Merge pull request #9739 from dgquintas/traceback_port_server

Port server missing import

1 files changed, 97 insertions, 89 deletions

diff --git a/tools/run_tests/python_utils/start_port_server.py b/tools/run_tests/python_utils/start_port_server.py
index 8ee7080168..4c9f6aac63 100644
--- a/tools/run_tests/python_utils/start_port_server.py
+++ b/tools/run_tests/python_utils/start_port_server.py
@@ -30,101 +30,109 @@
 from __future__ import print_function
 
 from six.moves import urllib
+import jobset
+import logging
 import os
+import socket
 import subprocess
-import tempfile
 import sys
+import tempfile
 import time
-import jobset
-import socket
+
 
 def start_port_server(port_server_port):
-  # check if a compatible port server is running
-  # if incompatible (version mismatch) ==> start a new one
-  # if not running ==> start a new one
-  # otherwise, leave it up
-  try:
-    version = int(urllib.request.urlopen(
-        'http://localhost:%d/version_number' % port_server_port,
-        timeout=10).read())
-    print('detected port server running version %d' % version)
-    running = True
-  except Exception as e:
-    print('failed to detect port server: %s' % sys.exc_info()[0])
-    print(e.strerror)
-    running = False
-  if running:
-    current_version = int(subprocess.check_output(
-        [sys.executable, os.path.abspath('tools/run_tests/python_utils/port_server.py'),
-         'dump_version']))
-    print('my port server is version %d' % current_version)
-    running = (version >= current_version)
+    # check if a compatible port server is running
+    # if incompatible (version mismatch) ==> start a new one
+    # if not running ==> start a new one
+    # otherwise, leave it up
+    try:
+        version = int(
+            urllib.request.urlopen(
+                'http://localhost:%d/version_number' % port_server_port,
+                timeout=10).read())
+        logging.info('detected port server running version %d', version)
+        running = True
+    except Exception as e:
+        logging.exception('failed to detect port server')
+        running = False
+    if running:
+        current_version = int(
+            subprocess.check_output([
+                sys.executable, os.path.abspath(
+                    'tools/run_tests/python_utils/port_server.py'),
+                'dump_version'
+            ]))
+        logging.info('my port server is version %d', current_version)
+        running = (version >= current_version)
+        if not running:
+            logging.info('port_server version mismatch: killing the old one')
+            urllib.request.urlopen('http://localhost:%d/quitquitquit' %
+                                   port_server_port).read()
+            time.sleep(1)
     if not running:
-      print('port_server version mismatch: killing the old one')
-      urllib.request.urlopen('http://localhost:%d/quitquitquit' % port_server_port).read()
-      time.sleep(1)
-  if not running:
-    fd, logfile = tempfile.mkstemp()
-    os.close(fd)
-    print('starting port_server, with log file %s' % logfile)
-    args = [sys.executable, os.path.abspath('tools/run_tests/python_utils/port_server.py'),
-            '-p', '%d' % port_server_port, '-l', logfile]
-    env = dict(os.environ)
-    env['BUILD_ID'] = 'pleaseDontKillMeJenkins'
-    if jobset.platform_string() == 'windows':
-      # Working directory of port server needs to be outside of Jenkins
-      # workspace to prevent file lock issues.
-      tempdir = tempfile.mkdtemp()
-      port_server = subprocess.Popen(
-          args,
-          env=env,
-          cwd=tempdir,
-          creationflags = 0x00000008, # detached process
-          close_fds=True)
-    else:
-      port_server = subprocess.Popen(
-          args,
-          env=env,
-          preexec_fn=os.setsid,
-          close_fds=True)
-    time.sleep(1)
-    # ensure port server is up
-    waits = 0
-    while True:
-      if waits > 10:
-        print('killing port server due to excessive start up waits')
-        port_server.kill()
-      if port_server.poll() is not None:
-        print('port_server failed to start')
-        # try one final time: maybe another build managed to start one
+        fd, logfile = tempfile.mkstemp()
+        os.close(fd)
+        logging.info('starting port_server, with log file %s', logfile)
+        args = [
+            sys.executable,
+            os.path.abspath('tools/run_tests/python_utils/port_server.py'),
+            '-p', '%d' % port_server_port, '-l', logfile
+        ]
+        env = dict(os.environ)
+        env['BUILD_ID'] = 'pleaseDontKillMeJenkins'
+        if jobset.platform_string() == 'windows':
+            # Working directory of port server needs to be outside of Jenkins
+            # workspace to prevent file lock issues.
+            tempdir = tempfile.mkdtemp()
+            port_server = subprocess.Popen(
+                args,
+                env=env,
+                cwd=tempdir,
+                creationflags=0x00000008,  # detached process
+                close_fds=True)
+        else:
+            port_server = subprocess.Popen(
+                args, env=env, preexec_fn=os.setsid, close_fds=True)
         time.sleep(1)
-        try:
-          urllib.request.urlopen('http://localhost:%d/get' % port_server_port,
-                          timeout=1).read()
-          print('last ditch attempt to contact port server succeeded')
-          break
-        except:
-          traceback.print_exc()
-          port_log = open(logfile, 'r').read()
-          print(port_log)
-          sys.exit(1)
-      try:
-        urllib.request.urlopen('http://localhost:%d/get' % port_server_port,
+        # ensure port server is up
+        waits = 0
+        while True:
+            if waits > 10:
+                logging.warning(
+                    'killing port server due to excessive start up waits')
+                port_server.kill()
+            if port_server.poll() is not None:
+                logging.error('port_server failed to start')
+                # try one final time: maybe another build managed to start one
+                time.sleep(1)
+                try:
+                    urllib.request.urlopen(
+                        'http://localhost:%d/get' % port_server_port,
                         timeout=1).read()
-        print('port server is up and ready')
-        break
-      except socket.timeout:
-        print('waiting for port_server: timeout')
-        traceback.print_exc();
-        time.sleep(1)
-        waits += 1
-      except urllib.error.URLError:
-        print('waiting for port_server: urlerror')
-        traceback.print_exc();
-        time.sleep(1)
-        waits += 1
-      except:
-        traceback.print_exc()
-        port_server.kill()
-        raise
-
+                    logging.info(
+                        'last ditch attempt to contact port server succeeded')
+                    break
+                except:
+                    logging.exception(
+                        'final attempt to contact port server failed')
+                    port_log = open(logfile, 'r').read()
+                    print(port_log)
+                    sys.exit(1)
+            try:
+                port_server_url = 'http://localhost:%d/get' % port_server_port
+                urllib.request.urlopen(port_server_url, timeout=1).read()
+                logging.info('port server is up and ready')
+                break
+            except socket.timeout:
+                logging.exception('while waiting for port_server')
+                time.sleep(1)
+                waits += 1
+            except urllib.error.URLError:
+                logging.exception('while waiting for port_server')
+                time.sleep(1)
+                waits += 1
+            except:
+                logging.exception('error while contacting port server at "%s".'
+                                  'Will try killing it.', port_server_url)
+                port_server.kill()
+                raise