def test_call_session_single(self):
finish = (
MAX_NUMBER_OF_SESSIONS.set_for_testing(1),
CLOSE_SESSIONS.set_for_testing(False)
)
try:
with patch('beeswax.server.hive_server2_lib.thrift_util.get_client') as get_client:
with patch('beeswax.server.hive_server2_lib.HiveServerClient.open_session') as open_session:
with patch('beeswax.server.hive_server2_lib.Session.objects.get_session') as get_session:
open_session.return_value = MagicMock(status_code=0)
get_session.return_value = None
fn = MagicMock(attr='test')
req = MagicMock()
server_config = get_query_server_config(name='beeswax')
client = HiveServerClient(server_config, self.user)
(res, session1) = client.call(fn, req, status=None)
open_session.assert_called_once()
# Reuse session from argument
(res, session2) = client.call(fn, req, status=None, session=session1)
open_session.assert_called_once() # open_session should not be called again, because we're reusing session
assert_equal(session1, session2)
# Reuse session from get_session
get_session.return_value = session1
(res, session3) = client.call(fn, req, status=None)
open_session.assert_called_once() # open_session should not be called again, because we're reusing session
assert_equal(session1, session3)
finally:
for f in finish:
f()
def test_call_session_close_idle_limit(self):
finish = (
MAX_NUMBER_OF_SESSIONS.set_for_testing(2),
CLOSE_SESSIONS.set_for_testing(True)
)
try:
with patch('beeswax.server.hive_server2_lib.thrift_util.get_client') as get_client:
with patch('beeswax.server.hive_server2_lib.HiveServerClient.open_session') as open_session:
with patch('beeswax.server.hive_server2_lib.Session.objects.get_n_sessions') as get_n_sessions:
get_n_sessions.return_value = MagicMock(count=MagicMock(return_value=2))
open_session.return_value = MagicMock(status_code=0)
fn = MagicMock(return_value=MagicMock(status=MagicMock(statusCode=0)))
req = MagicMock()
server_config = get_query_server_config(name='beeswax')
client = HiveServerClient(server_config, self.user)
assert_raises(Exception, client.call, fn, req, status=None)
get_n_sessions.return_value = MagicMock(count=MagicMock(return_value=1))
(res, session1) = client.call(fn, req, status=None)
open_session.assert_called_once()
finally:
for f in finish:
f()
def test_call_session_close_idle(self):
finish = (
MAX_NUMBER_OF_SESSIONS.set_for_testing(-1),
CLOSE_SESSIONS.set_for_testing(True)
)
try:
with patch('beeswax.server.hive_server2_lib.thrift_util.get_client') as get_client:
with patch('beeswax.server.hive_server2_lib.HiveServerClient.open_session') as open_session:
open_session.return_value = MagicMock(status_code=0)
fn = MagicMock(return_value=MagicMock(status=MagicMock(statusCode=0)))
req = MagicMock()
server_config = get_query_server_config(name='beeswax')
client = HiveServerClient(server_config, self.user)
(res, session1) = client.call(fn, req, status=None)
open_session.assert_called_once()
# Reuse session from argument
(res, session2) = client.call(fn, req, status=None, session=session1)
open_session.assert_called_once() # open_session should not be called again, because we're reusing session
assert_equal(session1, session2)
# Create new session
open_session.return_value = MagicMock(status_code=0)
(res, session3) = client.call(fn, req, status=None)
assert_equal(open_session.call_count, 2)
assert_not_equal(session1, session3)
finally:
for f in finish:
f()
def test_call_session_pool_limit(self):
finish = (MAX_NUMBER_OF_SESSIONS.set_for_testing(2),
