Merge pull request #58525 from monotek/fluentd-1.1.0

cluster/addons/fluentd-elasticsearch/fluentd-es-configmap.yaml

 kind: ConfigMap
 apiVersion: v1
+metadata:
+  name: fluentd-es-config-v0.1.3
+  namespace: kube-system
+  labels:
+    addonmanager.kubernetes.io/mode: Reconcile
 data:
+  system.conf: |-
+    <system>
+      root_dir /tmp/fluentd-buffers/
+    </system>
+
   containers.input.conf: |-
     # This configuration file for Fluentd / td-agent is used
     # to watch changes to Docker log files. The kubelet creates symlinks that
@@ -101,25 +111,19 @@ data:
     # CRI Log Example:
     # 2016-02-17T00:04:05.931087621Z stdout F [info:2016-02-16T16:04:05.930-08:00] Some log text here
     <source>
-      type tail
+      @id fluentd-containers.log
+      @type tail
       path /var/log/containers/*.log
       pos_file /var/log/es-containers.log.pos
       time_format %Y-%m-%dT%H:%M:%S.%NZ
       tag raw.kubernetes.*
+      format json
       read_from_head true
-      format multi_format
-      <pattern>
-        format json
-        time_key time
-        time_format %Y-%m-%dT%H:%M:%S.%NZ
-      </pattern>
-      <pattern>
-        format /^(?<time>.+) (?<stream>stdout|stderr) [^ ]* (?<log>.*)$/
-        time_format %Y-%m-%dT%H:%M:%S.%N%:z
-      </pattern>
     </source>
+
     # Detect exceptions in the log output and forward them as one log entry.
     <match raw.kubernetes.**>
+      @id raw.kubernetes
       @type detect_exceptions
       remove_tag_prefix raw
       message log
@@ -128,11 +132,25 @@ data:
       max_bytes 500000
       max_lines 1000
     </match>
+
   system.input.conf: |-
     # Example:
+    # 2015-12-21 23:17:22,066 [salt.state       ][INFO    ] Completed state [net.ipv4.ip_forward] at time 23:17:22.066081
+    <source>
+      @id minion
+      @type tail
+      format /^(?<time>[^ ]* [^ ,]*)[^\[]*\[[^\]]*\]\[(?<severity>[^ \]]*) *\] (?<message>.*)$/
+      time_format %Y-%m-%d %H:%M:%S
+      path /var/log/salt/minion
+      pos_file /var/log/salt.pos
+      tag salt
+    </source>
+
+    # Example:
     # Dec 21 23:17:22 gke-foo-1-1-4b5cbd14-node-4eoj startupscript: Finished running startup script /var/run/google.startup.script
     <source>
-      type tail
+      @id startupscript.log
+      @type tail
       format syslog
       path /var/log/startupscript.log
       pos_file /var/log/es-startupscript.log.pos
@@ -143,7 +161,8 @@ data:
     # time="2016-02-04T06:51:03.053580605Z" level=info msg="GET /containers/json"
     # time="2016-02-04T07:53:57.505612354Z" level=error msg="HTTP Error" err="No such image: -f" statusCode=404
     <source>
-      type tail
+      @id docker.log
+      @type tail
       format /^time="(?<time>[^)]*)" level=(?<severity>[^ ]*) msg="(?<message>[^"]*)"( err="(?<error>[^"]*)")?( statusCode=($<status_code>\d+))?/
       path /var/log/docker.log
       pos_file /var/log/es-docker.log.pos
@@ -153,7 +172,8 @@ data:
     # Example:
     # 2016/02/04 06:52:38 filePurge: successfully removed file /var/etcd/data/member/wal/00000000000006d0-00000000010a23d1.wal
     <source>
-      type tail
+      @id etcd.log
+      @type tail
       # Not parsing this, because it doesn't have anything particularly useful to
       # parse out of it (like severities).
       format none
@@ -169,7 +189,8 @@ data:
     # Example:
     # I0204 07:32:30.020537    3368 server.go:1048] POST /stats/container/: (13.972191ms) 200 [[Go-http-client/1.1] 10.244.1.3:40537]
     <source>
-      type tail
+      @id kubelet.log
+      @type tail
       format multiline
       multiline_flush_interval 5s
       format_firstline /^\w\d{4}/
@@ -183,7 +204,8 @@ data:
     # Example:
     # I1118 21:26:53.975789       6 proxier.go:1096] Port "nodePort for kube-system/default-http-backend:http" (:31429/tcp) was open before and is still needed
     <source>
-      type tail
+      @id kube-proxy.log
+      @type tail
       format multiline
       multiline_flush_interval 5s
       format_firstline /^\w\d{4}/
@@ -197,7 +219,8 @@ data:
     # Example:
     # I0204 07:00:19.604280       5 handlers.go:131] GET /api/v1/nodes: (1.624207ms) 200 [[kube-controller-manager/v1.1.3 (linux/amd64) kubernetes/6a81b50] 127.0.0.1:38266]
     <source>
-      type tail
+      @id kube-apiserver.log
+      @type tail
       format multiline
       multiline_flush_interval 5s
       format_firstline /^\w\d{4}/
@@ -211,7 +234,8 @@ data:
     # Example:
     # I0204 06:55:31.872680       5 servicecontroller.go:277] LB already exists and doesn't need update for service kube-system/kube-ui
     <source>
-      type tail
+      @id kube-controller-manager.log
+      @type tail
       format multiline
       multiline_flush_interval 5s
       format_firstline /^\w\d{4}/
@@ -225,7 +249,8 @@ data:
     # Example:
     # W0204 06:49:18.239674       7 reflector.go:245] pkg/scheduler/factory/factory.go:193: watch of *api.Service ended with: 401: The event in requested index is outdated and cleared (the requested history has been cleared [2578313/2577886]) [2579312]
     <source>
-      type tail
+      @id kube-scheduler.log
+      @type tail
       format multiline
       multiline_flush_interval 5s
       format_firstline /^\w\d{4}/
@@ -239,7 +264,8 @@ data:
     # Example:
     # I1104 10:36:20.242766       5 rescheduler.go:73] Running Rescheduler
     <source>
-      type tail
+      @id rescheduler.log
+      @type tail
       format multiline
       multiline_flush_interval 5s
       format_firstline /^\w\d{4}/
@@ -253,7 +279,8 @@ data:
     # Example:
     # I0603 15:31:05.793605       6 cluster_manager.go:230] Reading config from path /etc/gce.conf
     <source>
-      type tail
+      @id glbc.log
+      @type tail
       format multiline
       multiline_flush_interval 5s
       format_firstline /^\w\d{4}/
@@ -267,7 +294,8 @@ data:
     # Example:
     # I0603 15:31:05.793605       6 cluster_manager.go:230] Reading config from path /etc/gce.conf
     <source>
-      type tail
+      @id cluster-autoscaler.log
+      @type tail
       format multiline
       multiline_flush_interval 5s
       format_firstline /^\w\d{4}/
@@ -280,33 +308,47 @@ data:
 
     # Logs from systemd-journal for interesting services.
     <source>
-      type systemd
+      @id journald-docker
+      @type systemd
       filters [{ "_SYSTEMD_UNIT": "docker.service" }]
-      pos_file /var/log/gcp-journald-docker.pos
+      <storage>
+        @type local
+        persistent true
+      </storage>
       read_from_head true
       tag docker
     </source>
 
     <source>
-      type systemd
+      @id journald-kubelet
+      @type systemd
       filters [{ "_SYSTEMD_UNIT": "kubelet.service" }]
-      pos_file /var/log/gcp-journald-kubelet.pos
+      <storage>
+        @type local
+        persistent true
+      </storage>
       read_from_head true
       tag kubelet
     </source>
 
     <source>
-      type systemd
+      @id journald-node-problem-detector
+      @type systemd
       filters [{ "_SYSTEMD_UNIT": "node-problem-detector.service" }]
-      pos_file /var/log/gcp-journald-node-problem-detector.pos
+      <storage>
+        @type local
+        persistent true
+      </storage>
       read_from_head true
       tag node-problem-detector
     </source>
+
   forward.input.conf: |-
     # Takes the messages sent over TCP
     <source>
-      type forward
+      @type forward
     </source>
+
   monitoring.conf: |-
     # Prometheus Exporter Plugin
     # input plugin that exports metrics
@@ -341,32 +383,32 @@ data:
         host ${hostname}
       </labels>
     </source>
+
   output.conf: |-
     # Enriches records with Kubernetes metadata
     <filter kubernetes.**>
-      type kubernetes_metadata
+      @type kubernetes_metadata
     </filter>
 
