Updating containermonitoring addon to use the latest agent

parts/k8s/containeraddons/kubernetesmasteraddons-omsagent-daemonset.yaml

@@ -50,43 +50,143 @@ roleRef:
 ---
 kind: ConfigMap
 apiVersion: v1
-data:
-  kube.conf: "# Fluentd config file for OMS Docker - cluster components (kubeAPI)\r\n\r\n#Kubernetes
-    pod inventory\r\n<source>\r\n\ttype kubepodinventory\r\n\ttag oms.containerinsights.KubePodInventory\r\n\trun_interval
-    60s\r\n  log_level debug\r\n</source>\r\n\r\n#Kubernetes events\r\n<source>\r\n\ttype
-    kubeevents\r\n\ttag oms.api.KubeEvents.CollectionTime\r\n\trun_interval 60s\r\n
-    \ log_level debug\r\n</source>\r\n\r\n#Kubernetes logs\r\n<source>\r\n\ttype kubelogs\r\n\ttag
-    oms.api.KubeLogs\r\n\trun_interval 60s\r\n</source>\r\n\r\n#Kubernetes services\r\n<source>\r\n\ttype
-    kubeservices\r\n\ttag oms.api.KubeServices.CollectionTime\r\n\trun_interval 60s\r\n
-    \ log_level debug\r\n</source>\r\n\r\n#Kubernetes Nodes\r\n<source>\r\n\ttype
-    kubenodeinventory\r\n\ttag oms.containerinsights.KubeNodeInventory\r\n\trun_interval
-    60s\r\n  log_level debug\r\n</source>\r\n\r\n#Kubernetes perf\r\n<source>\r\n\ttype
-    kubeperf\r\n\ttag oms.api.KubePerf\r\n\trun_interval 60s\r\n  log_level debug\r\n</source>\r\n\r\n<match
-    oms.containerinsights.KubePodInventory**>\r\n  type out_oms\r\n  log_level debug\r\n
-    \ num_threads 5\r\n  buffer_chunk_limit 20m\r\n  buffer_type file\r\n  buffer_path
-    %STATE_DIR_WS%/out_oms_kubepods*.buffer\r\n  buffer_queue_limit 20\r\n  buffer_queue_full_action
-    drop_oldest_chunk\r\n  flush_interval 20s\r\n  retry_limit 10\r\n  retry_wait
-    30s\r\n  max_retry_wait 9m\r\n</match>\r\n\r\n<match oms.api.KubeEvents**>\r\n\ttype
-    out_oms_api\r\n\tlog_level debug\r\n  num_threads 5\r\n\tbuffer_chunk_limit 5m\r\n\tbuffer_type
-    file\r\n\tbuffer_path %STATE_DIR_WS%/out_oms_api_kubeevents*.buffer\r\n\tbuffer_queue_limit
-    10\r\n  buffer_queue_full_action drop_oldest_chunk\r\n\tflush_interval 20s\r\n\tretry_limit
-    10\r\n\tretry_wait 30s\r\n</match>\r\n\r\n<match oms.api.KubeLogs**>\r\n\ttype
-    out_oms_api\r\n\tlog_level debug\r\n  buffer_chunk_limit 10m\r\n\tbuffer_type
-    file\r\n\tbuffer_path %STATE_DIR_WS%/out_oms_api_kubernetes_logs*.buffer\r\n\tbuffer_queue_limit
-    10\r\n\tflush_interval 20s\r\n\tretry_limit 10\r\n\tretry_wait 30s\r\n</match>\r\n\r\n<match
-    oms.api.KubeServices**>\t  \r\n  type out_oms_api\r\n  log_level debug\r\n  num_threads
-    5\r\n  buffer_chunk_limit 20m\r\n  buffer_type file\r\n  buffer_path %STATE_DIR_WS%/out_oms_kubeservices*.buffer\r\n
-    \ buffer_queue_limit 20\r\n  buffer_queue_full_action drop_oldest_chunk\r\n  flush_interval
-    20s\r\n  retry_limit 10\r\n  retry_wait 30s\r\n  max_retry_wait 9m\r\n</match>\r\n\r\n<match
-    oms.containerinsights.KubeNodeInventory**>\r\n  type out_oms\r\n  log_level debug\r\n
-    \ num_threads 5\r\n  buffer_chunk_limit 20m\r\n  buffer_type file\r\n  buffer_path
-    %STATE_DIR_WS%/state/out_oms_kubenodes*.buffer\r\n  buffer_queue_limit 20\r\n
-    \ buffer_queue_full_action drop_oldest_chunk\r\n  flush_interval 20s\r\n  retry_limit
