| 45857 |
default
| collect at /opt/app/scheduler/jobs/dedup_job.py:386
+details
RDD: AdaptiveSparkPlan isFinalPlan=false
+- Filter isnotnull(canonical_id#17812016)
+- InMemoryTableScan [brand_context_id#17812008, supplier_id#17812009, canonical_id#17812016, is_primary#17812017, entity_name#17812010, city#17812011, state#17812012, country#17812013, threshold#17812018, create_date#17812019], [isnotnull(canonical_id#17812016)]
+- InMemoryRelation [brand_context_id#17812008, supplier_id#17812009, entity_name#17812010, city#17812011, state#17812012, country#17812013, supplier_type#17812014, declaring_supplier_id#17812015, canonical_id#17812016, is_primary#17812017, threshold#17812018, create_date#17812019], 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 06:02:59
| 0.1 s |
| 4.1 KiB | | | 160.0 B |