You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@flink.apache.org by ch...@apache.org on 2022/11/14 14:28:45 UTC

[flink] branch master updated: [FLINK-28165][yarn] Inline 'include_hadoop_aws' profile

This is an automated email from the ASF dual-hosted git repository.

chesnay pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/flink.git


The following commit(s) were added to refs/heads/master by this push:
     new 79870d10794 [FLINK-28165][yarn] Inline 'include_hadoop_aws' profile
79870d10794 is described below

commit 79870d10794bd3be384debcdecd2bf080c274ee8
Author: Chesnay Schepler <ch...@apache.org>
AuthorDate: Fri Nov 11 13:19:49 2022 +0100

    [FLINK-28165][yarn] Inline 'include_hadoop_aws' profile
---
 azure-pipelines.yml                                |   4 +-
 flink-yarn/pom.xml                                 | 116 +++++++++------------
 .../flink/yarn/YarnFileStageTestS3ITCase.java      |  26 -----
 tools/azure-pipelines/build-apache-repo.yml        |  12 +--
 4 files changed, 58 insertions(+), 100 deletions(-)

diff --git a/azure-pipelines.yml b/azure-pipelines.yml
index 557f9db7145..a62e5f8d07e 100644
--- a/azure-pipelines.yml
+++ b/azure-pipelines.yml
@@ -77,7 +77,7 @@ stages:
             vmImage: 'ubuntu-20.04'
           e2e_pool_definition:
             vmImage: 'ubuntu-20.04'
-          environment: PROFILE="-Dflink.hadoop.version=2.8.5 -Dinclude_hadoop_aws -Dscala-2.12"
+          environment: PROFILE="-Dflink.hadoop.version=2.8.5 -Dscala-2.12"
           run_end_to_end: false
           container: flink-build-container
           jdk: 8
@@ -97,5 +97,5 @@ stages:
       - template: tools/azure-pipelines/build-python-wheels.yml
         parameters:
           stage_name: cron_python_wheels
-          environment: PROFILE="-Dflink.hadoop.version=2.8.5 -Dinclude_hadoop_aws -Dscala-2.12"
+          environment: PROFILE="-Dflink.hadoop.version=2.8.5 -Dscala-2.12"
           container: flink-build-container
diff --git a/flink-yarn/pom.xml b/flink-yarn/pom.xml
index 333aa243beb..1583a851ece 100644
--- a/flink-yarn/pom.xml
+++ b/flink-yarn/pom.xml
@@ -129,73 +129,57 @@ under the License.
 				</exclusion>
 			</exclusions>
 		</dependency>
-	</dependencies>
 
