paxus_etl - Details for Job 100

Details for Job 100

Status: SUCCEEDED
Completed Stages: 1
Skipped Stages: 3

Enable zooming

digraph G { subgraph clusterstage_186 { label="Stage 186"; subgraph cluster120 { label="Scan parquet dl_pac_ife_paxus_raw_normalized_prod_v1._meta"; 48 [label="FileScanRDD [48]\njavaToPython at NativeMethodAccessorImpl.java:0"]; 49 [label="MapPartitionsRDD [49]\njavaToPython at NativeMethodAccessorImpl.java:0"]; } subgraph cluster116 { label="WholeStageCodegen (1)"; 50 [label="MapPartitionsRDD [50]\njavaToPython at NativeMethodAccessorImpl.java:0"]; } subgraph cluster115 { label="InMemoryTableScan"; 51 [label="MapPartitionsRDD [51]\njavaToPython at NativeMethodAccessorImpl.java:0"]; 52 [label="*(1) Filter ((isnotnull(_ingest_timestamp#86) AND (cast(replace(substring(_ingest_timestamp#86, 1, 10), -, ) as int) >= 20230418)) AND (cast(replace(substring(_ingest_timestamp#86, 1, 10), -, ) as int) <= 20230418))\n+- *(1) ColumnarToRow\n +- FileScan parquet dl_pac_ife_paxus_raw_normalized_prod_v1._meta[_ingest_dbid#83,_ingest_error_code#84,_ingest_input_s3uri#85,_ingest_timestamp#86,_intake_operator#87,_is_survey#88,_metafile_dttm#89,_table_count#90L,airplane_type#91,application_name#92,cmip#93,customer_name#94,flightarrival#95,flightdeparture#96,flightenddate#97,flightguid#98,flightnum#99,flightstartdate#100,icao_airline#101,metadata_info#102,multiple#103,offload_filename#104,offload_format_version#105,offload_type#106,... 7 more fields] Batched: true, DataFilters: [isnotnull(_ingest_timestamp#86), (cast(replace(substring(_ingest_timestamp#86, 1, 10), -, ) as i..., Format: Parquet, Location: InMemoryFileIndex(3788 paths)[s3://pac-dl-dst-ea5dd107-3e06-475b-9535-44a3016830f5/e9bb1a8a-c7d3-..., PartitionF... [52] [Cached]\njavaToPython at NativeMethodAccessorImpl.java:0"]; 53 [label="MapPartitionsRDD [53]\njavaToPython at NativeMethodAccessorImpl.java:0"]; 54 [label="MapPartitionsRDD [54]\njavaToPython at NativeMethodAccessorImpl.java:0"]; 55 [label="MapPartitionsRDD [55]\njavaToPython at NativeMethodAccessorImpl.java:0"]; } subgraph cluster114 { label="Exchange"; 56 [label="MapPartitionsRDD [56]\njavaToPython at NativeMethodAccessorImpl.java:0"]; } } 48->49; 49->50; 50->51; 51->52; 52->53; 53->54; 54->55; 55->56; }

digraph G { subgraph clusterstage_229 { label="Stage 229"; subgraph cluster1017 { label="Scan parquet dl_pac_ife_paxus_raw_normalized_prod_v1.audiodescriptiontable"; 354 [label="FileScanRDD [354]\nsave at NativeMethodAccessorImpl.java:0"]; 355 [label="MapPartitionsRDD [355]\nsave at NativeMethodAccessorImpl.java:0"]; } subgraph cluster1013 { label="WholeStageCodegen (8)"; 356 [label="MapPartitionsRDD [356]\nsave at NativeMethodAccessorImpl.java:0"]; } subgraph cluster1012 { label="Exchange"; 357 [label="MapPartitionsRDD [357]\nsave at NativeMethodAccessorImpl.java:0"]; } } 354->355; 355->356; 356->357; }

digraph G { subgraph clusterstage_240 { label="Stage 240 (skipped)"; subgraph cluster114 { label="Exchange"; 57 [label="ShuffledRowRDD [57]\njavaToPython at NativeMethodAccessorImpl.java:0"]; } subgraph cluster113 { label="InMemoryTableScan"; 58 [label="MapPartitionsRDD [58]\njavaToPython at NativeMethodAccessorImpl.java:0"]; 59 [label="Exchange SinglePartition, REPARTITION_BY_NUM, [id=#243]\n+- InMemoryTableScan [_ingest_dbid#83, _ingest_error_code#84, _ingest_input_s3uri#85, _ingest_timestamp#86, _intake_operator#87, _is_survey#88, _metafile_dttm#89, _table_count#90L, airplane_type#91, application_name#92, cmip#93, customer_name#94, flightarrival#95, flightdeparture#96, flightenddate#97, flightguid#98, flightnum#99, flightstartdate#100, icao_airline#101, metadata_info#102, multiple#103, offload_filename#104, offload_format_version#105, offload_type#106, ... 7 more fields]\n +- InMemoryRelation [_ingest_dbid#83, _ingest_error_code#84, _ingest_input_s3uri#85, _ingest_timestamp#86, _intake_operator#87, _is_survey#88, _metafile_dttm#89, _table_count#90L, airplane_type#91, application_name#92, cmip#93, customer_name#94, flightarrival#95, flightdeparture#96, flightenddate#97, flightguid#98, flightnum#99, flightstartdate#100, icao_airline#101, metadata_info#102, multiple#103, offload_filename#104, offload_format_version#105, offload_type#10... [59] [Cached]\njavaToPython at NativeMethodAccessorImpl.java:0"]; } subgraph cluster1127 { label="InMemoryTableScan"; 419 [label="MapPartitionsRDD [419]\nsave at NativeMethodAccessorImpl.java:0"]; 420 [label="MapPartitionsRDD [420]\nsave at NativeMethodAccessorImpl.java:0"]; 421 [label="MapPartitionsRDD [421]\nsave at NativeMethodAccessorImpl.java:0"]; } subgraph cluster1122 { label="WholeStageCodegen (26)"; 422 [label="MapPartitionsRDD [422]\nsave at NativeMethodAccessorImpl.java:0"]; } subgraph cluster1121 { label="Exchange"; 423 [label="MapPartitionsRDD [423]\nsave at NativeMethodAccessorImpl.java:0"]; } } 57->58; 58->59; 59->419; 419->420; 420->421; 421->422; 422->423; }

56,57

digraph G { subgraph clusterstage_241 { label="Stage 241"; subgraph cluster1307 { label="Exchange"; 499 [label="ShuffledRowRDD [499]\nsave at NativeMethodAccessorImpl.java:0"]; } subgraph cluster1411 { label="Exchange"; 529 [label="ShuffledRowRDD [529]\nsave at NativeMethodAccessorImpl.java:0"]; } subgraph cluster1398 { label="WholeStageCodegen (59)"; 530 [label="ZippedPartitionsRDD2 [530]\nsave at NativeMethodAccessorImpl.java:0"]; 531 [label="MapPartitionsRDD [531]\nsave at NativeMethodAccessorImpl.java:0"]; } subgraph cluster1397 { label="Window"; 532 [label="MapPartitionsRDD [532]\nsave at NativeMethodAccessorImpl.java:0"]; } subgraph cluster1393 { label="WholeStageCodegen (60)"; 533 [label="MapPartitionsRDD [533]\nsave at NativeMethodAccessorImpl.java:0"]; } subgraph cluster1392 { label="Exchange"; 534 [label="MapPartitionsRDD [534]\nsave at NativeMethodAccessorImpl.java:0"]; } } 499->530; 529->530; 530->531; 531->532; 532->533; 533->534; }

357,499

423,529

Completed Stages (1)

Stage Id ▾	Description	Submitted	Duration	Tasks: Succeeded/Total	Input	Output	Shuffle Read	Shuffle Write
241	save at NativeMethodAccessorImpl.java:0 +details org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:239) sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62) sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.lang.reflect.Method.invoke(Method.java:498) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.lang.Thread.run(Thread.java:750)	2023/05/03 17:13:28	25 s	1000/1000			172.0 GB	2.1 GB

Stage Id ▾

Description

Submitted

Duration

Tasks: Succeeded/Total

Input

Output

Shuffle Read

Shuffle Write

241

save at NativeMethodAccessorImpl.java:0 +details

org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:239)
sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
java.lang.reflect.Method.invoke(Method.java:498)
py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)
py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
py4j.Gateway.invoke(Gateway.java:282)
py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
py4j.commands.CallCommand.execute(CallCommand.java:79)
py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182)
py4j.ClientServerConnection.run(ClientServerConnection.java:106)
java.lang.Thread.run(Thread.java:750)

2023/05/03 17:13:28

25 s

1000/1000

172.0 GB

2.1 GB

Skipped Stages (3)

Stage Id ▾	Description	Submitted	Duration	Tasks: Succeeded/Total
240	save at NativeMethodAccessorImpl.java:0 +details org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:239) sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62) sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.lang.reflect.Method.invoke(Method.java:498) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.lang.Thread.run(Thread.java:750)	Unknown	Unknown	0/1
229	save at NativeMethodAccessorImpl.java:0 +details org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:239) sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62) sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.lang.reflect.Method.invoke(Method.java:498) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.lang.Thread.run(Thread.java:750)	Unknown	Unknown	0/651
186	javaToPython at NativeMethodAccessorImpl.java:0 +details org.apache.spark.sql.Dataset.javaToPython(Dataset.scala:3747) sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62) sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) java.lang.reflect.Method.invoke(Method.java:498) py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357) py4j.Gateway.invoke(Gateway.java:282) py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) py4j.commands.CallCommand.execute(CallCommand.java:79) py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182) py4j.ClientServerConnection.run(ClientServerConnection.java:106) java.lang.Thread.run(Thread.java:750)	Unknown	Unknown	0/1433

Stage Id ▾

Description

Submitted

Duration

Tasks: Succeeded/Total

Input

Output

Shuffle Read

Shuffle Write

240

save at NativeMethodAccessorImpl.java:0 +details

org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:239)
sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
java.lang.reflect.Method.invoke(Method.java:498)
py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)
py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
py4j.Gateway.invoke(Gateway.java:282)
py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
py4j.commands.CallCommand.execute(CallCommand.java:79)
py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182)
py4j.ClientServerConnection.run(ClientServerConnection.java:106)
java.lang.Thread.run(Thread.java:750)

Unknown

0/1

229

save at NativeMethodAccessorImpl.java:0 +details

org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:239)
sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
java.lang.reflect.Method.invoke(Method.java:498)
py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)
py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
py4j.Gateway.invoke(Gateway.java:282)
py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
py4j.commands.CallCommand.execute(CallCommand.java:79)
py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182)
py4j.ClientServerConnection.run(ClientServerConnection.java:106)
java.lang.Thread.run(Thread.java:750)

Unknown

0/651

186

javaToPython at NativeMethodAccessorImpl.java:0 +details

org.apache.spark.sql.Dataset.javaToPython(Dataset.scala:3747)
sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
java.lang.reflect.Method.invoke(Method.java:498)
py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)
py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
py4j.Gateway.invoke(Gateway.java:282)
py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
py4j.commands.CallCommand.execute(CallCommand.java:79)
py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182)
py4j.ClientServerConnection.run(ClientServerConnection.java:106)
java.lang.Thread.run(Thread.java:750)

Unknown

0/1433