good first cut

.gitignore

@@ -0,0 +1 @@
+.env*

docker-compose.yml

@@ -0,0 +1,23 @@
+version: '3'
+services:
+  telegraf:
+    container_name: telegraf-docker
+    image: telegraf
+    restart: unless-stopped
+    user: root:996
+    env_file:
+      - .env
+    volumes:
+      - ./telegraf/telegraf.conf:/etc/telegraf/telegraf.conf:ro
+      - /var/run/docker.sock:/var/run/docker.sock
+    depends_on:
+      - influxdb
+
+  promtail:
+    image: grafana/promtail
+    restart: unless-stopped
+    volumes:
+      - ./promtail:/etc/promtail
+      - /var/run/docker.sock:/var/run/docker.sock
+      - /var/log:/var/log:ro
+    command: -config.file=/etc/promtail/promtail-config.yml

promtail/promtail-config.yml

@@ -0,0 +1,23 @@
+server:
+  http_listen_port: 9080
+  grpc_listen_port: 0
+
+positions:
+  filename: /tmp/positions.yaml
+
+clients:
+  - url: http://loki:3100/loki/api/v1/push
+
+scrape_configs:
+  - job_name: flog_scrape
+    docker_sd_configs:
+      - host: unix:///var/run/docker.sock
+        refresh_interval: 5s
+    relabel_configs:
+      - source_labels: ['__meta_docker_container_name']
+        regex: '/(.*)'
+        target_label: 'container'
+      - source_labels: ['__meta_docker_container_log_stream']
+        target_label: 'logstream'
+      # - target_label: 'host'
+      #   replacement: 'docker-lxc'

