sparkforensics-server 0.6.0 → 0.8.1

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.
Files changed (410) hide show
  1. package/index.js +16 -7
  2. package/package.json +1 -1
  3. package/public/assets/AutoscalingChurn-DenWKTv-.js +1 -0
  4. package/public/assets/CacheUtilization-DLz7NdjV.js +1 -0
  5. package/public/assets/CachingOpportunity-zpQIqhzm.js +1 -0
  6. package/public/assets/ChartTheme-DAiARbLP.js +8 -0
  7. package/public/assets/ColdStart-C-9HjxWl.js +1 -0
  8. package/public/assets/ConfigAudit-D0V9tcrJ.js +1 -0
  9. package/public/assets/CoreUsageArea-yeerrljd.js +1 -0
  10. package/public/assets/Dashboard-DkUPrHKV.js +1 -0
  11. package/public/assets/DisclosureContext-DK1_iz6J.js +1 -0
  12. package/public/assets/DuplicatePlanSubtree-xDNDbCd3.js +1 -0
  13. package/public/assets/DurationHistogram-B6jsE0Ov.js +1 -0
  14. package/public/assets/EmptyState-C1uL40VU.js +1 -0
  15. package/public/assets/ExecutorUtilization-DXDZKmSc.js +1 -0
  16. package/public/assets/GcPressure-MRf7I4IG.js +1 -0
  17. package/public/assets/ImpactEstimate-Dm3xWbzV.js +1 -0
  18. package/public/assets/IncompleteRun-CaLOhMtf.js +1 -0
  19. package/public/assets/JobFailures-CzmzlvhO.js +1 -0
  20. package/public/assets/MemoryUtilization-AWUMUjCH.js +1 -0
  21. package/public/assets/NestedLoopJoin-C9sNr6Ss.js +1 -0
  22. package/public/assets/OverBroadcast-BOmRE6ca.js +1 -0
  23. package/public/assets/PartitionHint-BL2EmJfE.js +1 -0
  24. package/public/assets/PartitionSizing-BzBySvUq.js +1 -0
  25. package/public/assets/PlanExplorer-DdiQRcJU.js +1 -0
  26. package/public/assets/PlanGraphRoute-CIH9gBuR.js +1 -0
  27. package/public/assets/PlanView-B1hxzFRs.js +2 -0
  28. package/public/assets/PythonUdf-DvgCCueD.js +1 -0
  29. package/public/assets/RetryWaste-uXXu_CyM.js +1 -0
  30. package/public/assets/RowPagination-C-LzWkI5.js +1 -0
  31. package/public/assets/RowStatusCluster-Dbtmte7l.js +1 -0
  32. package/public/assets/ShuffleIO-nALwzC1_.js +1 -0
  33. package/public/assets/Skew-CHMEKgvk.js +1 -0
  34. package/public/assets/SlowHost-yyvjpHk6.js +1 -0
  35. package/public/assets/SmallFiles-y6odJ97n.js +1 -0
  36. package/public/assets/SpeculationWaste-C-SD2LOt.js +1 -0
  37. package/public/assets/Spill-DHTMmOup.js +1 -0
  38. package/public/assets/StageFailed-CQ3DxC9R.js +1 -0
  39. package/public/assets/StageFindingGroup-BgYLyj5q.js +1 -0
  40. package/public/assets/StageHeader-CIETkjVZ.js +1 -0
  41. package/public/assets/StagePill--P7PDd3s.js +1 -0
  42. package/public/assets/StageShape-BIv8vx_o.js +1 -0
  43. package/public/assets/StageSlowness-MMqzERxN.js +1 -0
  44. package/public/assets/Straggler-BgrY7AyW.js +1 -0
  45. package/public/assets/TaskFailures-BHHyKYTs.js +1 -0
  46. package/public/assets/TinyTask-DDScNhCl.js +1 -0
  47. package/public/assets/UnderBroadcast-CGIC04TI.js +1 -0
  48. package/public/assets/WidgetLeadSummary-CXFZP00C.js +1 -0
  49. package/public/assets/button-DbpTz2yk.js +1 -0
  50. package/public/assets/charts-vendor-CtTxwTeu.js +59 -0
  51. package/public/assets/composite-C9Nu2EI9.js +1 -0
  52. package/public/assets/d3-vendor-DNlD2-cz.js +1 -0
  53. package/public/assets/detector-registry-Bp8hrLua.js +2 -0
  54. package/public/assets/downsample-WmNM1qc9.js +1 -0
  55. package/public/assets/finding-anchor-Dr40LkS9.js +1 -0
  56. package/public/assets/findings-of-type-BL2u3RGZ.js +1 -0
  57. package/public/assets/impact-sort-mC5ISgX8.js +1 -0
  58. package/public/assets/inbox-KPU1Gppm.js +1 -0
  59. package/public/assets/index-CaRVPvAT.css +2 -0
  60. package/public/assets/index-fDiwfuoO.js +14 -0
  61. package/public/assets/inertValue-L9VxV0VE.js +1 -0
  62. package/public/assets/layout.worker-CLcBHxVp.js +3 -0
  63. package/public/assets/{parser-worker-CA5RxqKc.js → parser-worker-CRIOPMOW.js} +8 -8
  64. package/public/assets/plan-graph-vendor-Ce6d4HU6.js +7 -0
  65. package/public/assets/react-vendor-C6KcUD36.js +9 -0
  66. package/public/assets/select-BHqOqun5.js +1 -0
  67. package/public/assets/toggle-DPeN6aNa.js +1 -0
  68. package/public/assets/toggle-group-Kl3uyHSr.js +1 -0
  69. package/public/assets/usePagedRows-BafD6bEN.js +1 -0
  70. package/public/assets/useRecentFiles-DzJZAoOT.js +3 -0
  71. package/public/assets/useRegisterFieldControl-pQv-ZDoU.js +1 -0
  72. package/public/assets/useScrollLock-BCxn_dMp.js +1 -0
  73. package/public/assets/useSortMode-DjrAN-z4.js +1 -0
  74. package/public/docs/404.html +3 -3
  75. package/public/docs/assets/{app.CnWL6bKV.js → app.1gvzd5Zb.js} +1 -1
  76. package/public/docs/assets/chunks/@localSearchIndexroot.DS2TQP5_.js +1 -0
  77. package/public/docs/assets/chunks/{VPLocalSearchBox.C0IBKeRQ.js → VPLocalSearchBox.CNxT3s0I.js} +1 -1
  78. package/public/docs/assets/chunks/{theme.BH-2HuRf.js → theme.C5lLqUv7.js} +2 -2
  79. package/public/docs/assets/contributor-guide_architecture_board-widgets.md.CqKM_jEG.js +1 -0
  80. package/public/docs/assets/contributor-guide_architecture_board-widgets.md.CqKM_jEG.lean.js +1 -0
  81. package/public/docs/assets/{contributor-guide_architecture_board-widgets_caching-and-memory.md.CQgn1t_M.js → contributor-guide_architecture_board-widgets_caching-and-memory.md.BYDo3ClR.js} +1 -1
  82. package/public/docs/assets/contributor-guide_architecture_board-widgets_plan-advisor.md.ajUAVdbc.js +1 -0
  83. package/public/docs/assets/{contributor-guide_architecture_board-widgets_visual-system-and-templating.md.wulOueeB.js → contributor-guide_architecture_board-widgets_visual-system-and-templating.md.WqY74T0T.js} +1 -1
  84. package/public/docs/assets/contributor-guide_architecture_board-widgets_visual-system-and-templating.md.WqY74T0T.lean.js +1 -0
  85. package/public/docs/assets/contributor-guide_architecture_detector-contract.md.CHHgywoP.js +1 -0
  86. package/public/docs/assets/{contributor-guide_architecture_detector-contract.md.N4hhenrA.lean.js → contributor-guide_architecture_detector-contract.md.CHHgywoP.lean.js} +1 -1
  87. package/public/docs/assets/contributor-guide_architecture_detector-contract_plan-attribution.md.DIz3_oz9.js +1 -0
  88. package/public/docs/assets/contributor-guide_architecture_detector-contract_plan-attribution.md.DIz3_oz9.lean.js +1 -0
  89. package/public/docs/assets/contributor-guide_architecture_detector-contract_threshold-tables.md.WH4tRHPL.js +1 -0
  90. package/public/docs/assets/{contributor-guide_architecture_detector-contract_threshold-tables.md.Dp3c40rx.lean.js → contributor-guide_architecture_detector-contract_threshold-tables.md.WH4tRHPL.lean.js} +1 -1
  91. package/public/docs/assets/{contributor-guide_architecture_drill-down.md.CqZPrdo9.js → contributor-guide_architecture_drill-down.md.yB-Hz2XT.js} +1 -1
  92. package/public/docs/assets/{contributor-guide_architecture_drill-down.md.CqZPrdo9.lean.js → contributor-guide_architecture_drill-down.md.yB-Hz2XT.lean.js} +1 -1
  93. package/public/docs/assets/contributor-guide_architecture_drill-down_plan-graph.md.BQZE04sw.js +1 -0
  94. package/public/docs/assets/{contributor-guide_architecture_drill-down_plan-graph.md.DwOozIEs.lean.js → contributor-guide_architecture_drill-down_plan-graph.md.BQZE04sw.lean.js} +1 -1
  95. package/public/docs/assets/contributor-guide_architecture_impact-estimation.md.K71YB-Rr.js +1 -0
  96. package/public/docs/assets/{contributor-guide_architecture_impact-estimation.md.DfvbqEUu.lean.js → contributor-guide_architecture_impact-estimation.md.K71YB-Rr.lean.js} +1 -1
  97. package/public/docs/assets/contributor-guide_architecture_impact-estimation_caveats-tuning-and-coverage.md.DLCAffwn.js +1 -0
  98. package/public/docs/assets/{contributor-guide_architecture_impact-estimation_caveats-tuning-and-coverage.md.Cwm1jHmn.lean.js → contributor-guide_architecture_impact-estimation_caveats-tuning-and-coverage.md.DLCAffwn.lean.js} +1 -1
  99. package/public/docs/assets/contributor-guide_architecture_impact-estimation_stage-union-rollup.md.JFrzDMwo.js +1 -0
  100. package/public/docs/assets/contributor-guide_architecture_impact-estimation_stage-union-rollup.md.JFrzDMwo.lean.js +1 -0
  101. package/public/docs/assets/contributor-guide_architecture_overview.md.nxkpOhgf.js +1 -0
  102. package/public/docs/assets/contributor-guide_architecture_state-and-history_run-comparison-internals.md.U-9KMDFK.js +1 -0
  103. package/public/docs/assets/{contributor-guide_architecture_state-and-history_run-comparison-internals.md.CZA0JLtV.lean.js → contributor-guide_architecture_state-and-history_run-comparison-internals.md.U-9KMDFK.lean.js} +1 -1
  104. package/public/docs/assets/contributor-guide_architecture_widget-rendering.md.BrSz8Ezh.js +1 -0
  105. package/public/docs/assets/contributor-guide_architecture_widget-rendering_findings-tab.md.B7rjSF_h.js +1 -0
  106. package/public/docs/assets/contributor-guide_architecture_widget-rendering_findings-tab.md.B7rjSF_h.lean.js +1 -0
  107. package/public/docs/assets/{contributor-guide_architecture_widget-rendering_list-sort-mode.md.BuHKgH0C.js → contributor-guide_architecture_widget-rendering_list-sort-mode.md.37hcZJ7q.js} +1 -1
  108. package/public/docs/assets/{contributor-guide_architecture_widget-rendering_row-expand-contract.md.ZT89u9f1.js → contributor-guide_architecture_widget-rendering_row-expand-contract.md.mK_VmAWk.js} +1 -1
  109. package/public/docs/assets/{contributor-guide_architecture_worker-protocol.md.BAnhi2-d.js → contributor-guide_architecture_worker-protocol.md.Br6OE7RW.js} +1 -1
  110. package/public/docs/assets/contributor-guide_architecture_worker-protocol.md.Br6OE7RW.lean.js +1 -0
  111. package/public/docs/assets/contributor-guide_architecture_worker-protocol_cli-and-mcp.md.IVyaXrGe.js +1 -0
  112. package/public/docs/assets/{contributor-guide_architecture_worker-protocol_cli-and-mcp.md.BX1XnFbq.lean.js → contributor-guide_architecture_worker-protocol_cli-and-mcp.md.IVyaXrGe.lean.js} +1 -1
  113. package/public/docs/assets/{contributor-guide_architecture_worker-protocol_core-and-event-validation.md.DSVFPpWb.js → contributor-guide_architecture_worker-protocol_core-and-event-validation.md.DVSXn-bb.js} +1 -1
  114. package/public/docs/assets/{contributor-guide_architecture_worker-protocol_evidence-availability.md.CjimIDBY.js → contributor-guide_architecture_worker-protocol_evidence-availability.md.D3S5cyOW.js} +2 -2
  115. package/public/docs/assets/{contributor-guide_architecture_worker-protocol_evidence-availability.md.CjimIDBY.lean.js → contributor-guide_architecture_worker-protocol_evidence-availability.md.D3S5cyOW.lean.js} +1 -1
  116. package/public/docs/assets/contributor-guide_architecture_worker-protocol_evidence-report.md.CtmCU57I.js +1 -0
  117. package/public/docs/assets/{contributor-guide_architecture_worker-protocol_evidence-report.md.CiQl1MLb.lean.js → contributor-guide_architecture_worker-protocol_evidence-report.md.CtmCU57I.lean.js} +1 -1
  118. package/public/docs/assets/contributor-guide_contributing.md.DBW4drtZ.js +1 -0
  119. package/public/docs/assets/contributor-guide_development-setup.md.B21ZTDhn.js +15 -0
