sparkforensics-server 0.5.2 → 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 (445) 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/instrument-sans-latin-ext-wdth-normal-C5E2Gvlv.woff2 +0 -0
  63. package/public/assets/instrument-sans-latin-wdth-normal-BVScPF0l.woff2 +0 -0
  64. package/public/assets/jetbrains-mono-latin-ext-wght-normal-DBQx-q_a.woff2 +0 -0
  65. package/public/assets/jetbrains-mono-latin-wght-normal-B9CIFXIH.woff2 +0 -0
  66. package/public/assets/layout.worker-CLcBHxVp.js +3 -0
  67. package/public/assets/{parser-worker-CA5RxqKc.js → parser-worker-CRIOPMOW.js} +8 -8
  68. package/public/assets/plan-graph-vendor-Ce6d4HU6.js +7 -0
  69. package/public/assets/react-vendor-C6KcUD36.js +9 -0
  70. package/public/assets/select-BHqOqun5.js +1 -0
  71. package/public/assets/toggle-DPeN6aNa.js +1 -0
  72. package/public/assets/toggle-group-Kl3uyHSr.js +1 -0
  73. package/public/assets/usePagedRows-BafD6bEN.js +1 -0
  74. package/public/assets/useRecentFiles-DzJZAoOT.js +3 -0
  75. package/public/assets/useRegisterFieldControl-pQv-ZDoU.js +1 -0
  76. package/public/assets/useScrollLock-BCxn_dMp.js +1 -0
  77. package/public/assets/useSortMode-DjrAN-z4.js +1 -0
  78. package/public/docs/404.html +3 -7
  79. package/public/docs/assets/{app.eYTPqTeq.js → app.1gvzd5Zb.js} +1 -1
  80. package/public/docs/assets/chunks/@localSearchIndexroot.DS2TQP5_.js +1 -0
  81. package/public/docs/assets/chunks/{VPLocalSearchBox.DsZrQKQR.js → VPLocalSearchBox.CNxT3s0I.js} +1 -1
  82. package/public/docs/assets/chunks/{theme.DsTNE2pE.js → theme.C5lLqUv7.js} +2 -2
  83. package/public/docs/assets/contributor-guide_architecture_board-widgets.md.CqKM_jEG.js +1 -0
  84. package/public/docs/assets/contributor-guide_architecture_board-widgets.md.CqKM_jEG.lean.js +1 -0
  85. package/public/docs/assets/{contributor-guide_architecture_board-widgets_caching-and-memory.md.8bH1HnZp.js → contributor-guide_architecture_board-widgets_caching-and-memory.md.BYDo3ClR.js} +1 -1
  86. package/public/docs/assets/contributor-guide_architecture_board-widgets_plan-advisor.md.ajUAVdbc.js +1 -0
  87. package/public/docs/assets/contributor-guide_architecture_board-widgets_visual-system-and-templating.md.WqY74T0T.js +1 -0
  88. package/public/docs/assets/contributor-guide_architecture_board-widgets_visual-system-and-templating.md.WqY74T0T.lean.js +1 -0
  89. package/public/docs/assets/contributor-guide_architecture_detector-contract.md.CHHgywoP.js +1 -0
  90. package/public/docs/assets/{contributor-guide_architecture_detector-contract.md.wj6Et6UD.lean.js → contributor-guide_architecture_detector-contract.md.CHHgywoP.lean.js} +1 -1
  91. package/public/docs/assets/contributor-guide_architecture_detector-contract_plan-attribution.md.DIz3_oz9.js +1 -0
  92. package/public/docs/assets/contributor-guide_architecture_detector-contract_plan-attribution.md.DIz3_oz9.lean.js +1 -0
  93. package/public/docs/assets/contributor-guide_architecture_detector-contract_threshold-tables.md.WH4tRHPL.js +1 -0
  94. package/public/docs/assets/{contributor-guide_architecture_detector-contract_threshold-tables.md.CKjWG56Y.lean.js → contributor-guide_architecture_detector-contract_threshold-tables.md.WH4tRHPL.lean.js} +1 -1
  95. package/public/docs/assets/{contributor-guide_architecture_drill-down.md.CqZPrdo9.js → contributor-guide_architecture_drill-down.md.yB-Hz2XT.js} +1 -1
  96. 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
  97. package/public/docs/assets/contributor-guide_architecture_drill-down_plan-graph.md.BQZE04sw.js +1 -0
  98. 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
  99. package/public/docs/assets/contributor-guide_architecture_impact-estimation.md.K71YB-Rr.js +1 -0
  100. package/public/docs/assets/{contributor-guide_architecture_impact-estimation.md.CZv_ZGOp.lean.js → contributor-guide_architecture_impact-estimation.md.K71YB-Rr.lean.js} +1 -1
  101. package/public/docs/assets/contributor-guide_architecture_impact-estimation_caveats-tuning-and-coverage.md.DLCAffwn.js +1 -0
  102. package/public/docs/assets/{contributor-guide_architecture_impact-estimation_caveats-tuning-and-coverage.md.BUucRc0A.lean.js → contributor-guide_architecture_impact-estimation_caveats-tuning-and-coverage.md.DLCAffwn.lean.js} +1 -1
  103. package/public/docs/assets/contributor-guide_architecture_impact-estimation_stage-union-rollup.md.JFrzDMwo.js +1 -0
  104. package/public/docs/assets/contributor-guide_architecture_impact-estimation_stage-union-rollup.md.JFrzDMwo.lean.js +1 -0
  105. package/public/docs/assets/contributor-guide_architecture_overview.md.nxkpOhgf.js +1 -0
  106. package/public/docs/assets/contributor-guide_architecture_state-and-history_run-comparison-internals.md.U-9KMDFK.js +1 -0
  107. 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
  108. package/public/docs/assets/contributor-guide_architecture_widget-rendering.md.BrSz8Ezh.js +1 -0
  109. package/public/docs/assets/contributor-guide_architecture_widget-rendering_findings-tab.md.B7rjSF_h.js +1 -0
  110. package/public/docs/assets/contributor-guide_architecture_widget-rendering_findings-tab.md.B7rjSF_h.lean.js +1 -0
  111. 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
  112. 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
  113. package/public/docs/assets/{contributor-guide_architecture_worker-protocol.md.BAnhi2-d.js → contributor-guide_architecture_worker-protocol.md.Br6OE7RW.js} +1 -1
  114. package/public/docs/assets/contributor-guide_architecture_worker-protocol.md.Br6OE7RW.lean.js +1 -0
  115. package/public/docs/assets/contributor-guide_architecture_worker-protocol_cli-and-mcp.md.IVyaXrGe.js +1 -0
  116. package/public/docs/assets/{contributor-guide_architecture_worker-protocol_cli-and-mcp.md.DC1YqXBp.lean.js → contributor-guide_architecture_worker-protocol_cli-and-mcp.md.IVyaXrGe.lean.js} +1 -1
  117. 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
  118. 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
  119. 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
  120. package/public/docs/assets/contributor-guide_architecture_worker-protocol_evidence-report.md.CtmCU57I.js +1 -0
  121. package/public/docs/assets/{contributor-guide_architecture_worker-protocol_evidence-report.md.DVGZOWvW.lean.js → contributor-guide_architecture_worker-protocol_evidence-report.md.CtmCU57I.lean.js} +1 -1
  122. package/public/docs/assets/contributor-guide_contributing.md.DBW4drtZ.js +1 -0
  123. package/public/docs/assets/{contributor-guide_development-setup.md.D9bu4j_c.js → contributor-guide_development-setup.md.B21ZTDhn.js} +3 -3
  124. package/public/docs/assets/contributor-guide_development-setup.md.B21ZTDhn.lean.js +1 -0
  125. package/public/docs/assets/contributor-guide_testing.md.DpkozNoG.js +4 -0
  126. package/public/docs/assets/{contributor-guide_testing.md.By6XGR9a.lean.js → contributor-guide_testing.md.DpkozNoG.lean.js} +1 -1
  127. package/public/docs/assets/{index.md.CHJVslga.js → index.md.lMm7SUMz.js} +1 -1
  128. package/public/docs/assets/{index.md.CHJVslga.lean.js → index.md.lMm7SUMz.lean.js} +1 -1
  129. package/public/docs/assets/instrument-sans-latin-ext-wdth-normal.C5E2Gvlv.woff2 +0 -0
  130. package/public/docs/assets/instrument-sans-latin-wdth-normal.BVScPF0l.woff2 +0 -0
  131. package/public/docs/assets/jetbrains-mono-cyrillic-wght-normal.D73BlboJ.woff2 +0 -0
  132. package/public/docs/assets/jetbrains-mono-greek-wght-normal.Bw9x6K1M.woff2 +0 -0
  133. package/public/docs/assets/jetbrains-mono-latin-ext-wght-normal.DBQx-q_a.woff2 +0 -0
  134. package/public/docs/assets/jetbrains-mono-latin-wght-normal.B9CIFXIH.woff2 +0 -0
  135. package/public/docs/assets/jetbrains-mono-vietnamese-wght-normal.Bt-aOZkq.woff2 +0 -0
  136. package/public/docs/assets/style.Cfxqlj0y.css +1 -0
  137. package/public/docs/assets/user-guide_getting-started_ci-and-automation.md.C0pcQoNc.js +29 -0
  138. package/public/docs/assets/user-guide_getting-started_ci-and-automation.md.C0pcQoNc.lean.js +1 -0
  139. package/public/docs/assets/user-guide_getting-started_reading-the-dashboard.md.CGaxPX_1.js +1 -0
  140. 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
  141. 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
  142. package/public/docs/assets/{user-guide_mcp-tools.md.C65SjWUL.js → user-guide_mcp-tools.md.49r3L2YE.js} +1 -1
  143. 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
  144. package/public/docs/assets/user-guide_mcp-tools_compare-runs.md.BQ_kIptC.lean.js +1 -0
  145. package/public/docs/assets/user-guide_mcp-tools_diagnose-run.md.azCZXkH8.js +44 -0
  146. 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
  147. package/public/docs/assets/{user-guide_mcp-tools_evaluate-budgets.md.BB0nDY3Z.js → user-guide_mcp-tools_evaluate-budgets.md.dpQpRQ7z.js} +2 -2
  148. 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
  149. 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
  150. 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
  151. package/public/docs/assets/{user-guide_mcp-tools_get-run-summary.md.DpxZ4ZNp.js → user-guide_mcp-tools_get-run-summary.md.EhaIsele.js} +1 -1
  152. package/public/docs/assets/user-guide_run-comparison.md.B_LOkdBf.js +1 -0
  153. package/public/docs/assets/user-guide_run-comparison.md.B_LOkdBf.lean.js +1 -0
  154. package/public/docs/assets/user-guide_understanding-findings.md.C4riKCKl.js +1 -0
  155. package/public/docs/assets/user-guide_understanding-findings.md.C4riKCKl.lean.js +1 -0
  156. package/public/docs/contributor-guide/architecture/board-widgets/caching-and-memory.html +6 -10
  157. package/public/docs/contributor-guide/architecture/board-widgets/plan-advisor.html +6 -10
  158. package/public/docs/contributor-guide/architecture/board-widgets/visual-system-and-templating.html +6 -10
  159. package/public/docs/contributor-guide/architecture/board-widgets.html +6 -10
  160. package/public/docs/contributor-guide/architecture/detector-contract/plan-attribution.html +6 -10
  161. package/public/docs/contributor-guide/architecture/detector-contract/threshold-tables.html +6 -10
  162. package/public/docs/contributor-guide/architecture/detector-contract.html +6 -10
  163. package/public/docs/contributor-guide/architecture/drill-down/plan-graph.html +6 -10
  164. package/public/docs/contributor-guide/architecture/drill-down.html +6 -10
  165. package/public/docs/contributor-guide/architecture/impact-estimation/caveats-tuning-and-coverage.html +6 -10
  166. package/public/docs/contributor-guide/architecture/impact-estimation/stage-union-rollup.html +6 -10
  167. package/public/docs/contributor-guide/architecture/impact-estimation.html +6 -10
  168. package/public/docs/contributor-guide/architecture/index.html +5 -9
  169. package/public/docs/contributor-guide/architecture/overview.html +6 -10
  170. package/public/docs/contributor-guide/architecture/state-and-history/history-server-intake.html +5 -9
  171. package/public/docs/contributor-guide/architecture/state-and-history/run-comparison-internals.html +6 -10
  172. package/public/docs/contributor-guide/architecture/state-and-history.html +5 -9
  173. package/public/docs/contributor-guide/architecture/widget-rendering/findings-tab.html +6 -10
