# This configuration file for Fluentd / td-agent is used
# to watch changes to Docker log files that live in the
# directory /var/lib/docker/containers/ and are symbolically
# linked to from the /var/log directory using names that capture the
# pod name and container name. These logs are then submitted to
# Google Cloud Logging which assumes the installation of the cloud-logging plug-in.
#
# Example
# =======
# A line in the Docker log file might like 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 record reformer is used to write the tag to focus on the pod name
# and the Kubernetes container name. 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 record reformer is used is discard the var.log.containers prefix and
# the Docker container ID suffix and "kubernetes." is pre-pended giving the
# final tag which is ingested into Elasticsearch:
#   kubernetes.synthetic-logger-0.25lps-pod_default-synth-lgr
# 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).

# 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
  format json
  time_key time
  path /var/log/containers/*.log
  pos_file /var/log/gcp-containers.log.pos
  time_format %Y-%m-%dT%H:%M:%S.%NZ
  tag reform.*
  read_from_head true
</source>

<filter reform.**>
  type parser
  format /^(?<severity>\w)(?<time>\d{4} [^\s]*)\s+(?<pid>\d+)\s+(?<source>[^ \]]+)\] (?<log>.*)/
  reserve_data true
  suppress_parse_error_log true
  key_name log
</filter>

<match reform.**>
  type record_reformer
  enable_ruby true
  tag raw.kubernetes.${tag_suffix[4].split('-')[0..-2].join('-')}
</match>

# Detect exceptions in the log output and forward them as one log entry.
<match raw.kubernetes.**>
  type detect_exceptions
  remove_tag_prefix raw
  message log
  stream stream
  multiline_flush_interval 5
  max_bytes 500000
  max_lines 1000
</match>

# 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/gcp-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/gcp-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/gcp-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/gcp-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/gcp-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/gcp-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/gcp-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/gcp-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/gcp-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/gcp-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/gcp-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/gcp-cluster-autoscaler.log.pos
  tag cluster-autoscaler
</source>

# Logs from systemd-journal for interesting services.
<source>
  type systemd
  filters [{ "_SYSTEMD_UNIT": "docker.service" }]
  pos_file /var/log/gcp-journald-docker.pos
  read_from_head true
  tag docker
</source>

<source>
  type systemd
  filters [{ "_SYSTEMD_UNIT": "kubelet.service" }]
  pos_file /var/log/gcp-journald-kubelet.pos
  read_from_head true
  tag kubelet
</source>

# We use 2 output stanzas - one to handle the container logs and one to handle
# the node daemon logs, the latter of which explicitly sends its logs to the
# 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 google_cloud
  # 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
  # Set queue_full action to block because we want to pause gracefully
  # in case of the off-the-limits load instead of throwing an exception
  buffer_queue_full_action block
  # Set the chunk limit conservatively to avoid exceeding the GCL limit
  # of 10MiB per write request.
  buffer_chunk_limit 2M
  # Cap the combined memory usage of this buffer and the one below to
  # 2MiB/chunk * (6 + 2) chunks = 16 MiB
  buffer_queue_limit 6
  # Never wait more than 5 seconds before flushing logs in the non-error case.
  flush_interval 5s
  # Never wait longer than 30 seconds 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
</match>

# Keep a smaller buffer here since these logs are less important than the user's
# container logs.
<match **>
  type google_cloud
  detect_subservice false
  buffer_type file
  buffer_path /var/log/fluentd-buffers/kubernetes.system.buffer
  buffer_queue_full_action block
  buffer_chunk_limit 2M
  buffer_queue_limit 2
  flush_interval 5s
  max_retry_wait 30
  disable_retry_limit
  num_threads 2
</match>