-
Notifications
You must be signed in to change notification settings - Fork 28.6k
[SPARK-29331][SQL] create DS v2 Write at physical plan #26001
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Closed
Closed
Changes from all commits
Commits
Show all changes
2 commits
Select commit
Hold shift + click to select a range
File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
69 changes: 69 additions & 0 deletions
69
...core/src/main/scala/org/apache/spark/sql/execution/streaming/BaseStreamingWriteExec.scala
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,69 @@ | ||
| /* | ||
| * Licensed to the Apache Software Foundation (ASF) under one or more | ||
| * contributor license agreements. See the NOTICE file distributed with | ||
| * this work for additional information regarding copyright ownership. | ||
| * The ASF licenses this file to You under the Apache License, Version 2.0 | ||
| * (the "License"); you may not use this file except in compliance with | ||
| * the License. You may obtain a copy of the License at | ||
| * | ||
| * http://www.apache.org/licenses/LICENSE-2.0 | ||
| * | ||
| * Unless required by applicable law or agreed to in writing, software | ||
| * distributed under the License is distributed on an "AS IS" BASIS, | ||
| * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. | ||
| * See the License for the specific language governing permissions and | ||
| * limitations under the License. | ||
| */ | ||
|
|
||
| package org.apache.spark.sql.execution.streaming | ||
|
|
||
| import scala.collection.JavaConverters._ | ||
|
|
||
| import org.apache.spark.sql.catalyst.expressions.Attribute | ||
| import org.apache.spark.sql.catalyst.streaming.InternalOutputModes.{Append, Complete, Update} | ||
| import org.apache.spark.sql.connector.catalog.SupportsWrite | ||
| import org.apache.spark.sql.connector.write.SupportsTruncate | ||
| import org.apache.spark.sql.execution.{SparkPlan, UnaryExecNode} | ||
| import org.apache.spark.sql.streaming.OutputMode | ||
| import org.apache.spark.sql.types.StructType | ||
| import org.apache.spark.sql.util.CaseInsensitiveStringMap | ||
| import org.apache.spark.util.Utils | ||
|
|
||
| trait BaseStreamingWriteExec extends UnaryExecNode { | ||
| def table: SupportsWrite | ||
| def query: SparkPlan | ||
| def queryId: String | ||
| def querySchema: StructType | ||
| def outputMode: OutputMode | ||
| def options: Map[String, String] | ||
|
|
||
| override def child: SparkPlan = query | ||
| override def output: Seq[Attribute] = Nil | ||
|
|
||
| protected lazy val inputRDD = query.execute() | ||
| lazy val streamWrite = { | ||
| val writeBuilder = table.newWriteBuilder(new CaseInsensitiveStringMap(options.asJava)) | ||
| .withQueryId(queryId) | ||
| .withInputDataSchema(querySchema) | ||
| outputMode match { | ||
| case Append => | ||
| writeBuilder.buildForStreaming() | ||
|
|
||
| case Complete => | ||
| // TODO: we should do this check earlier when we have capability API. | ||
| require(writeBuilder.isInstanceOf[SupportsTruncate], | ||
| table.name + " does not support Complete mode.") | ||
| writeBuilder.asInstanceOf[SupportsTruncate].truncate().buildForStreaming() | ||
|
|
||
| case Update => | ||
| // Although no v2 sinks really support Update mode now, but during tests we do want them | ||
| // to pretend to support Update mode, and treat Update mode same as Append mode. | ||
| if (Utils.isTesting) { | ||
| writeBuilder.buildForStreaming() | ||
| } else { | ||
| throw new IllegalArgumentException( | ||
| "Data source v2 streaming sinks does not support Update mode.") | ||
| } | ||
| } | ||
| } | ||
| } |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Now we check the options at the physical plan phase, so this should not be
AnalysisExceptionanymore.There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
If this is unacceptable, then we may need to have analysis time write info and runtime write info.
Table.newWriteBuildertakes analysis time write info andWriteBuilder.buildtakes runtime write info.I'm not sure if it's worth this complexity.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Should it be SparkException? I think the last time we discussed these, it wasn't clear what type of exception to use after analysis. Maybe we need new exception types?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
We can use
SparkExceptionas well.IllegalArgumentExceptionis a standard java exception which indicates invalid input, I think it's OK to use it even after analysis.There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I think we typically want to always raise SparkException because all exception types inherit from it. Unless we are throwing an exception from a method where there is an illegal argument, but that's not what is happening here.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
In Spark SQL no exceptions inherit from it. In fact SparkException was rarely used in Spark SQL before we adding the v2 commands.
SparkExceptionis defined in spark core and usually used when Spark fails to run a task.In Spark SQL, AnalysisException and standard Java exceptions are more widely used.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Sorry, I thought that AnalysisException inherited from SparkException. Looks like I was wrong.