  174. package/public/docs/contributor-guide/architecture/widget-rendering/investigation-routing.html +5 -9
  175. package/public/docs/contributor-guide/architecture/widget-rendering/list-sort-mode.html +6 -10
  176. package/public/docs/contributor-guide/architecture/widget-rendering/reference-section.html +5 -9
  177. package/public/docs/contributor-guide/architecture/widget-rendering/row-expand-contract.html +6 -10
  178. package/public/docs/contributor-guide/architecture/widget-rendering.html +6 -10
  179. package/public/docs/contributor-guide/architecture/worker-protocol/cli-and-mcp.html +6 -10
  180. package/public/docs/contributor-guide/architecture/worker-protocol/core-and-event-validation.html +6 -10
  181. package/public/docs/contributor-guide/architecture/worker-protocol/evidence-availability.html +7 -11
  182. package/public/docs/contributor-guide/architecture/worker-protocol/evidence-report.html +6 -10
  183. package/public/docs/contributor-guide/architecture/worker-protocol.html +6 -10
  184. package/public/docs/contributor-guide/contributing.html +6 -10
  185. package/public/docs/contributor-guide/development-setup.html +8 -12
  186. package/public/docs/contributor-guide/testing.html +9 -10
  187. package/public/docs/favicon.svg +2 -2
  188. package/public/docs/hashmap.json +1 -1
  189. package/public/docs/index.html +6 -10
  190. package/public/docs/logo-dark.svg +1 -0
  191. package/public/docs/logo-light.svg +1 -0
  192. package/public/docs/tuning-reference/anti-patterns.html +5 -9
  193. package/public/docs/tuning-reference/aqe.html +5 -9
  194. package/public/docs/tuning-reference/bottleneck-broadcast-sizing.html +5 -9
  195. package/public/docs/tuning-reference/bottleneck-cold-start.html +5 -9
  196. package/public/docs/tuning-reference/bottleneck-duplicate-plan-subtree.html +5 -9
  197. package/public/docs/tuning-reference/bottleneck-failures.html +5 -9
  198. package/public/docs/tuning-reference/bottleneck-gc.html +5 -9
  199. package/public/docs/tuning-reference/bottleneck-job-failure-rate.html +5 -9
  200. package/public/docs/tuning-reference/bottleneck-memory-utilization.html +5 -9
  201. package/public/docs/tuning-reference/bottleneck-retry-waste.html +5 -9
  202. package/public/docs/tuning-reference/bottleneck-shuffle.html +5 -9
  203. package/public/docs/tuning-reference/bottleneck-skew.html +5 -9
  204. package/public/docs/tuning-reference/bottleneck-slow-host.html +5 -9
  205. package/public/docs/tuning-reference/bottleneck-small-files.html +5 -9
  206. package/public/docs/tuning-reference/bottleneck-spill.html +5 -9
  207. package/public/docs/tuning-reference/bottleneck-straggler.html +5 -9
  208. package/public/docs/tuning-reference/bottleneck-tiny-tasks.html +5 -9
  209. package/public/docs/tuning-reference/bottleneck-utilization.html +5 -9
  210. package/public/docs/tuning-reference/caching.html +5 -9
  211. package/public/docs/tuning-reference/cluster-config.html +5 -9
  212. package/public/docs/tuning-reference/config.html +5 -9
  213. package/public/docs/tuning-reference/data-formats.html +5 -9
  214. package/public/docs/tuning-reference/index.html +5 -9
  215. package/public/docs/tuning-reference/intro.html +5 -9
  216. package/public/docs/tuning-reference/joins.html +5 -9
  217. package/public/docs/tuning-reference/memory-model.html +5 -9
  218. package/public/docs/tuning-reference/metrics.html +5 -9
  219. package/public/docs/tuning-reference/partitioning.html +5 -9
  220. package/public/docs/tuning-reference/pyspark.html +5 -9
  221. package/public/docs/tuning-reference/shuffle.html +5 -9
  222. package/public/docs/tuning-reference/spark-architecture.html +5 -9
  223. package/public/docs/tuning-reference/table-formats.html +5 -9
  224. package/public/docs/user-guide/alternative-log-retrieval/managed-platforms.html +5 -9
  225. package/public/docs/user-guide/alternative-log-retrieval/ssh-bastion.html +5 -9
  226. package/public/docs/user-guide/alternative-log-retrieval.html +5 -9
  227. package/public/docs/user-guide/getting-started/ci-and-automation.html +17 -15
  228. package/public/docs/user-guide/getting-started/reading-the-dashboard.html +6 -10
  229. package/public/docs/user-guide/getting-started/regression-metric-keys.html +5 -9
  230. package/public/docs/user-guide/getting-started/tuning-thresholds.html +7 -11
  231. package/public/docs/user-guide/getting-started.html +5 -9
  232. package/public/docs/user-guide/mcp-tools/compare-runs.html +16 -15
  233. package/public/docs/user-guide/mcp-tools/diagnose-run.html +28 -11
  234. package/public/docs/user-guide/mcp-tools/evaluate-budgets.html +6 -10
  235. package/public/docs/user-guide/mcp-tools/get-finding-documentation.html +5 -9
  236. package/public/docs/user-guide/mcp-tools/get-finding-evidence.html +7 -10
  237. package/public/docs/user-guide/mcp-tools/get-reference-doc.html +5 -9
  238. package/public/docs/user-guide/mcp-tools/get-run-summary.html +6 -10
  239. package/public/docs/user-guide/mcp-tools/list-runs.html +5 -9
  240. package/public/docs/user-guide/mcp-tools.html +6 -10
  241. package/public/docs/user-guide/run-comparison/how-stages-are-matched.html +5 -9
  242. package/public/docs/user-guide/run-comparison.html +6 -10
  243. package/public/docs/user-guide/understanding-findings.html +6 -10
  244. package/public/export-template.html +46 -46
  245. package/public/favicon.svg +2 -2
  246. package/public/index.html +8 -10
  247. package/public/sample-runs/sample-run.ndjson.gz +0 -0
  248. package/vendor-core/allocation.js +126 -39
  249. package/vendor-core/analyzer.js +85 -58
  250. package/vendor-core/api-merge-writes.js +3 -0
  251. package/vendor-core/aqe-skew.js +347 -0
  252. package/vendor-core/cli/budgets.js +6 -4
  253. package/vendor-core/cli/collect-run-pair.js +89 -0
  254. package/vendor-core/cli/collect-run-worker.js +16 -0
  255. package/vendor-core/cli/collect-run.js +1 -2
  256. package/vendor-core/cli/native-zstd.js +12 -16
  257. package/vendor-core/comparability.js +234 -0
  258. package/vendor-core/comparison-output.js +15 -7
  259. package/vendor-core/comparison-verdict.js +105 -25
  260. package/vendor-core/core-source-hash.txt +1 -1
  261. package/vendor-core/core-time-series.js +0 -1
  262. package/vendor-core/core-usage-locality.js +1 -1
  263. package/vendor-core/delta-log-paths.js +10 -1
  264. package/vendor-core/detectors.js +1078 -416
  265. package/vendor-core/docs-config.js +0 -4
  266. package/vendor-core/docs-content/detection/cache.md +2 -1
  267. package/vendor-core/docs-content/detection/cfg.md +19 -11
  268. package/vendor-core/docs-content/detection/cold.md +2 -1
  269. package/vendor-core/docs-content/detection/gc.md +7 -3
  270. package/vendor-core/docs-content/detection/host.md +11 -1
  271. package/vendor-core/docs-content/detection/mem.md +17 -6
  272. package/vendor-core/docs-content/detection/part.md +3 -1
  273. package/vendor-core/docs-content/detection/plan.md +55 -13
  274. package/vendor-core/docs-content/detection/shfl.md +11 -5
  275. package/vendor-core/docs-content/detection/skew.md +48 -1
  276. package/vendor-core/docs-content/detection/slow.md +4 -2
  277. package/vendor-core/docs-content/detection/spec.md +6 -1
  278. package/vendor-core/docs-content/detection/spill.md +6 -3
  279. package/vendor-core/docs-content/detection/strag.md +19 -6
  280. package/vendor-core/docs-content/detection/tiny.md +9 -3
  281. package/vendor-core/docs-content/detection/util.md +6 -2
  282. package/vendor-core/effective-conf.js +7 -10
  283. package/vendor-core/efficiency-model.js +24 -16
  284. package/vendor-core/etl-phases.js +1 -2
  285. package/vendor-core/event-handlers.js +175 -57
  286. package/vendor-core/event-schemas.js +21 -16
  287. package/vendor-core/evidence-availability.js +9 -2
  288. package/vendor-core/evidence-report.js +118 -35
  289. package/vendor-core/executor-peaks.js +41 -0
  290. package/vendor-core/export-data.js +5 -5
  291. package/vendor-core/finding-identity.js +78 -0
  292. package/vendor-core/finding-presentation.js +129 -39
  293. package/vendor-core/finding-types.js +108 -30
  294. package/vendor-core/format-utils.js +14 -15
  295. package/vendor-core/html-export.js +1 -1
  296. package/vendor-core/impact-band.js +2 -2
  297. package/vendor-core/impact-format.js +47 -19
  298. package/vendor-core/impact-model.js +28 -17
  299. package/vendor-core/job-groups.js +4 -4
  300. package/vendor-core/mcp-server-factory.js +48 -12
  301. package/vendor-core/mcp-tools.js +179 -24
  302. package/vendor-core/median.js +2 -2
  303. package/vendor-core/nested-loop-join.js +73 -0
  304. package/vendor-core/occupancy.js +1 -2
  305. package/vendor-core/parser-worker.js +1 -1
  306. package/vendor-core/plan-graph-model.js +14 -22
  307. package/vendor-core/plan-node-detail.js +2 -3
  308. package/vendor-core/plan-summary.js +24 -19
  309. package/vendor-core/plan-tree-walk.js +6 -8
  310. package/vendor-core/python-stage.js +12 -1
  311. package/vendor-core/recommendation-rollup.js +13 -12
  312. package/vendor-core/redact.js +52 -46
  313. package/vendor-core/remediation.js +10 -5
  314. package/vendor-core/run-aggregates.js +6 -8
  315. package/vendor-core/run-comparison.js +226 -66
  316. package/vendor-core/run-identity.js +12 -0
  317. package/vendor-core/run-interpretation.js +21 -0
  318. package/vendor-core/run-metrics.js +2 -2
  319. package/vendor-core/run-output.js +44 -11
  320. package/vendor-core/run-totals.js +12 -0
  321. package/vendor-core/run-verdict.js +76 -3
  322. package/vendor-core/scaling-sim.js +3 -4
  323. package/vendor-core/snappy-block.js +2 -2
  324. package/vendor-core/spark-conf.js +168 -0
  325. package/vendor-core/sql-stages.js +2 -2
  326. package/vendor-core/stage-alignment.js +2 -12
  327. package/vendor-core/stage-identity.js +58 -3
  328. package/vendor-core/stage-label.js +14 -0
  329. package/vendor-core/stage-plan-nodes.js +17 -3
  330. package/vendor-core/stage-quantiles.js +141 -9
  331. package/vendor-core/stage-structure.js +17 -3
  332. package/vendor-core/threshold-overrides.js +9 -3
  333. package/vendor-core/types.js +70 -23
  334. package/vendor-core/wall-clock.js +8 -0
  335. package/vendor-core/wasted-core-hours.js +12 -12
  336. package/vendor-core/write-targets.js +146 -14
  337. package/vendor-core/zstd-worker-client.js +1 -1
  338. package/vendor-core/zstd-worker.js +1 -1
  339. package/public/assets/AutoscalingChurn-8t3U3isq.js +0 -1
  340. package/public/assets/CacheUtilization-CJs9tTum.js +0 -1
  341. package/public/assets/CachingOpportunity-D1NcHs0V.js +0 -1
  342. package/public/assets/ColdStart-CdRJ9gD8.js +0 -1
  343. package/public/assets/ConfigAudit-B5Gbe5js.js +0 -1
  344. package/public/assets/CoreUsageArea-a--NTRGY.js +0 -1
  345. package/public/assets/Dashboard-C1hNeX49.js +0 -2
  346. package/public/assets/DisclosureContext-ZpE6CkHx.js +0 -1
  347. package/public/assets/DuplicatePlanSubtree-dobXdz7E.js +0 -1
  348. package/public/assets/ExecutorUtilization-D9grwi7t.js +0 -1
  349. package/public/assets/GcPressure-8-G2ri10.js +0 -1
  350. package/public/assets/IncompleteRun-B91lky7a.js +0 -1
