[GitHub] [druid] jihoonson commented on a change in pull request #9375: Add support for optional cloud (aws, gcs, etc.) credentials for s3 for ingestion

[GitBox <gi...@apache.org>]

jihoonson commented on a change in pull request #9375: Add support for optional cloud (aws, gcs, etc.) credentials for s3 for ingestion
URL: https://github.com/apache/druid/pull/9375#discussion_r383538927
 
 

 ##########
 File path: extensions-core/s3-extensions/src/main/java/org/apache/druid/data/input/s3/S3InputSource.java
 ##########
 @@ -19,50 +19,88 @@
 
 package org.apache.druid.data.input.s3;
 
+import com.amazonaws.auth.AWSStaticCredentialsProvider;
+import com.amazonaws.auth.BasicAWSCredentials;
+import com.amazonaws.services.s3.AmazonS3ClientBuilder;
 import com.amazonaws.services.s3.model.S3ObjectSummary;
 import com.fasterxml.jackson.annotation.JacksonInject;
 import com.fasterxml.jackson.annotation.JsonCreator;
 import com.fasterxml.jackson.annotation.JsonProperty;
 import com.google.common.base.Preconditions;
+import com.google.common.base.Supplier;
+import com.google.common.base.Suppliers;
 import com.google.common.collect.ImmutableList;
 import org.apache.druid.data.input.InputSplit;
 import org.apache.druid.data.input.impl.CloudObjectInputSource;
 import org.apache.druid.data.input.impl.CloudObjectLocation;
+import org.apache.druid.data.input.impl.S3ConfigProperties;
 import org.apache.druid.data.input.impl.SplittableInputSource;
 import org.apache.druid.storage.s3.S3InputDataConfig;
+import org.apache.druid.storage.s3.S3StorageConfig;
 import org.apache.druid.storage.s3.S3StorageDruidModule;
 import org.apache.druid.storage.s3.S3Utils;
 import org.apache.druid.storage.s3.ServerSideEncryptingAmazonS3;
 
 import javax.annotation.Nullable;
 import java.net.URI;
 import java.util.List;
+import java.util.Objects;
 import java.util.stream.Stream;
 import java.util.stream.StreamSupport;
 
 public class S3InputSource extends CloudObjectInputSource<S3Entity>
 {
-  private final ServerSideEncryptingAmazonS3 s3Client;
+  // We lazily initialize s3Client to avoid costly s3 operation when we only need S3InputSource for stored information
+  // (such as for task logs) and not for ingestion. (This cost only applies for new s3Client created with
+  // s3ConfigProperties given).
+  private final Supplier<ServerSideEncryptingAmazonS3> s3Client;
 
 Review comment:
   nit: suggest `s3ClientSupplier`.

----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
 
For queries about this service, please contact Infrastructure at:
users@infra.apache.org


With regards,
Apache Git Services

---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@druid.apache.org
For additional commands, e-mail: commits-help@druid.apache.org