CLOSE_SESSIONS.set_for_testing(False))
try:
with patch('beeswax.server.hive_server2_lib.thrift_util.get_client'
) as get_client:
with patch(
'beeswax.server.hive_server2_lib.HiveServerClient.open_session'
) as open_session:
with patch(
'beeswax.server.hive_server2_lib.Session.objects.get_tez_session'
) as get_tez_session:
get_tez_session.side_effect = Exception('')
open_session.return_value = MagicMock(status_code=0)
fn = MagicMock(return_value=MagicMock(status=MagicMock(
statusCode=0)))
req = MagicMock()
server_config = get_query_server_config(name='beeswax')
client = HiveServerClient(server_config, self.user)
assert_raises(Exception,
client.call,
fn,
req,
status=None)
finally:
for f in finish:
f()
def test_call_session_close_idle_managed_queries(self):
finish = (
MAX_NUMBER_OF_SESSIONS.set_for_testing(-1),
CLOSE_SESSIONS.set_for_testing(True)
)
try:
with patch('beeswax.server.hive_server2_lib.thrift_util.get_client') as get_client:
with patch('beeswax.server.hive_server2_lib.HiveServerClient.open_session') as open_session:
with patch('beeswax.server.hive_server2_lib.HiveServerClient.close_session') as close_session:
with patch('beeswax.server.hive_server2_lib.HiveServerTRowSet') as HiveServerTRowSet:
status = MagicMock(status=MagicMock(statusCode=0))
status_return = MagicMock(return_value=status)
get_client.return_value = MagicMock(
return_value=status, GetSchemas=status_return, FetchResults=status_return, GetResultSetMetadata=status_return,
CloseOperation=status_return, ExecuteStatement=status_return, GetTables=status_return, GetColumns=status_return
)
open_session.return_value = MagicMock(status_code=0)
server_config = get_query_server_config(name='beeswax')
client = HiveServerClient(server_config, self.user)
res = client.get_databases()
assert_equal(open_session.call_count, 1)
assert_equal(close_session.call_count, 1)
res = client.get_database(MagicMock())
assert_equal(open_session.call_count, 2)
assert_equal(close_session.call_count, 2)
res = client.get_tables_meta(MagicMock(), MagicMock())
assert_equal(open_session.call_count, 3)
assert_equal(close_session.call_count, 3)
res = client.get_tables(MagicMock(), MagicMock())
assert_equal(open_session.call_count, 4)
assert_equal(close_session.call_count, 4)
res = client.get_table(MagicMock(), MagicMock())
assert_equal(open_session.call_count, 5)
assert_equal(close_session.call_count, 5)
res = client.get_columns(MagicMock(), MagicMock())
assert_equal(open_session.call_count, 6)
assert_equal(close_session.call_count, 6)
res = client.get_partitions(MagicMock(), MagicMock()) # get_partitions does 2 requests with 1 session each
assert_equal(open_session.call_count, 8)
assert_equal(close_session.call_count, 8)
finally:
for f in finish:
f()
def create_session(self, lang='hive', properties=None):
application = 'beeswax' if lang == 'hive' or lang == 'llap' else lang
if has_session_pool():
session = Session.objects.get_tez_session(
self.user, application, MAX_NUMBER_OF_SESSIONS.get())
elif not has_multiple_sessions():
session = Session.objects.get_session(self.user,
application=application)
else:
session = None
reuse_session = session is not None
if not reuse_session:
db = dbms.get(self.user,
query_server=get_query_server_config(
name=lang, connector=self.interpreter))
session = db.open_session(self.user)
response = {'type': lang, 'id': session.id}
if not properties:
config = None
if USE_DEFAULT_CONFIGURATION.get():
