Replace telegraf with prometheus exporters

Still missing SMART and ping, but those can come later.

Swapped as the polling model for prometheus doesn't play especially well with telegraf, and leads to gaps in data

ansible/galaxy-requirements.yml

@@ -2,7 +2,8 @@ collections:
   - ansible.posix
   - community.general
   - community.docker
-  - amazon.aws  # Dependency of rossmcdonald.telegraf
+  - name: https://github.com/prometheus-community/ansible
+    type: git
 
 roles:
   - src: geerlingguy.docker
@@ -13,8 +14,6 @@ roles:
   - src: ironicbadger.proxmox_nag_removal
     version: 1.0.1
   - src: chmduquesne.iptables_persistent
-  - src: rossmcdonald.telegraf
-    version: v1.2.0
   - src: geerlingguy.gitlab
     version: 3.2.0
   - src: dokku_bot.ansible_dokku

ansible/group_vars/all/node_exporter.yml

@@ -0,0 +1,3 @@
+node_exporter_version: 1.5.0
+node_exporter_web_listen_address: "{{ private_ip }}:9100"
+node_exporter_enabled_collectors: []  # Disable the systemd collector by default

ansible/main.yml

@@ -85,9 +85,10 @@
       become: true
     - zfs
     - pve_nebula_route
-    - telegraf
     - role: ironicbadger.snapraid
       become: true
+    - role: prometheus.prometheus.node_exporter
+      become: true
 
 - hosts: forrest
   roles:

ansible/roles/forrest/files/prometheus/docker-compose.yml

@@ -38,6 +38,16 @@ services:
     volumes:
       - ./alertmanager.yml:/etc/alertmanager/alertmanager.yml:ro
 
+  proxmox_exporter:
+    image: prompve/prometheus-pve-exporter:latest
+    restart: unless-stopped
+    user: "{{ docker_user.id }}"
+    environment:
+      - PVE_USER=prometheus@pve
+      - PVE_TOKEN_NAME=prometheus
+      - PVE_TOKEN_VALUE={{ prometheus_api_token }}
+      - PVE_VERIFY_SSL=false
+
 networks:
   grafana:
     external: true

ansible/roles/forrest/files/prometheus/prometheus.yml

@@ -5,14 +5,18 @@ alerting:
             - alertmanager:9093
 
 scrape_configs:
-  - job_name: telegraf
+  - job_name: pve
-    metric_relabel_configs:
-      - source_labels: [__name__]
-        regex: go_.+
-        action: drop
     static_configs:
       - targets:
-          - "{{ pve_hosts.pve.ip }}:9273"
+          - "{{ pve_hosts.pve.ip }}"
+    metrics_path: /pve
+    relabel_configs:
+      - source_labels: [__address__]
+        target_label: __param_target
+      - source_labels: [__param_target]
+        target_label: instance
+      - target_label: __address__
+        replacement: proxmox_exporter:9221
 
   - job_name: traefik
     metric_relabel_configs:
@@ -102,3 +106,13 @@ scrape_configs:
     metrics_path: /projects/{{ healthchecks_project_uuid }}/metrics/{{ healthcheck_api_token }}
     static_configs:
       - targets: [healthchecks.io]
+
+  - job_name: node
+    metrics_path: /metrics
+    static_configs:
+      - targets:
+          - "{{ pve_hosts.pve.ip }}:9100"
+    metric_relabel_configs:
+      - source_labels: [__name__]
+        regex: go_.+
+        action: drop

ansible/roles/forrest/vars/main.yml

@@ -9,3 +9,4 @@ healthcheck_api_token: "{{ vault_healthcheck_api_token }}"
 alertmanager_from_address: "{{ vault_alertmanager_from_address }}"
 alertmanager_smtp_password: "{{ vault_alertmanager_smtp_password }}"
 alertmanager_to_address: "{{ vault_alertmanager_to_address }}"
+prometheus_api_token: "{{ vault_prometheus_api_token }}"