  351. package/public/assets/JobFailures-BsWvBMyJ.js +0 -1
  352. package/public/assets/MemoryUtilization-BM5schZI.js +0 -1
  353. package/public/assets/OverBroadcast-DdN8JIJH.js +0 -1
  354. package/public/assets/PartitionHint-CUvbnnxy.js +0 -1
  355. package/public/assets/PartitionSizing-CY5HDYtp.js +0 -1
  356. package/public/assets/PlanExplorer-DgHCDBD_.js +0 -1
  357. package/public/assets/PlanGraphRoute-DH3KJb8j.js +0 -1
  358. package/public/assets/RetryWaste-DOnE9vGF.js +0 -1
  359. package/public/assets/ShuffleIO-MMnDESkF.js +0 -1
  360. package/public/assets/Skew-BmZZJ5ms.js +0 -1
  361. package/public/assets/SlowHost-CsJzfEqo.js +0 -1
  362. package/public/assets/SmallFiles-BoK3R1Ex.js +0 -1
  363. package/public/assets/SpeculationWaste-CnVxB5AJ.js +0 -1
  364. package/public/assets/Spill-BhNicyBy.js +0 -1
  365. package/public/assets/StageFailed-mAhHU4l_.js +0 -1
  366. package/public/assets/StageFindingGroup-BEtPWcT0.js +0 -1
  367. package/public/assets/StageHeader-DJkYkrsU.js +0 -1
  368. package/public/assets/StageShape-BDxRknLp.js +0 -1
  369. package/public/assets/StageSlowness-BPRw-otN.js +0 -1
  370. package/public/assets/Straggler-CZCbnOWP.js +0 -1
  371. package/public/assets/TaskFailures-C57YcLFQ.js +0 -1
  372. package/public/assets/TinyTask-Bi84qU7n.js +0 -1
  373. package/public/assets/UnderBroadcast-DdQV7htE.js +0 -1
  374. package/public/assets/charts-vendor-0VMaLVLN.js +0 -59
  375. package/public/assets/finding-anchor-Cl6_5hfV.js +0 -1
  376. package/public/assets/impact-sort-CssZ6MT2.js +0 -1
  377. package/public/assets/index-2h_TgUAb.css +0 -2
  378. package/public/assets/index-B-03mG7K.js +0 -14
  379. package/public/assets/plan-graph-vendor-BYl-AzN5.js +0 -7
  380. package/public/assets/react-vendor-DEdfrRTJ.js +0 -9
  381. package/public/assets/select-CQjNhprm.js +0 -1
  382. package/public/assets/usePagedRows-Dyl6T8Ok.js +0 -1
  383. package/public/assets/useRecentFiles-XZEnLlal.js +0 -11
  384. package/public/assets/useSortMode-Dhvit8dt.js +0 -1
  385. package/public/docs/assets/chunks/@localSearchIndexroot.u_e5bQz4.js +0 -1
  386. package/public/docs/assets/contributor-guide_architecture_board-widgets.md.YQcj5EI4.js +0 -1
  387. package/public/docs/assets/contributor-guide_architecture_board-widgets.md.YQcj5EI4.lean.js +0 -1
  388. package/public/docs/assets/contributor-guide_architecture_board-widgets_plan-advisor.md.RlzvUmNm.js +0 -1
  389. package/public/docs/assets/contributor-guide_architecture_board-widgets_visual-system-and-templating.md.DYgUpIJB.js +0 -1
  390. package/public/docs/assets/contributor-guide_architecture_board-widgets_visual-system-and-templating.md.DYgUpIJB.lean.js +0 -1
  391. package/public/docs/assets/contributor-guide_architecture_detector-contract.md.wj6Et6UD.js +0 -1
  392. package/public/docs/assets/contributor-guide_architecture_detector-contract_plan-attribution.md.yNex4bys.js +0 -1
  393. package/public/docs/assets/contributor-guide_architecture_detector-contract_plan-attribution.md.yNex4bys.lean.js +0 -1
  394. package/public/docs/assets/contributor-guide_architecture_detector-contract_threshold-tables.md.CKjWG56Y.js +0 -1
  395. package/public/docs/assets/contributor-guide_architecture_drill-down_plan-graph.md.DwOozIEs.js +0 -1
  396. package/public/docs/assets/contributor-guide_architecture_impact-estimation.md.CZv_ZGOp.js +0 -1
  397. package/public/docs/assets/contributor-guide_architecture_impact-estimation_caveats-tuning-and-coverage.md.BUucRc0A.js +0 -1
  398. package/public/docs/assets/contributor-guide_architecture_impact-estimation_stage-union-rollup.md.DdCGtAGu.js +0 -1
  399. package/public/docs/assets/contributor-guide_architecture_impact-estimation_stage-union-rollup.md.DdCGtAGu.lean.js +0 -1
  400. package/public/docs/assets/contributor-guide_architecture_overview.md.C1sSvm9i.js +0 -1
  401. package/public/docs/assets/contributor-guide_architecture_state-and-history_run-comparison-internals.md.CZA0JLtV.js +0 -1
  402. package/public/docs/assets/contributor-guide_architecture_widget-rendering.md.BOZ1azXG.js +0 -1
  403. package/public/docs/assets/contributor-guide_architecture_widget-rendering_findings-tab.md.BQXycK6G.js +0 -1
  404. package/public/docs/assets/contributor-guide_architecture_widget-rendering_findings-tab.md.BQXycK6G.lean.js +0 -1
  405. package/public/docs/assets/contributor-guide_architecture_worker-protocol.md.BAnhi2-d.lean.js +0 -1
  406. package/public/docs/assets/contributor-guide_architecture_worker-protocol_cli-and-mcp.md.DC1YqXBp.js +0 -1
  407. package/public/docs/assets/contributor-guide_architecture_worker-protocol_evidence-report.md.DVGZOWvW.js +0 -1
  408. package/public/docs/assets/contributor-guide_contributing.md.CQMvGwFt.js +0 -1
  409. package/public/docs/assets/contributor-guide_development-setup.md.D9bu4j_c.lean.js +0 -1
  410. package/public/docs/assets/contributor-guide_testing.md.By6XGR9a.js +0 -1
  411. package/public/docs/assets/inter-italic-cyrillic-ext.r48I6akx.woff2 +0 -0
  412. package/public/docs/assets/inter-italic-cyrillic.By2_1cv3.woff2 +0 -0
  413. package/public/docs/assets/inter-italic-greek-ext.1u6EdAuj.woff2 +0 -0
  414. package/public/docs/assets/inter-italic-greek.DJ8dCoTZ.woff2 +0 -0
  415. package/public/docs/assets/inter-italic-latin-ext.CN1xVJS-.woff2 +0 -0
  416. package/public/docs/assets/inter-italic-latin.C2AdPX0b.woff2 +0 -0
  417. package/public/docs/assets/inter-italic-vietnamese.BSbpV94h.woff2 +0 -0
  418. package/public/docs/assets/inter-roman-cyrillic-ext.BBPuwvHQ.woff2 +0 -0
  419. package/public/docs/assets/inter-roman-cyrillic.C5lxZ8CY.woff2 +0 -0
  420. package/public/docs/assets/inter-roman-greek-ext.CqjqNYQ-.woff2 +0 -0
  421. package/public/docs/assets/inter-roman-greek.BBVDIX6e.woff2 +0 -0
  422. package/public/docs/assets/inter-roman-latin-ext.4ZJIpNVo.woff2 +0 -0
  423. package/public/docs/assets/inter-roman-latin.Di8DUHzh.woff2 +0 -0
  424. package/public/docs/assets/inter-roman-vietnamese.BjW4sHH5.woff2 +0 -0
  425. package/public/docs/assets/style.tmDhD3c8.css +0 -1
  426. package/public/docs/assets/user-guide_getting-started_ci-and-automation.md.OUQqw3mI.js +0 -23
  427. package/public/docs/assets/user-guide_getting-started_ci-and-automation.md.OUQqw3mI.lean.js +0 -1
  428. package/public/docs/assets/user-guide_getting-started_reading-the-dashboard.md.Obf3W3__.js +0 -1
  429. package/public/docs/assets/user-guide_mcp-tools_compare-runs.md.Cc_gLoix.lean.js +0 -1
  430. package/public/docs/assets/user-guide_mcp-tools_diagnose-run.md.BP1vnHA5.js +0 -23
  431. package/public/docs/assets/user-guide_run-comparison.md.BUALkohi.js +0 -1
  432. package/public/docs/assets/user-guide_run-comparison.md.BUALkohi.lean.js +0 -1
  433. package/public/docs/assets/user-guide_understanding-findings.md.C9YRruMT.js +0 -1
  434. package/public/docs/assets/user-guide_understanding-findings.md.C9YRruMT.lean.js +0 -1
  435. /package/public/docs/assets/{contributor-guide_architecture_board-widgets_caching-and-memory.md.8bH1HnZp.lean.js → contributor-guide_architecture_board-widgets_caching-and-memory.md.BYDo3ClR.lean.js} +0 -0
  436. /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
  437. /package/public/docs/assets/{contributor-guide_architecture_overview.md.C1sSvm9i.lean.js → contributor-guide_architecture_overview.md.nxkpOhgf.lean.js} +0 -0
  438. /package/public/docs/assets/{contributor-guide_architecture_widget-rendering.md.BOZ1azXG.lean.js → contributor-guide_architecture_widget-rendering.md.BrSz8Ezh.lean.js} +0 -0
  439. /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
  440. /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
  441. /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
  442. /package/public/docs/assets/{contributor-guide_contributing.md.CQMvGwFt.lean.js → contributor-guide_contributing.md.DBW4drtZ.lean.js} +0 -0
  443. /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
  444. /package/public/docs/assets/{user-guide_mcp-tools.md.C65SjWUL.lean.js → user-guide_mcp-tools.md.49r3L2YE.lean.js} +0 -0
  445. /package/public/docs/assets/{user-guide_mcp-tools_get-run-summary.md.DpxZ4ZNp.lean.js → user-guide_mcp-tools_get-run-summary.md.EhaIsele.lean.js} +0 -0
package/public/docs/tuning-reference/pyspark.html CHANGED
@@ -6,30 +6,26 @@
6
6
  <title>PySpark Specifics | Spark Tuning Reference</title>
7
7
  <meta name="description" content="PySpark-specific performance: UDF serialization cost, Arrow-optimized and pandas UDF types, and Python-worker memory configs.">
8
8
  <meta name="generator" content="VitePress v1.6.4">
9
- <link rel="preload stylesheet" href="/docs/assets/style.tmDhD3c8.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.eYTPqTeq.js"></script>
13
- <link rel="preload" href="/docs/assets/inter-roman-latin.Di8DUHzh.woff2" as="font" type="font/woff2" crossorigin="">
14
- <link rel="modulepreload" href="/docs/assets/chunks/theme.DsTNE2pE.js">
12
+ <script type="module" src="/docs/assets/app.1gvzd5Zb.js"></script>
13
+ <link rel="modulepreload" href="/docs/assets/chunks/theme.C5lLqUv7.js">
15
14
  <link rel="modulepreload" href="/docs/assets/chunks/framework.DSg0KOwT.js">
16
15
  <link rel="modulepreload" href="/docs/assets/tuning-reference_pyspark.md.D-92XgF8.lean.js">
17
16
  <script>(()=>{const c=`${`[${["data","shuffle","product","bar"].join("-")}]`}, .VPNav, .VPLocalNav`,a=24,d=document.documentElement,l=t=>{const e=getComputedStyle(t);return e.display==="none"||t.getClientRects().length===0?0:e.position==="fixed"?t.getBoundingClientRect().bottom:e.position==="sticky"?(parseFloat(e.top)||0)+t.offsetHeight:0},u=()=>{try{return location.hash?document.getElementById(decodeURIComponent(location.hash.slice(1))):null}catch{return null}};let r=null;const s=()=>{const t=Array.from(document.querySelectorAll(c),l),e=Math.ceil(Math.max(0,...t))+a;if(e===r)return;const n=r;r=e,d.style.setProperty("--sf-anchor-offset",`${r}px`);const o=n===null?null:u();if(!o)return;const f=(parseFloat(getComputedStyle(o).paddingTop)||0)+2;Math.abs(o.getBoundingClientRect().top-n)<=f&&o.scrollIntoView()},i=()=>{const t=document.createElement("div");t.setAttribute("data-sf-anchor-offset",""),t.setAttribute("aria-hidden","true"),document.body.appendChild(t);const e=window.ResizeObserver?new ResizeObserver(s):null,n=()=>{e&&document.querySelectorAll(c).forEach(o=>e.observe(o)),s()};n(),new MutationObserver(n).observe(document.body,{childList:!0,subtree:!0}),window.addEventListener("resize",s),window.addEventListener("load",s)};document.readyState==="loading"?document.addEventListener("DOMContentLoaded",i,{once:!0}):i()})();</script>
18
17
  <link rel="icon" type="image/svg+xml" href="/docs/favicon.svg">
19
- <link rel="preconnect" href="https://fonts.googleapis.com">
20
- <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin="">
21
- <link rel="stylesheet" href="https://fonts.googleapis.com/css2?family=Recursive:wght,CASL@400..700,0..1&amp;family=JetBrains+Mono:wght@400;500;600&amp;display=swap">
22
18
  <script id="check-dark-mode">(()=>{const e=localStorage.getItem("vitepress-theme-appearance")||"auto",a=window.matchMedia("(prefers-color-scheme: dark)").matches;(!e||e==="auto"?a:e==="dark")&&document.documentElement.classList.add("dark")})();</script>
