mirror of
https://github.com/apache/impala.git
synced 2026-02-03 00:00:40 -05:00
bb9fb663ce
Impala-shell already uses HS2 protocol to connect to Impalad. This commit allows impala-shell to connect to any server (for example, Hive) using the hs2 protocol. This will be done via the "--strict_hs2_protocol" option. When the "--strict_hs2_protocol" option is turned on, only features supported by hs2 will work. For instance, "runtime-profile" is an impalad specific feature and will be disabled. The "--strict_hs2_protocol" will only work on servers that abide by the strict definition of what is supported by HS2. So one will be able to connect to Hive in this mode, but connections to Impala will not work. Any feature supported by Hive (e.g. kerberos authentication) should work as well. Note: While authentication should work, the test framework is not set up to create an HS2 server that does authentication at this point so this feature should be used with caution. Change-Id: I674a45640a4a7b3c9a577830dbc7b16a89865a9e Reviewed-on: http://gerrit.cloudera.org:8080/17660 Reviewed-by: Impala Public Jenkins <impala-public-jenkins@cloudera.com> Tested-by: Impala Public Jenkins <impala-public-jenkins@cloudera.com>
99 lines
4.0 KiB
Python
99 lines
4.0 KiB
Python
#!/usr/bin/env impala-python
|
|
# -*- coding: utf-8 -*-
|
|
#
|
|
# 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.
|
|
|
|
from shell.impala_client import ImpalaBeeswaxClient, ImpalaHS2Client
|
|
from tests.common.impala_test_suite import ImpalaTestSuite
|
|
from tests.common.test_dimensions import create_client_protocol_dimension
|
|
from tests.common.test_dimensions import create_client_protocol_no_strict_dimension
|
|
from util import get_impalad_host_port
|
|
|
|
|
|
class TestShellClient(ImpalaTestSuite):
|
|
"""Tests for the Impala Shell clients: ImpalaBeeswaxClient and ImpalaHS2Client."""
|
|
|
|
@classmethod
|
|
def get_workload(self):
|
|
return 'functional-query'
|
|
|
|
@classmethod
|
|
def add_test_dimensions(cls):
|
|
cls.ImpalaTestMatrix.add_dimension(create_client_protocol_dimension())
|
|
cls.ImpalaTestMatrix.add_dimension(create_client_protocol_no_strict_dimension())
|
|
|
|
def test_fetch_size(self, vector):
|
|
"""Tests that when result spooling is disabled, setting a small batch_size causes
|
|
the shell to fetch a single batch at a time, even when the configured fetch size is
|
|
larger than the batch_size."""
|
|
handle = None
|
|
num_rows = 100
|
|
batch_size = 10
|
|
query_options = {'batch_size': str(batch_size), 'spool_query_results': 'false'}
|
|
client = self.__get_shell_client(vector)
|
|
|
|
try:
|
|
client.connect()
|
|
handle = client.execute_query(
|
|
"select * from functional.alltypes limit {0}".format(num_rows), query_options)
|
|
self.__fetch_rows(client.fetch(handle), batch_size, num_rows)
|
|
finally:
|
|
if handle is not None: client.close_query(handle)
|
|
client.close_connection()
|
|
|
|
def test_fetch_size_result_spooling(self, vector):
|
|
"""Tests that when result spooling is enabled, that the exact fetch_size is honored
|
|
even if a small batch_size is configured."""
|
|
handle = None
|
|
fetch_size = 20
|
|
num_rows = 100
|
|
query_options = {'batch_size': '10', 'spool_query_results': 'true'}
|
|
client = self.__get_shell_client(vector, fetch_size)
|
|
|
|
try:
|
|
client.connect()
|
|
handle = client.execute_query(
|
|
"select * from functional.alltypes limit {0}".format(num_rows), query_options)
|
|
self.__fetch_rows(client.fetch(handle), num_rows / fetch_size, num_rows)
|
|
finally:
|
|
if handle is not None: client.close_query(handle)
|
|
client.close_connection()
|
|
|
|
def __fetch_rows(self, fetch_batches, num_batches, num_rows):
|
|
"""Fetches all rows using the given fetch_batches generator. Asserts that num_batches
|
|
batches are produced by the generator and that num_rows are returned."""
|
|
num_batches_count = 0
|
|
rows_per_batch = num_rows / num_batches
|
|
for fetch_batch in fetch_batches:
|
|
assert len(fetch_batch) == rows_per_batch
|
|
num_batches_count += 1
|
|
if num_batches_count == num_batches: break
|
|
assert num_batches_count == num_batches
|
|
|
|
def __get_shell_client(self, vector, fetch_size=1024):
|
|
"""Returns the client specified by the protocol in the given vector."""
|
|
impalad = get_impalad_host_port(vector).split(":")
|
|
protocol = vector.get_value("protocol")
|
|
if protocol == 'hs2':
|
|
return ImpalaHS2Client(impalad, fetch_size, None)
|
|
elif protocol == 'hs2-http':
|
|
return ImpalaHS2Client(impalad, fetch_size, None,
|
|
use_http_base_transport=True, http_path='cliservice')
|
|
elif protocol == 'beeswax':
|
|
return ImpalaBeeswaxClient(impalad, fetch_size, None)
|