sparkforensics-server 0.1.0 → 0.2.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (440) hide show
  1. package/README.md +6 -0
  2. package/index.js +40 -49
  3. package/lib/static-files.js +10 -6
  4. package/package.json +20 -1
  5. package/public/assets/AutoscalingChurn-CFJkiqxW.js +1 -0
  6. package/public/assets/CacheUtilization-kTKZBzDA.js +1 -0
  7. package/public/assets/CachingOpportunity-CU70EWcF.js +1 -0
  8. package/public/assets/ColdStart-hOI-WOvm.js +1 -0
  9. package/public/assets/ConfigAudit-B4oAksZY.js +1 -0
  10. package/public/assets/CoreUsageArea-D-dR3SQk.js +1 -0
  11. package/public/assets/Dashboard-MDhohsq4.js +4 -0
  12. package/public/assets/DuplicatePlanSubtree-54RKsfI7.js +1 -0
  13. package/public/assets/DurationHistogram-CviQyPNM.js +1 -0
  14. package/public/assets/EmptyState-v2ehFncc.js +1 -0
  15. package/public/assets/ExecutorUtilization-vHyFHgL6.js +1 -0
  16. package/public/assets/GcPressure-DINuhcno.js +1 -0
  17. package/public/assets/ImpactEstimate-C6GzFOY9.js +1 -0
  18. package/public/assets/IncompleteRun-a1kuCnU6.js +1 -0
  19. package/public/assets/JobFailures-CYwPfUhR.js +1 -0
  20. package/public/assets/MemoryUtilization-Dlfj0e_f.js +1 -0
  21. package/public/assets/OverBroadcast-BMu7Y8l9.js +1 -0
  22. package/public/assets/PartitionSizing-CvMGfSVB.js +1 -0
  23. package/public/assets/PlanExplorer-xYFme_Rx.js +1 -0
  24. package/public/assets/PlanGraphRoute-a3OGg6ET.js +1 -0
  25. package/public/assets/RetryWaste-JKRjOZ-J.js +1 -0
  26. package/public/assets/RowPagination-DypWbnic.js +1 -0
  27. package/public/assets/ShuffleIO-Mi8HiVu-.js +1 -0
  28. package/public/assets/Skew-C3iOScTC.js +1 -0
  29. package/public/assets/SlowHost-DKBg18v-.js +1 -0
  30. package/public/assets/SmallFiles-CCCB6AIu.js +1 -0
  31. package/public/assets/SpeculationWaste-DUNupw0_.js +1 -0
  32. package/public/assets/Spill-BlLdatik.js +1 -0
  33. package/public/assets/StageFailed-qtY7C7Yo.js +1 -0
  34. package/public/assets/StageFindingGroup-CoVdEZYs.js +1 -0
  35. package/public/assets/StageHeader-uDBLHgdg.js +1 -0
  36. package/public/assets/StagePill-CYCMdlIx.js +1 -0
  37. package/public/assets/StageShape-zs0mAjQJ.js +1 -0
  38. package/public/assets/StageSlowness-C7vg0u5Q.js +1 -0
  39. package/public/assets/Straggler-4BRGAQP4.js +1 -0
  40. package/public/assets/TaskFailures-CSjO23Kg.js +1 -0
  41. package/public/assets/TinyTask-6Zuovcn5.js +1 -0
  42. package/public/assets/UnderBroadcast-CePjo0ZV.js +1 -0
  43. package/public/assets/WidgetLeadSummary-DRNRVvn7.js +1 -0
  44. package/public/assets/{charts-vendor-NMqKV0H4.js → charts-vendor-Cf1-wzeH.js} +2 -2
  45. package/public/assets/downsample-D8XmJk6i.js +1 -0
  46. package/public/assets/finding-anchor-4TmpXd7j.js +1 -0
  47. package/public/assets/impact-sort-Cq6KOLqh.js +1 -0
  48. package/public/assets/inbox-DBFovbUX.js +1 -0
  49. package/public/assets/index-CHjV2-jB.js +9 -0
  50. package/public/assets/index-DMEtaP4u.css +1 -0
  51. package/public/assets/parser-worker-BMPPE37w.js +64 -0
  52. package/public/assets/plan-graph-vendor-B96a-e4N.js +7 -0
  53. package/public/assets/react-vendor-DA6opS-q.js +9 -0
  54. package/public/assets/select-D5fK-za0.js +1 -0
  55. package/public/assets/toggle-group-lbIXRG0W.js +1 -0
  56. package/public/assets/usePagedRows-CFoZrPr4.js +1 -0
  57. package/public/assets/useRecentFiles-BPGQ6XII.js +13 -0
  58. package/public/assets/useSortMode-BOPpfLhJ.js +1 -0
  59. package/public/docs/404.html +3 -3
  60. package/public/docs/assets/{app.Bxy4_HVA.js → app.BgzsaTS3.js} +1 -1
  61. package/public/docs/assets/aqe-loop.IwQSATHw.svg +1 -0
  62. package/public/docs/assets/aqe-loop.dark.DGbaxqJE.svg +1 -0
  63. package/public/docs/assets/broadcast-vs-shuffle.Db4WY1XK.svg +1 -0
  64. package/public/docs/assets/broadcast-vs-shuffle.dark.C7Bxs0mG.svg +1 -0
  65. package/public/docs/assets/cache-lifecycle.dark.B-hS7AgU.svg +1 -0
  66. package/public/docs/assets/cache-lifecycle.rEOVYQNU.svg +1 -0
  67. package/public/docs/assets/chunks/@localSearchIndexroot.PQ5JepCp.js +1 -0
  68. package/public/docs/assets/chunks/{VPLocalSearchBox.L5jNOIR3.js → VPLocalSearchBox.DOq3t-On.js} +1 -1
  69. package/public/docs/assets/chunks/duplicate-plan-subtree.dark.Cdp70QhV.js +1 -0
  70. package/public/docs/assets/chunks/{framework.CNDaxUod.js → framework.DSg0KOwT.js} +1 -1
  71. package/public/docs/assets/chunks/retry-escalation-ladder.dark.DHipdJgZ.js +1 -0
  72. package/public/docs/assets/chunks/theme.BP14rGBx.js +2 -0
  73. package/public/docs/assets/cold-start-timeline.DxC_Sc7w.svg +1 -0
  74. package/public/docs/assets/cold-start-timeline.dark.CZ17YcAG.svg +1 -0
  75. package/public/docs/assets/columnar-layout.PghGeOEA.svg +1 -0
  76. package/public/docs/assets/columnar-layout.dark.BVNlz0ff.svg +1 -0
  77. package/public/docs/assets/container-memory.DIO0AnIm.svg +1 -0
  78. package/public/docs/assets/container-memory.dark.CP-5zuCl.svg +1 -0
  79. package/public/docs/assets/contributor-guide_architecture_board-widgets.md.B-OsL91z.js +1 -0
  80. package/public/docs/assets/contributor-guide_architecture_board-widgets.md.B-OsL91z.lean.js +1 -0
  81. package/public/docs/assets/contributor-guide_architecture_detector-contract.md.BOeH4d1J.js +1 -0
  82. package/public/docs/assets/contributor-guide_architecture_detector-contract.md.BOeH4d1J.lean.js +1 -0
  83. package/public/docs/assets/contributor-guide_architecture_drill-down.md.BtPdlM7r.js +1 -0
  84. package/public/docs/assets/contributor-guide_architecture_drill-down.md.BtPdlM7r.lean.js +1 -0
  85. package/public/docs/assets/{contributor-guide_architecture_impact-estimation.md.CzlXOnCq.js → contributor-guide_architecture_impact-estimation.md.DYCDPgkh.js} +1 -1
  86. package/public/docs/assets/{contributor-guide_architecture_impact-estimation.md.CzlXOnCq.lean.js → contributor-guide_architecture_impact-estimation.md.DYCDPgkh.lean.js} +1 -1
  87. package/public/docs/assets/{contributor-guide_architecture_index.md.94lNbF-4.js → contributor-guide_architecture_index.md.3TO9ic6w.js} +1 -1
  88. package/public/docs/assets/{contributor-guide_architecture_index.md.94lNbF-4.lean.js → contributor-guide_architecture_index.md.3TO9ic6w.lean.js} +1 -1
  89. package/public/docs/assets/{contributor-guide_architecture_overview.md.mQFlN66o.js → contributor-guide_architecture_overview.md.CehiRmGn.js} +1 -1
  90. package/public/docs/assets/{contributor-guide_architecture_overview.md.mQFlN66o.lean.js → contributor-guide_architecture_overview.md.CehiRmGn.lean.js} +1 -1
  91. package/public/docs/assets/contributor-guide_architecture_state-and-history.md.m3S3UdMk.js +1 -0
  92. package/public/docs/assets/contributor-guide_architecture_state-and-history.md.m3S3UdMk.lean.js +1 -0
  93. package/public/docs/assets/contributor-guide_architecture_widget-rendering.md.DbqPf2OT.js +1 -0
  94. package/public/docs/assets/contributor-guide_architecture_widget-rendering.md.DbqPf2OT.lean.js +1 -0
  95. package/public/docs/assets/{contributor-guide_architecture_worker-protocol.md.BaS_L10g.js → contributor-guide_architecture_worker-protocol.md.B93qJ_tT.js} +2 -2
  96. package/public/docs/assets/{contributor-guide_architecture_worker-protocol.md.BaS_L10g.lean.js → contributor-guide_architecture_worker-protocol.md.B93qJ_tT.lean.js} +1 -1
  97. package/public/docs/assets/contributor-guide_contributing.md.CvRsdr6J.js +1 -0
  98. package/public/docs/assets/contributor-guide_contributing.md.CvRsdr6J.lean.js +1 -0
  99. package/public/docs/assets/{contributor-guide_development-setup.md.CpUMVtIK.js → contributor-guide_development-setup.md.DvAN_9mK.js} +1 -1
  100. package/public/docs/assets/{contributor-guide_development-setup.md.CpUMVtIK.lean.js → contributor-guide_development-setup.md.DvAN_9mK.lean.js} +1 -1
  101. package/public/docs/assets/{contributor-guide_testing.md.C0q-BJfl.js → contributor-guide_testing.md.6rIKqSyY.js} +1 -1
  102. package/public/docs/assets/{contributor-guide_testing.md.C0q-BJfl.lean.js → contributor-guide_testing.md.6rIKqSyY.lean.js} +1 -1
  103. package/public/docs/assets/dag-stages.DSz_S937.svg +1 -0
  104. package/public/docs/assets/dag-stages.dark.F72UzxH4.svg +1 -0
  105. package/public/docs/assets/driver-executor.D5pQ7YN1.svg +1 -0
  106. package/public/docs/assets/driver-executor.dark.BmX9cPvh.svg +1 -0
  107. package/public/docs/assets/duplicate-plan-subtree.B4cvN6fj.svg +1 -0
  108. package/public/docs/assets/duplicate-plan-subtree.dark.Dw8wS0Ag.svg +1 -0
  109. package/public/docs/assets/{index.md.CETnDZzR.js → index.md.CHJVslga.js} +1 -1
  110. package/public/docs/assets/{index.md.CETnDZzR.lean.js → index.md.CHJVslga.lean.js} +1 -1
  111. package/public/docs/assets/join-strategy.C_FvrCEo.svg +1 -0
  112. package/public/docs/assets/join-strategy.dark.ChMLnNII.svg +1 -0
  113. package/public/docs/assets/memory-borrowing.BqQRJg0u.svg +1 -0
  114. package/public/docs/assets/memory-borrowing.dark.Yhh20O9C.svg +1 -0
  115. package/public/docs/assets/memory-regions.XHvO7jHG.svg +1 -0
  116. package/public/docs/assets/memory-regions.dark.D4TP9_08.svg +1 -0
  117. package/public/docs/assets/repartition-vs-coalesce.BovLRrpj.svg +1 -0
  118. package/public/docs/assets/repartition-vs-coalesce.dark.BhAczKZQ.svg +1 -0
  119. package/public/docs/assets/retry-escalation-ladder.DyTKJJmZ.svg +1 -0
  120. package/public/docs/assets/retry-escalation-ladder.dark.BdsabtU3.svg +1 -0
  121. package/public/docs/assets/shuffle-map-reduce.KuOEZVmg.svg +1 -0
  122. package/public/docs/assets/shuffle-map-reduce.dark.BgQZnFSb.svg +1 -0
  123. package/public/docs/assets/spill-classification.BU2euYDO.svg +1 -0
  124. package/public/docs/assets/spill-classification.dark.D7i1M40d.svg +1 -0
  125. package/public/docs/assets/{style.D2mY0HUs.css → style.DXOMCXxn.css} +1 -1
  126. package/public/docs/assets/tuning-reference_anti-patterns.md.Df1YMIHu.js +1 -0
  127. package/public/docs/assets/tuning-reference_anti-patterns.md.Df1YMIHu.lean.js +1 -0
  128. package/public/docs/assets/tuning-reference_aqe.md.BIsCtLzm.js +1 -0
  129. package/public/docs/assets/tuning-reference_aqe.md.BIsCtLzm.lean.js +1 -0
  130. package/public/docs/assets/tuning-reference_bottleneck-broadcast-sizing.md.CEstB3Ia.js +1 -0
  131. package/public/docs/assets/tuning-reference_bottleneck-broadcast-sizing.md.CEstB3Ia.lean.js +1 -0
  132. package/public/docs/assets/tuning-reference_bottleneck-cold-start.md.CEuy-72y.js +7 -0
  133. package/public/docs/assets/tuning-reference_bottleneck-cold-start.md.CEuy-72y.lean.js +1 -0
  134. package/public/docs/assets/tuning-reference_bottleneck-duplicate-plan-subtree.md.CIohQDfn.js +1 -0
  135. package/public/docs/assets/tuning-reference_bottleneck-duplicate-plan-subtree.md.CIohQDfn.lean.js +1 -0
  136. package/public/docs/assets/tuning-reference_bottleneck-failures.md.4z5BXGJ2.js +6 -0
  137. package/public/docs/assets/tuning-reference_bottleneck-failures.md.4z5BXGJ2.lean.js +1 -0
  138. package/public/docs/assets/tuning-reference_bottleneck-gc.md.DSxzZRK7.js +6 -0
  139. package/public/docs/assets/tuning-reference_bottleneck-gc.md.DSxzZRK7.lean.js +1 -0
  140. package/public/docs/assets/tuning-reference_bottleneck-job-failure-rate.md.BaJl__1W.js +8 -0
  141. package/public/docs/assets/tuning-reference_bottleneck-job-failure-rate.md.BaJl__1W.lean.js +1 -0
  142. package/public/docs/assets/tuning-reference_bottleneck-memory-utilization.md.DbP-SJZc.js +7 -0
  143. package/public/docs/assets/tuning-reference_bottleneck-memory-utilization.md.DbP-SJZc.lean.js +1 -0
  144. package/public/docs/assets/tuning-reference_bottleneck-retry-waste.md.D5JMjVOt.js +1 -0
  145. package/public/docs/assets/tuning-reference_bottleneck-retry-waste.md.D5JMjVOt.lean.js +1 -0
  146. package/public/docs/assets/tuning-reference_bottleneck-shuffle.md.CM-nTmIH.js +12 -0
  147. package/public/docs/assets/tuning-reference_bottleneck-shuffle.md.CM-nTmIH.lean.js +1 -0
  148. package/public/docs/assets/tuning-reference_bottleneck-skew.md.BdUwiDhn.js +14 -0
  149. package/public/docs/assets/tuning-reference_bottleneck-skew.md.BdUwiDhn.lean.js +1 -0
  150. package/public/docs/assets/tuning-reference_bottleneck-slow-host.md.BlIo6UDW.js +7 -0
  151. package/public/docs/assets/tuning-reference_bottleneck-slow-host.md.BlIo6UDW.lean.js +1 -0
  152. package/public/docs/assets/tuning-reference_bottleneck-small-files.md.B8kloyx8.js +5 -0
  153. package/public/docs/assets/tuning-reference_bottleneck-small-files.md.B8kloyx8.lean.js +1 -0
  154. package/public/docs/assets/tuning-reference_bottleneck-spill.md.PNH7mITt.js +6 -0
  155. package/public/docs/assets/tuning-reference_bottleneck-spill.md.PNH7mITt.lean.js +1 -0
  156. package/public/docs/assets/tuning-reference_bottleneck-straggler.md.DY36fHN5.js +7 -0
  157. package/public/docs/assets/tuning-reference_bottleneck-straggler.md.DY36fHN5.lean.js +1 -0
  158. package/public/docs/assets/tuning-reference_bottleneck-tiny-tasks.md.QTV7O8kU.js +8 -0
  159. package/public/docs/assets/tuning-reference_bottleneck-tiny-tasks.md.QTV7O8kU.lean.js +1 -0
  160. package/public/docs/assets/tuning-reference_bottleneck-utilization.md.DTiueZC3.js +5 -0
  161. package/public/docs/assets/tuning-reference_bottleneck-utilization.md.DTiueZC3.lean.js +1 -0
  162. package/public/docs/assets/tuning-reference_caching.md.B7aQ8asB.js +1 -0
  163. package/public/docs/assets/tuning-reference_caching.md.B7aQ8asB.lean.js +1 -0
  164. package/public/docs/assets/tuning-reference_cluster-config.md.ZVmDGsQ3.js +1 -0
  165. package/public/docs/assets/tuning-reference_cluster-config.md.ZVmDGsQ3.lean.js +1 -0
  166. package/public/docs/assets/tuning-reference_config.md.UvveiWG3.js +1 -0
  167. package/public/docs/assets/tuning-reference_config.md.UvveiWG3.lean.js +1 -0
  168. package/public/docs/assets/tuning-reference_data-formats.md.bjCAWH3N.js +1 -0
  169. package/public/docs/assets/tuning-reference_data-formats.md.bjCAWH3N.lean.js +1 -0
  170. package/public/docs/assets/tuning-reference_index.md.BQ_NooMV.js +1 -0
  171. package/public/docs/assets/tuning-reference_index.md.BQ_NooMV.lean.js +1 -0
  172. package/public/docs/assets/tuning-reference_intro.md.CobD-lGB.js +1 -0
  173. package/public/docs/assets/tuning-reference_intro.md.CobD-lGB.lean.js +1 -0
  174. package/public/docs/assets/tuning-reference_joins.md.BtKs_CuW.js +1 -0
  175. package/public/docs/assets/tuning-reference_joins.md.BtKs_CuW.lean.js +1 -0
  176. package/public/docs/assets/tuning-reference_memory-model.md.DhT-n4y3.js +1 -0
  177. package/public/docs/assets/tuning-reference_memory-model.md.DhT-n4y3.lean.js +1 -0
  178. package/public/docs/assets/tuning-reference_metrics.md.mLOh7Apj.js +1 -0
  179. package/public/docs/assets/tuning-reference_metrics.md.mLOh7Apj.lean.js +1 -0
  180. package/public/docs/assets/tuning-reference_partitioning.md.q0zKF_8X.js +1 -0
  181. package/public/docs/assets/tuning-reference_partitioning.md.q0zKF_8X.lean.js +1 -0
  182. package/public/docs/assets/tuning-reference_pyspark.md.DDCfvN9t.js +6 -0
  183. package/public/docs/assets/tuning-reference_pyspark.md.DDCfvN9t.lean.js +1 -0
  184. package/public/docs/assets/tuning-reference_shuffle.md.BZZ7R4Ix.js +1 -0
  185. package/public/docs/assets/tuning-reference_shuffle.md.BZZ7R4Ix.lean.js +1 -0
  186. package/public/docs/assets/tuning-reference_spark-architecture.md.Dwzm5avO.js +1 -0
  187. package/public/docs/assets/tuning-reference_spark-architecture.md.Dwzm5avO.lean.js +1 -0
  188. package/public/docs/assets/tuning-reference_table-formats.md.D6wj-2dX.js +1 -0
  189. package/public/docs/assets/tuning-reference_table-formats.md.D6wj-2dX.lean.js +1 -0
  190. package/public/docs/assets/udf-execution-models.BUFDICuG.svg +1 -0
  191. package/public/docs/assets/udf-execution-models.dark.YTNS6GDq.svg +1 -0
  192. package/public/docs/assets/user-guide_alternative-log-retrieval.md.sU3KGarf.js +1 -0
  193. package/public/docs/assets/user-guide_alternative-log-retrieval.md.sU3KGarf.lean.js +1 -0
  194. package/public/docs/assets/user-guide_getting-started.md.DtEM37MK.js +3 -0
  195. package/public/docs/assets/user-guide_getting-started.md.DtEM37MK.lean.js +1 -0
  196. package/public/docs/assets/{user-guide_mcp-tools.md.DwYI1d6C.js → user-guide_mcp-tools.md.C8MiIu7F.js} +35 -5
  197. package/public/docs/assets/{user-guide_mcp-tools.md.DwYI1d6C.lean.js → user-guide_mcp-tools.md.C8MiIu7F.lean.js} +1 -1
  198. package/public/docs/assets/{user-guide_run-comparison.md.5-oaOfTu.js → user-guide_run-comparison.md.S0TWWmLY.js} +1 -1
  199. package/public/docs/assets/{user-guide_run-comparison.md.5-oaOfTu.lean.js → user-guide_run-comparison.md.S0TWWmLY.lean.js} +1 -1
  200. package/public/docs/assets/user-guide_understanding-findings.md.D0R_Y-R2.js +1 -0
  201. package/public/docs/assets/{user-guide_understanding-findings.md.CK2WZ0Tf.lean.js → user-guide_understanding-findings.md.D0R_Y-R2.lean.js} +1 -1