-    10\r\n  retry_wait 30s\r\n  max_retry_wait 9m\r\n</match>\r\n\r\n<match oms.api.KubePerf**>\t\r\n
-    \ type out_oms\r\n  log_level debug\r\n  num_threads 5\r\n  buffer_chunk_limit
-    20m\r\n  buffer_type file\r\n  buffer_path %STATE_DIR_WS%/out_oms_kubeperf*.buffer\r\n
-    \ buffer_queue_limit 20\r\n  buffer_queue_full_action drop_oldest_chunk\r\n  flush_interval
-    20s\r\n  retry_limit 10\r\n  retry_wait 30s\r\n  max_retry_wait 9m\r\n</match>\r\n"
+data:
+  kube.conf: |- 
+     # Fluentd config file for OMS Docker - cluster components (kubeAPI)
+     #Kubernetes pod inventory
+     <source>
+      type kubepodinventory
+      tag oms.containerinsights.KubePodInventory
+      run_interval 60s
+      log_level debug
+     </source>
+     #Kubernetes events
+     <source>
+      type kubeevents
+      tag oms.containerinsights.KubeEvents
+      run_interval 60s
+      log_level debug
+      </source>
+     #Kubernetes logs
+     <source>
+      type kubelogs
+      tag oms.api.KubeLogs
+      run_interval 60s
+     </source>
+     #Kubernetes services
+     <source>
+      type kubeservices
+      tag oms.containerinsights.KubeServices
+      run_interval 60s
+      log_level debug
+     </source>
+     #Kubernetes Nodes
+     <source>
+      type kubenodeinventory
+      tag oms.containerinsights.KubeNodeInventory
+      run_interval 60s
+      log_level debug
+     </source>
+     #Kubernetes perf
+     <source>
+      type kubeperf
+      tag oms.api.KubePerf
+      run_interval 60s
+      log_level debug
+     </source>
+     <match oms.containerinsights.KubePodInventory**>
+      type out_oms
+      log_level debug
+      num_threads 5
+      buffer_chunk_limit 20m
+      buffer_type file
+      buffer_path %STATE_DIR_WS%/out_oms_kubepods*.buffer
+      buffer_queue_limit 20
+      buffer_queue_full_action drop_oldest_chunk
+      flush_interval 20s
+      retry_limit 10
+      retry_wait 30s
+      max_retry_wait 9m
+     </match>
+     <match oms.containerinsights.KubeEvents**>
+      type out_oms
+      log_level debug
+      num_threads 5
+      buffer_chunk_limit 5m
+      buffer_type file
+      buffer_path %STATE_DIR_WS%/out_oms_kubeevents*.buffer
+      buffer_queue_limit 10
+      buffer_queue_full_action drop_oldest_chunk
+      flush_interval 20s
+      retry_limit 10
+      retry_wait 30s
+      max_retry_wait 9m
+     </match>
+     <match oms.api.KubeLogs**>
+      type out_oms_api
+      log_level debug
+      buffer_chunk_limit 10m
+      buffer_type file
+      buffer_path %STATE_DIR_WS%/out_oms_api_kubernetes_logs*.buffer
+      buffer_queue_limit 10
+      flush_interval 20s
+      retry_limit 10
+      retry_wait 30s
+     </match>
+     <match oms.containerinsights.KubeServices**>
+      type out_oms
+      log_level debug
+      num_threads 5
+      buffer_chunk_limit 20m
+      buffer_type file
+      buffer_path %STATE_DIR_WS%/out_oms_kubeservices*.buffer
+      buffer_queue_limit 20
+      buffer_queue_full_action drop_oldest_chunk
+      flush_interval 20s
+      retry_limit 10