-	<profiles>
-		<profile>
-			<!-- Hadoop >= 2.6 moved the S3 file systems from hadoop-common into hadoop-aws artifact
-				(see https://issues.apache.org/jira/browse/HADOOP-11074)
-				We can add the (test) dependency per default once 2.6 is the minimum required version.
-			-->
-			<id>include_hadoop_aws</id>
-			<activation>
-				<property>
-					<name>include_hadoop_aws</name>
-				</property>
-			</activation>
-			<dependencies>
-				<!-- for the S3 tests of YarnFileStageTestS3ITCase -->
-				<dependency>
-					<groupId>org.apache.hadoop</groupId>
-					<artifactId>hadoop-aws</artifactId>
-					<version>${flink.hadoop.version}</version>
-					<scope>test</scope>
-					<exclusions>
-						<exclusion>
-							<groupId>log4j</groupId>
-							<artifactId>log4j</artifactId>
-						</exclusion>
-						<exclusion>
-							<groupId>org.slf4j</groupId>
-							<artifactId>slf4j-log4j12</artifactId>
-						</exclusion>
-						<exclusion>
-							<groupId>org.apache.avro</groupId>
-							<artifactId>avro</artifactId>
-						</exclusion>
-						<!-- The aws-java-sdk-core requires jackson 2.6, but
-							hadoop pulls in 2.3 -->
-						<exclusion>
-							<groupId>com.fasterxml.jackson.core</groupId>
-							<artifactId>jackson-annotations</artifactId>
-						</exclusion>
-						<exclusion>
-							<groupId>com.fasterxml.jackson.core</groupId>
-							<artifactId>jackson-core</artifactId>
-						</exclusion>
-						<exclusion>
-							<groupId>com.fasterxml.jackson.core</groupId>
-							<artifactId>jackson-databind</artifactId>
-						</exclusion>
-					</exclusions>
-				</dependency>
-				<!-- override Hadoop's default dependency on too low SDK versions that do not work
-					with our httpcomponents version when initialising the s3a file system -->
-				<dependency>
-					<groupId>com.amazonaws</groupId>
-					<artifactId>aws-java-sdk-s3</artifactId>
-					<version>${aws.sdk.version}</version>
-					<scope>test</scope>
-				</dependency>
-				<dependency>
-					<groupId>com.amazonaws</groupId>
-					<artifactId>aws-java-sdk-sts</artifactId>
-					<version>${aws.sdk.version}</version>
-					<scope>test</scope>
-				</dependency>
-			</dependencies>
-		</profile>
-	</profiles>
+		<!-- for the S3 tests of YarnFileStageTestS3ITCase -->
+		<dependency>
+			<groupId>org.apache.hadoop</groupId>
+			<artifactId>hadoop-aws</artifactId>
+			<version>${flink.hadoop.version}</version>
+			<scope>test</scope>
+			<exclusions>
+				<exclusion>
+					<groupId>log4j</groupId>
+					<artifactId>log4j</artifactId>
+				</exclusion>
+				<exclusion>
+					<groupId>org.slf4j</groupId>
+					<artifactId>slf4j-log4j12</artifactId>
+				</exclusion>
+				<exclusion>
+					<groupId>org.apache.avro</groupId>
+					<artifactId>avro</artifactId>
+				</exclusion>
+				<!-- The aws-java-sdk-core requires jackson 2.6, but
+					hadoop pulls in 2.3 -->
+				<exclusion>
+					<groupId>com.fasterxml.jackson.core</groupId>
+					<artifactId>jackson-annotations</artifactId>
+				</exclusion>
+				<exclusion>
+					<groupId>com.fasterxml.jackson.core</groupId>
+					<artifactId>jackson-core</artifactId>
+				</exclusion>
+				<exclusion>
+					<groupId>com.fasterxml.jackson.core</groupId>
+					<artifactId>jackson-databind</artifactId>
+				</exclusion>
+			</exclusions>
+		</dependency>
+		<!-- override Hadoop's default dependency on too low SDK versions that do not work
+			with our httpcomponents version when initialising the s3a file system -->
+		<dependency>
+			<groupId>com.amazonaws</groupId>
+			<artifactId>aws-java-sdk-s3</artifactId>
+			<version>${aws.sdk.version}</version>
+			<scope>test</scope>
+		</dependency>
+		<dependency>
+			<groupId>com.amazonaws</groupId>
+			<artifactId>aws-java-sdk-sts</artifactId>
+			<version>${aws.sdk.version}</version>
+			<scope>test</scope>
+		</dependency>
+	</dependencies>
 
 	<build>
 		<plugins>
diff --git a/flink-yarn/src/test/java/org/apache/flink/yarn/YarnFileStageTestS3ITCase.java b/flink-yarn/src/test/java/org/apache/flink/yarn/YarnFileStageTestS3ITCase.java
index de576418d15..d323e35aeb4 100644
--- a/flink-yarn/src/test/java/org/apache/flink/yarn/YarnFileStageTestS3ITCase.java
+++ b/flink-yarn/src/test/java/org/apache/flink/yarn/YarnFileStageTestS3ITCase.java
@@ -34,8 +34,6 @@ import org.junit.jupiter.api.BeforeAll;
 import org.junit.jupiter.api.TestTemplate;
 import org.junit.jupiter.api.extension.ExtendWith;
 import org.junit.jupiter.api.io.TempDir;
-import org.slf4j.Logger;
-import org.slf4j.LoggerFactory;
 
 import java.io.File;
 import java.io.FileOutputStream;
@@ -46,7 +44,6 @@ import java.util.HashMap;
 import java.util.Map;
 import java.util.UUID;
 
-import static org.assertj.core.api.Assertions.assertThat;
 import static org.assertj.core.api.Assumptions.assumeThat;
 import static org.assertj.core.api.Assumptions.assumeThatThrownBy;
 
@@ -59,23 +56,13 @@ import static org.assertj.core.api.Assumptions.assumeThatThrownBy;
 @ExtendWith(RetryExtension.class)
 class YarnFileStageTestS3ITCase {
 
-    private static final Logger log = LoggerFactory.getLogger(YarnFileStageTestS3ITCase.class);
-
     private static final String TEST_DATA_DIR = "tests-" + UUID.randomUUID();
 
-    /** Number of tests executed. */
-    private static int numRecursiveUploadTests = 0;
-
-    /** Will be updated by {@link #checkCredentialsAndSetup(File)} if the test is not skipped. */
-    private static boolean skipTest = true;
-
     @BeforeAll
     static void checkCredentialsAndSetup(@TempDir File tempFolder) throws IOException {
         // check whether credentials exist
         S3TestCredentials.assumeCredentialsAvailable();
 
