November release fixes - activate one agent, adx schema v2, win perf issue, syslog deactivation

build/linux/installer/scripts/livenessprobe.sh

@@ -4,15 +4,25 @@
 (ps -ef | grep omsagent- | grep -v "grep")
 if [ $? -ne 0 ]
 then
- echo "Agent is NOT running" > /dev/termination-log
+ echo " omsagent is not running" > /dev/termination-log
  exit 1
 fi
 
+#optionally test to exit non zero value if oneagent is not running
+if [ -e "/opt/AZMON_CONTAINER_LOGS_EFFECTIVE_ROUTE_V2" ]; then
+  (ps -ef | grep "mdsd -l" | grep -v "grep")
+  if [ $? -ne 0 ]
+  then
+   echo "oneagent is not running" > /dev/termination-log
+   exit 1
+  fi
+fi
+
 #test to exit non zero value if fluentbit is not running
 (ps -ef | grep td-agent-bit | grep -v "grep")
 if [ $? -ne 0 ]
 then
- echo "Fluentbit is NOT running" > /dev/termination-log
+ echo "Fluentbit is not running" > /dev/termination-log
  exit 1
 fi
 

charts/azuremonitor-containers/templates/omsagent-daemonset-windows.yaml

@@ -46,7 +46,7 @@ spec:
        {{- end }}
        imagePullPolicy: IfNotPresent
        resources:
-{{ toYaml .Values.omsagent.resources.daemonset | indent 9 }}
+{{ toYaml .Values.omsagent.resources.daemonset-windows | indent 9 }}
        env:
        {{- if ne .Values.omsagent.env.clusterId "<your_cluster_id>" }}
        - name: AKS_RESOURCE_ID
@@ -96,6 +96,7 @@ spec:
               - C:\opt\omsagentwindows\scripts\cmd\livenessProbe.cmd
           periodSeconds: 60
           initialDelaySeconds: 180
+          timeoutSeconds: 15
    {{- with .Values.omsagent.tolerations }}
    tolerations: {{- toYaml . | nindent 8 }}
    {{- end }}

charts/azuremonitor-containers/templates/omsagent-daemonset.yaml

@@ -40,7 +40,7 @@ spec:
        {{- end }}
        imagePullPolicy: IfNotPresent
        resources:
-{{ toYaml .Values.omsagent.resources.daemonset | indent 9 }}
+{{ toYaml .Values.omsagent.resources.daemonset-linux | indent 9 }}
        env:
        {{- if ne .Values.omsagent.env.clusterId "<your_cluster_id>" }}
        - name: AKS_RESOURCE_ID

charts/azuremonitor-containers/values.yaml

@@ -116,13 +116,17 @@ omsagent:
   ## ref: http://kubernetes.io/docs/user-guide/compute-resources/
   ##
   resources:
-    daemonset:
+    daemonset-linux:
       requests:
         cpu: 75m
         memory: 225Mi
       limits:
         cpu: 150m
         memory: 600Mi
+    daemonset-windows:
+      limits:
+        cpu: 200m
+        memory: 600Mi
     deployment:
       requests:
         cpu: 150m

kubernetes/linux/main.sh

@@ -416,6 +416,97 @@ echo "DOCKER_CIMPROV_VERSION=$DOCKER_CIMPROV_VERSION"
 export DOCKER_CIMPROV_VERSION=$DOCKER_CIMPROV_VERSION
 echo "export DOCKER_CIMPROV_VERSION=$DOCKER_CIMPROV_VERSION" >> ~/.bashrc
 
