gistfile1.txt

3/01/31 15:23:00 INFO CodeGenerator: Code generated in 123.234953 ms
23/01/31 15:23:00 INFO CodeGenerator: Code generated in 10.748115 ms
23/01/31 15:23:00 INFO CodeGenerator: Code generated in 6.772988 ms
23/01/31 15:23:00 INFO CodeGenerator: Code generated in 10.096625 ms
23/01/31 15:23:01 WARN FileStreamSink: Assume no metadata directory. Error while looking for metadata directory in the path: s3://mybucket/lakefs/projects/testproject/_lakefs/retention/gc/uncommitted/<redacted>/uncommitted/.
org.apache.hadoop.fs.UnsupportedFileSystemException: No FileSystem for scheme "s3"
	at org.apache.hadoop.fs.FileSystem.getFileSystemClass(FileSystem.java:3443)
	at org.apache.hadoop.fs.FileSystem.createFileSystem(FileSystem.java:3466)
	at org.apache.hadoop.fs.FileSystem.access$300(FileSystem.java:174)
	at org.apache.hadoop.fs.FileSystem$Cache.getInternal(FileSystem.java:3574)
	at org.apache.hadoop.fs.FileSystem$Cache.get(FileSystem.java:3521)
	at org.apache.hadoop.fs.FileSystem.get(FileSystem.java:540)
	at org.apache.hadoop.fs.Path.getFileSystem(Path.java:365)

gistfile2.txt

./spark-3.3.1-bin-hadoop3/bin/spark-submit \
  --packages org.apache.hadoop:hadoop-aws:3.3.2 \
  --master spark://localhost:7077 \
  --class io.treeverse.gc.UncommittedGarbageCollector \
  -c spark.hadoop.lakefs.api.url=http://<lakefs instance>:8000/api/v1  \
  -c spark.hadoop.lakefs.api.access_key=<lakefs> \
  -c spark.hadoop.lakefs.api.secret_key=<lakefs> \
  -c spark.hadoop.fs.s3a.access.key=<aws> \
  -c spark.hadoop.fs.s3a.secret.key=<aws> \
  -c spark.hadoop.fs.s3a.session.token=<aws> \
  -c spark.hadoop.fs.s3a.endpoint=http://bucket.vpce-<reacted>-<redacted>.s3.us-gov-west-1.vpce.amazonaws.com \
  -c spark.hadoop.fs.s3a.endpoint.region=us-gov-west-1 \
  -c spark.hadoop.lakefs.gc.do_sweep=false \
  lakefs-spark-client-312-hadoop3-assembly-0.6.0.jar \
  testproject us-gov-west-1