sparkforensics-server 0.2.4 → 0.4.0
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/LICENSE +21 -0
- package/README.md +5 -1
- package/index.js +5 -4
- package/package.json +1 -1
- package/public/assets/AutoscalingChurn-CUSIvvab.js +1 -0
- package/public/assets/CacheUtilization-Ce0K6_X2.js +1 -0
- package/public/assets/CachingOpportunity-Cn-LmRA4.js +1 -0
- package/public/assets/ColdStart-BoiYzEyV.js +1 -0
- package/public/assets/ConfigAudit-BoJc6PAw.js +1 -0
- package/public/assets/CoreUsageArea-BFfXKu7K.js +1 -0
- package/public/assets/Dashboard-Bo_1jGqH.js +2 -0
- package/public/assets/DisclosureContext-LYzHroHO.js +1 -0
- package/public/assets/DuplicatePlanSubtree-BaAuGAoo.js +1 -0
- package/public/assets/ExecutorUtilization-OE6VMFkG.js +1 -0
- package/public/assets/GcPressure-AoL_ZNrV.js +1 -0
- package/public/assets/IncompleteRun-Bv6IzgsQ.js +1 -0
- package/public/assets/JobFailures-DF3U2z1f.js +1 -0
- package/public/assets/MemoryUtilization-B65OVZlq.js +1 -0
- package/public/assets/OverBroadcast-DXbJREDl.js +1 -0
- package/public/assets/PartitionSizing-DZLnjy0d.js +1 -0
- package/public/assets/PlanExplorer-DdmPkKO1.js +1 -0
- package/public/assets/PlanGraphRoute-C-BGmC6j.js +1 -0
- package/public/assets/RetryWaste-BbEPsdMw.js +1 -0
- package/public/assets/ShuffleIO-wZB94LS8.js +1 -0
- package/public/assets/Skew-SpQE7zeJ.js +1 -0
- package/public/assets/SlowHost-DwDBCTvr.js +1 -0
- package/public/assets/SmallFiles-yjY_6sT1.js +1 -0
- package/public/assets/SpeculationWaste-73PDmj0c.js +1 -0
- package/public/assets/Spill-DEw0Kd1i.js +1 -0
- package/public/assets/StageFailed-BEfXdEJc.js +1 -0
- package/public/assets/StageFindingGroup-Bzm2TY03.js +1 -0
- package/public/assets/StageHeader-BSV8ALhT.js +1 -0
- package/public/assets/StageShape-CzR4jHOt.js +1 -0
- package/public/assets/StageSlowness-vMPsnAaa.js +1 -0
- package/public/assets/Straggler-Cf__OGl5.js +1 -0
- package/public/assets/TaskFailures-BZ8kLZiO.js +1 -0
- package/public/assets/{TinyTask-DYXks5sT.js → TinyTask-CIPRxWfT.js} +1 -1
- package/public/assets/UnderBroadcast-CBm8ZPoS.js +1 -0
- package/public/assets/{finding-anchor-CDbHtqKT.js → finding-anchor-DF1cSHO1.js} +1 -1
- package/public/assets/impact-sort-7z0ZcBZf.js +1 -0
- package/public/assets/index-BcqTLKFp.css +2 -0
- package/public/assets/index-CEM9bz_x.js +13 -0
- package/public/assets/parser-worker-Q5KCPdKT.js +122 -0
- package/public/assets/react-vendor-BAKt3vny.js +9 -0
- package/public/assets/select-Cy5pmbrh.js +1 -0
- package/public/assets/usePagedRows-BjPOpUU8.js +1 -0
- package/public/assets/useRecentFiles-BrBl-AP1.js +11 -0
- package/public/assets/useSortMode-CU0vzThu.js +1 -0
- package/public/docs/404.html +2 -2
- package/public/docs/assets/{app.DsFQcynM.js → app.C6w47a9W.js} +1 -1
- package/public/docs/assets/chunks/@localSearchIndexroot.DbZy5EtM.js +1 -0
- package/public/docs/assets/chunks/{VPLocalSearchBox.oa8NbaiV.js → VPLocalSearchBox.BcTNvT55.js} +1 -1
- package/public/docs/assets/chunks/{theme.Ca4dR9dL.js → theme.D-mE6j02.js} +2 -2
- package/public/docs/assets/{contributor-guide_architecture_board-widgets.md.9ToZXcTk.js → contributor-guide_architecture_board-widgets.md.VTcYTH4d.js} +1 -1
- package/public/docs/assets/contributor-guide_architecture_detector-contract.md.CsqZHz_T.js +1 -0
- package/public/docs/assets/{contributor-guide_architecture_detector-contract.md.aQQfP7pj.lean.js → contributor-guide_architecture_detector-contract.md.CsqZHz_T.lean.js} +1 -1
- package/public/docs/assets/contributor-guide_architecture_drill-down.md.CFNCE8JB.js +1 -0
- package/public/docs/assets/{contributor-guide_architecture_drill-down.md.Bawx6NgP.lean.js → contributor-guide_architecture_drill-down.md.CFNCE8JB.lean.js} +1 -1
- package/public/docs/assets/contributor-guide_architecture_impact-estimation.md.HT9IJGIl.js +1 -0
- package/public/docs/assets/{contributor-guide_architecture_impact-estimation.md.sf9DU2bA.lean.js → contributor-guide_architecture_impact-estimation.md.HT9IJGIl.lean.js} +1 -1
- package/public/docs/assets/contributor-guide_architecture_overview.md.CTEqVeV4.js +1 -0
- package/public/docs/assets/contributor-guide_architecture_overview.md.CTEqVeV4.lean.js +1 -0
- package/public/docs/assets/contributor-guide_architecture_state-and-history.md.DOTVHjTV.js +1 -0
- package/public/docs/assets/{contributor-guide_architecture_state-and-history.md.C-xxn0q7.lean.js → contributor-guide_architecture_state-and-history.md.DOTVHjTV.lean.js} +1 -1
- package/public/docs/assets/contributor-guide_architecture_widget-rendering.md.BmpARZve.js +1 -0
- package/public/docs/assets/{contributor-guide_architecture_widget-rendering.md.DYwFeyjV.lean.js → contributor-guide_architecture_widget-rendering.md.BmpARZve.lean.js} +1 -1
- package/public/docs/assets/contributor-guide_architecture_worker-protocol.md.21pTYhFF.js +6 -0
- package/public/docs/assets/contributor-guide_architecture_worker-protocol.md.21pTYhFF.lean.js +1 -0
- package/public/docs/assets/contributor-guide_contributing.md.B2E9ni79.js +1 -0
- package/public/docs/assets/contributor-guide_contributing.md.B2E9ni79.lean.js +1 -0
- package/public/docs/assets/contributor-guide_development-setup.md.CjgZJwjK.js +15 -0
- package/public/docs/assets/{contributor-guide_development-setup.md.DvMV1xhQ.lean.js → contributor-guide_development-setup.md.CjgZJwjK.lean.js} +1 -1
- package/public/docs/assets/contributor-guide_testing.md.DTwhpoN2.js +1 -0
- package/public/docs/assets/contributor-guide_testing.md.DTwhpoN2.lean.js +1 -0
- package/public/docs/assets/tuning-reference_anti-patterns.md.D08Uaod7.js +1 -0
- package/public/docs/assets/tuning-reference_anti-patterns.md.D08Uaod7.lean.js +1 -0
- package/public/docs/assets/tuning-reference_aqe.md.C1Ae6A8u.js +1 -0
- package/public/docs/assets/tuning-reference_aqe.md.C1Ae6A8u.lean.js +1 -0
- package/public/docs/assets/tuning-reference_bottleneck-broadcast-sizing.md.6wjKuJNE.js +1 -0
- package/public/docs/assets/tuning-reference_bottleneck-broadcast-sizing.md.6wjKuJNE.lean.js +1 -0
- package/public/docs/assets/tuning-reference_bottleneck-cold-start.md.BVQbsuHP.js +7 -0
- package/public/docs/assets/tuning-reference_bottleneck-cold-start.md.BVQbsuHP.lean.js +1 -0
- package/public/docs/assets/tuning-reference_bottleneck-duplicate-plan-subtree.md.DtaYnaiF.js +1 -0
- package/public/docs/assets/tuning-reference_bottleneck-duplicate-plan-subtree.md.DtaYnaiF.lean.js +1 -0
- package/public/docs/assets/{tuning-reference_bottleneck-failures.md.CAsFf3RR.js → tuning-reference_bottleneck-failures.md.Z1Tdmdd3.js} +2 -2
- package/public/docs/assets/tuning-reference_bottleneck-failures.md.Z1Tdmdd3.lean.js +1 -0
- package/public/docs/assets/tuning-reference_bottleneck-gc.md.BCnXLf1n.js +6 -0
- package/public/docs/assets/tuning-reference_bottleneck-gc.md.BCnXLf1n.lean.js +1 -0
- package/public/docs/assets/tuning-reference_bottleneck-job-failure-rate.md.CcvQj2g9.js +8 -0
- package/public/docs/assets/tuning-reference_bottleneck-job-failure-rate.md.CcvQj2g9.lean.js +1 -0
- package/public/docs/assets/tuning-reference_bottleneck-memory-utilization.md.B-C0-8h-.js +7 -0
- package/public/docs/assets/tuning-reference_bottleneck-memory-utilization.md.B-C0-8h-.lean.js +1 -0
- package/public/docs/assets/tuning-reference_bottleneck-retry-waste.md.DCnhWiqj.js +1 -0
- package/public/docs/assets/tuning-reference_bottleneck-retry-waste.md.DCnhWiqj.lean.js +1 -0
- package/public/docs/assets/{tuning-reference_bottleneck-shuffle.md.DDMQVOW6.js → tuning-reference_bottleneck-shuffle.md.B5OMJCd3.js} +2 -2
- package/public/docs/assets/tuning-reference_bottleneck-shuffle.md.B5OMJCd3.lean.js +1 -0
- package/public/docs/assets/{tuning-reference_bottleneck-skew.md.B0MzhWcX.js → tuning-reference_bottleneck-skew.md.Cvo6NQm_.js} +1 -1
- package/public/docs/assets/tuning-reference_bottleneck-skew.md.Cvo6NQm_.lean.js +1 -0
- package/public/docs/assets/{tuning-reference_bottleneck-slow-host.md.BlIo6UDW.js → tuning-reference_bottleneck-slow-host.md.ja5qr3wq.js} +1 -1
- package/public/docs/assets/tuning-reference_bottleneck-slow-host.md.ja5qr3wq.lean.js +1 -0
- package/public/docs/assets/tuning-reference_bottleneck-small-files.md.Crjtb0i2.js +5 -0
- package/public/docs/assets/tuning-reference_bottleneck-small-files.md.Crjtb0i2.lean.js +1 -0
- package/public/docs/assets/tuning-reference_bottleneck-spill.md.Bl8KtSRg.js +6 -0
- package/public/docs/assets/tuning-reference_bottleneck-spill.md.Bl8KtSRg.lean.js +1 -0
- package/public/docs/assets/tuning-reference_bottleneck-straggler.md.B0VN8reT.js +7 -0
- package/public/docs/assets/tuning-reference_bottleneck-straggler.md.B0VN8reT.lean.js +1 -0
- package/public/docs/assets/tuning-reference_bottleneck-tiny-tasks.md.DQCftGhu.js +8 -0
- package/public/docs/assets/tuning-reference_bottleneck-tiny-tasks.md.DQCftGhu.lean.js +1 -0
- package/public/docs/assets/{tuning-reference_bottleneck-utilization.md.DqC_iGkw.js → tuning-reference_bottleneck-utilization.md.BXDl30f9.js} +1 -1
- package/public/docs/assets/tuning-reference_bottleneck-utilization.md.BXDl30f9.lean.js +1 -0
- package/public/docs/assets/tuning-reference_caching.md.CcaiMn_7.js +1 -0
- package/public/docs/assets/tuning-reference_caching.md.CcaiMn_7.lean.js +1 -0
- package/public/docs/assets/tuning-reference_cluster-config.md.DbWG1yZq.js +1 -0
- package/public/docs/assets/tuning-reference_cluster-config.md.DbWG1yZq.lean.js +1 -0
- package/public/docs/assets/tuning-reference_config.md.YUqSpwFB.js +1 -0
- package/public/docs/assets/tuning-reference_config.md.YUqSpwFB.lean.js +1 -0
- package/public/docs/assets/tuning-reference_data-formats.md.C5DX5xL4.js +1 -0
- package/public/docs/assets/tuning-reference_data-formats.md.C5DX5xL4.lean.js +1 -0
- package/public/docs/assets/tuning-reference_index.md.ZVIpQ6Dk.js +1 -0
- package/public/docs/assets/tuning-reference_index.md.ZVIpQ6Dk.lean.js +1 -0