  120. package/public/docs/assets/contributor-guide_development-setup.md.B21ZTDhn.lean.js +1 -0
  121. package/public/docs/assets/contributor-guide_testing.md.DpkozNoG.js +4 -0
  122. package/public/docs/assets/{contributor-guide_testing.md.By6XGR9a.lean.js → contributor-guide_testing.md.DpkozNoG.lean.js} +1 -1
  123. package/public/docs/assets/{index.md.CHJVslga.js → index.md.lMm7SUMz.js} +1 -1
  124. package/public/docs/assets/{index.md.CHJVslga.lean.js → index.md.lMm7SUMz.lean.js} +1 -1
  125. package/public/docs/assets/{style.CyK9Ss73.css → style.Cfxqlj0y.css} +1 -1
  126. package/public/docs/assets/user-guide_getting-started_ci-and-automation.md.C0pcQoNc.js +29 -0
  127. package/public/docs/assets/{user-guide_getting-started_ci-and-automation.md.BEepbDDL.lean.js → user-guide_getting-started_ci-and-automation.md.C0pcQoNc.lean.js} +1 -1
  128. package/public/docs/assets/user-guide_getting-started_reading-the-dashboard.md.CGaxPX_1.js +1 -0
  129. package/public/docs/assets/{user-guide_getting-started_tuning-thresholds.md.B_MyjyZm.js → user-guide_getting-started_tuning-thresholds.md.BGVE-wrc.js} +2 -2
  130. package/public/docs/assets/{user-guide_getting-started_tuning-thresholds.md.B_MyjyZm.lean.js → user-guide_getting-started_tuning-thresholds.md.BGVE-wrc.lean.js} +1 -1
  131. package/public/docs/assets/{user-guide_mcp-tools.md.C65SjWUL.js → user-guide_mcp-tools.md.49r3L2YE.js} +1 -1
  132. package/public/docs/assets/{user-guide_mcp-tools_compare-runs.md.Cc_gLoix.js → user-guide_mcp-tools_compare-runs.md.BQ_kIptC.js} +11 -6
  133. package/public/docs/assets/user-guide_mcp-tools_compare-runs.md.BQ_kIptC.lean.js +1 -0
  134. package/public/docs/assets/user-guide_mcp-tools_diagnose-run.md.azCZXkH8.js +44 -0
  135. package/public/docs/assets/{user-guide_mcp-tools_diagnose-run.md.BP1vnHA5.lean.js → user-guide_mcp-tools_diagnose-run.md.azCZXkH8.lean.js} +1 -1
  136. package/public/docs/assets/{user-guide_mcp-tools_evaluate-budgets.md.BB0nDY3Z.js → user-guide_mcp-tools_evaluate-budgets.md.dpQpRQ7z.js} +2 -2
  137. package/public/docs/assets/{user-guide_mcp-tools_evaluate-budgets.md.BB0nDY3Z.lean.js → user-guide_mcp-tools_evaluate-budgets.md.dpQpRQ7z.lean.js} +1 -1
  138. package/public/docs/assets/{user-guide_mcp-tools_get-finding-evidence.md.rKyu4wts.js → user-guide_mcp-tools_get-finding-evidence.md.CH6FkNLX.js} +2 -1
  139. package/public/docs/assets/{user-guide_mcp-tools_get-finding-evidence.md.rKyu4wts.lean.js → user-guide_mcp-tools_get-finding-evidence.md.CH6FkNLX.lean.js} +1 -1
  140. package/public/docs/assets/user-guide_run-comparison.md.B_LOkdBf.js +1 -0
  141. package/public/docs/assets/user-guide_run-comparison.md.B_LOkdBf.lean.js +1 -0
  142. package/public/docs/assets/user-guide_understanding-findings.md.C4riKCKl.js +1 -0
  143. package/public/docs/assets/user-guide_understanding-findings.md.C4riKCKl.lean.js +1 -0
  144. package/public/docs/contributor-guide/architecture/board-widgets/caching-and-memory.html +6 -6
  145. package/public/docs/contributor-guide/architecture/board-widgets/plan-advisor.html +6 -6
  146. package/public/docs/contributor-guide/architecture/board-widgets/visual-system-and-templating.html +6 -6
  147. package/public/docs/contributor-guide/architecture/board-widgets.html +6 -6
  148. package/public/docs/contributor-guide/architecture/detector-contract/plan-attribution.html +6 -6
  149. package/public/docs/contributor-guide/architecture/detector-contract/threshold-tables.html +6 -6
  150. package/public/docs/contributor-guide/architecture/detector-contract.html +6 -6
  151. package/public/docs/contributor-guide/architecture/drill-down/plan-graph.html +6 -6
  152. package/public/docs/contributor-guide/architecture/drill-down.html +6 -6
  153. package/public/docs/contributor-guide/architecture/impact-estimation/caveats-tuning-and-coverage.html +6 -6
  154. package/public/docs/contributor-guide/architecture/impact-estimation/stage-union-rollup.html +6 -6
  155. package/public/docs/contributor-guide/architecture/impact-estimation.html +6 -6
  156. package/public/docs/contributor-guide/architecture/index.html +5 -5
  157. package/public/docs/contributor-guide/architecture/overview.html +6 -6
  158. package/public/docs/contributor-guide/architecture/state-and-history/history-server-intake.html +5 -5
  159. package/public/docs/contributor-guide/architecture/state-and-history/run-comparison-internals.html +6 -6
  160. package/public/docs/contributor-guide/architecture/state-and-history.html +5 -5
  161. package/public/docs/contributor-guide/architecture/widget-rendering/findings-tab.html +6 -6
  162. package/public/docs/contributor-guide/architecture/widget-rendering/investigation-routing.html +5 -5
  163. package/public/docs/contributor-guide/architecture/widget-rendering/list-sort-mode.html +6 -6
  164. package/public/docs/contributor-guide/architecture/widget-rendering/reference-section.html +5 -5
  165. package/public/docs/contributor-guide/architecture/widget-rendering/row-expand-contract.html +6 -6
  166. package/public/docs/contributor-guide/architecture/widget-rendering.html +6 -6
  167. package/public/docs/contributor-guide/architecture/worker-protocol/cli-and-mcp.html +6 -6
  168. package/public/docs/contributor-guide/architecture/worker-protocol/core-and-event-validation.html +6 -6
  169. package/public/docs/contributor-guide/architecture/worker-protocol/evidence-availability.html +7 -7
  170. package/public/docs/contributor-guide/architecture/worker-protocol/evidence-report.html +6 -6
  171. package/public/docs/contributor-guide/architecture/worker-protocol.html +6 -6
  172. package/public/docs/contributor-guide/contributing.html +6 -6
  173. package/public/docs/contributor-guide/development-setup.html +8 -8
  174. package/public/docs/contributor-guide/testing.html +9 -6
  175. package/public/docs/hashmap.json +1 -1
  176. package/public/docs/index.html +6 -6
  177. package/public/docs/logo-dark.svg +1 -0
  178. package/public/docs/logo-light.svg +1 -0
  179. package/public/docs/tuning-reference/anti-patterns.html +5 -5
  180. package/public/docs/tuning-reference/aqe.html +5 -5
  181. package/public/docs/tuning-reference/bottleneck-broadcast-sizing.html +5 -5
  182. package/public/docs/tuning-reference/bottleneck-cold-start.html +5 -5
  183. package/public/docs/tuning-reference/bottleneck-duplicate-plan-subtree.html +5 -5
  184. package/public/docs/tuning-reference/bottleneck-failures.html +5 -5
  185. package/public/docs/tuning-reference/bottleneck-gc.html +5 -5
  186. package/public/docs/tuning-reference/bottleneck-job-failure-rate.html +5 -5
  187. package/public/docs/tuning-reference/bottleneck-memory-utilization.html +5 -5
  188. package/public/docs/tuning-reference/bottleneck-retry-waste.html +5 -5
  189. package/public/docs/tuning-reference/bottleneck-shuffle.html +5 -5
  190. package/public/docs/tuning-reference/bottleneck-skew.html +5 -5
  191. package/public/docs/tuning-reference/bottleneck-slow-host.html +5 -5
  192. package/public/docs/tuning-reference/bottleneck-small-files.html +5 -5
  193. package/public/docs/tuning-reference/bottleneck-spill.html +5 -5
  194. package/public/docs/tuning-reference/bottleneck-straggler.html +5 -5
  195. package/public/docs/tuning-reference/bottleneck-tiny-tasks.html +5 -5
  196. package/public/docs/tuning-reference/bottleneck-utilization.html +5 -5
  197. package/public/docs/tuning-reference/caching.html +5 -5
  198. package/public/docs/tuning-reference/cluster-config.html +5 -5
  199. package/public/docs/tuning-reference/config.html +5 -5
  200. package/public/docs/tuning-reference/data-formats.html +5 -5
  201. package/public/docs/tuning-reference/index.html +5 -5
  202. package/public/docs/tuning-reference/intro.html +5 -5
  203. package/public/docs/tuning-reference/joins.html +5 -5
  204. package/public/docs/tuning-reference/memory-model.html +5 -5
  205. package/public/docs/tuning-reference/metrics.html +5 -5
  206. package/public/docs/tuning-reference/partitioning.html +5 -5
  207. package/public/docs/tuning-reference/pyspark.html +5 -5
  208. package/public/docs/tuning-reference/shuffle.html +5 -5
  209. package/public/docs/tuning-reference/spark-architecture.html +5 -5
  210. package/public/docs/tuning-reference/table-formats.html +5 -5
  211. package/public/docs/user-guide/alternative-log-retrieval/managed-platforms.html +5 -5
  212. package/public/docs/user-guide/alternative-log-retrieval/ssh-bastion.html +5 -5
  213. package/public/docs/user-guide/alternative-log-retrieval.html +5 -5
  214. package/public/docs/user-guide/getting-started/ci-and-automation.html +16 -11
  215. package/public/docs/user-guide/getting-started/reading-the-dashboard.html +6 -6
  216. package/public/docs/user-guide/getting-started/regression-metric-keys.html +5 -5
  217. package/public/docs/user-guide/getting-started/tuning-thresholds.html +7 -7
  218. package/public/docs/user-guide/getting-started.html +5 -5
  219. package/public/docs/user-guide/mcp-tools/compare-runs.html +16 -11
  220. package/public/docs/user-guide/mcp-tools/diagnose-run.html +28 -7
  221. package/public/docs/user-guide/mcp-tools/evaluate-budgets.html +6 -6
  222. package/public/docs/user-guide/mcp-tools/get-finding-documentation.html +5 -5
  223. package/public/docs/user-guide/mcp-tools/get-finding-evidence.html +7 -6
  224. package/public/docs/user-guide/mcp-tools/get-reference-doc.html +5 -5
  225. package/public/docs/user-guide/mcp-tools/get-run-summary.html +5 -5
  226. package/public/docs/user-guide/mcp-tools/list-runs.html +5 -5
  227. package/public/docs/user-guide/mcp-tools.html +6 -6
  228. package/public/docs/user-guide/run-comparison/how-stages-are-matched.html +5 -5
  229. package/public/docs/user-guide/run-comparison.html +6 -6
  230. package/public/docs/user-guide/understanding-findings.html +6 -6
  231. package/public/export-template.html +45 -45
  232. package/public/index.html +8 -7
  233. package/public/sample-runs/sample-run.ndjson.gz +0 -0
  234. package/vendor-core/allocation.js +25 -23
  235. package/vendor-core/analyzer.js +85 -58
  236. package/vendor-core/api-merge-writes.js +2 -0
  237. package/vendor-core/aqe-skew.js +347 -0
  238. package/vendor-core/cli/budgets.js +6 -4
  239. package/vendor-core/cli/collect-run-pair.js +89 -0
  240. package/vendor-core/cli/collect-run-worker.js +16 -0
  241. package/vendor-core/cli/collect-run.js +1 -2
  242. package/vendor-core/cli/native-zstd.js +12 -16
  243. package/vendor-core/comparability.js +234 -0
  244. package/vendor-core/comparison-output.js +15 -7
  245. package/vendor-core/comparison-verdict.js +105 -25
  246. package/vendor-core/core-source-hash.txt +1 -1
  247. package/vendor-core/core-time-series.js +0 -1
  248. package/vendor-core/core-usage-locality.js +1 -1
  249. package/vendor-core/detectors.js +1007 -380
  250. package/vendor-core/docs-config.js +0 -4
  251. package/vendor-core/docs-content/detection/cache.md +2 -1
  252. package/vendor-core/docs-content/detection/cfg.md +19 -11