telegraf/telegraf.conf

@@ -0,0 +1,198 @@
+# Configuration for telegraf agent
+[agent]
+  ## Default data collection interval for all inputs
+  interval = "10s"
+  ## Rounds collection interval to 'interval'
+  ## ie, if interval="10s" then always collect on :00, :10, :20, etc.
+  round_interval = true
+
+  ## Telegraf will send metrics to outputs in batches of at most
+  ## metric_batch_size metrics.
+  ## This controls the size of writes that Telegraf sends to output plugins.
+  metric_batch_size = 1000
+
+  ## Maximum number of unwritten metrics per output.  Increasing this value
+  ## allows for longer periods of output downtime without dropping metrics at the
+  ## cost of higher maximum memory usage.
+  metric_buffer_limit = 10000
+
+  ## Collection jitter is used to jitter the collection by a random amount.
+  ## Each plugin will sleep for a random time within jitter before collecting.
+  ## This can be used to avoid many plugins querying things like sysfs at the
+  ## same time, which can have a measurable effect on the system.
+  collection_jitter = "0s"
+
+  ## Default flushing interval for all outputs. Maximum flush_interval will be
+  ## flush_interval + flush_jitter
+  flush_interval = "10s"
+  ## Jitter the flush interval by a random amount. This is primarily to avoid
+  ## large write spikes for users running a large number of telegraf instances.
+  ## ie, a jitter of 5s and interval 10s means flushes will happen every 10-15s
+  flush_jitter = "0s"
+
+  ## By default or when set to "0s", precision will be set to the same
+  ## timestamp order as the collection interval, with the maximum being 1s.
+  ##   ie, when interval = "10s", precision will be "1s"
+  ##       when interval = "250ms", precision will be "1ms"
+  ## Precision will NOT be used for service inputs. It is up to each individual
+  ## service input to set the timestamp at the appropriate precision.
+  ## Valid time units are "ns", "us" (or "µs"), "ms", "s".
+  precision = ""
+
+  ## Log at debug level.
+  # debug = false
+  ## Log only error level messages.
+  # quiet = false
+
+  ## Log target controls the destination for logs and can be one of "file",
+  ## "stderr" or, on Windows, "eventlog".  When set to "file", the output file
+  ## is determined by the "logfile" setting.
+  # logtarget = "file"
+
+  ## Name of the file to be logged to when using the "file" logtarget.  If set to
+  ## the empty string then logs are written to stderr.
+  # logfile = ""
+
+  ## The logfile will be rotated after the time interval specified.  When set
+  ## to 0 no time based rotation is performed.  Logs are rotated only when
+  ## written to, if there is no log activity rotation may be delayed.
+  # logfile_rotation_interval = "0d"
+
+  ## The logfile will be rotated when it becomes larger than the specified
+  ## size.  When set to 0 no size based rotation is performed.
+  # logfile_rotation_max_size = "0MB"
+
+  ## Maximum number of rotated archives to keep, any older logs are deleted.
+  ## If set to -1, no archives are removed.
+  # logfile_rotation_max_archives = 5
+
+  ## Pick a timezone to use when logging or type 'local' for local time.
+  ## Example: America/Chicago
+  # log_with_timezone = ""
+
+  ## Override default hostname, if empty use os.Hostname()
+  hostname = ""
+  ## If set to true, do no set the "host" tag in the telegraf agent.
+  omit_hostname = false
+[[outputs.influxdb_v2]]
+  ## The URLs of the InfluxDB cluster nodes.
+  ##
+  ## Multiple URLs can be specified for a single cluster, only ONE of the
+  ## urls will be written to each interval.
+  ##   ex: urls = ["https://us-west-2-1.aws.cloud2.influxdata.com"]
+  urls = ["http://influxdb:8086"]
+
+  ## Token for authentication.
+  token = "$INFLUX_WRITE_TOKEN"
+
+  ## Organization is the name of the organization you wish to write to; must exist.
+  organization = "$DOCKER_INFLUXDB_INIT_ORG"
+
+  ## Destination bucket to write into.
+  bucket = "docker"
+
+  ## The value of this tag will be used to determine the bucket.  If this
+  ## tag is not set the 'bucket' option is used as the default.
+  # bucket_tag = ""
+
+  ## If true, the bucket tag will not be added to the metric.
+  # exclude_bucket_tag = false
+
+  ## Timeout for HTTP messages.
+  # timeout = "5s"
+
+  ## Additional HTTP headers
+  # http_headers = {"X-Special-Header" = "Special-Value"}
+
+  ## HTTP Proxy override, if unset values the standard proxy environment
+  ## variables are consulted to determine which proxy, if any, should be used.
+  # http_proxy = "http://corporate.proxy:3128"
+
+  ## HTTP User-Agent
+  # user_agent = "telegraf"
+
+  ## Content-Encoding for write request body, can be set to "gzip" to
+  ## compress body or "identity" to apply no encoding.
+  # content_encoding = "gzip"
+
+  ## Enable or disable uint support for writing uints influxdb 2.0.
+  # influx_uint_support = false
+
+  ## Optional TLS Config for use on HTTP connections.
+  # tls_ca = "/etc/telegraf/ca.pem"
+  # tls_cert = "/etc/telegraf/cert.pem"
+  # tls_key = "/etc/telegraf/key.pem"
+  ## Use TLS but skip chain & host verification
+  # insecure_skip_verify = false
+# Read metrics about docker containers
+[[inputs.docker]]
+  ## Docker Endpoint
+  ##   To use TCP, set endpoint = "tcp://[ip]:[port]"
+  ##   To use environment variables (ie, docker-machine), set endpoint = "ENV"
+  endpoint = "unix:///var/run/docker.sock"
+
+  ## Set to true to collect Swarm metrics(desired_replicas, running_replicas)
+  ## Note: configure this in one of the manager nodes in a Swarm cluster.
+  ## configuring in multiple Swarm managers results in duplication of metrics.
+  gather_services = false
+
+  ## Only collect metrics for these containers. Values will be appended to
+  ## container_name_include.
+  ## Deprecated (1.4.0), use container_name_include
+#   container_names = []
+
+  ## Set the source tag for the metrics to the container ID hostname, eg first 12 chars
+  source_tag = false
+
+  ## Containers to include and exclude. Collect all if empty. Globs accepted.
+  container_name_include = []
+  container_name_exclude = []
+
+  ## Container states to include and exclude. Globs accepted.
+  ## When empty only containers in the "running" state will be captured.
+  ## example: container_state_include = ["created", "restarting", "running", "removing", "paused", "exited", "dead"]
+  ## example: container_state_exclude = ["created", "restarting", "running", "removing", "paused", "exited", "dead"]
+  # container_state_include = []
+  # container_state_exclude = []
+
+  ## Timeout for docker list, info, and stats commands
+  timeout = "5s"
+
+  ## Whether to report for each container per-device blkio (8:0, 8:1...),
+  ## network (eth0, eth1, ...) and cpu (cpu0, cpu1, ...) stats or not.
+  ## Usage of this setting is discouraged since it will be deprecated in favor of 'perdevice_include'.
+  ## Default value is 'true' for backwards compatibility, please set it to 'false' so that 'perdevice_include' setting
+  ## is honored.
+#   perdevice = true
+
+  ## Specifies for which classes a per-device metric should be issued
+  ## Possible values are 'cpu' (cpu0, cpu1, ...), 'blkio' (8:0, 8:1, ...) and 'network' (eth0, eth1, ...)
+  ## Please note that this setting has no effect if 'perdevice' is set to 'true'
+  perdevice_include = ["cpu", "blkio", "network"]
+
+  ## Whether to report for each container total blkio and network stats or not.
+  ## Usage of this setting is discouraged since it will be deprecated in favor of 'total_include'.
+  ## Default value is 'false' for backwards compatibility, please set it to 'true' so that 'total_include' setting
+  ## is honored.
+  total = false
+
+  ## Specifies for which classes a total metric should be issued. Total is an aggregated of the 'perdevice' values.
+  ## Possible values are 'cpu', 'blkio' and 'network'
+  ## Total 'cpu' is reported directly by Docker daemon, and 'network' and 'blkio' totals are aggregated by this plugin.
+  ## Please note that this setting has no effect if 'total' is set to 'false'
+  # total_include = ["cpu", "blkio", "network"]
+
+  ## docker labels to include and exclude as tags.  Globs accepted.
+  ## Note that an empty array for both will include all labels as tags
+  docker_label_include = []
+  docker_label_exclude = []
+
+  ## Which environment variables should we use as a tag
+  tag_env = ["JAVA_HOME", "HEAP_SIZE"]
+
+  ## Optional TLS Config
+  # tls_ca = "/etc/telegraf/ca.pem"
+  # tls_cert = "/etc/telegraf/cert.pem"
+  # tls_key = "/etc/telegraf/key.pem"
+  ## Use TLS but skip chain & host verification
+  # insecure_skip_verify = false