kubeasz/manifests/efk/fluentd-es-configmap.yaml

kind: ConfigMap
apiVersion: v1
metadata:
  name: fluentd-es-config-v0.2.0
  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
    # capture the pod name, namespace, container name & Docker container ID
    # to the docker logs for pods in the /var/log/containers directory on the host.
    # If running this fluentd configuration in a Docker container, the /var/log
    # directory should be mounted in the container.
    #
    # These logs are then submitted to Elasticsearch which assumes the
    # installation of the fluent-plugin-elasticsearch & the
    # fluent-plugin-kubernetes_metadata_filter plugins.
    # See https://github.com/uken/fluent-plugin-elasticsearch &
    # https://github.com/fabric8io/fluent-plugin-kubernetes_metadata_filter for
    # more information about the plugins.
    #
    # Example
    # =======
    # A line in the Docker log file might look like this JSON:
    #
    # {"log":"2014/09/25 21:15:03 Got request with path wombat\n",
    #  "stream":"stderr",
    #   "time":"2014-09-25T21:15:03.499185026Z"}
    #
    # The time_format specification below makes sure we properly
    # parse the time format produced by Docker. This will be
    # submitted to Elasticsearch and should appear like:
    # $ curl 'http://elasticsearch-logging:9200/_search?pretty'
    # ...
    # {
    #      "_index" : "logstash-2014.09.25",
    #      "_type" : "fluentd",
    #      "_id" : "VBrbor2QTuGpsQyTCdfzqA",
    #      "_score" : 1.0,
    #      "_source":{"log":"2014/09/25 22:45:50 Got request with path wombat\n",
    #                 "stream":"stderr","tag":"docker.container.all",
    #                 "@timestamp":"2014-09-25T22:45:50+00:00"}
    #    },
    # ...
    #
    # The Kubernetes fluentd plugin is used to write the Kubernetes metadata to the log
    # record & add labels to the log record if properly configured. This enables users
    # to filter & search logs on any metadata.
    # For example a Docker container's logs might be in the directory:
    #
    #  /var/lib/docker/containers/997599971ee6366d4a5920d25b79286ad45ff37a74494f262e3bc98d909d0a7b
    #
    # and in the file:
    #
    #  997599971ee6366d4a5920d25b79286ad45ff37a74494f262e3bc98d909d0a7b-json.log
    #
    # where 997599971ee6... is the Docker ID of the running container.
    # The Kubernetes kubelet makes a symbolic link to this file on the host machine
    # in the /var/log/containers directory which includes the pod name and the Kubernetes
    # container name:
    #
    #    synthetic-logger-0.25lps-pod_default_synth-lgr-997599971ee6366d4a5920d25b79286ad45ff37a74494f262e3bc98d909d0a7b.log
    #    ->
    #    /var/lib/docker/containers/997599971ee6366d4a5920d25b79286ad45ff37a74494f262e3bc98d909d0a7b/997599971ee6366d4a5920d25b79286ad45ff37a74494f262e3bc98d909d0a7b-json.log
    #
    # The /var/log directory on the host is mapped to the /var/log directory in the container
    # running this instance of Fluentd and we end up collecting the file:
    #
    #   /var/log/containers/synthetic-logger-0.25lps-pod_default_synth-lgr-997599971ee6366d4a5920d25b79286ad45ff37a74494f262e3bc98d909d0a7b.log
    #
    # This results in the tag:
    #
    #  var.log.containers.synthetic-logger-0.25lps-pod_default_synth-lgr-997599971ee6366d4a5920d25b79286ad45ff37a74494f262e3bc98d909d0a7b.log
    #
    # The Kubernetes fluentd plugin is used to extract the namespace, pod name & container name
    # which are added to the log message as a kubernetes field object & the Docker container ID
    # is also added under the docker field object.
    # The final tag is:
    #
    #   kubernetes.var.log.containers.synthetic-logger-0.25lps-pod_default_synth-lgr-997599971ee6366d4a5920d25b79286ad45ff37a74494f262e3bc98d909d0a7b.log
    #
    # And the final log record look like:
    #
    # {
    #   "log":"2014/09/25 21:15:03 Got request with path wombat\n",
    #   "stream":"stderr",
    #   "time":"2014-09-25T21:15:03.499185026Z",
    #   "kubernetes": {
    #     "namespace": "default",
    #     "pod_name": "synthetic-logger-0.25lps-pod",
    #     "container_name": "synth-lgr"
    #   },
    #   "docker": {
    #     "container_id": "997599971ee6366d4a5920d25b79286ad45ff37a74494f262e3bc98d909d0a7b"
    #   }
    # }
    #
    # This makes it easier for users to search for logs by pod name or by
    # the name of the Kubernetes container regardless of how many times the
    # Kubernetes pod has been restarted (resulting in a several Docker container IDs).

