mirror of
https://github.com/apache/impala.git
synced 2026-01-20 21:01:42 -05:00
ac87278b16
Add the -d option and -f option to the following commands: `hdfs dfs -copyFromLocal <localsrc> URI` `hdfs dfs -put [ - | <localsrc1> .. ]. <dst>` `hdfs dfs -cp URI [URI ...] <dest>` The -d option "Skip[s] creation of temporary file with the suffix ._COPYING_." which improves performance of these commands on S3 since S3 does not support metadata only renames. The -f option "Overwrites the destination if it already exists" combined with HADOOP-13884 this improves issues seen with S3 consistency issues by avoiding a HEAD request to check if the destination file exists or not. Added the method 'copy_from_local' to the BaseFilesystem class. Re-factored most usages of the aforementioned HDFS commands to use the filesystem_client. Some usages were not appropriate / worth refactoring, so occasionally this patch just adds the '-d' and '-f' options explicitly. All calls to '-put' were replaced with 'copyFromLocal' because they both copy files from the local fs to a HDFS compatible target fs. Since WebHDFS does not have good support for copying files, this patch removes the copy functionality from the PyWebHdfsClientWithChmod. Re-factored the hdfs_client so that it uses a DelegatingHdfsClient that delegates to either the HadoopFsCommandLineClient or PyWebHdfsClientWithChmod. Testing: * Ran core tests on HDFS and S3 Change-Id: I0d45db1c00554e6fb6bcc0b552596d86d4e30144 Reviewed-on: http://gerrit.cloudera.org:8080/14311 Reviewed-by: Impala Public Jenkins <impala-public-jenkins@cloudera.com> Tested-by: Impala Public Jenkins <impala-public-jenkins@cloudera.com>
68 lines
3.0 KiB
Python
68 lines
3.0 KiB
Python
# 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.
|
|
|
|
# Validates table stored on the LocalFileSystem.
|
|
#
|
|
import pytest
|
|
from subprocess import check_call, call
|
|
|
|
from tests.common.impala_test_suite import ImpalaTestSuite
|
|
from tests.common.skip import SkipIf
|
|
from tests.common.test_dimensions import create_single_exec_option_dimension
|
|
from tests.util.filesystem_utils import get_secondary_fs_path
|
|
|
|
@SkipIf.no_secondary_fs
|
|
class TestMultipleFilesystems(ImpalaTestSuite):
|
|
"""
|
|
Tests that tables and queries can span multiple filesystems.
|
|
"""
|
|
|
|
@classmethod
|
|
def get_workload(self):
|
|
return 'functional-query'
|
|
|
|
@classmethod
|
|
def add_test_dimensions(cls):
|
|
super(TestMultipleFilesystems, cls).add_test_dimensions()
|
|
cls.ImpalaTestMatrix.add_dimension(create_single_exec_option_dimension())
|
|
|
|
cls.ImpalaTestMatrix.add_constraint(lambda v:\
|
|
v.get_value('table_format').file_format == 'text' and \
|
|
v.get_value('table_format').compression_codec == 'none')
|
|
|
|
def _populate_secondary_fs_partitions(self, db_name):
|
|
# This directory may already exist. So we needn't mind if this call fails.
|
|
call(["hadoop", "fs", "-mkdir", get_secondary_fs_path("/multi_fs_tests/")], shell=False)
|
|
check_call(["hadoop", "fs", "-mkdir",
|
|
get_secondary_fs_path("/multi_fs_tests/%s.db/" % db_name)], shell=False)
|
|
self.filesystem_client.copy("/test-warehouse/alltypes_parquet/",
|
|
get_secondary_fs_path("/multi_fs_tests/%s.db/" % db_name), overwrite=True)
|
|
self.filesystem_client.copy("/test-warehouse/tinytable/", get_secondary_fs_path(
|
|
"/multi_fs_tests/%s.db/" % db_name), overwrite=True)
|
|
|
|
@pytest.mark.execute_serially
|
|
def test_multiple_filesystems(self, vector, unique_database):
|
|
try:
|
|
self._populate_secondary_fs_partitions(unique_database)
|
|
self.run_test_case('QueryTest/multiple-filesystems', vector, use_db=unique_database)
|
|
finally:
|
|
# We delete this from the secondary filesystem here because the database was created
|
|
# in HDFS but the queries will create this path in the secondary FS as well. So
|
|
# dropping the database will not delete the directory in the secondary FS.
|
|
check_call(["hadoop", "fs", "-rm", "-r",
|
|
get_secondary_fs_path("/multi_fs_tests/%s.db/" % unique_database)], shell=False)
|