  253. package/vendor-core/docs-content/detection/cold.md +2 -1
  254. package/vendor-core/docs-content/detection/gc.md +7 -3
  255. package/vendor-core/docs-content/detection/host.md +11 -1
  256. package/vendor-core/docs-content/detection/mem.md +17 -6
  257. package/vendor-core/docs-content/detection/part.md +3 -1
  258. package/vendor-core/docs-content/detection/plan.md +55 -13
  259. package/vendor-core/docs-content/detection/shfl.md +11 -5
  260. package/vendor-core/docs-content/detection/skew.md +47 -1
  261. package/vendor-core/docs-content/detection/slow.md +4 -2
  262. package/vendor-core/docs-content/detection/spec.md +6 -1
  263. package/vendor-core/docs-content/detection/spill.md +6 -3
  264. package/vendor-core/docs-content/detection/strag.md +19 -6
  265. package/vendor-core/docs-content/detection/tiny.md +9 -3
  266. package/vendor-core/effective-conf.js +7 -10
  267. package/vendor-core/efficiency-model.js +2 -2
  268. package/vendor-core/etl-phases.js +1 -2
  269. package/vendor-core/event-handlers.js +175 -57
  270. package/vendor-core/event-schemas.js +21 -16
  271. package/vendor-core/evidence-availability.js +9 -2
  272. package/vendor-core/evidence-report.js +118 -35
  273. package/vendor-core/executor-peaks.js +41 -0
  274. package/vendor-core/export-data.js +5 -5
  275. package/vendor-core/finding-identity.js +78 -0
  276. package/vendor-core/finding-presentation.js +116 -33
  277. package/vendor-core/finding-types.js +88 -21
  278. package/vendor-core/format-utils.js +14 -15
  279. package/vendor-core/html-export.js +1 -1
  280. package/vendor-core/impact-band.js +2 -2
  281. package/vendor-core/impact-format.js +47 -19
  282. package/vendor-core/impact-model.js +26 -15
  283. package/vendor-core/job-groups.js +4 -4
  284. package/vendor-core/mcp-server-factory.js +48 -12
  285. package/vendor-core/mcp-tools.js +179 -24
  286. package/vendor-core/median.js +2 -2
  287. package/vendor-core/nested-loop-join.js +73 -0
  288. package/vendor-core/occupancy.js +1 -2
  289. package/vendor-core/parser-worker.js +1 -1
  290. package/vendor-core/plan-graph-model.js +14 -22
  291. package/vendor-core/plan-node-detail.js +2 -3
  292. package/vendor-core/plan-summary.js +24 -19
  293. package/vendor-core/plan-tree-walk.js +6 -8
  294. package/vendor-core/python-stage.js +12 -1
  295. package/vendor-core/recommendation-rollup.js +13 -12
  296. package/vendor-core/redact.js +52 -46
  297. package/vendor-core/run-aggregates.js +6 -8
  298. package/vendor-core/run-comparison.js +226 -66
  299. package/vendor-core/run-identity.js +12 -0
  300. package/vendor-core/run-interpretation.js +21 -0
  301. package/vendor-core/run-metrics.js +2 -2
  302. package/vendor-core/run-output.js +32 -10
  303. package/vendor-core/run-totals.js +12 -0
  304. package/vendor-core/run-verdict.js +76 -3
  305. package/vendor-core/scaling-sim.js +3 -4
  306. package/vendor-core/snappy-block.js +2 -2
  307. package/vendor-core/spark-conf.js +168 -0
  308. package/vendor-core/sql-stages.js +2 -2
  309. package/vendor-core/stage-alignment.js +2 -12
  310. package/vendor-core/stage-identity.js +58 -3
  311. package/vendor-core/stage-label.js +14 -0
  312. package/vendor-core/stage-plan-nodes.js +17 -3
  313. package/vendor-core/stage-quantiles.js +141 -9
  314. package/vendor-core/stage-structure.js +17 -3
  315. package/vendor-core/threshold-overrides.js +9 -3
  316. package/vendor-core/types.js +58 -21
  317. package/vendor-core/wasted-core-hours.js +0 -1
  318. package/vendor-core/write-targets.js +114 -14
  319. package/vendor-core/zstd-worker-client.js +1 -1
  320. package/vendor-core/zstd-worker.js +1 -1
  321. package/public/assets/AutoscalingChurn-CRA2Mb7F.js +0 -1
  322. package/public/assets/CacheUtilization-Bh9OY_V9.js +0 -1
  323. package/public/assets/CachingOpportunity-oCiQwmTJ.js +0 -1
  324. package/public/assets/ColdStart-BJrtjfmn.js +0 -1
  325. package/public/assets/ConfigAudit-DMvKxySP.js +0 -1
  326. package/public/assets/CoreUsageArea-REC2zsKw.js +0 -1
  327. package/public/assets/Dashboard-BHZ76JCu.js +0 -2
  328. package/public/assets/DisclosureContext-OO7X1HAx.js +0 -1
  329. package/public/assets/DuplicatePlanSubtree-BgG-L-cK.js +0 -1
  330. package/public/assets/ExecutorUtilization-D2KhSVbY.js +0 -1
  331. package/public/assets/GcPressure-D1BTE8qh.js +0 -1
  332. package/public/assets/IncompleteRun-DD40xUpy.js +0 -1
  333. package/public/assets/JobFailures-YwNzCF19.js +0 -1
  334. package/public/assets/MemoryUtilization-9b8ee_3_.js +0 -1
  335. package/public/assets/OverBroadcast-CfctS8a8.js +0 -1
  336. package/public/assets/PartitionHint-CUvbnnxy.js +0 -1
  337. package/public/assets/PartitionSizing-VG8kBgG5.js +0 -1
  338. package/public/assets/PlanExplorer-DmubTAOP.js +0 -1
  339. package/public/assets/PlanGraphRoute-DctPZjS0.js +0 -1
  340. package/public/assets/RetryWaste-CnpM8bB7.js +0 -1
  341. package/public/assets/ShuffleIO-D13vGmas.js +0 -1
  342. package/public/assets/Skew-DlagstYP.js +0 -1
  343. package/public/assets/SlowHost-cSkLRZ_e.js +0 -1
  344. package/public/assets/SmallFiles-B-kERMcq.js +0 -1
  345. package/public/assets/SpeculationWaste-DaysAzXO.js +0 -1
  346. package/public/assets/Spill-H44Gz4US.js +0 -1
  347. package/public/assets/StageFailed-DCfii9h_.js +0 -1
  348. package/public/assets/StageFindingGroup-BXJ0Mj5n.js +0 -1
  349. package/public/assets/StageHeader--oN2J-oD.js +0 -1
  350. package/public/assets/StageShape-IZ80CZiJ.js +0 -1
  351. package/public/assets/StageSlowness--BRIaBc1.js +0 -1
  352. package/public/assets/Straggler-Ctq0Df_o.js +0 -1
  353. package/public/assets/TaskFailures-Bks_gqhL.js +0 -1
  354. package/public/assets/TinyTask-BssfzGFB.js +0 -1
  355. package/public/assets/UnderBroadcast-DsScrxc-.js +0 -1
  356. package/public/assets/charts-vendor-0VMaLVLN.js +0 -59
  357. package/public/assets/finding-anchor-BYW1oz5R.js +0 -1
  358. package/public/assets/impact-sort-xzy0g-Vh.js +0 -1
  359. package/public/assets/index-DhpRGMZc.css +0 -2
  360. package/public/assets/index-DwqkFUFk.js +0 -14
  361. package/public/assets/plan-graph-vendor-BYl-AzN5.js +0 -7
  362. package/public/assets/react-vendor-DfpuPQZf.js +0 -9
  363. package/public/assets/select-C8edjYTq.js +0 -1
  364. package/public/assets/usePagedRows-CsuUFeYx.js +0 -1
  365. package/public/assets/useRecentFiles-BvkKo3JN.js +0 -11
  366. package/public/assets/useSortMode-joX71BZN.js +0 -1
  367. package/public/docs/assets/chunks/@localSearchIndexroot.tE5pz54z.js +0 -1
  368. package/public/docs/assets/contributor-guide_architecture_board-widgets.md.YQcj5EI4.js +0 -1
  369. package/public/docs/assets/contributor-guide_architecture_board-widgets.md.YQcj5EI4.lean.js +0 -1
  370. package/public/docs/assets/contributor-guide_architecture_board-widgets_plan-advisor.md.RlzvUmNm.js +0 -1
  371. package/public/docs/assets/contributor-guide_architecture_board-widgets_visual-system-and-templating.md.wulOueeB.lean.js +0 -1
  372. package/public/docs/assets/contributor-guide_architecture_detector-contract.md.N4hhenrA.js +0 -1
  373. package/public/docs/assets/contributor-guide_architecture_detector-contract_plan-attribution.md.yNex4bys.js +0 -1
  374. package/public/docs/assets/contributor-guide_architecture_detector-contract_plan-attribution.md.yNex4bys.lean.js +0 -1
  375. package/public/docs/assets/contributor-guide_architecture_detector-contract_threshold-tables.md.Dp3c40rx.js +0 -1
  376. package/public/docs/assets/contributor-guide_architecture_drill-down_plan-graph.md.DwOozIEs.js +0 -1
  377. package/public/docs/assets/contributor-guide_architecture_impact-estimation.md.DfvbqEUu.js +0 -1
  378. package/public/docs/assets/contributor-guide_architecture_impact-estimation_caveats-tuning-and-coverage.md.Cwm1jHmn.js +0 -1
  379. package/public/docs/assets/contributor-guide_architecture_impact-estimation_stage-union-rollup.md.DdCGtAGu.js +0 -1
  380. package/public/docs/assets/contributor-guide_architecture_impact-estimation_stage-union-rollup.md.DdCGtAGu.lean.js +0 -1
  381. package/public/docs/assets/contributor-guide_architecture_overview.md.C1sSvm9i.js +0 -1
  382. package/public/docs/assets/contributor-guide_architecture_state-and-history_run-comparison-internals.md.CZA0JLtV.js +0 -1
  383. package/public/docs/assets/contributor-guide_architecture_widget-rendering.md.BOZ1azXG.js +0 -1
  384. package/public/docs/assets/contributor-guide_architecture_widget-rendering_findings-tab.md.BQXycK6G.js +0 -1
  385. package/public/docs/assets/contributor-guide_architecture_widget-rendering_findings-tab.md.BQXycK6G.lean.js +0 -1
  386. package/public/docs/assets/contributor-guide_architecture_worker-protocol.md.BAnhi2-d.lean.js +0 -1
  387. package/public/docs/assets/contributor-guide_architecture_worker-protocol_cli-and-mcp.md.BX1XnFbq.js +0 -1
  388. package/public/docs/assets/contributor-guide_architecture_worker-protocol_evidence-report.md.CiQl1MLb.js +0 -1
  389. package/public/docs/assets/contributor-guide_contributing.md.CQMvGwFt.js +0 -1
  390. package/public/docs/assets/contributor-guide_development-setup.md.DQdzera7.js +0 -15
  391. package/public/docs/assets/contributor-guide_development-setup.md.DQdzera7.lean.js +0 -1
  392. package/public/docs/assets/contributor-guide_testing.md.By6XGR9a.js +0 -1
  393. package/public/docs/assets/user-guide_getting-started_ci-and-automation.md.BEepbDDL.js +0 -24
  394. package/public/docs/assets/user-guide_getting-started_reading-the-dashboard.md.Obf3W3__.js +0 -1
  395. package/public/docs/assets/user-guide_mcp-tools_compare-runs.md.Cc_gLoix.lean.js +0 -1
  396. package/public/docs/assets/user-guide_mcp-tools_diagnose-run.md.BP1vnHA5.js +0 -23
  397. package/public/docs/assets/user-guide_run-comparison.md.BUALkohi.js +0 -1
  398. package/public/docs/assets/user-guide_run-comparison.md.BUALkohi.lean.js +0 -1
  399. package/public/docs/assets/user-guide_understanding-findings.md.3C7KCEZO.js +0 -1
  400. package/public/docs/assets/user-guide_understanding-findings.md.3C7KCEZO.lean.js +0 -1
  401. /package/public/docs/assets/{contributor-guide_architecture_board-widgets_caching-and-memory.md.CQgn1t_M.lean.js → contributor-guide_architecture_board-widgets_caching-and-memory.md.BYDo3ClR.lean.js} +0 -0
  402. /package/public/docs/assets/{contributor-guide_architecture_board-widgets_plan-advisor.md.RlzvUmNm.lean.js → contributor-guide_architecture_board-widgets_plan-advisor.md.ajUAVdbc.lean.js} +0 -0
  403. /package/public/docs/assets/{contributor-guide_architecture_overview.md.C1sSvm9i.lean.js → contributor-guide_architecture_overview.md.nxkpOhgf.lean.js} +0 -0
  404. /package/public/docs/assets/{contributor-guide_architecture_widget-rendering.md.BOZ1azXG.lean.js → contributor-guide_architecture_widget-rendering.md.BrSz8Ezh.lean.js} +0 -0
  405. /package/public/docs/assets/{contributor-guide_architecture_widget-rendering_list-sort-mode.md.BuHKgH0C.lean.js → contributor-guide_architecture_widget-rendering_list-sort-mode.md.37hcZJ7q.lean.js} +0 -0