  202. package/public/docs/contributor-guide/architecture/board-widgets.html +7 -7
  203. package/public/docs/contributor-guide/architecture/detector-contract.html +7 -7
  204. package/public/docs/contributor-guide/architecture/drill-down.html +7 -7
  205. package/public/docs/contributor-guide/architecture/impact-estimation.html +7 -7
  206. package/public/docs/contributor-guide/architecture/index.html +7 -7
  207. package/public/docs/contributor-guide/architecture/overview.html +7 -7
  208. package/public/docs/contributor-guide/architecture/state-and-history.html +7 -7
  209. package/public/docs/contributor-guide/architecture/widget-rendering.html +7 -7
  210. package/public/docs/contributor-guide/architecture/worker-protocol.html +8 -8
  211. package/public/docs/contributor-guide/contributing.html +7 -7
  212. package/public/docs/contributor-guide/development-setup.html +7 -7
  213. package/public/docs/contributor-guide/testing.html +7 -7
  214. package/public/docs/hashmap.json +1 -1
  215. package/public/docs/index.html +7 -7
  216. package/public/docs/tuning-reference/anti-patterns.html +29 -0
  217. package/public/docs/tuning-reference/aqe.html +29 -0
  218. package/public/docs/tuning-reference/bottleneck-broadcast-sizing.html +29 -0
  219. package/public/docs/tuning-reference/bottleneck-cold-start.html +35 -0
  220. package/public/docs/tuning-reference/bottleneck-duplicate-plan-subtree.html +30 -0
  221. package/public/docs/tuning-reference/bottleneck-failures.html +35 -0
  222. package/public/docs/tuning-reference/bottleneck-gc.html +34 -0
  223. package/public/docs/tuning-reference/bottleneck-job-failure-rate.html +37 -0
  224. package/public/docs/tuning-reference/bottleneck-memory-utilization.html +35 -0
  225. package/public/docs/tuning-reference/bottleneck-retry-waste.html +30 -0
  226. package/public/docs/tuning-reference/bottleneck-shuffle.html +40 -0
  227. package/public/docs/tuning-reference/bottleneck-skew.html +42 -0
  228. package/public/docs/tuning-reference/bottleneck-slow-host.html +35 -0
  229. package/public/docs/tuning-reference/bottleneck-small-files.html +33 -0
  230. package/public/docs/tuning-reference/bottleneck-spill.html +34 -0
  231. package/public/docs/tuning-reference/bottleneck-straggler.html +35 -0
  232. package/public/docs/tuning-reference/bottleneck-tiny-tasks.html +36 -0
  233. package/public/docs/tuning-reference/bottleneck-utilization.html +34 -0
  234. package/public/docs/tuning-reference/caching.html +29 -0
  235. package/public/docs/tuning-reference/cluster-config.html +29 -0
  236. package/public/docs/tuning-reference/config.html +29 -0
  237. package/public/docs/tuning-reference/data-formats.html +29 -0
  238. package/public/docs/tuning-reference/index.html +29 -0
  239. package/public/docs/tuning-reference/intro.html +29 -0
  240. package/public/docs/tuning-reference/joins.html +29 -0
  241. package/public/docs/tuning-reference/memory-model.html +29 -0
  242. package/public/docs/tuning-reference/metrics.html +29 -0
  243. package/public/docs/tuning-reference/partitioning.html +29 -0
  244. package/public/docs/tuning-reference/pyspark.html +34 -0
  245. package/public/docs/tuning-reference/shuffle.html +29 -0
  246. package/public/docs/tuning-reference/spark-architecture.html +29 -0
  247. package/public/docs/tuning-reference/table-formats.html +29 -0
  248. package/public/docs/user-guide/alternative-log-retrieval.html +29 -0
  249. package/public/docs/user-guide/getting-started.html +8 -8
  250. package/public/docs/user-guide/mcp-tools.html +41 -11
  251. package/public/docs/user-guide/run-comparison.html +7 -7
  252. package/public/docs/user-guide/understanding-findings.html +7 -7
  253. package/public/index.html +6 -6
  254. package/vendor-core/analyzer.js +74 -74
  255. package/vendor-core/cli/budgets.js +13 -27
  256. package/vendor-core/cli/collect-run.js +43 -19
  257. package/vendor-core/core-count.js +25 -27
  258. package/vendor-core/core-locality-ratio.js +4 -11
  259. package/vendor-core/core-time-series.js +6 -12
  260. package/vendor-core/core-usage-locality.js +3 -4
  261. package/vendor-core/detectors.js +256 -375
  262. package/vendor-core/docs-config.js +69 -21
  263. package/vendor-core/docs-content/chapters/01-intro.md +32 -0
  264. package/vendor-core/docs-content/chapters/02-spark-architecture.md +76 -0
  265. package/vendor-core/docs-content/chapters/03-memory-model.md +73 -0
  266. package/vendor-core/docs-content/chapters/04-partitioning.md +65 -0
  267. package/vendor-core/docs-content/chapters/05-joins.md +62 -0
  268. package/vendor-core/docs-content/chapters/06-shuffle.md +59 -0
  269. package/vendor-core/docs-content/chapters/07-data-formats.md +81 -0
  270. package/vendor-core/docs-content/chapters/07b-table-formats.md +56 -0
  271. package/vendor-core/docs-content/chapters/08-caching.md +58 -0
  272. package/vendor-core/docs-content/chapters/09-pyspark.md +78 -0
  273. package/vendor-core/docs-content/chapters/10-aqe.md +167 -0
  274. package/vendor-core/docs-content/chapters/11-cluster-config.md +170 -0
  275. package/vendor-core/docs-content/chapters/12-anti-patterns.md +171 -0
  276. package/vendor-core/docs-content/chapters/14-metrics.md +87 -0
  277. package/vendor-core/docs-content/chapters/15-config.md +93 -0
  278. package/vendor-core/docs-content/chapters/nav-index.json +370 -0
  279. package/vendor-core/docs-content/detection/cache.md +6 -0
  280. package/vendor-core/docs-content/detection/cfg.md +15 -0
  281. package/vendor-core/docs-content/detection/chrn.md +7 -0
  282. package/vendor-core/docs-content/detection/cold.md +4 -0
  283. package/vendor-core/docs-content/detection/cstor.md +4 -0
  284. package/vendor-core/docs-content/detection/fail.md +5 -0
  285. package/vendor-core/docs-content/detection/gc.md +4 -0
  286. package/vendor-core/docs-content/detection/host.md +5 -0
  287. package/vendor-core/docs-content/detection/incmp.md +6 -0
  288. package/vendor-core/docs-content/detection/jobs.md +4 -0
  289. package/vendor-core/docs-content/detection/local.md +7 -0
  290. package/vendor-core/docs-content/detection/mem.md +10 -0
  291. package/vendor-core/docs-content/detection/part.md +5 -0
  292. package/vendor-core/docs-content/detection/plan.md +14 -0
  293. package/vendor-core/docs-content/detection/retry.md +4 -0
  294. package/vendor-core/docs-content/detection/sfail.md +5 -0
  295. package/vendor-core/docs-content/detection/shape.md +5 -0
  296. package/vendor-core/docs-content/detection/shfl.md +4 -0
  297. package/vendor-core/docs-content/detection/skew.md +6 -0
  298. package/vendor-core/docs-content/detection/slow.md +6 -0
  299. package/vendor-core/docs-content/detection/spec.md +7 -0
  300. package/vendor-core/docs-content/detection/spill.md +7 -0
  301. package/vendor-core/docs-content/detection/strag.md +5 -0
  302. package/vendor-core/docs-content/detection/tiny.md +4 -0
  303. package/vendor-core/docs-content/detection/util.md +4 -0
  304. package/vendor-core/docs-content/diagrams/aqe-loop.dark.svg +1 -0
  305. package/vendor-core/docs-content/diagrams/aqe-loop.svg +1 -0
  306. package/vendor-core/docs-content/diagrams/broadcast-vs-shuffle.dark.svg +1 -0
  307. package/vendor-core/docs-content/diagrams/broadcast-vs-shuffle.svg +1 -0
  308. package/vendor-core/docs-content/diagrams/cache-lifecycle.dark.svg +1 -0
  309. package/vendor-core/docs-content/diagrams/cache-lifecycle.svg +1 -0
  310. package/vendor-core/docs-content/diagrams/cold-start-timeline.dark.svg +1 -0
  311. package/vendor-core/docs-content/diagrams/cold-start-timeline.svg +1 -0
  312. package/vendor-core/docs-content/diagrams/columnar-layout.dark.svg +1 -0
  313. package/vendor-core/docs-content/diagrams/columnar-layout.svg +1 -0
  314. package/vendor-core/docs-content/diagrams/container-memory.dark.svg +1 -0
  315. package/vendor-core/docs-content/diagrams/container-memory.svg +1 -0
  316. package/vendor-core/docs-content/diagrams/dag-stages.dark.svg +1 -0
  317. package/vendor-core/docs-content/diagrams/dag-stages.svg +1 -0
  318. package/vendor-core/docs-content/diagrams/driver-executor.dark.svg +1 -0
  319. package/vendor-core/docs-content/diagrams/driver-executor.svg +1 -0
  320. package/vendor-core/docs-content/diagrams/duplicate-plan-subtree.dark.svg +1 -0
  321. package/vendor-core/docs-content/diagrams/duplicate-plan-subtree.svg +1 -0
  322. package/vendor-core/docs-content/diagrams/join-strategy.dark.svg +1 -0
  323. package/vendor-core/docs-content/diagrams/join-strategy.svg +1 -0
  324. package/vendor-core/docs-content/diagrams/memory-borrowing.dark.svg +1 -0
  325. package/vendor-core/docs-content/diagrams/memory-borrowing.svg +1 -0
  326. package/vendor-core/docs-content/diagrams/memory-regions.dark.svg +1 -0
  327. package/vendor-core/docs-content/diagrams/memory-regions.svg +1 -0
  328. package/vendor-core/docs-content/diagrams/repartition-vs-coalesce.dark.svg +1 -0
  329. package/vendor-core/docs-content/diagrams/repartition-vs-coalesce.svg +1 -0
  330. package/vendor-core/docs-content/diagrams/retry-escalation-ladder.dark.svg +1 -0
  331. package/vendor-core/docs-content/diagrams/retry-escalation-ladder.svg +1 -0
  332. package/vendor-core/docs-content/diagrams/shuffle-map-reduce.dark.svg +1 -0
  333. package/vendor-core/docs-content/diagrams/shuffle-map-reduce.svg +1 -0
  334. package/vendor-core/docs-content/diagrams/spill-classification.dark.svg +1 -0
  335. package/vendor-core/docs-content/diagrams/spill-classification.svg +1 -0
  336. package/vendor-core/docs-content/diagrams/udf-execution-models.dark.svg +1 -0
  337. package/vendor-core/docs-content/diagrams/udf-execution-models.svg +1 -0
  338. package/vendor-core/docs-content/tuning/broadcast-sizing.md +78 -0
  339. package/vendor-core/docs-content/tuning/cold-start.md +81 -0
  340. package/vendor-core/docs-content/tuning/duplicate-plan-subtree.md +45 -0
  341. package/vendor-core/docs-content/tuning/failures.md +124 -0
  342. package/vendor-core/docs-content/tuning/gc.md +110 -0
  343. package/vendor-core/docs-content/tuning/job-failure-rate.md +101 -0
  344. package/vendor-core/docs-content/tuning/memory-utilization.md +58 -0
  345. package/vendor-core/docs-content/tuning/retry-waste.md +90 -0
  346. package/vendor-core/docs-content/tuning/shuffle.md +154 -0
  347. package/vendor-core/docs-content/tuning/skew.md +123 -0
  348. package/vendor-core/docs-content/tuning/slow-host.md +117 -0
  349. package/vendor-core/docs-content/tuning/small-files.md +99 -0
  350. package/vendor-core/docs-content/tuning/spill.md +114 -0
  351. package/vendor-core/docs-content/tuning/straggler.md +103 -0
  352. package/vendor-core/docs-content/tuning/tiny-tasks.md +94 -0
  353. package/vendor-core/docs-content/tuning/utilization.md +90 -0
  354. package/vendor-core/docs-site-config.js +10 -17
  355. package/vendor-core/efficiency-model.js +7 -13
  356. package/vendor-core/etl-phases.js +3 -5
  357. package/vendor-core/event-handlers.js +232 -134
  358. package/vendor-core/event-schemas.js +48 -114
  359. package/vendor-core/evidence-availability.js +5 -10
  360. package/vendor-core/evidence-report.js +72 -122
  361. package/vendor-core/export-data.js +48 -0
  362. package/vendor-core/finding-action-label.js +4 -10
  363. package/vendor-core/finding-filter-predicate.js +3 -7
  364. package/vendor-core/finding-generic-recommendation.js +112 -0
  365. package/vendor-core/finding-names.js +51 -0
  366. package/vendor-core/format-utils.js +112 -38
  367. package/vendor-core/impact-band.js +18 -24
  368. package/vendor-core/impact-estimator.js +38 -74
  369. package/vendor-core/ingest.js +7 -13
  370. package/vendor-core/job-groups.js +3 -6
  371. package/vendor-core/list-runs.js +278 -0
  372. package/vendor-core/load-vendored.js +6 -12
  373. package/vendor-core/log-header-peek.js +81 -0
  374. package/vendor-core/lz4-block.js +4 -6
  375. package/vendor-core/mcp-server-factory.js +38 -8
  376. package/vendor-core/mcp-tools.js +105 -76
  377. package/vendor-core/model-assembler.js +8 -16
  378. package/vendor-core/occupancy.js +5 -9
  379. package/vendor-core/parser-worker.js +18 -27
  380. package/vendor-core/plan-dot.js +2 -5
  381. package/vendor-core/plan-duration-attribution.js +78 -29
  382. package/vendor-core/plan-graph-model.js +126 -69
  383. package/vendor-core/plan-node-detail.js +31 -17
  384. package/vendor-core/plan-summary.js +19 -8
  385. package/vendor-core/recommendation-rollup.js +35 -39
  386. package/vendor-core/redact.js +72 -16
  387. package/vendor-core/rolling-log-reassembly.js +4 -6
  388. package/vendor-core/run-comparison.js +65 -70
  389. package/vendor-core/scaling-sim.js +5 -7
  390. package/vendor-core/session-snapshot.js +1 -1
  391. package/vendor-core/shs-fetch.js +4 -6
  392. package/vendor-core/shs-load.js +9 -13
  393. package/vendor-core/shs-request.js +1 -1
  394. package/vendor-core/stage-quantiles.js +14 -0
  395. package/vendor-core/types.js +78 -18
  396. package/vendor-core/wasted-core-hours.js +7 -12
  397. package/public/assets/AutoscalingChurn-CP5OjN6v.js +0 -1
  398. package/public/assets/CacheUtilization-BjyawXL6.js +0 -1
  399. package/public/assets/CachingOpportunity-DV2ABG2G.js +0 -1
  400. package/public/assets/ConfigAudit-DMiBhAoG.js +0 -1
  401. package/public/assets/CoreUsageArea-CGYIgPnt.js +0 -1
  402. package/public/assets/Dashboard-D1_IrWRs.js +0 -12
  403. package/public/assets/ExecutorTimeline-DkaAGqQT.js +0 -1
  404. package/public/assets/Failures-Crngoicu.js +0 -1
  405. package/public/assets/GcPressure-CFXm4BnA.js +0 -1
  406. package/public/assets/IncompleteRun-BWEJTb13.js +0 -1
  407. package/public/assets/JobFailures-BmjxCA-h.js +0 -1
  408. package/public/assets/MemoryUtilization-Bu2uQJbd.js +0 -1
  409. package/public/assets/PlanExplorer-DKUwF0uz.js +0 -1
  410. package/public/assets/PlanGraphRoute-BjPSugIG.js +0 -1
  411. package/public/assets/ShuffleIO--Rur3neu.js +0 -1
  412. package/public/assets/Spill-DIMpt8c2.js +0 -1
  413. package/public/assets/TaskSkew-BDr1DbeI.js +0 -1
  414. package/public/assets/index-4id52G-A.js +0 -9
  415. package/public/assets/index-D9kwVYIO.css +0 -1
  416. package/public/assets/parser-worker-00O9WEQC.js +0 -65
  417. package/public/assets/plan-graph-vendor-vZQHG2EJ.js +0 -7
  418. package/public/assets/react-vendor-u4pyvC5Y.js +0 -9
  419. package/public/assets/useRecentFiles-46iBU9zJ.js +0 -5
  420. package/public/docs/assets/chunks/@localSearchIndexroot.DclgKtlT.js +0 -1
  421. package/public/docs/assets/chunks/theme.CoT6y5bf.js +0 -2
  422. package/public/docs/assets/contributor-guide_architecture_board-widgets.md.BtjoE_1k.js +0 -1
  423. package/public/docs/assets/contributor-guide_architecture_board-widgets.md.BtjoE_1k.lean.js +0 -1
  424. package/public/docs/assets/contributor-guide_architecture_detector-contract.md.DQyCHQNM.js +0 -1
  425. package/public/docs/assets/contributor-guide_architecture_detector-contract.md.DQyCHQNM.lean.js +0 -1
  426. package/public/docs/assets/contributor-guide_architecture_drill-down.md.BKfyDQck.js +0 -1
  427. package/public/docs/assets/contributor-guide_architecture_drill-down.md.BKfyDQck.lean.js +0 -1
  428. package/public/docs/assets/contributor-guide_architecture_state-and-history.md.DaqttKgQ.js +0 -1
  429. package/public/docs/assets/contributor-guide_architecture_state-and-history.md.DaqttKgQ.lean.js +0 -1
  430. package/public/docs/assets/contributor-guide_architecture_widget-rendering.md.Bk6Iyj9S.js +0 -1
  431. package/public/docs/assets/contributor-guide_architecture_widget-rendering.md.Bk6Iyj9S.lean.js +0 -1
  432. package/public/docs/assets/contributor-guide_contributing.md.C-lKs70I.js +0 -1
  433. package/public/docs/assets/contributor-guide_contributing.md.C-lKs70I.lean.js +0 -1
  434. package/public/docs/assets/user-guide_getting-started.md.BJdD7a7_.js +0 -3
  435. package/public/docs/assets/user-guide_getting-started.md.BJdD7a7_.lean.js +0 -1
  436. package/public/docs/assets/user-guide_understanding-findings.md.CK2WZ0Tf.js +0 -1
  437. package/public/vendor/spark-doc/anchors.json +0 -205
  438. package/public/vendor/spark-doc/index.html +0 -4202
  439. package/public/vendor/spark-doc/landing.html +0 -418
  440. package/public/vendor/spark-doc/meta.html +0 -970
package/public/docs/tuning-reference/bottleneck-slow-host.html ADDED
@@ -0,0 +1,35 @@
1
+ <!DOCTYPE html>
2
+ <html lang="en-US" dir="ltr">
3
+ <head>
4
+ <meta charset="utf-8">
5
+ <meta name="viewport" content="width=device-width,initial-scale=1">
6
+ <title>Slow Host | SparkForensics</title>
7
+ <meta name="description" content="Docs for using and contributing to SparkForensics">
8
+ <meta name="generator" content="VitePress v1.6.4">
9
