Consolidate Grafana-stack and prometheus into Monitoring

homelab/server/config/grafana-stack/.env

@@ -1,2 +0,0 @@
-DOCKER_DATA=/home/joey/data/grafana-stack
-MINECRAFT_DIR=/home/joey/data/minecraft

homelab/server/config/grafana-stack/.forgetps.json

@@ -1 +0,0 @@
-[]

homelab/server/config/grafana-stack/docker-compose.yml

@@ -1,65 +0,0 @@
-version: '3'
-services:
-  influxdb:
-    image: influxdb:2.0
-    container_name: grafana_influxdb
-    restart: unless-stopped
-    networks:
-      - monitoring
-    ports:
-      - 8086:8086
-      - 8089:8089/udp
-    volumes:
-      - ./influxdb.conf:/etc/influxdb/influxdb.conf:ro
-      - "${DOCKER_DATA}/influxdb:/var/lib/influxdb"
-    environment:
-      - TZ=America/Los_Angeles
-      - DOCKER_INFLUXDB_INIT_MODE=setup
-      - DOCKER_INFLUXDB_INIT_USERNAME=jafner
-      - DOCKER_INFLUXDB_INIT_PASSWORD=***REMOVED***
-      - "DOCKER_INFLUXDB_INIT_ORG=Jafner Industries"
-      - DOCKER_INFLUXDB_INIT_BUCKET=Bucket
-      - DOCKER_INFLUXDB_INIT_ADMIN_TOKEN=***REMOVED***
-
-  telegraf:
-    image: telegraf:latest
-    container_name: grafana_telegraf
-    restart: unless-stopped
-    depends_on:
-      - influxdb
-    networks:
-      - monitoring
-    volumes:
-      - ./telegraf.conf:/etc/telegraf/telegraf.conf:ro
-      - ./scripts/.forgetps.json:/.forgetps.json:ro
-      - /sys:/rootfs/sys:ro
-      - /proc:/rootfs/proc:ro
-      - /etc:/rootfs/etc:ro
-
-  grafana:
-    image: mbarmem/grafana-render:latest
-    container_name: grafana_grafana
-    restart: unless-stopped
-    depends_on:
-      - influxdb
-      - telegraf
-    networks:
-      - monitoring
-      - web
-    user: "0"
-    volumes:  
-      - ${DOCKER_DATA}/grafana:/var/lib/grafana
-      - ./grafana.ini:/etc/grafana/grafana.ini
-    environment:
-      - GF_INSTALL_PLUGINS=grafana-clock-panel,grafana-simple-json-datasource,grafana-worldmap-panel,grafana-piechart-panel
-    labels:
-      - traefik.http.routers.grafana.rule=Host(`grafana.jafner.net`)
-      - traefik.http.routers.grafana.tls.certresolver=lets-encrypt
-      #- traefik.http.routers.grafana.middlewares=authelia@file
-
-networks:
-  monitoring:
-    external: true
-  web:
-    external: true
-