- package/public/docs/assets/tuning-reference_intro.md.BSSaDlqx.js +1 -0
- package/public/docs/assets/tuning-reference_intro.md.BSSaDlqx.lean.js +1 -0
- package/public/docs/assets/tuning-reference_joins.md.BVhNCDnE.js +1 -0
- package/public/docs/assets/tuning-reference_joins.md.BVhNCDnE.lean.js +1 -0
- package/public/docs/assets/tuning-reference_memory-model.md.CfjFdgbl.js +1 -0
- package/public/docs/assets/tuning-reference_memory-model.md.CfjFdgbl.lean.js +1 -0
- package/public/docs/assets/tuning-reference_metrics.md.C64VNEL4.js +1 -0
- package/public/docs/assets/tuning-reference_metrics.md.C64VNEL4.lean.js +1 -0
- package/public/docs/assets/tuning-reference_partitioning.md.CtLK0xsS.js +1 -0
- package/public/docs/assets/tuning-reference_partitioning.md.CtLK0xsS.lean.js +1 -0
- package/public/docs/assets/tuning-reference_pyspark.md.D-92XgF8.js +6 -0
- package/public/docs/assets/tuning-reference_pyspark.md.D-92XgF8.lean.js +1 -0
- package/public/docs/assets/tuning-reference_shuffle.md.Iq2v1oHJ.js +1 -0
- package/public/docs/assets/tuning-reference_shuffle.md.Iq2v1oHJ.lean.js +1 -0
- package/public/docs/assets/tuning-reference_spark-architecture.md._qwnE_Sc.js +1 -0
- package/public/docs/assets/tuning-reference_spark-architecture.md._qwnE_Sc.lean.js +1 -0
- package/public/docs/assets/tuning-reference_table-formats.md.BSYEK-eN.js +1 -0
- package/public/docs/assets/tuning-reference_table-formats.md.BSYEK-eN.lean.js +1 -0
- package/public/docs/assets/{user-guide_alternative-log-retrieval.md.B4tPGIal.js → user-guide_alternative-log-retrieval.md.ZHPSbBkF.js} +1 -1
- package/public/docs/assets/{user-guide_alternative-log-retrieval.md.B4tPGIal.lean.js → user-guide_alternative-log-retrieval.md.ZHPSbBkF.lean.js} +1 -1
- package/public/docs/assets/user-guide_getting-started.md.CEa2ZX-l.js +6 -0
- package/public/docs/assets/user-guide_getting-started.md.CEa2ZX-l.lean.js +1 -0
- package/public/docs/assets/{user-guide_mcp-tools.md.DGvolGzt.js → user-guide_mcp-tools.md.dQwIvdTF.js} +13 -7
- package/public/docs/assets/user-guide_mcp-tools.md.dQwIvdTF.lean.js +1 -0
- package/public/docs/assets/user-guide_run-comparison.md.ChLI3MK0.js +1 -0
- package/public/docs/assets/user-guide_run-comparison.md.ChLI3MK0.lean.js +1 -0
- package/public/docs/assets/user-guide_understanding-findings.md.D1ccs60C.js +1 -0
- package/public/docs/assets/{user-guide_understanding-findings.md.B29f0ucS.lean.js → user-guide_understanding-findings.md.D1ccs60C.lean.js} +1 -1
- package/public/docs/contributor-guide/architecture/board-widgets.html +5 -5
- package/public/docs/contributor-guide/architecture/detector-contract.html +5 -5
- package/public/docs/contributor-guide/architecture/drill-down.html +5 -5
- package/public/docs/contributor-guide/architecture/impact-estimation.html +5 -5
- package/public/docs/contributor-guide/architecture/index.html +3 -3
- package/public/docs/contributor-guide/architecture/overview.html +5 -5
- package/public/docs/contributor-guide/architecture/state-and-history.html +5 -5
- package/public/docs/contributor-guide/architecture/widget-rendering.html +5 -5
- package/public/docs/contributor-guide/architecture/worker-protocol.html +6 -6
- package/public/docs/contributor-guide/contributing.html +5 -5
- package/public/docs/contributor-guide/development-setup.html +13 -10
- package/public/docs/contributor-guide/testing.html +5 -5
- package/public/docs/hashmap.json +1 -1
- package/public/docs/index.html +3 -3
- package/public/docs/tuning-reference/anti-patterns.html +6 -6
- package/public/docs/tuning-reference/aqe.html +6 -6
- package/public/docs/tuning-reference/bottleneck-broadcast-sizing.html +6 -6
- package/public/docs/tuning-reference/bottleneck-cold-start.html +6 -6
- package/public/docs/tuning-reference/bottleneck-duplicate-plan-subtree.html +6 -6
- package/public/docs/tuning-reference/bottleneck-failures.html +6 -6
- package/public/docs/tuning-reference/bottleneck-gc.html +6 -6
- package/public/docs/tuning-reference/bottleneck-job-failure-rate.html +6 -6
- package/public/docs/tuning-reference/bottleneck-memory-utilization.html +6 -6
- package/public/docs/tuning-reference/bottleneck-retry-waste.html +6 -6
- package/public/docs/tuning-reference/bottleneck-shuffle.html +6 -6
- package/public/docs/tuning-reference/bottleneck-skew.html +6 -6
- package/public/docs/tuning-reference/bottleneck-slow-host.html +6 -6
- package/public/docs/tuning-reference/bottleneck-small-files.html +6 -6
- package/public/docs/tuning-reference/bottleneck-spill.html +6 -6
- package/public/docs/tuning-reference/bottleneck-straggler.html +6 -6
- package/public/docs/tuning-reference/bottleneck-tiny-tasks.html +6 -6
- package/public/docs/tuning-reference/bottleneck-utilization.html +6 -6
- package/public/docs/tuning-reference/caching.html +6 -6
- package/public/docs/tuning-reference/cluster-config.html +6 -6
- package/public/docs/tuning-reference/config.html +6 -6
- package/public/docs/tuning-reference/data-formats.html +6 -6
- package/public/docs/tuning-reference/index.html +6 -6
- package/public/docs/tuning-reference/intro.html +6 -6
- package/public/docs/tuning-reference/joins.html +6 -6
- package/public/docs/tuning-reference/memory-model.html +6 -6
- package/public/docs/tuning-reference/metrics.html +6 -6
- package/public/docs/tuning-reference/partitioning.html +6 -6
- package/public/docs/tuning-reference/pyspark.html +6 -6
- package/public/docs/tuning-reference/shuffle.html +6 -6
- package/public/docs/tuning-reference/spark-architecture.html +6 -6
- package/public/docs/tuning-reference/table-formats.html +6 -6
- package/public/docs/user-guide/alternative-log-retrieval.html +5 -5
- package/public/docs/user-guide/getting-started.html +9 -6
- package/public/docs/user-guide/mcp-tools.html +15 -9
- package/public/docs/user-guide/run-comparison.html +5 -5
- package/public/docs/user-guide/understanding-findings.html +5 -5
- package/public/export-template.html +111 -0
- package/public/index.html +4 -3
- package/vendor-core/analyzer.js +156 -48
- package/vendor-core/check-coverage.js +88 -0
- package/vendor-core/cli/budgets.js +31 -18
- package/vendor-core/cli/collect-run.js +76 -31
- package/vendor-core/cli/native-zstd.js +2 -2
- package/vendor-core/cli/threshold-config.js +28 -0
- package/vendor-core/comparison-verdict.js +177 -0
- package/vendor-core/core-source-hash.txt +1 -0
- package/vendor-core/core-usage-locality.js +56 -2
- package/vendor-core/detector-docs.js +58 -0
- package/vendor-core/detectors.js +933 -459
- package/vendor-core/docs-config.js +0 -36
- package/vendor-core/docs-content/chapters/nav-index.json +31 -0
- package/vendor-core/docs-content/detection/cstor.md +9 -0
- package/vendor-core/docs-content/detection/fail.md +6 -2
- package/vendor-core/docs-site-config.js +3 -0
- package/vendor-core/event-handlers.js +191 -6
- package/vendor-core/event-schemas.js +29 -0
- package/vendor-core/evidence-report.js +440 -112
- package/vendor-core/export-data.js +79 -6
- package/vendor-core/finding-action-label.js +9 -88
- package/vendor-core/finding-filter-predicate.js +9 -0
- package/vendor-core/finding-generic-recommendation.js +6 -104
- package/vendor-core/finding-names.js +21 -45
- package/vendor-core/finding-presentation.js +333 -0
- package/vendor-core/finding-tag-help.js +110 -0
- package/vendor-core/finding-types.js +361 -0
- package/vendor-core/findings-of-type.js +11 -0
- package/vendor-core/format-utils.js +92 -27
- package/vendor-core/html-export.js +51 -0
- package/vendor-core/impact-band.js +21 -8
- package/vendor-core/impact-estimator.js +8 -521
- package/vendor-core/impact-format.js +114 -0
- package/vendor-core/impact-model.js +175 -0
- package/vendor-core/ingest.js +2 -0
- package/vendor-core/intervals.js +13 -0
- package/vendor-core/list-runs.js +2 -3
- package/vendor-core/load-vendored.js +70 -5
- package/vendor-core/mcp-server-factory.js +14 -10
- package/vendor-core/mcp-tools.js +105 -45
- package/vendor-core/model-assembler.js +12 -0
- package/vendor-core/occupancy.js +1 -1
- package/vendor-core/parser-worker.js +22 -5
- package/vendor-core/plan-graph-model.js +3 -2
- package/vendor-core/plan-node-detail.js +1 -1
- package/vendor-core/recommendation-rollup.js +63 -3
- package/vendor-core/redact.js +68 -28
- package/vendor-core/run-comparison.js +40 -7
- package/vendor-core/run-interpretation.js +290 -0
- package/vendor-core/run-outcome.js +74 -0
- package/vendor-core/run-payload.js +17 -0
- package/vendor-core/run-shape.js +40 -0
- package/vendor-core/run-verdict.js +353 -0
- package/vendor-core/scaling-sim.js +4 -5
- package/vendor-core/scorecard-estimates.js +62 -0
- package/vendor-core/shs-fetch.js +175 -65
- package/vendor-core/shs-load.js +1 -1
- package/vendor-core/sql-stages.js +11 -0
- package/vendor-core/stage-quantiles.js +14 -0
- package/vendor-core/task-failure.js +151 -0
- package/vendor-core/threshold-overrides.js +160 -0
- package/vendor-core/threshold-summary.js +11 -33
- package/vendor-core/types.js +6 -42
- package/vendor-core/vendor/fflate.js +1 -1
- package/vendor-core/wall-clock.js +1 -12
- package/vendor-core/wasted-core-hours.js +2 -2
- package/vendor-core/zip-archive.js +167 -0
- package/public/assets/AutoscalingChurn-BOiUUfuY.js +0 -1
- package/public/assets/CacheUtilization-DwX7lisd.js +0 -1
- package/public/assets/CachingOpportunity-DUE3GKpx.js +0 -1
- package/public/assets/ColdStart-ZHxPrJmI.js +0 -1
- package/public/assets/ConfigAudit-BkVnq2XE.js +0 -1
- package/public/assets/CoreUsageArea-DobrSXk2.js +0 -1
- package/public/assets/Dashboard-y3_9iQJo.js +0 -1
- package/public/assets/DuplicatePlanSubtree-BSQZFeNq.js +0 -1
- package/public/assets/DurationHistogram-DlQv4ZCB.js +0 -1
- package/public/assets/EmptyState-DqnSxTjJ.js +0 -1
- package/public/assets/ExecutorUtilization-CuQUxaCd.js +0 -1
- package/public/assets/GcPressure-CLT5hkMJ.js +0 -1