+      retry_wait 30s
+      max_retry_wait 9m
+     </match>
+     <match oms.containerinsights.KubeNodeInventory**>
+      type out_oms
+      log_level debug
+      num_threads 5
+      buffer_chunk_limit 20m
+      buffer_type file
+      buffer_path %STATE_DIR_WS%/state/out_oms_kubenodes*.buffer
+      buffer_queue_limit 20
+      buffer_queue_full_action drop_oldest_chunk
+      flush_interval 20s
+      retry_limit 10
+      retry_wait 30s
+      max_retry_wait 9m
+     </match>
+     <match oms.api.ContainerNodeInventory**>
+      type out_oms_api
+      log_level debug
+      buffer_chunk_limit 20m
+      buffer_type file
+      buffer_path %STATE_DIR_WS%/out_oms_containernodeinventory*.buffer
+      buffer_queue_limit 20
+      flush_interval 20s
+      retry_limit 10
+      retry_wait 15s
+      max_retry_wait 9m
+     </match>
+     <match oms.api.KubePerf**>	
+      type out_oms
+      log_level debug
+      num_threads 5
+      buffer_chunk_limit 20m
+      buffer_type file
+      buffer_path %STATE_DIR_WS%/out_oms_kubeperf*.buffer
+      buffer_queue_limit 20
+      buffer_queue_full_action drop_oldest_chunk
+      flush_interval 20s
+      retry_limit 10
+      retry_wait 30s
+      max_retry_wait 9m
+     </match>
 metadata:
   name: omsagent-rs-config
   namespace: kube-system
@@ -136,7 +236,7 @@ spec:
                 fieldRef:
                   fieldPath: status.hostIP
             - name: ACS_RESOURCE_NAME
-              value: "my_acs_cluster_name"
+              value: "aks-engine-cluster"
             - name: DISABLE_KUBE_SYSTEM_LOG_COLLECTION
               value: "true"
             - name: ISTEST
@@ -157,7 +257,7 @@ spec:
           securityContext:
             privileged: true
           volumeMounts:
-            - mountPath: /var/run/docker.sock
+            - mountPath: /var/run/host
               name: docker-sock
             - mountPath: /var/log
               name: host-log
@@ -176,7 +276,7 @@ spec:
       volumes:
         - name: docker-sock
           hostPath:
-            path: /var/run/docker.sock
+            path: /var/run
         - name: container-hostname
           hostPath:
             path: /etc/hostname
@@ -235,7 +335,7 @@ spec:
                 fieldRef:
                   fieldPath: status.hostIP
             - name: ACS_RESOURCE_NAME
-              value: my_acs_cluster_name
+              value: "aks-engine-cluster"
             - name: DISABLE_KUBE_SYSTEM_LOG_COLLECTION
               value: "true"
             - name: ISTEST
@@ -248,7 +348,7 @@ spec:
             - containerPort: 25224
               protocol: UDP
           volumeMounts:
-            - mountPath: /var/run/docker.sock
+            - mountPath: /var/run/host
               name: docker-sock
             - mountPath: /var/log 
               name: host-log
@@ -273,7 +373,7 @@ spec:
       volumes:
         - name: docker-sock 
           hostPath:
-            path: /var/run/docker.sock
+            path: /var/run
         - name: container-hostname
           hostPath:
             path: /etc/hostname

pkg/api/addons.go