+ <link rel="preload stylesheet" href="/docs/assets/style.DXOMCXxn.css" as="style">
10
+ <link rel="preload stylesheet" href="/docs/vp-icons.css" as="style">
11
+
12
+ <script type="module" src="/docs/assets/app.BgzsaTS3.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.BP14rGBx.js">
15
+ <link rel="modulepreload" href="/docs/assets/chunks/framework.DSg0KOwT.js">
16
+ <link rel="modulepreload" href="/docs/assets/tuning-reference_bottleneck-slow-host.md.BlIo6UDW.lean.js">
17
+ <link rel="icon" type="image/svg+xml" href="/docs/favicon.svg">
18
+ <link rel="preconnect" href="https://fonts.googleapis.com">
19
+ <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin="">
20
+ <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">
21
+ <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>
22
+ <script id="check-mac-os">document.documentElement.classList.toggle("mac",/Mac|iPhone|iPod|iPad/i.test(navigator.platform));</script>
23
+ </head>
24
+ <body>
25
+ <div id="app"><div class="Layout" data-v-5d98c3a5><!--[--><!--]--><!--[--><span tabindex="-1" data-v-0b0ada53></span><a href="#VPContent" class="VPSkipLink visually-hidden" data-v-0b0ada53>Skip to content</a><!--]--><!----><header class="VPNav" data-v-5d98c3a5 data-v-ae24b3ad><div class="VPNavBar" data-v-ae24b3ad data-v-6aa21345><div class="wrapper" data-v-6aa21345><div class="container" data-v-6aa21345><div class="title" data-v-6aa21345><div class="VPNavBarTitle has-sidebar" data-v-6aa21345 data-v-1168a8e4><a class="title" href="/docs/" data-v-1168a8e4><!--[--><!--]--><!--[--><img class="VPImage logo" src="/docs/favicon.svg" alt data-v-8426fc1a><!--]--><span data-v-1168a8e4>SparkForensics</span><!--[--><!--]--></a></div></div><div class="content" data-v-6aa21345><div class="content-body" data-v-6aa21345><!--[--><!--]--><div class="VPNavBarSearch search" data-v-6aa21345><!--[--><!----><div id="local-search"><button type="button" class="DocSearch DocSearch-Button" aria-label="Search"><span class="DocSearch-Button-Container"><span class="vp-icon DocSearch-Search-Icon"></span><span class="DocSearch-Button-Placeholder">Search</span></span><span class="DocSearch-Button-Keys"><kbd class="DocSearch-Button-Key"></kbd><kbd class="DocSearch-Button-Key">K</kbd></span></button></div><!--]--></div><nav aria-labelledby="main-nav-aria-label" class="VPNavBarMenu menu" data-v-6aa21345 data-v-dc692963><span id="main-nav-aria-label" class="visually-hidden" data-v-dc692963> Main Navigation </span><!--[--><!--[--><a class="VPLink link VPNavBarMenuLink" href="/docs/user-guide/getting-started.html" tabindex="0" data-v-dc692963 data-v-e56f3d57><!--[--><span data-v-e56f3d57>User Guide</span><!--]--></a><!--]--><!--[--><a class="VPLink link VPNavBarMenuLink" href="/docs/contributor-guide/development-setup.html" tabindex="0" data-v-dc692963 data-v-e56f3d57><!--[--><span data-v-e56f3d57>Contributor Guide</span><!--]--></a><!--]--><!--[--><a class="VPLink link VPNavBarMenuLink" href="/docs/tuning-reference/" tabindex="0" data-v-dc692963 data-v-e56f3d57><!--[--><span data-v-e56f3d57>Tuning Reference</span><!--]--></a><!--]--><!--]--></nav><!----><div class="VPNavBarAppearance appearance" data-v-6aa21345 data-v-6c893767><button class="VPSwitch VPSwitchAppearance" type="button" role="switch" title aria-checked="false" data-v-6c893767 data-v-5337faa4 data-v-1d5665e3><span class="check" data-v-1d5665e3><span class="icon" data-v-1d5665e3><!--[--><span class="vpi-sun sun" data-v-5337faa4></span><span class="vpi-moon moon" data-v-5337faa4></span><!--]--></span></span></button></div><!----><div class="VPFlyout VPNavBarExtra extra" data-v-6aa21345 data-v-bb2aa2f0 data-v-cf11d7a2><button type="button" class="button" aria-haspopup="true" aria-expanded="false" aria-label="extra navigation" data-v-cf11d7a2><span class="vpi-more-horizontal icon" data-v-cf11d7a2></span></button><div class="menu" data-v-cf11d7a2><div class="VPMenu" data-v-cf11d7a2 data-v-b98bc113><!----><!--[--><!--[--><!----><div class="group" data-v-bb2aa2f0><div class="item appearance" data-v-bb2aa2f0><p class="label" data-v-bb2aa2f0>Appearance</p><div class="appearance-action" data-v-bb2aa2f0><button class="VPSwitch VPSwitchAppearance" type="button" role="switch" title aria-checked="false" data-v-bb2aa2f0 data-v-5337faa4 data-v-1d5665e3><span class="check" data-v-1d5665e3><span class="icon" data-v-1d5665e3><!--[--><span class="vpi-sun sun" data-v-5337faa4></span><span class="vpi-moon moon" data-v-5337faa4></span><!--]--></span></span></button></div></div></div><!----><!--]--><!--]--></div></div></div><!--[--><!--]--><button type="button" class="VPNavBarHamburger hamburger" aria-label="mobile navigation" aria-expanded="false" aria-controls="VPNavScreen" data-v-6aa21345 data-v-e5dd9c1c><span class="container" data-v-e5dd9c1c><span class="top" data-v-e5dd9c1c></span><span class="middle" data-v-e5dd9c1c></span><span class="bottom" data-v-e5dd9c1c></span></span></button></div></div></div></div><div class="divider" data-v-6aa21345><div class="divider-line" data-v-6aa21345></div></div></div><!----></header><div class="VPLocalNav has-sidebar empty" data-v-5d98c3a5 data-v-a6f0e41e><div class="container" data-v-a6f0e41e><button class="menu" aria-expanded="false" aria-controls="VPSidebarNav" data-v-a6f0e41e><span class="vpi-align-left menu-icon" data-v-a6f0e41e></span><span class="menu-text" data-v-a6f0e41e>Menu</span></button><div class="VPLocalNavOutlineDropdown" style="--vp-vh:0px;" data-v-a6f0e41e data-v-8a42e2b4><button data-v-8a42e2b4>Return to top</button><!----></div></div></div><aside class="VPSidebar" data-v-5d98c3a5 data-v-319d5ca6><div class="curtain" data-v-319d5ca6></div><nav class="nav" id="VPSidebarNav" aria-labelledby="sidebar-aria-label" tabindex="-1" data-v-319d5ca6><span class="visually-hidden" id="sidebar-aria-label" data-v-319d5ca6> Sidebar Navigation </span><!--[--><!--]--><!--[--><div class="no-transition group" data-v-c40bc020><section class="VPSidebarItem level-0" data-v-c40bc020 data-v-b3fd67f8><div class="item" role="button" tabindex="0" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><h2 class="text" data-v-b3fd67f8>Getting Started</h2><!----></div><div class="items" data-v-b3fd67f8><!--[--><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/intro.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Introduction</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><div class="no-transition group" data-v-c40bc020><section class="VPSidebarItem level-0" data-v-c40bc020 data-v-b3fd67f8><div class="item" role="button" tabindex="0" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><h2 class="text" data-v-b3fd67f8>Optimization Guide</h2><!----></div><div class="items" data-v-b3fd67f8><!--[--><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/spark-architecture.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Spark Execution Model</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/memory-model.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Memory Management</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/partitioning.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Partitioning</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/joins.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Join Optimization</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/shuffle.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Shuffle</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/data-formats.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Data Formats</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/table-formats.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Table Formats</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/caching.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Caching & Persistence</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/pyspark.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>PySpark Specifics</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/aqe.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Adaptive Query Execution</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/cluster-config.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Cluster Tuning</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/anti-patterns.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Anti-Patterns</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><div class="no-transition group" data-v-c40bc020><section class="VPSidebarItem level-0 has-active" data-v-c40bc020 data-v-b3fd67f8><div class="item" role="button" tabindex="0" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><h2 class="text" data-v-b3fd67f8>Detector Catalog</h2><!----></div><div class="items" data-v-b3fd67f8><!--[--><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-skew.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Task Skew</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-shuffle.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Shuffle I/O</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-spill.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Memory / Disk Spill</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-gc.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>GC Pressure</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-cold-start.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Cold Start</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-utilization.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Executor Utilization</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-slow-host.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Slow Host</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-failures.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Task Failures</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-straggler.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Stragglers</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-retry-waste.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Retry Waste</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-tiny-tasks.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Tiny Tasks</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-job-failure-rate.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Job Failure Rate</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-memory-utilization.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Memory Utilization</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-duplicate-plan-subtree.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Duplicate Plan Subtree</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-small-files.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Small Files</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-broadcast-sizing.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Broadcast Sizing</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><div class="no-transition group" data-v-c40bc020><section class="VPSidebarItem level-0" data-v-c40bc020 data-v-b3fd67f8><div class="item" role="button" tabindex="0" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><h2 class="text" data-v-b3fd67f8>Reference</h2><!----></div><div class="items" data-v-b3fd67f8><!--[--><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/metrics.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Metrics Glossary</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/config.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Spark Config Quick-Reference</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><!--]--><!--[--><!--]--></nav></aside><div class="VPContent has-sidebar" id="VPContent" data-v-5d98c3a5 data-v-1428d186><div class="VPDoc has-sidebar has-aside" data-v-1428d186 data-v-39a288b8><!--[--><!--]--><div class="container" data-v-39a288b8><div class="aside" data-v-39a288b8><div class="aside-curtain" data-v-39a288b8></div><div class="aside-container" data-v-39a288b8><div class="aside-content" data-v-39a288b8><div class="VPDocAside" data-v-39a288b8 data-v-3f215769><!--[--><!--]--><!--[--><!--]--><nav aria-labelledby="doc-outline-aria-label" class="VPDocAsideOutline" data-v-3f215769 data-v-a5bbad30><div class="content" data-v-a5bbad30><div class="outline-marker" data-v-a5bbad30></div><div aria-level="2" class="outline-title" id="doc-outline-aria-label" role="heading" data-v-a5bbad30>On this page</div><ul class="VPDocOutlineItem root" data-v-a5bbad30 data-v-b933a997><!--[--><!--]--></ul></div></nav><!--[--><!--]--><div class="spacer" data-v-3f215769></div><!--[--><!--]--><!----><!--[--><!--]--><!--[--><!--]--></div></div></div></div><div class="content" data-v-39a288b8><div class="content-container" data-v-39a288b8><!--[--><!--]--><main class="main" data-v-39a288b8><div style="position:relative;" class="vp-doc _docs_tuning-reference_bottleneck-slow-host" data-v-39a288b8><div><h1 id="bottleneck-slow-host" tabindex="-1">Slow Host <a class="header-anchor" href="#bottleneck-slow-host" aria-label="Permalink to &quot;Slow Host {#bottleneck-slow-host}&quot;">​</a></h1><p><span class="tag">HOST</span></p><h2 id="what-it-is" tabindex="-1">What it is <a class="header-anchor" href="#what-it-is" aria-label="Permalink to &quot;What it is&quot;">​</a></h2><p>A slow host bottleneck shows up when one machine in the cluster consistently turns in slower task times than its peers, independent of any single task&#39;s own data size. Unlike a stray <a href="./bottleneck-straggler.html">straggler task</a>, the effect is host-wide: every task Spark schedules there runs behind, which drags out the stage even when the workload itself is partitioned evenly.</p><h2 id="how-it-s-detected" tabindex="-1">How it&#39;s detected <a class="header-anchor" href="#how-it-s-detected" aria-label="Permalink to &quot;How it&#39;s detected&quot;">​</a></h2><p>Spark&#39;s event log carries the per-task detail behind this: turning on <code>spark.eventLog.enabled</code> logs the events that encode what the UI displays, persisted to storage<sup class="footnote-ref"><a href="#fn1" id="fnref1">[1]</a></sup>, and that same log backs the UI&#39;s Stages tab, which drills down into individual tasks and shows per-task metrics such as duration, GC time, and shuffle bytes read<sup class="footnote-ref"><a href="#fn2" id="fnref2">[2]</a></sup>.</p><p>A host reads as slow against the following synthetic threshold: host mean task duration ≥ 2× overall median AND the host holds ≥ 20% task share; the signal only applies with <code>taskCount ≥ 15</code> and <code>hosts.length ≥ 3</code>.</p><h2 id="why-it-matters" tabindex="-1">Why it matters <a class="header-anchor" href="#why-it-matters" aria-label="Permalink to &quot;Why it matters&quot;">​</a></h2><p>A host running persistently slow tasks behaves like a bottleneck baked into the cluster rather than into the workload: every task Spark places there inherits the delay, and since a stage&#39;s completion time is bounded by its slowest tasks, the rest of the cluster idles while the affected host catches up. Left alone, the same host keeps dragging down every later stage and job that lands work on it.</p><h2 id="how-to-fix-it" tabindex="-1">How to fix it <a class="header-anchor" href="#how-to-fix-it" aria-label="Permalink to &quot;How to fix it&quot;">​</a></h2><ul><li>Turn on speculative execution (<code>spark.speculation</code>, off by default) so Spark relaunches a copy of a task that&#39;s lagging far behind its peers instead of waiting on the slow host to finish it. A stage only becomes eligible once <code>spark.speculation.quantile</code> (default <code>0.9</code>) of its tasks have completed, and a task then qualifies once it runs more than <code>spark.speculation.multiplier</code> (default <code>3</code>) times the median duration, subject to a <code>spark.speculation.minTaskRuntime</code> floor (default <code>100ms</code>) so short tasks aren&#39;t speculated purely for looking slow, or, since Spark 3.4, an efficiency check (<code>spark.speculation.efficiency.enabled</code>, default <code>true</code>) that also requires the task&#39;s data-processing rate to lag the stage average<sup class="footnote-ref"><a href="#fn3" id="fnref3">[3]</a></sup>.</li><li>If the slow host also happens to hold data locality for the affected tasks, lowering <code>spark.locality.wait</code> (default <code>3s</code>), or the level-specific <code>spark.locality.wait.node</code>, <code>.rack</code>, and <code>.process</code> overrides, shortens how long Spark waits for a data-local slot before falling back to a less-local executor<sup class="footnote-ref"><a href="#fn3" id="fnref3:1">[3:1]</a></sup>.</li></ul><p>Turn on speculation and, if the slow host holds locality, shorten the wait; defaults shown:</p><div class="language-properties vp-adaptive-theme"><button title="Copy Code" class="copy"></button><span class="lang">properties</span><pre class="shiki shiki-themes github-light github-dark vp-code" tabindex="0"><code><span class="line"><span style="--shiki-light:#6A737D;--shiki-dark:#6A737D;"># Relaunch tasks stuck on a slow host (speculation is OFF by default)</span></span>
