[
https://issues.apache.org/jira/browse/FLINK-8439?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16558271#comment-16558271
]
ASF GitHub Bot commented on FLINK-8439:
---------------------------------------
aljoscha commented on a change in pull request #6405: [FLINK-8439] Add Flink
shading to AWS credential provider s3 hadoop c…
URL: https://github.com/apache/flink/pull/6405#discussion_r205442551
##########
File path:
flink-filesystems/flink-hadoop-fs/src/main/java/org/apache/flink/runtime/fs/hdfs/HadoopConfigLoader.java
##########
@@ -0,0 +1,134 @@
+/*
+ * 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.flink.runtime.fs.hdfs;
+
+import org.apache.flink.configuration.Configuration;
+import org.apache.flink.runtime.util.HadoopUtils;
+
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+
+import javax.annotation.Nonnull;
+
+import java.util.Collections;
+import java.util.HashSet;
+import java.util.Set;
+
+/** This class lazily loads hadoop configuration from resettable Flink's
configuration. */
+public class HadoopConfigLoader {
+ private static final Logger LOG =
LoggerFactory.getLogger(HadoopConfigLoader.class);
+
+ private static final Set<String> PACKAGE_PREFIXES_TO_SHADE =
+ new HashSet<>(Collections.singletonList("com.amazonaws."));
+
+ /** The prefixes that Flink adds to the Hadoop fs config. */
+ private final String[] flinkConfigPrefixes;
+
+ /** Keys that are replaced (after prefix replacement, to give a more
uniform experience
+ * across different file system implementations. */
+ private final String[][] mirroredConfigKeys;
+
+ /** Hadoop config prefix to replace Flink prefix. */
+ private final String hadoopConfigPrefix;
+
+ private final Set<String> configKeysToShade;
+ private final String flinkShadingPrefix;
+
+ /** Flink's configuration object. */
+ private Configuration flinkConfig;
+
+ /** Hadoop's configuration for the file systems, lazily initialized. */
+ private org.apache.hadoop.conf.Configuration hadoopConfig;
+
+ public HadoopConfigLoader(
+ @Nonnull String[] flinkConfigPrefixes,
+ @Nonnull String[][] mirroredConfigKeys,
+ @Nonnull String hadoopConfigPrefix,
+ @Nonnull Set<String> configKeysToShade,
+ @Nonnull String flinkShadingPrefix) {
+ this.flinkConfigPrefixes = flinkConfigPrefixes;
+ this.mirroredConfigKeys = mirroredConfigKeys;
+ this.hadoopConfigPrefix = hadoopConfigPrefix;
+ this.configKeysToShade = configKeysToShade;
+ this.flinkShadingPrefix = flinkShadingPrefix;
+ }
+
+ public void setFlinkConfig(Configuration config) {
+ flinkConfig = config;
+ hadoopConfig = null;
+ }
+
+ /** get the loaded Hadoop config (or fall back to one loaded from the
classpath). */
+ public org.apache.hadoop.conf.Configuration getOrLoadHadoopConfig() {
+ org.apache.hadoop.conf.Configuration hadoopConfig =
this.hadoopConfig;
+ if (hadoopConfig == null) {
+ if (flinkConfig != null) {
+ hadoopConfig =
mirrorCertianHadoopConfig(loadHadoopConfigFromFlink());
+ }
+ else {
+ LOG.warn("The factory has not been configured
prior to loading the S3 file system."
+ + " Using Hadoop configuration from the
classpath.");
+ hadoopConfig = new
org.apache.hadoop.conf.Configuration();
+ }
+ }
+ this.hadoopConfig = hadoopConfig;
+ return hadoopConfig;
+ }
+
+ // add additional config entries from the Flink config to the Hadoop
config
+ private org.apache.hadoop.conf.Configuration
loadHadoopConfigFromFlink() {
+ org.apache.hadoop.conf.Configuration hadoopConfig =
HadoopUtils.getHadoopConfiguration(flinkConfig);
+ for (String key : flinkConfig.keySet()) {
+ for (String prefix : flinkConfigPrefixes) {
+ if (key.startsWith(prefix)) {
+ String value =
flinkConfig.getString(key, null);
+ String newKey = hadoopConfigPrefix +
key.substring(prefix.length());
+ String newValue = fixHadoopConfig(key,
flinkConfig.getString(key, null));
+ hadoopConfig.set(newKey, newValue);
+
+ LOG.debug("Adding Flink config entry
for {} as {}={} to Hadoop config", key, newKey, value);
+ }
+ }
+ }
+ return hadoopConfig;
+ }
+
+ // mirror certain keys to make use more uniform across implementations
+ // with different keys
+ private org.apache.hadoop.conf.Configuration mirrorCertianHadoopConfig(
Review comment:
typo `Certian` -> `Certain`
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
> Document using a custom AWS Credentials Provider with flink-3s-fs-hadoop
> ------------------------------------------------------------------------
>
> Key: FLINK-8439
> URL: https://issues.apache.org/jira/browse/FLINK-8439
> Project: Flink
> Issue Type: Improvement
> Components: Documentation
> Reporter: Dyana Rose
> Assignee: Andrey Zagrebin
> Priority: Critical
> Labels: pull-request-available
> Fix For: 1.4.3, 1.5.3
>
>
> This came up when using the s3 for the file system backend and running under
> ECS.
> With no credentials in the container, hadoop-aws will default to EC2 instance
> level credentials when accessing S3. However when running under ECS, you will
> generally want to default to the task definition's IAM role.
> In this case you need to set the hadoop property
> {code:java}
> fs.s3a.aws.credentials.provider{code}
> to a fully qualified class name(s). see [hadoop-aws
> docs|https://github.com/apache/hadoop/blob/1ba491ff907fc5d2618add980734a3534e2be098/hadoop-tools/hadoop-aws/src/site/markdown/tools/hadoop-aws/index.md]
> This works as expected when you add this setting to flink-conf.yaml but there
> is a further 'gotcha.' Because the AWS sdk is shaded, the actual full class
> name for, in this case, the ContainerCredentialsProvider is
> {code:java}
> org.apache.flink.fs.s3hadoop.shaded.com.amazonaws.auth.ContainerCredentialsProvider{code}
>
> meaning the full setting is:
> {code:java}
> fs.s3a.aws.credentials.provider:
> org.apache.flink.fs.s3hadoop.shaded.com.amazonaws.auth.ContainerCredentialsProvider{code}
> If you instead set it to the unshaded class name you will see a very
> confusing error stating that the ContainerCredentialsProvider doesn't
> implement AWSCredentialsProvider (which it most certainly does.)
> Adding this information (how to specify alternate Credential Providers, and
> the name space gotcha) to the [AWS deployment
> docs|https://ci.apache.org/projects/flink/flink-docs-release-1.4/ops/deployment/aws.html]
> would be useful to anyone else using S3.
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
