Summed CPU time of every task attempt, including failed attempts, retries and speculative copies that lost. Null when no task recorded any. Misses Python worker CPU, see <code>python</code>.</td></tr><tr><td><code>time.executorRunTimeMs</code>, <code>time.gcTimeMs</code></td><td>Summed run time and JVM GC time of every task attempt, counted like the CPU time.</td></tr><tr><td><code>data.memorySpillBytes</code>, <code>data.diskSpillBytes</code></td><td>Summed spill.</td></tr><tr><td><code>data.shuffleReadBytes</code>, <code>data.shuffleWriteBytes</code></td><td>Summed shuffle bytes, local plus remote on the read side.</td></tr><tr><td><code>data.inputBytes</code>, <code>data.outputBytes</code>, <code>data.outputRows</code></td><td>Summed input, output and rows written. <code>outputRows</code> is null when no task reported rows.</td></tr><tr><td><code>data.peakExecutionMemoryBytes</code></td><td>The largest per-task peak execution memory. Null when every task reports 0.</td></tr><tr><td><code>shape.taskCount</code>, <code>shape.stageCount</code></td><td>Distinct task records and stages.</td></tr><tr><td><code>shape.failedStageAttempts</code></td><td>Stage attempts that ended with a failure reason, including an attempt Spark then resubmitted (a fetch failure, for example).</td></tr><tr><td><code>shape.retriedStages</code></td><td>Stages submitted more than once.</td></tr><tr><td><code>shape.failedTasks</code>, <code>shape.retriedTasks</code></td><td>Task-level counts: tasks whose final attempt failed, and task attempts superseded by a retry.</td></tr><tr><td><code>shape.maxSkew</code></td><td>The largest stage skew ratio, the figure <code>--max-skew</code> checks (P95 over median, or max over median for a stage with few tasks; <code>skew.minTasksForP95</code> from <code>--thresholds</code> applies).</td></tr><tr><td><code>allocation.coreHours</code>, <code>allocation.memoryGbHours</code></td><td>See <a href="#allocation">Allocation</a>.</td></tr><tr><td><code>allocation.dynamicAllocation</code>, <code>allocation.executorsPeak</code>, <code>allocation.executorsMean</code>, <code>allocation.executorCores</code>, <code>allocation.executorSeconds</code></td><td>The executor allocation behind the hours, see <a href="#allocation">Allocation</a>.</td></tr><tr><td><code>python.shareOfTaskRunTime</code></td><td>See <a href="#python-share">Python share</a>.</td></tr><tr><td><code>stages</code></td><td>The per-stage rows.</td></tr></tbody></table><p><code>stages</code> holds one row per stage fingerprint, keyed by the same fingerprint the run comparison matches stages on (the normalized stage name plus the stage's plan nodes), so the same stage has the same key in a baseline and a candidate run. A stage repeated in a loop shares one key: its row sums the repeats and lists them in <code>stageIds</code>. A row carries <code>durationMs</code>, <code>executorCpuTimeMs</code>, <code>executorRunTimeMs</code>, <code>gcTimeMs</code>, the spill, shuffle, input and output figures, <code>outputRows</code>, <code>peakExecutionMemoryBytes</code>, <code>taskCount</code>, <code>failedTasks</code>, <code>retriedTasks</code> and <code>skew</code> (the largest skew ratio among the repeats) as above, plus <code>failed</code> (an attempt of the stage failed), <code>retried</code> (the stage was submitted more than once) and <code>python</code> flags. The stage-attempt figures, run-level and per row, are null for a stage record that carries no attempt count. With <code>--redact</code> the <code>metrics</code> and <code>effectiveConf</code> blocks are built from the redacted run the report uses, so they carry the same <code>host-N</code> and <code>app-N</code> pseudonyms: the keys come from redacted stage names.</p><h3 id="allocation" tabindex="-1">Allocation <a class="header-anchor" href="#allocation" aria-label="Permalink to "Allocation""></a></h3><p><code>allocation.coreHours</code> is the sum over executors of cores times hours alive. <code>allocation.memoryGbHours</code> is the sum of memory times hours alive, in GiB (1024 MiB). An executor is alive from its executor-added event to its first later executor-removed event. One with no removal event closes at the application end when the log has one. In a cut-off log (<code>runComplete</code> false) it closes at the last timestamp the log records (the latest application, stage or executor event), so the figure is a lower bound.</p><p>Cores per executor are the executor-added event's total cores. Under dynamic allocation or YARN defaults, where <code>spark.executor.cores</code> is not set, that is the core count the cluster manager actually granted; when the event carries none, <code>spark.executor.cores</code> is used. If neither exists the core-hours are null.</p><p>Memory per executor is the container size Spark requests: <code>spark.executor.memory</code> (1g when unset), plus the overhead, plus <code>spark.memory.offHeap.size</code> when <code>spark.memory.offHeap.enabled</code> is <code>true</code>, plus <code>spark.executor.pyspark.memory</code>. The overhead is <code>spark.executor.memoryOverhead</code>, else the legacy <code>spark.yarn.executor.memoryOverhead</code>, else the larger of 384 MiB and <code>spark.executor.memoryOverheadFactor</code> (default 0.1) times the executor memory. Memory GB-hours are null when the log records no Spark properties at all, or a memory property cannot be read. Driver resources are not included.</p><p>The same alive intervals give the executor figures, each null when the log has no executor-added event:</p><ul><li><code>allocation.executorSeconds</code> is the sum of seconds alive over executors.</li><li><code>allocation.executorsPeak</code> is the largest number of executors alive at once.</li><li><code>allocation.executorsMean</code> is <code>executorSeconds</code> divided by the seconds from application start to close (the end, or the last recorded timestamp in a cut-off log), so the mean times the run's wall clock is <code>executorSeconds</code>. It is null when the log has no application start.</li><li><code>allocation.executorCores</code> is the cores per executor when every executor has the same count, null when a count is unknown or they differ.</li></ul><p><code>allocation.dynamicAllocation</code> is <code>on</code> or <code>off</code> when the log records <code>spark.dynamicAllocation.enabled</code>, and <code>null</code> when it does not. Spark's default is off, but a key the log never recorded is not reported as off. It is read whether or not the log has executor events. The <code>coldStart</code> and <code>autoscalingChurn</code> findings' <code>evidence.dynamicAllocation</code> reports <code>on</code> for any run not logged as off.</p><h3 id="python-share" tabindex="-1">Python share <a class="header-anchor" href="#python-share" aria-label="Permalink to "Python share""></a></h3><p><code>python.shareOfTaskRunTime</code> is the summed task run time of Python stages divided by the summed task run time of all stages; null when no task run time was recorded. It is <code>0</code> for a run with task time and no Python stage. Executor CPU time counts only the JVM task thread, so on a run with a high share it misses the CPU of the Python worker processes; treat <code>executorCpuTimeMs</code> as unreliable there.