  406. /package/public/docs/assets/{contributor-guide_architecture_widget-rendering_row-expand-contract.md.ZT89u9f1.lean.js → contributor-guide_architecture_widget-rendering_row-expand-contract.md.mK_VmAWk.lean.js} +0 -0
  407. /package/public/docs/assets/{contributor-guide_architecture_worker-protocol_core-and-event-validation.md.DSVFPpWb.lean.js → contributor-guide_architecture_worker-protocol_core-and-event-validation.md.DVSXn-bb.lean.js} +0 -0
  408. /package/public/docs/assets/{contributor-guide_contributing.md.CQMvGwFt.lean.js → contributor-guide_contributing.md.DBW4drtZ.lean.js} +0 -0
  409. /package/public/docs/assets/{user-guide_getting-started_reading-the-dashboard.md.Obf3W3__.lean.js → user-guide_getting-started_reading-the-dashboard.md.CGaxPX_1.lean.js} +0 -0
  410. /package/public/docs/assets/{user-guide_mcp-tools.md.C65SjWUL.lean.js → user-guide_mcp-tools.md.49r3L2YE.lean.js} +0 -0
@@ -6,11 +6,11 @@
6
6
  <title>Tiny Tasks | Spark Tuning Reference</title>
7
7
  <meta name="description" content="Detecting and mitigating tiny-task overhead: scheduling/serialization cost dominating once partitions shrink too far, and coalesce/repartition sizing fixes.">
8
8
  <meta name="generator" content="VitePress v1.6.4">
9
- <link rel="preload stylesheet" href="/docs/assets/style.CyK9Ss73.css" as="style">
9
+ <link rel="preload stylesheet" href="/docs/assets/style.Cfxqlj0y.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.CnWL6bKV.js"></script>
13
- <link rel="modulepreload" href="/docs/assets/chunks/theme.BH-2HuRf.js">
12
+ <script type="module" src="/docs/assets/app.1gvzd5Zb.js"></script>
13
+ <link rel="modulepreload" href="/docs/assets/chunks/theme.C5lLqUv7.js">
14
14
  <link rel="modulepreload" href="/docs/assets/chunks/framework.DSg0KOwT.js">
15
15
  <link rel="modulepreload" href="/docs/assets/tuning-reference_bottleneck-tiny-tasks.md.DQCftGhu.lean.js">
16
16
  <script>(()=>{const c=`${`[${["data","shuffle","product","bar"].join("-")}]`}, .VPNav, .VPLocalNav`,a=24,d=document.documentElement,l=t=>{const e=getComputedStyle(t);return e.display==="none"||t.getClientRects().length===0?0:e.position==="fixed"?t.getBoundingClientRect().bottom:e.position==="sticky"?(parseFloat(e.top)||0)+t.offsetHeight:0},u=()=>{try{return location.hash?document.getElementById(decodeURIComponent(location.hash.slice(1))):null}catch{return null}};let r=null;const s=()=>{const t=Array.from(document.querySelectorAll(c),l),e=Math.ceil(Math.max(0,...t))+a;if(e===r)return;const n=r;r=e,d.style.setProperty("--sf-anchor-offset",`${r}px`);const o=n===null?null:u();if(!o)return;const f=(parseFloat(getComputedStyle(o).paddingTop)||0)+2;Math.abs(o.getBoundingClientRect().top-n)<=f&&o.scrollIntoView()},i=()=>{const t=document.createElement("div");t.setAttribute("data-sf-anchor-offset",""),t.setAttribute("aria-hidden","true"),document.body.appendChild(t);const e=window.ResizeObserver?new ResizeObserver(s):null,n=()=>{e&&document.querySelectorAll(c).forEach(o=>e.observe(o)),s()};n(),new MutationObserver(n).observe(document.body,{childList:!0,subtree:!0}),window.addEventListener("resize",s),window.addEventListener("load",s)};document.readyState==="loading"?document.addEventListener("DOMContentLoaded",i,{once:!0}):i()})();</script>
@@ -19,7 +19,7 @@
19
19
  <script id="check-mac-os">document.documentElement.classList.toggle("mac",/Mac|iPhone|iPod|iPad/i.test(navigator.platform));</script>
20
20
  </head>
21
21
  <body>
22
- <div id="app"><div class="Layout" data-v-5d98c3a5><!--[--><!--]--><!--[--><span tabindex="-1" data-v-0b0ada53></span><a href="#VPContent" class="VPSkipLink visually-hidden" data-v-0b0ada53>Skip to content</a><!--]--><!----><header class="VPNav" data-v-5d98c3a5 data-v-ae24b3ad><div class="VPNavBar" data-v-ae24b3ad data-v-6aa21345><div class="wrapper" data-v-6aa21345><div class="container" data-v-6aa21345><div class="title" data-v-6aa21345><div class="VPNavBarTitle has-sidebar" data-v-6aa21345 data-v-1168a8e4><a class="title" href="/docs/" data-v-1168a8e4><!--[--><!--]--><!--[--><img class="VPImage logo" src="/docs/favicon.svg" alt data-v-8426fc1a><!--]--><span data-v-1168a8e4>SparkForensics</span><!--[--><!--]--></a></div></div><div class="content" data-v-6aa21345><div class="content-body" data-v-6aa21345><!--[--><!--]--><div class="VPNavBarSearch search" data-v-6aa21345><!--[--><!----><div id="local-search"><button type="button" class="DocSearch DocSearch-Button" aria-label="Search"><span class="DocSearch-Button-Container"><span class="vp-icon DocSearch-Search-Icon"></span><span class="DocSearch-Button-Placeholder">Search</span></span><span class="DocSearch-Button-Keys"><kbd class="DocSearch-Button-Key"></kbd><kbd class="DocSearch-Button-Key">K</kbd></span></button></div><!--]--></div><nav aria-labelledby="main-nav-aria-label" class="VPNavBarMenu menu" data-v-6aa21345 data-v-dc692963><span id="main-nav-aria-label" class="visually-hidden" data-v-dc692963> Main Navigation </span><!--[--><!--[--><a class="VPLink link VPNavBarMenuLink" href="/docs/user-guide/getting-started.html" tabindex="0" data-v-dc692963 data-v-e56f3d57><!--[--><span data-v-e56f3d57>User Guide</span><!--]--></a><!--]--><!--[--><a class="VPLink link VPNavBarMenuLink" href="/docs/contributor-guide/development-setup.html" tabindex="0" data-v-dc692963 data-v-e56f3d57><!--[--><span data-v-e56f3d57>Contributor Guide</span><!--]--></a><!--]--><!--[--><a class="VPLink link VPNavBarMenuLink" href="/docs/tuning-reference/" tabindex="0" data-v-dc692963 data-v-e56f3d57><!--[--><span data-v-e56f3d57>Tuning Reference</span><!--]--></a><!--]--><!--]--></nav><!----><div class="VPNavBarAppearance appearance" data-v-6aa21345 data-v-6c893767><button class="VPSwitch VPSwitchAppearance" type="button" role="switch" title aria-checked="false" data-v-6c893767 data-v-5337faa4 data-v-1d5665e3><span class="check" data-v-1d5665e3><span class="icon" data-v-1d5665e3><!--[--><span class="vpi-sun sun" data-v-5337faa4></span><span class="vpi-moon moon" data-v-5337faa4></span><!--]--></span></span></button></div><!----><div class="VPFlyout VPNavBarExtra extra" data-v-6aa21345 data-v-bb2aa2f0 data-v-cf11d7a2><button type="button" class="button" aria-haspopup="true" aria-expanded="false" aria-label="extra navigation" data-v-cf11d7a2><span class="vpi-more-horizontal icon" data-v-cf11d7a2></span></button><div class="menu" data-v-cf11d7a2><div class="VPMenu" data-v-cf11d7a2 data-v-b98bc113><!----><!--[--><!--[--><!----><div class="group" data-v-bb2aa2f0><div class="item appearance" data-v-bb2aa2f0><p class="label" data-v-bb2aa2f0>Appearance</p><div class="appearance-action" data-v-bb2aa2f0><button class="VPSwitch VPSwitchAppearance" type="button" role="switch" title aria-checked="false" data-v-bb2aa2f0 data-v-5337faa4 data-v-1d5665e3><span class="check" data-v-1d5665e3><span class="icon" data-v-1d5665e3><!--[--><span class="vpi-sun sun" data-v-5337faa4></span><span class="vpi-moon moon" data-v-5337faa4></span><!--]--></span></span></button></div></div></div><!----><!--]--><!--]--></div></div></div><!--[--><!--]--><button type="button" class="VPNavBarHamburger hamburger" aria-label="mobile navigation" aria-expanded="false" aria-controls="VPNavScreen" data-v-6aa21345 data-v-e5dd9c1c><span class="container" data-v-e5dd9c1c><span class="top" data-v-e5dd9c1c></span><span class="middle" data-v-e5dd9c1c></span><span class="bottom" data-v-e5dd9c1c></span></span></button></div></div></div></div><div class="divider" data-v-6aa21345><div class="divider-line" data-v-6aa21345></div></div></div><!----></header><div class="VPLocalNav has-sidebar empty" data-v-5d98c3a5 data-v-a6f0e41e><div class="container" data-v-a6f0e41e><button class="menu" aria-expanded="false" aria-controls="VPSidebarNav" data-v-a6f0e41e><span class="vpi-align-left menu-icon" data-v-a6f0e41e></span><span class="menu-text" data-v-a6f0e41e>Menu</span></button><div class="VPLocalNavOutlineDropdown" style="--vp-vh:0px;" data-v-a6f0e41e data-v-8a42e2b4><button data-v-8a42e2b4>Return to top</button><!----></div></div></div><aside class="VPSidebar" data-v-5d98c3a5 data-v-319d5ca6><div class="curtain" data-v-319d5ca6></div><nav class="nav" id="VPSidebarNav" aria-labelledby="sidebar-aria-label" tabindex="-1" data-v-319d5ca6><span class="visually-hidden" id="sidebar-aria-label" data-v-319d5ca6> Sidebar Navigation </span><!--[--><!--]--><!--[--><div class="no-transition group" data-v-c40bc020><section class="VPSidebarItem level-0" 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" 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 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>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_bottleneck-tiny-tasks" data-v-39a288b8><div><h1 id="bottleneck-tiny-tasks" tabindex="-1">Tiny Tasks <a class="header-anchor" href="#bottleneck-tiny-tasks" aria-label="Permalink to &quot;Tiny Tasks {#bottleneck-tiny-tasks}&quot;">​</a></h1><p><span class="tag">TINY</span></p><h2 id="what-it-is" tabindex="-1">What it is <a class="header-anchor" href="#what-it-is" aria-label="Permalink to &quot;What it is&quot;">​</a></h2><p>Every task pays a fixed placement and serialization cost before it does any real work. Spark schedules around data locality rather than moving data to code: &quot;Spark builds its scheduling around this general principle&quot; that shipping serialized code is cheaper than shipping data, preferring <code>PROCESS_LOCAL</code> locality down to <code>ANY</code> and waiting a configurable timeout for a busy CPU to free up before shipping data to a farther executor<sup class="footnote-ref"><a href="#fn1" id="fnref1">[1]</a></sup>. On top of that placement cost, every task also pays a serialization cost for its closure and, if not using Kryo, for its data: Java&#39;s default <code>ObjectOutputStream</code>-based serialization &quot;is flexible but often quite slow, and leads to large serialized formats,&quot; while Kryo is &quot;significantly faster and more compact than Java serialization (often as much as 10x)&quot;<sup class="footnote-ref"><a href="#fn1" id="fnref1:1">[1:1]</a></sup>. None of that overhead is large per task: Spark&#39;s own guidance leans toward more, smaller tasks rather than fewer, larger ones, unlike MapReduce: &quot;it&#39;s almost always better to err on the side of a larger number of tasks (and thus partitions)... The difference stems from the fact that MapReduce has a high startup overhead for tasks, while Spark does not&quot;<sup class="footnote-ref"><a href="#fn2" id="fnref2">[2]</a></sup>. But once partitions get small enough, that per-task overhead stops being negligible and starts to dominate.