monitoring: container, node dashboard improvements; separate common.py logic

monitoring: add grafanalib, containers dashboard
refactor: separate templating for j2 and normal files
2024-10-30 18:24:34 -07:00 · 2024-10-30 18:24:28 -07:00 · 2024-10-30 18:11:26 -07:00 · 2024-10-23 15:35:54 -07:00 · 2024-10-22 23:16:41 -07:00
23 changed files with 805 additions and 361 deletions
--- a/.idea/alpina.iml
+++ b/.idea/alpina.iml
@@ -4,7 +4,7 @@
    <content url="file://$MODULE_DIR$">
      <excludeFolder url="file://$MODULE_DIR$/venv" />
    </content>
-    <orderEntry type="jdk" jdkName="Poetry (alpina) (4)" jdkType="Python SDK" />
+    <orderEntry type="inheritedJdk" />
    <orderEntry type="sourceFolder" forTests="false" />
  </component>
  <component name="PyDocumentationSettings">
--- a/.idea/jsonSchemas.xml
+++ b/.idea/jsonSchemas.xml
@@ -39,6 +39,22 @@
            </SchemaInfo>
          </value>
        </entry>
+        <entry key="Loki">
+          <value>
+            <SchemaInfo>
+              <option name="name" value="Loki" />
+              <option name="relativePathToSchema" value="https://json.schemastore.org/loki.json" />
+              <option name="applicationDefined" value="true" />
+              <option name="patterns">
+                <list>
+                  <Item>
+                    <option name="path" value="roles/alpina/templates/services/monitoring/loki_config/loki-config.yaml.j2" />
+                  </Item>
+                </list>
+              </option>
+            </SchemaInfo>
+          </value>
+        </entry>
        <entry key="Traefik v2">
          <value>
            <SchemaInfo>
@@ -124,25 +140,6 @@
            </SchemaInfo>
          </value>
        </entry>
-        <entry key="prometheus.rules.json">
-          <value>
-            <SchemaInfo>
-              <option name="name" value="prometheus.rules.json" />
-              <option name="relativePathToSchema" value="https://json.schemastore.org/prometheus.rules.json" />
-              <option name="applicationDefined" value="true" />
-              <option name="patterns">
-                <list>
-                  <Item>
-                    <option name="path" value="roles/alpina/templates/services/monitoring/prometheus_config/container-alerts.yml" />
-                  </Item>
-                  <Item>
-                    <option name="path" value="roles/alpina/templates/services/monitoring/prometheus_config/container.alerts.yml" />
-                  </Item>
-                </list>
-              </option>
-            </SchemaInfo>
-          </value>
-        </entry>
      </map>
    </state>
  </component>
--- a/.idea/misc.xml
+++ b/.idea/misc.xml
@@ -3,5 +3,5 @@
  <component name="Black">
    <option name="sdkName" value="Poetry (alpina) (2)" />
  </component>
-  <component name="ProjectRootManager" version="2" project-jdk-name="Poetry (alpina) (4)" project-jdk-type="Python SDK" />
+  <component name="ProjectRootManager" version="2" project-jdk-name="Poetry (alpina)" project-jdk-type="Python SDK" />
 </project>
--- a/README.md
+++ b/README.md
@@ -8,6 +8,22 @@ running on top of TrueNAS SCALE, separating all the docker stuff from the applia

 # Notes

+## Monitoring
+The monitoring stack is set up to monitor all the containers and the host.
+
+This is a work in progress, Grafana is set up with grafanalib, a Python library that generates Grafana dashboards.
+The dashboards are generated from Python scripts in 
+[grafana_config/dashboards](roles/alpina/templates/services/monitoring/grafana_config/dashboards).
+
+This requires a custom grafana image, which is built from the 
+[Dockerfile](roles/alpina/templates/services/monitoring/Dockerfile).
+
+This also means it has to be manually rebuilt whenever the dashboards are updated.
+From the services/monitoring directory, run:
+```bash
+docker compose up -d --build --force-recreate grafana
+```
+
 ## IPv6
 The current configuration is designed to work with IPv6. 