</p><p>A stage is a Python stage when either signal holds:</p><ul><li>a plan node attributed to it is a Python operator (<code>PythonRDD</code>, <code>BatchEvalPython</code>, <code>ArrowEvalPython</code>, <code>PythonMapInArrow</code>, or a pandas/Arrow grouped or map operator such as <code>FlatMapGroupsInPandas</code>, including suffixed variants such as <code>BatchEvalPythonUDTF</code> and <code>FlatMapGroupsInPandasWithState</code> and the Spark 4.1 <code>ArrowAggregatePython</code> and <code>ArrowWindowPython</code>), which catches Python UDFs and UDTFs inside SQL;</li><li>its name or call site names <code>PythonRDD</code> or <code>org.apache.spark.api.python</code>, which catches RDD lambdas that have no plan and stages that cannot be matched to one.</li></ul><p>The "tasks mostly idle" check that keeps a low-CPU stage from being treated as waiting on an external system uses the same test.</p><h3 id="other-surfaces" tabindex="-1">Other surfaces <a class="header-anchor" href="#other-surfaces" aria-label="Permalink to "Other surfaces""></a></h3><p>Every figure the metrics block shares with another surface reads the same core code as that surface. The run comparison (the dashboard's comparison view, the CLI's <code>--baseline</code> and the MCP <code>compare_runs</code> tool) uses the same sums for run time, CPU time, GC time, spill, input, output and task count, so a comparison metric equals the matching <code>metrics</code> field for the same run, including the work of failed and speculative task attempts. Per-stage views in the dashboard (the stage table and stage detail) describe the stage's latest attempt and the task attempts that won, so a stage's own figures can be smaller than its row in <code>metrics.stages</code>. The dashboard's Unused core time, the <code>utilization</code> finding's percentage and its idle figure all measure against available capacity, which is <code>allocation.coreHours</code> (cores times the hours each executor was alive), so under dynamic allocation a run is never idle for cores it did not hold. The utilization finding's <code>cpuUtilizationPct</code> is a share of that capacity, and is null, as <code>time.executorCpuTimeMs</code> is, when the log recorded no CPU time.</p><h2 id="effective-conf" tabindex="-1">Effective conf <a class="header-anchor" href="#effective-conf" aria-label="Permalink to "Effective conf""></a></h2><p>The JSON output also carries <code>effectiveConf</code> (with its own <code>schemaVersion</code>), the Spark properties the run started with, so a script can check that a <code>--conf</code> overlay took effect. It is null when the log records no Spark properties. With <code>--baseline</code> it is inside <code>candidate</code>. The MCP <code>diagnose_run</code> tool returns the same block.</p><ul><li><code>values</code>: property to value, for every property that is not withheld.</li><li><code>maskedKeys</code>: properties present in the log whose value is withheld.</li><li><code>absentKeys</code>: with <code>--conf-keys</code>, the requested properties the log does not contain.</li></ul><p>A value is withheld when its key or value matches Spark's default secret pattern (<code>(?i)secret|password|token|access[.]?key</code>), as Spark's own redaction does, when its key names another credential form (<code>passwd</code>, <code>pwd</code>, <code>pass</code>, <code>apiKey</code>, <code>accountKey</code> as in <code>fs.azure.account.key.*</code>, <code>privateKey</code>, <code>sas</code>, <code>sig</code>, <code>credential</code>), when the key or value matches the job's own <code>spark.redaction.regex</code> (when the log records one; if that pattern uses syntax JavaScript cannot evaluate, every value is withheld), or when the key or value matches <code>--conf-redact-regex <pattern></code>. A withheld property shows that it is present, not what it is set to, so the output cannot tell you whether a masked property has the value you expected. No hash or other derivative of a withheld value is emitted.</p><p>In every other value, credentials are replaced with <code>[redacted]</code>: in a value that looks like a URL, <code>user:password@host</code> userinfo and the Oracle thin <code>user/password@host</code> form; in any value, <code>name=value</code> parameters named <code>password</code>, <code>passwd</code>, <code>pwd</code>, <code>pass</code>, <code>apikey</code>, <code>accountkey</code>, <code>sas</code>, <code>sig</code>, <code>signature</code> and similar (JDBC and ODBC strings, query strings, JVM options), including signature parameters such as Azure SAS <code>sig=</code> and <code>X-Amz-Signature=</code>. <code>--conf-keys a,b</code> narrows <code>values</code> and <code>maskedKeys</code> to the named properties.</p><p>With <code>--redact</code>, the host names the report pseudonymizes become <code>host-N</code> in every value: the values of <code>*.host</code> and <code>*.hostname</code> properties, executor hosts, and IP or EC2-style addresses. <code>spark.app.name</code> becomes the application's <code>app-N</code> pseudonym. A host name that appears only in some other property, such as <code>spark.yarn.historyServer.address</code>, is left as is; withhold it with <code>--conf-redact-regex</code> or leave it out with <code>--conf-keys</code>.</p><h2 id="pairing-stages-across-runs" tabindex="-1">Pairing stages across runs <a class="header-anchor" href="#pairing-stages-across-runs" aria-label="Permalink to "Pairing stages across runs {#pairing-stages-across-runs}""></a></h2><p>With <code>--baseline</code>, the <code>comparison</code> object pairs the stages of the two runs (<code>stagePairs</code>, with each pair's <code>deltas</code>) and reports <code>runtimeCoverage</code>, the share of both runs' executor run time that sits in paired or replanned stages. <code>confidence</code> is <code>ok</code>, <code>low</code> or <code>insufficient</code>: <code>low</code> when the application names differ or <code>runtimeCoverage</code> is under 0.9, <code>insufficient</code> when neither run recorded any executor run time. <code>confidence</code> does not change an exit code. The fields and the matching rules are in <a href="./../mcp-tools/compare-runs.html"><code>compare_runs</code></a> and <a href="./../run-comparison/how-stages-are-matched.html">How stages are matched</a>.</p><p>When a stage writes to a path that differs per run, for example <code>{sandbox_root}/{session}/{variant}/{batch}</code> where the variant is <code>baseline</code> in one run and <code>c07b</code> in the other, the write stage cannot pair, and it is often the heaviest. Pass <code>--normalize-path <regex></code>, repeatable, to rewrite what the patterns match, in every plan node's text, before stages are paired:</p><div class="language-bash vp-adaptive-theme"><button title="Copy Code" class="copy"></button><span class="lang">bash</span><pre class="shiki shiki-themes github-light github-dark vp-code" tabindex="0"><code><span class="line"><span style="--shiki-light:#6F42C1;--shiki-dark:#B392F0;">sparkforensics-analyze</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;"> candidate</span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;"> --baseline</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;"> baseline</span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;"> \</span></span>
|
|
46
43
|