-        skipTest = false;
-
         setupCustomHadoopConfig(tempFolder);
     }
 
@@ -84,18 +71,6 @@ class YarnFileStageTestS3ITCase {
         FileSystem.initialize(new Configuration());
     }
 
-    @AfterAll
-    static void checkAtLeastOneTestRun() {
-        if (!skipTest) {
-            assertThat(numRecursiveUploadTests)
-                    .as(
-                            "No S3 filesystem upload test executed. Please activate the "
-                                    + "'include_hadoop_aws' build profile or set '-Dinclude_hadoop_aws' during build "
-                                    + "(Hadoop >= 2.6 moved S3 filesystems out of hadoop-common).")
-                    .isGreaterThan(0);
-        }
-    }
-
     /**
      * Create a Hadoop config file containing S3 access credentials.
      *
@@ -148,7 +123,6 @@ class YarnFileStageTestS3ITCase {
      */
     private void testRecursiveUploadForYarn(String scheme, String pathSuffix, File tempFolder)
             throws Exception {
-        ++numRecursiveUploadTests;
 
         final Path basePath =
                 new Path(S3TestCredentials.getTestBucketUriWithScheme(scheme) + TEST_DATA_DIR);
diff --git a/tools/azure-pipelines/build-apache-repo.yml b/tools/azure-pipelines/build-apache-repo.yml
index 5499a2d07b1..f84237a9bc0 100644
--- a/tools/azure-pipelines/build-apache-repo.yml
+++ b/tools/azure-pipelines/build-apache-repo.yml
@@ -70,7 +70,7 @@ stages:
             name: Default
           e2e_pool_definition:
             vmImage: 'ubuntu-20.04'
-          environment: PROFILE="-Dflink.hadoop.version=2.8.5 -Dinclude_hadoop_aws -Dscala-2.12"
+          environment: PROFILE="-Dflink.hadoop.version=2.8.5 -Dscala-2.12"
           run_end_to_end: false
           container: flink-build-container
           jdk: 8
@@ -114,7 +114,7 @@ stages:
             vmImage: 'ubuntu-20.04'
           e2e_pool_definition:
             vmImage: 'ubuntu-20.04'
-          environment: PROFILE="-Dflink.hadoop.version=2.8.5 -Dinclude_hadoop_aws -Dscala-2.12"
+          environment: PROFILE="-Dflink.hadoop.version=2.8.5 -Dscala-2.12"
           run_end_to_end: true
           container: flink-build-container
           jdk: 8
@@ -125,7 +125,7 @@ stages:
             name: Default
           e2e_pool_definition:
             vmImage: 'ubuntu-20.04'
-          environment: PROFILE="-Dinclude_hadoop_aws -Dflink.hadoop.version=3.1.3 -Phadoop3-tests,hive3"
+          environment: PROFILE="-Dflink.hadoop.version=3.1.3 -Phadoop3-tests,hive3"
           run_end_to_end: true
           container: flink-build-container
           jdk: 8
@@ -136,7 +136,7 @@ stages:
             name: Default
           e2e_pool_definition:
             vmImage: 'ubuntu-20.04'
-          environment: PROFILE="-Dflink.hadoop.version=2.8.5 -Dinclude_hadoop_aws -Dscala-2.12 -Djdk11 -Pjava11-target"
+          environment: PROFILE="-Dflink.hadoop.version=2.8.5 -Dscala-2.12 -Djdk11 -Pjava11-target"
           run_end_to_end: true
           container: flink-build-container
           jdk: 11
@@ -147,7 +147,7 @@ stages:
             name: Default
           e2e_pool_definition:
             vmImage: 'ubuntu-20.04'
-          environment: PROFILE="-Dflink.hadoop.version=2.8.5 -Dinclude_hadoop_aws -Dscala-2.12 -Penable-adaptive-scheduler"
+          environment: PROFILE="-Dflink.hadoop.version=2.8.5 -Dscala-2.12 -Penable-adaptive-scheduler"
           run_end_to_end: true
           container: flink-build-container
           jdk: 8
@@ -162,5 +162,5 @@ stages:
       - template: build-python-wheels.yml
         parameters:
           stage_name: cron_python_wheels
-          environment: PROFILE="-Dflink.hadoop.version=2.8.5 -Dinclude_hadoop_aws -Dscala-2.12"
+          environment: PROFILE="-Dflink.hadoop.version=2.8.5 -Dscala-2.12"
           container: flink-build-container