26
+ <span class="line"><span style="--shiki-light:#D73A49;--shiki-dark:#F97583;">spark.speculation</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">=true</span></span>
27
+ <span class="line"><span style="--shiki-light:#D73A49;--shiki-dark:#F97583;">spark.speculation.quantile</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">=0.9 </span><span style="--shiki-light:#6A737D;--shiki-dark:#6A737D;"># default; fraction of tasks done before speculation starts</span></span>
28
+ <span class="line"><span style="--shiki-light:#D73A49;--shiki-dark:#F97583;">spark.speculation.multiplier</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">=3 </span><span style="--shiki-light:#6A737D;--shiki-dark:#6A737D;"># default; a task must run &gt; 3x the median to be relaunched</span></span>
29
+ <span class="line"></span>
30
+ <span class="line"><span style="--shiki-light:#6A737D;--shiki-dark:#6A737D;"># If the slow host holds data locality, wait less before falling back to another executor</span></span>
31
+ <span class="line"><span style="--shiki-light:#D73A49;--shiki-dark:#F97583;">spark.locality.wait</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">=3s </span><span style="--shiki-light:#6A737D;--shiki-dark:#6A737D;"># default; lower to fall back sooner</span></span></code></pre></div><h2 id="confidence" tabindex="-1">Confidence <a class="header-anchor" href="#confidence" aria-label="Permalink to &quot;Confidence&quot;">​</a></h2><p>The core <code>durationShare</code> dimension is validated: it measures host-wide task-duration inflation against the cluster median, the signal that separates a genuinely slow machine from normal task-time variance. Two secondary dimensions run best-effort and stay experimental. The <code>multiDim</code> dimension <span class="tag">EXPERIMENTAL</span> folds several per-host signals into one score, but that combined heuristic has not been validated. The <code>storageMemory</code> dimension <span class="tag">EXPERIMENTAL</span> likewise reads host-level memory pressure as a contributing factor without validation, so treat both as hints rather than verdicts.</p><h2 id="limitations-false-positive-risk" tabindex="-1">Limitations / false-positive risk <a class="header-anchor" href="#limitations-false-positive-risk" aria-label="Permalink to &quot;Limitations / false-positive risk&quot;">​</a></h2><p>A host that looks slow is not always a bad node. It can simply hold data locality for the tasks scheduled there, or carry one heavy stage that happens to be pinned to it, either of which inflates its mean task time without any hardware fault. The multi-dimensional scoring that reinforces the core signal is best-effort, so a match warrants a look at what that host was actually running before you conclude the machine itself is the problem.</p><h2 id="bottleneck-stage-slowness" tabindex="-1">Stage slowness <a class="header-anchor" href="#bottleneck-stage-slowness" aria-label="Permalink to &quot;Stage slowness {#bottleneck-stage-slowness}&quot;">​</a></h2><p><span class="tag">SLOW</span> <span class="tag">EXPERIMENTAL</span></p><p>This is an experimental fallback heuristic that shares the slow-host anchor and is suppressed whenever <code>slowHost</code> fires. It answers a different question: when no single machine is dragging, why does one stage still lag the rest of the job? The cause usually traces back to how the work was divided rather than where it ran.</p><p><strong>Too few partitions caps parallelism.</strong> Wide stages (joins, groupBy, aggregations) take their partition count from <code>spark.sql.shuffle.partitions</code>, which sits at a default of 200 whether the shuffle moves 20 MB or 500 GB unless you change it<sup class="footnote-ref"><a href="#fn4" id="fnref4">[4]</a></sup>. When that count is small relative to the cluster, only a handful of tasks carry the stage while cores sit idle, so it stretches out even as better-sized neighbors finish quickly. The first move is to raise its parallelism, aiming for at least two or three tasks per CPU core on a data-heavy stage, tuned through <code>spark.default.parallelism</code> and <code>spark.sql.shuffle.partitions</code><sup class="footnote-ref"><a href="#fn5" id="fnref5">[5]</a></sup>.</p><p><strong>Large data volume per task makes each task run long.</strong> That 200-partition default does not scale with input size, so a stage handling hundreds of gigabytes hands each task a large slice: fewer tasks run at once, per-executor load climbs, and the stage often trips memory errors. Roughly 100-200 MB per task tends to work well, and tasks grinding through around 3 GB each while spilling are a sign you need more partitions<sup class="footnote-ref"><a href="#fn4" id="fnref4:1">[4:1]</a></sup>.</p><p><strong>Heavy shuffle and spill inflate the stage&#39;s cost.</strong> Shuffles move data across executors so rows with the same key land together, and during those map and <a href="./shuffle.html">shuffle</a> operations Spark writes to and reads from local-disk shuffle files, which is heavy I/O that can become a bottleneck under the default configuration<sup class="footnote-ref"><a href="#fn2" id="fnref2:1">[2:1]</a></sup>. Volume per task feeds straight into it: once a partition outgrows the memory available in an executor, Spark <a href="./bottleneck-spill.html">spills</a> part of the data to disk, and spills are about the slowest thing a job can do because of the extra disk I/O and garbage collection, so the stage finishes but runs far less efficiently than the rest<sup class="footnote-ref"><a href="#fn4" id="fnref4:2">[4:2]</a></sup>.</p><h2 id="related" tabindex="-1">Related <a class="header-anchor" href="#related" aria-label="Permalink to &quot;Related&quot;">​</a></h2><ul><li><strong>Speculation &amp; locality tuning:</strong> <a href="./cluster-config.html">Cluster Tuning</a></li></ul><hr class="footnotes-sep"><section class="footnotes"><ol class="footnotes-list"><li id="fn1" class="footnote-item"><p><a href="https://spark.apache.org/docs/latest/monitoring.html#spark-history-server" target="_blank" rel="noreferrer">Monitoring and Instrumentation</a> <a href="#fnref1" class="footnote-backref">↩︎</a></p></li><li id="fn2" class="footnote-item"><p><em>Learning Spark, 2nd Edition</em>, Damji, Wenig, Das, Lee, ch. 7 <a href="#fnref2" class="footnote-backref">↩︎</a> <a href="#fnref2:1" class="footnote-backref">↩︎</a></p></li><li id="fn3" class="footnote-item"><p><a href="https://spark.apache.org/docs/latest/configuration.html" target="_blank" rel="noreferrer">Configuration (Spark)</a> <a href="#fnref3" class="footnote-backref">↩︎</a> <a href="#fnref3:1" class="footnote-backref">↩︎</a></p></li><li id="fn4" class="footnote-item"><p><a href="https://luminousmen.com/post/spark-partitions" target="_blank" rel="noreferrer">Spark Partitions</a> <a href="#fnref4" class="footnote-backref">↩︎</a> <a href="#fnref4:1" class="footnote-backref">↩︎</a> <a href="#fnref4:2" class="footnote-backref">↩︎</a></p></li><li id="fn5" class="footnote-item"><p><em>Spark: The Definitive Guide</em>, Chambers &amp; Zaharia (O&#39;Reilly, 2018) <a href="#fnref5" class="footnote-backref">↩︎</a></p></li></ol></section></div></div></main><footer class="VPDocFooter" data-v-39a288b8 data-v-e257564d><!--[--><!--]--><!----><nav class="prev-next" aria-labelledby="doc-footer-aria-label" data-v-e257564d><span class="visually-hidden" id="doc-footer-aria-label" data-v-e257564d>Pager</span><div class="pager" data-v-e257564d><a class="VPLink link pager-link prev" href="/docs/tuning-reference/bottleneck-utilization.html" data-v-e257564d><!--[--><span class="desc" data-v-e257564d>Previous page</span><span class="title" data-v-e257564d>Executor Utilization</span><!--]--></a></div><div class="pager" data-v-e257564d><a class="VPLink link pager-link next" href="/docs/tuning-reference/bottleneck-failures.html" data-v-e257564d><!--[--><span class="desc" data-v-e257564d>Next page</span><span class="title" data-v-e257564d>Task Failures</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\":\"B-OsL91z\",\"contributor-guide_architecture_detector-contract.md\":\"BOeH4d1J\",\"contributor-guide_architecture_drill-down.md\":\"BtPdlM7r\",\"contributor-guide_architecture_impact-estimation.md\":\"DYCDPgkh\",\"contributor-guide_architecture_index.md\":\"3TO9ic6w\",\"contributor-guide_architecture_overview.md\":\"CehiRmGn\",\"contributor-guide_architecture_state-and-history.md\":\"m3S3UdMk\",\"contributor-guide_architecture_widget-rendering.md\":\"DbqPf2OT\",\"contributor-guide_architecture_worker-protocol.md\":\"B93qJ_tT\",\"contributor-guide_contributing.md\":\"CvRsdr6J\",\"contributor-guide_development-setup.md\":\"DvAN_9mK\",\"contributor-guide_testing.md\":\"6rIKqSyY\",\"index.md\":\"CHJVslga\",\"tuning-reference_anti-patterns.md\":\"Df1YMIHu\",\"tuning-reference_aqe.md\":\"BIsCtLzm\",\"tuning-reference_bottleneck-broadcast-sizing.md\":\"CEstB3Ia\",\"tuning-reference_bottleneck-cold-start.md\":\"CEuy-72y\",\"tuning-reference_bottleneck-duplicate-plan-subtree.md\":\"CIohQDfn\",\"tuning-reference_bottleneck-failures.md\":\"4z5BXGJ2\",\"tuning-reference_bottleneck-gc.md\":\"DSxzZRK7\",\"tuning-reference_bottleneck-job-failure-rate.md\":\"BaJl__1W\",\"tuning-reference_bottleneck-memory-utilization.md\":\"DbP-SJZc\",\"tuning-reference_bottleneck-retry-waste.md\":\"D5JMjVOt\",\"tuning-reference_bottleneck-shuffle.md\":\"CM-nTmIH\",\"tuning-reference_bottleneck-skew.md\":\"BdUwiDhn\",\"tuning-reference_bottleneck-slow-host.md\":\"BlIo6UDW\",\"tuning-reference_bottleneck-small-files.md\":\"B8kloyx8\",\"tuning-reference_bottleneck-spill.md\":\"PNH7mITt\",\"tuning-reference_bottleneck-straggler.md\":\"DY36fHN5\",\"tuning-reference_bottleneck-tiny-tasks.md\":\"QTV7O8kU\",\"tuning-reference_bottleneck-utilization.md\":\"DTiueZC3\",\"tuning-reference_caching.md\":\"B7aQ8asB\",\"tuning-reference_cluster-config.md\":\"ZVmDGsQ3\",\"tuning-reference_config.md\":\"UvveiWG3\",\"tuning-reference_data-formats.md\":\"bjCAWH3N\",\"tuning-reference_index.md\":\"BQ_NooMV\",\"tuning-reference_intro.md\":\"CobD-lGB\",\"tuning-reference_joins.md\":\"BtKs_CuW\",\"tuning-reference_memory-model.md\":\"DhT-n4y3\",\"tuning-reference_metrics.md\":\"mLOh7Apj\",\"tuning-reference_partitioning.md\":\"q0zKF_8X\",\"tuning-reference_pyspark.md\":\"DDCfvN9t\",\"tuning-reference_shuffle.md\":\"BZZ7R4Ix\",\"tuning-reference_spark-architecture.md\":\"Dwzm5avO\",\"tuning-reference_table-formats.md\":\"D6wj-2dX\",\"user-guide_alternative-log-retrieval.md\":\"sU3KGarf\",\"user-guide_getting-started.md\":\"DtEM37MK\",\"user-guide_mcp-tools.md\":\"C8MiIu7F\",\"user-guide_run-comparison.md\":\"S0TWWmLY\",\"user-guide_understanding-findings.md\":\"D0R_Y-R2\"}");window.__VP_SITE_DATA__=JSON.parse("{\"lang\":\"en-US\",\"dir\":\"ltr\",\"title\":\"SparkForensics\",\"description\":\"Docs for using and contributing to SparkForensics\",\"base\":\"/docs/\",\"head\":[],\"router\":{\"prefetchLinks\":true},\"appearance\":true,\"themeConfig\":{\"logo\":\"/favicon.svg\",\"nav\":[{\"text\":\"User Guide\",\"link\":\"/user-guide/getting-started\"},{\"text\":\"Contributor Guide\",\"link\":\"/contributor-guide/development-setup\"},{\"text\":\"Tuning Reference\",\"link\":\"/tuning-reference/\"}],\"sidebar\":{\"/tuning-reference/\":[{\"text\":\"Getting Started\",\"items\":[{\"text\":\"Introduction\",\"link\":\"/tuning-reference/intro\"}]},{\"text\":\"Optimization Guide\",\"items\":[{\"text\":\"Spark Execution Model\",\"link\":\"/tuning-reference/spark-architecture\"},{\"text\":\"Memory Management\",\"link\":\"/tuning-reference/memory-model\"},{\"text\":\"Partitioning\",\"link\":\"/tuning-reference/partitioning\"},{\"text\":\"Join Optimization\",\"link\":\"/tuning-reference/joins\"},{\"text\":\"Shuffle\",\"link\":\"/tuning-reference/shuffle\"},{\"text\":\"Data Formats\",\"link\":\"/tuning-reference/data-formats\"},{\"text\":\"Table Formats\",\"link\":\"/tuning-reference/table-formats\"},{\"text\":\"Caching & Persistence\",\"link\":\"/tuning-reference/caching\"},{\"text\":\"PySpark Specifics\",\"link\":\"/tuning-reference/pyspark\"},{\"text\":\"Adaptive Query Execution\",\"link\":\"/tuning-reference/aqe\"},{\"text\":\"Cluster Tuning\",\"link\":\"/tuning-reference/cluster-config\"},{\"text\":\"Anti-Patterns\",\"link\":\"/tuning-reference/anti-patterns\"}]},{\"text\":\"Detector Catalog\",\"items\":[{\"text\":\"Task Skew\",\"link\":\"/tuning-reference/bottleneck-skew\"},{\"text\":\"Shuffle I/O\",\"link\":\"/tuning-reference/bottleneck-shuffle\"},{\"text\":\"Memory / Disk Spill\",\"link\":\"/tuning-reference/bottleneck-spill\"},{\"text\":\"GC Pressure\",\"link\":\"/tuning-reference/bottleneck-gc\"},{\"text\":\"Cold Start\",\"link\":\"/tuning-reference/bottleneck-cold-start\"},{\"text\":\"Executor Utilization\",\"link\":\"/tuning-reference/bottleneck-utilization\"},{\"text\":\"Slow Host\",\"link\":\"/tuning-reference/bottleneck-slow-host\"},{\"text\":\"Task Failures\",\"link\":\"/tuning-reference/bottleneck-failures\"},{\"text\":\"Stragglers\",\"link\":\"/tuning-reference/bottleneck-straggler\"},{\"text\":\"Retry Waste\",\"link\":\"/tuning-reference/bottleneck-retry-waste\"},{\"text\":\"Tiny Tasks\",\"link\":\"/tuning-reference/bottleneck-tiny-tasks\"},{\"text\":\"Job Failure Rate\",\"link\":\"/tuning-reference/bottleneck-job-failure-rate\"},{\"text\":\"Memory Utilization\",\"link\":\"/tuning-reference/bottleneck-memory-utilization\"},{\"text\":\"Duplicate Plan Subtree\",\"link\":\"/tuning-reference/bottleneck-duplicate-plan-subtree\"},{\"text\":\"Small Files\",\"link\":\"/tuning-reference/bottleneck-small-files\"},{\"text\":\"Broadcast Sizing\",\"link\":\"/tuning-reference/bottleneck-broadcast-sizing\"}]},{\"text\":\"Reference\",\"items\":[{\"text\":\"Metrics Glossary\",\"link\":\"/tuning-reference/metrics\"},{\"text\":\"Spark Config Quick-Reference\",\"link\":\"/tuning-reference/config\"}]}],\"/user-guide/\":[{\"text\":\"User Guide\",\"items\":[{\"text\":\"Getting started\",\"link\":\"/user-guide/getting-started\"},{\"text\":\"Understanding findings\",\"link\":\"/user-guide/understanding-findings\"},{\"text\":\"Run comparison mode\",\"link\":\"/user-guide/run-comparison\"},{\"text\":\"MCP tools reference\",\"link\":\"/user-guide/mcp-tools\"},{\"text\":\"Alternative log retrieval\",\"link\":\"/user-guide/alternative-log-retrieval\"}]}],\"/contributor-guide/\":[{\"text\":\"Contributor Guide\",\"items\":[{\"text\":\"Development setup\",\"link\":\"/contributor-guide/development-setup\"},{\"text\":\"Architecture\",\"link\":\"/contributor-guide/architecture/\",\"collapsed\":true,\"items\":[{\"text\":\"Overview\",\"link\":\"/contributor-guide/architecture/overview\"},{\"text\":\"Worker protocol\",\"link\":\"/contributor-guide/architecture/worker-protocol\"},{\"text\":\"State & history intake\",\"link\":\"/contributor-guide/architecture/state-and-history\"},{\"text\":\"Detector contract\",\"link\":\"/contributor-guide/architecture/detector-contract\"},{\"text\":\"Impact estimation\",\"link\":\"/contributor-guide/architecture/impact-estimation\"},{\"text\":\"Widget rendering\",\"link\":\"/contributor-guide/architecture/widget-rendering\"},{\"text\":\"Board widgets\",\"link\":\"/contributor-guide/architecture/board-widgets\"},{\"text\":\"Drill-down\",\"link\":\"/contributor-guide/architecture/drill-down\"}]},{\"text\":\"Testing & verification\",\"link\":\"/contributor-guide/testing\"},{\"text\":\"Contributing\",\"link\":\"/contributor-guide/contributing\"}]}]},\"search\":{\"provider\":\"local\"}},\"locales\":{},\"scrollOffset\":134,\"cleanUrls\":false}");</script>
33
+
34
+ </body>
35
+ </html>
package/public/docs/tuning-reference/bottleneck-small-files.html ADDED
@@ -0,0 +1,33 @@
1
+ <!DOCTYPE html>
2
+ <html lang="en-US" dir="ltr">
3
+ <head>
4
+ <meta charset="utf-8">
5
+ <meta name="viewport" content="width=device-width,initial-scale=1">
6
+ <title>Small Files | SparkForensics</title>
7
+ <meta name="description" content="Docs for using and contributing to SparkForensics">
8
+ <meta name="generator" content="VitePress v1.6.4">
9
+ <link rel="preload stylesheet" href="/docs/assets/style.DXOMCXxn.css" as="style">
10
+ <link rel="preload stylesheet" href="/docs/vp-icons.css" as="style">
11
+
12
+ <script type="module" src="/docs/assets/app.BgzsaTS3.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.BP14rGBx.js">
15
+ <link rel="modulepreload" href="/docs/assets/chunks/framework.DSg0KOwT.js">