- package/public/assets/ImpactEstimate-Df_laG-n.js +0 -1
- package/public/assets/IncompleteRun-CpIkS4XZ.js +0 -1
- package/public/assets/JobFailures-DKbvYc4J.js +0 -1
- package/public/assets/MemoryUtilization-C5kHmXIb.js +0 -1
- package/public/assets/OverBroadcast-C5pF66aq.js +0 -1
- package/public/assets/PartitionSizing-BvEJQ5M1.js +0 -1
- package/public/assets/PlanExplorer-DjGTZifP.js +0 -1
- package/public/assets/PlanGraphRoute-DoIGA7_H.js +0 -1
- package/public/assets/RetryWaste-C0znHd_w.js +0 -1
- package/public/assets/RowPagination-2icPidMP.js +0 -1
- package/public/assets/ShuffleIO-L_XSnJ_V.js +0 -1
- package/public/assets/Skew-w4uV5H_g.js +0 -1
- package/public/assets/SlowHost-D5tWJ1UR.js +0 -1
- package/public/assets/SmallFiles-CTtNiSOh.js +0 -1
- package/public/assets/SpeculationWaste-xCKwjz2K.js +0 -1
- package/public/assets/Spill-BT8my24K.js +0 -1
- package/public/assets/StageFailed-De3vVDbc.js +0 -1
- package/public/assets/StageFindingGroup-R4OW-g4U.js +0 -1
- package/public/assets/StageHeader-CGeWqC-0.js +0 -1
- package/public/assets/StagePill-BwwKLcFl.js +0 -1
- package/public/assets/StageShape-D4LmPVyV.js +0 -1
- package/public/assets/StageSlowness-8-z6qn4Q.js +0 -1
- package/public/assets/Straggler-BIgxsowI.js +0 -1
- package/public/assets/TaskFailures-B9lLt6Rw.js +0 -1
- package/public/assets/UnderBroadcast-BWqWMpeG.js +0 -1
- package/public/assets/WidgetLeadSummary-BdUUi7L5.js +0 -1
- package/public/assets/downsample-WmNM1qc9.js +0 -1
- package/public/assets/impact-sort-DxaUheWV.js +0 -1
- package/public/assets/inbox-M_EuWNiK.js +0 -1
- package/public/assets/index-CjVklAdW.css +0 -2
- package/public/assets/index-pnImGbgQ.js +0 -9
- package/public/assets/parser-worker-C3BAO6z9.js +0 -117
- package/public/assets/react-vendor-D2TLlSzI.js +0 -9
- package/public/assets/select-C-MZGNpb.js +0 -1
- package/public/assets/toggle-group-C3nz7UQ_.js +0 -1
- package/public/assets/usePagedRows-jNUWgVTD.js +0 -1
- package/public/assets/useRecentFiles-0XuhS91q.js +0 -11
- package/public/assets/useSortMode-DHlKZeWv.js +0 -1
- package/public/docs/assets/chunks/@localSearchIndexroot.BEfYag5Q.js +0 -1
- package/public/docs/assets/contributor-guide_architecture_detector-contract.md.aQQfP7pj.js +0 -1
- package/public/docs/assets/contributor-guide_architecture_drill-down.md.Bawx6NgP.js +0 -1
- package/public/docs/assets/contributor-guide_architecture_impact-estimation.md.sf9DU2bA.js +0 -1
- package/public/docs/assets/contributor-guide_architecture_overview.md.BXQdgG5u.js +0 -1
- package/public/docs/assets/contributor-guide_architecture_overview.md.BXQdgG5u.lean.js +0 -1
- package/public/docs/assets/contributor-guide_architecture_state-and-history.md.C-xxn0q7.js +0 -1
- package/public/docs/assets/contributor-guide_architecture_widget-rendering.md.DYwFeyjV.js +0 -1
- package/public/docs/assets/contributor-guide_architecture_worker-protocol.md.P7d1vtEJ.js +0 -6
- package/public/docs/assets/contributor-guide_architecture_worker-protocol.md.P7d1vtEJ.lean.js +0 -1
- package/public/docs/assets/contributor-guide_contributing.md.CvRsdr6J.js +0 -1
- package/public/docs/assets/contributor-guide_contributing.md.CvRsdr6J.lean.js +0 -1
- package/public/docs/assets/contributor-guide_development-setup.md.DvMV1xhQ.js +0 -12
- package/public/docs/assets/contributor-guide_testing.md.BU6vyA-9.js +0 -1
- package/public/docs/assets/contributor-guide_testing.md.BU6vyA-9.lean.js +0 -1
- package/public/docs/assets/tuning-reference_anti-patterns.md.Df1YMIHu.js +0 -1
- package/public/docs/assets/tuning-reference_anti-patterns.md.Df1YMIHu.lean.js +0 -1
- package/public/docs/assets/tuning-reference_aqe.md.BIsCtLzm.js +0 -1
- package/public/docs/assets/tuning-reference_aqe.md.BIsCtLzm.lean.js +0 -1
- package/public/docs/assets/tuning-reference_bottleneck-broadcast-sizing.md.CEstB3Ia.js +0 -1
- package/public/docs/assets/tuning-reference_bottleneck-broadcast-sizing.md.CEstB3Ia.lean.js +0 -1
- package/public/docs/assets/tuning-reference_bottleneck-cold-start.md.CEuy-72y.js +0 -7
- package/public/docs/assets/tuning-reference_bottleneck-cold-start.md.CEuy-72y.lean.js +0 -1
- package/public/docs/assets/tuning-reference_bottleneck-duplicate-plan-subtree.md.CIohQDfn.js +0 -1
- package/public/docs/assets/tuning-reference_bottleneck-duplicate-plan-subtree.md.CIohQDfn.lean.js +0 -1
- package/public/docs/assets/tuning-reference_bottleneck-failures.md.CAsFf3RR.lean.js +0 -1
- package/public/docs/assets/tuning-reference_bottleneck-gc.md.B4T3kJYV.js +0 -6
- package/public/docs/assets/tuning-reference_bottleneck-gc.md.B4T3kJYV.lean.js +0 -1
- package/public/docs/assets/tuning-reference_bottleneck-job-failure-rate.md.BaJl__1W.js +0 -8
- package/public/docs/assets/tuning-reference_bottleneck-job-failure-rate.md.BaJl__1W.lean.js +0 -1
- package/public/docs/assets/tuning-reference_bottleneck-memory-utilization.md.DbP-SJZc.js +0 -7
- package/public/docs/assets/tuning-reference_bottleneck-memory-utilization.md.DbP-SJZc.lean.js +0 -1
- package/public/docs/assets/tuning-reference_bottleneck-retry-waste.md.D5JMjVOt.js +0 -1
- package/public/docs/assets/tuning-reference_bottleneck-retry-waste.md.D5JMjVOt.lean.js +0 -1
- package/public/docs/assets/tuning-reference_bottleneck-shuffle.md.DDMQVOW6.lean.js +0 -1
- package/public/docs/assets/tuning-reference_bottleneck-skew.md.B0MzhWcX.lean.js +0 -1
- package/public/docs/assets/tuning-reference_bottleneck-slow-host.md.BlIo6UDW.lean.js +0 -1
- package/public/docs/assets/tuning-reference_bottleneck-small-files.md.DHGMTmPs.js +0 -5
- package/public/docs/assets/tuning-reference_bottleneck-small-files.md.DHGMTmPs.lean.js +0 -1
- package/public/docs/assets/tuning-reference_bottleneck-spill.md.PNH7mITt.js +0 -6
- package/public/docs/assets/tuning-reference_bottleneck-spill.md.PNH7mITt.lean.js +0 -1
- package/public/docs/assets/tuning-reference_bottleneck-straggler.md.DIbXdAcQ.js +0 -7
- package/public/docs/assets/tuning-reference_bottleneck-straggler.md.DIbXdAcQ.lean.js +0 -1
- package/public/docs/assets/tuning-reference_bottleneck-tiny-tasks.md.CB05v3zh.js +0 -8
- package/public/docs/assets/tuning-reference_bottleneck-tiny-tasks.md.CB05v3zh.lean.js +0 -1
- package/public/docs/assets/tuning-reference_bottleneck-utilization.md.DqC_iGkw.lean.js +0 -1
- package/public/docs/assets/tuning-reference_caching.md.B7aQ8asB.js +0 -1
- package/public/docs/assets/tuning-reference_caching.md.B7aQ8asB.lean.js +0 -1
- package/public/docs/assets/tuning-reference_cluster-config.md.CD6vzYtD.js +0 -1
- package/public/docs/assets/tuning-reference_cluster-config.md.CD6vzYtD.lean.js +0 -1
- package/public/docs/assets/tuning-reference_config.md.UvveiWG3.js +0 -1
- package/public/docs/assets/tuning-reference_config.md.UvveiWG3.lean.js +0 -1
- package/public/docs/assets/tuning-reference_data-formats.md.bjCAWH3N.js +0 -1
- package/public/docs/assets/tuning-reference_data-formats.md.bjCAWH3N.lean.js +0 -1
- package/public/docs/assets/tuning-reference_index.md.BQ_NooMV.js +0 -1
- package/public/docs/assets/tuning-reference_index.md.BQ_NooMV.lean.js +0 -1
- package/public/docs/assets/tuning-reference_intro.md.CobD-lGB.js +0 -1
- package/public/docs/assets/tuning-reference_intro.md.CobD-lGB.lean.js +0 -1
- package/public/docs/assets/tuning-reference_joins.md.BtKs_CuW.js +0 -1
- package/public/docs/assets/tuning-reference_joins.md.BtKs_CuW.lean.js +0 -1
- package/public/docs/assets/tuning-reference_memory-model.md.CWhvgevP.js +0 -1
- package/public/docs/assets/tuning-reference_memory-model.md.CWhvgevP.lean.js +0 -1
- package/public/docs/assets/tuning-reference_metrics.md.mLOh7Apj.js +0 -1
- package/public/docs/assets/tuning-reference_metrics.md.mLOh7Apj.lean.js +0 -1
- package/public/docs/assets/tuning-reference_partitioning.md.q0zKF_8X.js +0 -1
- package/public/docs/assets/tuning-reference_partitioning.md.q0zKF_8X.lean.js +0 -1
- package/public/docs/assets/tuning-reference_pyspark.md.DDCfvN9t.js +0 -6
- package/public/docs/assets/tuning-reference_pyspark.md.DDCfvN9t.lean.js +0 -1
- package/public/docs/assets/tuning-reference_shuffle.md.BZZ7R4Ix.js +0 -1
- package/public/docs/assets/tuning-reference_shuffle.md.BZZ7R4Ix.lean.js +0 -1
- package/public/docs/assets/tuning-reference_spark-architecture.md.Dwzm5avO.js +0 -1
- package/public/docs/assets/tuning-reference_spark-architecture.md.Dwzm5avO.lean.js +0 -1
- package/public/docs/assets/tuning-reference_table-formats.md.D6wj-2dX.js +0 -1
- package/public/docs/assets/tuning-reference_table-formats.md.D6wj-2dX.lean.js +0 -1
- package/public/docs/assets/user-guide_getting-started.md.BJvwLEIM.js +0 -3
- package/public/docs/assets/user-guide_getting-started.md.BJvwLEIM.lean.js +0 -1
- package/public/docs/assets/user-guide_mcp-tools.md.DGvolGzt.lean.js +0 -1
- package/public/docs/assets/user-guide_run-comparison.md.CQc1aoU8.js +0 -1
- package/public/docs/assets/user-guide_run-comparison.md.CQc1aoU8.lean.js +0 -1
- package/public/docs/assets/user-guide_understanding-findings.md.B29f0ucS.js +0 -1
- /package/public/docs/assets/{contributor-guide_architecture_board-widgets.md.9ToZXcTk.lean.js → contributor-guide_architecture_board-widgets.md.VTcYTH4d.lean.js} +0 -0
|
@@ -9,11 +9,11 @@
|
|
|
9
9
|
<link rel="preload stylesheet" href="/docs/assets/style.DSixAiZE.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.
|
|
12
|
+
<script type="module" src="/docs/assets/app.C6w47a9W.js"></script>
|
|
13
13
|
<link rel="preload" href="/docs/assets/inter-roman-latin.Di8DUHzh.woff2" as="font" type="font/woff2" crossorigin="">
|
|
14
|
-
<link rel="modulepreload" href="/docs/assets/chunks/theme.
|
|
14
|
+
<link rel="modulepreload" href="/docs/assets/chunks/theme.D-mE6j02.js">
|
|
15
15
|
<link rel="modulepreload" href="/docs/assets/chunks/framework.DSg0KOwT.js">
|
|
16
|
-
<link rel="modulepreload" href="/docs/assets/contributor-guide_testing.md.
