This is an automated email from the ASF dual-hosted git repository.
gurwls223 pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/spark.git
The following commit(s) were added to refs/heads/master by this push:
new 281f174304a [SPARK-44981][PYTHON][CONNECT][FOLLOW-UP] Explicitly pass
runtime configurations only
281f174304a is described below
commit 281f174304a5b1d9a146502dfdfd000d15924327
Author: Hyukjin Kwon <gurwls...@apache.org>
AuthorDate: Tue Aug 29 22:45:00 2023 +0900
[SPARK-44981][PYTHON][CONNECT][FOLLOW-UP] Explicitly pass runtime
configurations only
### What changes were proposed in this pull request?
This PR is a followup of https://github.com/apache/spark/pull/42694 that
only allows to pass runtime configurations.
### Why are the changes needed?
Excluding static SQL configurations cannot exclude core configurations. For
example, if you pass `spark.jars` with `local-cluster` mode, it shows
unneccesary warnings as below:
```bash
./bin/pyspark --remote "local-cluster[1,2,1024]"
```
it shows warnings as below:
```
23/08/29 16:58:08 ERROR ErrorUtils: Spark Connect RPC error during: config.
UserId: hyukjin.kwon. SessionId: 5c331d52-bf65-4f1c-9416-899e00d4a7d9.
org.apache.spark.sql.AnalysisException: [CANNOT_MODIFY_CONFIG] Cannot
modify the value of the Spark config: "spark.jars".
See also
'https://spark.apache.org/docs/latest/sql-migration-guide.html#ddl-statements'.
at
org.apache.spark.sql.errors.QueryCompilationErrors$.cannotModifyValueOfSparkConfigError(QueryCompilationErrors.scala:3233)
at
org.apache.spark.sql.RuntimeConfig.requireNonStaticConf(RuntimeConfig.scala:166)
at org.apache.spark.sql.RuntimeConfig.set(RuntimeConfig.scala:42)
at
org.apache.spark.sql.connect.service.SparkConnectConfigHandler.$anonfun$handleSet$1(SparkConnectConfigHandler.scala:67)
at
org.apache.spark.sql.connect.service.SparkConnectConfigHandler.$anonfun$handleSet$1$adapted(SparkConnectConfigHandler.scala:65)
at scala.collection.Iterator.foreach(Iterator.scala:943)
at scala.collection.Iterator.foreach$(Iterator.scala:943)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1431)
at
org.apache.spark.sql.connect.service.SparkConnectConfigHandler.handleSet(SparkConnectConfigHandler.scala:65)
at
org.apache.spark.sql.connect.service.SparkConnectConfigHandler.handle(SparkConnectConfigHandler.scala:40)
at
org.apache.spark.sql.connect.service.SparkConnectService.config(SparkConnectService.scala:120)
at
org.apache.spark.connect.proto.SparkConnectServiceGrpc$MethodHandlers.invoke(SparkConnectServiceGrpc.java:751)
at
org.sparkproject.connect.grpc.io.grpc.stub.ServerCalls$UnaryServerCallHandler$UnaryServerCallListener.onHalfClose(ServerCalls.java:182)
at
org.sparkproject.connect.grpc.io.grpc.internal.ServerCallImpl$ServerStreamListenerImpl.halfClosed(ServerCallImpl.java:346)
at
org.sparkproject.connect.grpc.io.grpc.internal.ServerImpl$JumpToApplicationThreadServerStreamListener$1HalfClosed.runInContext(ServerImpl.java:860)
at
org.sparkproject.connect.grpc.io.grpc.internal.ContextRunnable.run(ContextRunnable.java:37)
at
org.sparkproject.connect.grpc.io.grpc.internal.SerializingExecutor.run(SerializingExecutor.java:133)
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
at java.lang.Thread.run(Thread.java:748)
/Users/hyukjin.kwon/workspace/forked/spark/python/pyspark/sql/connect/session.py:186:
UserWarning: [CANNOT_MODIFY_CONFIG] Cannot modify the value of the Spark
config: "spark.jars".
See also
'https://spark.apache.org/docs/latest/sql-migration-guide.html#ddl-statements'.
warnings.warn(str(e))
23/08/29 16:58:08 ERROR ErrorUtils: Spark Connect RPC error during: config.
UserId: hyukjin.kwon. SessionId: 5c331d52-bf65-4f1c-9416-899e00d4a7d9.
org.apache.spark.sql.AnalysisException: [CANNOT_MODIFY_CONFIG] Cannot
modify the value of the Spark config: "spark.jars".