<span class="line"><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;"> --normalize-path</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;"> '/sandbox/[^/]+/[^/]+/'</span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;"> --format</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;"> json</span></span></code></pre></div><p>Every match is replaced with a fixed token. Despite the name it is a generic regular expression, not only for paths. It needs <code>--baseline</code> and applies to every candidate of a several-candidates run. It changes which stages pair, and so <code>stagePairs</code>, <code>runtimeCoverage</code> and <code>confidence</code>; findings and the other metrics are untouched. At most 16 patterns of 200 characters each. An invalid pattern, or one that matches the empty string, exits <code>2</code> before any log is read.</p><h2 id="several-budgets-and-several-candidates" tabindex="-1">Several budgets and several candidates <a class="header-anchor" href="#several-budgets-and-several-candidates" aria-label="Permalink to "Several budgets and several candidates""></a></h2><h3 id="several-regression-budgets" tabindex="-1">Several regression budgets <a class="header-anchor" href="#several-regression-budgets" aria-label="Permalink to "Several regression budgets""></a></h3><p><code>--max-regression-pct</code> checks one metric. To gate on several in one call, repeat <code>--regression-budget <metric>:<pct></code>, or list them in a file passed with <code>--budgets <file></code>. Both need <code>--baseline</code>, and each budget takes a <a href="./regression-metric-keys.html#regression-metric-keys">metric key</a> and a percentage of zero or more:</p><div class="language-bash vp-adaptive-theme"><button title="Copy Code" class="copy"></button><span class="lang">bash</span><pre class="shiki shiki-themes github-light github-dark vp-code" tabindex="0"><code><span class="line"><span style="--shiki-light:#6F42C1;--shiki-dark:#B392F0;">sparkforensics-analyze</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;"> candidate</span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;"> --baseline</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;"> baseline</span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;"> \</span></span>
|
|
47
|
-
<span class="line"><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;"> --regression-budget</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;"> wallClock:10</span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;"> --regression-budget</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;"> gcTime:25</span></span></code></pre></div><p>The <code>--budgets</code> file is JSON with one key, <code>regression</code>, mapping a metric key to its percentage:</p><div class="language-json vp-adaptive-theme"><button title="Copy Code" class="copy"></button><span class="lang">json</span><pre class="shiki shiki-themes github-light github-dark vp-code" tabindex="0"><code><span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">{ </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">"regression"</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: { </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">"wallClock"</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">10</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">, </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">"gcTime"</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">25</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">, </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">"failedTaskRate"</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">0</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> } }</span></span></code></pre></div><p>The CLI refuses to run, with exit code 2 and a message naming the problem, for an unknown top-level key, an unknown metric key, a percentage that is not a non-negative number (in the file a JSON number, not a string; on the flag plain digits such as <code>10</code> or <code>2.5</code>), or a file that can't be read or isn't valid JSON.</p><p>The budgets combine like this:</p><ul><li><code>--max-regression-pct</code> with <code>--regression-metric</code> (default <code>wallClock</code>) still works and counts as one more budget next to the new ones.</li><li>Each metric can be budgeted once across the legacy pair, the repeated flag and the file. A metric named twice is a usage error (exit 2), even when both give the same percentage.</li><li>Each budget is checked on its own and gives one <code>max-regression</code> result that carries <code>metric</code>, the key it checks. Any violated budget makes the run exit <code>1</code>; otherwise an inconclusive one makes it exit <code>3</code>. A budget on a metric the baseline or the candidate log can't provide is inconclusive, never a pass.</li></ul><h3 id="
|
|
48
|
-
<script>window.__VP_HASH_MAP__=JSON.parse("{\"contributor-guide_architecture_board-widgets.md\":\"YQcj5EI4\",\"contributor-guide_architecture_board-widgets_caching-and-memory.md\":\"8bH1HnZp\",\"contributor-guide_architecture_board-widgets_plan-advisor.md\":\"RlzvUmNm\",\"contributor-guide_architecture_board-widgets_visual-system-and-templating.md\":\"DYgUpIJB\",\"contributor-guide_architecture_detector-contract.md\":\"wj6Et6UD\",\"contributor-guide_architecture_detector-contract_plan-attribution.md\":\"yNex4bys\",\"contributor-guide_architecture_detector-contract_threshold-tables.md\":\"fkPBXsU2\",\"contributor-guide_architecture_drill-down.md\":\"CqZPrdo9\",\"contributor-guide_architecture_drill-down_plan-graph.md\":\"DwOozIEs\",\"contributor-guide_architecture_impact-estimation.md\":\"CZv_ZGOp\",\"contributor-guide_architecture_impact-estimation_caveats-tuning-and-coverage.md\":\"BUucRc0A\",\"contributor-guide_architecture_impact-estimation_stage-union-rollup.md\":\"DdCGtAGu\",\"contributor-guide_architecture_index.md\":\"tymxf1Fh\",\"contributor-guide_architecture_overview.md\":\"C1sSvm9i\",\"contributor-guide_architecture_state-and-history.md\":\"DyCBdjuM\",\"contributor-guide_architecture_state-and-history_history-server-intake.md\":\"C298hrHZ\",\"contributor-guide_architecture_state-and-history_run-comparison-internals.md\":\"uuAKpY0Y\",\"contributor-guide_architecture_widget-rendering.md\":\"BOZ1azXG\",\"contributor-guide_architecture_widget-rendering_findings-tab.md\":\"BQXycK6G\",\"contributor-guide_architecture_widget-rendering_investigation-routing.md\":\"BGdiyElu\",\"contributor-guide_architecture_widget-rendering_list-sort-mode.md\":\"BuHKgH0C\",\"contributor-guide_architecture_widget-rendering_reference-section.md\":\"DWqC80bN\",\"contributor-guide_architecture_widget-rendering_row-expand-contract.md\":\"ZT89u9f1\",\"contributor-guide_architecture_worker-protocol.md\":\"BAnhi2-d\",\"contributor-guide_architecture_worker-protocol_cli-and-mcp.md\":\"Dk08VS7n\",\"contributor-guide_architecture_worker-protocol_core-and-event-validation.md\":\"DSVFPpWb\",\"contributor-guide_architecture_worker-protocol_evidence-availability.md\":\"CjimIDBY\",\"contributor-guide_architecture_worker-protocol_evidence-report.md\":\"DVGZOWvW\",\"contributor-guide_contributing.md\":\"CQMvGwFt\",\"contributor-guide_development-setup.md\":\"D9bu4j_c\",\"contributor-guide_testing.md\":\"By6XGR9a\",\"index.md\":\"CHJVslga\",\"tuning-reference_anti-patterns.md\":\"D08Uaod7\",\"tuning-reference_aqe.md\":\"C1Ae6A8u\",\"tuning-reference_bottleneck-broadcast-sizing.md\":\"6wjKuJNE\",\"tuning-reference_bottleneck-cold-start.md\":\"BVQbsuHP\",\"tuning-reference_bottleneck-duplicate-plan-subtree.md\":\"DtaYnaiF\",\"tuning-reference_bottleneck-failures.md\":\"Z1Tdmdd3\",\"tuning-reference_bottleneck-gc.md\":\"BCnXLf