homelab/server/config/grafana-stack/influxdb.conf

@@ -1,305 +0,0 @@
-### Welcome to the InfluxDB configuration file.
-
-# Once every 24 hours InfluxDB will report usage data to usage.influxdata.com
-# The data includes a random ID, os, arch, version, the number of series and other
-# usage data. No data from user databases is ever transmitted.
-# Change this option to true to disable reporting.
-reporting-disabled = false
-
-# we'll try to get the hostname automatically, but if it the os returns something
-# that isn't resolvable by other servers in the cluster, use this option to
-# manually set the hostname
-# hostname = "localhost"
-
-###
-### [meta]
-###
-### Controls the parameters for the Raft consensus group that stores metadata
-### about the InfluxDB cluster.
-###
-
-[meta]
-  # Where the metadata/raft database is stored
-  dir = "/var/lib/influxdb/meta"
-
-  retention-autocreate = true
-
-  # If log messages are printed for the meta service
-  logging-enabled = true
-  pprof-enabled = false
-
-  # The default duration for leases.
-  lease-duration = "1m0s"
-
-###
-### [data]
-###
-### Controls where the actual shard data for InfluxDB lives and how it is
-### flushed from the WAL. "dir" may need to be changed to a suitable place
-### for your system, but the WAL settings are an advanced configuration. The
-### defaults should work for most systems.
-###
-
-[data]
-  # Controls if this node holds time series data shards in the cluster
-  enabled = true
-
-  dir = "/var/lib/influxdb/data"
-
-  # These are the WAL settings for the storage engine >= 0.9.3
-  wal-dir = "/var/lib/influxdb/wal"
-  wal-logging-enabled = true
-
-  # Trace logging provides more verbose output around the tsm engine. Turning
-  # this on can provide more useful output for debugging tsm engine issues.
-  # trace-logging-enabled = false
-
-  # Whether queries should be logged before execution. Very useful for troubleshooting, but will
-  # log any sensitive data contained within a query.
-  # query-log-enabled = true
-
-  # Settings for the TSM engine
-
-  # CacheMaxMemorySize is the maximum size a shard's cache can
-  # reach before it starts rejecting writes.
-  # cache-max-memory-size = 524288000
-
-  # CacheSnapshotMemorySize is the size at which the engine will
-  # snapshot the cache and write it to a TSM file, freeing up memory
-  # cache-snapshot-memory-size = 26214400
-
-  # CacheSnapshotWriteColdDuration is the length of time at
-  # which the engine will snapshot the cache and write it to
-  # a new TSM file if the shard hasn't received writes or deletes
-  # cache-snapshot-write-cold-duration = "1h"
-
-  # MinCompactionFileCount is the minimum number of TSM files
-  # that need to exist before a compaction cycle will run
-  # compact-min-file-count = 3
-
-  # CompactFullWriteColdDuration is the duration at which the engine
-  # will compact all TSM files in a shard if it hasn't received a
-  # write or delete
-  # compact-full-write-cold-duration = "24h"
-
-  # MaxPointsPerBlock is the maximum number of points in an encoded
-  # block in a TSM file. Larger numbers may yield better compression
-  # but could incur a performance penalty when querying
-  # max-points-per-block = 1000
-
-###
-### [coordinator]
-###
-### Controls the clustering service configuration.
-###
-
-[coordinator]
-  write-timeout = "10s"
-  max-concurrent-queries = 0
-  query-timeout = "0"
-  log-queries-after = "0"
-  max-select-point = 0
-  max-select-series = 0
-  max-select-buckets = 0
-
-###
-### [retention]
-###
-### Controls the enforcement of retention policies for evicting old data.
-###
-
-[retention]
-  enabled = true
-  check-interval = "30m"
-
-###
-### [shard-precreation]
-###
-### Controls the precreation of shards, so they are available before data arrives.
-### Only shards that, after creation, will have both a start- and end-time in the
-### future, will ever be created. Shards are never precreated that would be wholly
-### or partially in the past.
-
-[shard-precreation]
-  enabled = true
-  check-interval = "10m"
-  advance-period = "30m"
-
-###
-### Controls the system self-monitoring, statistics and diagnostics.
-###
-### The internal database for monitoring data is created automatically if
-### if it does not already exist. The target retention within this database
-### is called 'monitor' and is also created with a retention period of 7 days
-### and a replication factor of 1, if it does not exist. In all cases the
-### this retention policy is configured as the default for the database.
-
-[monitor]
-  store-enabled = true # Whether to record statistics internally.
-  store-database = "_internal" # The destination database for recorded statistics
-  store-interval = "10s" # The interval at which to record statistics
-
-###
-### [admin]
-###
-### Controls the availability of the built-in, web-based admin interface. If HTTPS is
-### enabled for the admin interface, HTTPS must also be enabled on the [http] service.
-###
-
-[admin]
-  enabled = true
-  bind-address = ":8083"
-  https-enabled = false