23
19
  <script id="check-mac-os">document.documentElement.classList.toggle("mac",/Mac|iPhone|iPod|iPad/i.test(navigator.platform));</script>
24
20
  </head>
25
21
  <body>
26
- <div id="app"><div class="Layout" data-v-5d98c3a5><!--[--><!--]--><!--[--><span tabindex="-1" data-v-0b0ada53></span><a href="#VPContent" class="VPSkipLink visually-hidden" data-v-0b0ada53>Skip to content</a><!--]--><!----><header class="VPNav" data-v-5d98c3a5 data-v-ae24b3ad><div class="VPNavBar" data-v-ae24b3ad data-v-6aa21345><div class="wrapper" data-v-6aa21345><div class="container" data-v-6aa21345><div class="title" data-v-6aa21345><div class="VPNavBarTitle has-sidebar" data-v-6aa21345 data-v-1168a8e4><a class="title" href="/docs/" data-v-1168a8e4><!--[--><!--]--><!--[--><img class="VPImage logo" src="/docs/favicon.svg" alt data-v-8426fc1a><!--]--><span data-v-1168a8e4>SparkForensics</span><!--[--><!--]--></a></div></div><div class="content" data-v-6aa21345><div class="content-body" data-v-6aa21345><!--[--><!--]--><div class="VPNavBarSearch search" data-v-6aa21345><!--[--><!----><div id="local-search"><button type="button" class="DocSearch DocSearch-Button" aria-label="Search"><span class="DocSearch-Button-Container"><span class="vp-icon DocSearch-Search-Icon"></span><span class="DocSearch-Button-Placeholder">Search</span></span><span class="DocSearch-Button-Keys"><kbd class="DocSearch-Button-Key"></kbd><kbd class="DocSearch-Button-Key">K</kbd></span></button></div><!--]--></div><nav aria-labelledby="main-nav-aria-label" class="VPNavBarMenu menu" data-v-6aa21345 data-v-dc692963><span id="main-nav-aria-label" class="visually-hidden" data-v-dc692963> Main Navigation </span><!--[--><!--[--><a class="VPLink link VPNavBarMenuLink" href="/docs/user-guide/getting-started.html" tabindex="0" data-v-dc692963 data-v-e56f3d57><!--[--><span data-v-e56f3d57>User Guide</span><!--]--></a><!--]--><!--[--><a class="VPLink link VPNavBarMenuLink" href="/docs/contributor-guide/development-setup.html" tabindex="0" data-v-dc692963 data-v-e56f3d57><!--[--><span data-v-e56f3d57>Contributor Guide</span><!--]--></a><!--]--><!--[--><a class="VPLink link VPNavBarMenuLink" href="/docs/tuning-reference/" tabindex="0" data-v-dc692963 data-v-e56f3d57><!--[--><span data-v-e56f3d57>Tuning Reference</span><!--]--></a><!--]--><!--]--></nav><!----><div class="VPNavBarAppearance appearance" data-v-6aa21345 data-v-6c893767><button class="VPSwitch VPSwitchAppearance" type="button" role="switch" title aria-checked="false" data-v-6c893767 data-v-5337faa4 data-v-1d5665e3><span class="check" data-v-1d5665e3><span class="icon" data-v-1d5665e3><!--[--><span class="vpi-sun sun" data-v-5337faa4></span><span class="vpi-moon moon" data-v-5337faa4></span><!--]--></span></span></button></div><!----><div class="VPFlyout VPNavBarExtra extra" data-v-6aa21345 data-v-bb2aa2f0 data-v-cf11d7a2><button type="button" class="button" aria-haspopup="true" aria-expanded="false" aria-label="extra navigation" data-v-cf11d7a2><span class="vpi-more-horizontal icon" data-v-cf11d7a2></span></button><div class="menu" data-v-cf11d7a2><div class="VPMenu" data-v-cf11d7a2 data-v-b98bc113><!----><!--[--><!--[--><!----><div class="group" data-v-bb2aa2f0><div class="item appearance" data-v-bb2aa2f0><p class="label" data-v-bb2aa2f0>Appearance</p><div class="appearance-action" data-v-bb2aa2f0><button class="VPSwitch VPSwitchAppearance" type="button" role="switch" title aria-checked="false" data-v-bb2aa2f0 data-v-5337faa4 data-v-1d5665e3><span class="check" data-v-1d5665e3><span class="icon" data-v-1d5665e3><!--[--><span class="vpi-sun sun" data-v-5337faa4></span><span class="vpi-moon moon" data-v-5337faa4></span><!--]--></span></span></button></div></div></div><!----><!--]--><!--]--></div></div></div><!--[--><!--]--><button type="button" class="VPNavBarHamburger hamburger" aria-label="mobile navigation" aria-expanded="false" aria-controls="VPNavScreen" data-v-6aa21345 data-v-e5dd9c1c><span class="container" data-v-e5dd9c1c><span class="top" data-v-e5dd9c1c></span><span class="middle" data-v-e5dd9c1c></span><span class="bottom" data-v-e5dd9c1c></span></span></button></div></div></div></div><div class="divider" data-v-6aa21345><div class="divider-line" data-v-6aa21345></div></div></div><!----></header><div class="VPLocalNav has-sidebar empty" data-v-5d98c3a5 data-v-a6f0e41e><div class="container" data-v-a6f0e41e><button class="menu" aria-expanded="false" aria-controls="VPSidebarNav" data-v-a6f0e41e><span class="vpi-align-left menu-icon" data-v-a6f0e41e></span><span class="menu-text" data-v-a6f0e41e>Menu</span></button><div class="VPLocalNavOutlineDropdown" style="--vp-vh:0px;" data-v-a6f0e41e data-v-8a42e2b4><button data-v-8a42e2b4>Return to top</button><!----></div></div></div><aside class="VPSidebar" data-v-5d98c3a5 data-v-319d5ca6><div class="curtain" data-v-319d5ca6></div><nav class="nav" id="VPSidebarNav" aria-labelledby="sidebar-aria-label" tabindex="-1" data-v-319d5ca6><span class="visually-hidden" id="sidebar-aria-label" data-v-319d5ca6> Sidebar Navigation </span><!--[--><!--]--><!--[--><div class="no-transition group" data-v-c40bc020><section class="VPSidebarItem level-0" data-v-c40bc020 data-v-b3fd67f8><div class="item" role="button" tabindex="0" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><h2 class="text" data-v-b3fd67f8>Getting Started</h2><!----></div><div class="items" data-v-b3fd67f8><!--[--><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/intro.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Introduction</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><div class="no-transition group" data-v-c40bc020><section class="VPSidebarItem level-0 has-active" data-v-c40bc020 data-v-b3fd67f8><div class="item" role="button" tabindex="0" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><h2 class="text" data-v-b3fd67f8>Optimization Guide</h2><!----></div><div class="items" data-v-b3fd67f8><!--[--><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/spark-architecture.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Spark Execution Model</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/memory-model.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Memory Management</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/partitioning.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Partitioning</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/joins.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Join Optimization</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/shuffle.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Shuffle</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/data-formats.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Data Formats</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/table-formats.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Table Formats</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/caching.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Caching & Persistence</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/pyspark.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>PySpark Specifics</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/aqe.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Adaptive Query Execution</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/cluster-config.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Cluster Tuning</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/anti-patterns.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Anti-Patterns</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><div class="no-transition group" data-v-c40bc020><section class="VPSidebarItem level-0" data-v-c40bc020 data-v-b3fd67f8><div class="item" role="button" tabindex="0" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><h2 class="text" data-v-b3fd67f8>Detector Catalog</h2><!----></div><div class="items" data-v-b3fd67f8><!--[--><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-skew.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Task Skew</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-shuffle.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Shuffle I/O</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-spill.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Memory / Disk Spill</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-gc.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>GC Pressure</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-cold-start.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Cold Start</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-utilization.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Executor Utilization</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-slow-host.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Slow Host</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-failures.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Task Failures</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-straggler.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Stragglers</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-retry-waste.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Retry Waste</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-tiny-tasks.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Tiny Tasks</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-job-failure-rate.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Job Failure Rate</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-memory-utilization.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Memory Utilization</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-duplicate-plan-subtree.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Duplicate Plan Subtree</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-small-files.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Small Files</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-broadcast-sizing.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Broadcast Sizing</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><div class="no-transition group" data-v-c40bc020><section class="VPSidebarItem level-0" data-v-c40bc020 data-v-b3fd67f8><div class="item" role="button" tabindex="0" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><h2 class="text" data-v-b3fd67f8>Reference</h2><!----></div><div class="items" data-v-b3fd67f8><!--[--><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/metrics.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Metrics Glossary</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/config.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Spark Config Quick-Reference</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><!--]--><!--[--><!--]--></nav></aside><div class="VPContent has-sidebar" id="VPContent" data-v-5d98c3a5 data-v-1428d186><div class="VPDoc has-sidebar has-aside" data-v-1428d186 data-v-39a288b8><!--[--><!