@@ -196,8 +196,8 @@ func (cs *ContainerService) setAddonsConfig(isUpdate bool) {
 		Name:    ContainerMonitoringAddonName,
 		Enabled: to.BoolPtr(DefaultContainerMonitoringAddonEnabled),
 		Config: map[string]string{
-			"omsAgentVersion":       "1.6.0-42",
-			"dockerProviderVersion": "2.0.0-3",
+			"omsAgentVersion":       "1.8.1.256",
+			"dockerProviderVersion": "3.0.0-3",
 		},
 		Containers: []KubernetesContainerSpec{
 			{
@@ -206,7 +206,7 @@ func (cs *ContainerService) setAddonsConfig(isUpdate bool) {
 				MemoryRequests: "200Mi",
 				CPULimits:      "150m",
 				MemoryLimits:   "750Mi",
-				Image:          "microsoft/oms:ciprod11292018",
+				Image:          "microsoft/oms:ciprod01092019",
 			},
 		},
 	}

pkg/api/defaults_test.go

@@ -196,7 +196,7 @@ func TestAssignDefaultAddonImages(t *testing.T) {
 		DefaultReschedulerAddonName:        "k8s.gcr.io/rescheduler:v0.3.1",
 		DefaultMetricsServerAddonName:      "k8s.gcr.io/metrics-server-amd64:v0.2.1",
 		NVIDIADevicePluginAddonName:        "nvidia/k8s-device-plugin:1.10",
-		ContainerMonitoringAddonName:       "microsoft/oms:ciprod11292018",
+		ContainerMonitoringAddonName:       "microsoft/oms:ciprod01092019",
 		IPMASQAgentAddonName:               "k8s.gcr.io/ip-masq-agent-amd64:v2.0.0",
 		AzureCNINetworkMonitoringAddonName: "containernetworking/networkmonitor:v0.0.4",
 		DefaultDNSAutoscalerAddonName:      "k8s.gcr.io/cluster-proportional-autoscaler-amd64:1.1.1",

pkg/api/k8s_versions.go

@@ -28,7 +28,7 @@ var k8sComponentVersions = map[string]map[string]string{
 		"tiller":                           "tiller:v2.11.0",
 		"rescheduler":                      "rescheduler:v0.4.0",
 		"aci-connector":                    "virtual-kubelet:latest",
-		ContainerMonitoringAddonName:       "oms:ciprod10162018-2",
+		ContainerMonitoringAddonName:       "oms:ciprod01092019",
 		AzureCNINetworkMonitoringAddonName: "networkmonitor:v0.0.4",
 		"cluster-autoscaler":               "cluster-autoscaler:v1.13.1",
 		NVIDIADevicePluginAddonName:        "k8s-device-plugin:1.11",
@@ -61,7 +61,7 @@ var k8sComponentVersions = map[string]map[string]string{
 		"tiller":                           "tiller:v2.11.0",
 		"rescheduler":                      "rescheduler:v0.4.0",
 		"aci-connector":                    "virtual-kubelet:latest",
-		ContainerMonitoringAddonName:       "oms:ciprod10162018-2",
+		ContainerMonitoringAddonName:       "oms:ciprod01092019",
 		AzureCNINetworkMonitoringAddonName: "networkmonitor:v0.0.4",
 		"cluster-autoscaler":               "cluster-autoscaler:v1.12.1",
 		NVIDIADevicePluginAddonName:        "k8s-device-plugin:1.11",
@@ -93,7 +93,7 @@ var k8sComponentVersions = map[string]map[string]string{
 		"tiller":                           "tiller:v2.11.0",
 		"rescheduler":                      "rescheduler:v0.4.0",
 		"aci-connector":                    "virtual-kubelet:latest",
-		ContainerMonitoringAddonName:       "oms:ciprod10162018-2",
+		ContainerMonitoringAddonName:       "oms:ciprod01092019",
 		AzureCNINetworkMonitoringAddonName: "networkmonitor:v0.0.4",
 		"cluster-autoscaler":               "cluster-autoscaler:v1.3.4",