</p><h2 id="how-it-s-detected" tabindex="-1">How it&#39;s detected <a class="header-anchor" href="#how-it-s-detected" aria-label="Permalink to &quot;How it&#39;s detected&quot;">​</a></h2><p>The failure mode is partitions so small that scheduling and serialization overhead outweighs the actual work. With Spark&#39;s default of 200 shuffle partitions applied to a dataset of only a few megabytes, &quot;those 200 partitions will each get like ten rows. Tasks become microscopic. Most of your CPUs will just be sitting there doing nothing, wasting cluster hours&quot;<sup class="footnote-ref"><a href="#fn3" id="fnref3">[3]</a></sup>. The same small-partition penalty shows up on the <a href="./bottleneck-shuffle.html">shuffle-read side</a>: production measurements found &quot;the average shuffle block size is only 10s of KBs, which leads to delayed shuffle data fetch,&quot; and the shuffle reduce stages with the largest fetch delays (over 30 seconds per task) were consistently the ones with small block sizes<sup class="footnote-ref"><a href="#fn4" id="fnref4">[4]</a></sup>. A high task count paired with very short median task duration, and/or very small shuffle block sizes on the read side, are the signals to look for.</p><h2 id="why-it-matters" tabindex="-1">Why it matters <a class="header-anchor" href="#why-it-matters" aria-label="Permalink to &quot;Why it matters&quot;">​</a></h2><p>Tiny tasks waste cluster capacity even though no single task is a straggler the way <a href="./bottleneck-skew.html">skewed</a> or <a href="./bottleneck-straggler.html">straggler</a> tasks are: the cost here is spread evenly across thousands of tasks, each individually cheap but collectively adding up in scheduling and serialization overhead, while cores that could be doing other useful work sit mostly idle between task launches<sup class="footnote-ref"><a href="#fn3" id="fnref3:1">[3:1]</a></sup>.</p><h2 id="how-to-fix-it" tabindex="-1">How to fix it <a class="header-anchor" href="#how-to-fix-it" aria-label="Permalink to &quot;How to fix it&quot;">​</a></h2><ul><li><code>coalesce()</code> merges existing partitions without a shuffle (&quot;no data movement, no shuffle&quot;) and is typically used right before a write, e.g. <code>df.coalesce(100).write.parquet(...)</code>, to collapse many tiny output files into a manageable number cheaply<sup class="footnote-ref"><a href="#fn3" id="fnref3:2">[3:2]</a></sup>. Because it only stacks partitions together rather than redistributing data, it doesn&#39;t fix an uneven underlying distribution (uneven input partitions stay uneven, just grouped) and pushing it too far (<code>coalesce(1)</code>) kills parallelism by funneling all work onto one executor while the rest sit idle<sup class="footnote-ref"><a href="#fn3" id="fnref3:3">[3:3]</a></sup>.</li><li><code>repartition()</code> performs a full reshuffle, giving control and rebalancing that Spark won&#39;t do on its own: with <code>df.repartition(200)</code>, &quot;you&#39;re paying for predictability&quot;<sup class="footnote-ref"><a href="#fn3" id="fnref3:4">[3:4]</a></sup>. Use it when the partitioning itself needs to be fixed or rebalanced, not merely reduced in count, accepting the shuffle cost to get there.</li><li>There&#39;s a middle option, <code>coalesce(N, shuffle=True)</code>, which &quot;acts more like a repartition, but leaning toward reduction... not free (you pay for the shuffle cost) but you get better distribution and fewer partitions&quot;<sup class="footnote-ref"><a href="#fn3" id="fnref3:5">[3:5]</a></sup>.</li><li>Rule of thumb: reach for <code>coalesce()</code> when only the partition count needs to shrink and the existing distribution is already reasonably even (e.g. collapsing output files); reach for <code>repartition()</code> when the distribution itself is the problem.</li></ul><blockquote><p><strong>PySpark:</strong> both are one-line calls on a DataFrame: <code>df.coalesce(100)</code> for a shuffle-free merge, <code>df.repartition(200)</code> for a full reshuffle, or <code>df.coalesce(100, shuffle=True)</code> for the shuffled middle option.</p></blockquote><p>The three sizing calls, side by side:</p><div class="language-python vp-adaptive-theme"><button title="Copy Code" class="copy"></button><span class="lang">python</span><pre class="shiki shiki-themes github-light github-dark vp-code" tabindex="0"><code><span class="line"><span style="--shiki-light:#6A737D;--shiki-dark:#6A737D;"># Collapse many tiny output files without a shuffle (use when distribution is already even)</span></span>
22
+ <div id="app"><div class="Layout" data-v-5d98c3a5><!--[--><!--]--><!--[--><span tabindex="-1" data-v-0b0ada53></span><a href="#VPContent" class="VPSkipLink visually-hidden" data-v-0b0ada53>Skip to content</a><!--]--><!----><header class="VPNav" data-v-5d98c3a5 data-v-ae24b3ad><div class="VPNavBar" data-v-ae24b3ad data-v-6aa21345><div class="wrapper" data-v-6aa21345><div class="container" data-v-6aa21345><div class="title" data-v-6aa21345><div class="VPNavBarTitle has-sidebar" data-v-6aa21345 data-v-1168a8e4><a class="title" href="/docs/" data-v-1168a8e4><!--[--><!--]--><!--[--><!--[--><!--[--><img class="VPImage dark logo" src="/docs/logo-dark.svg" alt data-v-8426fc1a><!--]--><!--[--><img class="VPImage light logo" src="/docs/logo-light.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><!--]--><!--[--><a class="VPLink link VPNavBarMenuLink" href="/docs/.." target="_self" tabindex="0" data-v-dc692963 data-v-e56f3d57><!--[--><span data-v-e56f3d57>Open app</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" 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 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>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_bottleneck-tiny-tasks" data-v-39a288b8><div><h1 id="bottleneck-tiny-tasks" tabindex="-1">Tiny Tasks <a class="header-anchor" href="#bottleneck-tiny-tasks" aria-label="Permalink to &quot;Tiny Tasks {#bottleneck-tiny-tasks}&quot;">​</a></h1><p><span class="tag">TINY</span></p><h2 id="what-it-is" tabindex="-1">What it is <a class="header-anchor" href="#what-it-is" aria-label="Permalink to &quot;What it is&quot;">​</a></h2><p>Every task pays a fixed placement and serialization cost before it does any real work. Spark schedules around data locality rather than moving data to code: &quot;Spark builds its scheduling around this general principle&quot; that shipping serialized code is cheaper than shipping data, preferring <code>PROCESS_LOCAL</code> locality down to <code>ANY</code> and waiting a configurable timeout for a busy CPU to free up before shipping data to a farther executor<sup class="footnote-ref"><a href="#fn1" id="fnref1">[1]</a></sup>. On top of that placement cost, every task also pays a serialization cost for its closure and, if not using Kryo, for its data: Java&#39;s default <code>ObjectOutputStream</code>-based serialization &quot;is flexible but often quite slow, and leads to large serialized formats,&quot; while Kryo is &quot;significantly faster and more compact than Java serialization (often as much as 10x)&quot;<sup class="footnote-ref"><a href="#fn1" id="fnref1:1">[1:1]</a></sup>. None of that overhead is large per task: Spark&#39;s own guidance leans toward more, smaller tasks rather than fewer, larger ones, unlike MapReduce: &quot;it&#39;s almost always better to err on the side of a larger number of tasks (and thus partitions)... The difference stems from the fact that MapReduce has a high startup overhead for tasks, while Spark does not&quot;<sup class="footnote-ref"><a href="#fn2" id="fnref2">[2]</a></sup>. But once partitions get small enough, that per-task overhead stops being negligible and starts to dominate.</p><h2 id="how-it-s-detected" tabindex="-1">How it&#39;s detected <a class="header-anchor" href="#how-it-s-detected" aria-label="Permalink to &quot;How it&#39;s detected&quot;">​</a></h2><p>The failure mode is partitions so small that scheduling and serialization overhead outweighs the actual work. With Spark&#39;s default of 200 shuffle partitions applied to a dataset of only a few megabytes, &quot;those 200 partitions will each get like ten rows. Tasks become microscopic. Most of your CPUs will just be sitting there doing nothing, wasting cluster hours&quot;<sup class="footnote-ref"><a href="#fn3" id="fnref3">[3]</a></sup>. The same small-partition penalty shows up on the <a href="./bottleneck-shuffle.html">shuffle-read side</a>: production measurements found &quot;the average shuffle block size is only 10s of KBs, which leads to delayed shuffle data fetch,&quot; and the shuffle reduce stages with the largest fetch delays (over 30 seconds per task) were consistently the ones with small block sizes<sup class="footnote-ref"><a href="#fn4" id="fnref4">[4]</a></sup>. A high task count paired with very short median task duration, and/or very small shuffle block sizes on the read side, are the signals to look for.</p><h2 id="why-it-matters" tabindex="-1">Why it matters <a class="header-anchor" href="#why-it-matters" aria-label="Permalink to &quot;Why it matters&quot;">​</a></h2><p>Tiny tasks waste cluster capacity even though no single task is a straggler the way <a href="./bottleneck-skew.html">skewed</a> or <a href="./bottleneck-straggler.html">straggler</a> tasks are: the cost here is spread evenly across thousands of tasks, each individually cheap but collectively adding up in scheduling and serialization overhead, while cores that could be doing other useful work sit mostly idle between task launches<sup class="footnote-ref"><a href="#fn3" id="fnref3:1">[3:1]</a></sup>.</p><h2 id="how-to-fix-it" tabindex="-1">How to fix it <a class="header-anchor" href="#how-to-fix-it" aria-label="Permalink to &quot;How to fix it&quot;">​</a></h2><ul><li><code>coalesce()</code> merges existing partitions without a shuffle (&quot;no data movement, no shuffle&quot;) and is typically used right before a write, e.g. <code>df.coalesce(100).write.parquet(...)</code>, to collapse many tiny output files into a manageable number cheaply<sup class="footnote-ref"><a href="#fn3" id="fnref3:2">[3:2]</a></sup>. Because it only stacks partitions together rather than redistributing data, it doesn&#39;t fix an uneven underlying distribution (uneven input partitions stay uneven, just grouped) and pushing it too far (<code>coalesce(1)</code>) kills parallelism by funneling all work onto one executor while the rest sit idle<sup class="footnote-ref"><a href="#fn3" id="fnref3:3">[3:3]</a></sup>.</li><li><code>repartition()</code> performs a full reshuffle, giving control and rebalancing that Spark won&#39;t do on its own: with <code>df.repartition(200)</code>, &quot;you&#39;re paying for predictability&quot;<sup class="footnote-ref"><a href="#fn3" id="fnref3:4">[3:4]</a></sup>. Use it when the partitioning itself needs to be fixed or rebalanced, not merely reduced in count, accepting the shuffle cost to get there.</li><li>There&#39;s a middle option, <code>coalesce(N, shuffle=True)</code>, which &quot;acts more like a repartition, but leaning toward reduction... not free (you pay for the shuffle cost) but you get better distribution and fewer partitions&quot;<sup class="footnote-ref"><a href="#fn3" id="fnref3:5">[3:5]</a></sup>.</li><li>Rule of thumb: reach for <code>coalesce()</code> when only the partition count needs to shrink and the existing distribution is already reasonably even (e.g. collapsing output files); reach for <code>repartition()</code> when the distribution itself is the problem.</li></ul><blockquote><p><strong>PySpark:</strong> both are one-line calls on a DataFrame: <code>df.coalesce(100)</code> for a shuffle-free merge, <code>df.repartition(200)</code> for a full reshuffle, or <code>df.coalesce(100, shuffle=True)</code> for the shuffled middle option.</p></blockquote><p>The three sizing calls, side by side:</p><div class="language-python vp-adaptive-theme"><button title="Copy Code" class="copy"></button><span class="lang">python</span><pre class="shiki shiki-themes github-light github-dark vp-code" tabindex="0"><code><span class="line"><span style="--shiki-light:#6A737D;--shiki-dark:#6A737D;"># Collapse many tiny output files without a shuffle (use when distribution is already even)</span></span>
