kubespray/roles/kubernetes-apps/efk/fluentd/templates/fluentd-config.yml.j2

apiVersion: v1
kind: ConfigMap
metadata:
  name: fluentd-config
  namespace: "{{ system_namespace }}"
data:
  {{ fluentd_config_file }}: |
    # 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.
    # Maintainer: Jimmi Dyson <jimmidyson@gmail.com>
    #
    # 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).
    #
    # TODO: Propagate the labels associated with a container along with its logs
    # so users can query logs using labels as well as or instead of the pod name
    # and container name. This is simply done via configuration of the Kubernetes
    # fluentd plugin but requires secrets to be enabled in the fluent pod. This is a
    # problem yet to be solved as secrets are not usable in static pods which the fluentd
    # pod must be until a per-node controller is available in Kubernetes.
    # Prevent fluentd from handling records containing its own logs. Otherwise
    # it can lead to an infinite loop, when error in sending one message generates
    # another message which also fails to be sent and so on.
    <match fluent.**>
      type null
    </match>
    # 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"}
    <source>
      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 kubernetes.*
      format json
      read_from_head true
    </source>
    # Example:
    # 2015-12-21 23:17:22,066 [salt.state       ][INFO    ] Completed state [net.ipv4.ip_forward] at time 23:17:22.066081
    <source>
      type tail
      format /^(?<time>[^ ]* [^ ,]*)[^\[]*\[[^\]]*\]\[(?<severity>[^ \]]*) *\] (?<message>.*)$/
      time_format %Y-%m-%d %H:%M:%S
      path /var/log/salt/minion
      pos_file /var/log/es-salt.pos
      tag salt
    </source>
    # Example:
    # Dec 21 23:17:22 gke-foo-1-1-4b5cbd14-node-4eoj startupscript: Finished running startup script /var/run/google.startup.script
    <source>
      type tail
      format syslog
      path /var/log/startupscript.log
      pos_file /var/log/es-startupscript.log.pos
      tag startupscript
    </source>
    # Examples:
    # time="2016-02-04T06:51:03.053580605Z" level=info msg="GET /containers/json"
    # time="2016-02-04T07:53:57.505612354Z" level=error msg="HTTP Error" err="No such image: -f" statusCode=404
    <source>
      type tail
      format /^time="(?<time>[^)]*)" level=(?<severity>[^ ]*) msg="(?<message>[^"]*)"( err="(?<error>[^"]*)")?( statusCode=($<status_code>\d+))?/
      path /var/log/docker.log
      pos_file /var/log/es-docker.log.pos
      tag docker
    </source>
    # Example:
    # 2016/02/04 06:52:38 filePurge: successfully removed file /var/etcd/data/member/wal/00000000000006d0-00000000010a23d1.wal
    <source>
      type tail
      # Not parsing this, because it doesn't have anything particularly useful to
      # parse out of it (like severities).
      format none
      path /var/log/etcd.log
      pos_file /var/log/es-etcd.log.pos
      tag etcd
    </source>
    # Multi-line parsing is required for all the kube logs because very large log
    # statements, such as those that include entire object bodies, get split into
    # multiple lines by glog.
    # 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
      format multiline
      multiline_flush_interval 5s
      format_firstline /^\w\d{4}/
      format1 /^(?<severity>\w)(?<time>\d{4} [^\s]*)\s+(?<pid>\d+)\s+(?<source>[^ \]]+)\] (?<message>.*)/
      time_format %m%d %H:%M:%S.%N
      path /var/log/kubelet.log
      pos_file /var/log/es-kubelet.log.pos
      tag kubelet
    </source>
    # 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
      format multiline
      multiline_flush_interval 5s
      format_firstline /^\w\d{4}/
      format1 /^(?<severity>\w)(?<time>\d{4} [^\s]*)\s+(?<pid>\d+)\s+(?<source>[^ \]]+)\] (?<message>.*)/
      time_format %m%d %H:%M:%S.%N
      path /var/log/kube-proxy.log
      pos_file /var/log/es-kube-proxy.log.pos
      tag kube-proxy
    </source>
    # 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
      format multiline
      multiline_flush_interval 5s
      format_firstline /^\w\d{4}/
      format1 /^(?<severity>\w)(?<time>\d{4} [^\s]*)\s+(?<pid>\d+)\s+(?<source>[^ \]]+)\] (?<message>.*)/
      time_format %m%d %H:%M:%S.%N
      path /var/log/kube-apiserver.log
      pos_file /var/log/es-kube-apiserver.log.pos
      tag kube-apiserver
    </source>
    # 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
      format multiline
      multiline_flush_interval 5s
      format_firstline /^\w\d{4}/
      format1 /^(?<severity>\w)(?<time>\d{4} [^\s]*)\s+(?<pid>\d+)\s+(?<source>[^ \]]+)\] (?<message>.*)/
      time_format %m%d %H:%M:%S.%N
      path /var/log/kube-controller-manager.log
      pos_file /var/log/es-kube-controller-manager.log.pos
      tag kube-controller-manager
    </source>
    # 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
      format multiline
      multiline_flush_interval 5s
      format_firstline /^\w\d{4}/
      format1 /^(?<severity>\w)(?<time>\d{4} [^\s]*)\s+(?<pid>\d+)\s+(?<source>[^ \]]+)\] (?<message>.*)/
      time_format %m%d %H:%M:%S.%N
      path /var/log/kube-scheduler.log
      pos_file /var/log/es-kube-scheduler.log.pos
      tag kube-scheduler
    </source>
    # Example:
    # I1104 10:36:20.242766       5 rescheduler.go:73] Running Rescheduler
    <source>
      type tail
      format multiline
      multiline_flush_interval 5s
      format_firstline /^\w\d{4}/
      format1 /^(?<severity>\w)(?<time>\d{4} [^\s]*)\s+(?<pid>\d+)\s+(?<source>[^ \]]+)\] (?<message>.*)/
      time_format %m%d %H:%M:%S.%N
      path /var/log/rescheduler.log
      pos_file /var/log/es-rescheduler.log.pos
      tag rescheduler
    </source>
    # Example:
    # I0603 15:31:05.793605       6 cluster_manager.go:230] Reading config from path /etc/gce.conf
    <source>
      type tail
      format multiline
      multiline_flush_interval 5s
      format_firstline /^\w\d{4}/
      format1 /^(?<severity>\w)(?<time>\d{4} [^\s]*)\s+(?<pid>\d+)\s+(?<source>[^ \]]+)\] (?<message>.*)/
      time_format %m%d %H:%M:%S.%N
      path /var/log/glbc.log
      pos_file /var/log/es-glbc.log.pos
      tag glbc
    </source>
    # Example:
    # I0603 15:31:05.793605       6 cluster_manager.go:230] Reading config from path /etc/gce.conf
    <source>
      type tail
      format multiline
      multiline_flush_interval 5s
      format_firstline /^\w\d{4}/
      format1 /^(?<severity>\w)(?<time>\d{4} [^\s]*)\s+(?<pid>\d+)\s+(?<source>[^ \]]+)\] (?<message>.*)/
      time_format %m%d %H:%M:%S.%N
      path /var/log/cluster-autoscaler.log
      pos_file /var/log/es-cluster-autoscaler.log.pos
      tag cluster-autoscaler
    </source>
    <filter kubernetes.**>
      type kubernetes_metadata
    </filter>
    ## Prometheus Exporter Plugin
    ## input plugin that exports metrics
    #<source>
    #  type prometheus
    #</source>
    #<source>
    #  type monitor_agent
    #</source>
    #<source>
    #  type forward
    #</source>
    ## input plugin that collects metrics from MonitorAgent
    #<source>
    #  @type prometheus_monitor
    #  <labels>
    #    host ${hostname}
    #  </labels>
    #</source>
    ## input plugin that collects metrics for output plugin
    #<source>
    #  @type prometheus_output_monitor
    #  <labels>
    #    host ${hostname}
    #  </labels>
    #</source>
    ## input plugin that collects metrics for in_tail plugin
    #<source>
    #  @type prometheus_tail_monitor
    #  <labels>
    #    host ${hostname}
    #  </labels>
    #</source>
    <match **>
       type elasticsearch
       user "#{ENV['FLUENT_ELASTICSEARCH_USER']}"
       password "#{ENV['FLUENT_ELASTICSEARCH_PASSWORD']}"
       log_level info
       include_tag_key true
       host elasticsearch-logging
       port 9200
       logstash_format true
       # Set the chunk limit the same as for fluentd-gcp.
       buffer_chunk_limit 2M
       # Cap buffer memory usage to 2MiB/chunk * 32 chunks = 64 MiB
       buffer_queue_limit 32
       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 8
    </match>