    # Json Log Example:
    # {"log":"[info:2016-02-16T16:04:05.930-08:00] Some log text here\n","stream":"stdout","time":"2016-02-17T00:04:05.931087621Z"}
    # 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>
      @id fluentd-containers.log
      @type tail
      path /var/log/containers/*.log
      pos_file /var/log/es-containers.log.pos
      tag raw.kubernetes.*
      read_from_head true
      <parse>
        @type 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>
      </parse>
    </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
      stream stream
      multiline_flush_interval 5
      max_bytes 500000
      max_lines 1000
    </match>

    # Concatenate multi-line logs
    <filter **>
      @id filter_concat
      @type concat
      key log
      use_first_timestamp true
      multiline_end_regexp /\n$/
      separator ""
    </filter>

    # Enriches records with Kubernetes metadata
    <filter kubernetes.**>
      @id filter_kubernetes_metadata
      @type kubernetes_metadata
    </filter>

    # Fixes json fields in Elasticsearch
    <filter kubernetes.**>
      @id filter_parser
      @type parser
      key_name log
      reserve_data true
      remove_key_name_field true
      <parse>
        @type multi_format
        <pattern>
          format json
        </pattern>
        <pattern>
          format none
        </pattern>
      </parse>
    </filter>

  system.input.conf: |-

    # Logs from systemd-journal for interesting services.
    # TODO(random-liu): Remove this after cri container runtime rolls out.
    <source>
      @id journald-docker
      @type systemd
      matches [{ "_SYSTEMD_UNIT": "docker.service" }]
      <storage>
        @type local
        persistent true
        path /var/log/journald-docker.pos
      </storage>
      read_from_head true
      tag docker
    </source>

    <source>
      @id journald-container-runtime
      @type systemd
      matches [{ "_SYSTEMD_UNIT": "{{ fluentd_container_runtime_service }}.service" }]
      <storage>
        @type local
        persistent true
        path /var/log/journald-container-runtime.pos
      </storage>
      read_from_head true
      tag container-runtime
    </source>

    <source>
      @id journald-etcd
      @type systemd
      matches [{ "_SYSTEMD_UNIT": "etcd.service" }]
      <storage>
        @type local
        persistent true
        path /var/log/journald-etcd.pos
      </storage>
      read_from_head true
      tag etcd
    </source>

    <source>
      @id journald-kube-apiserver
      @type systemd
      matches [{ "_SYSTEMD_UNIT": "kube-apiserver.service" }]
      <storage>
        @type local
        persistent true
        path /var/log/journald-kube-apiserver.pos
      </storage>
      read_from_head true
      tag kube-apiserver
    </source>

    <source>
      @id journald-kube-controller-manager
      @type systemd
      matches [{ "_SYSTEMD_UNIT": "kube-controller-manager.service" }]
      <storage>
        @type local
        persistent true
        path /var/log/journald-kube-controller-manager.pos
      </storage>
      read_from_head true
      tag kube-controller-manager
    </source>

    <source>
      @id journald-kube-scheduler
      @type systemd
      matches [{ "_SYSTEMD_UNIT": "kube-scheduler.service" }]
      <storage>
        @type local
        persistent true
        path /var/log/journald-kube-scheduler.pos
      </storage>
      read_from_head true
      tag kube-scheduler
    </source>

    <source>
      @id journald-kubelet
      @type systemd
      matches [{ "_SYSTEMD_UNIT": "kubelet.service" }]
      <storage>
        @type local
        persistent true
        path /var/log/journald-kubelet.pos
      </storage>
      read_from_head true
      tag kubelet
    </source>

    <source>
      @id journald-kube-proxy
      @type systemd
      matches [{ "_SYSTEMD_UNIT": "kube-proxy.service" }]
      <storage>
        @type local
        persistent true
        path /var/log/journald-kube-proxy.pos
      </storage>
      read_from_head true
      tag kube-proxy
    </source>

    <source>
      @id journald-node-problem-detector
      @type systemd
      matches [{ "_SYSTEMD_UNIT": "node-problem-detector.service" }]
      <storage>
        @type local
        persistent true
        path /var/log/journald-node-problem-detector.pos
      </storage>
      read_from_head true
      tag node-problem-detector
    </source>

    <source>
      @id kernel
      @type systemd
      matches [{ "_TRANSPORT": "kernel" }]
      <storage>
        @type local
        persistent true
        path /var/log/kernel.pos
      </storage>
      <entry>
        fields_strip_underscores true
        fields_lowercase true
      </entry>
      read_from_head true
      tag kernel
    </source>

  forward.input.conf: |-
    # Takes the messages sent over TCP
    <source>
      @id forward
      @type forward
    </source>

  monitoring.conf: |-
    # Prometheus Exporter Plugin
    # input plugin that exports metrics
    <source>
      @id prometheus
      @type prometheus
    </source>

    <source>
      @id monitor_agent
      @type monitor_agent
    </source>

    # input plugin that collects metrics from MonitorAgent
    <source>
      @id prometheus_monitor
      @type prometheus_monitor
      <labels>
        host ${hostname}
      </labels>
    </source>

    # input plugin that collects metrics for output plugin
    <source>
      @id prometheus_output_monitor
      @type prometheus_output_monitor
      <labels>
        host ${hostname}
      </labels>
    </source>

    # input plugin that collects metrics for in_tail plugin
    <source>
      @id prometheus_tail_monitor
      @type prometheus_tail_monitor
      <labels>
        host ${hostname}
      </labels>
    </source>

  output.conf: |-
    <match **>
      @id elasticsearch
      @type elasticsearch
      @log_level info
      type_name _doc
      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>