--]--><div class="container" data-v-39a288b8><div class="aside" data-v-39a288b8><div class="aside-curtain" data-v-39a288b8></div><div class="aside-container" data-v-39a288b8><div class="aside-content" data-v-39a288b8><div class="VPDocAside" data-v-39a288b8 data-v-3f215769><!--[--><!--]--><!--[--><!--]--><nav aria-labelledby="doc-outline-aria-label" class="VPDocAsideOutline" data-v-3f215769 data-v-a5bbad30><div class="content" data-v-a5bbad30><div class="outline-marker" data-v-a5bbad30></div><div aria-level="2" class="outline-title" id="doc-outline-aria-label" role="heading" data-v-a5bbad30>On this page</div><ul class="VPDocOutlineItem root" data-v-a5bbad30 data-v-b933a997><!--[--><!--]--></ul></div></nav><!--[--><!--]--><div class="spacer" data-v-3f215769></div><!--[--><!--]--><!----><!--[--><!--]--><!--[--><!--]--></div></div></div></div><div class="content" data-v-39a288b8><div class="content-container" data-v-39a288b8><!--[--><!--]--><main class="main" data-v-39a288b8><div style="position:relative;" class="vp-doc _docs_tuning-reference_pyspark" data-v-39a288b8><div><h1 id="pyspark" tabindex="-1">PySpark Specifics <a class="header-anchor" href="#pyspark" aria-label="Permalink to &quot;PySpark Specifics {#pyspark}&quot;">​</a></h1><h2 id="crossing-the-jvm-python-boundary" tabindex="-1">Crossing the JVM/Python boundary <a class="header-anchor" href="#crossing-the-jvm-python-boundary" aria-label="Permalink to &quot;Crossing the JVM/Python boundary&quot;">​</a></h2><p>A plain PySpark UDF runs one row at a time in a separate Python process, and getting each row there costs something real: &quot;PySpark UDFs required data movement between the JVM and Python, which was quite expensive,&quot; using pickle to serialize the data across that boundary<sup class="footnote-ref"><a href="#fn1" id="fnref1">[1]</a></sup>. <em>Spark: The Definitive Guide</em> breaks the cost down further. Starting the extra Python process is one expense, but &quot;the real cost is in serializing the data to Python,&quot; and once the data is over there the JVM can no longer manage that worker&#39;s memory, so JVM and Python end up competing for the same machine&#39;s RAM and the worker can fail under pressure<sup class="footnote-ref"><a href="#fn2" id="fnref2">[2]</a></sup>. That&#39;s the underlying reason the same source recommends writing UDFs in Scala or Java and calling them from Python when that&#39;s practical<sup class="footnote-ref"><a href="#fn2" id="fnref2:1">[2:1]</a></sup>.</p><p>Since Spark 3.4 the row-at-a-time path can itself be Arrow-optimized without giving up row semantics: set <code>useArrow=True</code> on <code>udf()</code>, or flip the session-wide <code>spark.sql.execution.pythonUDF.arrow.enabled</code> (default <code>false</code>), and a regular Python UDF becomes an &quot;Arrow Python UDF&quot; that still runs row by row but moves data with Arrow instead of pickle<sup class="footnote-ref"><a href="#fn3" id="fnref3">[3]</a></sup><sup class="footnote-ref"><a href="#fn4" id="fnref4">[4]</a></sup>. The session config only takes effect when <code>useArrow</code> is left unset on the UDF itself<sup class="footnote-ref"><a href="#fn3" id="fnref3:1">[3:1]</a></sup>.</p><img class="light-only" src="/docs/assets/udf-execution-models.BUFDICuG.svg" alt="Across the JVM to Python boundary a plain Python UDF pickles row-at-a-time, an Arrow-optimized UDF uses Arrow transfer with row semantics, and a pandas UDF passes whole Arrow batches with no per-row handoff."><img class="dark-only" src="/docs/assets/udf-execution-models.dark.YTNS6GDq.svg" alt="Across the JVM to Python boundary a plain Python UDF pickles row-at-a-time, an Arrow-optimized UDF uses Arrow transfer with row semantics, and a pandas UDF passes whole Arrow batches with no per-row handoff."><p>The pandas UDF (vectorized UDF, introduced in Spark 2.3) goes further and drops the per-row JVM↔Python handoff entirely: it hands the Python worker whole Arrow batches, operated on as pandas Series or DataFrames, so there&#39;s nothing to pickle row by row<sup class="footnote-ref"><a href="#fn1" id="fnref1:1">[1:1]</a></sup>. Three shapes cover most cases. <strong>SCALAR</strong> (<code>pandas.Series, ... -&gt; pandas.Series</code>) is the direct vectorized swap-in for a row-at-a-time scalar UDF (computing <code>v + 1</code>, or <code>cubed(x)</code>); PySpark calls the function once per Arrow batch and concatenates the results back into a column<sup class="footnote-ref"><a href="#fn5" id="fnref5">[5]</a></sup><sup class="footnote-ref"><a href="#fn1" id="fnref1:2">[1:2]</a></sup>. <strong>SCALAR_ITER</strong> (<code>Iterator[Series] -&gt; Iterator[Series]</code>) works the same way internally, but takes and yields an iterator instead of a single Series, which lets a function prefetch across batches<sup class="footnote-ref"><a href="#fn3" id="fnref3:2">[3:2]</a></sup>. <strong>MAP_ITER</strong>, exposed as <code>DataFrame.mapInPandas()</code> rather than as a <code>pandas_udf</code> type, maps an iterator of whole <code>pandas.DataFrame</code> partitions to another iterator of <code>pandas.DataFrame</code>s and, unlike the other two, can change the row count<sup class="footnote-ref"><a href="#fn3" id="fnref3:3">[3:3]</a></sup>. A related grouped-map API, <code>DataFrame.groupBy().applyInPandas()</code>, splits the DataFrame into groups and runs a <code>pandas.DataFrame -&gt; pandas.DataFrame</code> function per group: split, apply, combine<sup class="footnote-ref"><a href="#fn5" id="fnref5:1">[5:1]</a></sup><sup class="footnote-ref"><a href="#fn3" id="fnref3:4">[3:4]</a></sup>.</p><p><code>spark.sql.execution.arrow.pyspark.enabled</code> isn&#39;t limited to pandas UDFs, either: it also governs Arrow-based columnar transfer for <code>DataFrame.toPandas()</code> and for <code>SparkSession.createDataFrame()</code> when given a pandas DataFrame or NumPy ndarray<sup class="footnote-ref"><a href="#fn4" id="fnref4:1">[4:1]</a></sup><sup class="footnote-ref"><a href="#fn3" id="fnref3:5">[3:5]</a></sup>. A companion flag, <code>spark.sql.execution.arrow.pyspark.fallback.enabled</code>, silently drops back to the non-Arrow path if an error occurs before computation starts<sup class="footnote-ref"><a href="#fn3" id="fnref3:6">[3:6]</a></sup><sup class="footnote-ref"><a href="#fn4" id="fnref4:2">[4:2]</a></sup>.</p><p>Two worker-level configs round out the picture. <code>spark.python.worker.reuse</code> (default <code>true</code>) keeps a fixed pool of Python worker processes alive across tasks instead of forking a fresh one each time, which also means a large broadcast variable doesn&#39;t have to cross the JVM↔Python boundary again for every task<sup class="footnote-ref"><a href="#fn4" id="fnref4:3">[4:3]</a></sup>. <code>spark.python.worker.memory</code> (default <code>512m</code>) is a per-worker, Spark-managed accounting threshold for in-worker aggregation buffering (not an OS-enforced cap), and Spark <a href="./bottleneck-spill.html">spills to disk</a> once it&#39;s exceeded<sup class="footnote-ref"><a href="#fn4" id="fnref4:4">[4:4]</a></sup>.</p><h2 id="measuring-the-gap" tabindex="-1">Measuring the gap <a class="header-anchor" href="#measuring-the-gap" aria-label="Permalink to &quot;Measuring the gap&quot;">​</a></h2><p>The clearest measurement here is workload-level. Databricks&#39; introductory pandas-UDF post ran three operations (Plus One, Cumulative Probability, Subtract Mean) over a 10M-row, two-column DataFrame on a single-node Databricks Community Edition cluster, and found pandas UDFs &quot;perform much better than row-at-a-time UDFs across the board, ranging from 3x to over 100x&quot;<sup class="footnote-ref"><a href="#fn5" id="fnref5:2">[5:2]</a></sup>. If a job&#39;s Python UDFs are a suspected bottleneck, expect an order-of-magnitude gap between a row-at-a-time UDF and its pandas-UDF equivalent, not a marginal one.</p><p>The comparisons in the corpus consistently favor <code>pyspark.sql.functions</code> and vectorized code over row-at-a-time UDFs. For the &quot;plus one&quot; example, &quot;built-in column operators can perform much faster in this scenario,&quot; and the pandas UDF equivalent is &quot;much faster than the row-at-a-time version&quot; because it&#39;s vectorized over the Series<sup class="footnote-ref"><a href="#fn5" id="fnref5:3">[5:3]</a></sup>. A Python UDF that could instead be expressed with built-in column functions is worth flagging on its own.</p><p>On the memory side, the two failure modes look different and are worth telling apart. A worker that spills is showing up in Spark&#39;s own accounting: it exceeded <code>spark.python.worker.memory</code> during aggregation and wrote to disk, which is expected behavior, not a crash<sup class="footnote-ref"><a href="#fn4" id="fnref4:5">[4:5]</a></sup>. A worker that&#39;s actually killed is a container-level event: if total container memory (JVM heap plus off-heap plus the Python process) exceeds what YARN or Kubernetes allocated, &quot;Kubernetes won&#39;t hesitate&quot; and the process is &quot;OOMKilled&quot;<sup class="footnote-ref"><a href="#fn6" id="fnref6">[6]</a></sup>. That boundary is governed by <a href="./memory-model.html">executor overhead</a> and <code>spark.executor.pyspark.memory</code> settings, not by <code>worker.memory</code>.</p><h2 id="what-the-gap-costs" tabindex="-1">What the gap costs <a class="header-anchor" href="#what-the-gap-costs" aria-label="Permalink to &quot;What the gap costs&quot;">​</a></h2><p>Those numbers point to a structural cost, not a tuning quirk. The JVM↔Python boundary is where a plain Python UDF pays twice: once to start the separate process, and again (the larger cost) to serialize every row across it<sup class="footnote-ref"><a href="#fn2" id="fnref2:2">[2:2]</a></sup>. Because the JVM can&#39;t manage memory inside the Python process once data has crossed over, the two runtimes end up competing for the same machine&#39;s memory, and the Python worker can fail under that pressure<sup class="footnote-ref"><a href="#fn2" id="fnref2:3">[2:3]</a></sup>. That&#39;s a correctness risk as well as a performance one, and it&#39;s why <em>Spark: The Definitive Guide</em> recommends Scala/Java UDFs called from Python over native Python UDFs wherever that&#39;s practical<sup class="footnote-ref"><a href="#fn2" id="fnref2:4">[2:4]</a></sup>.</p><p>The magnitude backs this up: Databricks measured pandas UDFs beating row-at-a-time UDFs by 3x to over 100x depending on the operation<sup class="footnote-ref"><a href="#fn5" id="fnref5:4">[5:4]</a></sup>. Skipping per-row pickling (by moving to Arrow-based row UDFs or, further, to pandas UDFs operating on whole batches) isn&#39;t a marginal tuning knob here; it changes which order of magnitude a job runs at.</p><p>The two memory configs matter for different reasons, too. <code>spark.python.worker.memory</code> only controls when Spark chooses to spill aggregation state to disk; tuning it trades disk I/O for headroom, it doesn&#39;t prevent a crash<sup class="footnote-ref"><a href="#fn4" id="fnref4:6">[4:6]</a></sup>. Actual OOM kills happen at the container boundary, and <code>spark.executor.pyspark.memory</code> (which leans on Python&#39;s <code>resource</code> module and so doesn&#39;t cap memory on macOS and doesn&#39;t exist at all on Windows) is the config that&#39;s actually in that path<sup class="footnote-ref"><a href="#fn4" id="fnref4:7">[4:7]</a></sup>. Conflating the two means tuning the wrong knob when a Python worker gets OOMKilled.