config = DefaultConfiguration.objects.get_configuration_for_user(
app=lang, user=self.user)
if config is not None:
properties = config.properties_list
else:
properties = self.get_properties(lang)
response['properties'] = properties
response['configuration'] = json.loads(session.properties)
response['reuse_session'] = reuse_session
response['session_id'] = ''
try:
decoded_guid = session.get_handle().sessionId.guid
response['session_id'] = unpack_guid(decoded_guid)
except Exception as e:
LOG.warn('Failed to decode session handle: %s' % e)
if lang == 'impala' and session:
http_addr = _get_impala_server_url(session)
response['http_addr'] = http_addr
return response
def get_query_server_config(name='beeswax', connector=None):
if connector and has_connectors(): # TODO: Give empty connector when no connector in use
LOG.debug("Query via connector %s" % name)
query_server = get_query_server_config_via_connector(connector)
else:
LOG.debug("Query via ini %s" % name)
if name == "llap":
activeEndpoint = cache.get('llap')
if activeEndpoint is None:
if HIVE_DISCOVERY_LLAP.get():
LOG.debug("Checking zookeeper for discovering Hive LLAP server endpoint")
zk = KazooClient(hosts=libzookeeper_conf.ENSEMBLE.get(), read_only=True)
zk.start()
if HIVE_DISCOVERY_LLAP_HA.get():
znode = "{0}/instances".format(HIVE_DISCOVERY_LLAP_ZNODE.get())
LOG.debug("Setting up Hive LLAP HA with the following node {0}".format(znode))
if zk.exists(znode):
hiveservers = zk.get_children(znode)
if not hiveservers:
raise PopupException(_('There is no running Hive LLAP server available'))
LOG.info("Available Hive LLAP servers: {0}".format(hiveservers))
for server in hiveservers:
llap_servers = json.loads(zk.get("{0}/{1}".format(znode, server))[0])["internal"][0]
if llap_servers["api"] == "activeEndpoint":
LOG.info("Selecting Hive LLAP server: {0}".format(llap_servers))
cache.set(
"llap",
json.dumps({
"host": llap_servers["addresses"][0]["host"],
"port": llap_servers["addresses"][0]["port"]
}),
CACHE_TIMEOUT.get()
)
else:
LOG.error("Hive LLAP endpoint not found, reverting to config values")
cache.set("llap", json.dumps({"host": HIVE_SERVER_HOST.get(), "port": HIVE_HTTP_THRIFT_PORT.get()}), CACHE_TIMEOUT.get())
else:
znode = "{0}".format(HIVE_DISCOVERY_LLAP_ZNODE.get())
LOG.debug("Setting up Hive LLAP with the following node {0}".format(znode))
if zk.exists(znode):
hiveservers = zk.get_children(znode)
for server in hiveservers:
cache.set(
"llap",
json.dumps({
"host": server.split(';')[0].split('=')[1].split(":")[0],
"port": server.split(';')[0].split('=')[1].split(":")[1]
})
)
zk.stop()
else:
LOG.debug("Zookeeper discovery not enabled, reverting to config values")
cache.set("llap", json.dumps({"host": LLAP_SERVER_HOST.get(), "port": LLAP_SERVER_THRIFT_PORT.get()}), CACHE_TIMEOUT.get())
activeEndpoint = json.loads(cache.get("llap"))
elif name != 'hms' and name != 'impala':
activeEndpoint = cache.get("hiveserver2")
if activeEndpoint is None:
if HIVE_DISCOVERY_HS2.get():
hiveservers = get_zk_hs2()
LOG.debug("Available Hive Servers: {0}".format(hiveservers))
if not hiveservers:
raise PopupException(_('There is no running Hive server available'))
server_to_use = 0
LOG.debug("Selected Hive server {0}: {1}".format(server_to_use, hiveservers[server_to_use]))
cache.set(
"hiveserver2",
json.dumps({
"host": hiveservers[server_to_use].split(";")[0].split("=")[1].split(":")[0],
"port": hiveservers[server_to_use].split(";")[0].split("=")[1].split(":")[1]
})
)
else:
cache.set("hiveserver2", json.dumps({"host": HIVE_SERVER_HOST.get(), "port": HIVE_HTTP_THRIFT_PORT.get()}))
else:
# Setting hs2 cache in-case there is no HS2 discovery
cache.set("hiveserver2", json.dumps({"host": HIVE_SERVER_HOST.get(), "port": HIVE_HTTP_THRIFT_PORT.get()}))
if HIVE_DISCOVERY_HS2.get():
# Replace ActiveEndpoint if the current HS2 is down
hiveservers = get_zk_hs2()
if hiveservers is not None:
server_to_use = 0
hs2_host_name = hiveservers[server_to_use].split(";")[0].split("=")[1].split(":")[0]
hs2_in_active_endpoint = hs2_host_name in activeEndpoint
LOG.debug("Is the current HS2 active {0}".format(hs2_in_active_endpoint))
if not hs2_in_active_endpoint:
LOG.error(
'Current HiveServer is down, working to connect with the next available HiveServer from Zookeeper')
reset_ha()
server_to_use = 0
LOG.debug("Selected HiveServer {0}: {1}".format(server_to_use, hiveservers[server_to_use]))
cache.set(
"hiveserver2",
json.dumps({
"host": hiveservers[server_to_use].split(";")[0].split("=")[1].split(":")[0],
"port": hiveservers[server_to_use].split(";")[0].split("=")[1].split(":")[1]
})
)
activeEndpoint = json.loads(cache.get("hiveserver2"))
if name == 'impala':
from impala.dbms import get_query_server_config as impala_query_server_config
query_server = impala_query_server_config()
elif name == 'hms':
kerberos_principal = get_hiveserver2_kerberos_principal(HIVE_SERVER_HOST.get())
query_server = {
'server_name': 'hms',
'server_host': HIVE_METASTORE_HOST.get() if not cluster_config else cluster_config.get('server_host'),
'server_port': HIVE_METASTORE_PORT.get(),
'principal': kerberos_principal,
'transport_mode': 'http' if hiveserver2_transport_mode() == 'HTTP' else 'socket',
'auth_username': AUTH_USERNAME.get(),
'auth_password': AUTH_PASSWORD.get(),
'use_sasl': HIVE_USE_SASL.get()
}
else:
kerberos_principal = get_hiveserver2_kerberos_principal(HIVE_SERVER_HOST.get())
query_server = {
'server_name': 'beeswax' if name != 'hplsql' else 'hplsql',
'server_host': activeEndpoint["host"],
'server_port': LLAP_SERVER_PORT.get() if name == 'llap' else HIVE_SERVER_PORT.get(),
'principal': kerberos_principal,
'http_url': '%(protocol)s://%(host)s:%(port)s/%(end_point)s' % {
'protocol': 'https' if hiveserver2_use_ssl() else 'http',
'host': activeEndpoint["host"],
'port': activeEndpoint["port"],
'end_point': hiveserver2_thrift_http_path()
},
'transport_mode': 'http' if hiveserver2_transport_mode() == 'HTTP' else 'socket',
'auth_username': AUTH_USERNAME.get(),
'auth_password': AUTH_PASSWORD.get(),
'use_sasl': HIVE_USE_SASL.get(),
'close_sessions': CLOSE_SESSIONS.get(),
'has_session_pool': has_session_pool(),
'max_number_of_sessions': MAX_NUMBER_OF_SESSIONS.get()
}
if name == 'sparksql': # Extends Hive as very similar
from spark.conf import SQL_SERVER_HOST as SPARK_SERVER_HOST, SQL_SERVER_PORT as SPARK_SERVER_PORT, USE_SASL as SPARK_USE_SASL
query_server.update({
'server_name': 'sparksql',
'server_host': SPARK_SERVER_HOST.get(),
'server_port': SPARK_SERVER_PORT.get(),
'use_sasl': SPARK_USE_SASL.get()
})
if not query_server.get('dialect'):
query_server['dialect'] = query_server['server_name']
debug_query_server = query_server.copy()
debug_query_server['auth_password_used'] = bool(debug_query_server.pop('auth_password', None))
LOG.debug("Query Server: %s" % debug_query_server)
return query_server
def create_session(self, lang='hive', properties=None):
application = 'beeswax' if lang == 'hive' or lang == 'llap' else lang