16
+ <link rel="modulepreload" href="/docs/assets/tuning-reference_bottleneck-small-files.md.B8kloyx8.lean.js">
17
+ <link rel="icon" type="image/svg+xml" href="/docs/favicon.svg">
18
+ <link rel="preconnect" href="https://fonts.googleapis.com">
19
+ <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin="">
20
+ <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">
21
+ <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>
22
+ <script id="check-mac-os">document.documentElement.classList.toggle("mac",/Mac|iPhone|iPod|iPad/i.test(navigator.platform));</script>
23
+ </head>
24
+ <body>
25
+ <div id="app"><div class="Layout" data-v-5d98c3a5><!--[--><!--]--><!--[--><span tabindex="-1" data-v-0b0ada53></span><a href="#VPContent" class="VPSkipLink visually-hidden" data-v-0b0ada53>Skip to content</a><!--]--><!----><header class="VPNav" data-v-5d98c3a5 data-v-ae24b3ad><div class="VPNavBar" data-v-ae24b3ad data-v-6aa21345><div class="wrapper" data-v-6aa21345><div class="container" data-v-6aa21345><div class="title" data-v-6aa21345><div class="VPNavBarTitle has-sidebar" data-v-6aa21345 data-v-1168a8e4><a class="title" href="/docs/" data-v-1168a8e4><!--[--><!--]--><!--[--><img class="VPImage logo" src="/docs/favicon.svg" alt data-v-8426fc1a><!--]--><span data-v-1168a8e4>SparkForensics</span><!--[--><!--]--></a></div></div><div class="content" data-v-6aa21345><div class="content-body" data-v-6aa21345><!--[--><!--]--><div class="VPNavBarSearch search" data-v-6aa21345><!--[--><!----><div id="local-search"><button type="button" class="DocSearch DocSearch-Button" aria-label="Search"><span class="DocSearch-Button-Container"><span class="vp-icon DocSearch-Search-Icon"></span><span class="DocSearch-Button-Placeholder">Search</span></span><span class="DocSearch-Button-Keys"><kbd class="DocSearch-Button-Key"></kbd><kbd class="DocSearch-Button-Key">K</kbd></span></button></div><!--]--></div><nav aria-labelledby="main-nav-aria-label" class="VPNavBarMenu menu" data-v-6aa21345 data-v-dc692963><span id="main-nav-aria-label" class="visually-hidden" data-v-dc692963> Main Navigation </span><!--[--><!--[--><a class="VPLink link VPNavBarMenuLink" href="/docs/user-guide/getting-started.html" tabindex="0" data-v-dc692963 data-v-e56f3d57><!--[--><span data-v-e56f3d57>User Guide</span><!--]--></a><!--]--><!--[--><a class="VPLink link VPNavBarMenuLink" href="/docs/contributor-guide/development-setup.html" tabindex="0" data-v-dc692963 data-v-e56f3d57><!--[--><span data-v-e56f3d57>Contributor Guide</span><!--]--></a><!--]--><!--[--><a class="VPLink link VPNavBarMenuLink" href="/docs/tuning-reference/" tabindex="0" data-v-dc692963 data-v-e56f3d57><!--[--><span data-v-e56f3d57>Tuning Reference</span><!--]--></a><!--]--><!--]--></nav><!----><div class="VPNavBarAppearance appearance" data-v-6aa21345 data-v-6c893767><button class="VPSwitch VPSwitchAppearance" type="button" role="switch" title aria-checked="false" data-v-6c893767 data-v-5337faa4 data-v-1d5665e3><span class="check" data-v-1d5665e3><span class="icon" data-v-1d5665e3><!--[--><span class="vpi-sun sun" data-v-5337faa4></span><span class="vpi-moon moon" data-v-5337faa4></span><!--]--></span></span></button></div><!----><div class="VPFlyout VPNavBarExtra extra" data-v-6aa21345 data-v-bb2aa2f0 data-v-cf11d7a2><button type="button" class="button" aria-haspopup="true" aria-expanded="false" aria-label="extra navigation" data-v-cf11d7a2><span class="vpi-more-horizontal icon" data-v-cf11d7a2></span></button><div class="menu" data-v-cf11d7a2><div class="VPMenu" data-v-cf11d7a2 data-v-b98bc113><!----><!--[--><!--[--><!----><div class="group" data-v-bb2aa2f0><div class="item appearance" data-v-bb2aa2f0><p class="label" data-v-bb2aa2f0>Appearance</p><div class="appearance-action" data-v-bb2aa2f0><button class="VPSwitch VPSwitchAppearance" type="button" role="switch" title aria-checked="false" data-v-bb2aa2f0 data-v-5337faa4 data-v-1d5665e3><span class="check" data-v-1d5665e3><span class="icon" data-v-1d5665e3><!--[--><span class="vpi-sun sun" data-v-5337faa4></span><span class="vpi-moon moon" data-v-5337faa4></span><!--]--></span></span></button></div></div></div><!----><!--]--><!--]--></div></div></div><!--[--><!--]--><button type="button" class="VPNavBarHamburger hamburger" aria-label="mobile navigation" aria-expanded="false" aria-controls="VPNavScreen" data-v-6aa21345 data-v-e5dd9c1c><span class="container" data-v-e5dd9c1c><span class="top" data-v-e5dd9c1c></span><span class="middle" data-v-e5dd9c1c></span><span class="bottom" data-v-e5dd9c1c></span></span></button></div></div></div></div><div class="divider" data-v-6aa21345><div class="divider-line" data-v-6aa21345></div></div></div><!----></header><div class="VPLocalNav has-sidebar empty" data-v-5d98c3a5 data-v-a6f0e41e><div class="container" data-v-a6f0e41e><button class="menu" aria-expanded="false" aria-controls="VPSidebarNav" data-v-a6f0e41e><span class="vpi-align-left menu-icon" data-v-a6f0e41e></span><span class="menu-text" data-v-a6f0e41e>Menu</span></button><div class="VPLocalNavOutlineDropdown" style="--vp-vh:0px;" data-v-a6f0e41e data-v-8a42e2b4><button data-v-8a42e2b4>Return to top</button><!----></div></div></div><aside class="VPSidebar" data-v-5d98c3a5 data-v-319d5ca6><div class="curtain" data-v-319d5ca6></div><nav class="nav" id="VPSidebarNav" aria-labelledby="sidebar-aria-label" tabindex="-1" data-v-319d5ca6><span class="visually-hidden" id="sidebar-aria-label" data-v-319d5ca6> Sidebar Navigation </span><!--[--><!--]--><!--[--><div class="no-transition group" data-v-c40bc020><section class="VPSidebarItem level-0" data-v-c40bc020 data-v-b3fd67f8><div class="item" role="button" tabindex="0" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><h2 class="text" data-v-b3fd67f8>Getting Started</h2><!----></div><div class="items" data-v-b3fd67f8><!--[--><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/intro.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Introduction</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><div class="no-transition group" data-v-c40bc020><section class="VPSidebarItem level-0" data-v-c40bc020 data-v-b3fd67f8><div class="item" role="button" tabindex="0" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><h2 class="text" data-v-b3fd67f8>Optimization Guide</h2><!----></div><div class="items" data-v-b3fd67f8><!--[--><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/spark-architecture.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Spark Execution Model</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/memory-model.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Memory Management</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/partitioning.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Partitioning</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/joins.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Join Optimization</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/shuffle.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Shuffle</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/data-formats.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Data Formats</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/table-formats.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Table Formats</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/caching.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Caching & Persistence</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/pyspark.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>PySpark Specifics</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/aqe.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Adaptive Query Execution</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/cluster-config.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Cluster Tuning</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/anti-patterns.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Anti-Patterns</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><div class="no-transition group" data-v-c40bc020><section class="VPSidebarItem level-0 has-active" data-v-c40bc020 data-v-b3fd67f8><div class="item" role="button" tabindex="0" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><h2 class="text" data-v-b3fd67f8>Detector Catalog</h2><!----></div><div class="items" data-v-b3fd67f8><!--[--><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-skew.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Task Skew</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-shuffle.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Shuffle I/O</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-spill.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Memory / Disk Spill</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-gc.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>GC Pressure</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-cold-start.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Cold Start</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-utilization.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Executor Utilization</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-slow-host.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Slow Host</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-failures.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Task Failures</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-straggler.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Stragglers</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-retry-waste.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Retry Waste</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-tiny-tasks.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Tiny Tasks</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-job-failure-rate.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Job Failure Rate</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-memory-utilization.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Memory Utilization</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-duplicate-plan-subtree.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Duplicate Plan Subtree</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-small-files.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Small Files</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-broadcast-sizing.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Broadcast Sizing</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><div class="no-transition group" data-v-c40bc020><section class="VPSidebarItem level-0" data-v-c40bc020 data-v-b3fd67f8><div class="item" role="button" tabindex="0" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><h2 class="text" data-v-b3fd67f8>Reference</h2><!----></div><div class="items" data-v-b3fd67f8><!--[--><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/metrics.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Metrics Glossary</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/config.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Spark Config Quick-Reference</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><!--]--><!--[--><!--]--></nav></aside><div class="VPContent has-sidebar" id="VPContent" data-v-5d98c3a5 data-v-1428d186><div class="VPDoc has-sidebar has-aside" data-v-1428d186 data-v-39a288b8><!--[--><!--]--><div class="container" data-v-39a288b8><div class="aside" data-v-39a288b8><div class="aside-curtain" data-v-39a288b8></div><div class="aside-container" data-v-39a288b8><div class="aside-content" data-v-39a288b8><div class="VPDocAside" data-v-39a288b8 data-v-3f215769><!--[--><!--]--><!--[--><!--]--><nav aria-labelledby="doc-outline-aria-label" class="VPDocAsideOutline" data-v-3f215769 data-v-a5bbad30><div class="content" data-v-a5bbad30><div class="outline-marker" data-v-a5bbad30></div><div aria-level="2" class="outline-title" id="doc-outline-aria-label" role="heading" data-v-a5bbad30>On this page</div><ul class="VPDocOutlineItem root" data-v-a5bbad30 data-v-b933a997><!--[--><!--]--></ul></div></nav><!--[--><!--]--><div class="spacer" data-v-3f215769></div><!--[--><!--]--><!----><!--[--><!--]--><!--[--><!--]--></div></div></div></div><div class="content" data-v-39a288b8><div class="content-container" data-v-39a288b8><!--[--><!--]--><main class="main" data-v-39a288b8><div style="position:relative;" class="vp-doc _docs_tuning-reference_bottleneck-small-files" data-v-39a288b8><div><h1 id="bottleneck-small-files" tabindex="-1">Small Files <a class="header-anchor" href="#bottleneck-small-files" aria-label="Permalink to &quot;Small Files {#bottleneck-small-files}&quot;">​</a></h1><p><span class="tag">SMALLFILES</span></p><h2 id="what-it-is" tabindex="-1">What it is <a class="header-anchor" href="#what-it-is" aria-label="Permalink to &quot;What it is&quot;">​</a></h2><p>The small-files problem is the cost of managing a large count of tiny files. Writing many small files runs up significant metadata overhead, and Spark handles that pattern badly; distributed filesystems such as HDFS handle it badly too, which is why it earned the name &quot;small file problem&quot;<sup class="footnote-ref"><a href="#fn1" id="fnref1">[1]</a></sup>. The same trap shows up on the read side. Push <code>spark.sql.files.maxPartitionBytes</code> (default 128 MB, aligned to the <a href="./data-formats.html">Parquet</a> block size) too low and Spark carves the input into many small partition files, piling on disk I/O and the filesystem overhead of opening, closing, and listing directories, all of which are slow on a distributed store<sup class="footnote-ref"><a href="#fn2" id="fnref2">[2]</a></sup><sup class="footnote-ref"><a href="#fn3" id="fnref3">[3]</a></sup>.</p><p>Spark writes one file per output partition, so a job left with 200 partitions writes 200 files and one left with 3000 writes 3000, even when many of those files hold only a handful of rows. That count then punishes every downstream job forced to read thousands of tiny files<sup class="footnote-ref"><a href="#fn4" id="fnref4">[4]</a></sup>. The opposite extreme is not free either: files that are too large make it inefficient to read a whole block when you only need a few rows<sup class="footnote-ref"><a href="#fn5" id="fnref5">[5]</a></sup>.</p><h2 id="how-it-s-detected" tabindex="-1">How it&#39;s detected <a class="header-anchor" href="#how-it-s-detected" aria-label="Permalink to &quot;How it&#39;s detected&quot;">​</a></h2><p>Reading the SQL plan surfaces write paths that will emit far more output files than the data warrants, keying off the one-file-per-output-partition rule<sup class="footnote-ref"><a href="#fn4" id="fnref4:1">[4:1]</a></sup>. The signal is a high output-partition count against a modest data volume, which foreshadows a directory full of tiny files.</p><table tabindex="0"><thead><tr><th>Signal</th><th>What it points to</th></tr></thead><tbody><tr><td>Output partition count high vs. data volume</td><td>Many tiny files on write</td></tr><tr><td>Read partitioning below <code>spark.sql.files.maxPartitionBytes</code> (128 MB)</td><td>Over-split input, excess filesystem I/O<sup class="footnote-ref"><a href="#fn2" id="fnref2:1">[2:1]</a></sup><sup class="footnote-ref"><a href="#fn3" id="fnref3:1">[3:1]</a></sup></td></tr></tbody></table><h2 id="why-it-matters" tabindex="-1">Why it matters <a class="header-anchor" href="#why-it-matters" aria-label="Permalink to &quot;Why it matters&quot;">​</a></h2><p>Every extra file is another open, close, and directory-list operation, and on a distributed filesystem those are not cheap<sup class="footnote-ref"><a href="#fn2" id="fnref2:2">[2:2]</a></sup>. The count compounds downstream: a stage that scatters 3000 tiny files hands the next job 3000 files to read back, so the metadata tax is paid twice over<sup class="footnote-ref"><a href="#fn4" id="fnref4:2">[4:2]</a></sup>. None of it is a single dramatic failure. The waste is spread thin across the file count, which is exactly why it goes unnoticed until listing and I/O start to dominate.</p><h2 id="how-to-fix-it" tabindex="-1">How to fix it <a class="header-anchor" href="#how-to-fix-it" aria-label="Permalink to &quot;How to fix it&quot;">​</a></h2><p>Repartition right before the write so the output lands in fewer, better-sized files.</p><ul><li><code>coalesce()</code> is a shuffle-free merge: it fuses existing partitions with no data movement, so <code>df.coalesce(100).write.parquet(...)</code> collapses 3000 tiny files into 100 reasonable ones<sup class="footnote-ref"><a href="#fn4" id="fnref4:3">[4:3]</a></sup>. It does not rebalance, though, so uneven inputs stay uneven once lumped together, and pushing it to <code>coalesce(1)</code> kills parallelism by forcing one executor to do all the work<sup class="footnote-ref"><a href="#fn4" id="fnref4:4">[4:4]</a></sup>.</li><li><code>repartition()</code> is a full reshuffle that buys even distribution at the cost of that <a href="./shuffle.html">shuffle</a>. Reach for it when the distribution itself needs fixing, not just the file count<sup class="footnote-ref"><a href="#fn4" id="fnref4:5">[4:5]</a></sup>.</li></ul><blockquote><p><strong>PySpark:</strong> both are one-line calls on a DataFrame: <code>df.coalesce(100)</code> for a shuffle-free merge, or <code>df.repartition(100)</code> when the data also needs rebalancing.</p></blockquote><div class="language-python vp-adaptive-theme"><button title="Copy Code" class="copy"></button><span class="lang">python</span><pre class="shiki shiki-themes github-light github-dark vp-code" tabindex="0"><code><span class="line"><span style="--shiki-light:#6A737D;--shiki-dark:#6A737D;"># Collapse many tiny output files without a shuffle (distribution already even)</span></span>