</p><h2 id="closing-the-gap" tabindex="-1">Closing the gap <a class="header-anchor" href="#closing-the-gap" aria-label="Permalink to &quot;Closing the gap&quot;">​</a></h2><p>Closing that gap means avoiding the boundary crossing altogether, or crossing it as cheaply as possible. Where the logic allows it, prefer a built-in <code>pyspark.sql.functions</code> expression or a Scala/Java UDF called from Python over a plain row-at-a-time Python UDF<sup class="footnote-ref"><a href="#fn2" id="fnref2:5">[2:5]</a></sup><sup class="footnote-ref"><a href="#fn5" id="fnref5:5">[5:5]</a></sup>; this is the change with the largest documented payoff, 3x to over 100x<sup class="footnote-ref"><a href="#fn5" id="fnref5:6">[5:6]</a></sup>.</p><p>Where a Python UDF is unavoidable, cut the row-at-a-time cost first by turning on Arrow for it:</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:#6F42C1;--shiki-dark:#B392F0;">@udf</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">(</span><span style="--shiki-light:#E36209;--shiki-dark:#FFAB70;">returnType</span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583;">=</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">&#39;int&#39;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">, </span><span style="--shiki-light:#E36209;--shiki-dark:#FFAB70;">useArrow</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 style="--shiki-light:#6A737D;--shiki-dark:#6A737D;"># An Arrow Python UDF</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 has-active" data-v-c40bc020 data-v-b3fd67f8><div class="item" role="button" tabindex="0" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><h2 class="text" data-v-b3fd67f8>Optimization Guide</h2><!----></div><div class="items" data-v-b3fd67f8><!--[--><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/spark-architecture.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Spark Execution Model</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/memory-model.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Memory Management</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/partitioning.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Partitioning</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/joins.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Join Optimization</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/shuffle.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Shuffle</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/data-formats.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Data Formats</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/table-formats.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Table Formats</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/caching.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Caching & Persistence</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/pyspark.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>PySpark Specifics</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/aqe.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Adaptive Query Execution</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/cluster-config.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Cluster Tuning</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/anti-patterns.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Anti-Patterns</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><div class="no-transition group" data-v-c40bc020><section class="VPSidebarItem level-0" data-v-c40bc020 data-v-b3fd67f8><div class="item" role="button" tabindex="0" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><h2 class="text" data-v-b3fd67f8>Detector Catalog</h2><!----></div><div class="items" data-v-b3fd67f8><!--[--><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-skew.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Task Skew</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-shuffle.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Shuffle I/O</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-spill.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Memory / Disk Spill</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-gc.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>GC Pressure</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-cold-start.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Cold Start</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-utilization.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Executor Utilization</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-slow-host.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Slow Host</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-failures.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Task Failures</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-straggler.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Stragglers</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-retry-waste.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Retry Waste</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-tiny-tasks.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Tiny Tasks</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-job-failure-rate.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Job Failure Rate</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-memory-utilization.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Memory Utilization</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-duplicate-plan-subtree.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Duplicate Plan Subtree</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-small-files.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Small Files</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-broadcast-sizing.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Broadcast Sizing</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><div class="no-transition group" data-v-c40bc020><section class="VPSidebarItem level-0" data-v-c40bc020 data-v-b3fd67f8><div class="item" role="button" tabindex="0" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><h2 class="text" data-v-b3fd67f8>Reference</h2><!----></div><div class="items" data-v-b3fd67f8><!--[--><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/metrics.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Metrics Glossary</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/config.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Spark Config Quick-Reference</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><!--]--><!--[--><!--]--></nav></aside><div class="VPContent has-sidebar" id="VPContent" data-v-5d98c3a5 data-v-1428d186><div class="VPDoc has-sidebar has-aside" data-v-1428d186 data-v-39a288b8><!--[--><!--]--><div class="container" data-v-39a288b8><div class="aside" data-v-39a288b8><div class="aside-curtain" data-v-39a288b8></div><div class="aside-container" data-v-39a288b8><div class="aside-content" data-v-39a288b8><div class="VPDocAside" data-v-39a288b8 data-v-3f215769><!--[--><!--]--><!--[--><!--]--><nav aria-labelledby="doc-outline-aria-label" class="VPDocAsideOutline" data-v-3f215769 data-v-a5bbad30><div class="content" data-v-a5bbad30><div class="outline-marker" data-v-a5bbad30></div><div aria-level="2" class="outline-title" id="doc-outline-aria-label" role="heading" data-v-a5bbad30>On this page</div><ul class="VPDocOutlineItem root" data-v-a5bbad30 data-v-b933a997><!--[--><!--]--></ul></div></nav><!--[--><!--]--><div class="spacer" data-v-3f215769></div><!--[--><!--]--><!----><!--[--><!--]--><!--[--><!--]--></div></div></div></div><div class="content" data-v-39a288b8><div class="content-container" data-v-39a288b8><!--[--><!--]--><main class="main" data-v-39a288b8><div style="position:relative;" class="vp-doc _docs_tuning-reference_pyspark" data-v-39a288b8><div><h1 id="pyspark" tabindex="-1">PySpark Specifics <a class="header-anchor" href="#pyspark" aria-label="Permalink to &quot;PySpark Specifics {#pyspark}&quot;">​</a></h1><h2 id="crossing-the-jvm-python-boundary" tabindex="-1">Crossing the JVM/Python boundary <a class="header-anchor" href="#crossing-the-jvm-python-boundary" aria-label="Permalink to &quot;Crossing the JVM/Python boundary&quot;">​</a></h2><p>A plain PySpark UDF runs one row at a time in a separate Python process, and getting each row there costs something real: &quot;PySpark UDFs required data movement between the JVM and Python, which was quite expensive,&quot; using pickle to serialize the data across that boundary<sup class="footnote-ref"><a href="#fn1" id="fnref1">[1]</a></sup>. <em>Spark: The Definitive Guide</em> breaks the cost down further. Starting the extra Python process is one expense, but &quot;the real cost is in serializing the data to Python,&quot; and once the data is over there the JVM can no longer manage that worker&#39;s memory, so JVM and Python end up competing for the same machine&#39;s RAM and the worker can fail under pressure<sup class="footnote-ref"><a href="#fn2" id="fnref2">[2]</a></sup>. That&#39;s the underlying reason the same source recommends writing UDFs in Scala or Java and calling them from Python when that&#39;s practical<sup class="footnote-ref"><a href="#fn2" id="fnref2:1">[2:1]</a></sup>.</p><p>Since Spark 3.4 the row-at-a-time path can itself be Arrow-optimized without giving up row semantics: set <code>useArrow=True</code> on <code>udf()</code>, or flip the session-wide <code>spark.sql.execution.pythonUDF.arrow.enabled</code> (default <code>false</code>), and a regular Python UDF becomes an &quot;Arrow Python UDF&quot; that still runs row by row but moves data with Arrow instead of pickle<sup class="footnote-ref"><a href="#fn3" id="fnref3">[3]</a></sup><sup class="footnote-ref"><a href="#fn4" id="fnref4">[4]</a></sup>. The session config only takes effect when <code>useArrow</code> is left unset on the UDF itself<sup class="footnote-ref"><a href="#fn3" id="fnref3:1">[3:1]</a></sup>.</p><img class="light-only" src="/docs/assets/udf-execution-models.BUFDICuG.svg" alt="Across the JVM to Python boundary a plain Python UDF pickles row-at-a-time, an Arrow-optimized UDF uses Arrow transfer with row semantics, and a pandas UDF passes whole Arrow batches with no per-row handoff."><img class="dark-only" src="/docs/assets/udf-execution-models.dark.YTNS6GDq.svg" alt="Across the JVM to Python boundary a plain Python UDF pickles row-at-a-time, an Arrow-optimized UDF uses Arrow transfer with row semantics, and a pandas UDF passes whole Arrow batches with no per-row handoff."