Add dnsmasq-metrics to the standard DNS pod

- Enables prometheus metrics on kube-dns
- Explicitly set v=0 logging for now

cluster/addons/dns/skydns-rc.yaml.base

@@ -73,10 +73,15 @@ spec:
           initialDelaySeconds: 3
           timeoutSeconds: 5
         args:
-        # command = "/kube-dns"
         - --domain=__PILLAR__DNS__DOMAIN__.
         - --dns-port=10053
+        # This should be set to v=2 only after the new image (cut from 1.5) has
+        # been released, otherwise we will flood the logs.
+        - --v=0
         __PILLAR__FEDERATIONS__DOMAIN__MAP__
+        env:
+        - name: PROMETHEUS_PORT
+          value: "10055"
         ports:
         - containerPort: 10053
           name: dns-local
@@ -84,6 +89,9 @@ spec:
         - containerPort: 10053
           name: dns-tcp-local
           protocol: TCP
+        - containerPort: 10055
+          name: metrics
+          protocol: TCP
       - name: dnsmasq
         image: gcr.io/google_containers/kube-dnsmasq-amd64:1.4
         livenessProbe:
@@ -107,6 +115,32 @@ spec:
         - containerPort: 53
           name: dns-tcp
           protocol: TCP
+        # see: https://github.com/kubernetes/kubernetes/issues/29055 for details
+        resources:
+          requests:
+            cpu: 150m
+            memory: 10Mi
+      - name: dnsmasq-metrics
+        image: gcr.io/google_containers/dnsmasq-metrics-amd64:1.0
+        livenessProbe:
+          httpGet:
+            path: /metrics
+            port: 10054
+            scheme: HTTP
+          initialDelaySeconds: 60
+          timeoutSeconds: 5
+          successThreshold: 1
+          failureThreshold: 5
+        args:
+        - --v=2
+        - --logtostderr
+        ports:
+        - containerPort: 10054
+          name: metrics
+          protocol: TCP
+        resources:
+          requests:
+            memory: 10Mi
       - name: healthz
         image: gcr.io/google_containers/exechealthz-amd64:1.2
         resources:

cluster/addons/dns/skydns-rc.yaml.in

@@ -73,10 +73,15 @@ spec:
           initialDelaySeconds: 3
           timeoutSeconds: 5
         args:
-        # command = "/kube-dns"
         - --domain={{ pillar['dns_domain'] }}.
         - --dns-port=10053
+        # This should be set to v=2 only after the new image (cut from 1.5) has
+        # been released, otherwise we will flood the logs.
+        - --v=0
         {{ pillar['federations_domain_map'] }}
+        env:
+        - name: PROMETHEUS_PORT
+          value: "10055"
         ports:
         - containerPort: 10053
           name: dns-local
@@ -84,6 +89,9 @@ spec:
         - containerPort: 10053
           name: dns-tcp-local
           protocol: TCP
+        - containerPort: 10055
+          name: metrics
+          protocol: TCP
       - name: dnsmasq
         image: gcr.io/google_containers/kube-dnsmasq-amd64:1.4
         livenessProbe:
@@ -107,6 +115,32 @@ spec:
         - containerPort: 53
           name: dns-tcp
           protocol: TCP
+        # see: https://github.com/kubernetes/kubernetes/issues/29055 for details
+        resources:
+          requests:
+            cpu: 150m
+            memory: 10Mi
+      - name: dnsmasq-metrics
+        image: gcr.io/google_containers/dnsmasq-metrics-amd64:1.0
+        livenessProbe:
+          httpGet:
+            path: /metrics
+            port: 10054
+            scheme: HTTP
+          initialDelaySeconds: 60
+          timeoutSeconds: 5
+          successThreshold: 1
+          failureThreshold: 5
+        args:
+        - --v=2
+        - --logtostderr
+        ports:
+        - containerPort: 10054
+          name: metrics
+          protocol: TCP
+        resources:
+          requests:
+            memory: 10Mi
       - name: healthz
         image: gcr.io/google_containers/exechealthz-amd64:1.2
         resources:

cluster/addons/dns/skydns-rc.yaml.sed

@@ -73,9 +73,14 @@ spec:
           initialDelaySeconds: 3
           timeoutSeconds: 5
         args:
-        # command = "/kube-dns"
         - --domain=$DNS_DOMAIN.
         - --dns-port=10053
+        # This should be set to v=2 only after the new image (cut from 1.5) has
+        # been released, otherwise we will flood the logs.
+        - --v=0
+        env:
+        - name: PROMETHEUS_PORT
+          value: "10055"
         ports:
         - containerPort: 10053
           name: dns-local
@@ -83,6 +88,9 @@ spec:
         - containerPort: 10053
           name: dns-tcp-local
           protocol: TCP
+        - containerPort: 10055
+          name: metrics
+          protocol: TCP
       - name: dnsmasq
         image: gcr.io/google_containers/kube-dnsmasq-amd64:1.4
         livenessProbe:
@@ -106,6 +114,32 @@ spec:
         - containerPort: 53
           name: dns-tcp
           protocol: TCP
+        # see: https://github.com/kubernetes/kubernetes/issues/29055 for details
+        resources:
+          requests:
+            cpu: 150m
+            memory: 10Mi
+      - name: dnsmasq-metrics
+        image: gcr.io/google_containers/dnsmasq-metrics-amd64:1.0
+        livenessProbe:
+          httpGet:
+            path: /metrics
+            port: 10054
+            scheme: HTTP
+          initialDelaySeconds: 60
+          timeoutSeconds: 5
+          successThreshold: 1
+          failureThreshold: 5
+        args:
+        - --v=2
+        - --logtostderr
+        ports:
+        - containerPort: 10054
+          name: metrics
+          protocol: TCP
+        resources:
+          requests:
+            memory: 10Mi
       - name: healthz
         image: gcr.io/google_containers/exechealthz-amd64:1.2
         resources:

cluster/gce/coreos/kube-manifests/addons/dns/skydns-rc.yaml

@@ -56,6 +56,10 @@ spec:
         # command = "/kube-dns"
         - --domain=${DNS_DOMAIN}.
         - --dns-port=10053
+        - --v=0
+        env:
+          - name: PROMETHEUS_PORT
+            value: "10055"
         ports:
         - containerPort: 10053
           name: dns-local
@@ -63,6 +67,9 @@ spec:
         - containerPort: 10053
           name: dns-tcp-local
           protocol: TCP
+        - containerPort: 10055
+          name: metrics
+          protocol: TCP
       - name: dnsmasq
         image: gcr.io/google_containers/kube-dnsmasq-amd64:1.4
         livenessProbe:
@@ -86,6 +93,27 @@ spec:
         - containerPort: 53
           name: dns-tcp
           protocol: TCP
+      - name: dnsmasq-metrics
+        image: gcr.io/google_containers/dnsmasq-metrics-amd64:1.0
+        livenessProbe:
+          httpGet:
+            path: /metrics
+            port: 10054
+            scheme: HTTP
+          initialDelaySeconds: 60
+          timeoutSeconds: 5
+          successThreshold: 1
+          failureThreshold: 5
+        args:
+        - --v=2
+        - --logtostderr
+        ports:
+        - containerPort: 10054
+          name: metrics
+          protocol: TCP
+        resources:
+          requests:
+            memory: 10Mi
       - name: healthz
         image: gcr.io/google_containers/exechealthz-amd64:1.2
         resources:

cluster/juju/layers/kubernetes/templates/kubedns-rc.yaml

@@ -72,8 +72,12 @@ spec:
         # command = "/kube-dns"
         - --domain={{ pillar['dns_domain'] }}.
         - --dns-port=10053
+        - --v=0
         - --kube_master_url=http://{{ private_address }}:8080
         {{ pillar['federations_domain_map'] }}
+        env:
+          - name: PROMETHEUS_PORT
+            value: "10055"
         ports:
         - containerPort: 10053
           name: dns-local
@@ -81,6 +85,9 @@ spec:
         - containerPort: 10053
           name: dns-tcp-local
           protocol: TCP
+        - containerPort: 10055
+          name: metrics
+          protocol: TCP
       - name: dnsmasq
         image: gcr.io/google_containers/kube-dnsmasq-{{ arch }}:1.4
         livenessProbe:
@@ -104,6 +111,27 @@ spec:
         - containerPort: 53
           name: dns-tcp
           protocol: TCP
+      - name: dnsmasq-metrics
+        image: gcr.io/google_containers/dnsmasq-metrics-amd64:1.0
+        livenessProbe:
+          httpGet:
+            path: /metrics
+            port: 10054
+            scheme: HTTP
+          initialDelaySeconds: 60
+          timeoutSeconds: 5
+          successThreshold: 1
+          failureThreshold: 5
+        args:
+        - --v=2
+        - --logtostderr
+        ports:
+        - containerPort: 10054
+          name: metrics
+          protocol: TCP
+        resources:
+          requests:
+            memory: 10Mi
       - name: healthz
         image: gcr.io/google_containers/exechealthz-{{ arch }}:1.2
         resources: