def query_store_api(request, path=None):
response = {'status': -1}
if USE_PROXY.get():
content_type = 'application/json; charset=UTF-8'
headers = {'X-Requested-By': 'das', 'Content-Type': content_type}
client = HttpClient(QUERY_STORE.SERVER_URL.get())
resource = Resource(client)
if USE_SASL.get():
client.set_kerberos_auth()
try:
response = resource.invoke(request.method, path,
request.GET.dict(), request.body,
headers)
except RestException as e:
ex_response = e.get_parent_ex().response
response['code'] = ex_response.status_code
response['message'] = ex_response.reason
response['content'] = ex_response.text
else:
if path == 'api/query/search':
filters = json.loads(request.body)
resp = get_api(request.user,
interface='queries-hive').apps(filters['search'])
response = resp['apps']
return JsonResponse(response)
def _query_store_proxy(request, path=None):
response = {'status': -1}
headers = {
'x-do-as': request.user.username,
'X-Requested-By': 'das',
'Content-Type': 'application/json; charset=UTF-8'
}
client = HttpClient(QUERY_STORE.SERVER_URL.get())
resource = Resource(client)
if USE_SASL.get():
client.set_kerberos_auth()
try:
response = resource.invoke(request.method, path, request.GET.dict(),
request.body, headers)
except RestException as e:
ex_response = e.get_parent_ex().response
if ex_response is not None:
response['code'] = ex_response.status_code
response['message'] = ex_response.reason
response['content'] = ex_response.text
else:
response['message'] = 'Query store not reachable!'
response['content'] = e.message
return response
def query_store_download_bundle(request, id=None):
response = {}
client = HttpClient(QUERY_STORE.SERVER_URL.get())
resource = Resource(client)
if USE_SASL.get():
client.set_kerberos_auth()
app = resource.get('api/data-bundle/' + id)
response = FileResponse((app, 'rb'), content_type='application/octet-stream')
response['Content-Disposition'] = 'attachment; filename=' + id + '.zip'
return response
def _create_query_store_client(request,
content_type='application/json; charset=UTF-8'):
headers = {
'x-do-as': request.user.username,
'X-Requested-By': 'das',
'Content-Type': content_type
}
client = HttpClient(QUERY_STORE.SERVER_URL.get())
client.set_headers(headers)
if USE_SASL.get():
client.set_kerberos_auth()
return client
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 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()
}
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()
})
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