See also
'https://spark.apache.org/docs/latest/sql-migration-guide.html#ddl-statements'.
at
org.apache.spark.sql.errors.QueryCompilationErrors$.cannotModifyValueOfSparkConfigError(QueryCompilationErrors.scala:3233)
at
org.apache.spark.sql.RuntimeConfig.requireNonStaticConf(RuntimeConfig.scala:166)
at org.apache.spark.sql.RuntimeConfig.set(RuntimeConfig.scala:42)
at
org.apache.spark.sql.connect.service.SparkConnectConfigHandler.$anonfun$handleSet$1(SparkConnectConfigHandler.scala:67)
at
org.apache.spark.sql.connect.service.SparkConnectConfigHandler.$anonfun$handleSet$1$adapted(SparkConnectConfigHandler.scala:65)
at scala.collection.Iterator.foreach(Iterator.scala:943)
at scala.collection.Iterator.foreach$(Iterator.scala:943)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1431)
at
org.apache.spark.sql.connect.service.SparkConnectConfigHandler.handleSet(SparkConnectConfigHandler.scala:65)
at
org.apache.spark.sql.connect.service.SparkConnectConfigHandler.handle(SparkConnectConfigHandler.scala:40)
at
org.apache.spark.sql.connect.service.SparkConnectService.config(SparkConnectService.scala:120)
at
org.apache.spark.connect.proto.SparkConnectServiceGrpc$MethodHandlers.invoke(SparkConnectServiceGrpc.java:751)
at
org.sparkproject.connect.grpc.io.grpc.stub.ServerCalls$UnaryServerCallHandler$UnaryServerCallListener.onHalfClose(ServerCalls.java:182)
at
org.sparkproject.connect.grpc.io.grpc.internal.ServerCallImpl$ServerStreamListenerImpl.halfClosed(ServerCallImpl.java:346)
at
org.sparkproject.connect.grpc.io.grpc.internal.ServerImpl$JumpToApplicationThreadServerStreamListener$1HalfClosed.runInContext(ServerImpl.java:860)
at
org.sparkproject.connect.grpc.io.grpc.internal.ContextRunnable.run(ContextRunnable.java:37)
at
org.sparkproject.connect.grpc.io.grpc.internal.SerializingExecutor.run(SerializingExecutor.java:133)
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
at java.lang.Thread.run(Thread.java:748)
```
### Does this PR introduce _any_ user-facing change?
No, the original change has not been released out yet.
### How was this patch tested?
Manually tested as described above.
### Was this patch authored or co-authored using generative AI tooling?
No
Closes #42718 from HyukjinKwon/SPARK-44981-followup.
Authored-by: Hyukjin Kwon <gurwls...@apache.org>
Signed-off-by: Hyukjin Kwon <gurwls...@apache.org>
---
python/pyspark/sql/connect/session.py | 13 +++++++------
1 file changed, 7 insertions(+), 6 deletions(-)
diff --git a/python/pyspark/sql/connect/session.py
b/python/pyspark/sql/connect/session.py
index 6c01aad06c0..c326f94d80c 100644
--- a/python/pyspark/sql/connect/session.py
+++ b/python/pyspark/sql/connect/session.py
@@ -885,12 +885,13 @@ class SparkSession:
SparkContext.getOrCreate(create_conf(loadDefaults=True,
_jvm=SparkContext._jvm))
)
- # Lastly remove all static configurations that are not allowed
to set in the regular
- # Spark Connect session.
- jvm = SparkContext._jvm
- utl = jvm.org.apache.spark.sql.api.python.PythonSQLUtils #
type: ignore[union-attr]
- for conf_set in utl.listStaticSQLConfigs():
- opts.pop(conf_set._1(), None)
+ # Lastly only keep runtime configurations because other
configurations are
+ # disallowed to set in the regular Spark Connect session.
+ utl = SparkContext._jvm.PythonSQLUtils # type:
ignore[union-attr]
+ runtime_conf_keys = [c._1() for c in
utl.listRuntimeSQLConfigs()]
+ new_opts = {k: opts[k] for k in opts if k in runtime_conf_keys}
+ opts.clear()
+ opts.update(new_opts)
finally:
if origin_remote is not None:
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org
For additional commands, e-mail: commits-h...@spark.apache.org