26
+ <span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">df.coalesce(</span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">100</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">).write.parquet(path)</span></span>
27
+ <span class="line"></span>
28
+ <span class="line"><span style="--shiki-light:#6A737D;--shiki-dark:#6A737D;"># Full reshuffle to a target count when the distribution itself needs fixing</span></span>
29
+ <span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">df.repartition(</span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">100</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">).write.parquet(path)</span></span></code></pre></div><p>For runtime control, <a href="./aqe.html">Adaptive Query Execution</a> can merge tiny shuffle partitions on its own. With <code>spark.sql.adaptive.enabled</code> and <code>spark.sql.adaptive.coalescePartitions.enabled</code> (default true) set, AQE coalesces contiguous shuffle partitions toward <code>spark.sql.adaptive.advisoryPartitionSizeInBytes</code> (default 64 MB)<sup class="footnote-ref"><a href="#fn4" id="fnref4:6">[4:6]</a></sup><sup class="footnote-ref"><a href="#fn5" id="fnref5:1">[5:1]</a></sup>. Just mind the scope: AQE only engages after the first shuffle, so it fixes shuffle-output partition counts but will not repair input-side partitioning or a bad file layout on disk<sup class="footnote-ref"><a href="#fn6" id="fnref6">[6]</a></sup>.</p><h2 id="confidence" tabindex="-1">Confidence <a class="header-anchor" href="#confidence" aria-label="Permalink to &quot;Confidence&quot;">​</a></h2><p>The core inference, that one output file per partition times a high partition count yields many tiny files, is grounded directly in Spark&#39;s write behavior<sup class="footnote-ref"><a href="#fn4" id="fnref4:7">[4:7]</a></sup>, and the mitigation levers (<code>coalesce()</code>, <code>repartition()</code>, and AQE coalescing) are documented Spark features<sup class="footnote-ref"><a href="#fn4" id="fnref4:8">[4:8]</a></sup><sup class="footnote-ref"><a href="#fn5" id="fnref5:2">[5:2]</a></sup>.</p><h2 id="limitations-false-positive-risk" tabindex="-1">Limitations / false-positive risk <a class="header-anchor" href="#limitations-false-positive-risk" aria-label="Permalink to &quot;Limitations / false-positive risk&quot;">​</a></h2><p>A high file count can be perfectly legitimate: partitioned output deliberately fans data across many files by partition column, so a large count there is by design, not a defect. And AQE coalescing is not a cure-all here, since it only affects post-shuffle partitions and leaves the input file layout untouched<sup class="footnote-ref"><a href="#fn6" id="fnref6:1">[6:1]</a></sup>. The signal reflects the shape, not intent, so confirm the write is not an intended partitioned layout before acting.</p><h2 id="related" tabindex="-1">Related <a class="header-anchor" href="#related" aria-label="Permalink to &quot;Related&quot;">​</a></h2><ul><li><strong>Partition sizing:</strong> <a href="./partitioning.html">Partitioning</a></li><li><strong>Too many small tasks:</strong> <a href="./bottleneck-tiny-tasks.html">Tiny Tasks</a></li></ul><hr class="footnotes-sep"><section class="footnotes"><ol class="footnotes-list"><li id="fn1" class="footnote-item"><p><em>Spark: The Definitive Guide</em>, Chambers &amp; Zaharia, ch. 19 <a href="#fnref1" class="footnote-backref">↩︎</a></p></li><li id="fn2" class="footnote-item"><p><em>Learning Spark, 2nd Edition</em>, Damji, Wenig, Das, Lee, ch. 7 <a href="#fnref2" class="footnote-backref">↩︎</a> <a href="#fnref2:1" class="footnote-backref">↩︎</a> <a href="#fnref2:2" class="footnote-backref">↩︎</a></p></li><li id="fn3" class="footnote-item"><p><a href="https://raw.githubusercontent.com/apache/spark/v3.5.0/sql/catalyst/src/main/scala/org/apache/spark/sql/internal/SQLConf.scala" target="_blank" rel="noreferrer">SQLConf.scala</a> <a href="#fnref3" class="footnote-backref">↩︎</a> <a href="#fnref3:1" class="footnote-backref">↩︎</a></p></li><li id="fn4" class="footnote-item"><p><a href="https://luminousmen.com/post/spark-partitions" target="_blank" rel="noreferrer">Spark Partitions</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></p></li><li id="fn5" class="footnote-item"><p><a href="https://spark.apache.org/docs/latest/sql-performance-tuning.html" target="_blank" rel="noreferrer">Performance Tuning (Spark SQL, DataFrames and Datasets Guide)</a> <a href="#fnref5" class="footnote-backref">↩︎</a> <a href="#fnref5:1" class="footnote-backref">↩︎</a> <a href="#fnref5:2" class="footnote-backref">↩︎</a></p></li><li id="fn6" class="footnote-item"><p><a href="https://luminousmen.com/post/the-apache-spark-optimization-checklist" target="_blank" rel="noreferrer">The Apache Spark Optimization Checklist</a> <a href="#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/bottleneck-duplicate-plan-subtree.html" data-v-e257564d><!--[--><span class="desc" data-v-e257564d>Previous page</span><span class="title" data-v-e257564d>Duplicate Plan Subtree</span><!--]--></a></div><div class="pager" data-v-e257564d><a class="VPLink link pager-link next" href="/docs/tuning-reference/bottleneck-broadcast-sizing.html" data-v-e257564d><!--[--><span class="desc" data-v-e257564d>Next page</span><span class="title" data-v-e257564d>Broadcast Sizing</span><!--]--></a></div></nav></footer><!--[--><!--]--></div></div></div><!--[--><!--]--></div></div><!----><!--[--><!--]--></div></div>
30
+ <script>window.__VP_HASH_MAP__=JSON.parse("{\"contributor-guide_architecture_board-widgets.md\":\"B-OsL91z\",\"contributor-guide_architecture_detector-contract.md\":\"BOeH4d1J\",\"contributor-guide_architecture_drill-down.md\":\"BtPdlM7r\",\"contributor-guide_architecture_impact-estimation.md\":\"DYCDPgkh\",\"contributor-guide_architecture_index.md\":\"3TO9ic6w\",\"contributor-guide_architecture_overview.md\":\"CehiRmGn\",\"contributor-guide_architecture_state-and-history.md\":\"m3S3UdMk\",\"contributor-guide_architecture_widget-rendering.md\":\"DbqPf2OT\",\"contributor-guide_architecture_worker-protocol.md\":\"B93qJ_tT\",\"contributor-guide_contributing.md\":\"CvRsdr6J\",\"contributor-guide_development-setup.md\":\"DvAN_9mK\",\"contributor-guide_testing.md\":\"6rIKqSyY\",\"index.md\":\"CHJVslga\",\"tuning-reference_anti-patterns.md\":\"Df1YMIHu\",\"tuning-reference_aqe.md\":\"BIsCtLzm\",\"tuning-reference_bottleneck-broadcast-sizing.md\":\"CEstB3Ia\",\"tuning-reference_bottleneck-cold-start.md\":\"CEuy-72y\",\"tuning-reference_bottleneck-duplicate-plan-subtree.md\":\"CIohQDfn\",\"tuning-reference_bottleneck-failures.md\":\"4z5BXGJ2\",\"tuning-reference_bottleneck-gc.md\":\"DSxzZRK7\",\"tuning-reference_bottleneck-job-failure-rate.md\":\"BaJl__1W\",\"tuning-reference_bottleneck-memory-utilization.md\":\"DbP-SJZc\",\"tuning-reference_bottleneck-retry-waste.md\":\"D5JMjVOt\",\"tuning-reference_bottleneck-shuffle.md\":\"CM-nTmIH\",\"tuning-reference_bottleneck-skew.md\":\"BdUwiDhn\",\"tuning-reference_bottleneck-slow-host.md\":\"BlIo6UDW\",\"tuning-reference_bottleneck-small-files.md\":\"B8kloyx8\",\"tuning-reference_bottleneck-spill.md\":\"PNH7mITt\",\"tuning-reference_bottleneck-straggler.md\":\"DY36fHN5\",\"tuning-reference_bottleneck-tiny-tasks.md\":\"QTV7O8kU\",\"tuning-reference_bottleneck-utilization.md\":\"DTiueZC3\",\"tuning-reference_caching.md\":\"B7aQ8asB\",\"tuning-reference_cluster-config.md\":\"ZVmDGsQ3\",\"tuning-reference_config.md\":\"UvveiWG3\",\"tuning-reference_data-formats.md\":\"bjCAWH3N\",\"tuning-reference_index.md\":\"BQ_NooMV\",\"tuning-reference_intro.md\":\"CobD-lGB\",\"tuning-reference_joins.md\":\"BtKs_CuW\",\"tuning-reference_memory-model.md\":\"DhT-n4y3\",\"tuning-reference_metrics.md\":\"mLOh7Apj\",\"tuning-reference_partitioning.md\":\"q0zKF_8X\",\"tuning-reference_pyspark.md\":\"DDCfvN9t\",\"tuning-reference_shuffle.md\":\"BZZ7R4Ix\",\"tuning-reference_spark-architecture.md\":\"Dwzm5avO\",\"tuning-reference_table-formats.md\":\"D6wj-2dX\",\"user-guide_alternative-log-retrieval.md\":\"sU3KGarf\",\"user-guide_getting-started.md\":\"DtEM37MK\",\"user-guide_mcp-tools.md\":\"C8MiIu7F\",\"user-guide_run-comparison.md\":\"S0TWWmLY\",\"user-guide_understanding-findings.md\":\"D0R_Y-R2\"}");window.__VP_SITE_DATA__=JSON.parse("{\"lang\":\"en-US\",\"dir\":\"ltr\",\"title\":\"SparkForensics\",\"description\":\"Docs for using and contributing to SparkForensics\",\"base\":\"/docs/\",\"head\":[],\"router\":{\"prefetchLinks\":true},\"appearance\":true,\"themeConfig\":{\"logo\":\"/favicon.svg\",\"nav\":[{\"text\":\"User Guide\",\"link\":\"/user-guide/getting-started\"},{\"text\":\"Contributor Guide\",\"link\":\"/contributor-guide/development-setup\"},{\"text\":\"Tuning Reference\",\"link\":\"/tuning-reference/\"}],\"sidebar\":{\"/tuning-reference/\":[{\"text\":\"Getting Started\",\"items\":[{\"text\":\"Introduction\",\"link\":\"/tuning-reference/intro\"}]},{\"text\":\"Optimization Guide\",\"items\":[{\"text\":\"Spark Execution Model\",\"link\":\"/tuning-reference/spark-architecture\"},{\"text\":\"Memory Management\",\"link\":\"/tuning-reference/memory-model\"},{\"text\":\"Partitioning\",\"link\":\"/tuning-reference/partitioning\"},{\"text\":\"Join Optimization\",\"link\":\"/tuning-reference/joins\"},{\"text\":\"Shuffle\",\"link\":\"/tuning-reference/shuffle\"},{\"text\":\"Data Formats\",\"link\":\"/tuning-reference/data-formats\"},{\"text\":\"Table Formats\",\"link\":\"/tuning-reference/table-formats\"},{\"text\":\"Caching & Persistence\",\"link\":\"/tuning-reference/caching\"},{\"text\":\"PySpark Specifics\",\"link\":\"/tuning-reference/pyspark\"},{\"text\":\"Adaptive Query Execution\",\"link\":\"/tuning-reference/aqe\"},{\"text\":\"Cluster Tuning\",\"link\":\"/tuning-reference/cluster-config\"},{\"text\":\"Anti-Patterns\",\"link\":\"/tuning-reference/anti-patterns\"}]},{\"text\":\"Detector Catalog\",\"items\":[{\"text\":\"Task Skew\",\"link\":\"/tuning-reference/bottleneck-skew\"},{\"text\":\"Shuffle I/O\",\"link\":\"/tuning-reference/bottleneck-shuffle\"},{\"text\":\"Memory / Disk Spill\",\"link\":\"/tuning-reference/bottleneck-spill\"},{\"text\":\"GC Pressure\",\"link\":\"/tuning-reference/bottleneck-gc\"},{\"text\":\"Cold Start\",\"link\":\"/tuning-reference/bottleneck-cold-start\"},{\"text\":\"Executor Utilization\",\"link\":\"/tuning-reference/bottleneck-utilization\"},{\"text\":\"Slow Host\",\"link\":\"/tuning-reference/bottleneck-slow-host\"},{\"text\":\"Task Failures\",\"link\":\"/tuning-reference/bottleneck-failures\"},{\"text\":\"Stragglers\",\"link\":\"/tuning-reference/bottleneck-straggler\"},{\"text\":\"Retry Waste\",\"link\":\"/tuning-reference/bottleneck-retry-waste\"},{\"text\":\"Tiny Tasks\",\"link\":\"/tuning-reference/bottleneck-tiny-tasks\"},{\"text\":\"Job Failure Rate\",\"link\":\"/tuning-reference/bottleneck-job-failure-rate\"},{\"text\":\"Memory Utilization\",\"link\":\"/tuning-reference/bottleneck-memory-utilization\"},{\"text\":\"Duplicate Plan Subtree\",\"link\":\"/tuning-reference/bottleneck-duplicate-plan-subtree\"},{\"text\":\"Small Files\",\"link\":\"/tuning-reference/bottleneck-small-files\"},{\"text\":\"Broadcast Sizing\",\"link\":\"/tuning-reference/bottleneck-broadcast-sizing\"}]},{\"text\":\"Reference\",\"items\":[{\"text\":\"Metrics Glossary\",\"link\":\"/tuning-reference/metrics\"},{\"text\":\"Spark Config Quick-Reference\",\"link\":\"/tuning-reference/config\"}]}],\"/user-guide/\":[{\"text\":\"User Guide\",\"items\":[{\"text\":\"Getting started\",\"link\":\"/user-guide/getting-started\"},{\"text\":\"Understanding findings\",\"link\":\"/user-guide/understanding-findings\"},{\"text\":\"Run comparison mode\",\"link\":\"/user-guide/run-comparison\"},{\"text\":\"MCP tools reference\",\"link\":\"/user-guide/mcp-tools\"},{\"text\":\"Alternative log retrieval\",\"link\":\"/user-guide/alternative-log-retrieval\"}]}],\"/contributor-guide/\":[{\"text\":\"Contributor Guide\",\"items\":[{\"text\":\"Development setup\",\"link\":\"/contributor-guide/development-setup\"},{\"text\":\"Architecture\",\"link\":\"/contributor-guide/architecture/\",\"collapsed\":true,\"items\":[{\"text\":\"Overview\",\"link\":\"/contributor-guide/architecture/overview\"},{\"text\":\"Worker protocol\",\"link\":\"/contributor-guide/architecture/worker-protocol\"},{\"text\":\"State & history intake\",\"link\":\"/contributor-guide/architecture/state-and-history\"},{\"text\":\"Detector contract\",\"link\":\"/contributor-guide/architecture/detector-contract\"},{\"text\":\"Impact estimation\",\"link\":\"/contributor-guide/architecture/impact-estimation\"},{\"text\":\"Widget rendering\",\"link\":\"/contributor-guide/architecture/widget-rendering\"},{\"text\":\"Board widgets\",\"link\":\"/contributor-guide/architecture/board-widgets\"},{\"text\":\"Drill-down\",\"link\":\"/contributor-guide/architecture/drill-down\"}]},{\"text\":\"Testing & verification\",\"link\":\"/contributor-guide/testing\"},{\"text\":\"Contributing\",\"link\":\"/contributor-guide/contributing\"}]}]},\"search\":{\"provider\":\"local\"}},\"locales\":{},\"scrollOffset\":134,\"cleanUrls\":false}");</script>
31
+
32
+ </body>
33
+ </html>
package/public/docs/tuning-reference/bottleneck-spill.html ADDED
@@ -0,0 +1,34 @@
1
+ <!DOCTYPE html>
2
+ <html lang="en-US" dir="ltr">
3
+ <head>
4
+ <meta charset="utf-8">
5
+ <meta name="viewport" content="width=device-width,initial-scale=1">
6
+ <title>Memory / Disk Spill | SparkForensics</title>
7
+ <meta name="description" content="Docs for using and contributing to SparkForensics">
8
+ <meta name="generator" content="VitePress v1.6.4">
9
+ <link rel="preload stylesheet" href="/docs/assets/style.DXOMCXxn.css" as="style">
10
+ <link rel="preload stylesheet" href="/docs/vp-icons.css" as="style">
11
+
12
+ <script type="module" src="/docs/assets/app.BgzsaTS3.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.BP14rGBx.js">
15
+ <link rel="modulepreload" href="/docs/assets/chunks/framework.DSg0KOwT.js">
16
+ <link rel="modulepreload" href="/docs/assets/tuning-reference_bottleneck-spill.md.PNH7mITt.lean.js">
17
+ <link rel="icon" type="image/svg+xml" href="/docs/favicon.svg">
18
+ <link rel="preconnect" href="https://fonts.googleapis.com">
19
+ <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin="">
20
+ <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">
21
+ <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>
22
+ <script id="check-mac-os">document.documentElement.classList.toggle("mac",/Mac|iPhone|iPod|iPad/i.test(navigator.platform));</script>
23
+ </head>
24
+ <body>
25