><p>The pandas UDF (vectorized UDF, introduced in Spark 2.3) goes further and drops the per-row JVM↔Python handoff entirely: it hands the Python worker whole Arrow batches, operated on as pandas Series or DataFrames, so there&#39;s nothing to pickle row by row<sup class="footnote-ref"><a href="#fn1" id="fnref1:1">[1:1]</a></sup>. Three shapes cover most cases. <strong>SCALAR</strong> (<code>pandas.Series, ... -&gt; pandas.Series</code>) is the direct vectorized swap-in for a row-at-a-time scalar UDF (computing <code>v + 1</code>, or <code>cubed(x)</code>); PySpark calls the function once per Arrow batch and concatenates the results back into a column<sup class="footnote-ref"><a href="#fn5" id="fnref5">[5]</a></sup><sup class="footnote-ref"><a href="#fn1" id="fnref1:2">[1:2]</a></sup>. <strong>SCALAR_ITER</strong> (<code>Iterator[Series] -&gt; Iterator[Series]</code>) works the same way internally, but takes and yields an iterator instead of a single Series, which lets a function prefetch across batches<sup class="footnote-ref"><a href="#fn3" id="fnref3:2">[3:2]</a></sup>. <strong>MAP_ITER</strong>, exposed as <code>DataFrame.mapInPandas()</code> rather than as a <code>pandas_udf</code> type, maps an iterator of whole <code>pandas.DataFrame</code> partitions to another iterator of <code>pandas.DataFrame</code>s and, unlike the other two, can change the row count<sup class="footnote-ref"><a href="#fn3" id="fnref3:3">[3:3]</a></sup>. A related grouped-map API, <code>DataFrame.groupBy().applyInPandas()</code>, splits the DataFrame into groups and runs a <code>pandas.DataFrame -&gt; pandas.DataFrame</code> function per group: split, apply, combine<sup class="footnote-ref"><a href="#fn5" id="fnref5:1">[5:1]</a></sup><sup class="footnote-ref"><a href="#fn3" id="fnref3:4">[3:4]</a></sup>.</p><p><code>spark.sql.execution.arrow.pyspark.enabled</code> isn&#39;t limited to pandas UDFs, either: it also governs Arrow-based columnar transfer for <code>DataFrame.toPandas()</code> and for <code>SparkSession.createDataFrame()</code> when given a pandas DataFrame or NumPy ndarray<sup class="footnote-ref"><a href="#fn4" id="fnref4:1">[4:1]</a></sup><sup class="footnote-ref"><a href="#fn3" id="fnref3:5">[3:5]</a></sup>. A companion flag, <code>spark.sql.execution.arrow.pyspark.fallback.enabled</code>, silently drops back to the non-Arrow path if an error occurs before computation starts<sup class="footnote-ref"><a href="#fn3" id="fnref3:6">[3:6]</a></sup><sup class="footnote-ref"><a href="#fn4" id="fnref4:2">[4:2]</a></sup>.</p><p>Two worker-level configs round out the picture. <code>spark.python.worker.reuse</code> (default <code>true</code>) keeps a fixed pool of Python worker processes alive across tasks instead of forking a fresh one each time, which also means a large broadcast variable doesn&#39;t have to cross the JVM↔Python boundary again for every task<sup class="footnote-ref"><a href="#fn4" id="fnref4:3">[4:3]</a></sup>. <code>spark.python.worker.memory</code> (default <code>512m</code>) is a per-worker, Spark-managed accounting threshold for in-worker aggregation buffering (not an OS-enforced cap), and Spark <a href="./bottleneck-spill.html">spills to disk</a> once it&#39;s exceeded<sup class="footnote-ref"><a href="#fn4" id="fnref4:4">[4:4]</a></sup>.</p><h2 id="measuring-the-gap" tabindex="-1">Measuring the gap <a class="header-anchor" href="#measuring-the-gap" aria-label="Permalink to &quot;Measuring the gap&quot;">​</a></h2><p>The clearest measurement here is workload-level. Databricks&#39; introductory pandas-UDF post ran three operations (Plus One, Cumulative Probability, Subtract Mean) over a 10M-row, two-column DataFrame on a single-node Databricks Community Edition cluster, and found pandas UDFs &quot;perform much better than row-at-a-time UDFs across the board, ranging from 3x to over 100x&quot;<sup class="footnote-ref"><a href="#fn5" id="fnref5:2">[5:2]</a></sup>. If a job&#39;s Python UDFs are a suspected bottleneck, expect an order-of-magnitude gap between a row-at-a-time UDF and its pandas-UDF equivalent, not a marginal one.</p><p>The comparisons in the corpus consistently favor <code>pyspark.sql.functions</code> and vectorized code over row-at-a-time UDFs. For the &quot;plus one&quot; example, &quot;built-in column operators can perform much faster in this scenario,&quot; and the pandas UDF equivalent is &quot;much faster than the row-at-a-time version&quot; because it&#39;s vectorized over the Series<sup class="footnote-ref"><a href="#fn5" id="fnref5:3">[5:3]</a></sup>. A Python UDF that could instead be expressed with built-in column functions is worth flagging on its own.</p><p>On the memory side, the two failure modes look different and are worth telling apart. A worker that spills is showing up in Spark&#39;s own accounting: it exceeded <code>spark.python.worker.memory</code> during aggregation and wrote to disk, which is expected behavior, not a crash<sup class="footnote-ref"><a href="#fn4" id="fnref4:5">[4:5]</a></sup>. A worker that&#39;s actually killed is a container-level event: if total container memory (JVM heap plus off-heap plus the Python process) exceeds what YARN or Kubernetes allocated, &quot;Kubernetes won&#39;t hesitate&quot; and the process is &quot;OOMKilled&quot;<sup class="footnote-ref"><a href="#fn6" id="fnref6">[6]</a></sup>. That boundary is governed by <a href="./memory-model.html">executor overhead</a> and <code>spark.executor.pyspark.memory</code> settings, not by <code>worker.memory</code>.</p><h2 id="what-the-gap-costs" tabindex="-1">What the gap costs <a class="header-anchor" href="#what-the-gap-costs" aria-label="Permalink to &quot;What the gap costs&quot;">​</a></h2><p>Those numbers point to a structural cost, not a tuning quirk. The JVM↔Python boundary is where a plain Python UDF pays twice: once to start the separate process, and again (the larger cost) to serialize every row across it<sup class="footnote-ref"><a href="#fn2" id="fnref2:2">[2:2]</a></sup>. Because the JVM can&#39;t manage memory inside the Python process once data has crossed over, the two runtimes end up competing for the same machine&#39;s memory, and the Python worker can fail under that pressure<sup class="footnote-ref"><a href="#fn2" id="fnref2:3">[2:3]</a></sup>. That&#39;s a correctness risk as well as a performance one, and it&#39;s why <em>Spark: The Definitive Guide</em> recommends Scala/Java UDFs called from Python over native Python UDFs wherever that&#39;s practical<sup class="footnote-ref"><a href="#fn2" id="fnref2:4">[2:4]</a></sup>.</p><p>The magnitude backs this up: Databricks measured pandas UDFs beating row-at-a-time UDFs by 3x to over 100x depending on the operation<sup class="footnote-ref"><a href="#fn5" id="fnref5:4">[5:4]</a></sup>. Skipping per-row pickling (by moving to Arrow-based row UDFs or, further, to pandas UDFs operating on whole batches) isn&#39;t a marginal tuning knob here; it changes which order of magnitude a job runs at.</p><p>The two memory configs matter for different reasons, too. <code>spark.python.worker.memory</code> only controls when Spark chooses to spill aggregation state to disk; tuning it trades disk I/O for headroom, it doesn&#39;t prevent a crash<sup class="footnote-ref"><a href="#fn4" id="fnref4:6">[4:6]</a></sup>. Actual OOM kills happen at the container boundary, and <code>spark.executor.pyspark.memory</code> (which leans on Python&#39;s <code>resource</code> module and so doesn&#39;t cap memory on macOS and doesn&#39;t exist at all on Windows) is the config that&#39;s actually in that path<sup class="footnote-ref"><a href="#fn4" id="fnref4:7">[4:7]</a></sup>. Conflating the two means tuning the wrong knob when a Python worker gets OOMKilled.</p><h2 id="closing-the-gap" tabindex="-1">Closing the gap <a class="header-anchor" href="#closing-the-gap" aria-label="Permalink to &quot;Closing the gap&quot;">​</a></h2><p>Closing that gap means avoiding the boundary crossing altogether, or crossing it as cheaply as possible. Where the logic allows it, prefer a built-in <code>pyspark.sql.functions</code> expression or a Scala/Java UDF called from Python over a plain row-at-a-time Python UDF<sup class="footnote-ref"><a href="#fn2" id="fnref2:5">[2:5]</a></sup><sup class="footnote-ref"><a href="#fn5" id="fnref5:5">[5:5]</a></sup>; this is the change with the largest documented payoff, 3x to over 100x<sup class="footnote-ref"><a href="#fn5" id="fnref5:6">[5:6]</a></sup>.</p><p>Where a Python UDF is unavoidable, cut the row-at-a-time cost first by turning on Arrow for it:</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:#6F42C1;--shiki-dark:#B392F0;">@udf</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">(</span><span style="--shiki-light:#E36209;--shiki-dark:#FFAB70;">returnType</span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583;">=</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">&#39;int&#39;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">, </span><span style="--shiki-light:#E36209;--shiki-dark:#FFAB70;">useArrow</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 style="--shiki-light:#6A737D;--shiki-dark:#6A737D;"># An Arrow Python UDF</span></span>
27
23
  <span class="line"><span style="--shiki-light:#D73A49;--shiki-dark:#F97583;">def</span><span style="--shiki-light:#6F42C1;--shiki-dark:#B392F0;"> arrow_slen</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">(s):</span></span>
28
24
  <span class="line"><span style="--shiki-light:#D73A49;--shiki-dark:#F97583;"> return</span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;"> len</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">(s)</span></span></code></pre></div><p>or set the session-wide equivalent so existing UDFs pick it up without code changes.</p><blockquote><p><strong>PySpark:</strong> <code>spark.conf.set(&quot;spark.sql.execution.pythonUDF.arrow.enabled&quot;, &quot;true&quot;)</code> turns plain UDFs into Arrow-backed ones, as long as <code>useArrow</code> isn&#39;t explicitly set on the UDF itself<sup class="footnote-ref"><a href="#fn3" id="fnref3:7">[3:7]</a></sup><sup class="footnote-ref"><a href="#fn4" id="fnref4:8">[4:8]</a></sup>.</p></blockquote><p>Beyond that, reach for the vectorized APIs instead of a scalar UDF:</p><ul><li>Use a <strong>SCALAR</strong> pandas UDF (<code>pandas.Series, ... -&gt; pandas.Series</code>) as the default vectorized replacement for a row-at-a-time scalar UDF<sup class="footnote-ref"><a href="#fn5" id="fnref5:7">[5:7]</a></sup><sup class="footnote-ref"><a href="#fn1" id="fnref1:3">[1:3]</a></sup>.</li><li>Use <strong>SCALAR_ITER</strong> (<code>Iterator[Series] -&gt; Iterator[Series]</code>) when the function needs expensive one-time setup. The documented pattern initializes state once, then loops over the batch iterator reusing it, instead of re-initializing per batch<sup class="footnote-ref"><a href="#fn3" id="fnref3:8">[3:8]</a></sup>:</li></ul><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:#D73A49;--shiki-dark:#F97583;">def</span><span style="--shiki-light:#6F42C1;--shiki-dark:#B392F0;"> apply_with_state</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">(iterator):</span></span>
29
25
  <span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> state </span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583;">=</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> very_expensive_initialization()</span></span>
30
26