ansible/roles/forrest/vars/vault.yml

@@ -1,49 +1,52 @@
 $ANSIBLE_VAULT;1.1;AES256
-61666339653630373931366533656437386337663739313532663339356562656466373461303837
+36623535313964653161353330663436356239613837653837393939373034353031646535333535
-3132343434633835333035303863346532363137656565380a646239326534346135333737653337
+6439313832316239616233306632373934616134616466380a316361363263373938636161666535
-31626663636661396462353765653830396132306531393965306439316437623866306166656430
+31613461333637373732626233623434316335353964353433643635653566613933393361336139
-3664373263643666350a353139653633663233623064353532313136393865333763353233343132
+3864373963396264320a376634346331373762313733323961386566646338633936303631303566
-61363864666534636630623639346361656361633235313535323030633434656136626131656237
+66616534326430653266396635353932623661363533356537636662636537656434363562646230
-62633433613537363431336664313166306539616431626131653337363536633536386561373630
+30613831336561376639393466373739373138313931333163353061633465623362666564313631
-32323165393538636437653361363766636139646166646538666462333337333837383966643263
+66623235353531613737643937613430323934376433393836346339626137616561313062663234
-31646562316433323962353439353636393965393962633665306232653737353233346632326233
+63363736326439623661376132613136383465393761653236663631613339653066356436653630
-36333863623933313238663434643737363638666662323238643238326165396433653462663934
+66623865303735616335373231643233386639323838353534613337316161633765396234366533
-62663538366633386533316432323535656563346435353665333430623434616634393565633962
+33616631663530643764373937346262633734366339303837393737666665363465333239343933
-65383262356333643437636531663034303933313534393965633739633031393139386633376134
+35613962396534336232623833303034643639323931633966396439383463396261313862626335
-35653164313830643065613439663462306131383135366363653834386230363639366233643866
+31323434613838353961336136613966636635646632393839663664376632373834313265643338
-30626638306666653065353237663434633333376337343133656237666662343163656164353935
+30663132633362323831313231333164643665386535323231646262656631383631393539616639
-39386262303664653164356431643466306463343564633064376532663133393432626333393236
+34343563353064303833383236626136666264316236316537333965313162616637323966363335
-39306463663963383234363664643265393434363138373062643165313332643833663464343766
+32353936663162316564306337353861396634353935353935306135343665316262643831396537
-33393162336535303136653230633135636266653863646331346630386131303131333636613938
+61393266383538666563363261646534636632303332343662636631316663343930303766623638
-66386331643966313236356634623938363835323439343234613164616132616137353237356162
+35376565343638316339623061396536643636313966383633346231633631353032356661386132
-66333964363361353436396634353735663963643239356164333434373166623731643038656136
+66623439336338616666626431303635373833666137326234653161336434346133636261363662
-32376339316434373836333532373664323762636634336361616437306132356637616162303231
+39313732303736386137656664303365363234336265643064306562643435633838373864353862
-30356263366137363337316631643536643539653237636362386366656434353861343239306431
+33366635333630373162656630666232333563623066333461653963363961623435646631373561
-33326163336536636233643434633461626430313536376632623334303938316364316162386365
+64643738346138366566303233326663383835386132663034313461383161616164636332396332
-38393138356538623235663539393166306366396364306335656534366663616336666637323138
+37663131386135393833373461663432666264363065666630646164633134303439663435616235
-32343035373063306462636163616364616332333263663737653235613230313465363466616565
+35656234313761376532306264393637653433623863383830323935316332383338623134323366
-36373831383364333837303433663839353363663730333665663138386635626530323633626661
+31336665386137323132363962363335623635336131373930353635353663333366363266303138
-62633066633361366562383737646565613566653866663136326135383533303962326637316132
+35626262613261636561373730626635303836623561643436646430653365663432323938393863
-39313832303538363432646432616433303966626133653461363530623966363133646530353931
+63633331663462323163646237386262376337313330323036613434383165616530643362616131
-62646334646336633162633763613333663937636262633138323932313632653630393162363439
+63616562353964316634646434653138333266646633616631653663663838306163616633643234
-37343739313066343831623265353164386239373430623735343739373737373130643631343664
+61333230373237613436343662363434303766383336376232353066313231666330613761643366
-31626633303764633831646565653732326363336431353433353365633433626665353733663336
+36326638326439653966643430313366376661633636366565393461623438323366373333663633
-32643132666565373332323136386630633561656632613335613965343439633831336336306464
+61633763623631333665363333646433656166633364303836623566333336343761613435353138
-62303234646233633366383430366431336430356463643630623566373333646532333663623466
+37366165613263653564386334303030623333646164303662363065333831376334656537613130
-63326364393166393461653366373634626333623836303466636136663331383239336432363661
+33373864663237383064653461616165653834393063663332643235316139333539623463343161
-62383836653562633765333034306161326539396330663831363135326235343535393663363638
+38636564626466633631393938653066373764663935353763626133623762306164383831663061
-36616130663538376534616161393930633462316539643561323665313339646234306232656662
+34333065326666373337663931313763383739383763333235333939376133363236643136346233
-30356139303465313561636433646162346136303632653230353437383063396438616536376533
+62643833376631643036613963643939333133343036613332313866373032646332363231313139
-30363362613635336162336537333932306666666632336664613631623830616538633131663365
+61373365653665343066636162356336373833393363373866343436323639623435383831363335
-36656164623139643333333237376333656632306436313865656337616439343434383231616561
+30333033326638363930613030356664333233633339666366643062353634333161343838666231
-32323232306437353034643735356532653233306131356632393963616337303835663632653837
+32346332663538653937623136653438636463323463376263303962353562313833373937303066
-63656433633061313034656565373061643132623163626230386561323466353534323734326437
+65303037323030653434313164393766633134306435633263363335636561356264376665363639
-34336439363563373637336139376261376439306166656337663366383463313938333731306664
+35613731373437386566663266656266343639326334303239613862353963323436633836383766
-34393062653536346464373637343232666465336564613235323931373465323864386362336561
+35323930633039396535616265643234303639393035363865643236623838333337626135343665
-37633837336136373030346533633562343439316264333462623763666162373938326437353638
+36373038666332376663333565623362303631663830336131343438353764653831633433363436
-63343062313732356338623731626232626265366466623437383734313630393030366330353864
+36333839303433623966363561313564303037393165383732323763353232653564346138666438
-63613766373438366564663761623766353636303066343665353437643830626364663031336537
+30653836626139356133346538616135313034633966373036303461393562363336386633626365
-36663739303232363162646464663339623939363733393835383366636463643633396362363137
+33393565643730383634346238356462313435366538636234656237613864656165656439363061
-62613138656563666661363630633935346433356235303936356431343637663938646161343266
+32626235323362333239373631383830653035383164646364343461376562636564343063353139
-61313861346562396439383262396435313064643264353536326238623461653965626334653866
+61306535333466653937303635353962376162376431336563316130343530636431623537633332
-36646239313666396338
+65373333376338353930316561636530343062653964323463653632653332376432343237656465
+63333437613064313438353134333566303033313339323162643061363836643931343135396130
+32623435653533326563616263323938343332306362383034663139653965626231336637383939
+313534343431303739396263303737303365