-  https-certificate = "/etc/ssl/influxdb.pem"
-
-###
-### [http]
-###
-### Controls how the HTTP endpoints are configured. These are the primary
-### mechanism for getting data into and out of InfluxDB.
-###
-
-[http]
-  enabled = true
-  bind-address = ":8086"
-  auth-enabled = false
-  log-enabled = true
-  write-tracing = false
-  pprof-enabled = false
-  https-enabled = false
-  https-certificate = "/etc/ssl/influxdb.pem"
-  ### Use a separate private key location.
-  # https-private-key = ""
-  max-row-limit = 10000
-  realm = "InfluxDB"
-
-###
-### [subsciber]
-###
-### Controls the subscriptions, which can be used to fork a copy of all data
-### received by the InfluxDB host.
-###
-
-[subsciber]
-  enabled = true
-  http-timeout = "30s"
-
-
-###
-### [[graphite]]
-###
-### Controls one or many listeners for Graphite data.
-###
-
-[[graphite]]
-  enabled = false
-  # database = "graphite"
-  # bind-address = ":2003"
-  # protocol = "tcp"
-  # consistency-level = "one"
-
-  # These next lines control how batching works. You should have this enabled
-  # otherwise you could get dropped metrics or poor performance. Batching
-  # will buffer points in memory if you have many coming in.
-
-  # batch-size = 5000 # will flush if this many points get buffered
-  # batch-pending = 10 # number of batches that may be pending in memory
-  # batch-timeout = "1s" # will flush at least this often even if we haven't hit buffer limit
-  # udp-read-buffer = 0 # UDP Read buffer size, 0 means OS default. UDP listener will fail if set above OS max.
-
-  ### This string joins multiple matching 'measurement' values providing more control over the final measurement name.
-  # separator = "."
-
-  ### Default tags that will be added to all metrics.  These can be overridden at the template level
-  ### or by tags extracted from metric
-  # tags = ["region=us-east", "zone=1c"]
-
-  ### Each template line requires a template pattern.  It can have an optional
-  ### filter before the template and separated by spaces.  It can also have optional extra
-  ### tags following the template.  Multiple tags should be separated by commas and no spaces
-  ### similar to the line protocol format.  There can be only one default template.
-  # templates = [
-  #   "*.app env.service.resource.measurement",
-  #   # Default template
-  #   "server.*",
-  # ]
-
-###
-### [collectd]
-###
-### Controls one or many listeners for collectd data.
-###
-
-[[collectd]]
-  enabled = false
-  # bind-address = ""
-  # database = ""
-  # typesdb = ""
-
-  # These next lines control how batching works. You should have this enabled
-  # otherwise you could get dropped metrics or poor performance. Batching
-  # will buffer points in memory if you have many coming in.
-
-  # batch-size = 1000 # will flush if this many points get buffered
-  # batch-pending = 5 # number of batches that may be pending in memory
-  # batch-timeout = "1s" # will flush at least this often even if we haven't hit buffer limit
-  # read-buffer = 0 # UDP Read buffer size, 0 means OS default. UDP listener will fail if set above OS max.
-
-###
-### [opentsdb]
-###
-### Controls one or many listeners for OpenTSDB data.
-###
-
-[[opentsdb]]
-  enabled = false
-  # bind-address = ":4242"
-  # database = "opentsdb"
-  # retention-policy = ""
-  # consistency-level = "one"
-  # tls-enabled = false
-  # certificate= ""
-  # log-point-errors = true # Log an error for every malformed point.
-
-  # These next lines control how batching works. You should have this enabled
-  # otherwise you could get dropped metrics or poor performance. Only points
-  # metrics received over the telnet protocol undergo batching.
-
-  # batch-size = 1000 # will flush if this many points get buffered
-  # batch-pending = 5 # number of batches that may be pending in memory
-  # batch-timeout = "1s" # will flush at least this often even if we haven't hit buffer limit
-
-###
-### [[udp]]
-###
-### Controls the listeners for InfluxDB line protocol data via UDP.
-###
-
-[[udp]]
-  enabled = true
-  bind-address = "0.0.0.0:8089"
-  database = "host"
-  # retention-policy = ""
-
-  # These next lines control how batching works. You should have this enabled
-  # otherwise you could get dropped metrics or poor performance. Batching
-  # will buffer points in memory if you have many coming in.
-
-  batch-size = 1000 # will flush if this many points get buffered
-  # batch-pending = 5 # number of batches that may be pending in memory
-  batch-timeout = "1s" # will flush at least this often even if we haven't hit buffer limit
-  # read-buffer = 0 # UDP Read buffer size, 0 means OS default. UDP listener will fail if set above OS max.
-
-  # set the expected UDP payload size; lower values tend to yield better performance, default is max UDP size 65536
-  # udp-payload-size = 65536
-
-###
-### [continuous_queries]
-###
-### Controls how continuous queries are run within InfluxDB.
-###
-
-[continuous_queries]
-  log-enabled = true
-  enabled = true
-  # run-interval = "1s" # interval for how often continuous queries will be checked if they need to run

