Change fluentd-gcp monitoring to use metrics exposed by SD plugin

cluster/addons/fluentd-gcp/fluentd-gcp-configmap.yaml

@@ -70,18 +70,6 @@ data:
 
     # Detect exceptions in the log output and forward them as one log entry.
     <match raw.kubernetes.**>
-      @type copy
-
-      <store>
-        @type prometheus
-
-        <metric>
-          type counter
-          name logging_line_count
-          desc Total number of lines generated by application containers
-        </metric>
-      </store>
-      <store>
       @type detect_exceptions
 
       remove_tag_prefix raw
@@ -90,7 +78,6 @@ data:
       multiline_flush_interval 5
       max_bytes 500000
       max_lines 1000
-      </store>
     </match>
   system.input.conf: |-
     # Example:
@@ -342,11 +329,11 @@ data:
     # compute.googleapis.com service rather than container.googleapis.com to keep
     # them separate since most users don't care about the node logs.
     <match kubernetes.**>
-      @type copy
-
-      <store>
       @type google_cloud
 
+      # Collect metrics in Prometheus registry about plugin activity.
+      enable_monitoring true
+      monitoring_type prometheus
       # Set the buffer type to file to improve the reliability and reduce the memory consumption
       buffer_type file
       buffer_path /var/log/fluentd-buffers/kubernetes.containers.buffer
@@ -367,29 +354,15 @@ data:
       disable_retry_limit
       # Use multiple threads for processing.
       num_threads 2
-      </store>
-      <store>
-        @type prometheus
-
-        <metric>
-          type counter
-          name logging_entry_count
-          desc Total number of log entries generated by either application containers or system components
-          <labels>
-            component container
-          </labels>
-        </metric>
-      </store>
     </match>
 
     # Keep a smaller buffer here since these logs are less important than the user's
     # container logs.
     <match **>
-      @type copy
-
-      <store>
       @type google_cloud
 
+      enable_monitoring true
+      monitoring_type prometheus
       detect_subservice false
       buffer_type file
       buffer_path /var/log/fluentd-buffers/kubernetes.system.buffer
@@ -400,19 +373,6 @@ data:
       max_retry_wait 30
       disable_retry_limit
       num_threads 2
-      </store>
-      <store>
-        @type prometheus
-
-        <metric>
-          type counter
-          name logging_entry_count
-          desc Total number of log entries generated by either application containers or system components
-          <labels>
-            component system
-          </labels>
-        </metric>
-      </store>
     </match>
 metadata:
   name: fluentd-gcp-config-v1.1

cluster/addons/fluentd-gcp/fluentd-gcp-ds.yaml

@@ -27,7 +27,7 @@ spec:
       hostNetwork: true
       containers:
       - name: fluentd-gcp
-        image: gcr.io/google-containers/fluentd-gcp:2.0.7
+        image: gcr.io/google-containers/fluentd-gcp:2.0.8
         # If fluentd consumes its own logs, the following situation may happen:
         # fluentd fails to send a chunk to the server => writes it to the log =>
         # tries to send this message to the server => fails to send a chunk and so on.
@@ -90,13 +90,13 @@ spec:
                 exit 1;
               fi;
       - name: prometheus-to-sd-exporter
-        image: gcr.io/google-containers/prometheus-to-sd:v0.1.0
+        image: gcr.io/google-containers/prometheus-to-sd:v0.1.3
         command:
           - /monitor
           - --component=fluentd
           - --target-port=31337
           - --stackdriver-prefix=container.googleapis.com/internal/addons
-          - --whitelisted-metrics=logging_line_count,logging_entry_count
+          - --whitelisted-metrics=stackdriver_successful_requests_count,stackdriver_failed_requests_count,stackdriver_ingested_entries_count,stackdriver_dropped_entries_count
         volumeMounts:
         - name: ssl-certs
           mountPath: /etc/ssl/certs