gistfile1.txt

# This configuration file for Fluentd 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/containers 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 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 original tag is derived from the log file's location.
# 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,
# the namespace 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
# where 'synthetic-logger-0.25lps-pod' is the pod name, 'default' is the
# namespace name, 'synth-lgr' is the container name and '997599971ee6..' is
# the container ID.
# The record reformer is used to extract pod_name, namespace_name and
# container_name from the tag and set them in a local_resource_id in the
# format of:
# 'k8s_container.<NAMESPACE_NAME>.<POD_NAME>.<CONTAINER_NAME>'.
# The reformer also changes the tags to 'stderr' or 'stdout' based on the
# value of 'stream'.
# local_resource_id is later used by google_cloud plugin to determine the
# monitored resource to ingest logs against.

# 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>
  @type tail
  path /var/log/containers/*.log
  pos_file /var/log/gcp-containers.log.pos
  # Tags at this point are in the format of:
  # reform.var.log.containers.<POD_NAME>_<NAMESPACE_NAME>_<CONTAINER_NAME>-<CONTAINER_ID>.log
  tag reform.*
  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>

<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
  emit_invalid_record_to_error false
  key_name log
</filter>

<match reform.**>
  @type record_reformer
  enable_ruby true
  <record>
    # Extract local_resource_id from tag for 'k8s_container' monitored
    # resource. The format is:
    # 'k8s_container.<namespace_name>.<pod_name>.<container_name>'.
    "logging.googleapis.com/local_resource_id" ${"k8s_container.#{tag_suffix[4].rpartition('.')[0].split('_')[1]}.#{tag_suffix[4].rpartition('.')[0].split('_')[0]}.#{tag_suffix[4].rpartition('.')[0].split('_')[2].rpartition('-')[0]}"}
    # Rename the field 'log' to a more generic field 'message'. This way the
    # fluent-plugin-google-cloud knows to flatten the field as textPayload
    # instead of jsonPayload after extracting 'time', 'severity' and
    # 'stream' from the record.
    message ${record['log']}
    # If 'severity' is not set, assume stderr is ERROR and stdout is INFO.
    severity ${record['severity'] || if record['stream'] == 'stderr' then 'ERROR' else 'INFO' end}
  </record>
  tag ${if record['stream'] == 'stderr' then 'raw.stderr' else 'raw.stdout' end}
  remove_keys stream,log
</match>

# Detect exceptions in the log output and forward them as one log entry.
<match {raw.stderr,raw.stdout}>
  @type detect_exceptions

  remove_tag_prefix raw
  message message
  stream "logging.googleapis.com/local_resource_id"
  multiline_flush_interval 5
  max_bytes 500000
  max_lines 1000
</match>