| 46867 |
default
| collect at /opt/app/scheduler/jobs/dedup_job.py:386
+details
RDD: AdaptiveSparkPlan isFinalPlan=false
+- Filter isnotnull(canonical_id#18144934)
+- InMemoryTableScan [brand_context_id#18144926, supplier_id#18144927, canonical_id#18144934, is_primary#18144935, entity_name#18144928, city#18144929, state#18144930, country#18144931, threshold#18144936, create_date#18144937], [isnotnull(canonical_id#18144934)]
+- InMemoryRelation [brand_context_id#18144926, supplier_id#18144927, entity_name#18144928, city#18144929, state#18144930, country#18144931, supplier_type#18144932, declaring_supplier_id#18144933, canonical_id#18144934, is_primary#18144935, threshold#18144936, create_date#18144937], StorageLevel(disk, memory, deserialized, 1 replicas)
+- *(1) Scan JDBCRelation((
SELECT DISTINCT
v.brand_context_id,
v.supplier_id,
v.entity_name,
v.city,
v.state,
v.country,
v.supplier_type,
v.declaring_supplier_id,
...
org.apache.spark.sql.Dataset.collectToPython(Dataset.scala:4145)
jdk.internal.reflect.GeneratedMethodAccessor253.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)
py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374)
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.base/java.lang.Thread.run(Unknown Source)
|
2026/10/20 07:32:58
| 0.2 s |
| 11.7 KiB | | | 480.0 B |