  <span class="line"><span style="--shiki-light:#D73A49;--shiki-dark:#F97583;"> for</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> batch </span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583;">in</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> iterator:</span></span>
31
27
  <span class="line"><span style="--shiki-light:#D73A49;--shiki-dark:#F97583;"> yield</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> calculate_with_state(batch, state)</span></span></code></pre></div><ul><li>Use <code>DataFrame.mapInPandas()</code> when the transform needs to change row count (filtering, expansion, deduplication) rather than map one-to-one<sup class="footnote-ref"><a href="#fn3" id="fnref3:9">[3:9]</a></sup>.</li><li>Use <code>DataFrame.groupBy().applyInPandas()</code> for per-group logic that needs the whole group as state, such as subtracting a group mean or fitting a per-group regression<sup class="footnote-ref"><a href="#fn5" id="fnref5:8">[5:8]</a></sup><sup class="footnote-ref"><a href="#fn3" id="fnref3:10">[3:10]</a></sup>. Size groups with care: a full group loads into memory before the function runs, and <code>maxRecordsPerBatch</code> doesn&#39;t apply to groups, so a skewed group risks OOM<sup class="footnote-ref"><a href="#fn3" id="fnref3:11">[3:11]</a></sup>.</li></ul><p>For pandas/NumPy conversion at the driver, turn on Arrow explicitly rather than relying on defaults.</p><blockquote><p><strong>PySpark:</strong> with <code>spark.sql.execution.arrow.pyspark.enabled</code> set to <code>&quot;true&quot;</code>, <code>spark.createDataFrame(pdf)</code> and <code>df.select(&quot;*&quot;).toPandas()</code> convert through Arrow and return the same result as the non-Arrow path<sup class="footnote-ref"><a href="#fn4" id="fnref4:9">[4:9]</a></sup><sup class="footnote-ref"><a href="#fn3" id="fnref3:12">[3:12]</a></sup>. <code>spark.sql.execution.arrow.pyspark.fallback.enabled</code> keeps a safety net by falling back silently on pre-computation errors<sup class="footnote-ref"><a href="#fn3" id="fnref3:13">[3:13]</a></sup><sup class="footnote-ref"><a href="#fn4" id="fnref4:10">[4:10]</a></sup>.</p></blockquote><p>Leave <code>spark.python.worker.reuse</code> at its default (<code>true</code>) unless there&#39;s a specific reason not to; it keeps a fixed pool of Python workers alive so a large broadcast variable isn&#39;t re-shipped to Python for every task<sup class="footnote-ref"><a href="#fn4" id="fnref4:11">[4:11]</a></sup>. If a job spills at the Python-worker level, <code>spark.python.worker.memory</code> is the knob for that; if it&#39;s getting OOMKilled at the container level, look at executor overhead and <code>spark.executor.pyspark.memory</code> instead, keeping in mind the latter&#39;s <code>resource</code>-module limitations on macOS and its absence on Windows<sup class="footnote-ref"><a href="#fn4" id="fnref4:12">[4:12]</a></sup><sup class="footnote-ref"><a href="#fn6" id="fnref6:1">[6:1]</a></sup>.</p><h2 id="sources" tabindex="-1">Sources <a class="header-anchor" href="#sources" aria-label="Permalink to &quot;Sources&quot;">​</a></h2><hr class="footnotes-sep"><section class="footnotes"><ol class="footnotes-list"><li id="fn1" class="footnote-item"><p><em>Learning Spark, 2nd Edition</em>, Damji, Wenig, Das &amp; Lee, ch. 5 <a href="#fnref1" class="footnote-backref">↩︎</a> <a href="#fnref1:1" class="footnote-backref">↩︎</a> <a href="#fnref1:2" class="footnote-backref">↩︎</a> <a href="#fnref1:3" class="footnote-backref">↩︎</a></p></li><li id="fn2" class="footnote-item"><p><em>Spark: The Definitive Guide</em>, Chambers &amp; Zaharia, ch. 6 <a href="#fnref2" class="footnote-backref">↩︎</a> <a href="#fnref2:1" class="footnote-backref">↩︎</a> <a href="#fnref2:2" class="footnote-backref">↩︎</a> <a href="#fnref2:3" class="footnote-backref">↩︎</a> <a href="#fnref2:4" class="footnote-backref">↩︎</a> <a href="#fnref2:5" class="footnote-backref">↩︎</a></p></li><li id="fn3" class="footnote-item"><p><a href="https://spark.apache.org/docs/3.5.8/api/python/user_guide/sql/arrow_pandas.html" target="_blank" rel="noreferrer">Apache Arrow in PySpark</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> <a href="#fnref3:6" class="footnote-backref">↩︎</a> <a href="#fnref3:7" class="footnote-backref">↩︎</a> <a href="#fnref3:8" class="footnote-backref">↩︎</a> <a href="#fnref3:9" class="footnote-backref">↩︎</a> <a href="#fnref3:10" class="footnote-backref">↩︎</a> <a href="#fnref3:11" class="footnote-backref">↩︎</a> <a href="#fnref3:12" class="footnote-backref">↩︎</a> <a href="#fnref3:13" class="footnote-backref">↩︎</a></p></li><li id="fn4" class="footnote-item"><p><a href="https://spark.apache.org/docs/latest/configuration.html" target="_blank" rel="noreferrer">Configuration — Spark</a> <a href="#fnref4" class="footnote-backref">↩︎</a> <a href="#fnref4:1" class="footnote-backref">↩︎</a> <a href="#fnref4:2" class="footnote-backref">↩︎</a> <a href="#fnref4:3" class="footnote-backref">↩︎</a> <a href="#fnref4:4" class="footnote-backref">↩︎</a> <a href="#fnref4:5" class="footnote-backref">↩︎</a> <a href="#fnref4:6" class="footnote-backref">↩︎</a> <a href="#fnref4:7" class="footnote-backref">↩︎</a> <a href="#fnref4:8" class="footnote-backref">↩︎</a> <a href="#fnref4:9" class="footnote-backref">↩︎</a> <a href="#fnref4:10" class="footnote-backref">↩︎</a> <a href="#fnref4:11" class="footnote-backref">↩︎</a> <a href="#fnref4:12" class="footnote-backref">↩︎</a></p></li><li id="fn5" class="footnote-item"><p><a href="https://www.databricks.com/blog/2017/10/30/introducing-vectorized-udfs-for-pyspark.html" target="_blank" rel="noreferrer">Introducing Pandas UDF for PySpark</a> <a href="#fnref5" class="footnote-backref">↩︎</a> <a href="#fnref5:1" class="footnote-backref">↩︎</a> <a href="#fnref5:2" class="footnote-backref">↩︎</a> <a href="#fnref5:3" class="footnote-backref">↩︎</a> <a href="#fnref5:4" class="footnote-backref">↩︎</a> <a href="#fnref5:5" class="footnote-backref">↩︎</a> <a href="#fnref5:6" class="footnote-backref">↩︎</a> <a href="#fnref5:7" class="footnote-backref">↩︎</a> <a href="#fnref5:8" class="footnote-backref">↩︎</a></p></li><li id="fn6" class="footnote-item"><p><a href="https://luminousmen.com/post/dive-into-spark-memory" target="_blank" rel="noreferrer">Dive into Spark memory management</a> <a href="#fnref6" class="footnote-backref">↩︎</a> <a href="#fnref6:1" 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/caching.html" data-v-e257564d><!--[--><span class="desc" data-v-e257564d>Previous page</span><span class="title" data-v-e257564d>Caching & Persistence</span><!--]--></a></div><div class="pager" data-v-e257564d><a class="VPLink link pager-link next" href="/docs/tuning-reference/aqe.html" data-v-e257564d><!--[--><span class="desc" data-v-e257564d>Next page</span><span class="title" data-v-e257564d>Adaptive Query Execution</span><!--]--></a></div></nav></footer><!--[--><!--]--></div></div></div><!--[--><!--]--></div></div><!----><!--[--><!--]--></div></div>
32
- <script>window.__VP_HASH_MAP__=JSON.parse("{\"contributor-guide_architecture_board-widgets.md\":\"YQcj5EI4\",\"contributor-guide_architecture_board-widgets_caching-and-memory.md\":\"8bH1HnZp\",\"contributor-guide_architecture_board-widgets_plan-advisor.md\":\"RlzvUmNm\",\"contributor-guide_architecture_board-widgets_visual-system-and-templating.md\":\"DYgUpIJB\",\"contributor-guide_architecture_detector-contract.md\":\"wj6Et6UD\",\"contributor-guide_architecture_detector-contract_plan-attribution.md\":\"yNex4bys\",\"contributor-guide_architecture_detector-contract_threshold-tables.md\":\"CKjWG56Y\",\"contributor-guide_architecture_drill-down.md\":\"CqZPrdo9\",\"contributor-guide_architecture_drill-down_plan-graph.md\":\"DwOozIEs\",\"contributor-guide_architecture_impact-estimation.md\":\"CZv_ZGOp\",\"contributor-guide_architecture_impact-estimation_caveats-tuning-and-coverage.md\":\"BUucRc0A\",\"contributor-guide_architecture_impact-estimation_stage-union-rollup.md\":\"DdCGtAGu\",\"contributor-guide_architecture_index.md\":\"tymxf1Fh\",\"contributor-guide_architecture_overview.md\":\"C1sSvm9i\",\"contributor-guide_architecture_state-and-history.md\":\"DyCBdjuM\",\"contributor-guide_architecture_state-and-history_history-server-intake.md\":\"C298hrHZ\",\"contributor-guide_architecture_state-and-history_run-comparison-internals.md\":\"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\":\"DC1YqXBp\",\"contributor-guide_architecture_worker-protocol_core-and-event-validation.md\":\"DSVFPpWb\",\"contributor-guide_architecture_worker-protocol_evidence-availability.md\":\"CjimIDBY\",\"contributor-guide_architecture_worker-protocol_evidence-report.md\":\"DVGZOWvW\",\"contributor-guide_contributing.md\":\"CQMvGwFt\",\"contributor-guide_development-setup.md\":\"D9bu4j_c\",\"contributor-guide_testing.md\":\"By6XGR9a\",\"index.md\":\"CHJVslga\",\"tuning-reference_anti-patterns.md\":\"D08Uaod7\",\"tuning-reference_aqe.md\":\"C1Ae6A8u\",\"tuning-reference_bottleneck-broadcast-sizing.md\":\"6wjKuJNE\",\"tuning-reference_bottleneck-cold-start.md\":\"BVQbsuHP\",\"tuning-reference_bottleneck-duplicate-plan-subtree.md\":\"DtaYnaiF\",\"tuning-reference_bottleneck-failures.md\":\"Z1Tdmdd3\",\"tuning-reference_bottleneck-gc.md\":\"BCnXLf1n\",\"tuning-reference_bottleneck-job-failure-rate.md\":\"CcvQj2g9\",\"tuning-reference_bottleneck-memory-utilization.md\":\"B-C0-8h-\",\"tuning-reference_bottleneck-retry-waste.md\":\"DCnhWiqj\",\"tuning-reference_bottleneck-shuffle.md\":\"B5OMJCd3\",\"tuning-reference_bottleneck-skew.md\":\"Cvo6NQm_\",\"tuning-reference_bottleneck-slow-host.md\":\"ja5qr3wq\",\"tuning-reference_bottleneck-small-files.md\":\"Crjtb0i2\",\"tuning-reference_bottleneck-spill.md\":\"Bl8KtSRg\",\"tuning-reference_bottleneck-straggler.md\":\"B0VN8reT\",\"tuning-reference_bottleneck-tiny-tasks.md\":\"DQCftGhu\",\"tuning-reference_bottleneck-utilization.md\":\"BXDl30f9\",\"tuning-reference_caching.md\":\"CcaiMn_7\",\"tuning-reference_cluster-config.md\":\"DbWG1yZq\",\"tuning-reference_config.md\":\"YUqSpwFB\",\"tuning-reference_data-formats.md\":\"C5DX5xL4\",\"tuning-reference_index.md\":\"ZVIpQ6Dk\",\"tuning-reference_intro.md\":\"BSSaDlqx\",\"tuning-reference_joins.md\":\"BVhNCDnE\",\"tuning-reference_memory-model.md\":\"CfjFdgbl\",\"tuning-reference_metrics.md\":\"C64VNEL4\",\"tuning-reference_partitioning.md\":\"CtLK0xsS\",\"tuning-reference_pyspark.md\":\"D-92XgF8\",\"tuning-reference_shuffle.md\":\"Iq2v1oHJ\",\"tuning-reference_spark-architecture.md\":\"_qwnE_Sc\",\"tuning-reference_table-formats.md\":\"BSYEK-eN\",\"user-guide_alternative-log-retrieval.md\":\"CJpYvHGo\",\"user-guide_alternative-log-retrieval_managed-platforms.md\":\"DvDwHNtC\",\"user-guide_alternative-log-retrieval_ssh-bastion.md\":\"Gszzlplv\",\"user-guide_getting-started.md\":\"DYHHHkQR\",\"user-guide_getting-started_ci-and-automation.md\":\"OUQqw3mI\",\"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\":\"DpxZ4ZNp\",\"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\":\"C9YRruMT\"}");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>
28
+ <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>
33
29
 
34
30
  </body>
35
31
  </html>