1n\",\"tuning-reference_bottleneck-job-failure-rate.md\":\"CcvQj2g9\",\"tuning-reference_bottleneck-memory-utilization.md\":\"B-C0-8h-\",\"tuning-reference_bottleneck-retry-waste.md\":\"DCnhWiqj\",\"tuning-reference_bottleneck-shuffle.md\":\"B5OMJCd3\",\"tuning-reference_bottleneck-skew.md\":\"Cvo6NQm_\",\"tuning-reference_bottleneck-slow-host.md\":\"ja5qr3wq\",\"tuning-reference_bottleneck-small-files.md\":\"Crjtb0i2\",\"tuning-reference_bottleneck-spill.md\":\"Bl8KtSRg\",\"tuning-reference_bottleneck-straggler.md\":\"B0VN8reT\",\"tuning-reference_bottleneck-tiny-tasks.md\":\"DQCftGhu\",\"tuning-reference_bottleneck-utilization.md\":\"BXDl30f9\",\"tuning-reference_caching.md\":\"CcaiMn_7\",\"tuning-reference_cluster-config.md\":\"DbWG1yZq\",\"tuning-reference_config.md\":\"YUqSpwFB\",\"tuning-reference_data-formats.md\":\"C5DX5xL4\",\"tuning-reference_index.md\":\"ZVIpQ6Dk\",\"tuning-reference_intro.md\":\"BSSaDlqx\",\"tuning-reference_joins.md\":\"BVhNCDnE\",\"tuning-reference_memory-model.md\":\"CfjFdgbl\",\"tuning-reference_metrics.md\":\"C64VNEL4\",\"tuning-reference_partitioning.md\":\"CtLK0xsS\",\"tuning-reference_pyspark.md\":\"D-92XgF8\",\"tuning-reference_shuffle.md\":\"Iq2v1oHJ\",\"tuning-reference_spark-architecture.md\":\"_qwnE_Sc\",\"tuning-reference_table-formats.md\":\"BSYEK-eN\",\"user-guide_alternative-log-retrieval.md\":\"CJpYvHGo\",\"user-guide_alternative-log-retrieval_managed-platforms.md\":\"DvDwHNtC\",\"user-guide_alternative-log-retrieval_ssh-bastion.md\":\"Gszzlplv\",\"user-guide_getting-started.md\":\"DYHHHkQR\",\"user-guide_getting-started_ci-and-automation.md\":\"DpnfKz3x\",\"user-guide_getting-started_reading-the-dashboard.md\":\"Obf3W3__\",\"user-guide_getting-started_regression-metric-keys.md\":\"B_gzr2Mw\",\"user-guide_getting-started_tuning-thresholds.md\":\"B_MyjyZm\",\"user-guide_mcp-tools.md\":\"C65SjWUL\",\"user-guide_mcp-tools_compare-runs.md\":\"CPowlb2q\",\"user-guide_mcp-tools_diagnose-run.md\":\"BP1vnHA5\",\"user-guide_mcp-tools_evaluate-budgets.md\":\"Dq5Azk8G\",\"user-guide_mcp-tools_get-finding-documentation.md\":\"BtTTHNV6\",\"user-guide_mcp-tools_get-finding-evidence.md\":\"rKyu4wts\",\"user-guide_mcp-tools_get-reference-doc.md\":\"Yac4tH3u\",\"user-guide_mcp-tools_get-run-summary.md\":\"DpxZ4ZNp\",\"user-guide_mcp-tools_list-runs.md\":\"DpQPeCM3\",\"user-guide_run-comparison.md\":\"B6aNtDYF\",\"user-guide_run-comparison_how-stages-are-matched.md\":\"XBzQ1oEU\",\"user-guide_understanding-findings.md\":\"Dqt2H_C1\"}");window.__VP_SITE_DATA__=JSON.parse("{\"lang\":\"en-US\",\"dir\":\"ltr\",\"title\":\"SparkForensics\",\"description\":\"Docs for using and contributing to SparkForensics\",\"base\":\"/docs/\",\"head\":[],\"router\":{\"prefetchLinks\":true},\"appearance\":true,\"themeConfig\":{\"logo\":\"/favicon.svg\",\"nav\":[{\"text\":\"User Guide\",\"link\":\"/user-guide/getting-started\"},{\"text\":\"Contributor Guide\",\"link\":\"/contributor-guide/development-setup\"},{\"text\":\"Tuning Reference\",\"link\":\"/tuning-reference/\"}],\"sidebar\":{\"/tuning-reference/\":[{\"text\":\"Getting Started\",\"items\":[{\"text\":\"Introduction\",\"link\":\"/tuning-reference/intro\"}]},{\"text\":\"Optimization Guide\",\"items\":[{\"text\":\"Spark Execution Model\",\"link\":\"/tuning-reference/spark-architecture\"},{\"text\":\"Memory Management\",\"link\":\"/tuning-reference/memory-model\"},{\"text\":\"Partitioning\",\"link\":\"/tuning-reference/partitioning\"},{\"text\":\"Join Optimization\",\"link\":\"/tuning-reference/joins\"},{\"text\":\"Shuffle\",\"link\":\"/tuning-reference/shuffle\"},{\"text\":\"Data Formats\",\"link\":\"/tuning-reference/data-formats\"},{\"text\":\"Table Formats\",\"link\":\"/tuning-reference/table-formats\"},{\"text\":\"Caching & Persistence\",\"link\":\"/tuning-reference/caching\"},{\"text\":\"PySpark Specifics\",\"link\":\"/tuning-reference/pyspark\"},{\"text\":\"Adaptive Query Execution\",\"link\":\"/tuning-reference/aqe\"},{\"text\":\"Cluster Tuning\",\"link\":\"/tuning-reference/cluster-config\"},{\"text\":\"Anti-Patterns\",\"link\":\"/tuning-reference/anti-patterns\"}]},{\"text\":\"Detector Catalog\",\"items\":[{\"text\":\"Task Skew\",\"link\":\"/tuning-reference/bottleneck-skew\"},{\"text\":\"Shuffle I/O\",\"link\":\"/tuning-reference/bottleneck-shuffle\"},{\"text\":\"Memory / Disk Spill\",\"link\":\"/tuning-reference/bottleneck-spill\"},{\"text\":\"GC Pressure\",\"link\":\"/tuning-reference/bottleneck-gc\"},{\"text\":\"Cold Start\",\"link\":\"/tuning-reference/bottleneck-cold-start\"},{\"text\":\"Executor Utilization\",\"link\":\"/tuning-reference/bottleneck-utilization\"},{\"text\":\"Slow Host\",\"link\":\"/tuning-reference/bottleneck-slow-host\"},{\"text\":\"Task Failures\",\"link\":\"/tuning-reference/bottleneck-failures\"},{\"text\":\"Stragglers\",\"link\":\"/tuning-reference/bottleneck-straggler\"},{\"text\":\"Retry Waste\",\"link\":\"/tuning-reference/bottleneck-retry-waste\"},{\"text\":\"Tiny Tasks\",\"link\":\"/tuning-reference/bottleneck-tiny-tasks\"},{\"text\":\"Job Failure Rate\",\"link\":\"/tuning-reference/bottleneck-job-failure-rate\"},{\"text\":\"Memory Utilization\",\"link\":\"/tuning-reference/bottleneck-memory-utilization\"},{\"text\":\"Duplicate Plan Subtree\",\"link\":\"/tuning-reference/bottleneck-duplicate-plan-subtree\"},{\"text\":\"Small Files\",\"link\":\"/tuning-reference/bottleneck-small-files\"},{\"text\":\"Broadcast Sizing\",\"link\":\"/tuning-reference/bottleneck-broadcast-sizing\"}]},{\"text\":\"Reference\",\"items\":[{\"text\":\"Metrics Glossary\",\"link\":\"/tuning-reference/metrics\"},{\"text\":\"Spark Config Quick-Reference\",\"link\":\"/tuning-reference/config\"}]}],\"/user-guide/\":[{\"text\":\"User Guide\",\"items\":[{\"text\":\"Getting started\",\"link\":\"/user-guide/getting-started\",\"collapsed\":true,\"items\":[{\"text\":\"Reading the dashboard\",\"link\":\"/user-guide/getting-started/reading-the-dashboard\"},{\"text\":\"CI and automation\",\"link\":\"/user-guide/getting-started/ci-and-automation\"},{\"text\":\"Tuning detector thresholds\",\"link\":\"/user-guide/getting-started/tuning-thresholds\"},{\"text\":\"Regression metric keys\",\"link\":\"/user-guide/getting-started/regression-metric-keys\"}]},{\"text\":\"Understanding findings\",\"link\":\"/user-guide/understanding-findings\"},{\"text\":\"Run comparison mode\",\"link\":\"/user-guide/run-comparison\",\"collapsed\":true,\"items\":[{\"text\":\"How stages are matched\",\"link\":\"/user-guide/run-comparison/how-stages-are-matched\"}]},{\"text\":\"MCP tools reference\",\"link\":\"/user-guide/mcp-tools\",\"collapsed\":true,\"items\":[{\"text\":\"diagnose_run\",\"link\":\"/user-guide/mcp-tools/diagnose-run\"},{\"text\":\"get_run_summary\",\"link\":\"/user-guide/mcp-tools/get-run-summary\"},{\"text\":\"evaluate_budgets\",\"link\":\"/user-guide/mcp-tools/evaluate-budgets\"},{\"text\":\"compare_runs\",\"link\":\"/user-guide/mcp-tools/compare-runs\"},{\"text\":\"get_finding_evidence\",\"link\":\"/user-guide/mcp-tools/get-finding-evidence\"},{\"text\":\"get_finding_documentation\",\"link\":\"/user-guide/mcp-tools/get-finding-documentation\"},{\"text\":\"get_reference_doc\",\"link\":\"/user-guide/mcp-tools/get-reference-doc\"},{\"text\":\"list_runs\",\"link\":\"/user-guide/mcp-tools/list-runs\"}]},{\"text\":\"Finding your event log\",\"link\":\"/user-guide/alternative-log-retrieval\",\"collapsed\":true,\"items\":[{\"text\":\"Managed platforms\",\"link\":\"/user-guide/alternative-log-retrieval/managed-platforms\"},{\"text\":\"Behind