 However, because of how (not properly) I'm doing the subnetting 
--- a/group_vars/alpina/vars.yml
+++ b/group_vars/alpina/vars.yml
@@ -24,8 +24,6 @@ minio_password: "{{ vault_minio_password }}"
 influxdb_admin_password: "{{ vault_influxdb_admin_password }}"
 influxdb_admin_token: "{{ vault_influxdb_admin_token }}"

-alertmanager_discord_webhook: "{{ vault_alertmanager_discord_webhook }}"
-
 # Traefik
 acme_email: "{{ vault_acme_email }}"
 cloudflare_api_token: "{{ vault_cloudflare_api_token }}"
--- a/group_vars/alpina/vault.yml
+++ b/group_vars/alpina/vault.yml
@@ -1,96 +1,88 @@
 $ANSIBLE_VAULT;1.1;AES256
-32653863663065353431636364373163613536643238613961666561653663633530646165643766
-3833323937353331313136633965393061616135366534660a333037383066303431623830313464
-65346431633238666534373033663138353438313762326361666233353866663534363536643034
-3636323439316261630a623262336331663431633266336235653034323234383566323963623365
-32626363626164373536663464643632393761346137623866633237643038306265636362626561
-61313634353634373530383061393364613461303132326335316566326436633635633131643433
-31376539396639326464333233643933373737313064363262323639363964643862633035396161
-35643037636535623966626131393538643432396536643365383736636262356135373434376433
-32316361343330303431376234323632323932376635343964383733633761326639393966383039
-35646131343034663962363335373661323065663764396631343461383661663738386163323633
-36303464646532633235663662666663343238633465663334326463383133643239666634653739
-35396130393961303230396236303766336666643930626161333338326137663235323066663032
-33376564373563323635356233616264313663373534333636643236393866613062656338353864
-66386132663362363832366661646462316139353132626662663934336530386534376538633235
-62653131653835323261373435373631396466353738306362616266616532313435323633613933
-61646132346536323632643865326234356535346566346532383162393265613931343962303463
-31636334343736666434353835633734396465653862613234386431306463326134613931646232
-32353535663133623434643866336165616232613662336533383432633338373763643337616637
-38323237646461376433316164646366383438316639633162303739383263656265633364303565
-36643339356136653332666230633939636264306431636562323864373037623138363739616561
-37613364653737353638646564323439646138646536636564303866636233616264383466656439
-33646232653061616437656162353036313834616162313936353533393833313432656534343363
-35636638326236646163323463356634326534623165306461316530353936646162323435633862
-64396464303363323837316162353734626663643962303534336637336632333463393734383532
-66616534666466393333386337363238383432643764373864613461363766333932333862363332
-61313364613031376334326635636432346532613462613265643462636436663963323862353733
-38396261613332396633666130653262313234633132353264363266336231373535306532383661
-65323530653531646339626537653433303332656535346639393466353133363833326236656231
-33336265373463396135653730616266346331376461346433343464326238323034653330393732
-36643432316662333633333036633761653031393433333338663633386264656535623534653463
-36363565303333356361616539376532353066336137336134656465383364636361656664356439
-65326334643631663665376530646433323439653864623964323363396561313663636538356536
-63626336303862333364363166353437353163656238303765636662636137383337623563666264
-66326633343230386638616438393436633431343264343231386563613935626430306337343533
-66656366333332326131343661356236396430303832303834653530623639353036663436373862
-61336437386338343965653563646664643438353232306231316564616462643236646239333062
-38643461346639623964626438396631396139383332666130316635656530653136333662353566
-36313261646330373963663032316662383137366436636534383366636362366435393036373264
-34646537666462363531343335336638343038333633663862666163306662643634326533316561
-61613235366233636530663462353066646530386265623534663336376364323237343936646134
-31616563653864383565306439613932396562613835613562326264326535636630646666366335
-36653631353961353933386236636534393636356334633336313333383238353838336335646630
-63633365666530623562323634303935326362643762616532303531303139333565643835396163
-36353130656365326435343130613234336637346461313639653133623933376163393935366266
-66653337353732363038663164363663623266356366663637343466393836353965343730666362
-38663636336265383331666666616535366334616431306164303738306436333364653765356662
-37316433323563323431623164386337343563663538333435616333343433396236356363333262
-61396664326234343136666331356465333233663135613839616334623033316362336162613731
-38646530326538643337323838326563303130643934623939346635343331356531373235663937
-62396530383365666439373632613633633233376139616138323033613135383330333132643839
-65363833616337656662653462323436303531653635663739633366616532333761323238353764
-39373836303735393165393435323139346661346135636138613731373165386533386333393364
-32336265386334386338653734353565343733393931373436336233333031356531313739636666
-61376234393631343236643137616631373564376132623534333939346162353662306661393438
-32326566373934653463653737383131386431363664333535626361646637613632383132623533
-32343465366562363765353366333330633631353936613930376631336538306230626632303966
-31343936386535663165663066663862656439306363326337313561396132316338363930323632
-33313061623534373338623931663934396339633564353533626639373837323832366132343538
-63373862663137306665383732303863343564343830636233613139666631626532373938386663
-35646331646462356639383964373732393866653963643832633661323430323430613330633364
-35343262366362646165383032333236623863656264353964623136643631326135623538306261
-37393839343331653665356131343063316232303963636462653238333466636334616435666463
-65636662383930353238623130363834616137643830633261646338363435343839633565303562
-37623231396163346464303464333962336261353634396236613132306464643764356265656137
-32373263613964396430646332666235303634373431643939623963633334326135626565656662
-30646166303732643562653166633232666635343665616665653566316632303861613861313333
-38393636663137333231613239353661656338333536656563616237343234623031363535666637
-61343662663965663161666436366630366432363733663537613064386130326466343366383232
-32363662343561666665323565356163383932336361656132373263363239636666613461366339
-31323264393866386239353333386161643330343262366666323533303737373163313262313766
-61303638366263346232353134333431613730386431623235323537323962666133613939353762
-63326361633630323937353163383930626336663365626532613031623532393932316138353335
-32363262393764663135393466616639373965313238323935383531633434633038663437646662
-31633265373937316533373332316132363061386133356231623230393739326464333761336338
-38626234646164616265633061346239363164376532383834356435346232653065326362343363
-39613532356166633133626563643238373661323937353635343464666339323561326136623366
-62633637656462376136633963653263346565366563646533373431613761616231653739613537
-32343332356435393635363837396463613165626337346235303363613764306132343539333836
-63386633626332396339383165303166653334663239313066666632356165643161356262346230
-32636365636364663466343939663538386439343336303537636230306263643534653339313538
-31373165363962373337636138336561336638633762373363646139366339323031313664306534
-30623130663037323839666166323162393065643535663866383062356330633137343239316436
-32303132393739653363376138633430313832383165663366626436653033663637616664346632
-63633439663734393236343265323533633639316133323336373064633138363266316135363335
-31336637666331333139306537333565333064666433653730633430336261656665613263663937
-64313230656333373838346439623061393164393239393934306336373063303934663334353532
-31313637623466313835313566616161376230343532653561343364383133653736646338303631
-36356164303630303433356332343630616465383831623036383833393330663566616333653161
-63393361643266323336393962663263323338633634633033393762656139393665353630633637
-39386462303731396261613961613238616237373332656361303139633763303837653765623464
-64333565666532653864383861333433353731343161613231383836353966353636373762306132
-35333536373939656638356333383135313231306433656536383933623634653263353434393238
-32323037666135316337633465666335376332326633346665643333656139386465353134356636
-36333434303538326135346539313734393939353163316666366438613133333464623732666438
-663934323030303937623038343662646163
+36636236366435333738633465323539336231393239656538643863643233346563333836623335
+3136393936656261396434316232356338313838373666660a653464613833306133343232623864
+61666561336462376664363463313533353238623031613664353063396236343663643936303730
+6235646336306636360a653238633038306532613436633132363231613862383636313838623461
+32633366326136346435613232396632396365656138643361643139353430663637353565383664
+36623961663030653639316131376535363138343965636437653139646233613765323439393030
+31666137346339663162393836636638636431326232323461353661613062623032306130393965
+38313931313935666633343835303232333961633232623538383138366262663335323764323939
+32373333663834626633363265373632356439633862316562323565646530383534653338353165
+38396434353332623164346137383238343536303130616666643065306431656137303263323135
+34316662353031653932396239623733313037383935383762623136346636323434363231623161
+30393864353466643637316566663366363231373335663331323932663837626239663633663965
+66333531323861663130353531323339386566303630366236636135393439356634393732623033
+31336231363935633436363962316666666336303338313636386163313666636336343464336133
+33313730303961663632323435323963663530623265663664343735643061323332343265343431
+61363039333730623562363233373537633138663239313132336666313237373137353663326538
+32366130326635366433393434653735616132366264386461363063393265623765666461626366
+38636239376534653230663932393930343162333262643130633835343363613061623932363761
+64643164323335376565646137643763316562343565366462376162333633313737303465373362
+63343734633536353661353165346632666230616138396461336332623365366432313734343837
+30613736313961663334326335333834336634373338326631313739363765303036303132346166
+37313030373264383564383936396339623061616134356663333733653838393537306336313135
+32336261356437653863653839373130323035346538343938646265653239376236373932646433
+35373932326535643763396563373138626239393661373231393066323335336264373835336635
+38393732643630336364363834303534663334396363623261383339313939663461303236646237
+36393330373534383836373065373239353836653137306338336638396662363434303839363466
+37303332343464663733653632363239366337656364333532313237633935616637333361383763
+62363063323362323565363837333264346161353032643039323839336666656333336433376231
+36363335626137366135373230613436653232663138343862623562306331336330356630316166
+30613264353165343634663461373630653632366333313837373237613339336638396338376465
+64633638373263376330343561303664666139663237326637663964386133623164626339346635
+66636365366562343636653362656133306164353761346661343430356633613063656466316262
+31633932313532663930303837353863333664393563646566396164666236633832633235653362
+63663931353436623034653733313766393465363466363831643130643939356335643166356436
+38386530333264313263636438376134666235646636316233653330613735323234313036356639
+61316164376434616239646235326661323363333835393430646462323234356138653163616530
+65623233636435396462343437626130353735643530376538633762346332653162353563386366
+32656633633935626238323431643631633434633032303435383037353834653964326336616530
+30363765663133313239373664383830393238303439653531316664636532363135636563356666
+34376636373033353665373261363536393562653638306661663832326139383565613862333831
+38616238616332326532656430393331383161376237393365666639363732363164306332343336
+37366638326464373261386431623731306663616262633837313965633530616265326536323136
+62366365666461383535663637633332626464643062653139623333663038316536353930653266
+37343830613062346533613762663738343138383537396435643765323237623130363564396462
+61663063643135303539313062396338353061346336303938626361343238366366393533363638
+31313437623631626437393761366537636664393863306164373431653133316639623630353336
+65313037636533393362363266366231393334613264343331623531393666336336626265366163
+34663161396633666162326564313735373137303337386538633866653331646635633532336465
+34386166373436386566656135313438363733353139663630613430363332656239356139393532
+35626337666639376664346631323938316538333066353363646562323266353165366632656137
+66366162376165626564363230353062666364646363366637666433636333316536623435623836
+62346566363362363939353038396566653238666138666531396338323262323965383031336362
+34613332363334653531383231363539343133333531666564386133346562323338366139663438
+31613466366438643566333632326239653662636464373337326537313234393038306132343730
+36633136366162643966396362643165313336383862653435343630646431306366656636353230
+64326633346561613662383863356531306563623439363566643733336535303335303164633535
+36356463616162313039386434323637383937613133623131373033373462363365643730666166
+65383166346638313533326366346433656461346439343838306564393336383536633732343965
+39306231386130303433616361366363366163646534316138623362393063663438313165643762
+39393332653564333762663762366633386135353865366338396138666265653662373535666366
+35613937613366323064316561643435353830316239396464393737613835373964626437316464
+39643664656565633966393832643033323130636562383233323636363361353430353062323439
+39396464633336623963633963326461316562333162333766613064336462613235336531623437
+30383063653666633839646533386239366637346230363033306161386537303039376465303535
+34643162323065326264343662303138313063303834353832393663616239383739313133393532
+62393766343037666564326132386139346661383564366366646530346434373366326531356138
+31323531653338653130303733363764636430336563336439666132626434363463306631363334
+39623332376334383338633132653262653735346563626365613336623435396539383630366332
+31316638393562376131363166633163333332633332393062393962613132366538653865663264
+38313237393436353333323431336361653938343034346164353335366535396265633961333138
+65386137356161643732636531613166633464326163303336303439383435376331373935333563
+64633961623761393131333234656530653737346563643963643833383262383434653266343362
+35623832643032346133346363646136646438663761363330666231316434306232623339656535
+34393337666237656262313439386336336466373466663663616139353463316265396135626366
+62313562306334343831616364633933343463386233323637313832316635346235623830333461
+33663530343966383739643261653736363865323438363430653661653964643339633833386438
+36333331366334366461346636636462343335313234663864613864366134356161396662383632
+36663538373761353937313666363262626435623537646665646364353934373638366261333234
+36353439303663656531666637376364313838386130343966316138356338643135316139363630
+30386635376565363931333331336431303562346431323534643238333337386264616161356163
+35663766306635626235373663643064393233346364666663393236353561653362373361666164
+65653566666234626464356338613834323332383939643935323337376162316163333034643062
+63646237646234636561313038383636373936656164333735323461626233633337623764383830
+66383161346336633962643032376662656566396666343662656337306333313836613335643961
+64323961663032373239636430306430383639306333363938303837386139643230353061623937
+36373733636337616264313432643230303935626666633533666135666538626266626266643864
+376430653461346366626432636336653437
--- a/roles/alpina/templates/apps/nextcloud/.env.notify_push.j2
+++ b/roles/alpina/templates/apps/nextcloud/.env.notify_push.j2
--- a/roles/alpina/templates/services/monitoring/.env.alertmanager.j2
+++ b/roles/alpina/templates/services/monitoring/.env.alertmanager.j2
@@ -1 +0,0 @@
-DISCORD_WEBHOOK={{ alertmanager_discord_webhook }}
--- a/roles/alpina/templates/services/monitoring/Dockerfile
+++ b/roles/alpina/templates/services/monitoring/Dockerfile
@@ -4,6 +4,10 @@ RUN pip install grafanalib

 COPY ./grafana_config/dashboards /dashboards

+# Required for grafanalib to find the shared python files like common.py
+# https://github.com/weaveworks/grafanalib/issues/58
+ENV PYTHONPATH=/dashboards
+
 RUN generate-dashboards /dashboards/*.dashboard.py

 FROM grafana/grafana:latest
--- a/roles/alpina/templates/services/monitoring/alertmanager_config/alertmanager.yml.j2
+++ b/roles/alpina/templates/services/monitoring/alertmanager_config/alertmanager.yml.j2
@@ -1,68 +0,0 @@
-# The root route on which each incoming alert enters.