|
|
16
|
+
<link rel="modulepreload" href="/docs/assets/contributor-guide_testing.md.DTwhpoN2.lean.js">
|
|
17
17
|
<link rel="icon" type="image/svg+xml" href="/docs/favicon.svg">
|
|
18
18
|
<link rel="preconnect" href="https://fonts.googleapis.com">
|
|
19
19
|
<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin="">
|
|
@@ -22,8 +22,8 @@
|
|
|
22
22
|
<script id="check-mac-os">document.documentElement.classList.toggle("mac",/Mac|iPhone|iPod|iPad/i.test(navigator.platform));</script>
|
|
23
23
|
</head>
|
|
24
24
|
<body>
|
|
25
|
-
<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>Contributor Guide</h2><!----></div><div class="items" data-v-b3fd67f8><!--[--><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/contributor-guide/development-setup.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Development setup</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/contributor-guide/architecture/" data-v-b3fd67f8><!--[--><h3 class="text" data-v-b3fd67f8>Architecture</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/contributor-guide/architecture/overview.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Overview</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/contributor-guide/architecture/worker-protocol.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Worker protocol</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/contributor-guide/architecture/state-and-history.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>State & history intake</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/contributor-guide/architecture/detector-contract.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Detector contract</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/contributor-guide/architecture/impact-estimation.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Impact estimation</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/contributor-guide/architecture/widget-rendering.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Widget rendering</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/contributor-guide/architecture/board-widgets.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Board widgets</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/contributor-guide/architecture/drill-down.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Drill-down</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/contributor-guide/testing.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Testing & verification</p><!--]--></a><!----></div><!----></div><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/contributor-guide/contributing.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Contributing</p><!--]--></a><!----></div><!----></div><!--]--></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_contributor-guide_testing" data-v-39a288b8><div><h1 id="testing-verification" tabindex="-1">Testing & verification <a class="header-anchor" href="#testing-verification" aria-label="Permalink to "Testing & verification""></a></h1><p>Before opening a PR:</p><ol><li>Run the full suite: <code>npm test</code> (root) and, if you touched <code>server/</code>, <code>npm run test:server</code> too: it's a separate package with its own dependencies, not covered by the root suite.</li><li>Typecheck: <code>npx tsc --noEmit</code>.</li><li>Lint: <code>npm run lint</code>. This also runs automatically on every commit via <code>.githooks/pre-commit</code>, but run it yourself so you catch failures before committing.</li><li>For any UI change, verify it in a real browser (Playwright or headless Chrome). Unit and jsdom tests check code correctness; they don't prove a feature works end-to-end. Drive the app, exercise the golden path and the edge cases, and look for regressions elsewhere on the dashboard.</li><li>Report the passing test count when you're done, not "tests pass."</li></ol><p>Sample Spark event logs for manual testing live outside this repo. Keep them in a sibling <code>../spark-log-examples/</code> directory: real <code>.zstd</code> event logs plus baseline/candidate pairs for run comparison.</p><h2 id="testing-layout" tabindex="-1">Testing layout <a class="header-anchor" href="#testing-layout" aria-label="Permalink to "Testing layout""></a></h2><p>Vitest throughout, two environments in one run. Core logic tests (<code>tests/*.test.js</code>, covering parser, analyzer, detectors, format-utils, etc.) run under Node. View tests (<code>tests/view/*.test.tsx</code>) declare <code>// @vitest-environment jsdom</code> and use React Testing Library (<code>render</code>/<code>screen</code>/<code>userEvent</code>). There are no hand-rolled DOM-mounting jsdom tests left: the old <code>tests/widgets/*.test.js</code> suite called <code>src/widgets/*.js</code>'s <code>renderX(mount, ...)</code> functions directly, and every behavior it covered now has an RTL equivalent.</p><p><code>server/</code> is a separate npm package with its own Vitest config and <code>npm test</code>, not run by the root suite. One test there, <code>server/test/bin.test.js</code>, packs and installs the real published tarball and spawns the real <code>.bin</code> entry point: the only test that exercises the production build end-to-end.</p><p>Two contract tests guard invariants that a future edit could silently break. The "detector contract" suite in <code>tests/analyzer.test.js</code> asserts <code>stageSlowness</code> stays array-index-after <code>slowHost</code> in <code>DETECTORS</code> (see <a href="./architecture/detector-contract.html#detector-contract">Detector contract</a>). <code>tests/view/detector-registry.test.tsx</code> asserts <code>REGISTRY</code> completeness against every <code>DETECTORS</code> type, including the <code>underBroadcast</code>/<code>overBroadcast</code> correction: <code>broadcastSizing</code> itself is never an emitted <code>finding.type</code>, as the doc comment above <code>REGISTRY</code> in <code>src/view/detector-registry.tsx</code> explains.</p><h2 id="test-fixtures" tabindex="-1">Test fixtures <a class="header-anchor" href="#test-fixtures" aria-label="Permalink to "Test fixtures""></a></h2><p>Real Spark event logs from private workloads live under <code>examples/</code>, gitignored: they're large, and their file names and contents identify the jobs that produced them, so they never enter this public repo. Tests, docs and scripts refer to them only by the neutral labels below. A test that reads one skips when its file is missing, so the suite passes without any of them. To run those tests, copy or symlink your own logs into <code>examples/</code> under these names:</p><table tabindex="0"><thead><tr><th>Label</th><th>Log it stands for</th><th>Used by</th></tr></thead><tbody><tr><td><code>private-log-01.zstd</code></td><td>~12 MB zstd run with Plan Advisor findings</td><td><code>impact-estimator-real-log.test.js</code>, <code>plan-node-stage-mapping-real-log.test.js</code>, spot-checks in <a href="./architecture/impact-estimation.html">Impact estimation</a></td></tr><tr><td><code>private-log-02.zstd</code></td><td>~2 MB zstd run with a heavy shuffle-and-spill stage</td><td><code>plan-node-stage-mapping-real-log.test.js</code>, spot-checks in <a href="./architecture/impact-estimation.html">Impact estimation</a></td></tr><tr><td><code>private-log-03.zstd</code></td><td>~28 MB zstd run with about 1,200 stages</td><td>timing spot-check in <a href="./architecture/impact-estimation.html">Impact estimation</a></td></tr><tr><td><code>private-log-04.zstd</code></td><td>~9 MB zstd run whose stage 394 plan became <code>plan-graph-stage-394.json</code></td><td><code>scripts/extract-plan-fixture.mjs</code></td></tr><tr><td><code>private-log-05</code></td><td>~76 MB uncompressed NDJSON run, 62 stages</td><td><code>parser-worker.test.js</code>; also a fast end-to-end smoke test</td></tr><tr><td><code>private-log-06</code></td><td>~1.3 GB uncompressed NDJSON run</td><td><code>detectors-plan.test.js</code>; also a stress test for the Web Worker streaming path</td></tr><tr><td><code>private-log-07</code></td><td>~120 MB log from a Spark History Server download</td><td>none: check the <code>LZ4Block</code> codec decoder by hand; <code>tests/lz4-block.test.js</code> uses a small hardcoded byte array instead</td></tr></tbody></table><p><code>scripts/extract-plan-fixture.mjs</code> anonymizes every table, column, path and literal before it writes the committed fixture; keep it that way if you extract another one.</p><p>Of the finding types moved onto the Gold Standard row/expand contract in the widget-gold-standard plan, only <code>retryWaste</code> and <code>autoscalingChurn</code> fire on any of the 15 real logs in <code>../spark-log-examples/</code>. <code>failures</code>, <code>stageFailed</code>, and <code>jobFailureRate</code> fire on none of them; they were verified with unit tests only (<code>tests/view/failures.test.tsx</code>, <code>tests/view/job-failures.test.tsx</code>), not against a real log.</p><p><code>dev/log-corpus/</code> is a git submodule pointing at the public <code>spark-event-corpus-data</code> repo, pinned to a tag. It backs <code>packages/server/test/shs-proxy-fixture.test.js</code>, which loads a real <code>*-parquet-baseline.ndjson</code> fixture and asserts the <code>/shs-proxy</code> route streams it back unmodified. Populate it locally with <code>git submodule update --init dev/log-corpus</code>; without it, the test suite skips (see <a href="./development-setup.html">Development setup</a>).</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/contributor-guide/architecture/drill-down.html" data-v-e257564d><!--[--><span class="desc" data-v-e257564d>Previous page</span><span class="title" data-v-e257564d>Drill-down</span><!--]--></a></div><div class="pager" data-v-e257564d><a class="VPLink link pager-link next" href="/docs/contributor-guide/contributing.html" data-v-e257564d><!--[--><span class="desc" data-v-e257564d>Next page</span><span class="title" data-v-e257564d>Contributing</span><!--]--></a></div></nav></footer><!--[--><!--]--></div></div></div><!--[--><!--]--></div></div><!----><!--[--><!--]--></div></div>
|
|
26
|
-
<script>window.__VP_HASH_MAP__=JSON.parse("{\"contributor-guide_architecture_board-widgets.md\":\"
|
|
25
|
+
<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>Contributor Guide</h2><!----></div><div class="items" data-v-b3fd67f8><!--[--><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/contributor-guide/development-setup.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Development setup</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/contributor-guide/architecture/" data-v-b3fd67f8><!--[--><h3 class="text" data-v-b3fd67f8>Architecture</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/contributor-guide/architecture/overview.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Overview</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/contributor-guide/architecture/worker-protocol.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Worker protocol</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/contributor-guide/architecture/state-and-history.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>State & history intake</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/contributor-guide/architecture/detector-contract.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Detector contract</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/contributor-guide/architecture/impact-estimation.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Impact estimation</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/contributor-guide/architecture/widget-rendering.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Widget rendering</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/contributor-guide/architecture/board-widgets.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Board widgets</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/contributor-guide/architecture/drill-down.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Drill-down</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/contributor-guide/testing.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Testing & verification</p><!--]--></a><!----></div><!----></div><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/contributor-guide/contributing.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Contributing</p><!--]--></a><!----></div><!----></div><!--]--></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_contributor-guide_testing" data-v-39a288b8><div><h1 id="testing-verification" tabindex="-1">Testing & verification <a class="header-anchor" href="#testing-verification" aria-label="Permalink to "Testing & verification""></a></h1><p>Before opening a PR:</p><ol><li>Run the full suite: <code>npm test</code> (root), plus <code>npm run test:core</code>, <code>npm run test:cli</code>, <code>npm run test:mcp</code> and <code>npm run test:server</code> for the packages you touched. Each of those four packages has its own Vitest config and suite, none of them covered by the root <code>npm test</code>.</li><li>Typecheck: <code>npx tsc --noEmit</code>.</li><li>Lint: <code>npm run lint</code>. This also runs automatically on every commit via <code>.githooks/pre-commit</code>, but run it yourself so you catch failures before committing.</li><li>For any UI change, verify it in a real browser (Playwright or headless Chrome). Unit and jsdom tests check code correctness; they don't prove a feature works end-to-end. Drive the app, exercise the golden path and the edge cases, and look for regressions elsewhere on the dashboard.</li><li>Report the passing test count when you're done, not "tests pass."</li></ol><p>Sample Spark event logs for manual testing live outside this repo. Keep them in a sibling <code>../spark-log-examples/</code> directory: real <code>.zstd</code> event logs plus several <code>run-compare-*-baseline-*</code>/<code>run-compare-*-candidate-*</code> pairs for run comparison. They are private and this repo is public: never put their file names, app IDs, app names, tables or paths in tracked files, commits or PR text. Use the neutral <code>private-log-NN</code> labels under <a href="#test-fixtures">Test fixtures</a>, and synthetic IDs such as <code>application_0000000000000_0001</code>.</p><h2 id="testing-layout" tabindex="-1">Testing layout <a class="header-anchor" href="#testing-layout" aria-label="Permalink to "Testing layout""></a></h2><p>Vitest throughout. Core logic tests (<code>packages/core/test/*.test.js</code>, covering parser, analyzer, detectors, format-utils, etc.) run under Node via <code>npm run test:core</code>. The root <code>npm test</code> runs two environments in one run: root-level tooling tests (<code>tests/*.test.js</code>) under Node, and view tests (<code>tests/view/*.test.tsx</code>), which declare <code>// @vitest-environment jsdom</code> and use React Testing Library (<code>render</code>/<code>screen</code>/<code>userEvent</code>). There are no hand-rolled DOM-mounting jsdom tests left: the old <code>tests/widgets/*.test.js</code> suite called <code>src/widgets/*.js</code>'s <code>renderX(mount, ...)