+#region check to auto-activate oneagent, to route container logs,
+#Intent is to activate one agent routing for all managed clusters with region in the regionllist, unless overridden by configmap
+# AZMON_CONTAINER_LOGS_ROUTE  will have route (if any) specified in the config map 
+# AZMON_CONTAINER_LOGS_EFFECTIVE_ROUTE will have the final route that we compute & set, based on our region list logic
+echo "************start oneagent log routing checks************"
+# by default, use configmap route for safer side
+AZMON_CONTAINER_LOGS_EFFECTIVE_ROUTE=$AZMON_CONTAINER_LOGS_ROUTE
+
+#trim region list
+oneagentregions="$(echo $AZMON_CONTAINERLOGS_ONEAGENT_REGIONS | xargs)"
+#lowercase region list
+typeset -l oneagentregions=$oneagentregions
+echo "oneagent regions: $oneagentregions"
+#trim current region
+currentregion="$(echo $AKS_REGION | xargs)"
+#lowercase current region
+typeset -l currentregion=$currentregion
+echo "current region: $currentregion"
+
+#initilze isoneagentregion as false
+isoneagentregion=false
+
+#set isoneagentregion as true if matching region is found
+if [ ! -z $oneagentregions ] && [ ! -z $currentregion ]; then
+  for rgn in $(echo $oneagentregions | sed "s/,/ /g"); do
+    if [ "$rgn" == "$currentregion" ]; then
+          isoneagentregion=true
+          echo "current region is in oneagent regions..."
+          break
+    fi
+  done
+else
+  echo "current region is not in oneagent regions..."
+fi
+
+if [ "$isoneagentregion" = true ]; then 
+   #if configmap has a routing for logs, but current region is in the oneagent region list, take the configmap route
+   if [ ! -z $AZMON_CONTAINER_LOGS_ROUTE ]; then   
+      AZMON_CONTAINER_LOGS_EFFECTIVE_ROUTE=$AZMON_CONTAINER_LOGS_ROUTE
+      echo "oneagent region is true for current region:$currentregion and config map logs route is not empty. so using config map logs route as effective route:$AZMON_CONTAINER_LOGS_EFFECTIVE_ROUTE"
+   else #there is no configmap route, so route thru oneagent
+      AZMON_CONTAINER_LOGS_EFFECTIVE_ROUTE="v2"
+      echo "oneagent region is true for current region:$currentregion and config map logs route is empty. so using oneagent as effective route:$AZMON_CONTAINER_LOGS_EFFECTIVE_ROUTE"
+   fi
+else
+   echo "oneagent region is false for current region:$currentregion"
+fi
+
+
+#start oneagent
+if [ ! -e "/etc/config/kube.conf" ]; then
+   if [ ! -z $AZMON_CONTAINER_LOGS_EFFECTIVE_ROUTE ]; then
+      echo "container logs configmap route is $AZMON_CONTAINER_LOGS_ROUTE"
+      echo "container logs effective route is $AZMON_CONTAINER_LOGS_EFFECTIVE_ROUTE"
+      #trim
+      containerlogsroute="$(echo $AZMON_CONTAINER_LOGS_EFFECTIVE_ROUTE | xargs)"
+      # convert to lowercase
+      typeset -l containerlogsroute=$containerlogsroute
+
+      echo "setting AZMON_CONTAINER_LOGS_EFFECTIVE_ROUTE as :$containerlogsroute"
+      export AZMON_CONTAINER_LOGS_EFFECTIVE_ROUTE=$containerlogsroute
+      echo "export AZMON_CONTAINER_LOGS_EFFECTIVE_ROUTE=$containerlogsroute" >> ~/.bashrc
+      source ~/.bashrc
+
+      if [ "$containerlogsroute" == "v2" ]; then
+            echo "activating oneagent..."
+            echo "configuring mdsd..."
+            cat /etc/mdsd.d/envmdsd | while read line; do
+                  echo $line >> ~/.bashrc
+            done
+            source /etc/mdsd.d/envmdsd
+
+            echo "setting mdsd workspaceid & key for workspace:$CIWORKSPACE_id"
+            export CIWORKSPACE_id=$CIWORKSPACE_id
+            echo "export CIWORKSPACE_id=$CIWORKSPACE_id" >> ~/.bashrc
+            export CIWORKSPACE_key=$CIWORKSPACE_key
+            echo "export CIWORKSPACE_key=$CIWORKSPACE_key" >> ~/.bashrc
+
+            source ~/.bashrc
+
+            dpkg -l | grep mdsd | awk '{print $2 " " $3}'
+
+            echo "starting mdsd ..."
+            mdsd -l -e ${MDSD_LOG}/mdsd.err -w ${MDSD_LOG}/mdsd.warn -o ${MDSD_LOG}/mdsd.info -q ${MDSD_LOG}/mdsd.qos &
+
+            touch /opt/AZMON_CONTAINER_LOGS_EFFECTIVE_ROUTE_V2
+      fi
+   fi
+fi
+echo "************end oneagent log routing checks************"
+
 #telegraf & fluentbit requirements
 if [ ! -e "/etc/config/kube.conf" ]; then
       if [ "$CONTAINER_RUNTIME" == "docker" ]; then
@@ -491,37 +582,13 @@ dpkg -l | grep td-agent-bit | awk '{print $2 " " $3}'
 