-route:
-  group_by: ["alertname", "job"]
-  group_wait: 20s
-  group_interval: 5m
-  repeat_interval: 3h
-  receiver: discord_webhook
-
-receivers:
-  - name: "discord_webhook"
-    discord_configs:
-      - webhook_url: "{{ alertmanager_discord_webhook }}"
-{#        - send_resolved: true#}
-{#            username: 'Alertmanager'#}
-{#            webhook_configs:#}
-{#            - send_resolved: true#}
-{#                url: '{{ alertmanager_discord_webhook }}'#}
-{#                username: 'Alertmanager'#}
-{#                icon_url: 'https://prometheus.io/assets/icon.png'#}
-{#                icon_emoji: ':alert:'#}
-{#                send_resolved: true#}
-{#                text: "{{ .CommonAnnotations.summary }}"#}
-{#                title: "{{ .CommonLabels.alertname }}"#}
-{#                color: '{{ if eq .Status "firing" }}#FF0000{{ else }}#00FF00{{ end }}'#}
-{#                footer: '{{ .CommonLabels.monitor }}'#}
-{#                footer_icon: 'https://prometheus.io/assets/icon.png'#}
-{#                actions:#}
-{#                - type: 'button'#}
-{#                    text: 'Open in Grafana'#}
-{#                    url: '{{ .ExternalURL }}'#}
-{#                    style: 'primary'#}
-{#                    send_resolved: true#}
-{#                    confirm:#}
-{#                    title: 'Are you sure?'#}
-{#                    text: 'This will open Grafana in a new tab.'#}
-{#                    ok_text: 'Yes'#}
-{#                    dismiss_text: 'No'#}
-{#                fields:#}
-{#                - title: 'Description'#}
-{#                    value: "{{ .CommonAnnotations.description }}"#}
-{#                    short: false#}
-{#                - title: 'Details'#}
-{#                    value: "{{ .CommonAnnotations.details }}"#}
-{#                    short: false#}
-{#                - title: 'Severity'#}
-{#                    value: '{{ if eq .Labels.severity "critical" }}Critical{{ else if eq .Labels.severity "warning" }}Warning{{ else }}Info{{ end }}'#}
-{#                    short: true#}
-{#                - title: 'Host'#}
-{#                    value: '{{ .CommonLabels.monitor }}'#}
-{#                    short: true#}
-{#                - title: 'Starts At'#}
-{#                    value: '{{ .StartsAt.Format "2006-01-02 15:04:05" }}'#}
-{#                    short: true#}
-{#                - title: 'Ends At'#}
-{#                    value: '{{ .EndsAt.Format "2006-01-02 15:04:05" }}'#}
-{#                    short: true#}
-{#                - title: 'Runbook'#}
-{#                    value: '{{ .CommonAnnotations.runbook_url }}'#}
-{#                    short: true#}
-{#                - title: 'Dashboard'#}
-{#                    value: '{{ .CommonAnnotations.dashboard_url }}'#}
-{#                    short: true#}
-{#                - title: 'Alerting Rule'#}
-{#                    value: '{{ .CommonLabels.alertname }}'#}
-{#                    short: true#}
-{#                - title: 'Alerting Rule Description'#}
-{#                    value: '{{ .CommonLabels.alertname }}'#}
-{#                    short: true#}
--- a/roles/alpina/templates/services/monitoring/docker-compose.yml.j2
+++ b/roles/alpina/templates/services/monitoring/docker-compose.yml.j2
@@ -60,33 +60,17 @@ services:
  prometheus:
    image: prom/prometheus:latest
    container_name: prometheus
-    labels:
-      - {{ helpers.traefik_labels('prom', port='9090') | indent(6) }}
    restart: unless-stopped
    # Needed to make config files readable (not anymore, TODO: remove)
    user: "{{ remote_uid }}"
    command:
      - --config.file=/etc/prometheus/prometheus.yml
      - --storage.tsdb.retention.time=30d
-      - --web.external-url=https://prom.{{ domain }}/
    volumes:
      - ./prometheus_config:/etc/prometheus:ro
      - {{ base_volume_path }}/monitoring/prometheus_configs:/etc/prometheus/extra:ro
      - {{ base_volume_path }}/monitoring/prometheus:/prometheus

-  alertmanager:
-    image: prom/alertmanager:latest
-    container_name: alertmanager
-    labels:
-      - {{ helpers.traefik_labels('alert', port='9093') | indent(6) }}
-    restart: unless-stopped
-    command:
-      - --config.file=/etc/alertmanager/alertmanager.yml
-      - --web.external-url=https://alert.{{ domain }}/
-    volumes:
-      - ./alertmanager_config:/etc/alertmanager:ro
-      - {{ base_volume_path }}/monitoring/alertmanager:/alertmanager
-
  node-exporter:
    image: prom/node-exporter:latest
    container_name: node-exporter
@@ -100,6 +84,11 @@ services:
    image: gcr.io/cadvisor/cadvisor:latest
    container_name: cadvisor
    restart: unless-stopped
+    command:
+      - --docker_only=true
+      - --store_container_labels=false
+      - --whitelisted_container_labels=com.docker.compose.project,com.docker.compose.service
+      - --enable_metrics=cpu,cpuLoad,diskIO,memory,network,oom_event,process
    volumes:
      - /:/rootfs:ro
      - /var/run:/var/run:rw
--- a/roles/alpina/templates/services/monitoring/grafana_config/dashboards/alpina.yaml
+++ b/roles/alpina/templates/services/monitoring/grafana_config/dashboards/alpina.yaml
@@ -3,7 +3,7 @@ apiVersion: 1
 providers:
  - name: "Grafana"
    org_id: 1
-    folder: "Services"
+    folder: "Alpina"
    type: "file"
    options:
      path: "/etc/grafana/provisioning/dashboards"
--- a/roles/alpina/templates/services/monitoring/grafana_config/dashboards/common.py
+++ b/roles/alpina/templates/services/monitoring/grafana_config/dashboards/common.py
@@ -0,0 +1,27 @@
+from grafanalib.core import Template
+
+# TODO: consider default params for common params like line width, show points, tooltip
+
+PrometheusTemplate = Template(
+    name='datasource',
+    type='datasource',
+    label='Prometheus',
+    query='prometheus',
+)
+
+# TODO: this slightly less (clown emoji), normal Target gave me errors in grafana
+class LokiTarget(object):
+    def __init__(self, loki_datasource, expr, legendFormat, refId):
+        self.loki_datasource = loki_datasource
+        self.expr = expr
+        self.legendFormat = legendFormat
+        self.refId = refId
+
+    def to_json_data(self):
+        return {
+            'datasource': self.loki_datasource,
+            'expr': self.expr,
+            'legendFormat': self.legendFormat,
+            'refId': self.refId,
+            'queryType': 'range',
+        }
--- a/roles/alpina/templates/services/monitoring/grafana_config/dashboards/containers.dashboard.py
+++ b/roles/alpina/templates/services/monitoring/grafana_config/dashboards/containers.dashboard.py
@@ -5,28 +5,21 @@ from grafanalib.core import (
 )
 from grafanalib.formatunits import BYTES_IEC, SECONDS, BYTES_SEC_IEC

-prom_datasource='prometheus'
-loki_datasource='loki'
+from common import LokiTarget, PrometheusTemplate

-# TODO: this is (clown emoji), normal Target gave me errors in grafana
-class LokiTarget(object):
-    def to_json_data(self):
-        return {
-            'datasource': loki_datasource,
-            'expr': '{compose_project=~"$compose_project", container_name=~"$container_name"} |= `$logs_query`',
-            'legendFormat': '{{ container_name }}',
-            'refId': 'A',
-            'queryType': 'range',
-        }
+prom_datasource='${datasource}'
+loki_datasource='loki'

 dashboard = Dashboard(
    title='Containers',
    uid='containers',
    description='Data for compose projects from default Prometheus datasource collected by Cadvisor',
    tags=[
-        'example'
+        'linux',
+        'docker',
    ],
    templating=Templating(list=[
+        PrometheusTemplate,
        Template(
            name='compose_project',
            label='Compose Project',
@@ -44,7 +37,6 @@ dashboard = Dashboard(
            includeAll=True,
            multi=True,
            refresh=REFRESH_ON_TIME_RANGE_CHANGE,
-
        ),
        Template(
            name='logs_query',
@@ -56,7 +48,6 @@ dashboard = Dashboard(
    timezone='browser',
    panels=[
        TimeSeries(
-            id=1,
            title='Container Memory Usage',
            unit=BYTES_IEC,
            gridPos=GridPos(h=8, w=12, x=0, y=0),
@@ -76,13 +67,14 @@ dashboard = Dashboard(