uses_session_pool = has_session_pool()
uses_multiple_sessions = has_multiple_sessions()
if lang == 'impala':
uses_session_pool = False
uses_multiple_sessions = False
try:
if uses_session_pool:
session = Session.objects.get_tez_session(
self.user, application, MAX_NUMBER_OF_SESSIONS.get())
elif not uses_multiple_sessions:
session = Session.objects.get_session(self.user,
application=application)
else:
session = None
except Exception as e:
if 'Connection refused' in str(
e) or 'Name or service not known' in str(e):
LOG.exception(
'Connection being refused or service is not available in either session or in multiple sessions'
'- HA failover')
reset_ha()
reuse_session = session is not None
if not reuse_session:
db = dbms.get(self.user,
query_server=get_query_server_config(
name=lang, connector=self.interpreter))
try:
session = db.open_session(self.user)
except Exception as e:
if 'Connection refused' in str(
e) or 'Name or service not known' in str(e):
LOG.exception(
'Connection being refused or service is not available in reuse session - HA failover'
)
reset_ha()
response = {'type': lang, 'id': session.id}
if not properties:
config = None
if USE_DEFAULT_CONFIGURATION.get():
config = DefaultConfiguration.objects.get_configuration_for_user(
app=lang, user=self.user)
if config is not None:
properties = config.properties_list
else:
properties = self.get_properties(lang)
response['properties'] = properties
response['configuration'] = json.loads(session.properties)
response['reuse_session'] = reuse_session
response['session_id'] = ''
try:
decoded_guid = session.get_handle().sessionId.guid
response['session_id'] = unpack_guid(decoded_guid)
except Exception as e:
LOG.warning('Failed to decode session handle: %s' % e)
if lang == 'impala' and session:
http_addr = _get_impala_server_url(session)
response['http_addr'] = http_addr
return response
def get_query_server_config(name='beeswax', connector=None):
if connector and has_connectors(): # TODO: Give empty connector when no connector in use
query_server = get_query_server_config_via_connector(connector)
else:
LOG.debug("Query cluster %s" % name)
if name == "llap":
activeEndpoint = cache.get('llap')
if activeEndpoint is None:
if HIVE_DISCOVERY_LLAP.get():
LOG.debug("Checking zookeeper for Hive Server Interactive endpoint")
zk = KazooClient(hosts=libzookeeper_conf.ENSEMBLE.get(), read_only=True)
zk.start()
if HIVE_DISCOVERY_LLAP_HA.get():
znode = "{0}/instances".format(HIVE_DISCOVERY_LLAP_ZNODE.get())
LOG.debug("Setting up LLAP with the following node {0}".format(znode))
if zk.exists(znode):
hiveservers = zk.get_children(znode)
for server in hiveservers:
llap_servers= json.loads(zk.get("{0}/{1}".format(znode, server))[0])["internal"][0]
if llap_servers["api"] == "activeEndpoint":
cache.set("llap", json.dumps({"host": llap_servers["addresses"][0]["host"], "port": llap_servers["addresses"][0]["port"]}), CACHE_TIMEOUT.get())
else:
LOG.error("LLAP Endpoint not found, reverting to HiveServer2")
cache.set("llap", json.dumps({"host": HIVE_SERVER_HOST.get(), "port": HIVE_HTTP_THRIFT_PORT.get()}), CACHE_TIMEOUT.get())
else:
znode = "{0}".format(HIVE_DISCOVERY_LLAP_ZNODE.get())
LOG.debug("Setting up LLAP with the following node {0}".format(znode))
if zk.exists(znode):
hiveservers = zk.get_children(znode)
for server in hiveservers:
cache.set("llap", json.dumps({"host": server.split(';')[0].split('=')[1].split(":")[0], "port": server.split(';')[0].split('=')[1].split(":")[1]}))
