Files
impala/tests/query_test/test_chars.py
Sailesh Mukil ed7f5ebf53 IMPALA-1878: Support INSERT and LOAD DATA on S3 and between filesystems
Previously Impala disallowed LOAD DATA and INSERT on S3. This patch
functionally enables LOAD DATA and INSERT on S3 without making major
changes for the sake of improving performance over S3. This patch also
enables both INSERT and LOAD DATA between file systems.

S3 does not support the rename operation, so the staged files in S3
are copied instead of renamed, which contributes to the slow
performance on S3.

The FinalizeSuccessfulInsert() function now does not make any
underlying assumptions of the filesystem it is on and works across
all supported filesystems. This is done by adding a full URI field to
the base directory for a partition in the TInsertPartitionStatus.
Also, the HdfsOp class now does not assume a single filesystem and
gets connections to the filesystems based on the URI of the file it
is operating on.

Added a python S3 client called 'boto3' to access S3 from the python
tests. A new class called S3Client is introduced which creates
wrappers around the boto3 functions and have the same function
signatures as PyWebHdfsClient by deriving from a base abstract class
BaseFileSystem so that they can be interchangeably through a
'generic_client'. test_load.py is refactored to use this generic
client. The ImpalaTestSuite setup creates a client according to the
TARGET_FILESYSTEM environment variable and assigns it to the
'generic_client'.

P.S: Currently, the test_load.py runs 4x slower on S3 than on
HDFS. Performance needs to be improved in future patches. INSERT
performance is slower than on HDFS too. This is mainly because of an
extra copy that happens between staging and the final location of a
file. However, larger INSERTs come closer to HDFS permformance than
smaller inserts.

ACLs are not taken care of for S3 in this patch. It is something
that still needs to be discussed before implementing.

Change-Id: I94e15ad67752dce21c9b7c1dced6e114905a942d
Reviewed-on: http://gerrit.cloudera.org:8080/2574
Reviewed-by: Sailesh Mukil <sailesh@cloudera.com>
Tested-by: Internal Jenkins
2016-05-12 14:17:49 -07:00

120 lines
4.9 KiB
Python

# Copyright (c) 2012 Cloudera, Inc. All rights reserved.
#
import logging
import os
import pytest
from copy import copy
from tests.common.test_vector import *
from tests.common.impala_test_suite import *
from tests.common.skip import SkipIfS3
from tests.util.filesystem_utils import WAREHOUSE
class TestStringQueries(ImpalaTestSuite):
@classmethod
def get_workload(cls):
return 'functional-query'
def setup_method(self, method):
self.__cleanup_char_tables()
self.__create_char_tables()
def teardown_method(self, method):
self.__cleanup_char_tables()
def __cleanup_char_tables(self):
self.client.execute('drop table if exists functional.test_char_tmp');
self.client.execute('drop table if exists functional.test_varchar_tmp');
self.client.execute('drop table if exists functional.allchars');
self.client.execute('drop table if exists functional.allchars_par');
self.client.execute('drop table if exists functional.test_char_nulls');
def __create_char_tables(self):
self.client.execute(
'create table if not exists ' +
'functional.test_varchar_tmp (vc varchar(5))')
self.client.execute(
'create table if not exists functional.test_char_tmp (c char(5))')
self.client.execute(
'create table if not exists functional.allchars ' +
'(cshort char(5), clong char(140), vc varchar(5))')
self.client.execute(
'create table if not exists functional.allchars_par ' +
'(cshort char(5), clong char(140), vc varchar(5)) stored as parquet')
# Regression test for IMPALA-1339
self.client.execute('create table if not exists ' +
'''functional.test_char_nulls ( c20 char(20),
c40 char(40),
c60 char(60),
c80 char(80),
c81 char(81),
c82 char(82),
c100 char(100),
c120 char(120),
c140 char(140))''')
self.client.execute('insert into functional.test_char_nulls ' +
'values (NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL)');
self.client.execute('insert into functional.test_char_nulls ' +
'values (NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL)');
@classmethod
def add_test_dimensions(cls):
super(TestStringQueries, cls).add_test_dimensions()
cls.TestMatrix.add_dimension(
create_exec_option_dimension(disable_codegen_options=[False, True]))
cls.TestMatrix.add_constraint(lambda v:\
v.get_value('table_format').file_format in ['text'] and
v.get_value('table_format').compression_codec in ['none'])
@pytest.mark.execute_serially
def test_varchar(self, vector):
self.run_test_case('QueryTest/chars', vector)
class TestCharFormats(ImpalaTestSuite):
@classmethod
def get_workload(cls):
return 'functional-query'
def setup_method(self, method):
self.__create_char_tables()
def __create_char_tables(self):
self.client.execute('''create external table if not exists
functional_parquet.chars_formats
(cs CHAR(5), cl CHAR(140), vc VARCHAR(32))
STORED AS PARQUET
LOCATION "/test-warehouse/chars_formats_parquet"''')
self.client.execute('''create external table if not exists
functional.chars_formats
(cs CHAR(5), cl CHAR(140), vc VARCHAR(32))
ROW FORMAT delimited fields terminated by ',' escaped by '\\\\'
STORED AS TEXTFILE
LOCATION "/test-warehouse/chars_formats_text"
''')
self.client.execute('''create external table if not exists
functional_avro_snap.chars_formats
(cs CHAR(5), cl CHAR(140), vc VARCHAR(32))
STORED AS AVRO
LOCATION "/test-warehouse/chars_formats_avro_snap"
TBLPROPERTIES ('avro.schema.literal'='{"type":"record",
"name":"CharTypesTest","doc":"Schema generated by Kite",
"fields":[
{"name":"cs","type":["null","string"], "doc":"Type inferred"},
{"name":"cl","type":["null","string"], "doc":"Type inferred"},
{"name":"vc","type":["null","string"],"doc":"Type inferred"}]}')''')
@classmethod
def add_test_dimensions(cls):
super(TestCharFormats, cls).add_test_dimensions()
cls.TestMatrix.add_dimension(
create_exec_option_dimension(disable_codegen_options=[False, True]))
cls.TestMatrix.add_constraint(lambda v:
(v.get_value('table_format').file_format in ['avro'] and
v.get_value('table_format').compression_codec in ['snap']) or
v.get_value('table_format').file_format in ['parquet'] or
(v.get_value('table_format').file_format in ['text'] and
v.get_value('table_format').compression_codec in ['none']))
def test_char_format(self, vector):
self.run_test_case('QueryTest/chars-formats', vector)