+ <div id="app"><div class="Layout" data-v-5d98c3a5><!--[--><!--]--><!--[--><span tabindex="-1" data-v-0b0ada53></span><a href="#VPContent" class="VPSkipLink visually-hidden" data-v-0b0ada53>Skip to content</a><!--]--><!----><header class="VPNav" data-v-5d98c3a5 data-v-ae24b3ad><div class="VPNavBar" data-v-ae24b3ad data-v-6aa21345><div class="wrapper" data-v-6aa21345><div class="container" data-v-6aa21345><div class="title" data-v-6aa21345><div class="VPNavBarTitle has-sidebar" data-v-6aa21345 data-v-1168a8e4><a class="title" href="/docs/" data-v-1168a8e4><!--[--><!--]--><!--[--><img class="VPImage logo" src="/docs/favicon.svg" alt data-v-8426fc1a><!--]--><span data-v-1168a8e4>SparkForensics</span><!--[--><!--]--></a></div></div><div class="content" data-v-6aa21345><div class="content-body" data-v-6aa21345><!--[--><!--]--><div class="VPNavBarSearch search" data-v-6aa21345><!--[--><!----><div id="local-search"><button type="button" class="DocSearch DocSearch-Button" aria-label="Search"><span class="DocSearch-Button-Container"><span class="vp-icon DocSearch-Search-Icon"></span><span class="DocSearch-Button-Placeholder">Search</span></span><span class="DocSearch-Button-Keys"><kbd class="DocSearch-Button-Key"></kbd><kbd class="DocSearch-Button-Key">K</kbd></span></button></div><!--]--></div><nav aria-labelledby="main-nav-aria-label" class="VPNavBarMenu menu" data-v-6aa21345 data-v-dc692963><span id="main-nav-aria-label" class="visually-hidden" data-v-dc692963> Main Navigation </span><!--[--><!--[--><a class="VPLink link VPNavBarMenuLink" href="/docs/user-guide/getting-started.html" tabindex="0" data-v-dc692963 data-v-e56f3d57><!--[--><span data-v-e56f3d57>User Guide</span><!--]--></a><!--]--><!--[--><a class="VPLink link VPNavBarMenuLink" href="/docs/contributor-guide/development-setup.html" tabindex="0" data-v-dc692963 data-v-e56f3d57><!--[--><span data-v-e56f3d57>Contributor Guide</span><!--]--></a><!--]--><!--[--><a class="VPLink link VPNavBarMenuLink" href="/docs/tuning-reference/" tabindex="0" data-v-dc692963 data-v-e56f3d57><!--[--><span data-v-e56f3d57>Tuning Reference</span><!--]--></a><!--]--><!--]--></nav><!----><div class="VPNavBarAppearance appearance" data-v-6aa21345 data-v-6c893767><button class="VPSwitch VPSwitchAppearance" type="button" role="switch" title aria-checked="false" data-v-6c893767 data-v-5337faa4 data-v-1d5665e3><span class="check" data-v-1d5665e3><span class="icon" data-v-1d5665e3><!--[--><span class="vpi-sun sun" data-v-5337faa4></span><span class="vpi-moon moon" data-v-5337faa4></span><!--]--></span></span></button></div><!----><div class="VPFlyout VPNavBarExtra extra" data-v-6aa21345 data-v-bb2aa2f0 data-v-cf11d7a2><button type="button" class="button" aria-haspopup="true" aria-expanded="false" aria-label="extra navigation" data-v-cf11d7a2><span class="vpi-more-horizontal icon" data-v-cf11d7a2></span></button><div class="menu" data-v-cf11d7a2><div class="VPMenu" data-v-cf11d7a2 data-v-b98bc113><!----><!--[--><!--[--><!----><div class="group" data-v-bb2aa2f0><div class="item appearance" data-v-bb2aa2f0><p class="label" data-v-bb2aa2f0>Appearance</p><div class="appearance-action" data-v-bb2aa2f0><button class="VPSwitch VPSwitchAppearance" type="button" role="switch" title aria-checked="false" data-v-bb2aa2f0 data-v-5337faa4 data-v-1d5665e3><span class="check" data-v-1d5665e3><span class="icon" data-v-1d5665e3><!--[--><span class="vpi-sun sun" data-v-5337faa4></span><span class="vpi-moon moon" data-v-5337faa4></span><!--]--></span></span></button></div></div></div><!----><!--]--><!--]--></div></div></div><!--[--><!--]--><button type="button" class="VPNavBarHamburger hamburger" aria-label="mobile navigation" aria-expanded="false" aria-controls="VPNavScreen" data-v-6aa21345 data-v-e5dd9c1c><span class="container" data-v-e5dd9c1c><span class="top" data-v-e5dd9c1c></span><span class="middle" data-v-e5dd9c1c></span><span class="bottom" data-v-e5dd9c1c></span></span></button></div></div></div></div><div class="divider" data-v-6aa21345><div class="divider-line" data-v-6aa21345></div></div></div><!----></header><div class="VPLocalNav has-sidebar empty" data-v-5d98c3a5 data-v-a6f0e41e><div class="container" data-v-a6f0e41e><button class="menu" aria-expanded="false" aria-controls="VPSidebarNav" data-v-a6f0e41e><span class="vpi-align-left menu-icon" data-v-a6f0e41e></span><span class="menu-text" data-v-a6f0e41e>Menu</span></button><div class="VPLocalNavOutlineDropdown" style="--vp-vh:0px;" data-v-a6f0e41e data-v-8a42e2b4><button data-v-8a42e2b4>Return to top</button><!----></div></div></div><aside class="VPSidebar" data-v-5d98c3a5 data-v-319d5ca6><div class="curtain" data-v-319d5ca6></div><nav class="nav" id="VPSidebarNav" aria-labelledby="sidebar-aria-label" tabindex="-1" data-v-319d5ca6><span class="visually-hidden" id="sidebar-aria-label" data-v-319d5ca6> Sidebar Navigation </span><!--[--><!--]--><!--[--><div class="no-transition group" data-v-c40bc020><section class="VPSidebarItem level-0" data-v-c40bc020 data-v-b3fd67f8><div class="item" role="button" tabindex="0" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><h2 class="text" data-v-b3fd67f8>Getting Started</h2><!----></div><div class="items" data-v-b3fd67f8><!--[--><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/intro.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Introduction</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><div class="no-transition group" data-v-c40bc020><section class="VPSidebarItem level-0" data-v-c40bc020 data-v-b3fd67f8><div class="item" role="button" tabindex="0" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><h2 class="text" data-v-b3fd67f8>Optimization Guide</h2><!----></div><div class="items" data-v-b3fd67f8><!--[--><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/spark-architecture.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Spark Execution Model</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/memory-model.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Memory Management</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/partitioning.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Partitioning</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/joins.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Join Optimization</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/shuffle.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Shuffle</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/data-formats.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Data Formats</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/table-formats.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Table Formats</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/caching.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Caching & Persistence</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/pyspark.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>PySpark Specifics</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/aqe.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Adaptive Query Execution</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/cluster-config.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Cluster Tuning</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/anti-patterns.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Anti-Patterns</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><div class="no-transition group" data-v-c40bc020><section class="VPSidebarItem level-0 has-active" data-v-c40bc020 data-v-b3fd67f8><div class="item" role="button" tabindex="0" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><h2 class="text" data-v-b3fd67f8>Detector Catalog</h2><!----></div><div class="items" data-v-b3fd67f8><!--[--><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-skew.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Task Skew</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-shuffle.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Shuffle I/O</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-spill.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Memory / Disk Spill</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-gc.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>GC Pressure</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-cold-start.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Cold Start</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-utilization.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Executor Utilization</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-slow-host.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Slow Host</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-failures.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Task Failures</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-straggler.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Stragglers</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-retry-waste.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Retry Waste</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-tiny-tasks.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Tiny Tasks</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-job-failure-rate.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Job Failure Rate</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-memory-utilization.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Memory Utilization</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-duplicate-plan-subtree.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Duplicate Plan Subtree</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-small-files.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Small Files</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/bottleneck-broadcast-sizing.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Broadcast Sizing</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><div class="no-transition group" data-v-c40bc020><section class="VPSidebarItem level-0" data-v-c40bc020 data-v-b3fd67f8><div class="item" role="button" tabindex="0" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><h2 class="text" data-v-b3fd67f8>Reference</h2><!----></div><div class="items" data-v-b3fd67f8><!--[--><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/metrics.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Metrics Glossary</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b3fd67f8><div class="item" data-v-b3fd67f8><div class="indicator" data-v-b3fd67f8></div><a class="VPLink link link" href="/docs/tuning-reference/config.html" data-v-b3fd67f8><!--[--><p class="text" data-v-b3fd67f8>Spark Config Quick-Reference</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><!--]--><!--[--><!--]--></nav></aside><div class="VPContent has-sidebar" id="VPContent" data-v-5d98c3a5 data-v-1428d186><div class="VPDoc has-sidebar has-aside" data-v-1428d186 data-v-39a288b8><!--[--><!--]--><div class="container" data-v-39a288b8><div class="aside" data-v-39a288b8><div class="aside-curtain" data-v-39a288b8></div><div class="aside-container" data-v-39a288b8><div class="aside-content" data-v-39a288b8><div class="VPDocAside" data-v-39a288b8 data-v-3f215769><!--[--><!--]--><!--[--><!--]--><nav aria-labelledby="doc-outline-aria-label" class="VPDocAsideOutline" data-v-3f215769 data-v-a5bbad30><div class="content" data-v-a5bbad30><div class="outline-marker" data-v-a5bbad30></div><div aria-level="2" class="outline-title" id="doc-outline-aria-label" role="heading" data-v-a5bbad30>On this page</div><ul class="VPDocOutlineItem root" data-v-a5bbad30 data-v-b933a997><!--[--><!--]--></ul></div></nav><!--[--><!--]--><div class="spacer" data-v-3f215769></div><!--[--><!--]--><!----><!--[--><!--]--><!--[--><!--]--></div></div></div></div><div class="content" data-v-39a288b8><div class="content-container" data-v-39a288b8><!--[--><!--]--><main class="main" data-v-39a288b8><div style="position:relative;" class="vp-doc _docs_tuning-reference_bottleneck-spill" data-v-39a288b8><div><h1 id="bottleneck-spill" tabindex="-1">Memory / Disk Spill <a class="header-anchor" href="#bottleneck-spill" aria-label="Permalink to &quot;Memory / Disk Spill {#bottleneck-spill}&quot;">​</a></h1><p><span class="tag">SPILL</span></p><h2 id="what-it-is" tabindex="-1">What it is <a class="header-anchor" href="#what-it-is" aria-label="Permalink to &quot;What it is&quot;">​</a></h2><p>Spill happens when a task&#39;s share of execution memory runs out during a sort or hash aggregation. Each task gets its own <code>TaskMemoryManager</code>, which arbitrates the shared execution pool across every task running concurrently on an executor; with <code>n</code> tasks running concurrently, each is allowed to allocate somewhere between <code>1/(2n)</code> and <code>1/n</code> of total execution memory: a soft limit, not a hard stop.<sup class="footnote-ref"><a href="#fn1" id="fnref1">[1]</a></sup> When a task&#39;s sort or hash-aggregation operator keeps requesting execution-memory pages it can&#39;t get, Spark doesn&#39;t fail immediately: it blocks the requesting task, triggers a spill of that task&#39;s in-memory data structure to disk, or, in the worst case, throws an <code>OutOfMemoryError</code>.<sup class="footnote-ref"><a href="#fn1" id="fnref1:1">[1:1]</a></sup></p><p>The spill path runs through Spark&#39;s map/shuffle I/O machinery: shuffle partitions created by wide transformations like <code>groupBy()</code> or <code>join()</code> spill to the executors&#39; local disks, at the location set by <code>spark.local.directory</code>.<sup class="footnote-ref"><a href="#fn2" id="fnref2">[2]</a></sup> SQL physical operators apply the same idea with their own guardrails: <code>SortMergeJoinExec</code>&#39;s in-memory buffer and the cartesian-product operator&#39;s buffer both spill once they cross a configured row-count threshold, which by default is <code>spark.shuffle.spill.numElementsForceSpillThreshold</code>.<sup class="footnote-ref"><a href="#fn3" id="fnref3">[3]</a></sup> Whatever the trigger, the resulting spilled bytes are exposed on the task metrics as <code>memoryBytesSpilled</code>, visible in the Spark UI and event log.<sup class="footnote-ref"><a href="#fn4" id="fnref4">[4]</a></sup></p><h2 id="how-it-s-detected" tabindex="-1">How it&#39;s detected <a class="header-anchor" href="#how-it-s-detected" aria-label="Permalink to &quot;How it&#39;s detected&quot;">​</a></h2><p>Detection: any <code>memoryBytesSpilled &gt; 0</code> → Warning. The classification is the actionable signal.</p><p>Spill classification:</p><ul><li><code>skew</code>: ≥ 80% of tasks have zero spill; fix: address <a href="./bottleneck-skew.html">task skew</a>, not memory.</li><li><code>volume</code>: &lt; 20% of tasks have zero spill; fix: more partitions or more memory.</li><li><code>unclassified</code>: neither condition; treat as volume.</li></ul><img class="light-only" src="/docs/assets/spill-classification.BU2euYDO.svg" alt="How a nonzero memoryBytesSpilled is classified as skew, volume, or unclassified from the share of tasks with zero spill, and the fix each classification points to."><img class="dark-only" src="/docs/assets/spill-classification.dark.D7i1M40d.svg" alt="How a nonzero memoryBytesSpilled is classified as skew, volume, or unclassified from the share of tasks with zero spill, and the fix each classification points to."><h2 id="why-it-matters" tabindex="-1">Why it matters <a class="header-anchor" href="#why-it-matters" aria-label="Permalink to &quot;Why it matters&quot;">​</a></h2><p>Spill is the fallback Spark reaches for once a task can no longer get the execution memory it&#39;s asking for: rather than failing outright, it blocks the task, writes its buffered data to disk, or (if that&#39;s not enough) throws an <code>OutOfMemoryError</code>.<sup class="footnote-ref"><a href="#fn1" id="fnref1:2">[1:2]</a></sup> A task that&#39;s spilling has already given up pure in-memory speed to keep running at all, which is why the skew-vs-volume split above is the actionable part of the signal: the two failure shapes call for opposite fixes.</p><h2 id="how-to-fix-it" tabindex="-1">How to fix it <a class="header-anchor" href="#how-to-fix-it" aria-label="Permalink to &quot;How to fix it&quot;">​</a></h2><ul><li><strong>Skew</strong>: When only a few tasks spill, the problem is the shape of the data, not the size of the memory pool. <code>repartition()</code> is the tool for this: reach for it specifically to fix a lopsided partition distribution or to increase partition count<sup class="footnote-ref"><a href="#fn5" id="fnref5">[5]</a></sup>, in contrast to <code>coalesce()</code>, which never rebalances skewed data because it just stacks existing partitions together: partitions that were uneven going in are still uneven coming out.<sup class="footnote-ref"><a href="#fn6" id="fnref6">[6]</a></sup> For skewed joins, <a href="./aqe.html">Adaptive Query Execution</a> can detect and split<sup class="footnote-ref"><a href="#fn7" id="fnref7">[7]</a></sup> oversized partitions automatically: a partition counts as skewed once it&#39;s larger than <code>spark.sql.adaptive.skewJoin.skewedPartitionFactor</code> (default <code>5.0</code>) times the median partition size, and also larger than <code>spark.sql.adaptive.skewJoin.skewedPartitionThresholdInBytes</code> (default <code>256 MB</code>).<sup class="footnote-ref"><a href="#fn8" id="fnref8">[8]</a></sup><sup class="footnote-ref"><a href="#fn9" id="fnref9">[9]</a></sup> Before AQE existed, the manual equivalent was salting: adding a prefix to the skewed keys to make the same key look different, then adjusting the data distribution accordingly.<sup class="footnote-ref"><a href="#fn7" id="fnref7:1">[7:1]</a></sup> Databricks&#39; <code>/*+ SKEW(...) */</code> hint lets you name the skewed relation and specific key values directly, so the planner targets just those keys instead of relying on automatic detection.<sup class="footnote-ref"><a href="#fn10" id="fnref10">[10]</a></sup></li><li><strong>Volume</strong>: When most tasks spill, the fix is more room to work with: more partitions, more memory, or both. <code>repartition(n)</code> guarantees exactly <code>n</code> output partitions via a hash shuffle<sup class="footnote-ref"><a href="#fn11" id="fnref11">[11]</a></sup>, and since Spark&#39;s per-task startup overhead is low (unlike MapReduce&#39;s), the general bias is to err toward more partitions rather than fewer.<sup class="footnote-ref"><a href="#fn12" id="fnref12">[12]</a></sup><code>spark.sql.files.maxPartitionBytes</code> (default <code>128 MB</code>) is the equivalent lever on the input side, governing how much file data gets packed into each input partition before a shuffle even happens.<sup class="footnote-ref"><a href="#fn6" id="fnref6:1">[6:1]</a></sup> On the memory side, execution memory is a fraction of the JVM heap. <code>spark.memory.fraction</code> (default <code>0.6</code>) sizes the shared execution/storage region as <code>(JVM heap − 300 MiB) × spark.memory.fraction</code><sup class="footnote-ref"><a href="#fn13" id="fnref13">[13]</a></sup>. Because each task&#39;s slice of that region is capped by the <code>TaskMemoryManager</code> at between <code>1/(2n)</code> and <code>1/n</code> of the total,<sup class="footnote-ref"><a href="#fn1" id="fnref1:3">[1:3]</a></sup> giving executors more memory, or running fewer concurrent tasks on each one, directly raises the ceiling before spill kicks in.</li></ul><p>For the <strong>volume</strong> case, give tasks more room: defaults shown, comments say which way to move:</p><div class="language-properties vp-adaptive-theme"><button title="Copy Code" class="copy"></button><span class="lang">properties</span><pre class="shiki shiki-themes github-light github-dark vp-code" tabindex="0"><code><span class="line"><span style="--shiki-light:#6A737D;--shiki-dark:#6A737D;"># Create more, smaller input partitions before the shuffle (default 128m)</span></span>