</code> functions directly, and every behavior it covered now has an RTL equivalent.</p><p><code>packages/cli</code>, <code>packages/mcp</code> and <code>packages/server</code> are separate npm packages, each with its own Vitest config and suite, not run by the root suite. Each has a pack-and-spawn test (for example <code>packages/server/test/bin.test.js</code>) that packs and installs the real published tarball and spawns the real <code>.bin</code> entry point, exercising the production build end-to-end.</p><p>Two contract tests guard invariants that a future edit could silently break. The "detector contract" suite in <code>packages/core/test/analyzer.test.js</code> asserts <code>stageSlowness</code> stays array-index-after <code>slowHost</code> in <code>DETECTORS</code> (see <a href="./architecture/detector-contract.html#detector-contract">Detector contract</a>). <code>REGISTRY</code> and <code>FINDING_PRESENTATION</code> completeness is a compile-time check, not a test: both are typed against the emitted <code>FindingType</code> union, so <code>npx tsc --noEmit</code> fails on a missing or extra key (see <a href="./architecture/detector-contract.html#detector-contract">Detector contract</a>).</p><h2 id="test-fixtures" tabindex="-1">Test fixtures <a class="header-anchor" href="#test-fixtures" aria-label="Permalink to "Test fixtures""></a></h2><p>Real Spark event logs from private workloads live under <code>examples/</code>, gitignored: they're large, and their file names and contents identify the jobs that produced them, so they never enter this public repo. Tests, docs and scripts refer to them only by the neutral labels below. A test that reads one skips when its file is missing, so the suite passes without any of them. To run those tests, copy or symlink your own logs into <code>examples/</code> under these names:</p><table tabindex="0"><thead><tr><th>Label</th><th>Log it stands for</th><th>Used by</th></tr></thead><tbody><tr><td><code>private-log-01.zstd</code></td><td>~12 MB zstd run with Plan Advisor findings</td><td><code>impact-estimator-real-log.test.js</code>, <code>plan-node-stage-mapping-real-log.test.js</code>, spot-checks in <a href="./architecture/impact-estimation.html">Impact estimation</a></td></tr><tr><td><code>private-log-02.zstd</code></td><td>~2 MB zstd run with a heavy shuffle-and-spill stage</td><td><code>plan-node-stage-mapping-real-log.test.js</code>, spot-checks in <a href="./architecture/impact-estimation.html">Impact estimation</a></td></tr><tr><td><code>private-log-03.zstd</code></td><td>~28 MB zstd run with about 1,200 stages</td><td>timing spot-check in <a href="./architecture/impact-estimation.html">Impact estimation</a></td></tr><tr><td><code>private-log-04.zstd</code></td><td>~9 MB zstd run whose stage 394 plan became <code>plan-graph-stage-394.json</code></td><td><code>scripts/extract-plan-fixture.mjs</code></td></tr><tr><td><code>private-log-05</code></td><td>~76 MB uncompressed NDJSON run, 62 stages</td><td><code>parser-worker.test.js</code>; also a fast end-to-end smoke test</td></tr><tr><td><code>private-log-06</code></td><td>~1.3 GB uncompressed NDJSON run</td><td><code>detectors-plan.test.js</code>; also a stress test for the Web Worker streaming path</td></tr><tr><td><code>private-log-07</code></td><td>~120 MB log from a Spark History Server download</td><td>none: check the <code>LZ4Block</code> codec decoder by hand; <code>packages/core/test/lz4-block.test.js</code> uses a small hardcoded byte array instead</td></tr></tbody></table><p><code>scripts/extract-plan-fixture.mjs</code> anonymizes every table, column, path and literal before it writes the committed fixture; keep it that way if you extract another one.</p><p>Of the finding types moved onto the Gold Standard row/expand contract in the widget-gold-standard plan, only <code>retryWaste</code> and <code>autoscalingChurn</code> fire on any of the 15 real logs in <code>../spark-log-examples/</code>. <code>failures</code>, <code>stageFailed</code>, and <code>jobFailureRate</code> fire on none of them; they were verified with unit tests only (<code>tests/view/task-failures.test.tsx</code>, <code>tests/view/stage-failed.test.tsx</code>, <code>tests/view/job-failures.test.tsx</code>), not against a real log.</p><p><code>dev/log-corpus/</code> is a git submodule pointing at the public <code>spark-event-corpus-data</code> repo, pinned to a tag. It backs <code>packages/server/test/shs-proxy-fixture.test.js</code>, which loads a real <code>*-parquet-baseline.ndjson</code> fixture and asserts the <code>/shs-proxy</code> route streams it back unmodified. Populate it locally with <code>git submodule update --init dev/log-corpus</code>; without it, the test suite skips (see <a href="./development-setup.html">Development setup</a>). CI checks it out, so these tests run there.</p><h3 id="corpus-regression-snapshot" tabindex="-1">Corpus regression snapshot <a class="header-anchor" href="#corpus-regression-snapshot" aria-label="Permalink to "Corpus regression snapshot""></a></h3><p><code>dev/corpus-snapshot.json</code> records every finding (type, location, band, confidence, value, impact estimate) that the detectors produce on each public corpus log, plus its stage, SQL execution and skipped-line counts, with timings and memory left out so it is deterministic. CI's <code>core</code> job re-analyzes the corpus and fails on any difference, printing the added, removed, re-banded and re-estimated findings and changed counts per log:</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;">node</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;"> dev/bench-analyze.mjs</span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;"> --check</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;"> dev/corpus-snapshot.json</span></span></code></pre></div><p>When a detector, threshold or estimator change is meant to alter findings, read that diff, confirm each change is the one you intended, then refresh the snapshot and commit it with the change:</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;">node</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;"> dev/bench-analyze.mjs</span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;"> --update</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;"> dev/corpus-snapshot.json</span></span></code></pre></div><p>Both default to <code>dev/log-corpus/logs</code> and its <code>external/</code> folder. Only public corpus logs belong in the snapshot: never pass private logs to <code>--update</code>.</p><h3 id="detector-and-estimate-tools" tabindex="-1">Detector and estimate tools <a class="header-anchor" href="#detector-and-estimate-tools" aria-label="Permalink to "Detector and estimate tools""></a></h3><p>Record before and after numbers from these in the commit that changes a detector, threshold, estimate or the vendored fzstd.</p><ul><li><code>node dev/bench-analyze.mjs [--repeat N] --out snap.json <file|dir>...</code> snapshots every finding (band, estimate) plus parse and analyze timings, one child process per log. <code>--diff a.json b.json [--verbose]</code> shows the findings added, removed or re-banded between two snapshots.</li><li><code>node --max-old-space-size=12000 dev/eval-tail-replay.mjs [--set detector.threshold=value] [--verbose] <file|dir>...</code> scores skew and straggler against a task-level replay (precision, recall, estimate error). <code>--verbose</code> lists each miss, false positive and estimate more than 2x off.</li><li><code>node dev/fuzz-fzstd.mjs --upstream <pristine fzstd esm/index.mjs> <log.zstd>...</code> checks the locally patched <code>packages/core/src/vendor/fzstd.js</code> against upstream, on whole logs and on randomly corrupted prefixes. Run it after any fzstd edit.</li></ul><p>CI also runs a <code>node18</code> job, because the published <code>cli</code>, <code>mcp</code> and <code>server</code> packages declare <code>engines.node >=18</code> while vitest needs Node 22+. It packs the three tarballs on <code>.nvmrc</code>'s Node, installs them on Node 18, runs the CLI over every corpus log plus a zstd copy of one, checks that the MCP server answers <code>initialize</code>, and starts <code>sparkforensics-server</code> to check it serves the app and answers <code>initialize</code> on <code>/mcp</code>.</p><h2 id="test-suite-growth-discipline" tabindex="-1">Test-suite growth discipline <a class="header-anchor" href="#test-suite-growth-discipline" aria-label="Permalink to "Test-suite growth discipline""></a></h2><p>Widget and detector test files collect copy-pasted boilerplate fast (a 2026-09 pass trimmed 19 files by a net 272 lines with no behavior change). Before adding a widget test file, or a per-widget or per-detector test:</p><ul><li>Cross-cutting widget behavior (impact/stage sort-toggle default and flip, density-gated visibility, 6-at-a-time pagination) belongs in a shared helper under <code>tests/view/_shared/</code>, called from each widget's test file. Extract into it only when a test body is identical to an existing one apart from the widget name, fixture or label. A widget with a real difference (a <code>React.lazy</code>-loaded chunk, a custom row finder) keeps its own test.</li><li><code>packages/core/test/fixtures/</code> holds the shared stage and app fixture factories (<code>makeStage</code>/<code>makeApp</code>). Import them instead of pasting a local copy into a new core test file.</li><li>Before adding a small test file, check whether a sibling file's <code>describe</code> block already covers that surface. A detector-catalog shape check, for example, belongs in <code>analyzer.test.js</code>'s <code>detector contract</code> block.</li><li>Calling an exported pure function directly, or calling the documented event reducer (<code>processEvent</code> in <code>parser-worker.ts</code>, see the <a href="./architecture/worker-protocol.html">worker protocol</a>) with one event and inspecting the state, is normal unit testing. Don't rewrite reducer-style tests into NDJSON-through-<code>runParse</code> integration tests to avoid touching internals: that costs readability for no real safety.</li></ul></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/contributor-guide/architecture/drill-down.html" data-v-e257564d><!--[--><span class="desc" data-v-e257564d>Previous page</span><span class="title" data-v-e257564d>Drill-down</span><!--]--></a></div><div class="pager" data-v-e257564d><a class="VPLink link pager-link next" href="/docs/contributor-guide/contributing.html" data-v-e257564d><!--[--><span class="desc" data-v-e257564d>Next page</span><span class="title" data-v-e257564d>Contributing</span><!--]--></a></div></nav></footer><!--[--><!--]--></div></div></div><!--[--><!--]--></div></div><!----><!--[--><!--]--></div></div>
|
|
26
|
+
<script>window.__VP_HASH_MAP__=JSON.parse("{\"contributor-guide_architecture_board-widgets.md\":\"VTcYTH4d\",\"contributor-guide_architecture_detector-contract.md\":\"CsqZHz_T\",\"contributor-guide_architecture_drill-down.md\":\"CFNCE8JB\",\"contributor-guide_architecture_impact-estimation.md\":\"HT9IJGIl\",\"contributor-guide_architecture_index.md\":\"3TO9ic6w\",\"contributor-guide_architecture_overview.md\":\"CTEqVeV4\",\"contributor-guide_architecture_state-and-history.md\":\"DOTVHjTV\",\"contributor-guide_architecture_widget-rendering.md\":\"BmpARZve\",\"contributor-guide_architecture_worker-protocol.md\":\"21pTYhFF\",\"contributor-guide_contributing.md\":\"B2E9ni79\",\"contributor-guide_development-setup.md\":\"CjgZJwjK\",\"contributor-guide_testing.md\":\"DTwhpoN2\",\"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\":\"ZHPSbBkF\",\"user-guide_getting-started.md\":\"CEa2ZX-l\",\"user-guide_mcp-tools.md\":\"dQwIvdTF\",\"user-guide_run-comparison.md\":\"ChLI3MK0\",\"user-guide_understanding-findings.md\":\"D1ccs60C\"}");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\"},{\"text\":\"Understanding findings\",\"link\":\"/user-guide/understanding-findings\"},{\"text\":\"Run comparison mode\",\"link\":\"/user-guide/run-comparison\"},{\"text\":\"MCP tools reference\",\"link\":\"/user-guide/mcp-tools\"},{\"text\":\"Alternative log retrieval\",\"link\":\"/user-guide/alternative-log-retrieval\"}]}],\"/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\"},{\"text\":\"State & history intake\",\"link\":\"/contributor-guide/architecture/state-and-history\"},{\"text\":\"Detector contract\",\"link\":\"/contributor-guide/architecture/detector-contract\"},{\"text\":\"Impact estimation\",\"link\":\"/contributor-guide/architecture/impact-estimation\"},{\"text\":\"Widget rendering\",\"link\":\"/contributor-guide/architecture/widget-rendering\"},{\"text\":\"Board widgets\",\"link\":\"/contributor-guide/architecture/board-widgets\"},{\"text\":\"Drill-down\",\"link\":\"/contributor-guide/architecture/drill-down\"}]},{\"text\":\"Testing & verification\",\"link\":\"/contributor-guide/testing\"},{\"text\":\"Contributing\",\"link\":\"/contributor-guide/contributing\"}]}]},\"search\":{\"provider\":\"local\"}},\"locales\":{},\"scrollOffset\":134,\"cleanUrls\":false}");</script>
|
|
27
27
|
|
|
28
28
|
</body>
|
|
29
29
|
</html>
|
package/public/docs/hashmap.json
CHANGED
|
@@ -1 +1 @@
|
|
|
1
|
-
{"contributor-guide_architecture_board-widgets.md":"
|
|
1
|
+
{"contributor-guide_architecture_board-widgets.md":"VTcYTH4d","contributor-guide_architecture_detector-contract.md":"CsqZHz_T","contributor-guide_architecture_drill-down.md":"CFNCE8JB","contributor-guide_architecture_impact-estimation.md":"HT9IJGIl","contributor-guide_architecture_index.md":"3TO9ic6w","contributor-guide_architecture_overview.md":"CTEqVeV4","contributor-guide_architecture_state-and-history.md":"DOTVHjTV","contributor-guide_architecture_widget-rendering.md":"BmpARZve","contributor-guide_architecture_worker-protocol.md":"21pTYhFF","contributor-guide_contributing.md":"B2E9ni79","contributor-guide_development-setup.md":"CjgZJwjK","contributor-guide_testing.md":"DTwhpoN2","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":"ZHPSbBkF","user-guide_getting-started.md":"CEa2ZX-l","user-guide_mcp-tools.md":"dQwIvdTF","user-guide_run-comparison.md":"ChLI3MK0","user-guide_understanding-findings.md":"D1ccs60C"}
|
package/public/docs/index.html
CHANGED
|
@@ -9,9 +9,9 @@
|
|
|
9
9
|
<link rel="preload stylesheet" href="/docs/assets/style.DSixAiZE.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.