23
23
  <span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">df.coalesce(</span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">100</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">).write.parquet(path)</span></span>
24
24
  <span class="line"></span>
25
25
  <span class="line"><span style="--shiki-light:#6A737D;--shiki-dark:#6A737D;"># Full reshuffle to a target count — use when the distribution itself needs rebalancing</span></span>
@@ -27,7 +27,7 @@
27
27
  <span class="line"></span>
28
28
  <span class="line"><span style="--shiki-light:#6A737D;--shiki-dark:#6A737D;"># Middle ground: reduce partition count but still rebalance (pays a shuffle)</span></span>
29
29
  <span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">df </span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583;">=</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> df.coalesce(</span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">100</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">, </span><span style="--shiki-light:#E36209;--shiki-dark:#FFAB70;">shuffle</span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583;">=</span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">True</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">)</span></span></code></pre></div><h2 id="limitations-false-positive-risk" tabindex="-1">Limitations / false-positive risk <a class="header-anchor" href="#limitations-false-positive-risk" aria-label="Permalink to &quot;Limitations / false-positive risk&quot;">​</a></h2><p>Very short tasks are not always a problem. A tiny final stage can be perfectly fine, and one that just writes a small result set doesn&#39;t need to be resized. The scheduling-overhead penalty only bites when tiny tasks dominate the stage, so treat a handful of short tasks as noise rather than a finding.</p><h2 id="related" tabindex="-1">Related <a class="header-anchor" href="#related" aria-label="Permalink to &quot;Related&quot;">​</a></h2><ul><li><strong>Partition sizing:</strong> <a href="./partitioning.html">Partitioning</a></li></ul><hr class="footnotes-sep"><section class="footnotes"><ol class="footnotes-list"><li id="fn1" class="footnote-item"><p><a href="https://spark.apache.org/docs/latest/tuning.html" target="_blank" rel="noreferrer">Tuning (Spark)</a> <a href="#fnref1" class="footnote-backref">↩︎</a> <a href="#fnref1:1" 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): Cloudera</a> <a href="#fnref2" class="footnote-backref">↩︎</a></p></li><li id="fn3" class="footnote-item"><p><a href="https://luminousmen.com/post/spark-partitions" target="_blank" rel="noreferrer">Spark Partitions</a> <a href="#fnref3" class="footnote-backref">↩︎</a> <a href="#fnref3:1" class="footnote-backref">↩︎</a> <a href="#fnref3:2" class="footnote-backref">↩︎</a> <a href="#fnref3:3" class="footnote-backref">↩︎</a> <a href="#fnref3:4" class="footnote-backref">↩︎</a> <a href="#fnref3:5" class="footnote-backref">↩︎</a></p></li><li id="fn4" class="footnote-item"><p><a href="https://issues.apache.org/jira/browse/SPARK-30602" target="_blank" rel="noreferrer">SPARK-30602</a> <a href="#fnref4" 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/bottleneck-retry-waste.html" data-v-e257564d><!--[--><span class="desc" data-v-e257564d>Previous page</span><span class="title" data-v-e257564d>Retry Waste</span><!--]--></a></div><div class="pager" data-v-e257564d><a class="VPLink link pager-link next" href="/docs/tuning-reference/bottleneck-job-failure-rate.html" data-v-e257564d><!--[--><span class="desc" data-v-e257564d>Next page</span><span class="title" data-v-e257564d>Job Failure Rate</span><!--]--></a></div></nav></footer><!--[--><!--]--></div></div></div><!--[--><!--]--></div></div><!----><!--[--><!--]--></div></div>
30
- <script>window.__VP_HASH_MAP__=JSON.parse("{\"contributor-guide_architecture_board-widgets.md\":\"YQcj5EI4\",\"contributor-guide_architecture_board-widgets_caching-and-memory.md\":\"CQgn1t_M\",\"contributor-guide_architecture_board-widgets_plan-advisor.md\":\"RlzvUmNm\",\"contributor-guide_architecture_board-widgets_visual-system-and-templating.md\":\"wulOueeB\",\"contributor-guide_architecture_detector-contract.md\":\"N4hhenrA\",\"contributor-guide_architecture_detector-contract_plan-attribution.md\":\"yNex4bys\",\"contributor-guide_architecture_detector-contract_threshold-tables.md\":\"Dp3c40rx\",\"contributor-guide_architecture_drill-down.md\":\"CqZPrdo9\",\"contributor-guide_architecture_drill-down_plan-graph.md\":\"DwOozIEs\",\"contributor-guide_architecture_impact-estimation.md\":\"DfvbqEUu\",\"contributor-guide_architecture_impact-estimation_caveats-tuning-and-coverage.md\":\"Cwm1jHmn\",\"contributor-guide_architecture_impact-estimation_stage-union-rollup.md\":\"DdCGtAGu\",\"contributor-guide_architecture_index.md\":\"tymxf1Fh\",\"contributor-guide_architecture_overview.md\":\"C1sSvm9i\",\"contributor-guide_architecture_state-and-history.md\":\"DyCBdjuM\",\"contributor-guide_architecture_state-and-history_history-server-intake.md\":\"C298hrHZ\",\"contributor-guide_architecture_state-and-history_run-comparison-internals.md\":\"CZA0JLtV\",\"contributor-guide_architecture_widget-rendering.md\":\"BOZ1azXG\",\"contributor-guide_architecture_widget-rendering_findings-tab.md\":\"BQXycK6G\",\"contributor-guide_architecture_widget-rendering_investigation-routing.md\":\"BGdiyElu\",\"contributor-guide_architecture_widget-rendering_list-sort-mode.md\":\"BuHKgH0C\",\"contributor-guide_architecture_widget-rendering_reference-section.md\":\"DWqC80bN\",\"contributor-guide_architecture_widget-rendering_row-expand-contract.md\":\"ZT89u9f1\",\"contributor-guide_architecture_worker-protocol.md\":\"BAnhi2-d\",\"contributor-guide_architecture_worker-protocol_cli-and-mcp.md\":\"BX1XnFbq\",\"contributor-guide_architecture_worker-protocol_core-and-event-validation.md\":\"DSVFPpWb\",\"contributor-guide_architecture_worker-protocol_evidence-availability.md\":\"CjimIDBY\",\"contributor-guide_architecture_worker-protocol_evidence-report.md\":\"CiQl1MLb\",\"contributor-guide_contributing.md\":\"CQMvGwFt\",\"contributor-guide_development-setup.md\":\"DQdzera7\",\"contributor-guide_testing.md\":\"By6XGR9a\",\"index.md\":\"CHJVslga\",\"tuning-reference_anti-patterns.md\":\"D08Uaod7\",\"tuning-reference_aqe.md\":\"C1Ae6A8u\",\"tuning-reference_bottleneck-broadcast-sizing.md\":\"6wjKuJNE\",\"tuning-reference_bottleneck-cold-start.md\":\"BVQbsuHP\",\"tuning-reference_bottleneck-duplicate-plan-subtree.md\":\"DtaYnaiF\",\"tuning-reference_bottleneck-failures.md\":\"Z1Tdmdd3\",\"tuning-reference_bottleneck-gc.md\":\"BCnXLf1n\",\"tuning-reference_bottleneck-job-failure-rate.md\":\"CcvQj2g9\",\"tuning-reference_bottleneck-memory-utilization.md\":\"B-C0-8h-\",\"tuning-reference_bottleneck-retry-waste.md\":\"DCnhWiqj\",\"tuning-reference_bottleneck-shuffle.md\":\"B5OMJCd3\",\"tuning-reference_bottleneck-skew.md\":\"Cvo6NQm_\",\"tuning-reference_bottleneck-slow-host.md\":\"ja5qr3wq\",\"tuning-reference_bottleneck-small-files.md\":\"Crjtb0i2\",\"tuning-reference_bottleneck-spill.md\":\"Bl8KtSRg\",\"tuning-reference_bottleneck-straggler.md\":\"B0VN8reT\",\"tuning-reference_bottleneck-tiny-tasks.md\":\"DQCftGhu\",\"tuning-reference_bottleneck-utilization.md\":\"BXDl30f9\",\"tuning-reference_caching.md\":\"CcaiMn_7\",\"tuning-reference_cluster-config.md\":\"DbWG1yZq\",\"tuning-reference_config.md\":\"YUqSpwFB\",\"tuning-reference_data-formats.md\":\"C5DX5xL4\",\"tuning-reference_index.md\":\"ZVIpQ6Dk\",\"tuning-reference_intro.md\":\"BSSaDlqx\",\"tuning-reference_joins.md\":\"BVhNCDnE\",\"tuning-reference_memory-model.md\":\"CfjFdgbl\",\"tuning-reference_metrics.md\":\"C64VNEL4\",\"tuning-reference_partitioning.md\":\"CtLK0xsS\",\"tuning-reference_pyspark.md\":\"D-92XgF8\",\"tuning-reference_shuffle.md\":\"Iq2v1oHJ\",\"tuning-reference_spark-architecture.md\":\"_qwnE_Sc\",\"tuning-reference_table-formats.md\":\"BSYEK-eN\",\"user-guide_alternative-log-retrieval.md\":\"CJpYvHGo\",\"user-guide_alternative-log-retrieval_managed-platforms.md\":\"DvDwHNtC\",\"user-guide_alternative-log-retrieval_ssh-bastion.md\":\"Gszzlplv\",\"user-guide_getting-started.md\":\"DYHHHkQR\",\"user-guide_getting-started_ci-and-automation.md\":\"BEepbDDL\",\"user-guide_getting-started_reading-the-dashboard.md\":\"Obf3W3__\",\"user-guide_getting-started_regression-metric-keys.md\":\"B_gzr2Mw\",\"user-guide_getting-started_tuning-thresholds.md\":\"B_MyjyZm\",\"user-guide_mcp-tools.md\":\"C65SjWUL\",\"user-guide_mcp-tools_compare-runs.md\":\"Cc_gLoix\",\"user-guide_mcp-tools_diagnose-run.md\":\"BP1vnHA5\",\"user-guide_mcp-tools_evaluate-budgets.md\":\"BB0nDY3Z\",\"user-guide_mcp-tools_get-finding-documentation.md\":\"BtTTHNV6\",\"user-guide_mcp-tools_get-finding-evidence.md\":\"rKyu4wts\",\"user-guide_mcp-tools_get-reference-doc.md\":\"Yac4tH3u\",\"user-guide_mcp-tools_get-run-summary.md\":\"EhaIsele\",\"user-guide_mcp-tools_list-runs.md\":\"DpQPeCM3\",\"user-guide_run-comparison.md\":\"BUALkohi\",\"user-guide_run-comparison_how-stages-are-matched.md\":\"DSXGu2tA\",\"user-guide_understanding-findings.md\":\"3C7KCEZO\"}");window.