an SSH bastion\",\"link\":\"/user-guide/alternative-log-retrieval/ssh-bastion\"}]}]}],\"/contributor-guide/\":[{\"text\":\"Contributor Guide\",\"items\":[{\"text\":\"Development setup\",\"link\":\"/contributor-guide/development-setup\"},{\"text\":\"Architecture\",\"link\":\"/contributor-guide/architecture/\",\"collapsed\":true,\"items\":[{\"text\":\"Overview\",\"link\":\"/contributor-guide/architecture/overview\"},{\"text\":\"Worker protocol\",\"link\":\"/contributor-guide/architecture/worker-protocol\",\"collapsed\":true,\"items\":[{\"text\":\"Evidence availability\",\"link\":\"/contributor-guide/architecture/worker-protocol/evidence-availability\"},{\"text\":\"Evidence report and finding identity\",\"link\":\"/contributor-guide/architecture/worker-protocol/evidence-report\"},{\"text\":\"CLI and MCP server\",\"link\":\"/contributor-guide/architecture/worker-protocol/cli-and-mcp\"},{\"text\":\"Core and event validation\",\"link\":\"/contributor-guide/architecture/worker-protocol/core-and-event-validation\"}]},{\"text\":\"State & history intake\",\"link\":\"/contributor-guide/architecture/state-and-history\",\"collapsed\":true,\"items\":[{\"text\":\"Run comparison internals\",\"link\":\"/contributor-guide/architecture/state-and-history/run-comparison-internals\"},{\"text\":\"History Server intake\",\"link\":\"/contributor-guide/architecture/state-and-history/history-server-intake\"}]},{\"text\":\"Detector contract\",\"link\":\"/contributor-guide/architecture/detector-contract\",\"collapsed\":true,\"items\":[{\"text\":\"Plan attribution\",\"link\":\"/contributor-guide/architecture/detector-contract/plan-attribution\"},{\"text\":\"Threshold tables\",\"link\":\"/contributor-guide/architecture/detector-contract/threshold-tables\"}]},{\"text\":\"Impact estimation\",\"link\":\"/contributor-guide/architecture/impact-estimation\",\"collapsed\":true,\"items\":[{\"text\":\"Stage union rollup\",\"link\":\"/contributor-guide/architecture/impact-estimation/stage-union-rollup\"},{\"text\":\"Caveats, tuning and coverage\",\"link\":\"/contributor-guide/architecture/impact-estimation/caveats-tuning-and-coverage\"}]},{\"text\":\"Widget rendering\",\"link\":\"/contributor-guide/architecture/widget-rendering\",\"collapsed\":true,\"items\":[{\"text\":\"Findings tab\",\"link\":\"/contributor-guide/architecture/widget-rendering/findings-tab\"},{\"text\":\"List sort mode\",\"link\":\"/contributor-guide/architecture/widget-rendering/list-sort-mode\"},{\"text\":\"Row/expand contract\",\"link\":\"/contributor-guide/architecture/widget-rendering/row-expand-contract\"},{\"text\":\"ReferenceSection\",\"link\":\"/contributor-guide/architecture/widget-rendering/reference-section\"},{\"text\":\"Investigation routing\",\"link\":\"/contributor-guide/architecture/widget-rendering/investigation-routing\"}]},{\"text\":\"Board widgets\",\"link\":\"/contributor-guide/architecture/board-widgets\",\"collapsed\":true,\"items\":[{\"text\":\"Plan Advisor\",\"link\":\"/contributor-guide/architecture/board-widgets/plan-advisor\"},{\"text\":\"Caching and memory widgets\",\"link\":\"/contributor-guide/architecture/board-widgets/caching-and-memory\"},{\"text\":\"Visual system and templating\",\"link\":\"/contributor-guide/architecture/board-widgets/visual-system-and-templating\"}]},{\"text\":\"Drill-down\",\"link\":\"/contributor-guide/architecture/drill-down\",\"collapsed\":true,\"items\":[{\"text\":\"Plan graph\",\"link\":\"/contributor-guide/architecture/drill-down/plan-graph\"}]}]},{\"text\":\"Testing & verification\",\"link\":\"/contributor-guide/testing\"},{\"text\":\"Contributing\",\"link\":\"/contributor-guide/contributing\"}]}]},\"search\":{\"provider\":\"local\"}},\"locales\":{},\"scrollOffset\":{\"selector\":\"[data-sf-anchor-offset]\",\"padding\":0},\"cleanUrls\":false}");</script>
|
|
44
|
+
<span class="line"><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;"> --regression-budget</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;"> wallClock:10</span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;"> --regression-budget</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;"> gcTime:25</span></span></code></pre></div><p>The <code>--budgets</code> file is JSON with one key, <code>regression</code>, mapping a metric key to its percentage:</p><div class="language-json vp-adaptive-theme"><button title="Copy Code" class="copy"></button><span class="lang">json</span><pre class="shiki shiki-themes github-light github-dark vp-code" tabindex="0"><code><span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">{ </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">"regression"</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: { </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">"wallClock"</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">10</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">, </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">"gcTime"</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">25</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">, </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">"failedTaskRate"</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">0</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> } }</span></span></code></pre></div><p>The CLI refuses to run, with exit code 2 and a message naming the problem, for an unknown top-level key, an unknown metric key, a percentage that is not a non-negative number (in the file a JSON number, not a string; on the flag plain digits such as <code>10</code> or <code>2.5</code>), or a file that can't be read or isn't valid JSON.</p><p>The budgets combine like this:</p><ul><li><code>--max-regression-pct</code> with <code>--regression-metric</code> (default <code>wallClock</code>) still works and counts as one more budget next to the new ones.</li><li>Each metric can be budgeted once across the legacy pair, the repeated flag and the file. A metric named twice is a usage error (exit 2), even when both give the same percentage.</li><li>Each budget is checked on its own and gives one <code>max-regression</code> result that carries <code>metric</code>, the key it checks. Any violated budget makes the run exit <code>1</code>; otherwise an inconclusive one makes it exit <code>3</code>. A budget on a metric the baseline or the candidate log can't provide is inconclusive, never a pass.</li></ul><h3 id="per-stage-regression-budgets" tabindex="-1">Per-stage regression budgets <a class="header-anchor" href="#per-stage-regression-budgets" aria-label="Permalink to "Per-stage regression budgets""></a></h3><p><code>--max-regression-pct</code> and <code>--regression-budget</code> judge a whole-run metric. To gate on the stages themselves, repeat <code>--stage-regression-budget <metric>:<pct></code> (with <code>--baseline</code>). The budget fails when any paired stage's metric grew by more than the percentage against its baseline stage. The metric is one of <code>executorRunTime</code>, <code>executorCpuTime</code>, <code>memoryBytesSpilled</code>, <code>diskBytesSpilled</code>, <code>shuffleReadBytes</code> and <code>shuffleWriteBytes</code>:</p><div class="language-sh vp-adaptive-theme"><button title="Copy Code" class="copy"></button><span class="lang">sh</span><pre class="shiki shiki-themes github-light github-dark vp-code" tabindex="0"><code><span class="line"><span style="--shiki-light:#6F42C1;--shiki-dark:#B392F0;">sparkforensics-analyze</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;"> candidate.zstd</span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;"> --baseline</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;"> baseline.zstd</span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;"> \</span></span>