     <match **>
-       type elasticsearch
-       log_level info
-       include_tag_key true
-       host elasticsearch-logging
-       port 9200
-       logstash_format true
-       # Set the chunk limits.
-       buffer_chunk_limit 2M
-       buffer_queue_limit 8
-       flush_interval 5s
-       # Never wait longer than 5 minutes between retries.
-       max_retry_wait 30
-       # Disable the limit on the number of retries (retry forever).
-       disable_retry_limit
-       # Use multiple threads for processing.
-       num_threads 2
+      @id elasticsearch
+      @type elasticsearch
+      @log_level info
+      include_tag_key true
+      host elasticsearch-logging
+      port 9200
+      logstash_format true
+      <buffer>
+        @type file
+        path /var/log/fluentd-buffers/kubernetes.system.buffer
+        flush_mode interval
+        retry_type exponential_backoff
+        flush_thread_count 2
+        flush_interval 5s
+        retry_forever
+        retry_max_interval 30
+        chunk_limit_size 2M
+        queue_limit_length 8
+        overflow_action block
+      </buffer>
     </match>
-metadata:
-  name: fluentd-es-config-v0.1.2
-  namespace: kube-system
-  labels:
-    addonmanager.kubernetes.io/mode: Reconcile

cluster/addons/fluentd-elasticsearch/fluentd-es-ds.yaml

@@ -48,24 +48,24 @@ roleRef:
 apiVersion: apps/v1
 kind: DaemonSet
 metadata:
-  name: fluentd-es-v2.0.3
+  name: fluentd-es-v2.0.4
   namespace: kube-system
   labels:
     k8s-app: fluentd-es
-    version: v2.0.3
+    version: v2.0.4
     kubernetes.io/cluster-service: "true"
     addonmanager.kubernetes.io/mode: Reconcile
 spec:
   selector:
     matchLabels:
       k8s-app: fluentd-es
-      version: v2.0.3
+      version: v2.0.4
   template:
     metadata:
       labels:
         k8s-app: fluentd-es
         kubernetes.io/cluster-service: "true"
-        version: v2.0.3
+        version: v2.0.4
       # This annotation ensures that fluentd does not get evicted if the node
       # supports critical pod annotation based priority scheme.
       # Note that this does not guarantee admission on the nodes (#40573).
@@ -75,7 +75,7 @@ spec:
       serviceAccountName: fluentd-es
       containers:
       - name: fluentd-es
-        image: gcr.io/google-containers/fluentd-elasticsearch:v2.0.3
+        image: gcr.io/google-containers/fluentd-elasticsearch:v2.0.4
         env:
         - name: FLUENTD_ARGS
           value: --no-supervisor -q
@@ -112,4 +112,4 @@ spec:
           path: /usr/lib64
       - name: config-volume
         configMap:
-          name: fluentd-es-config-v0.1.2
+          name: fluentd-es-config-v0.1.3

cluster/addons/fluentd-elasticsearch/fluentd-es-image/Dockerfile

@@ -21,6 +21,8 @@
 
 FROM debian:stretch-slim
 
+ARG DEBIAN_FRONTEND=noninteractive
+
 COPY clean-apt /usr/bin
 COPY clean-install /usr/bin
 COPY Gemfile /Gemfile

cluster/addons/fluentd-elasticsearch/fluentd-es-image/Gemfile

 source 'https://rubygems.org'
 
-gem 'fluentd', '~>0.12.32'
-gem 'activesupport', '~>4.2.6'
-gem 'fluent-plugin-kubernetes_metadata_filter', '~>0.27.0'
-gem 'fluent-plugin-elasticsearch', '~>1.9.5'
-gem 'fluent-plugin-systemd', '~>0.0.8'
-gem 'fluent-plugin-detect-exceptions', '~>0.0.8'
+gem 'fluentd', '<=1.1.0'
+gem 'activesupport', '~>5.1.4'
+gem 'fluent-plugin-kubernetes_metadata_filter', '~>1.0.0'
+gem 'fluent-plugin-elasticsearch', '~>2.4.1'
+gem 'fluent-plugin-systemd', '~>0.3.1'
+gem 'fluent-plugin-detect-exceptions', '~>0.0.9'
 gem 'fluent-plugin-prometheus', '~>0.3.0'
-gem 'fluent-plugin-multi-format-parser', '~>0.1.1'
-gem 'oj', '~>2.18.1'
+gem 'fluent-plugin-multi-format-parser', '~>1.0.0'
+gem 'oj', '~>3.3.1.0'

cluster/addons/fluentd-elasticsearch/fluentd-es-image/Makefile

@@ -16,7 +16,7 @@
 
 PREFIX = gcr.io/google-containers
 IMAGE = fluentd-elasticsearch
-TAG = v2.0.3
+TAG = v2.0.4
 
 build:
 	docker build --pull -t $(PREFIX)/$(IMAGE):$(TAG) .

cluster/addons/fluentd-elasticsearch/fluentd-es-image/fluent.conf

@@ -2,7 +2,7 @@
 
 # Do not collect fluentd's own logs to avoid infinite loops.
 <match fluent.**>
-  type null
+  @type null
 </match>
 
 @include /etc/fluent/config.d/*.conf