|
|
12
|
+
<script type="module" src="/docs/assets/app.C6w47a9W.js"></script>
|
|
13
13
|
<link rel="preload" href="/docs/assets/inter-roman-latin.Di8DUHzh.woff2" as="font" type="font/woff2" crossorigin="">
|
|
14
|
-
<link rel="modulepreload" href="/docs/assets/chunks/theme.
|
|
14
|
+
<link rel="modulepreload" href="/docs/assets/chunks/theme.D-mE6j02.js">
|
|
15
15
|
<link rel="modulepreload" href="/docs/assets/chunks/framework.DSg0KOwT.js">
|
|
16
16
|
<link rel="modulepreload" href="/docs/assets/index.md.CHJVslga.lean.js">
|
|
17
17
|
<link rel="icon" type="image/svg+xml" href="/docs/favicon.svg">
|
|
@@ -23,7 +23,7 @@
|
|
|
23
23
|
</head>
|
|
24
24
|
<body>
|
|
25
25
|
<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" 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="VPContent is-home" id="VPContent" data-v-5d98c3a5 data-v-1428d186><div class="VPHome" data-v-1428d186 data-v-8b561e3d><!--[--><!--]--><div class="VPHero VPHomeHero" data-v-8b561e3d data-v-4f9c455b><div class="container" data-v-4f9c455b><div class="main" data-v-4f9c455b><!--[--><!--]--><!--[--><h1 class="heading" data-v-4f9c455b><span class="name clip" data-v-4f9c455b>SparkForensics</span><span class="text" data-v-4f9c455b>Docs</span></h1><p class="tagline" data-v-4f9c455b>Find out why your Spark job is slow, ranked by which fix saves the most time.</p><!--]--><!--[--><!--]--><!----><!--[--><!--]--></div><!----></div></div><!--[--><!--]--><!--[--><!--]--><div class="VPFeatures VPHomeFeatures" data-v-8b561e3d data-v-a6181336><div class="container" data-v-a6181336><div class="items" data-v-a6181336><!--[--><div class="grid-2 item" data-v-a6181336><a class="VPLink link no-icon VPFeature" href="/docs/user-guide/getting-started.html" data-v-a6181336 data-v-a3976bdc><!--[--><article class="box" data-v-a3976bdc><!----><h2 class="title" data-v-a3976bdc>User Guide</h2><p class="details" data-v-a3976bdc>Load a run, read the findings, compare two runs, use the MCP tools.</p><div class="link-text" data-v-a3976bdc><p class="link-text-value" data-v-a3976bdc>Get started <span class="vpi-arrow-right link-text-icon" data-v-a3976bdc></span></p></div></article><!--]--></a></div><div class="grid-2 item" data-v-a6181336><a class="VPLink link no-icon VPFeature" href="/docs/contributor-guide/development-setup.html" data-v-a6181336 data-v-a3976bdc><!--[--><article class="box" data-v-a3976bdc><!----><h2 class="title" data-v-a3976bdc>Contributor Guide</h2><p class="details" data-v-a3976bdc>Set up the project, read the architecture, run the tests, propose a change.</p><div class="link-text" data-v-a3976bdc><p class="link-text-value" data-v-a3976bdc>Start contributing <span class="vpi-arrow-right link-text-icon" data-v-a3976bdc></span></p></div></article><!--]--></a></div><!--]--></div></div></div><!--[--><!--]--><div class="vp-doc container" style="" data-v-8b561e3d data-v-8e2d4988><!--[--><div style="position:relative;" data-v-8b561e3d><div></div></div><!--]--></div></div></div><!----><!--[--><!--]--></div></div>
|
|
26
|
-
<script>window.__VP_HASH_MAP__=JSON.parse("{\"contributor-guide_architecture_board-widgets.md\":\"
|
|
26
|
+
<script>window.__VP_HASH_MAP__=JSON.parse("{\"contributor-guide_architecture_board-widgets.md\":\"VTcYTH4d\",\"contributor-guide_architecture_detector-contract.md\":\"CsqZHz_T\",\"contributor-guide_architecture_drill-down.md\":\"CFNCE8JB\",\"contributor-guide_architecture_impact-estimation.md\":\"HT9IJGIl\",\"contributor-guide_architecture_index.md\":\"3TO9ic6w\",\"contributor-guide_architecture_overview.md\":\"CTEqVeV4\",\"contributor-guide_architecture_state-and-history.md\":\"DOTVHjTV\",\"contributor-guide_architecture_widget-rendering.md\":\"BmpARZve\",\"contributor-guide_architecture_worker-protocol.md\":\"21pTYhFF\",\"contributor-guide_contributing.md\":\"B2E9ni79\",\"contributor-guide_development-setup.md\":\"CjgZJwjK\",\"contributor-guide_testing.md\":\"DTwhpoN2\",\"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\":\"ZHPSbBkF\",\"user-guide_getting-started.md\":\"CEa2ZX-l\",\"user-guide_mcp-tools.md\":\"dQwIvdTF\",\"user-guide_run-comparison.md\":\"ChLI3MK0\",\"user-guide_understanding-findings.md\":\"D1ccs60C\"}");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\"},{\"text\":\"Understanding findings\",\"link\":\"/user-guide/understanding-findings\"},{\"text\":\"Run comparison mode\",\"link\":\"/user-guide/run-comparison\"},{\"text\":\"MCP tools reference\",\"link\":\"/user-guide/mcp-tools\"},{\"text\":\"Alternative log retrieval\",\"link\":\"/user-guide/alternative-log-retrieval\"}]}],\"/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\"},{\"text\":\"State & history intake\",\"link\":\"/contributor-guide/architecture/state-and-history\"},{\"text\":\"Detector contract\",\"link\":\"/contributor-guide/architecture/detector-contract\"},{\"text\":\"Impact estimation\",\"link\":\"/contributor-guide/architecture/impact-estimation\"},{\"text\":\"Widget rendering\",\"link\":\"/contributor-guide/architecture/widget-rendering\"},{\"text\":\"Board widgets\",\"link\":\"/contributor-guide/architecture/board-widgets\"},{\"text\":\"Drill-down\",\"link\":\"/contributor-guide/architecture/drill-down\"}]},{\"text\":\"Testing & verification\",\"link\":\"/contributor-guide/testing\"},{\"text\":\"Contributing\",\"link\":\"/contributor-guide/contributing\"}]}]},\"search\":{\"provider\":\"local\"}},\"locales\":{},\"scrollOffset\":134,\"cleanUrls\":false}");</script>
|
|
27
27
|
|
|
28
28
|
</body>
|
|
29
29
|
</html>
|
|
@@ -3,17 +3,17 @@
|
|
|
3
3
|
<head>
|
|
4
4
|
<meta charset="utf-8">
|
|
5
5
|
<meta name="viewport" content="width=device-width,initial-scale=1">
|
|
6
|
-
<title>Anti-Patterns |
|
|
7
|
-
<meta name="description" content="
|
|
6
|
+
<title>Anti-Patterns | Spark Tuning Reference</title>
|
|
7
|
+
<meta name="description" content="Checklist of a dozen recurring Spark performance anti-patterns, each with what it is, how to detect it, why it hurts, and how to fix it.">
|
|
8
8
|
<meta name="generator" content="VitePress v1.6.4">
|
|
9
9
|
<link rel="preload stylesheet" href="/docs/assets/style.DSixAiZE.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.
|
|
12
|
+
<script type="module" src="/docs/assets/app.C6w47a9W.js"></script>
|
|
13
13
|
<link rel="preload" href="/docs/assets/inter-roman-latin.Di8DUHzh.woff2" as="font" type="font/woff2" crossorigin="">
|
|
14
|
-
<link rel="modulepreload" href="/docs/assets/chunks/theme.
|
|
14
|
+
<link rel="modulepreload" href="/docs/assets/chunks/theme.D-mE6j02.js">
|
|
15
15
|
<link rel="modulepreload" href="/docs/assets/chunks/framework.DSg0KOwT.js">
|
|
16
|
-
<link rel="modulepreload" href="/docs/assets/tuning-reference_anti-patterns.md.
|
|
16
|
+
<link rel="modulepreload" href="/docs/assets/tuning-reference_anti-patterns.md.D08Uaod7.lean.js">
|
|
17
17
|
<link rel="icon" type="image/svg+xml" href="/docs/favicon.svg">
|
|
18
18
|
<link rel="preconnect" href="https://fonts.googleapis.com">
|
|
19
19
|
<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin="">
|
|
@@ -23,7 +23,7 @@
|
|
|
23
23
|
</head>
|
|
24
24
|
<body>
|
|
25
25
|
<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" 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>Getting Started</h2><!----></div><div class="items" data-v-b3fd67f8><!--[--><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/tuning-reference/intro.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Introduction</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><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>Optimization Guide</h2><!----></div><div class="items" data-v-b3fd67f8><!--[--><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/tuning-reference/spark-architecture.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Spark Execution Model</p><!--]--></a><!----></div><!----></div><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/tuning-reference/memory-model.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Memory Management</p><!--]--></a><!----></div><!----></div><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/tuning-reference/partitioning.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Partitioning</p><!--]--></a><!----></div><!----></div><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/tuning-reference/joins.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Join Optimization</p><!--]--></a><!----></div><!----></div><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/tuning-reference/shuffle.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Shuffle</p><!--]--></a><!----></div><!----></div><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/tuning-reference/data-formats.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Data Formats</p><!--]--></a><!----></div><!----></div><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/tuning-reference/table-formats.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Table Formats</p><!--]--></a><!----></div><!----></div><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/tuning-reference/caching.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Caching & Persistence</p><!--]--></a><!----></div><!----></div><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/tuning-reference/pyspark.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>PySpark Specifics</p><!--]--></a><!----></div><!----></div><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/tuning-reference/aqe.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Adaptive Query Execution</p><!--]--></a><!----></div><!----></div><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/tuning-reference/cluster-config.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Cluster Tuning</p><!--]--></a><!----></div><!----></div><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/tuning-reference/anti-patterns.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Anti-Patterns</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><div class="no-transition group" data-v-c40bc020><section class="VPSidebarItem level-0" 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>Detector Catalog</h2><!----></div><div class="items" data-v-b3fd67f8><!--[--><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/tuning-reference/bottleneck-skew.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Task Skew</p><!--]--></a><!----></div><!----></div><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/tuning-reference/bottleneck-shuffle.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Shuffle I/O</p><!--]--></a><!----></div><!----></div><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/tuning-reference/bottleneck-spill.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Memory / Disk Spill</p><!--]--></a><!----></div><!----></div><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/tuning-reference/bottleneck-gc.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>GC Pressure</p><!--]--></a><!----></div><!----></div><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/tuning-reference/bottleneck-cold-start.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Cold Start</p><!--]--></a><!----></div><!----></div><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/tuning-reference/bottleneck-utilization.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Executor Utilization</p><!--]--></a><!----></div><!----></div><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/tuning-reference/bottleneck-slow-host.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Slow Host</p><!--]--></a><!----></div><!----></div><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/tuning-reference/bottleneck-failures.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Task Failures</p><!--]--></a><!----></div><!----></div><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/tuning-reference/bottleneck-straggler.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Stragglers</p><!--]--></a><!----></div><!----></div><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/tuning-reference/bottleneck-retry-waste.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Retry Waste</p><!--]--></a><!----></div><!----></div><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/tuning-reference/bottleneck-tiny-tasks.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Tiny Tasks</p><!--]--></a><!----></div><!