Monitoring proxy for time series data

appengine/chrome_infra_mon_proxy/main.py

Index: appengine/chrome_infra_mon_proxy/main.py
diff --git a/appengine/chrome_infra_mon_proxy/main.py b/appengine/chrome_infra_mon_proxy/main.py
new file mode 100644
index 0000000000000000000000000000000000000000..0eaf309a5af18bfe5d43ad20fefc33298f3a2c62
--- /dev/null
+++ b/appengine/chrome_infra_mon_proxy/main.py
@@ -0,0 +1,103 @@
+# Copyright 2015 The Chromium Authors. All rights reserved.
+# Use of this source code is governed by a BSD-style license that can be
+# found in the LICENSE file.
+
+import logging
+import random
+import os
+import sys
+import time
+import urllib2
+import webapp2
+
+from protorpc import messages
+from protorpc import message_types
+from protorpc import remote
+
+from google.appengine.api import app_identity, taskqueue
+
+import common
+from components import auth
+
+VM_MODULES = ['vm1', 'vm2', 'vm3']
+
+
+def require_group_membership(group_name):
+  """Authenticating decorator for handler methods.
+
+  Requires the user to be part of group in production, and
+  skips authorization for dev appserver.
+  """
+  if common.is_development_server():
+    auth_decorator = auth.public
+  else:
+    auth_decorator = auth.require( # pragma: no branch
+        lambda: auth.is_group_member(group_name))
+
+  def decorator(fn):
+    return auth_decorator(fn)
+  return decorator
+
+
+class NoBackendException(Exception):
+  pass
+
+
+class LoadBalancer(object):
+  """Balance the load among VM modules.
+
+  TODO(sergeyberezin): take into account health checks on the
+  corresponding NAT boxes. Specifically, fetch the health status
+  from the datastore in __init__(), and update it periodically as needed.
+  """
+  def __init__(self):
+    pass
+
+  def choose_module(self):
+    """Select a module to send the data to."""
+    # TODO(sergeyberezin) Implement load percentages for modules, for
+    # draining / canary / live rolling updates.
+    # TODO(sergeyberezin): perform health checks for the corresponding
+    # NAT boxes and drain modules appropriately.
+    return random.choice(VM_MODULES)
+
+
+def forward_data(data):

[agable, 2015/04/27 20:51:07]

Not in this CL, but immediately after: I'd like the ability (temporarily) to
split traffic between various forwarding locations. In particular so that I can
spin up the entire linux fleet sending data to the app to make sure it works,
but then still be able to slowly ramp up traffic to the real mon-api. So we
could send 90% to /dev/null and 10% to the real endpoint, and then 50/50, etc.

[Sergey Berezin, 2015/04/27 21:45:51]

Good idea, I'll add it to the list. I was thinking about a similar feature to
spin down / ramp up traffic to individual VM modules, so we can gracefully
rollout updates.

+  """Forwards the raw data to the backend."""
+  # Task queue should work correctly both in dev and prod server.
+  lb = LoadBalancer()
+  module_name = lb.choose_module()
+  logging.info('Forwarding request to module: %s', module_name)
+  hostname = app_identity.get_default_version_hostname()
+  if common.is_development_server():
+    protocol = 'http'
+  else:
+    protocol = 'https'
+  url = '%s://%s/%s' % (protocol, hostname, module_name)
+  request = urllib2.Request(url, data)
+  urllib2.urlopen(request)
+
+
+class MonacqHandler(auth.AuthenticatingHandler):
+  # Disable XSRF in local dev appserver; otherwise requests will fail.
+  if common.is_development_server():
+    xsrf_token_enforce_on = []  # pragma: no cover
+
+  @require_group_membership('service-account-monitoring-proxy')
+  def post(self):
+    forward_data(self.request.body)
+
+
+class MainHandler(common.BaseHandler):
+  def get(self):
+    self.render_response('main.html', title='Chrome Infra Monitoring Proxy')
+
+
+logging.basicConfig(level=logging.DEBUG)
+
+main_handlers = [
+    (r'/', MainHandler),
+    (r'/monacq', MonacqHandler),
+]
+
+app = webapp2.WSGIApplication(main_handlers, debug=True)