zk.stop()
else:
LOG.debug("Zookeeper Discovery not enabled, reverting to config values")
cache.set("llap", json.dumps({"host": LLAP_SERVER_HOST.get(), "port": LLAP_SERVER_THRIFT_PORT.get()}), CACHE_TIMEOUT.get())
activeEndpoint = json.loads(cache.get("llap"))
elif name != 'hms' and name != 'impala':
activeEndpoint = cache.get("hiveserver2")
if activeEndpoint is None:
if HIVE_DISCOVERY_HS2.get():
zk = KazooClient(hosts=libzookeeper_conf.ENSEMBLE.get(), read_only=True)
zk.start()
znode = HIVE_DISCOVERY_HIVESERVER2_ZNODE.get()
LOG.info("Setting up Hive with the following node {0}".format(znode))
if zk.exists(znode):
hiveservers = zk.get_children(znode)
server_to_use = 0 # if CONF.HIVE_SPREAD.get() randint(0, len(hiveservers)-1) else 0
cache.set("hiveserver2", json.dumps({"host": hiveservers[server_to_use].split(";")[0].split("=")[1].split(":")[0], "port": hiveservers[server_to_use].split(";")[0].split("=")[1].split(":")[1]}))
else:
cache.set("hiveserver2", json.dumps({"host": HIVE_SERVER_HOST.get(), "port": HIVE_HTTP_THRIFT_PORT.get()}))
zk.stop()
else:
cache.set("hiveserver2", json.dumps({"host": HIVE_SERVER_HOST.get(), "port": HIVE_HTTP_THRIFT_PORT.get()}))
activeEndpoint = json.loads(cache.get("hiveserver2"))
if name == 'impala':
from impala.dbms import get_query_server_config as impala_query_server_config
query_server = impala_query_server_config()
elif name == 'hms':
kerberos_principal = hive_site.get_hiveserver2_kerberos_principal(HIVE_SERVER_HOST.get())
query_server = {
'server_name': 'hms',
'server_host': HIVE_METASTORE_HOST.get() if not cluster_config else cluster_config.get('server_host'),
'server_port': HIVE_METASTORE_PORT.get(),
'principal': kerberos_principal,
'transport_mode': 'http' if hive_site.hiveserver2_transport_mode() == 'HTTP' else 'socket',
'auth_username': AUTH_USERNAME.get(),
'auth_password': AUTH_PASSWORD.get(),
'use_sasl': HIVE_USE_SASL.get()
}
else:
kerberos_principal = hive_site.get_hiveserver2_kerberos_principal(HIVE_SERVER_HOST.get())
query_server = {
'server_name': 'beeswax',
'server_host': activeEndpoint["host"],
'server_port': LLAP_SERVER_PORT.get() if name == 'llap' else HIVE_SERVER_PORT.get(),
'principal': kerberos_principal,
'http_url': '%(protocol)s://%(host)s:%(port)s/%(end_point)s' % {
'protocol': 'https' if hiveserver2_use_ssl() else 'http',
'host': activeEndpoint["host"],
'port': activeEndpoint["port"],
'end_point': hive_site.hiveserver2_thrift_http_path()
},
'transport_mode': 'http' if hive_site.hiveserver2_transport_mode() == 'HTTP' else 'socket',
'auth_username': AUTH_USERNAME.get(),
'auth_password': AUTH_PASSWORD.get(),
'use_sasl': HIVE_USE_SASL.get(),
'close_sessions': CLOSE_SESSIONS.get(),
'has_session_pool': has_session_pool(),
'max_number_of_sessions': MAX_NUMBER_OF_SESSIONS.get()
}
if name == 'sparksql': # Extends Hive as very similar
from spark.conf import SQL_SERVER_HOST as SPARK_SERVER_HOST, SQL_SERVER_PORT as SPARK_SERVER_PORT, USE_SASL as SPARK_USE_SASL
query_server.update({
'server_name': 'sparksql',
'server_host': SPARK_SERVER_HOST.get(),
'server_port': SPARK_SERVER_PORT.get(),
'use_sasl': SPARK_USE_SASL.get()
})
if not query_server.get('dialect'):
query_server['dialect'] = query_server['server_name']
debug_query_server = query_server.copy()
debug_query_server['auth_password_used'] = bool(debug_query_server.pop('auth_password', None))
LOG.debug("Query Server: %s" % debug_query_server)
return query_server