sensu 0.20.2 → 0.20.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 540fbe4cb2a3911f73843e77d4986c9dd90b92d6
-  data.tar.gz: eb5827d8b2d41073722166e1da5d6f3a6028be2c
+  metadata.gz: b4b99ec27fad9dd917c0a15b4aee2effdd105cce
+  data.tar.gz: 6599a21f33b14289af3b2d4bc7ecbf983853f16c
 SHA512:
-  metadata.gz: 55b82945c73ea8689cc18ce34ba8c7cdb4c1ac9db752821afe012a7316af6fc5671850d79d94272f1d56ea9540cfcaf30f3073207aa47992ba6ddbcaeae93423
-  data.tar.gz: f96fbe0650b5f7b533ed1a1325ca8de822f61218556e4023a12dff404a238dd8c2662cbe2f1266206f6416eb39407dcb210cfc410dabfb5499c9b29b6c9ae563
+  metadata.gz: 495461ab13fbeb0c93e838e66f357cb7a109fabd7467ec8fff47a78c565a1964563af35b580058a2f79bbaf0bff6c193939532744119c16a39fc83a72fc24620
+  data.tar.gz: 2d9b0a49eb9c887b9061020cf10ec42fe2c73e9e70d936def991a0f30243c8526536a8e4d069dafeaef7e31e0a3e304b3f283044a0fa892fb1bb1edc1c677882

data/CHANGELOG.md

@@ -1,3 +1,14 @@
+## 0.20.3 - 2015-08-11
+
+### Other
+
+Improved Sensu server leader election and resignation. Changes include the
+use of a unique leader ID to help guard against cases where there could be
+multiple leaders.
+
+Fixed bridge extensions; they now receive all event data, including events
+that normally do not result in an action (e.g. OK check results).
+
 ## 0.20.2 - 2015-08-06
 
 ### Other

data/lib/sensu/constants.rb

@@ -1,7 +1,7 @@
 module Sensu
   unless defined?(Sensu::VERSION)
     # Sensu release version.
-    VERSION = "0.20.2"
+    VERSION = "0.20.3"
 
     # Sensu check severities.
     SEVERITIES = %w[ok warning critical unknown]

data/lib/sensu/server/process.rb

@@ -126,37 +126,17 @@ module Sensu
         }.flatten.compact.uniq
       end
 
-      # Run event bridge extensions, within the Sensu EventMachine
-      # reactor (event loop). The extension API `safe_run()` method is
-      # used to guard against most errors. Bridges are for relaying
-      # Sensu event data to other services.
-      #
-      # @param event [Hash]
-      def event_bridges(event)
-        @extensions[:bridges].each do |name, bridge|
-          bridge.safe_run(event) do |output, status|
-            @logger.debug("bridge extension output", {
-              :extension => bridge.definition,
-              :output => output
-            })
-          end
-        end
-      end
-
       # Process an event: filter -> mutate -> handle.
       #
-      # This method runs event bridges, relaying the event data to
-      # other services. This method also determines the appropriate
-      # handlers for the event, filtering and mutating the event data
-      # for each of them. The `@handling_event_count` is incremented
-      # by `1`, for each event handler chain (filter -> mutate ->
-      # handle).
+      # This method determines the appropriate handlers for an event,
+      # filtering and mutating the event data for each of them. The
+      # `@handling_event_count` is incremented by `1`, for each event
+      # handler chain (filter -> mutate -> handle).
       #
       # @param event [Hash]
       def process_event(event)
         log_level = event[:check][:type] == "metric" ? :debug : :info
         @logger.send(log_level, "processing event", :event => event)
-        event_bridges(event)
         handler_list = Array((event[:check][:handlers] || event[:check][:handler]) || "default")
         handlers = derive_handlers(handler_list)
         handlers.each do |handler|
@@ -169,6 +149,23 @@ module Sensu
         end
       end
 
+      # Run event bridge extensions, within the Sensu EventMachine
+      # reactor (event loop). The extension API `safe_run()` method is
+      # used to guard against most errors. Bridges are for relaying
+      # Sensu event data to other services.
+      #
+      # @param event [Hash]
+      def event_bridges(event)
+        @extensions[:bridges].each do |name, bridge|
+          bridge.safe_run(event) do |output, status|
+            @logger.debug("bridge extension output", {
+              :extension => bridge.definition,
+              :output => output
+            })
+          end
+        end
+      end
+
       # Add a check result to an aggregate. A check aggregate uses the
       # check `:name` and the `:issued` timestamp as its unique
       # identifier. An aggregate uses several counters: the total
@@ -300,8 +297,10 @@ module Sensu
       # registry. If the previous conditions are not met, and check
       # `:type` is `metric` and the `:status` is `0`, the event
       # registry is not updated, but the provided callback is called
-      # with the event data. JSON serialization is used when storing
-      # data in the registry.
+      # with the event data. All event data is sent to event bridge
+      # extensions, including events that do not normally produce an
+      # action. JSON serialization is used when storing data in the
+      # registry.
       #
       # @param client [Hash]
       # @param check [Hash]
@@ -338,6 +337,7 @@ module Sensu
           elsif check[:type] == "metric"
             callback.call(event)
           end
+          event_bridges(event)
         end
       end
 
@@ -746,8 +746,85 @@ module Sensu
         setup_check_result_aggregation_pruner
       end
 