__VP_SITE_DATA__=JSON.parse("{\"lang\":\"en-US\",\"dir\":\"ltr\",\"title\":\"SparkForensics\",\"description\":\"Docs for using and contributing to SparkForensics\",\"base\":\"/docs/\",\"head\":[],\"router\":{\"prefetchLinks\":true},\"appearance\":true,\"themeConfig\":{\"logo\":\"/favicon.svg\",\"nav\":[{\"text\":\"User Guide\",\"link\":\"/user-guide/getting-started\"},{\"text\":\"Contributor Guide\",\"link\":\"/contributor-guide/development-setup\"},{\"text\":\"Tuning Reference\",\"link\":\"/tuning-reference/\"}],\"sidebar\":{\"/tuning-reference/\":[{\"text\":\"Getting Started\",\"items\":[{\"text\":\"Introduction\",\"link\":\"/tuning-reference/intro\"}]},{\"text\":\"Optimization Guide\",\"items\":[{\"text\":\"Spark Execution Model\",\"link\":\"/tuning-reference/spark-architecture\"},{\"text\":\"Memory Management\",\"link\":\"/tuning-reference/memory-model\"},{\"text\":\"Partitioning\",\"link\":\"/tuning-reference/partitioning\"},{\"text\":\"Join Optimization\",\"link\":\"/tuning-reference/joins\"},{\"text\":\"Shuffle\",\"link\":\"/tuning-reference/shuffle\"},{\"text\":\"Data Formats\",\"link\":\"/tuning-reference/data-formats\"},{\"text\":\"Table Formats\",\"link\":\"/tuning-reference/table-formats\"},{\"text\":\"Caching & Persistence\",\"link\":\"/tuning-reference/caching\"},{\"text\":\"PySpark Specifics\",\"link\":\"/tuning-reference/pyspark\"},{\"text\":\"Adaptive Query Execution\",\"link\":\"/tuning-reference/aqe\"},{\"text\":\"Cluster Tuning\",\"link\":\"/tuning-reference/cluster-config\"},{\"text\":\"Anti-Patterns\",\"link\":\"/tuning-reference/anti-patterns\"}]},{\"text\":\"Detector Catalog\",\"items\":[{\"text\":\"Task Skew\",\"link\":\"/tuning-reference/bottleneck-skew\"},{\"text\":\"Shuffle I/O\",\"link\":\"/tuning-reference/bottleneck-shuffle\"},{\"text\":\"Memory / Disk Spill\",\"link\":\"/tuning-reference/bottleneck-spill\"},{\"text\":\"GC Pressure\",\"link\":\"/tuning-reference/bottleneck-gc\"},{\"text\":\"Cold Start\",\"link\":\"/tuning-reference/bottleneck-cold-start\"},{\"text\":\"Executor Utilization\",\"link\":\"/tuning-reference/bottleneck-utilization\"},{\"text\":\"Slow Host\",\"link\":\"/tuning-reference/bottleneck-slow-host\"},{\"text\":\"Task Failures\",\"link\":\"/tuning-reference/bottleneck-failures\"},{\"text\":\"Stragglers\",\"link\":\"/tuning-reference/bottleneck-straggler\"},{\"text\":\"Retry Waste\",\"link\":\"/tuning-reference/bottleneck-retry-waste\"},{\"text\":\"Tiny Tasks\",\"link\":\"/tuning-reference/bottleneck-tiny-tasks\"},{\"text\":\"Job Failure Rate\",\"link\":\"/tuning-reference/bottleneck-job-failure-rate\"},{\"text\":\"Memory Utilization\",\"link\":\"/tuning-reference/bottleneck-memory-utilization\"},{\"text\":\"Duplicate Plan Subtree\",\"link\":\"/tuning-reference/bottleneck-duplicate-plan-subtree\"},{\"text\":\"Small Files\",\"link\":\"/tuning-reference/bottleneck-small-files\"},{\"text\":\"Broadcast Sizing\",\"link\":\"/tuning-reference/bottleneck-broadcast-sizing\"}]},{\"text\":\"Reference\",\"items\":[{\"text\":\"Metrics Glossary\",\"link\":\"/tuning-reference/metrics\"},{\"text\":\"Spark Config Quick-Reference\",\"link\":\"/tuning-reference/config\"}]}],\"/user-guide/\":[{\"text\":\"User Guide\",\"items\":[{\"text\":\"Getting started\",\"link\":\"/user-guide/getting-started\",\"collapsed\":true,\"items\":[{\"text\":\"Reading the dashboard\",\"link\":\"/user-guide/getting-started/reading-the-dashboard\"},{\"text\":\"CI and automation\",\"link\":\"/user-guide/getting-started/ci-and-automation\"},{\"text\":\"Tuning detector thresholds\",\"link\":\"/user-guide/getting-started/tuning-thresholds\"},{\"text\":\"Regression metric keys\",\"link\":\"/user-guide/getting-started/regression-metric-keys\"}]},{\"text\":\"Understanding findings\",\"link\":\"/user-guide/understanding-findings\"},{\"text\":\"Run comparison mode\",\"link\":\"/user-guide/run-comparison\",\"collapsed\":true,\"items\":[{\"text\":\"How stages are matched\",\"link\":\"/user-guide/run-comparison/how-stages-are-matched\"}]},{\"text\":\"MCP tools reference\",\"link\":\"/user-guide/mcp-tools\",\"collapsed\":true,\"items\":[{\"text\":\"diagnose_run\",\"link\":\"/user-guide/mcp-tools/diagnose-run\"},{\"text\":\"get_run_summary\",\"link\":\"/user-guide/mcp-tools/get-run-summary\"},{\"text\":\"evaluate_budgets\",\"link\":\"/user-guide/mcp-tools/evaluate-budgets\"},{\"text\":\"compare_runs\",\"link\":\"/user-guide/mcp-tools/compare-runs\"},{\"text\":\"get_finding_evidence\",\"link\":\"/user-guide/mcp-tools/get-finding-evidence\"},{\"text\":\"get_finding_documentation\",\"link\":\"/user-guide/mcp-tools/get-finding-documentation\"},{\"text\":\"get_reference_doc\",\"link\":\"/user-guide/mcp-tools/get-reference-doc\"},{\"text\":\"list_runs\",\"link\":\"/user-guide/mcp-tools/list-runs\"}]},{\"text\":\"Finding your event log\",\"link\":\"/user-guide/alternative-log-retrieval\",\"collapsed\":true,\"items\":[{\"text\":\"Managed platforms\",\"link\":\"/user-guide/alternative-log-retrieval/managed-platforms\"},{\"text\":\"Behind an SSH bastion\",\"link\":\"/user-guide/alternative-log-retrieval/ssh-bastion\"}]}]}],\"/contributor-guide/\":[{\"text\":\"Contributor Guide\",\"items\":[{\"text\":\"Development setup\",\"link\":\"/contributor-guide/development-setup\"},{\"text\":\"Architecture\",\"link\":\"/contributor-guide/architecture/\",\"collapsed\":true,\"items\":[{\"text\":\"Overview\",\"link\":\"/contributor-guide/architecture/overview\"},{\"text\":\"Worker protocol\",\"link\":\"/contributor-guide/architecture/worker-protocol\",\"collapsed\":true,\"items\":[{\"text\":\"Evidence availability\",\"link\":\"/contributor-guide/architecture/worker-protocol/evidence-availability\"},{\"text\":\"Evidence report and finding identity\",\"link\":\"/contributor-guide/architecture/worker-protocol/evidence-report\"},{\"text\":\"CLI and MCP server\",\"link\":\"/contributor-guide/architecture/worker-protocol/cli-and-mcp\"},{\"text\":\"Core and event validation\",\"link\":\"/contributor-guide/architecture/worker-protocol/core-and-event-validation\"}]},{\"text\":\"State & history intake\",\"link\":\"/contributor-guide/architecture/state-and-history\",\"collapsed\":true,\"items\":[{\"text\":\"Run comparison internals\",\"link\":\"/contributor-guide/architecture/state-and-history/run-comparison-internals\"},{\"text\":\"History Server intake\",\"link\":\"/contributor-guide/architecture/state-and-history/history-server-intake\"}]},{\"text\":\"Detector contract\",\"link\":\"/contributor-guide/architecture/detector-contract\",\"collapsed\":true,\"items\":[{\"text\":\"Plan attribution\",\"link\":\"/contributor-guide/architecture/detector-contract/plan-attribution\"},{\"text\":\"Threshold tables\",\"link\":\"/contributor-guide/architecture/detector-contract/threshold-tables\"}]},{\"text\":\"Impact estimation\",\"link\":\"/contributor-guide/architecture/impact-estimation\",\"collapsed\":true,\"items\":[{\"text\":\"Stage union rollup\",\"link\":\"/contributor-guide/architecture/impact-estimation/stage-union-rollup\"},{\"text\":\"Caveats, tuning and coverage\",\"link\":\"/contributor-guide/architecture/impact-estimation/caveats-tuning-and-coverage\"}]},{\"text\":\"Widget rendering\",\"link\":\"/contributor-guide/architecture/widget-rendering\",\"collapsed\":true,\"items\":[{\"text\":\"Findings tab\",\"link\":\"/contributor-guide/architecture/widget-rendering/findings-tab\"},{\"text\":\"List sort mode\",\"link\":\"/contributor-guide/architecture/widget-rendering/list-sort-mode\"},{\"text\":\"Row/expand contract\",\"link\":\"/contributor-guide/architecture/widget-rendering/row-expand-contract\"},{\"text\":\"ReferenceSection\",\"link\":\"/contributor-guide/architecture/widget-rendering/reference-section\"},{\"text\":\"Investigation routing\",\"link\":\"/contributor-guide/architecture/widget-rendering/investigation-routing\"}]},{\"text\":\"Board widgets\",\"link\":\"/contributor-guide/architecture/board-widgets\",\"collapsed\":true,\"items\":[{\"text\":\"Plan Advisor\",\"link\":\"/contributor-guide/architecture/board-widgets/plan-advisor\"},{\"text\":\"Caching and memory widgets\",\"link\":\"/contributor-guide/architecture/board-widgets/caching-and-memory\"},{\"text\":\"Visual system and templating\",\"link\":\"/contributor-guide/architecture/board-widgets/visual-system-and-templating\"}]},{\"text\":\"Drill-down\",\"link\":\"/contributor-guide/architecture/drill-down\",\"collapsed\":true,\"items\":[{\"text\":\"Plan graph\",\"link\":\"/contributor-guide/architecture/drill-down/plan-graph\"}]}]},{\"text\":\"Testing & verification\",\"link\":\"/contributor-guide/testing\"},{\"text\":\"Contributing\",\"link\":\"/contributor-guide/contributing\"}]}]},\"search\":{\"provider\":\"local\"}},\"locales\":{},\"scrollOffset\":{\"selector\":\"[data-sf-anchor-offset]\",\"padding\":0},\"cleanUrls\":false}");</script>
30
+ <script>window.__VP_HASH_MAP__=JSON.parse("{\"contributor-guide_architecture_board-widgets.md\":\"CqKM_jEG\",\"contributor-guide_architecture_board-widgets_caching-and-memory.md\":\"BYDo3ClR\",\"contributor-guide_architecture_board-widgets_plan-advisor.md\":\"ajUAVdbc\",\"contributor-guide_architecture_board-widgets_visual-system-and-templating.md\":\"WqY74T0T\",\"contributor-guide_architecture_detector-contract.md\":\"CHHgywoP\",\"contributor-guide_architecture_detector-contract_plan-attribution.md\":\"DIz3_oz9\",\"contributor-guide_architecture_detector-contract_threshold-tables.md\":\"WH4tRHPL\",\"contributor-guide_architecture_drill-down.md\":\"yB-Hz2XT\",\"contributor-guide_architecture_drill-down_plan-graph.md\":\"BQZE04sw\",\"contributor-guide_architecture_impact-estimation.md\":\"K71YB-Rr\",\"contributor-guide_architecture_impact-estimation_caveats-tuning-and-coverage.md\":\"DLCAffwn\",\"contributor-guide_architecture_impact-estimation_stage-union-rollup.md\":\"JFrzDMwo\",\"contributor-guide_architecture_index.md\":\"tymxf1Fh\",\"contributor-guide_architecture_overview.md\":\"nxkpOhgf\",\"contributor-guide_architecture_state-and-history.md\":\"DyCBdjuM\",\"contributor-guide_architecture_state-and-history_history-server-intake.md\":\"C298hrHZ\",\"contributor-guide_architecture_state-and-history_run-comparison-internals.md\":\"U-9KMDFK\",\"contributor-guide_architecture_widget-rendering.md\":\"BrSz8Ezh\",\"contributor-guide_architecture_widget-rendering_findings-tab.md\":\"B7rjSF_h\",\"contributor-guide_architecture_widget-rendering_investigation-routing.md\":\"BGdiyElu\",\"contributor-guide_architecture_widget-rendering_list-sort-mode.md\":\"37hcZJ7q\",\"contributor-guide_architecture_widget-rendering_reference-section.md\":\"DWqC80bN\",\"contributor-guide_architecture_widget-rendering_row-expand-contract.md\":\"mK_VmAWk\",\"contributor-guide_architecture_worker-protocol.md\":\"Br6OE7RW\",\"contributor-guide_architecture_worker-protocol_cli-and-mcp.md\":\"IVyaXrGe\",\"contributor-guide_architecture_worker-protocol_core-and-event-validation.md\":\"DVSXn-bb\",\"contributor-guide_architecture_worker-protocol_evidence-availability.md\":\"D3S5cyOW\",\"contributor-guide_architecture_worker-protocol_evidence-report.md\":\"CtmCU57I\",\"contributor-guide_contributing.md\":\"DBW4drtZ\",\"contributor-guide_development-setup.md\":\"B21ZTDhn\",\"contributor-guide_testing.md\":\"DpkozNoG\",\"index.md\":\"lMm7SUMz\",\"tuning-reference_anti-patterns.md\":\"D08Uaod7\",\"tuning-reference_aqe.md\":\"C1Ae6A8u\",\"tuning-reference_bottleneck-broadcast-sizing.md\":\"6wjKuJNE\",\"tuning-reference_bottleneck-cold-start.md\":\"BVQbsuHP\",\"tuning-reference_bottleneck-duplicate-plan-subtree.md\":\"DtaYnaiF\",\"tuning-reference_bottleneck-failures.md\":\"Z1Tdmdd3\",\"tuning-reference_bottleneck-gc.md\":\"BCnXLf1n\",\"tuning-reference_bottleneck-job-failure-rate.md\":\"CcvQj2g9\",\"tuning-reference_bottleneck-memory-utilization.md\":\"B-C0-8h-\",\"tuning-reference_bottleneck-retry-waste.md\":\"DCnhWiqj\",\"tuning-reference_bottleneck-shuffle.md\":\"B5OMJCd3\",\"tuning-reference_bottleneck-skew.md\":\"Cvo6NQm_\",\"tuning-reference_bottleneck-slow-host.md\":\"ja5qr3wq\",\"tuning-reference_bottleneck-small-files.md\":\"Crjtb0i2\",\"tuning-reference_bottleneck-spill.md\":\"Bl8KtSRg\",\"tuning-reference_bottleneck-straggler.md\":\"B0VN8reT\",\"tuning-reference_bottleneck-tiny-tasks.md\":\"DQCftGhu\",\"tuning-reference_bottleneck-utilization.md\":\"BXDl30f9\",\"tuning-reference_caching.md\":\"CcaiMn_7\",\"tuning-reference_cluster-config.md\":\"DbWG1yZq\",\"tuning-reference_config.md\":\"YUqSpwFB\",\"tuning-reference_data-formats.md\":\"C5DX5xL4\",\"tuning-reference_index.md\":\"ZVIpQ6Dk\",\"tuning-reference_intro.md\":\"BSSaDlqx\",\"tuning-reference_joins.md\":\"BVhNCDnE\",\"tuning-reference_memory-model.md\":\"CfjFdgbl\",\"tuning-reference_metrics.md\":\"C64VNEL4\",\"tuning-reference_partitioning.md\":\"CtLK0xsS\",\"tuning-reference_pyspark.md\":\"D-92XgF8\",\"tuning-reference_shuffle.md\":\"Iq2v1oHJ\",\"tuning-reference_spark-architecture.md\":\"_qwnE_Sc\",\"tuning-reference_table-formats.md\":\"BSYEK-eN\",\"user-guide_alternative-log-retrieval.md\":\"CJpYvHGo\",\"user-guide_alternative-log-retrieval_managed-platforms.md\":\"DvDwHNtC\",\"user-guide_alternative-log-retrieval_ssh-bastion.md\":\"Gszzlplv\",\"user-guide_getting-started.md\":\"DYHHHkQR\",\"user-guide_getting-started_ci-and-automation.md\":\"C0pcQoNc\",\"user-guide_getting-started_reading-the-dashboard.md\":\"CGaxPX_1\",\"user-guide_getting-started_regression-metric-keys.md\":\"B_gzr2Mw\",\"user-guide_getting-started_tuning-thresholds.md\":\"BGVE-wrc\",\"user-guide_mcp-tools.md\":\"49r3L2YE\",\"user-guide_mcp-tools_compare-runs.md\":\"BQ_kIptC\",\"user-guide_mcp-tools_diagnose-run.md\":\"azCZXkH8\",\"user-guide_mcp-tools_evaluate-budgets.md\":\"dpQpRQ7z\",\"user-guide_mcp-tools_get-finding-documentation.md\":\"BtTTHNV6\",\"user-guide_mcp-tools_get-finding-evidence.md\":\"CH6FkNLX\",\"user-guide_mcp-tools_get-reference-doc.md\":\"Yac4tH3u\",\"user-guide_mcp-tools_get-run-summary.md\":\"EhaIsele\",\"user-guide_mcp-tools_list-runs.md\":\"DpQPeCM3\",\"user-guide_run-comparison.md\":\"B_LOkdBf\",\"user-guide_run-comparison_how-stages-are-matched.md\":\"DSXGu2tA\",\"user-guide_understanding-findings.md\":\"C4riKCKl\"}");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\":{\"light\":\"/logo-light.svg\",\"dark\":\"/logo-dark.svg\"},\"nav\":[{\"text\":\"User Guide\",\"link\":\"/user-guide/getting-started\"},{\"text\":\"Contributor Guide\",\"link\":\"/contributor-guide/development-setup\"},{\"text\":\"Tuning Reference\",\"link\":\"/tuning-reference/\"},{\"text\":\"Open app\",\"link\":\"/..\",\"target\":\"_self\"}],\"sidebar\":{\"/tuning-reference/\":[{\"text\":\"Getting Started\",\"items\":[{\"text\":\"Introduction\",\"link\":\"/tuning-reference/intro\"}]},{\"text\":\"Optimization Guide\",\"items\":[{\"text\":\"Spark Execution Model\",\"link\":\"/tuning-reference/spark-architecture\"},{\"text\":\"Memory Management\",\"link\":\"/tuning-reference/memory-model\"},{\"text\":\"Partitioning\",\"link\":\"/tuning-reference/partitioning\"},{\"text\":\"Join Optimization\",\"link\":\"/tuning-reference/joins\"},{\"text\":\"Shuffle\",\"link\":\"/tuning-reference/shuffle\"},{\"text\":\"Data Formats\",\"link\":\"/tuning-reference/data-formats\"},{\"text\":\"Table Formats\",\"link\":\"/tuning-reference/table-formats\"},{\"text\":\"Caching & Persistence\",\"link\":\"/tuning-reference/caching\"},{\"text\":\"PySpark Specifics\",\"link\":\"/tuning-reference/pyspark\"},{\"text\":\"Adaptive Query Execution\",\"link\":\"/tuning-reference/aqe\"},{\"text\":\"Cluster Tuning\",\"link\":\"/tuning-reference/cluster-config\"},{\"text\":\"Anti-Patterns\",\"link\":\"/tuning-reference/anti-patterns\"}]},{\"text\":\"Detector Catalog\",\"items\":[{\"text\":\"Task Skew\",\"link\":\"/tuning-reference/bottleneck-skew\"},{\"text\":\"Shuffle I/O\",\"link\":\"/tuning-reference/bottleneck-shuffle\"},{\"text\":\"Memory / Disk Spill\",\"link\":\"/tuning-reference/bottleneck-spill\"},{\"text\":\"GC Pressure\",\"link\":\"/tuning-reference/bottleneck-gc\"},{\"text\":\"Cold Start\",\"link\":\"/tuning-reference/bottleneck-cold-start\"},{\"text\":\"Executor Utilization\",\"link\":\"/tuning-reference/bottleneck-utilization\"},{\"text\":\"Slow Host\",\"link\":\"/tuning-reference/bottleneck-slow-host\"},{\"text\":\"Task Failures\",\"link\":\"/tuning-reference/bottleneck-failures\"},{\"text\":\"Stragglers\",\"link\":\"/tuning-reference/bottleneck-straggler\"},{\"text\":\"Retry Waste\",\"link\":\"/tuning-reference/bottleneck-retry-waste\"},{\"text\":\"Tiny Tasks\",\"link\":\"/tuning-reference/bottleneck-tiny-tasks\"},{\"text\":\"Job Failure Rate\",\"link\":\"/tuning-reference/bottleneck-job-failure-rate\"},{\"text\":\"Memory Utilization\",\"link\":\"/tuning-reference/bottleneck-memory-utilization\"},{\"text\":\"Duplicate Plan Subtree\",\"link\":\"/tuning-reference/bottleneck-duplicate-plan-subtree\"},{\"text\":\"Small Files\",\"link\":\"/tuning-reference/bottleneck-small-files\"},{\"text\":\"Broadcast Sizing\",\"link\":\"/tuning-reference/bottleneck-broadcast-sizing\"}]},{\"text\":\"Reference\",\"items\":[{\"text\":\"Metrics Glossary\",\"link\":\"/tuning-reference/metrics\"},{\"text\":\"Spark Config Quick-Reference\",\"link\":\"/tuning-reference/config\"}]}],\"/user-guide/\":[{\"text\":\"User Guide\",\"items\":[{\"text\":\"Getting started\",\"link\":\"/user-guide/getting-started\",\"collapsed\":true,\"items\":[{\"text\":\"Reading the dashboard\",\"link\":\"/user-guide/getting-started/reading-the-dashboard\"},{\"text\":\"CI and automation\",\"link\":\"/user-guide/getting-started/ci-and-automation\"},{\"text\":\"Tuning detector thresholds\",\"link\":\"/user-guide/getting-started/tuning-thresholds\"},{\"text\":\"Regression metric keys\",\"link\":\"/user-guide/getting-started/regression-metric-keys\"}]},{\"text\":\"Understanding findings\",\"link\":\"/user-guide/understanding-findings\"},{\"text\":\"Run comparison mode\",\"link\":\"/user-guide/run-comparison\",\"collapsed\":true,\"items\":[{\"text\":\"How stages are matched\",\"link\":\"/user-guide/run-comparison/how-stages-are-matched\"}]},{\"text\":\"MCP tools reference\",\"link\":\"/user-guide/mcp-tools\",\"collapsed\":true,\"items\":[{\"text\":\"diagnose_run\",\"link\":\"/user-guide/mcp-tools/diagnose-run\"},{\"text\":\"get_run_summary\",\"link\":\"/user-guide/mcp-tools/get-run-summary\"},{\"text\":\"evaluate_budgets\",\"link\":\"/user-guide/mcp-tools/evaluate-budgets\"},{\"text\":\"compare_runs\",\"link\":\"/user-guide/mcp-tools/compare-runs\"},{\"text\":\"get_finding_evidence\",\"link\":\"/user-guide/mcp-tools/get-finding-evidence\"},{\"text\":\"get_finding_documentation\",\"link\":\"/user-guide/mcp-tools/get-finding-documentation\"},{\"text\":\"get_reference_doc\",\"link\":\"/user-guide/mcp-tools/get-reference-doc\"},{\"text\":\"list_runs\",\"link\":\"/user-guide/mcp-tools/list-runs\"}]},{\"text\":\"Finding your event log\",\"link\":\"/user-guide/alternative-log-retrieval\",\"collapsed\":true,\"items\":[{\"text\":\"Managed platforms\",\"link\":\"/user-guide/alternative-log-retrieval/managed-platforms\"},{\"text\":\"Behind an SSH bastion\",\"link\":\"/user-guide/alternative-log-retrieval/ssh-bastion\"}]}]}],\"/contributor-guide/\":[{\"text\":\"Contributor Guide\",\"items\":[{\"text\":\"Development setup\",\"link\":\"/contributor-guide/development-setup\"},{\"text\":\"Architecture\",\"link\":\"/contributor-guide/architecture/\",\"collapsed\":true,\"items\":[{\"text\":\"Overview\",\"link\":\"/contributor-guide/architecture/overview\"},{\"text\":\"Worker protocol\",\"link\":\"/contributor-guide/architecture/worker-protocol\",\"collapsed\":true,\"items\":[{\"text\":\"Evidence availability\",\"link\":\"/contributor-guide/architecture/worker-protocol/evidence-availability\"},{\"text\":\"Evidence report and finding identity\",\"link\":\"/contributor-guide/architecture/worker-protocol/evidence-report\"},{\"text\":\"CLI and MCP server\",\"link\":\"/contributor-guide/architecture/worker-protocol/cli-and-mcp\"},{\"text\":\"Core and event validation\",\"link\":\"/contributor-guide/architecture/worker-protocol/core-and-event-validation\"}]},{\"text\":\"State & history intake\",\"link\":\"/contributor-guide/architecture/state-and-history\",\"collapsed\":true,\"items\":[{\"text\":\"Run comparison internals\",\"link\":\"/contributor-guide/architecture/state-and-history/run-comparison-internals\"},{\"text\":\"History Server intake\",\"link\":\"/contributor-guide/architecture/state-and-history/history-server-intake\"}]},{\"text\":\"Detector contract\",\"link\":\"/contributor-guide/architecture/detector-contract\",\"collapsed\":true,\"items\":[{\"text\":\"Plan attribution\",\"link\":\"/contributor-guide/architecture/detector-contract/plan-attribution\"},{\"text\":\"Threshold tables\",\"link\":\"/contributor-guide/architecture/detector-contract/threshold-tables\"}]},{\"text\":\"Impact estimation\",\"link\":\"/contributor-guide/architecture/impact-estimation\",\"collapsed\":true,\"items\":[{\"text\":\"Stage union rollup\",\"link\":\"/contributor-guide/architecture/impact-estimation/stage-union-rollup\"},{\"text\":\"Caveats, tuning and coverage\",\"link\":\"/contributor-guide/architecture/impact-estimation/caveats-tuning-and-coverage\"}]},{\"text\":\"Widget rendering\",\"link\":\"/contributor-guide/architecture/widget-rendering\",\"collapsed\":true,\"items\":[{\"text\":\"Findings tab\",\"link\":\"/contributor-guide/architecture/widget-rendering/findings-tab\"},{\"text\":\"List sort mode\",\"link\":\"/contributor-guide/architecture/widget-rendering/list-sort-mode\"},{\"text\":\"Row/expand contract\",\"link\":\"/contributor-guide/architecture/widget-rendering/row-expand-contract\"},{\"text\":\"ReferenceSection\",\"link\":\"/contributor-guide/architecture/widget-rendering/reference-section\"},{\"text\":\"Investigation routing\",\"link\":\"/contributor-guide/architecture/widget-rendering/investigation-routing\"}]},{\"text\":\"Board widgets\",\"link\":\"/contributor-guide/architecture/board-widgets\",\"collapsed\":true,\"items\":[{\"text\":\"Plan Advisor\",\"link\":\"/contributor-guide/architecture/board-widgets/plan-advisor\"},{\"text\":\"Caching and memory widgets\",\"link\":\"/contributor-guide/architecture/board-widgets/caching-and-memory\"},{\"text\":\"Visual system and templating\",\"link\":\"/contributor-guide/architecture/board-widgets/visual-system-and-templating\"}]},{\"text\":\"Drill-down\",\"link\":\"/contributor-guide/architecture/drill-down\",\"collapsed\":true,\"items\":[{\"text\":\"Plan graph\",\"link\":\"/contributor-guide/architecture/drill-down/plan-graph\"}]}]},{\"text\":\"Testing & verification\",\"link\":\"/contributor-guide/testing\"},{\"text\":\"Contributing\",\"link\":\"/contributor-guide/contributing\"}]}]},\"search\":{\"provider\":\"local\"}},\"locales\":{},\"scrollOffset\":{\"selector\":\"[data-sf-anchor-offset]\",\"padding\":0},\"cleanUrls\":false}");</script>
31
31
 
32
32
  </body>
33
33
  </html>