big-data/hadoop
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

HADOOP-17343. Upgrade AWS SDK to 1.11.901 (#2468)

Browse Source 
Contributed by Steve Loughran.
This commit is contained in:
Steve Loughran 2020-11-23 14:08:12 +00:00
parent ced08fd87f
commit e4bc64cce0
3 changed files with 93 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
LICENSE-binary
View File

@ -215,7 +215,7 @@ com.aliyun:aliyun-java-sdk-ecs:4.2.0
com.aliyun:aliyun-java-sdk-ram:3.0.0
com.aliyun:aliyun-java-sdk-sts:3.0.0
com.aliyun.oss:aliyun-sdk-oss:3.4.1
com.amazonaws:aws-java-sdk-bundle:1.11.563
com.amazonaws:aws-java-sdk-bundle:1.11.901
com.cedarsoftware:java-util:1.9.0
com.cedarsoftware:json-io:2.5.1
com.fasterxml.jackson.core:jackson-annotations:2.9.9

2
hadoop-project/pom.xml
View File

@ -182,7 +182,7 @@
<exec-maven-plugin.version>1.3.1</exec-maven-plugin.version>
<make-maven-plugin.version>1.0-beta-1</make-maven-plugin.version>
<surefire.fork.timeout>900</surefire.fork.timeout>
<aws-java-sdk.version>1.11.563</aws-java-sdk.version>
<aws-java-sdk.version>1.11.901</aws-java-sdk.version>
<hsqldb.version>2.3.4</hsqldb.version>
<frontend-maven-plugin.version>1.6</frontend-maven-plugin.version>
<jasmine-maven-plugin.version>2.1</jasmine-maven-plugin.version>

100
hadoop-tools/hadoop-aws/src/site/markdown/tools/hadoop-aws/testing.md
View File

