pingsutw commented on code in PR #989:
URL: https://github.com/apache/submarine/pull/989#discussion_r952131883


##########
submarine-experiment-prehandler/fs_prehandler/hdfs_prehandler.py:
##########
@@ -15,26 +15,39 @@
 
 import logging
 import os
+import subprocess
 
 from fs_prehandler import FsPreHandler
 from fsspec.implementations.arrow import HadoopFileSystem
 
 class HDFSPreHandler(FsPreHandler):
     def __init__(self):
         self.hdfs_host=os.environ['HDFS_HOST']
-        self.hdfs_port=int(os.environ['HDFS_PORT'])
+        self.hdfs_port=os.environ['HDFS_PORT']
         self.hdfs_source=os.environ['HDFS_SOURCE']
         self.dest_path=os.environ['DEST_PATH']
         self.enable_kerberos=os.environ['ENABLE_KERBEROS']
+        self.hadoop_home=os.environ['HADOOP_HOME']
+        self.dest_minio_host=os.environ['DEST_MINIO_HOST']
+        self.dest_minio_port=os.environ['DEST_MINIO_PORT']
+        self.minio_access_key=os.environ['MINIO_ACCESS_KEY']
+        self.minio_secert_key=os.environ['MINIO_SECRET_KEY']
 
         logging.info('HDFS_HOST:%s' % self.hdfs_host)
-        logging.info('HDFS_PORT:%d' % self.hdfs_port)
+        logging.info('HDFS_PORT:%s' % self.hdfs_port)
         logging.info('HDFS_SOURCE:%s' % self.hdfs_source)
+        logging.info('MINIO_DEST_HOST:%s' % self.dest_minio_host)
+        logging.info('MINIO_DEST_PORT:%s' % self.dest_minio_port)
         logging.info('DEST_PATH:%s' % self.dest_path)
         logging.info('ENABLE_KERBEROS:%s' % self.enable_kerberos)
 
-        self.fs = HadoopFileSystem(host=self.hdfs_host, port=self.hdfs_port)
-
     def process(self):
-        self.fs.get(self.hdfs_source, self.dest_path, recursive=True)
+
+        p = subprocess.run([self.hadoop_home+'/bin/hadoop', 'distcp'
+            , '-Dfs.s3a.endpoint=http://' + self.dest_minio_host + ':' + 
self.dest_minio_port + '/'

Review Comment:
   related to https://issues.apache.org/jira/browse/HADOOP-12963



-- 
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.

To unsubscribe, e-mail: [email protected]

For queries about this service, please contact Infrastructure at:
[email protected]

Reply via email to