|
|
45
|
+
<span class="line"><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;"> --stage-regression-budget</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;"> executorRunTime:25</span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;"> --stage-regression-budget</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;"> diskBytesSpilled:0</span></span></code></pre></div><ul><li>The stages come from the comparison's <code>stagePairs</code>. By default only <code>exact</code> and <code>structural</code> pairs count, since an <code>aligned</code> pair may compare different work. <code>--stage-quality exact,structural,aligned</code> chooses the qualities; each pair's <code>quality</code> and <code>score</code> are in the comparison output. Stages a re-plan left over are not paired and are not checked.</li><li>Each metric gives one <code>max-stage-regression</code> result carrying <code>metric</code>, whose detail names the worst offenders by <code>pairId</code>. A violation exits <code>1</code>.</li><li>A stage that grew from a zero baseline exceeds any percentage.</li><li>It is inconclusive (exit <code>3</code>) when no eligible stage pairs or the metric is missing on every one, never a pass. A comparison with <code>low</code> or <code>insufficient</code> confidence is still judged on the pairs it has.</li><li>A metric can be budgeted once. <code>--stage-quality</code> without <code>--stage-regression-budget</code>, an unknown metric or quality, and a metric named twice are usage errors (exit <code>2</code>), and so are <code>inputBytes</code> and <code>outputBytes</code>: workload volume has no regression direction.</li></ul><h3 id="several-candidates" tabindex="-1">Several candidates <a class="header-anchor" href="#several-candidates" aria-label="Permalink to "Several candidates""></a></h3><p>Pass two or more logs as positional arguments, with <code>--baseline</code>, to compare each against the same baseline. The baseline is parsed once. Output is NDJSON: one line per candidate, in argument order, written as each one finishes. <code>--out <path></code> writes the lines to a file instead of stdout, and <code>--format ndjson</code> selects this output for a single candidate too. The mode can't be combined with <code>--export-html</code>, <code>--shs-base-url</code>, <code>--format json</code> or <code>--format md</code> (exit 2). <code>--redact</code>, <code>--thresholds</code>, <code>--impact</code>, <code>--type</code>, <code>--stage</code>, <code>--conf-keys</code>, <code>--conf-redact-regex</code> and every budget flag apply to each candidate.</p><p>Each line is one JSON object:</p><table tabindex="0"><thead><tr><th>Field</th><th>Meaning</th></tr></thead><tbody><tr><td><code>log</code></td><td>The candidate path, as given on the command line. With <code>--redact</code>, <code>candidate-<n></code> instead, <code>n</code> being the candidate's 1-based position.</td></tr><tr><td><code>status</code></td><td><code>pass</code>, <code>violation</code>, <code>inconclusive</code> or <code>error</code>.</td></tr><tr><td><code>exitCode</code></td><td>The exit code this line alone would give: <code>0</code> for <code>pass</code>, <code>1</code> for <code>violation</code>, <code>3</code> for <code>inconclusive</code>, and for <code>error</code> <code>4</code> (the log can't be read or parsed) or <code>6</code> (an internal failure while analyzing it).</td></tr><tr><td><code>error</code></td><td>The message when <code>status</code> is <code>error</code>; otherwise <code>null</code>. With <code>--redact</code>, a generic message that names no path.</td></tr><tr><td><code>budgets</code></td><td>This candidate's budget results, each with <code>name</code>, <code>status</code> (<code>pass</code>, <code>violation</code> or <code>inconclusive</code>) and <code>detail</code>, plus <code>metric</code> on <code>max-regression</code> and <code>max-stage-regression</code>. Empty for an <code>error</code> line.</td></tr><tr><td><code>candidate</code></td><td>The candidate's report with its <code>metrics</code> and <code>effectiveConf</code> blocks, the same object the single-candidate JSON output carries under <code>candidate</code>. <code>null</code> for an <code>error</code> line.</td></tr><tr><td><code>comparison</code></td><td><code>verdict</code>, <code>confidence</code>, <code>reason</code>, <code>matchedCoverage</code>, <code>runtimeCoverage</code>, <code>metrics</code>, <code>findings</code>, <code>comparisonSchemaVersion</code>, <code>stagePairs</code>, <code>unmatched</code>, <code>replanned</code>, <code>bookkeepingStageIds</code> and <code>executionAlignment</code>, the same object the single-candidate JSON output carries under <code>comparison</code>. <code>null</code> for an <code>error</code> line.</td></tr></tbody></table><p>A line's <code>status</code> follows the single-candidate rules: <code>violation</code> if any budget result is a violation, else <code>inconclusive</code> if any is inconclusive (including the <code>run-complete</code> check for a log with no <code>ApplicationEnd</code>), else <code>pass</code>.</p><p>A candidate that can't be read or parsed doesn't stop the others. Its line has <code>status: "error"</code>, <code>exitCode: 4</code>, the message in <code>error</code>, and <code>null</code> for <code>candidate</code> and <code>comparison</code>, as a single-candidate run exits <code>4</code> for a candidate it can't parse. The process exit code is the worst line, in the order <code>6</code>, <code>5</code>, <code>4</code>, <code>1</code>, <code>3</code>, <code>0</code>, so an unreadable candidate outranks a violation and a violation outranks an inconclusive result.</p><p>Two failures stop the batch before any line is written:</p><ul><li>A usage error (bad flags or arguments, an invalid <code>--thresholds</code> or <code>--budgets</code> file) exits <code>2</code>.</li><li>A baseline that can't be read or parsed exits <code>5</code>. Fix the baseline and run the batch again.</li></ul><p>An internal failure that isn't tied to one candidate, such as an unwritable <code>--out</code> path, exits <code>6</code>.</p><p>With <code>--redact</code>, no candidate path is written anywhere, since event-log file names usually carry the app id. <code>log</code> and the <code>stderr</code> line prefixes name each candidate by its 1-based position (<code>candidate-1</code>, <code>candidate-2</code>, ...), and an <code>error</code> line carries a generic message instead of the parser's, which may quote the path: <code>Candidate 2 could not be read or parsed.</code>, or <code>could not be analyzed</code> for an internal failure. An unreadable baseline prints <code>The baseline could not be read or parsed.</code> to <code>stderr</code>. A single-candidate run does the same, naming <code>The baseline</code> or <code>The candidate</code>.</p></div></div></main><footer class="VPDocFooter" data-v-39a288b8 data-v-e257564d><!--[--><!--]--><!----><nav class="prev-next" aria-labelledby="doc-footer-aria-label" data-v-e257564d><span class="visually-hidden" id="doc-footer-aria-label" data-v-e257564d>Pager</span><div class="pager" data-v-e257564d><a class="VPLink link pager-link prev" href="/docs/user-guide/getting-started/reading-the-dashboard.html" data-v-e257564d><!--[--><span class="desc" data-v-e257564d>Previous page</span><span class="title" data-v-e257564d>Reading the dashboard</span><!--]--></a></div><div class="pager" data-v-e257564d><a class="VPLink link pager-link next" href="/docs/user-guide/getting-started/tuning-thresholds.html" data-v-e257564d><!--[--><span class="desc" data-v-e257564d>Next page</span><span class="title" data-v-e257564d>Tuning detector thresholds</span><!--]--></a></div></nav></footer><!--[--><!--]--></div></div></div><!--[--><!--]--></div></div><!----><!--[--><!--]--></div></div>