+      # Create a lock timestamp (integer), current time including
+      # milliseconds. This method is used by Sensu server leader
+      # election.
+      #
+      # @return [Integer]
+      def create_lock_timestamp
+        (Time.now.to_f * 1000).to_i
+      end
+
+      # Create/return the unique Sensu server leader ID for the
+      # current process.
+      #
+      # @return [String]
+      def leader_id
+        @leader_id ||= random_uuid
+      end
+
+      # Become the Sensu server leader, responsible for specific
+      # duties (`leader_duties()`). Unless the current process is
+      # already the leader, this method sets the leader ID stored in
+      # Redis to the unique random leader ID for the process. If the
+      # leader ID in Redis is successfully updated, `@is_leader` is
+      # set to true and `leader_duties()` is called to begin the
+      # tasks/duties of the Sensu server leader.
+      def become_the_leader
+        unless @is_leader
+          @redis.set("leader", leader_id) do
+            @logger.info("i am now the leader")
+            @is_leader = true
+            leader_duties
+          end
+        else
+          @logger.debug("i am already the leader")
+        end
+      end
+
+      # Resign as leader, if the current process is the Sensu server
+      # leader. This method cancels and clears the leader timers,
+      # those with references stored in the timers hash under
+      # `:leader`, and `@is_leader` is set to `false`. The leader ID
+      # and leader lock are not removed from Redis, as they will be
+      # updated when another server is elected to be the leader, this
+      # method does not need to handle Redis connectivity issues.
+      def resign_as_leader
+        if @is_leader
+          @logger.warn("resigning as leader")
+          @timers[:leader].each do |timer|
+            timer.cancel
+          end
+          @timers[:leader].clear
+          @is_leader = false
+        else
+          @logger.debug("not currently the leader")
+        end
+      end
+
+      # Updates the Sensu server leader lock timestamp. The current
+      # leader ID is retrieved from Redis and compared with the leader
+      # ID of the current process to determine if it is still the
+      # Sensu server leader. If the current process is still the
+      # leader, the leader lock timestamp is updated. If the current
+      # process is no longer the leader (regicide),
+      # `resign_as_leader()` is called for cleanup, so there is not
+      # more than one leader.
+      def update_leader_lock
+        @redis.get("leader") do |current_leader_id|
+          if current_leader_id == leader_id
+            @redis.set("lock:leader", create_lock_timestamp) do
+              @logger.debug("updated leader lock timestamp")
+            end
+          else
+            @logger.warn("another sensu server has been elected as leader")
+            resign_as_leader
+          end
+        end
+      end
+
       # Request a leader election, a process to determine if the
-      # current process is the leader Sensu server, with its
+      # current process is the Sensu server leader, with its
       # own/unique duties. A Redis key/value is used as a central
       # lock, using the "SETNX" Redis command to set the key/value if
       # it does not exist, using a timestamp for the value. If the
@@ -758,23 +835,18 @@ module Sensu
       # "GETSET" Redis command is used to set a new timestamp and
       # fetch the previous value to compare them, to determine if it
       # was set by the current process. If the current process is able
-      # to set the timestamp value, it becomes the leader. The leader
-      # has `@is_leader` set to `true`.
+      # to set the timestamp value, it becomes the leader.
       def request_leader_election
-        @redis.setnx("lock:leader", Time.now.to_i) do |created|
+        @redis.setnx("lock:leader", create_lock_timestamp) do |created|
           if created
-            @is_leader = true
-            @logger.info("i am the leader")
-            leader_duties
+            become_the_leader
           else
-            @redis.get("lock:leader") do |current_timestamp|
-              lock_timestamp = (Time.now.to_f * 1000).to_i
-              if lock_timestamp - current_timestamp.to_i >= 30000
-                @redis.getset("lock:leader", lock_timestamp) do |previous_timestamp|
-                  if previous_timestamp == current_timestamp
-                    @is_leader = true
-                    @logger.info("i am now the leader")
-                    leader_duties
+            @redis.get("lock:leader") do |current_lock_timestamp|
+              new_lock_timestamp = create_lock_timestamp
+              if new_lock_timestamp - current_lock_timestamp.to_i >= 30000
+                @redis.getset("lock:leader", new_lock_timestamp) do |previous_lock_timestamp|
+                  if previous_lock_timestamp == current_lock_timestamp
+                    become_the_leader
                   end
                 end
               end
@@ -795,33 +867,13 @@ module Sensu
         end
         @timers[:run] << EM::PeriodicTimer.new(10) do
           if @is_leader
-            lock_timestamp = (Time.now.to_f * 1000).to_i
-            @redis.set("lock:leader", lock_timestamp) do
-              @logger.debug("updated leader lock timestamp")
-            end
+            update_leader_lock
           else
             request_leader_election
           end
         end
       end
 
-      # Resign as leader, if the current process is the Sensu server
-      # leader. This method cancels and clears the leader timers,
-      # those with references stored in the timers hash under
-      # `:leader`, and `@is_leader`is set to `false`.
-      def resign_as_leader
-        if @is_leader
-          @logger.warn("resigning as leader")
-          @timers[:leader].each do |timer|
-            timer.cancel
-          end
-          @timers[:leader].clear
-          @is_leader = false
-        else
-          @logger.debug("not currently leader")
-        end
-      end
-
       # Unsubscribe from transport subscriptions (all of them). This
       # method is called when there are issues with connectivity, or
       # the process is stopping.

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: sensu
 version: !ruby/object:Gem::Version
-  version: 0.20.2
+  version: 0.20.3
 platform: ruby
 authors:
 - Sean Porter
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-08-06 00:00:00.000000000 Z
+date: 2015-08-11 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: multi_json