 #dpkg -l | grep telegraf | awk '{print $2 " " $3}'
 
-#start oneagent
-if [ ! -e "/etc/config/kube.conf" ]; then
-   if [ ! -z $AZMON_CONTAINER_LOGS_ROUTE ]; then
-      echo "container logs route is defined as $AZMON_CONTAINER_LOGS_ROUTE"
-      #trim
-      containerlogsroute="$(echo $AZMON_CONTAINER_LOGS_ROUTE | xargs)"
-      # convert to lowercase
-      typeset -l containerlogsroute=$containerlogsroute
-      if [ "$containerlogsroute" == "v2" ]; then
-            echo "containerlogsroute $containerlogsroute"
-            echo "configuring mdsd..."
-            cat /etc/mdsd.d/envmdsd | while read line; do
-                  echo $line >> ~/.bashrc
-            done
-            source /etc/mdsd.d/envmdsd
 
-            echo "setting mdsd workspaceid & key for workspace:$CIWORKSPACE_id"
-            export CIWORKSPACE_id=$CIWORKSPACE_id
-            echo "export CIWORKSPACE_id=$CIWORKSPACE_id" >> ~/.bashrc
-            export CIWORKSPACE_key=$CIWORKSPACE_key
-            echo "export CIWORKSPACE_key=$CIWORKSPACE_key" >> ~/.bashrc
 
-            source ~/.bashrc
+echo "stopping rsyslog..."
+service rsyslog stop
 
-            dpkg -l | grep mdsd | awk '{print $2 " " $3}'
-
-            echo "starting mdsd ..."
-            mdsd -l -e ${MDSD_LOG}/mdsd.err -w ${MDSD_LOG}/mdsd.warn -o ${MDSD_LOG}/mdsd.info -q ${MDSD_LOG}/mdsd.qos &
-      fi
-   fi
-fi
+echo "getting rsyslog status..."
+service rsyslog status
 
 shutdown() {
 	/opt/microsoft/omsagent/bin/service_control stop

kubernetes/linux/setup.sh

@@ -31,8 +31,8 @@ mv $TMPDIR/omsbundle* $TMPDIR/omsbundle
 /usr/bin/dpkg -i $TMPDIR/omsbundle/110/omsagent*.deb
 #/usr/bin/dpkg -i $TMPDIR/omsbundle/100/omsconfig*.deb
 
-#install oneagent - Latest dev bits (7/17)
-wget https://github.com/microsoft/Docker-Provider/releases/download/7172020-oneagent/azure-mdsd_1.5.124-build.develop.1294_x86_64.deb
+#install oneagent - Official bits (10/18)
+wget https://github.com/microsoft/Docker-Provider/releases/download/10182020-oneagent/azure-mdsd_1.5.126-build.master.99_x86_64.deb
 /usr/bin/dpkg -i $TMPDIR/azure-mdsd*.deb
 cp -f $TMPDIR/mdsd.xml /etc/mdsd.d
 cp -f $TMPDIR/envmdsd /etc/mdsd.d

kubernetes/omsagent.yaml

@@ -347,7 +347,7 @@ spec:
           imagePullPolicy: IfNotPresent
           resources:
             limits:
-              cpu: 150m
+              cpu: 250m
               memory: 600Mi
             requests:
               cpu: 75m
@@ -370,6 +370,8 @@ spec:
             # Update this with the user assigned msi client id for omsagent
             - name: USER_ASSIGNED_IDENTITY_CLIENT_ID
               value: ""
+            - name: AZMON_CONTAINERLOGS_ONEAGENT_REGIONS
+              value: "koreacentral,norwayeast"
           securityContext:
             privileged: true
           ports:
@@ -650,11 +652,8 @@ spec:
          imagePullPolicy: IfNotPresent
          resources:
           limits:
-           cpu: 150m
+           cpu: 200m
            memory: 600Mi
-          requests:
-           cpu: 75m
-           memory: 225Mi
          env:
           # azure devops pipeline uses AKS_RESOURCE_ID and AKS_REGION hence ensure to uncomment these
           - name: AKS_RESOURCE_ID
@@ -696,6 +695,7 @@ spec:
               - C:\opt\omsagentwindows\scripts\cmd\livenessProbe.cmd
           periodSeconds: 60
           initialDelaySeconds: 180
+          timeoutSeconds: 15
      affinity:
        nodeAffinity:
          requiredDuringSchedulingIgnoredDuringExecution: