Add test_timeout to limit test run time

Added 'test-timeout' option to be able to break the test process with
kill signal if the test runs longer than this amount of seconds. By
default it is equal to 110 seconds. This value should be bigger than
'replication-sync-timeout' (which is 100 seconds by default) and
lower than 'no-output-timeout' (which is 120 seconds by default).

This timeout helped to avoid of issues with hanging tests till reach
of 'no-output-timeout' timeout, when overall testing exits. For now
if the test hangs than 'test-timeout' timeout helps to exit the test
processes. It gives the test-run worker chance to restart the failed
test either continue tests in worker queue. Before this fix tests,
hanged, like [1] and [2], for now the same issues resolved, like [3]
and [4] appropriate.

To reproduce the issues like [2], try to set 'test-timeout' not enough
to complete the test on 'restart server ...' command, like:

  ./test-run.py replication/quorum.test.lua --test-timeout 5 \
    --no-output-timeout 10 --conf memtx

The fix resolves the issue #157 together with PR #186, which helps
to kill the instances when SIGTERM couldn't do it.

Part of #157

[1] - https://gitlab.com/tarantool/tarantool/-/jobs/835734706#L4968
[2] - https://gitlab.com/tarantool/tarantool/-/jobs/822649038#L4835
[3] - https://gitlab.com/tarantool/tarantool/-/jobs/874058059#L4993
[4] - https://gitlab.com/tarantool/tarantool/-/jobs/874058745#L5316

lib/app_server.py

@@ -6,7 +6,9 @@
 
 from gevent.subprocess import Popen, PIPE
 
+from lib.colorer import color_stdout
 from lib.colorer import color_log
+from lib.options import Options
 from lib.preprocessor import TestState
 from lib.server import Server
 from lib.tarantool_server import Test
@@ -16,12 +18,22 @@
 from lib.utils import format_process
 from lib.utils import warn_unix_socket
 from test import TestRunGreenlet, TestExecutionError
+from threading import Timer
+
+
+def timeout_handler(server_process, test_timeout):
+    color_stdout("Test timeout of %d secs reached\t" % test_timeout, schema='error')
+    server_process.kill()
 
 
 def run_server(execs, cwd, server, logfile, retval):
     os.putenv("LISTEN", server.iproto)
     server.process = Popen(execs, stdout=PIPE, stderr=PIPE, cwd=cwd)
+    test_timeout = Options().args.test_timeout
+    timer = Timer(test_timeout, timeout_handler, [server.process, test_timeout])
+    timer.start()
     stdout, stderr = server.process.communicate()
+    timer.cancel()
     sys.stdout.write(stdout)
     with open(logfile, 'a') as f:
         f.write(stderr)

lib/options.py

@@ -190,6 +190,14 @@ def __init__(self):
                 Such files created by workers in the "var/reproduce" directory.
                 Note: The option works now only with parallel testing.""")
 
+        parser.add_argument(
+                "--test-timeout",
+                dest="test_timeout",
+                default=110,
+                type=int,
+                help="""Break the test process with kill signal if the test runs
+                longer than this amount of seconds. Default: 110 [seconds].""")
+
         parser.add_argument(
                 "--no-output-timeout",
                 dest="no_output_timeout",

lib/tarantool_server.py

@@ -14,6 +14,7 @@
 import yaml
 
 from gevent import socket
+from gevent import Timeout
 from greenlet import GreenletExit
 
 try:
@@ -24,6 +25,7 @@
 from lib.admin_connection import AdminConnection, AdminAsyncConnection
 from lib.box_connection import BoxConnection
 from lib.colorer import color_stdout, color_log
+from lib.options import Options
 from lib.preprocessor import TestState
 from lib.server import Server
 from lib.test import Test
@@ -38,12 +40,15 @@
 def save_join(green_obj, timeout=None):
     """
     Gevent join wrapper for
-    test-run stop-on-crash feature
+    test-run stop-on-crash/stop-on-timeout feature
 
-    :return True in case of crash and False otherwise
+    :return True in case of crash or test timeout and False otherwise
     """
     try:
-        green_obj.join(timeout=timeout)
+        green_obj.get(timeout=timeout)
+    except Timeout:
+        color_stdout("Test timeout of %d secs reached\t" % timeout, schema='error')
+        return True
     except GreenletExit:
         return True
     # We don't catch TarantoolStartError here to propagate it to a parent
@@ -54,7 +59,6 @@ def save_join(green_obj, timeout=None):
 class LuaTest(Test):
     """ Handle *.test.lua and *.test.sql test files. """
 
-    TIMEOUT = 60 * 10
     RESULT_FILE_VERSION_INITIAL = 1
     RESULT_FILE_VERSION_DEFAULT = 2
     RESULT_FILE_VERSION_LINE_RE = re.compile(
@@ -372,7 +376,7 @@ def execute(self, server):
         lua.start()
         crash_occured = True
         try:
-            crash_occured = save_join(lua, timeout=self.TIMEOUT)
+            crash_occured = save_join(lua, timeout=Options().args.test_timeout)
             self.killall_servers(server, ts, crash_occured)
         except KeyboardInterrupt:
             # prevent tests greenlet from writing to the real stdout