ansible/roles/telegraf/files/telegraf.conf

@@ -1,122 +0,0 @@
-# Global tags can be specified here in key="value" format.
-[global_tags]
-  # dc = "us-east-1" # will tag all metrics with dc=us-east-1
-  # rack = "1a"
-  ## Environment variables can be used as tags, and throughout the config file
-  # user = "$USER"
-
-
-# Configuration for telegraf agent
-[agent]
-  ## Default data collection interval for all inputs
-  interval = "60s"
-  ## 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
-
-  ## Override default hostname, if empty use os.Hostname()
-  hostname = "{{ ansible_hostname }}"
-  ## If set to true, do no set the "host" tag in the telegraf agent.
-  omit_hostname = false
-
-
-###############################################################################
-#                            OUTPUT PLUGINS                                   #
-###############################################################################
-
-[[outputs.prometheus_client]]
-  listen = "{{ private_ip }}:9273"
-  metric_version = 2
-
-###############################################################################
-#                            INPUT PLUGINS                                    #
-###############################################################################
-
-[[inputs.ping]]
-  urls = ["192.168.1.1", "9.9.9.9"]
-  ping_interval = 60.0
-
-[[inputs.smart]]
-  use_sudo = true
-
-[[inputs.proxmox]]
-  base_url = "https://{{ pve_hosts.pve.ip }}:8006/api2/json/"
-  api_token = "telegraf@pve!telegraf={{ proxmox_telegraf_token }}"
-  node_name = "pve"
-  insecure_skip_verify = true
-
-[[inputs.disk]]
-  ignore_fs = ["tmpfs", "devtmpfs", "devfs", "iso9660", "overlay", "aufs", "squashfs"]
-
-[[inputs.system]]
-
-[[inputs.sensors]]
-
-[[inputs.nvidia_smi]]
-
-[[inputs.exec]]
-  command = "speedtest --json"
-  name_override = "speedtest"
-  timeout = "2m"
-  interval = "10m"
-  data_format = "json"

ansible/roles/telegraf/tasks/main.yml

@@ -1,10 +0,0 @@
-- name: Install and configure telegraf
-  import_role:
-    name: rossmcdonald.telegraf
-  become: true
-
-- name: Let telegraf do smart stats
-  lineinfile:
-    path: /etc/sudoers
-    line: "{{ telegraf_runas_user }}  ALL=(ALL) NOPASSWD: /usr/sbin/smartctl"
-  become: true

ansible/roles/telegraf/vars/main.yml

@@ -1,11 +0,0 @@
-telegraf_configuration_template: files/telegraf.conf
-telegraf_aws_tags: false
-
-proxmox_telegraf_token: !vault |
-  $ANSIBLE_VAULT;1.1;AES256
-  34646261333165343031323566643738353363393864363035303037653838383038363162346164
-  6239313461393366373534636539613639623061393231640a613837343731373462666662356563
-  34343934313165623433646335383064333136343237353030353532653631633635366135336134
-  3931336436656561350a376137636666633937636134663139326630623761386435653435653338
-  36643232396361313436666533373737626365633662383239623561373061313636366231636330
-  3539303065366366323137336432613165336462363330363735