Merge branch 'ci_feature' into ci_feature_prod

Author: vishiy

source/code/dockerapi/DockerRemoteApi.cpp

@@ -21,6 +21,15 @@ def shutdown
     end
 
     def filter(tag, time, record)
+      begin
+        #Try to force utf-8 encoding on the string so that all characters can flow through to
+        #$log.info "before : #{record['LogEntry']}"
+        record['LogEntry'].force_encoding('UTF-8')
+      rescue
+        $log.error "Failed to convert record['LogEntry'] : '#{record['LogEntry']}' to UTF-8 using force_encoding."
+        $log.error "Current string encoding for record['LogEntry'] is #{record['LogEntry'].encoding}"
+      end
+
       record['Computer'] =  @hostname
       wrapper = {
                  "DataType"=>"CONTAINER_LOG_BLOB",

source/code/plugin/filter_container_log.rb

@@ -54,7 +54,11 @@ def enumerate()
                     #router.emit(@tag, time, record) if record    
             end 
 
-            router.emit_stream(@tag, eventStream) if eventStream          
+            router.emit_stream(@tag, eventStream) if eventStream
+            if (ENV['ISTEST'] == true && eventStream.count > 0)
+              $log.info("in_cadvisor_perf::emit-stream : Success @ #{Time.now.utc.iso8601}")
+            end
+
             rescue  => errorStr
             $log.warn "Failed to retrieve cadvisor metric data: #{errorStr}"
             $log.debug_backtrace(errorStr.backtrace)

source/code/plugin/in_cadvisor_perf.rb

@@ -68,16 +68,25 @@ def enumerate
                     # populate the KubeNodeInventory Status field. A possible value for this field could be "Ready OutofDisk"
                     # implying that the node is ready for hosting pods, however its out of disk.
 
-                    if items['status'].key?("conditions") && !items['status']['conditions'].empty? 
+                    if items['status'].key?("conditions") && !items['status']['conditions'].empty?
+                      allNodeConditions="" 
                       items['status']['conditions'].each do |condition|
                           if condition['status'] == "True"
-                              record['Status'] += condition['type']
+                            if !allNodeConditions.empty?
+                              allNodeConditions = allNodeConditions + "," + condition['type']
+                            else
+                              allNodeConditions = condition['type']
+                            end
                           end 
                           #collect last transition to/from ready (no matter ready is true/false)
                           if condition['type'] == "Ready" && !condition['lastTransitionTime'].nil?
                             record['LastTransitionTimeReady'] = condition['lastTransitionTime']
                           end
                       end 
+                      if !allNodeConditions.empty?
+                        record['Status'] = allNodeConditions
+                      end
+
                     end
 
                     record['KubeletVersion'] = items['status']['nodeInfo']['kubeletVersion']
@@ -90,6 +99,9 @@ def enumerate
                     eventStream.add(emitTime, wrapper) if wrapper
                 end 
                 router.emit_stream(@tag, eventStream) if eventStream
+               if (ENV['ISTEST'] == true && eventStream.count > 0)
+                 $log.info("in_kube_nodeinventory::emit-stream : Success @ #{Time.now.utc.iso8601}")
+               end
             end  
           rescue  => errorStr
             $log.warn "Failed to retrieve node inventory: #{errorStr}"

source/code/plugin/in_kube_nodes.rb

@@ -92,13 +92,39 @@ def parse_and_emit_records(podInventory, serviceList)
           record['PodLabel'] = [items['metadata']['labels']]
           record['Namespace'] = podNameSpace
           record['PodCreationTimeStamp'] = items['metadata']['creationTimestamp']
-          record['PodStartTime'] = items['status']['startTime']
-          record['PodStatus'] = items['status']['phase']
-          record['PodIp'] =items['status']['podIP']
+          #for unscheduled (non-started) pods startTime does NOT exist
+          if !items['status']['startTime'].nil?
+            record['PodStartTime'] = items['status']['startTime']
+          else
+            record['PodStartTime'] = ""
+          end
+          #podStatus
+          # the below is for accounting 'NodeLost' scenario, where-in the pod(s) in the lost node is still being reported as running
+          podReadyCondition = true
+          if !items['status']['reason'].nil? && items['status']['reason'] == "NodeLost"
+            items['status']['conditions'].each do |condition|
+              if condition['type'] == "Ready" && condition['status'] == "False"
+                podReadyCondition = false
+                break
+              end
+            end
+          end
+          if podReadyCondition == false
+            record['PodStatus'] = "Unknown"
+          else
+            record['PodStatus'] = items['status']['phase']
+          end
+          #for unscheduled (non-started) pods podIP does NOT exist
+          if !items['status']['podIP'].nil?
+            record['PodIp'] =items['status']['podIP']
+          else
+            record['PodIp'] = ""
+          end
+          #for unscheduled (non-started) pods nodeName does NOT exist
           if !items['spec']['nodeName'].nil?
             record['Computer'] = items['spec']['nodeName']
           else
-            next  
+            record['Computer'] = ""
           end  
           record['ClusterId'] = KubernetesApiClient.getClusterId
           record['ClusterName'] = KubernetesApiClient.getClusterName
@@ -134,15 +160,22 @@ def parse_and_emit_records(podInventory, serviceList)
               #      "message": "Back-off 5m0s restarting failed container=metrics-server pod=metrics-server-2011498749-3g453_kube-system(5953be5f-fcae-11e7-a356-000d3ae0e432)"
               #   }
               # },
-              record['ContainerStatus'] = containerStatus.keys[0]
+              # the below is for accounting 'NodeLost' scenario, where-in the containers in the lost node/pod(s) is still being reported as running
+              if podReadyCondition == false
+                record['ContainerStatus'] = "Unknown"
+              else
+                record['ContainerStatus'] = containerStatus.keys[0]
+              end
               #TODO : Remove ContainerCreationTimeStamp from here since we are sending it as a metric
               #Picking up both container and node start time from cAdvisor to be consistent
               if containerStatus.keys[0] == "running"
                 record['ContainerCreationTimeStamp'] = container['state']['running']['startedAt']
               end
               podRestartCount += containerRestartCount	
               records.push(record.dup) 
-            end  
+            end 
+          else # for unscheduled pods there are no status.containerStatuses, in this case we still want the pod
+            records.push(record) 
           end  #container status block end
           records.each do |record|
             if !record.nil?
@@ -157,6 +190,9 @@ def parse_and_emit_records(podInventory, serviceList)
           end  
         end  #podInventory block end
         router.emit_stream(@tag, eventStream) if eventStream
+        if (ENV['ISTEST'] == true && eventStream.count > 0)
+          $log.info("in_kube_podinventory::emit-stream : Success @ #{Time.now.utc.iso8601}")
+        end
       rescue  => errorStr
         $log.warn "Failed in parse_and_emit_record pod inventory: #{errorStr}"
         $log.debug_backtrace(errorStr.backtrace)