----></div><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/tuning-reference/bottleneck-job-failure-rate.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Job Failure Rate</p><!--]--></a><!----></div><!----></div><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/tuning-reference/bottleneck-memory-utilization.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Memory Utilization</p><!--]--></a><!----></div><!----></div><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/tuning-reference/bottleneck-duplicate-plan-subtree.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Duplicate Plan Subtree</p><!--]--></a><!----></div><!----></div><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/tuning-reference/bottleneck-small-files.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Small Files</p><!--]--></a><!----></div><!----></div><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/tuning-reference/bottleneck-broadcast-sizing.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Broadcast Sizing</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><div class="no-transition group" data-v-c40bc020><section class="VPSidebarItem level-0" 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>Reference</h2><!----></div><div class="items" data-v-b3fd67f8><!--[--><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/tuning-reference/metrics.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Metrics Glossary</p><!--]--></a><!----></div><!----></div><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/tuning-reference/config.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Spark Config Quick-Reference</p><!--]--></a><!----></div><!----></div><!--]--></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_tuning-reference_anti-patterns" data-v-39a288b8><div><h1 id="anti-patterns" tabindex="-1">Anti-Patterns <a class="header-anchor" href="#anti-patterns" aria-label="Permalink to "Anti-Patterns {#anti-patterns}""></a></h1><p>Practitioner checklists on Spark performance converge on a recurring handful of mistakes rather than exotic ones. Each entry below covers what the mistake is, how to detect it, why it hurts, and how to fix it.</p><ol><li><p><strong>Staying on the RDD API instead of DataFrame/Dataset</strong></p><ul><li><strong>What:</strong> Building jobs on the RDD API (or RDD-based MLlib) instead of the DataFrame/Dataset API.</li><li><strong>Detect:</strong> Code that drives its logic through <code>.map</code>/<code>.filter</code> lambdas over RDDs, or that calls into the RDD-based MLlib API.</li><li><strong>Why:</strong> RDDs are lambda-driven, so Spark cannot see inside the closures. It can't apply predicate pushdown, filter reordering, Adaptive Query Execution, or cost-based join reordering. The RDD-based MLlib API is in maintenance mode for the same reason.<sup class="footnote-ref"><a href="#fn1" id="fnref1">[1]</a></sup></li><li><strong>Fix:</strong> Use the DataFrame/Dataset API so Catalyst can optimize the query plan.</li></ul></li><li><p><strong>Reading CSV/JSON without an explicit schema</strong></p><ul><li><strong>What:</strong> Reading raw CSV or JSON files without supplying an explicit schema.</li><li><strong>Detect:</strong> A read step that spends noticeable time before any real work starts, because Spark is inferring types from the data itself.</li><li><strong>Why:</strong> Schema inference forces a full scan of the data just to determine types, and CSV/JSON don't support the column pruning, predicate pushdown, or stats-based file skipping that a columnar format does.<sup class="footnote-ref"><a href="#fn1" id="fnref1:1">[1:1]</a></sup></li><li><strong>Fix:</strong> Supply an explicit schema, or prefer Parquet for analytical workloads, where column pruning, predicate pushdown, and stats-based file skipping work out of the box.<sup class="footnote-ref"><a href="#fn1" id="fnref1:2">[1:2]</a></sup></li></ul></li><li><p><strong>Compressing input files with a non-splittable codec (GZIP)</strong></p><ul><li><strong>What:</strong> Storing input data as large GZIP files.</li><li><strong>Detect:</strong> One task/executor taking far longer than the rest on a stage reading GZIP-compressed input, while other executors sit idle.</li><li><strong>Why:</strong> A GZIP file can't be split across executors, so a single node has to decompress the whole file alone.<sup class="footnote-ref"><a href="#fn1" id="fnref1:3">[1:3]</a></sup></li><li><strong>Fix:</strong> Use a splittable codec instead: Snappy, LZ4, or ZSTD.<sup class="footnote-ref"><a href="#fn1" id="fnref1:4">[1:4]</a></sup></li></ul></li><li><p><strong>Storing data as JSON instead of a binary columnar/row format</strong></p><ul><li><strong>What:</strong> Persisting datasets as JSON rather than a binary columnar or row format.</li><li><strong>Detect:</strong> Read-heavy jobs where a large, recurring share of stage time goes to parsing the same JSON structures on every read.</li><li><strong>Why:</strong> JSON has to be re-parsed from text on every single read.<sup class="footnote-ref"><a href="#fn2" id="fnref2">[2]</a></sup></li><li><strong>Fix:</strong> Store data as Avro, Parquet, Thrift, or Protobuf structs in a sequence file to avoid the repeated parsing cost.<sup class="footnote-ref"><a href="#fn2" id="fnref2:1">[2:1]</a></sup></li></ul></li><li><p><strong>Not registering custom classes with Kryo</strong></p><ul><li><strong>What:</strong> Using Kryo serialization without registering the application's custom classes.</li><li><strong>Detect:</strong> Larger-than-expected serialized record sizes, and poor efficiency when using a serialized cache storage level such as <code>MEMORY_SER</code>.</li><li><strong>Why:</strong> Unregistered classes increase serialized-record size and hurt serialized cache storage levels.<sup class="footnote-ref"><a href="#fn2" id="fnref2:2">[2:2]</a></sup></li><li><strong>Fix:</strong> Register the application's custom classes with Kryo.</li></ul></li><li><p><strong>Calling <code>collect()</code> on a large DataFrame</strong></p><ul><li><p><strong>What:</strong> Materializing an entire DataFrame into driver memory with <code>collect()</code>.</p></li><li><p><strong>Detect:</strong> A driver <code>OutOfMemoryError</code>, or a job that aborts once <code>spark.driver.maxResultSize</code> (default 1 GB) is exceeded. Spark also logs a warning once a single task's serialized result passes roughly 1 MB.<sup class="footnote-ref"><a href="#fn3" id="fnref3">[3]</a></sup><sup class="footnote-ref"><a href="#fn1" id="fnref1:5">[1:5]</a></sup></p></li><li><p><strong>Why:</strong> <code>collect()</code> gathers every <code>Row</code> from every partition into a single in-memory <code>Array</code> that lives entirely on the driver, not the cluster. The driver JVM has to hold the whole result set in its own heap.<sup class="footnote-ref"><a href="#fn3" id="fnref3:1">[3:1]</a></sup><sup class="footnote-ref"><a href="#fn4" id="fnref4">[4]</a></sup><sup class="footnote-ref"><a href="#fn5" id="fnref5">[5]</a></sup><sup class="footnote-ref"><a href="#fn6" id="fnref6">[6]</a></sup></p></li><li><p><strong>Fix:</strong> Use aggregations or <code>take(n)</code> instead of collecting the full result set.</p><blockquote><p><strong>PySpark:</strong> <code>toPandas()</code> performs the same driver-side collection as <code>collect()</code> for Python users, so avoid it on large DataFrames too.<sup class="footnote-ref"><a href="#fn6" id="fnref6:1">[6:1]</a></sup></p></blockquote></li></ul></li><li><p><strong>Assuming <code>cache()</code> + <code>count()</code> guarantees the DataFrame stays fully cached</strong></p><ul><li><strong>What:</strong> Treating <code>df.cache(); df.count()</code> as a guarantee that the DataFrame remains fully persisted for later actions.</li><li><strong>Detect:</strong> Later actions on a supposedly-cached DataFrame recompute from source instead of hitting the cache. There's no built-in visibility into how much of a DataFrame is still actually cached, so this typically only surfaces as unexpectedly slow recomputation.<sup class="footnote-ref"><a href="#fn7" id="fnref7">[7]</a></sup></li><li><strong>Why:</strong> <code>count()</code> does force every partition to be computed and attempted for caching, unlike <code>take</code>/<code>limit</code>, which only touch the partitions they need.<sup class="footnote-ref"><a href="#fn5" id="fnref5:1">[5:1]</a></sup><sup class="footnote-ref"><a href="#fn7" id="fnref7:1">[7:1]</a></sup> But partitions can't be fractionally cached: if there isn't room for all of them, the ones that don't fit are silently dropped and recomputed on next access.<sup class="footnote-ref"><a href="#fn5" id="fnref5:2">[5:2]</a></sup> Cached blocks also compete with execution for the same memory pool and can be evicted under pressure without warning, and caching is tied to the <em>analyzed</em> (pre-optimization) logical plan, so a semantically identical query with a different analyzed plan bypasses the cache entirely and recomputes from source.<sup class="footnote-ref"><a href="#fn7" id="fnref7:2">[7:2]</a></sup> Losing an executor drops any cached block that wasn't stored with a replicated storage level like <code>MEMORY_AND_DISK_2</code>.<sup class="footnote-ref"><a href="#fn7" id="fnref7:3">[7:3]</a></sup></li><li><strong>Fix:</strong> Keep using <code>.cache()</code> followed by <code>.count()</code> to force materialization, but don't assume that guarantees persistence (there's no built-in way to confirm how much of the DataFrame is actually cached<sup class="footnote-ref"><a href="#fn7" id="fnref7:4">[7:4]</a></sup>), and use a replicated storage level if losing a cached partition to executor failure would be costly.</li></ul></li><li><p><strong>Row-at-a-time Python UDFs</strong></p><ul><li><strong>What:</strong> Writing Python UDFs that operate one row at a time instead of vectorized Pandas UDFs.</li><li><strong>Detect:</strong> A UDF-heavy stage where most of the time goes to serialization rather than actual computation.<sup class="footnote-ref"><a href="#fn8" id="fnref8">[8]</a></sup></li><li><strong>Why:</strong> The overhead is serialization plus per-row JVM↔Python data movement, not raw Python interpreter speed. Row-at-a-time UDFs "suffer from high serialization and invocation overhead."<sup class="footnote-ref"><a href="#fn9" id="fnref9">[9]</a></sup> RDD-era Python UDFs pay a <em>double</em> serialization cost: Java/Scala objects are serialized, then re-serialized to Python via <code>cloudpickle</code> and back on every call.<sup class="footnote-ref"><a href="#fn8" id="fnref8:1">[8:1]</a></sup> A Databricks benchmark on a 10M-row DataFrame showed vectorized Pandas UDFs beating row-at-a-time UDFs "across the board, ranging from 3x to over 100x."<sup class="footnote-ref"><a href="#fn9" id="fnref9:1">[9:1]</a></sup></li><li><strong>Fix:</strong> Use vectorized Pandas UDFs instead of row-at-a-time UDFs: once data is transferred via Arrow, there's no need to serialize/pickle it, since it's already in a format consumable by the Python process.<sup class="footnote-ref"><a href="#fn5" id="fnref5:3">[5:3]</a></sup></li></ul></li><li><p><strong>Leaving <code>spark.sql.shuffle.partitions</code> at its default of 200</strong></p><ul><li><strong>What:</strong> Never tuning <code>spark.sql.shuffle.partitions</code> away from its default of 200 for wide transformations (<code>join</code>, <code>groupBy</code>, aggregations).</li><li><strong>Detect:</strong> In the Spark UI Stages tab, too few partitions for the data size shows up as "Spill (Memory)" or "Spill (Disk)" entries against a stage; too many partitions for the data size shows up as a large task/stage count where each task's duration is dominated by scheduling and bookkeeping, often paired with a large number of tiny output files.<sup class="footnote-ref"><a href="#fn10" id="fnref10">[10]</a></sup></li><li><strong>Why:</strong> 200 is a fixed default regardless of whether you're joining 5MB or 5TB.<sup class="footnote-ref"><a href="#fn10" id="fnref10:1">[10:1]</a></sup><sup class="footnote-ref"><a href="#fn11" id="fnref11">[11]</a></sup> Too few partitions means each one holds more data than fits comfortably in executor memory, which increases load per executor and leads to spills once partition size exceeds available memory.