 		NVIDIADevicePluginAddonName:        "k8s-device-plugin:1.11",
@@ -125,7 +125,7 @@ var k8sComponentVersions = map[string]map[string]string{
 		"tiller":                           "tiller:v2.11.0",
 		"rescheduler":                      "rescheduler:v0.3.1",
 		"aci-connector":                    "virtual-kubelet:latest",
-		ContainerMonitoringAddonName:       "oms:ciprod10162018-2",
+		ContainerMonitoringAddonName:       "oms:ciprod01092019",
 		AzureCNINetworkMonitoringAddonName: "networkmonitor:v0.0.4",
 		"cluster-autoscaler":               "cluster-autoscaler:v1.2.2",
 		NVIDIADevicePluginAddonName:        "k8s-device-plugin:1.10",
@@ -157,7 +157,7 @@ var k8sComponentVersions = map[string]map[string]string{
 		"tiller":                           "tiller:v2.11.0",
 		"rescheduler":                      "rescheduler:v0.3.1",
 		"aci-connector":                    "virtual-kubelet:latest",
-		ContainerMonitoringAddonName:       "oms:ciprod10162018-2",
+		ContainerMonitoringAddonName:       "oms:ciprod01092019",
 		AzureCNINetworkMonitoringAddonName: "networkmonitor:v0.0.4",
 		"cluster-autoscaler":               "cluster-autoscaler:v1.1.2",
 		"k8s-dns-sidecar":                  "k8s-dns-sidecar-amd64:1.14.7",
@@ -188,7 +188,7 @@ var k8sComponentVersions = map[string]map[string]string{
 		"tiller":                           "tiller:v2.11.0",
 		"rescheduler":                      "rescheduler:v0.3.1",
 		"aci-connector":                    "virtual-kubelet:latest",
-		ContainerMonitoringAddonName:       "oms:ciprod10162018-2",
+		ContainerMonitoringAddonName:       "oms:ciprod01092019",
 		AzureCNINetworkMonitoringAddonName: "networkmonitor:v0.0.4",
 		"nodestatusfreq":                   DefaultKubernetesNodeStatusUpdateFrequency,
 		"nodegraceperiod":                  DefaultKubernetesCtrlMgrNodeMonitorGracePeriod,
@@ -217,7 +217,7 @@ var k8sComponentVersions = map[string]map[string]string{
 		"tiller":                           "tiller:v2.11.0",
 		"rescheduler":                      "rescheduler:v0.3.1",
 		"aci-connector":                    "virtual-kubelet:latest",
-		ContainerMonitoringAddonName:       "oms:ciprod10162018-2",
+		ContainerMonitoringAddonName:       "oms:ciprod01092019",
 		AzureCNINetworkMonitoringAddonName: "networkmonitor:v0.0.4",
 		"nodestatusfreq":                   DefaultKubernetesNodeStatusUpdateFrequency,
 		"nodegraceperiod":                  DefaultKubernetesCtrlMgrNodeMonitorGracePeriod,
@@ -246,7 +246,7 @@ var k8sComponentVersions = map[string]map[string]string{
 		"tiller":                           "tiller:v2.11.0",
 		"rescheduler":                      "rescheduler:v0.3.1",
 		"aci-connector":                    "virtual-kubelet:latest",
-		ContainerMonitoringAddonName:       "oms:ciprod10162018-2",
+		ContainerMonitoringAddonName:       "oms:ciprod01092019",
 		AzureCNINetworkMonitoringAddonName: "networkmonitor:v0.0.4",
 		"nodestatusfreq":                   DefaultKubernetesNodeStatusUpdateFrequency,
 		"nodegraceperiod":                  DefaultKubernetesCtrlMgrNodeMonitorGracePeriod,