homelab/server/config/grafana-stack/scripts/.forgetps.json

@@ -1 +0,0 @@
-[{"dim":"minecraft:overworld","tpt":0.000,"tps":20.000},{"dim":"minecraft:the_nether","tpt":0.000,"tps":20.000},{"dim":"minecraft:the_end","tpt":0.000,"tps":20.000},{"dim":"rftoolsdim:coaldim","tpt":0.000,"tps":20.000},{"dim":"compactmachines:compact_world","tpt":0.000,"tps":20.000},{"dim":"rats:ratlantis","tpt":0.000,"tps":20.000},{"dim":"rftoolsdim:dim1","tpt":0.000,"tps":20.000},{"dim":"rftoolsdim:fluoritedim","tpt":0.000,"tps":20.000},{"dim":"rftoolsdim:dim2","tpt":0.000,"tps":20.000},{"dim":"rftoolsdim:dim3","tpt":0.000,"tps":20.000},{"dim":"rftoolsdim:dim4","tpt":0.000,"tps":20.000},{"dim":"rftoolsdim:uraniumtendrils","tpt":0.000,"tps":20.000},{"dim":"rftoolsdim:dim5","tpt":0.000,"tps":20.000},{"dim":"rftoolsdim:dim6","tpt":0.000,"tps":20.000},{"dim":"atum:atum","tpt":0.000,"tps":20.000},{"dim":"rftoolsdim:uraniumdim","tpt":0.000,"tps":20.000},{"dim":"mythicbotany:alfheim","tpt":0.000,"tps":20.000},{"dim":"undergarden:undergarden","tpt":0.000,"tps":20.000},{"dim":"Overall","tpt":0.000,"tps":20.000}]

homelab/server/config/grafana-stack/telegraf.conf

@@ -1,32 +0,0 @@
-[global_tags]
-[agent]
-  interval = "10s"
-  round_interval = true
-  metric_batch_size = 1000
-  metric_buffer_limit = 10000
-  collection_jitter = "0s"
-  flush_interval = "10s"
-  flush_jitter = "0s"
-  precision = ""
-  hostname = ""
-  omit_hostname = false
-[[outputs.influxdb_v2]]
-  urls = ["http://influxdb:8086"]
-  organization = "Jafner Industries"
-  bucket = "Bucket"
-  token = "***REMOVED***"
-[[inputs.cpu]]
-  percpu = true
-  totalcpu = true
-  collect_cpu_time = false
-  report_active = false
-[[inputs.disk]]
-  ignore_fs = ["tmpfs", "devtmpfs", "devfs", "iso9660", "overlay", "aufs", "squashfs"]
-[[inputs.mem]]
-[[inputs.system]]
-[[inputs.sensors]]
-[[inputs.file]]
-  files = ["/.forgetps.json"]
-  data_format = "json"
-  name_override = "tickinfo"
-  tag_keys = ["dim"]  

homelab/server/config/monitoring/.env

@@ -0,0 +1 @@
+DOCKER_DATA=/home/joey/data/monitoring

homelab/server/config/monitoring/docker-compose.yml

@@ -1,5 +1,21 @@
 version: '3'
 services:
+    grafana:
+        image: grafana/grafana-oss:latest
+        container_name: grafana_grafana
+        restart: unless-stopped
+        networks:
+            - monitoring
+            - web
+        user: "0"
+        volumes:  
+            - ${DOCKER_DATA}/grafana:/var/lib/grafana
+            - ./grafana.ini:/etc/grafana/grafana.ini
+        labels:
+            - traefik.http.routers.grafana.rule=Host(`grafana.jafner.net`)
+            - traefik.http.routers.grafana.tls.certresolver=lets-encrypt
+            #- traefik.http.routers.grafana.middlewares=authelia@file
+
     prometheus:
         image: prom/prometheus:latest
         container_name: monitoring_prometheus