|
|
46
|
+
<script>window.__VP_HASH_MAP__=JSON.parse("{\"contributor-guide_architecture_board-widgets.md\":\"YQcj5EI4\",\"contributor-guide_architecture_board-widgets_caching-and-memory.md\":\"CQgn1t_M\",\"contributor-guide_architecture_board-widgets_plan-advisor.md\":\"RlzvUmNm\",\"contributor-guide_architecture_board-widgets_visual-system-and-templating.md\":\"wulOueeB\",\"contributor-guide_architecture_detector-contract.md\":\"N4hhenrA\",\"contributor-guide_architecture_detector-contract_plan-attribution.md\":\"yNex4bys\",\"contributor-guide_architecture_detector-contract_threshold-tables.md\":\"Dp3c40rx\",\"contributor-guide_architecture_drill-down.md\":\"CqZPrdo9\",\"contributor-guide_architecture_drill-down_plan-graph.md\":\"DwOozIEs\",\"contributor-guide_architecture_impact-estimation.md\":\"DfvbqEUu\",\"contributor-guide_architecture_impact-estimation_caveats-tuning-and-coverage.md\":\"Cwm1jHmn\",\"contributor-guide_architecture_impact-estimation_stage-union-rollup.md\":\"DdCGtAGu\",\"contributor-guide_architecture_index.md\":\"tymxf1Fh\",\"contributor-guide_architecture_overview.md\":\"C1sSvm9i\",\"contributor-guide_architecture_state-and-history.md\":\"DyCBdjuM\",\"contributor-guide_architecture_state-and-history_history-server-intake.md\":\"C298hrHZ\",\"contributor-guide_architecture_state-and-history_run-comparison-internals.md\":\"CZA0JLtV\",\"contributor-guide_architecture_widget-rendering.md\":\"BOZ1azXG\",\"contributor-guide_architecture_widget-rendering_findings-tab.md\":\"BQXycK6G\",\"contributor-guide_architecture_widget-rendering_investigation-routing.md\":\"BGdiyElu\",\"contributor-guide_architecture_widget-rendering_list-sort-mode.md\":\"BuHKgH0C\",\"contributor-guide_architecture_widget-rendering_reference-section.md\":\"DWqC80bN\",\"contributor-guide_architecture_widget-rendering_row-expand-contract.md\":\"ZT89u9f1\",\"contributor-guide_architecture_worker-protocol.md\":\"BAnhi2-d\",\"contributor-guide_architecture_worker-protocol_cli-and-mcp.md\":\"BX1XnFbq\",\"contributor-guide_architecture_worker-protocol_core-and-event-validation.md\":\"DSVFPpWb\",\"contributor-guide_architecture_worker-protocol_evidence-availability.md\":\"CjimIDBY\",\"contributor-guide_architecture_worker-protocol_evidence-report.md\":\"CiQl1MLb\",\"contributor-guide_contributing.md\":\"CQMvGwFt\",\"contributor-guide_development-setup.md\":\"DQdzera7\",\"contributor-guide_testing.md\":\"By6XGR9a\",\"index.md\":\"CHJVslga\",\"tuning-reference_anti-patterns.md\":\"D08Uaod7\",\"tuning-reference_aqe.md\":\"C1Ae6A8u\",\"tuning-reference_bottleneck-broadcast-sizing.md\":\"6wjKuJNE\",\"tuning-reference_bottleneck-cold-start.md\":\"BVQbsuHP\",\"tuning-reference_bottleneck-duplicate-plan-subtree.md\":\"DtaYnaiF\",\"tuning-reference_bottleneck-failures.md\":\"Z1Tdmdd3\",\"tuning-reference_bottleneck-gc.md\":\"BCnXLf1n\",\"tuning-reference_bottleneck-job-failure-rate.md\":\"CcvQj2g9\",\"tuning-reference_bottleneck-memory-utilization.md\":\"B-C0-8h-\",\"tuning-reference_bottleneck-retry-waste.md\":\"DCnhWiqj\",\"tuning-reference_bottleneck-shuffle.md\":\"B5OMJCd3\",\"tuning-reference_bottleneck-skew.md\":\"Cvo6NQm_\",\"tuning-reference_bottleneck-slow-host.md\":\"ja5qr3wq\",\"tuning-reference_bottleneck-small-files.md\":\"Crjtb0i2\",\"tuning-reference_bottleneck-spill.md\":\"Bl8KtSRg\",\"tuning-reference_bottleneck-straggler.md\":\"B0VN8reT\",\"tuning-reference_bottleneck-tiny-tasks.md\":\"DQCftGhu\",\"tuning-reference_bottleneck-utilization.md\":\"BXDl30f9\",\"tuning-reference_caching.md\":\"CcaiMn_7\",\"tuning-reference_cluster-config.md\":\"DbWG1yZq\",\"tuning-reference_config.md\":\"YUqSpwFB\",\"tuning-reference_data-formats.md\":\"C5DX5xL4\",\"tuning-reference_index.md\":\"ZVIpQ6Dk\",\"tuning-reference_intro.md\":\"BSSaDlqx\",\"tuning-reference_joins.md\":\"BVhNCDnE\",\"tuning-reference_memory-model.md\":\"CfjFdgbl\",\"tuning-reference_metrics.md\":\"C64VNEL4\",\"tuning-reference_partitioning.md\":\"CtLK0xsS\",\"tuning-reference_pyspark.md\":\"D-92XgF8\",\"tuning-reference_shuffle.md\":\"Iq2v1oHJ\",\"tuning-reference_spark-architecture.md\":\"_qwnE_Sc\",\"tuning-reference_table-formats.md\":\"BSYEK-eN\",\"user-guide_alternative-log-retrieval.md\":\"CJpYvHGo\",\"user-guide_alternative-log-retrieval_managed-platforms.md\":\"DvDwHNtC\",\"user-guide_alternative-log-retrieval_ssh-bastion.md\":\"Gszzlplv\",\"user-guide_getting-started.md\":\"DYHHHkQR\",\"user-guide_getting-started_ci-and-automation.md\":\"BEepbDDL\",\"user-guide_getting-started_reading-the-dashboard.md\":\"Obf3W3__\",\"user-guide_getting-started_regression-metric-keys.md\":\"B_gzr2Mw\",\"user-guide_getting-started_tuning-thresholds.md\":\"B_MyjyZm\",\"user-guide_mcp-tools.md\":\"C65SjWUL\",\"user-guide_mcp-tools_compare-runs.md\":\"Cc_gLoix\",\"user-guide_mcp-tools_diagnose-run.md\":\"BP1vnHA5\",\"user-guide_mcp-tools_evaluate-budgets.md\":\"BB0nDY3Z\",\"user-guide_mcp-tools_get-finding-documentation.md\":\"BtTTHNV6\",\"user-guide_mcp-tools_get-finding-evidence.md\":\"rKyu4wts\",\"user-guide_mcp-tools_get-reference-doc.md\":\"Yac4tH3u\",\"user-guide_mcp-tools_get-run-summary.md\":\"EhaIsele\",\"user-guide_mcp-tools_list-runs.md\":\"DpQPeCM3\",\"user-guide_run-comparison.md\":\"BUALkohi\",\"user-guide_run-comparison_how-stages-are-matched.md\":\"DSXGu2tA\",\"user-guide_understanding-findings.md\":\"3C7KCEZO\"}");window.__VP_SITE_DATA__=JSON.parse("{\"lang\":\"en-US\",\"dir\":\"ltr\",\"title\":\"SparkForensics\",\"description\":\"Docs for using and contributing to SparkForensics\",\"base\":\"/docs/\",\"head\":[],\"router\":{\"prefetchLinks\":true},\"appearance\":true,\"themeConfig\":{\"logo\":\"/favicon.svg\",\"nav\":[{\"text\":\"User Guide\",\"link\":\"/user-guide/getting-started\"},{\"text\":\"Contributor Guide\",\"link\":\"/contributor-guide/development-setup\"},{\"text\":\"Tuning Reference\",\"link\":\"/tuning-reference/\"}],\"sidebar\":{\"/tuning-reference/\":[{\"text\":\"Getting Started\",\"items\":[{\"text\":\"Introduction\",\"link\":\"/tuning-reference/intro\"}]},{\"text\":\"Optimization Guide\",\"items\":[{\"text\":\"Spark Execution Model\",\"link\":\"/tuning-reference/spark-architecture\"},{\"text\":\"Memory Management\",\"link\":\"/tuning-reference/memory-model\"},{\"text\":\"Partitioning\",\"link\":\"/tuning-reference/partitioning\"},{\"text\":\"Join Optimization\",\"link\":\"/tuning-reference/joins\"},{\"text\":\"Shuffle\",\"link\":\"/tuning-reference/shuffle\"},{\"text\":\"Data Formats\",\"link\":\"/tuning-reference/data-formats\"},{\"text\":\"Table Formats\",\"link\":\"/tuning-reference/table-formats\"},{\"text\":\"Caching & Persistence\",\"link\":\"/tuning-reference/caching\"},{\"text\":\"PySpark Specifics\",\"link\":\"/tuning-reference/pyspark\"},{\"text\":\"Adaptive Query