@ -1499,36 +1499,69 @@ export HADOOP_OPTIONAL_TOOLS="hadoop-aws"
Run some basic s3guard commands as well as file operations.
```bash
export BUCKET=s3a://example-bucket-name
export BUCKETNAME=example-bucket-name
export BUCKET=s3a://$BUCKETNAME
bin/hadoop s3guard bucket-info $BUCKET
bin/hadoop s3guard set-capacity $BUCKET
bin/hadoop s3guard set-capacity -read 15 -write 15 $BUCKET
bin/hadoop s3guard uploads $BUCKET
# repeat twice, once with "no" and once with "yes" as responses
bin/hadoop s3guard uploads -abort $BUCKET
# ---------------------------------------------------
# assuming s3guard is enabled
# if on pay-by-request, expect an error message and exit code of -1
bin/hadoop s3guard set-capacity $BUCKET
# skip for PAY_PER_REQUEST
bin/hadoop s3guard set-capacity -read 15 -write 15 $BUCKET
bin/hadoop s3guard bucket-info -guarded $BUCKET
bin/hadoop s3guard diff $BUCKET/
bin/hadoop s3guard prune -minutes 10 $BUCKET/
bin/hadoop s3guard import $BUCKET/
bin/hadoop s3guard import -verbose $BUCKET/
bin/hadoop s3guard authoritative -verbose $BUCKET
# ---------------------------------------------------
# root filesystem operatios
# ---------------------------------------------------
bin/hadoop fs -ls $BUCKET/
# assuming file is not yet created, expect error and status code of 1
bin/hadoop fs -ls $BUCKET/file
# exit code of 0 even when path doesn't exist
bin/hadoop fs -rm -R -f $BUCKET/dir-no-trailing
bin/hadoop fs -rm -R -f $BUCKET/dir-trailing/
# error because it is a directory
bin/hadoop fs -rm $BUCKET/
bin/hadoop fs -touchz $BUCKET/file
# expect I/O error as root dir is not empty
bin/hadoop fs -rm -r $BUCKET/
bin/hadoop fs -rm -r $BUCKET/\*
# now success
# expect I/O error as it is the root directory
bin/hadoop fs -rm -r $BUCKET/
# succeeds
bin/hadoop fs -rm -r $BUCKET/\*
# ---------------------------------------------------
# File operations
# ---------------------------------------------------
bin/hadoop fs -mkdir $BUCKET/dir-no-trailing
# fails with S3Guard
# used to fail with S3Guard
bin/hadoop fs -mkdir $BUCKET/dir-trailing/
bin/hadoop fs -touchz $BUCKET/file
bin/hadoop fs -ls $BUCKET/
bin/hadoop fs -mv $BUCKET/file $BUCKET/file2
# expect "No such file or directory"
bin/hadoop fs -stat $BUCKET/file
# expect success
bin/hadoop fs -stat $BUCKET/file2
# expect "file exists"
bin/hadoop fs -mkdir $BUCKET/dir-no-trailing
bin/hadoop fs -mv $BUCKET/file2 $BUCKET/dir-no-trailing
bin/hadoop fs -stat $BUCKET/dir-no-trailing/file2
@ -1545,8 +1578,57 @@ bin/hadoop fs -checksum $BUCKET/dir-no-trailing/file2
# expect "etag" + a long string
bin/hadoop fs -D fs.s3a.etag.checksum.enabled=true -checksum $BUCKET/dir-no-trailing/file2
bin/hadoop fs -expunge -immediate -fs $BUCKET
# ---------------------------------------------------
# Delegation Token support
# ---------------------------------------------------
# failure unless delegation tokens are enabled
bin/hdfs fetchdt --webservice $BUCKET secrets.bin
# success
bin/hdfs fetchdt -D fs.s3a.delegation.token.binding=org.apache.hadoop.fs.s3a.auth.delegation.SessionTokenBinding --webservice $BUCKET secrets.bin
bin/hdfs fetchdt -print secrets.bin
# expect warning "No TokenRenewer defined for token kind S3ADelegationToken/Session"
bin/hdfs fetchdt -renew secrets.bin
# ---------------------------------------------------
# Directory markers
# ---------------------------------------------------
# require success
bin/hadoop s3guard bucket-info -markers aware $BUCKET
# expect failure unless bucket policy is keep
bin/hadoop s3guard bucket-info -markers keep $BUCKET/path
# you may need to set this on a per-bucket basis if you have already been
# playing with options
bin/hadoop s3guard -D fs.s3a.directory.marker.retention=keep bucket-info -markers keep $BUCKET/path
bin/hadoop s3guard -D fs.s3a.bucket.$BUCKETNAME.directory.marker.retention=keep bucket-info -markers keep $BUCKET/path
# expect to see "Directory markers will be kept" messages and status code of "46"
bin/hadoop fs -D fs.s3a.bucket.$BUCKETNAME.directory.marker.retention=keep -mkdir $BUCKET/p1
bin/hadoop fs -D fs.s3a.bucket.$BUCKETNAME.directory.marker.retention=keep -mkdir $BUCKET/p1/p2
bin/hadoop fs -D fs.s3a.bucket.$BUCKETNAME.directory.marker.retention=keep -touchz $BUCKET/p1/p2/file
# expect failure as markers will be found for /p1/ and /p1/p2/
bin/hadoop s3guard markers -audit -verbose $BUCKET
# clean will remove markers
bin/hadoop s3guard markers -clean -verbose $BUCKET
# expect success and exit code of 0
bin/hadoop s3guard markers -audit -verbose $BUCKET
# ---------------------------------------------------
# S3 Select on Landsat
# ---------------------------------------------------
export LANDSATGZ=s3a://landsat-pds/scene_list.gz
bin/hadoop s3guard select -header use -compression gzip $LANDSATGZ \
"SELECT s.entityId,s.cloudCover FROM S3OBJECT s WHERE s.cloudCover < '0.0' LIMIT 100"
```
### Other tests