<sup class="footnote-ref"><a href="#fn10" id="fnref10:2">[10:2]</a></sup> Too many partitions on a small dataset can shrink tasks to around ten rows each, so "most of your CPUs will just be sitting there doing nothing."<sup class="footnote-ref"><a href="#fn10" id="fnref10:3">[10:3]</a></sup></li><li><strong>Fix:</strong> Increase <code>spark.sql.shuffle.partitions</code> if tasks are processing multiple GB each and spilling; decrease it if tasks finish in a couple of seconds and write tiny files. A rough starting target is 100–200 MB of data per task, tuned per dataset.<sup class="footnote-ref"><a href="#fn10" id="fnref10:4">[10:4]</a></sup></li></ul></li><li><p><strong>Broadcasting a table that's too large</strong></p><ul><li><strong>What:</strong> Forcing or allowing a broadcast join on a table that's too large to broadcast safely.</li><li><strong>Detect:</strong> A driver <code>OutOfMemoryError</code> during a broadcast join.</li><li><strong>Why:</strong> The small side of the join has to be collected onto the driver before it can be broadcast to every executor. That collection step is the same driver-memory operation as <code>.collect()</code>, and it's what fails, not executor-side replication or a serialization timeout: "if you try to broadcast something too large, you can crash your driver node (because that collect is expensive)."<sup class="footnote-ref"><a href="#fn4" id="fnref4:1">[4:1]</a></sup></li><li><strong>Fix:</strong> Use <code>spark.sql.autoBroadcastJoinThreshold</code> to control the maximum size Spark will broadcast, or increase driver memory.<sup class="footnote-ref"><a href="#fn4" id="fnref4:2">[4:2]</a></sup></li></ul></li><li><p><strong>Reaching for <code>coalesce(1)</code> before every single-file write</strong></p><ul><li><strong>What:</strong> Always using <code>coalesce(1)</code> instead of <code>repartition(1)</code> when a single output file is needed.</li><li><strong>Detect:</strong> The entire upstream stage (including filtering/transformation work that would otherwise run in parallel) collapses onto a single task/executor, leaving the rest of the cluster idle.</li><li><strong>Why:</strong> <code>coalesce</code> is a narrow transformation, so it "causes the upstream partitions in the entire stage to execute with the level of parallelism assigned by coalesce," fusing all preceding work down to one task.<sup class="footnote-ref"><a href="#fn6" id="fnref6:2">[6:2]</a></sup> <code>repartition</code> triggers a full shuffle instead, which inserts an explicit shuffle boundary so the upstream stage keeps its original parallelism.<sup class="footnote-ref"><a href="#fn4" id="fnref4:3">[4:3]</a></sup><sup class="footnote-ref"><a href="#fn6" id="fnref6:3">[6:3]</a></sup></li><li><strong>Fix:</strong> Use <code>repartition(1)</code> when there is meaningful upstream computation you don't want collapsed onto a single executor; reserve <code>coalesce(1)</code> for when the upstream stage is already cheap and paying for a shuffle would be wasted cost.<sup class="footnote-ref"><a href="#fn6" id="fnref6:4">[6:4]</a></sup></li></ul></li><li><p><strong>Not verifying predicate pushdown is actually happening</strong></p><ul><li><strong>What:</strong> Assuming filters and column projections are pushed down to the data source without checking the physical plan.</li><li><strong>Detect:</strong> Run <code>.explain()</code> and look at the <code>Scan</code> node for a <code>PushedFilters</code> marker. For example, <code>*Scan JDBCRel... PushedFilters: [*In(DEST_COUNTRY_NAME, [Anguilla, Sweden])]</code>. Column pruning is verified the same way: a <code>.select()</code> on one column should show a narrowed <code>ReadSchema</code> at the scan rather than a full-table scan.<sup class="footnote-ref"><a href="#fn4" id="fnref4:4">[4:4]</a></sup></li><li><strong>Why:</strong> Spark pushes down simple filters (column equality, <code>IN</code>, <code>IS NULL</code>) to JDBC sources automatically, but anything with a computed column or cast won't push down and gets evaluated in Spark after the full read.<sup class="footnote-ref"><a href="#fn1" id="fnref1:6">[1:6]</a></sup> Some sources also only partially handle a filter and leave Spark to re-evaluate it as a safety mechanism; that's still a "good" pushdown since the amount of data read is reduced.<sup class="footnote-ref"><a href="#fn6" id="fnref6:5">[6:5]</a></sup></li><li><strong>Fix:</strong> Check <code>explain</code> output (paired with <code>printSchema</code>)<sup class="footnote-ref"><a href="#fn6" id="fnref6:6">[6:6]</a></sup> for <code>PushedFilters</code> after writing a filter, and rewrite filters that use casts or computed columns as simple predicates where possible so they can push down.<sup class="footnote-ref"><a href="#fn4" id="fnref4:5">[4:5]</a></sup><sup class="footnote-ref"><a href="#fn1" id="fnref1:7">[1:7]</a></sup></li></ul></li></ol><h2 id="sources" tabindex="-1">Sources <a class="header-anchor" href="#sources" aria-label="Permalink to "Sources""></a></h2><hr class="footnotes-sep"><section class="footnotes"><ol class="footnotes-list"><li id="fn1" class="footnote-item"><p><a href="https://luminousmen.com/post/the-apache-spark-optimization-checklist" target="_blank" rel="noreferrer">The Apache Spark Optimization Checklist</a> <a href="#fnref1" class="footnote-backref">↩︎</a> <a href="#fnref1:1" class="footnote-backref">↩︎</a> <a href="#fnref1:2" class="footnote-backref">↩︎</a> <a href="#fnref1:3" class="footnote-backref">↩︎</a> <a href="#fnref1:4" class="footnote-backref">↩︎</a> <a href="#fnref1:5" class="footnote-backref">↩︎</a> <a href="#fnref1:6" class="footnote-backref">↩︎</a> <a href="#fnref1:7" class="footnote-backref">↩︎</a></p></li><li id="fn2" class="footnote-item"><p><a href="https://blog.cloudera.com/how-to-tune-your-apache-spark-jobs-part-2/" target="_blank" rel="noreferrer">How to Tune Your Apache Spark Jobs (Part 2)</a> <a href="#fnref2" class="footnote-backref">↩︎</a> <a href="#fnref2:1" class="footnote-backref">↩︎</a> <a href="#fnref2:2" class="footnote-backref">↩︎</a></p></li><li id="fn3" class="footnote-item"><p><em>Advanced Analytics with PySpark</em>, Tandon, Ryza, Laserson et al., ch. 2 <a href="#fnref3" class="footnote-backref">↩︎</a> <a href="#fnref3:1" class="footnote-backref">↩︎</a></p></li><li id="fn4" class="footnote-item"><p><em>Spark: The Definitive Guide</em>, Chambers & Zaharia, chs. 5, 8, 9, 18, 19 <a href="#fnref4" class="footnote-backref">↩︎</a> <a href="#fnref4:1" class="footnote-backref">↩︎</a> <a href="#fnref4:2" class="footnote-backref">↩︎</a> <a href="#fnref4:3" class="footnote-backref">↩︎</a> <a href="#fnref4:4" class="footnote-backref">↩︎</a> <a href="#fnref4:5" class="footnote-backref">↩︎</a></p></li><li id="fn5" class="footnote-item"><p><em>Learning Spark, 2nd Edition</em>, Damji, Wenig, Das & Lee, chs. 3, 5, 7 <a href="#fnref5" class="footnote-backref">↩︎</a> <a href="#fnref5:1" class="footnote-backref">↩︎</a> <a href="#fnref5:2" class="footnote-backref">↩︎</a> <a href="#fnref5:3" class="footnote-backref">↩︎</a></p></li><li id="fn6" class="footnote-item"><p><em>High Performance Spark, 2nd Edition</em>, Karau, Polak & Warren, chs. 5, 7 <a href="#fnref6" class="footnote-backref">↩︎</a> <a href="#fnref6:1" class="footnote-backref">↩︎</a> <a href="#fnref6:2" class="footnote-backref">↩︎</a> <a href="#fnref6:3" class="footnote-backref">↩︎</a> <a href="#fnref6:4" class="footnote-backref">↩︎</a> <a href="#fnref6:5" class="footnote-backref">↩︎</a> <a href="#fnref6:6" class="footnote-backref">↩︎</a></p></li><li id="fn7" class="footnote-item"><p><a href="https://luminousmen.com/post/explaining-the-mechanics-of-spark-caching" target="_blank" rel="noreferrer">Explaining the Mechanics of Spark Caching</a> <a href="#fnref7" class="footnote-backref">↩︎</a> <a href="#fnref7:1" class="footnote-backref">↩︎</a> <a href="#fnref7:2" class="footnote-backref">↩︎</a> <a href="#fnref7:3" class="footnote-backref">↩︎</a> <a href="#fnref7:4" class="footnote-backref">↩︎</a></p></li><li id="fn8" class="footnote-item"><p><a href="https://luminousmen.com/post/spark-tips-dataframe-api" target="_blank" rel="noreferrer">Spark Tips: DataFrame API</a> <a href="#fnref8" class="footnote-backref">↩︎</a> <a href="#fnref8:1" class="footnote-backref">↩︎</a></p></li><li id="fn9" class="footnote-item"><p><a href="https://www.databricks.com/blog/2017/10/30/introducing-vectorized-udfs-for-pyspark.html" target="_blank" rel="noreferrer">Introducing Vectorized UDFs for PySpark</a> <a href="#fnref9" class="footnote-backref">↩︎</a> <a href="#fnref9:1" class="footnote-backref">↩︎</a></p></li><li id="fn10" class="footnote-item"><p><a href="https://luminousmen.com/post/spark-partitions" target="_blank" rel="noreferrer">Spark Partitions</a> <a href="#fnref10" class="footnote-backref">↩︎</a> <a href="#fnref10:1" class="footnote-backref">↩︎</a> <a href="#fnref10:2" class="footnote-backref">↩︎</a> <a href="#fnref10:3" class="footnote-backref">↩︎</a> <a href="#fnref10:4" class="footnote-backref">↩︎</a></p></li><li id="fn11" class="footnote-item"><p><a href="https://spark.apache.org/docs/latest/configuration.html" target="_blank" rel="noreferrer">Configuration — Spark</a> <a href="#fnref11" class="footnote-backref">↩︎</a></p></li></ol></section></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/tuning-reference/cluster-config.html" data-v-e257564d><!--[--><span class="desc" data-v-e257564d>Previous page</span><span class="title" data-v-e257564d>Cluster Tuning</span><!--]--></a></div><div class="pager" data-v-e257564d><a class="VPLink link pager-link next" href="/docs/tuning-reference/bottleneck-skew.html" data-v-e257564d><!--[--><span class="desc" data-v-e257564d>Next page</span><span class="title" data-v-e257564d>Task Skew</span><!--]--></a></div></nav></footer><!--[--><!--]--></div></div></div><!--[--><!--]--></div></div><!----><!--[--><!--]--></div></div>
|
|
26
|
-
<script>window.__VP_HASH_MAP__=JSON.parse("{\"contributor-guide_architecture_board-widgets.md\":\"
|
|
26
|
+
<script>window.__VP_HASH_MAP__=JSON.parse("{\"contributor-guide_architecture_board-widgets.md\":\"VTcYTH4d\",\"contributor-guide_architecture_detector-contract.md\":\"CsqZHz_T\",\"contributor-guide_architecture_drill-down.md\":\"CFNCE8JB\",\"contributor-guide_architecture_impact-estimation.md\":\"HT9IJGIl\",\"contributor-guide_architecture_index.md\":\"3TO9ic6w\",\"contributor-guide_architecture_overview.md\":\"CTEqVeV4\",\"contributor-guide_architecture_state-and-history.md\":\"DOTVHjTV\",\"contributor-guide_architecture_widget-rendering.md\":\"BmpARZve\",\"contributor-guide_architecture_worker-protocol.md\":\"21pTYhFF\",\"contributor-guide_contributing.md\":\"B2E9ni79\",\"contributor-guide_development-setup.md\":\"CjgZJwjK\",\"contributor-guide_testing.md\":\"DTwhpoN2\",\"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\":\"ZHPSbBkF\",\"user-guide_getting-started.md\":\"CEa2ZX-l\",\"user-guide_mcp-tools.md\":\"dQwIvdTF\",\"user-guide_run-comparison.md\":\"ChLI3MK0\",\"user-guide_understanding-findings.md\":\"D1ccs60C\"}");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\"},{\"text\":\"Understanding findings\",\"link\":\"/user-guide/understanding-findings\"},{\"text\":\"Run comparison mode\",\"link\":\"/user-guide/run-comparison\"},{\"text\":\"MCP tools reference\",\"link\":\"/user-guide/mcp-tools\"},{\"text\":\"Alternative log retrieval\",\"link\":\"/user-guide/alternative-log-retrieval\"}]}],\"/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\"},{\"text\":\"State & history intake\",\"link\":\"/contributor-guide/architecture/state-and-history\"},{\"text\":\"Detector contract\",\"link\":\"/contributor-guide/architecture/detector-contract\"},{\"text\":\"Impact estimation\",\"link\":\"/contributor-guide/architecture/impact-estimation\"},{\"text\":\"Widget rendering\",\"link\":\"/contributor-guide/architecture/widget-rendering\"},{\"text\":\"Board widgets\",\"link\":\"/contributor-guide/architecture/board-widgets\"},{\"text\":\"Drill-down\",\"link\":\"/contributor-guide/architecture/drill-down\"}]},{\"text\":\"Testing & verification\",\"link\":\"/contributor-guide/testing\"},{\"text\":\"Contributing\",\"link\":\"/contributor-guide/contributing\"}]}]},\"search\":{\"provider\":\"local\"}},\"locales\":{},\"scrollOffset\":134,\"cleanUrls\":false}");</script>
|
|
27
27
|
|
|
28
28
|
</body>
|
|
29
29
|
</html>
|