Execution\",\"link\":\"/tuning-reference/aqe\"},{\"text\":\"Cluster Tuning\",\"link\":\"/tuning-reference/cluster-config\"},{\"text\":\"Anti-Patterns\",\"link\":\"/tuning-reference/anti-patterns\"}]},{\"text\":\"Detector Catalog\",\"items\":[{\"text\":\"Task Skew\",\"link\":\"/tuning-reference/bottleneck-skew\"},{\"text\":\"Shuffle I/O\",\"link\":\"/tuning-reference/bottleneck-shuffle\"},{\"text\":\"Memory / Disk Spill\",\"link\":\"/tuning-reference/bottleneck-spill\"},{\"text\":\"GC Pressure\",\"link\":\"/tuning-reference/bottleneck-gc\"},{\"text\":\"Cold Start\",\"link\":\"/tuning-reference/bottleneck-cold-start\"},{\"text\":\"Executor Utilization\",\"link\":\"/tuning-reference/bottleneck-utilization\"},{\"text\":\"Slow Host\",\"link\":\"/tuning-reference/bottleneck-slow-host\"},{\"text\":\"Task Failures\",\"link\":\"/tuning-reference/bottleneck-failures\"},{\"text\":\"Stragglers\",\"link\":\"/tuning-reference/bottleneck-straggler\"},{\"text\":\"Retry Waste\",\"link\":\"/tuning-reference/bottleneck-retry-waste\"},{\"text\":\"Tiny Tasks\",\"link\":\"/tuning-reference/bottleneck-tiny-tasks\"},{\"text\":\"Job Failure Rate\",\"link\":\"/tuning-reference/bottleneck-job-failure-rate\"},{\"text\":\"Memory Utilization\",\"link\":\"/tuning-reference/bottleneck-memory-utilization\"},{\"text\":\"Duplicate Plan Subtree\",\"link\":\"/tuning-reference/bottleneck-duplicate-plan-subtree\"},{\"text\":\"Small Files\",\"link\":\"/tuning-reference/bottleneck-small-files\"},{\"text\":\"Broadcast Sizing\",\"link\":\"/tuning-reference/bottleneck-broadcast-sizing\"}]},{\"text\":\"Reference\",\"items\":[{\"text\":\"Metrics Glossary\",\"link\":\"/tuning-reference/metrics\"},{\"text\":\"Spark Config Quick-Reference\",\"link\":\"/tuning-reference/config\"}]}],\"/user-guide/\":[{\"text\":\"User Guide\",\"items\":[{\"text\":\"Getting started\",\"link\":\"/user-guide/getting-started\",\"collapsed\":true,\"items\":[{\"text\":\"Reading the dashboard\",\"link\":\"/user-guide/getting-started/reading-the-dashboard\"},{\"text\":\"CI and automation\",\"link\":\"/user-guide/getting-started/ci-and-automation\"},{\"text\":\"Tuning detector thresholds\",\"link\":\"/user-guide/getting-started/tuning-thresholds\"},{\"text\":\"Regression metric keys\",\"link\":\"/user-guide/getting-started/regression-metric-keys\"}]},{\"text\":\"Understanding findings\",\"link\":\"/user-guide/understanding-findings\"},{\"text\":\"Run comparison mode\",\"link\":\"/user-guide/run-comparison\",\"collapsed\":true,\"items\":[{\"text\":\"How stages are matched\",\"link\":\"/user-guide/run-comparison/how-stages-are-matched\"}]},{\"text\":\"MCP tools reference\",\"link\":\"/user-guide/mcp-tools\",\"collapsed\":true,\"items\":[{\"text\":\"diagnose_run\",\"link\":\"/user-guide/mcp-tools/diagnose-run\"},{\"text\":\"get_run_summary\",\"link\":\"/user-guide/mcp-tools/get-run-summary\"},{\"text\":\"evaluate_budgets\",\"link\":\"/user-guide/mcp-tools/evaluate-budgets\"},{\"text\":\"compare_runs\",\"link\":\"/user-guide/mcp-tools/compare-runs\"},{\"text\":\"get_finding_evidence\",\"link\":\"/user-guide/mcp-tools/get-finding-evidence\"},{\"text\":\"get_finding_documentation\",\"link\":\"/user-guide/mcp-tools/get-finding-documentation\"},{\"text\":\"get_reference_doc\",\"link\":\"/user-guide/mcp-tools/get-reference-doc\"},{\"text\":\"list_runs\",\"link\":\"/user-guide/mcp-tools/list-runs\"}]},{\"text\":\"Finding your event log\",\"link\":\"/user-guide/alternative-log-retrieval\",\"collapsed\":true,\"items\":[{\"text\":\"Managed platforms\",\"link\":\"/user-guide/alternative-log-retrieval/managed-platforms\"},{\"text\":\"Behind an SSH bastion\",\"link\":\"/user-guide/alternative-log-retrieval/ssh-bastion\"}]}]}],\"/contributor-guide/\":[{\"text\":\"Contributor Guide\",\"items\":[{\"text\":\"Development setup\",\"link\":\"/contributor-guide/development-setup\"},{\"text\":\"Architecture\",\"link\":\"/contributor-guide/architecture/\",\"collapsed\":true,\"items\":[{\"text\":\"Overview\",\"link\":\"/contributor-guide/architecture/overview\"},{\"text\":\"Worker protocol\",\"link\":\"/contributor-guide/architecture/worker-protocol\",\"collapsed\":true,\"items\":[{\"text\":\"Evidence availability\",\"link\":\"/contributor-guide/architecture/worker-protocol/evidence-availability\"},{\"text\":\"Evidence report and finding identity\",\"link\":\"/contributor-guide/architecture/worker-protocol/evidence-report\"},{\"text\":\"CLI and MCP server\",\"link\":\"/contributor-guide/architecture/worker-protocol/cli-and-mcp\"},{\"text\":\"Core and event validation\",\"link\":\"/contributor-guide/architecture/worker-protocol/core-and-event-validation\"}]},{\"text\":\"State & history intake\",\"link\":\"/contributor-guide/architecture/state-and-history\",\"collapsed\":true,\"items\":[{\"text\":\"Run comparison internals\",\"link\":\"/contributor-guide/architecture/state-and-history/run-comparison-internals\"},{\"text\":\"History Server intake\",\"link\":\"/contributor-guide/architecture/state-and-history/history-server-intake\"}]},{\"text\":\"Detector contract\",\"link\":\"/contributor-guide/architecture/detector-contract\",\"collapsed\":true,\"items\":[{\"text\":\"Plan attribution\",\"link\":\"/contributor-guide/architecture/detector-contract/plan-attribution\"},{\"text\":\"Threshold tables\",\"link\":\"/contributor-guide/architecture/detector-contract/threshold-tables\"}]},{\"text\":\"Impact estimation\",\"link\":\"/contributor-guide/architecture/impact-estimation\",\"collapsed\":true,\"items\":[{\"text\":\"Stage union rollup\",\"link\":\"/contributor-guide/architecture/impact-estimation/stage-union-rollup\"},{\"text\":\"Caveats, tuning and coverage\",\"link\":\"/contributor-guide/architecture/impact-estimation/caveats-tuning-and-coverage\"}]},{\"text\":\"Widget rendering\",\"link\":\"/contributor-guide/architecture/widget-rendering\",\"collapsed\":true,\"items\":[{\"text\":\"Findings tab\",\"link\":\"/contributor-guide/architecture/widget-rendering/findings-tab\"},{\"text\":\"List sort mode\",\"link\":\"/contributor-guide/architecture/widget-rendering/list-sort-mode\"},{\"text\":\"Row/expand contract\",\"link\":\"/contributor-guide/architecture/widget-rendering/row-expand-contract\"},{\"text\":\"ReferenceSection\",\"link\":\"/contributor-guide/architecture/widget-rendering/reference-section\"},{\"text\":\"Investigation routing\",\"link\":\"/contributor-guide/architecture/widget-rendering/investigation-routing\"}]},{\"text\":\"Board widgets\",\"link\":\"/contributor-guide/architecture/board-widgets\",\"collapsed\":true,\"items\":[{\"text\":\"Plan Advisor\",\"link\":\"/contributor-guide/architecture/board-widgets/plan-advisor\"},{\"text\":\"Caching and memory widgets\",\"link\":\"/contributor-guide/architecture/board-widgets/caching-and-memory\"},{\"text\":\"Visual system and templating\",\"link\":\"/contributor-guide/architecture/board-widgets/visual-system-and-templating\"}]},{\"text\":\"Drill-down\",\"link\":\"/contributor-guide/architecture/drill-down\",\"collapsed\":true,\"items\":[{\"text\":\"Plan graph\",\"link\":\"/contributor-guide/architecture/drill-down/plan-graph\"}]}]},{\"text\":\"Testing & verification\",\"link\":\"/contributor-guide/testing\"},{\"text\":\"Contributing\",\"link\":\"/contributor-guide/contributing\"}]}]},\"search\":{\"provider\":\"local\"}},\"locales\":{},\"scrollOffset\":{\"selector\":\"[data-sf-anchor-offset]\",\"padding\":0},\"cleanUrls\":false}");</script>
|
|
49
47
|
|
|
50
48
|
</body>
|
|
51
49
|
</html>
|