26
+ <span class="line"><span style="--shiki-light:#D73A49;--shiki-dark:#F97583;">spark.sql.files.maxPartitionBytes</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">=128m</span></span>
27
+ <span class="line"></span>
28
+ <span class="line"><span style="--shiki-light:#6A737D;--shiki-dark:#6A737D;"># Execution/storage share of (JVM heap - 300MiB) (default 0.6);</span></span>
29
+ <span class="line"><span style="--shiki-light:#6A737D;--shiki-dark:#6A737D;"># raising it grows execution memory but starves the untracked user-memory region</span></span>
30
+ <span class="line"><span style="--shiki-light:#D73A49;--shiki-dark:#F97583;">spark.memory.fraction</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">=0.6</span></span></code></pre></div><p>For the <strong>skew</strong> case (only a few tasks spill), the fix is <code>df.repartition(n)</code>, not more memory: see <a href="./partitioning.html">Partitioning</a>.</p><h2 id="confidence" tabindex="-1">Confidence <a class="header-anchor" href="#confidence" aria-label="Permalink to &quot;Confidence&quot;">​</a></h2><p>The core detection (any <code>memoryBytesSpilled &gt; 0</code>) and the skew-vs-volume classification are validated: both the skew branch (most tasks spill nothing, so the shape of the data is the problem) and the volume branch (nearly every task spills, so the pool is too small) map to a well-understood fix, and neither needs further validation. <span class="tag">EXPERIMENTAL</span> When a spill matches neither shape, it falls back to a low-confidence unclassified finding that still requires validation, because there is no confirmed cause to act on; the page defaults it to the volume remedy, but that is a guess, not a diagnosis.</p><h2 id="limitations-false-positive-risk" tabindex="-1">Limitations / false-positive risk <a class="header-anchor" href="#limitations-false-positive-risk" aria-label="Permalink to &quot;Limitations / false-positive risk&quot;">​</a></h2><p>Some spill is normal. A large aggregation or join can spill by design once its working set outgrows execution memory, and a small spill on a healthy stage rarely repays the effort of chasing it. The raw <code>memoryBytesSpilled &gt; 0</code> trigger fires on both the actionable and the routine cases, so treat a small spill as informational until the skew-vs-volume split says otherwise.</p><h2 id="related" tabindex="-1">Related <a class="header-anchor" href="#related" aria-label="Permalink to &quot;Related&quot;">​</a></h2><ul><li><strong>Why it happens:</strong> <a href="./memory-model.html">Memory Management</a>, <a href="./partitioning.html">Partitioning</a></li></ul><hr class="footnotes-sep"><section class="footnotes"><ol class="footnotes-list"><li id="fn1" class="footnote-item"><p><a href="https://luminousmen.com/post/dive-into-spark-memory" target="_blank" rel="noreferrer">Diving into Spark Memory Management</a> <a href="#fnref1" class="footnote-backref">↩︎</a> <a href="#fnref1:1" class="footnote-backref">↩︎</a> <a href="#fnref1:2" class="footnote-backref">↩︎</a> <a href="#fnref1:3" class="footnote-backref">↩︎</a></p></li><li id="fn2" class="footnote-item"><p><em>Learning Spark, 2nd Edition</em>, Damji, Wenig, Das, Lee, ch. 7 <a href="#fnref2" class="footnote-backref">↩︎</a></p></li><li id="fn3" class="footnote-item"><p><a href="https://raw.githubusercontent.com/apache/spark/v3.5.0/sql/catalyst/src/main/scala/org/apache/spark/sql/internal/SQLConf.scala" target="_blank" rel="noreferrer">SQLConf.scala</a> <a href="#fnref3" class="footnote-backref">↩︎</a></p></li><li id="fn4" class="footnote-item"><p><a href="https://spark.apache.org/docs/latest/monitoring.html#spark-history-server" target="_blank" rel="noreferrer">Monitoring and Instrumentation</a> <a href="#fnref4" class="footnote-backref">↩︎</a></p></li><li id="fn5" class="footnote-item"><p><em>Spark: The Definitive Guide</em>, Chambers &amp; Zaharia, ch. 19 <a href="#fnref5" class="footnote-backref">↩︎</a></p></li><li id="fn6" class="footnote-item"><p><a href="https://luminousmen.com/post/spark-partitions" target="_blank" rel="noreferrer">Spark Partitions</a> <a href="#fnref6" class="footnote-backref">↩︎</a> <a href="#fnref6:1" class="footnote-backref">↩︎</a></p></li><li id="fn7" class="footnote-item"><p><a href="https://issues.apache.org/jira/browse/SPARK-29544" target="_blank" rel="noreferrer">SPARK-29544: Optimize Skewed Join in SQL Adaptive Execution</a> <a href="#fnref7" class="footnote-backref">↩︎</a> <a href="#fnref7:1" class="footnote-backref">↩︎</a></p></li><li id="fn8" class="footnote-item"><p><a href="https://spark.apache.org/docs/latest/configuration.html" target="_blank" rel="noreferrer">Configuration (Spark)</a> <a href="#fnref8" class="footnote-backref">↩︎</a></p></li><li id="fn9" class="footnote-item"><p><a href="https://spark.apache.org/docs/latest/sql-performance-tuning.html" target="_blank" rel="noreferrer">Performance Tuning (Spark SQL, DataFrames and Datasets Guide)</a> <a href="#fnref9" class="footnote-backref">↩︎</a></p></li><li id="fn10" class="footnote-item"><p><a href="https://docs.databricks.com/aws/en/archive/legacy/skew-join" target="_blank" rel="noreferrer">Skew Join Optimization</a> <a href="#fnref10" class="footnote-backref">↩︎</a></p></li><li id="fn11" class="footnote-item"><p><a href="https://raw.githubusercontent.com/apache/spark/v3.5.0/core/src/main/scala/org/apache/spark/rdd/RDD.scala" target="_blank" rel="noreferrer">RDD.scala</a> <a href="#fnref11" class="footnote-backref">↩︎</a></p></li><li id="fn12" class="footnote-item"><p><a href="https://blog.cloudera.com/how-to-tune-your-apache-spark-jobs-part-2/" target="_blank" rel="noreferrer">How to Tune Your Apache Spark Jobs (Part 2): Cloudera Engineering Blog</a> <a href="#fnref12" class="footnote-backref">↩︎</a></p></li><li id="fn13" class="footnote-item"><p><a href="https://spark.apache.org/docs/latest/tuning.html" target="_blank" rel="noreferrer">Spark Tuning Guide</a> <a href="#fnref13" class="footnote-backref">↩︎</a></p></li></ol></section></div></div></main><footer class="VPDocFooter" data-v-39a288b8 data-v-e257564d><!--[--><!--]--><!----><nav class="prev-next" aria-labelledby="doc-footer-aria-label" data-v-e257564d><span class="visually-hidden" id="doc-footer-aria-label" data-v-e257564d>Pager</span><div class="pager" data-v-e257564d><a class="VPLink link pager-link prev" href="/docs/tuning-reference/bottleneck-shuffle.html" data-v-e257564d><!--[--><span class="desc" data-v-e257564d>Previous page</span><span class="title" data-v-e257564d>Shuffle I/O</span><!--]--></a></div><div class="pager" data-v-e257564d><a class="VPLink link pager-link next" href="/docs/tuning-reference/bottleneck-gc.html" data-v-e257564d><!--[--><span class="desc" data-v-e257564d>Next page</span><span class="title" data-v-e257564d>GC Pressure</span><!--]--></a></div></nav></footer><!--[--><!--]--></div></div></div><!--[--><!--]--></div></div><!----><!--[--><!--]--></div></div>
31
+ <script>window.__VP_HASH_MAP__=JSON.parse("{\"contributor-guide_architecture_board-widgets.md\":\"B-OsL91z\",\"contributor-guide_architecture_detector-contract.md\":\"BOeH4d1J\",\"contributor-guide_architecture_drill-down.md\":\"BtPdlM7r\",\"contributor-guide_architecture_impact-estimation.md\":\"DYCDPgkh\",\"contributor-guide_architecture_index.md\":\"3TO9ic6w\",\"contributor-guide_architecture_overview.md\":\"CehiRmGn\",\"contributor-guide_architecture_state-and-history.md\":\"m3S3UdMk\",\"contributor-guide_architecture_widget-rendering.md\":\"DbqPf2OT\",\"contributor-guide_architecture_worker-protocol.md\":\"B93qJ_tT\",\"contributor-guide_contributing.md\":\"CvRsdr6J\",\"contributor-guide_development-setup.md\":\"DvAN_9mK\",\"contributor-guide_testing.md\":\"6rIKqSyY\",\"index.md\":\"CHJVslga\",\"tuning-reference_anti-patterns.md\":\"Df1YMIHu\",\"tuning-reference_aqe.md\":\"BIsCtLzm\",\"tuning-reference_bottleneck-broadcast-sizing.md\":\"CEstB3Ia\",\"tuning-reference_bottleneck-cold-start.md\":\"CEuy-72y\",\"tuning-reference_bottleneck-duplicate-plan-subtree.md\":\"CIohQDfn\",\"tuning-reference_bottleneck-failures.md\":\"4z5BXGJ2\",\"tuning-reference_bottleneck-gc.md\":\"DSxzZRK7\",\"tuning-reference_bottleneck-job-failure-rate.md\":\"BaJl__1W\",\"tuning-reference_bottleneck-memory-utilization.md\":\"DbP-SJZc\",\"tuning-reference_bottleneck-retry-waste.md\":\"D5JMjVOt\",\"tuning-reference_bottleneck-shuffle.md\":\"CM-nTmIH\",\"tuning-reference_bottleneck-skew.md\":\"BdUwiDhn\",\"tuning-reference_bottleneck-slow-host.md\":\"BlIo6UDW\",\"tuning-reference_bottleneck-small-files.md\":\"B8kloyx8\",\"tuning-reference_bottleneck-spill.md\":\"PNH7mITt\",\"tuning-reference_bottleneck-straggler.md\":\"DY36fHN5\",\"tuning-reference_bottleneck-tiny-tasks.md\":\"QTV7O8kU\",\"tuning-reference_bottleneck-utilization.md\":\"DTiueZC3\",\"tuning-reference_caching.md\":\"B7aQ8asB\",\"tuning-reference_cluster-config.md\":\"ZVmDGsQ3\",\"tuning-reference_config.md\":\"UvveiWG3\",\"tuning-reference_data-formats.md\":\"bjCAWH3N\",\"tuning-reference_index.md\":\"BQ_NooMV\",\"tuning-reference_intro.md\":\"CobD-lGB\",\"tuning-reference_joins.md\":\"BtKs_CuW\",\"tuning-reference_memory-model.md\":\"DhT-n4y3\",\"tuning-reference_metrics.md\":\"mLOh7Apj\",\"tuning-reference_partitioning.md\":\"q0zKF_8X\",\"tuning-reference_pyspark.md\":\"DDCfvN9t\",\"tuning-reference_shuffle.md\":\"BZZ7R4Ix\",\"tuning-reference_spark-architecture.md\":\"Dwzm5avO\",\"tuning-reference_table-formats.md\":\"D6wj-2dX\",\"user-guide_alternative-log-retrieval.md\":\"sU3KGarf\",\"user-guide_getting-started.md\":\"DtEM37MK\",\"user-guide_mcp-tools.md\":\"C8MiIu7F\",\"user-guide_run-comparison.md\":\"S0TWWmLY\",\"user-guide_understanding-findings.md\":\"D0R_Y-R2\"}");window.__VP_SITE_DATA__=JSON.parse("{\"lang\":\"en-US\",\"dir\":\"ltr\",\"title\":\"SparkForensics\",\"description\":\"Docs for using and contributing to SparkForensics\",\"base\":\"/docs/\",\"head\":[],\"router\":{\"prefetchLinks\":true},\"appearance\":true,\"themeConfig\":{\"logo\":\"/favicon.svg\",\"nav\":[{\"text\":\"User Guide\",\"link\":\"/user-guide/getting-started\"},{\"text\":\"Contributor Guide\",\"link\":\"/contributor-guide/development-setup\"},{\"text\":\"Tuning Reference\",\"link\":\"/tuning-reference/\"}],\"sidebar\":{\"/tuning-reference/\":[{\"text\":\"Getting Started\",\"items\":[{\"text\":\"Introduction\",\"link\":\"/tuning-reference/intro\"}]},{\"text\":\"Optimization Guide\",\"items\":[{\"text\":\"Spark Execution Model\",\"link\":\"/tuning-reference/spark-architecture\"},{\"text\":\"Memory Management\",\"link\":\"/tuning-reference/memory-model\"},{\"text\":\"Partitioning\",\"link\":\"/tuning-reference/partitioning\"},{\"text\":\"Join Optimization\",\"link\":\"/tuning-reference/joins\"},{\"text\":\"Shuffle\",\"link\":\"/tuning-reference/shuffle\"},{\"text\":\"Data Formats\",\"link\":\"/tuning-reference/data-formats\"},{\"text\":\"Table Formats\",\"link\":\"/tuning-reference/table-formats\"},{\"text\":\"Caching & Persistence\",\"link\":\"/tuning-reference/caching\"},{\"text\":\"PySpark Specifics\",\"link\":\"/tuning-reference/pyspark\"},{\"text\":\"Adaptive Query Execution\",\"link\":\"/tuning-reference/aqe\"},{\"text\":\"Cluster Tuning\",\"link\":\"/tuning-reference/cluster-config\"},{\"text\":\"Anti-Patterns\",\"link\":\"/tuning-reference/anti-patterns\"}]},{\"text\":\"Detector Catalog\",\"items\":[{\"text\":\"Task Skew\",\"link\":\"/tuning-reference/bottleneck-skew\"},{\"text\":\"Shuffle I/O\",\"link\":\"/tuning-reference/bottleneck-shuffle\"},{\"text\":\"Memory / Disk Spill\",\"link\":\"/tuning-reference/bottleneck-spill\"},{\"text\":\"GC Pressure\",\"link\":\"/tuning-reference/bottleneck-gc\"},{\"text\":\"Cold Start\",\"link\":\"/tuning-reference/bottleneck-cold-start\"},{\"text\":\"Executor Utilization\",\"link\":\"/tuning-reference/bottleneck-utilization\"},{\"text\":\"Slow Host\",\"link\":\"/tuning-reference/bottleneck-slow-host\"},{\"text\":\"Task Failures\",\"link\":\"/tuning-reference/bottleneck-failures\"},{\"text\":\"Stragglers\",\"link\":\"/tuning-reference/bottleneck-straggler\"},{\"text\":\"Retry Waste\",\"link\":\"/tuning-reference/bottleneck-retry-waste\"},{\"text\":\"Tiny Tasks\",\"link\":\"/tuning-reference/bottleneck-tiny-tasks\"},{\"text\":\"Job Failure Rate\",\"link\":\"/tuning-reference/bottleneck-job-failure-rate\"},{\"text\":\"Memory Utilization\",\"link\":\"/tuning-reference/bottleneck-memory-utilization\"},{\"text\":\"Duplicate Plan Subtree\",\"link\":\"/tuning-reference/bottleneck-duplicate-plan-subtree\"},{\"text\":\"Small Files\",\"link\":\"/tuning-reference/bottleneck-small-files\"},{\"text\":\"Broadcast Sizing\",\"link\":\"/tuning-reference/bottleneck-broadcast-sizing\"}]},{\"text\":\"Reference\",\"items\":[{\"text\":\"Metrics Glossary\",\"link\":\"/tuning-reference/metrics\"},{\"text\":\"Spark Config Quick-Reference\",\"link\":\"/tuning-reference/config\"}]}],\"/user-guide/\":[{\"text\":\"User Guide\",\"items\":[{\"text\":\"Getting started\",\"link\":\"/user-guide/getting-started\"},{\"text\":\"Understanding findings\",\"link\":\"/user-guide/understanding-findings\"},{\"text\":\"Run comparison mode\",\"link\":\"/user-guide/run-comparison\"},{\"text\":\"MCP tools reference\",\"link\":\"/user-guide/mcp-tools\"},{\"text\":\"Alternative log retrieval\",\"link\":\"/user-guide/alternative-log-retrieval\"}]}],\"/contributor-guide/\":[{\"text\":\"Contributor Guide\",\"items\":[{\"text\":\"Development setup\",\"link\":\"/contributor-guide/development-setup\"},{\"text\":\"Architecture\",\"link\":\"/contributor-guide/architecture/\",\"collapsed\":true,\"items\":[{\"text\":\"Overview\",\"link\":\"/contributor-guide/architecture/overview\"},{\"text\":\"Worker protocol\",\"link\":\"/contributor-guide/architecture/worker-protocol\"},{\"text\":\"State & history intake\",\"link\":\"/contributor-guide/architecture/state-and-history\"},{\"text\":\"Detector contract\",\"link\":\"/contributor-guide/architecture/detector-contract\"},{\"text\":\"Impact estimation\",\"link\":\"/contributor-guide/architecture/impact-estimation\"},{\"text\":\"Widget rendering\",\"link\":\"/contributor-guide/architecture/widget-rendering\"},{\"text\":\"Board widgets\",\"link\":\"/contributor-guide/architecture/board-widgets\"},{\"text\":\"Drill-down\",\"link\":\"/contributor-guide/architecture/drill-down\"}]},{\"text\":\"Testing & verification\",\"link\":\"/contributor-guide/testing\"},{\"text\":\"Contributing\",\"link\":\"/contributor-guide/contributing\"}]}]},\"search\":{\"provider\":\"local\"}},\"locales\":{},\"scrollOffset\":134,\"cleanUrls\":false}");</script>
32
+
33
+ </body>
34
+ </html>