            ],
        ),
        TimeSeries(
-            id=2,
            title='Container CPU Usage',
            unit=SECONDS,
            gridPos=GridPos(h=8, w=12, x=12, y=0),
            lineWidth=2,
            fillOpacity=10,
            showPoints='never',
+            tooltipMode='all',
+            tooltipSort='desc',
            targets=[
                Target(
                    datasource=prom_datasource,
@@ -93,7 +85,6 @@ dashboard = Dashboard(
            ],
        ),
        TimeSeries(
-            id=3,
            title='Container Network Traffic',
            unit=BYTES_SEC_IEC,
            gridPos=GridPos(h=8, w=12, x=0, y=8),
@@ -118,7 +109,6 @@ dashboard = Dashboard(
            ],
        ),
        Logs(
-            id=4,
            title='',
            gridPos=GridPos(h=8, w=12, x=12, y=8),
            showLabels=True,
@@ -127,13 +117,12 @@ dashboard = Dashboard(
            prettifyLogMessage=True,
            dedupStrategy='numbers',
            targets=[
-                LokiTarget(),
-                # Target(
-                #     datasource=loki_datasource,
-                #     expr='{compose_project=~"$compose_project", container_name=~"$container_name"} |= `$logs_query`',
-                #     legendFormat='{{ container_name }}',
-                #     refId='A',
-                # ),
+                LokiTarget(
+                    loki_datasource=loki_datasource,
+                    expr='{compose_project=~"$compose_project", container_name=~"$container_name"} |= `$logs_query`',
+                    legendFormat='{{ container_name }}',
+                    refId='A',
+                ),
            ],
        ),
    ],
--- a/roles/alpina/templates/services/monitoring/grafana_config/dashboards/example.dashboard.py
+++ b/roles/alpina/templates/services/monitoring/grafana_config/dashboards/example.dashboard.py
@@ -1,51 +0,0 @@
-from grafanalib.core import (
-    Dashboard, TimeSeries, GaugePanel,
-    Target, GridPos,
-    OPS_FORMAT
-)
-
-dashboard = Dashboard(
-    title="Python generated example dashboard",
-    description="Example dashboard using the Random Walk and default Prometheus datasource",
-    tags=[
-        'example'
-    ],
-    timezone="browser",
-    panels=[
-        TimeSeries(
-            title="Random Walk",
-            dataSource='default',
-            targets=[
-                Target(
-                    datasource='grafana',
-                    expr='example',
-                ),
-            ],
-            gridPos=GridPos(h=8, w=16, x=0, y=0),
-        ),
-        GaugePanel(
-            title="Random Walk",
-            dataSource='default',
-            targets=[
-                Target(
-                    datasource='grafana',
-                    expr='example',
-                ),
-            ],
-            gridPos=GridPos(h=4, w=4, x=17, y=0),
-        ),
-        TimeSeries(
-            title="Prometheus http requests",
-            dataSource='prometheus',
-            targets=[
-                Target(
-                    expr='rate(prometheus_http_requests_total[5m])',
-                    legendFormat="{{ handler }}",
-                    refId='A',
-                ),
-            ],
-            unit=OPS_FORMAT,
-            gridPos=GridPos(h=8, w=16, x=0, y=10),
-        ),
-    ],
-).auto_panel_ids()
--- a/roles/alpina/templates/services/monitoring/grafana_config/dashboards/node.dashboard.py
+++ b/roles/alpina/templates/services/monitoring/grafana_config/dashboards/node.dashboard.py
@@ -0,0 +1,139 @@
+from grafanalib.core import Dashboard, Templating, Template, TimeSeries, PERCENT_UNIT_FORMAT, GridPos, Target
+from grafanalib.formatunits import BYTES_IEC
+
+from common import PrometheusTemplate
+from node_consts import CPU_BASIC_COLORS, MEMORY_BASIC_COLORS
+
+dashboard = Dashboard(
+    title='Node Exporter',
+    uid='node',
+    description='Node Exporter (not quite full)',
+    tags=[
+        'linux',
+    ],
+    timezone='browser',
+    templating=Templating(list=[
+        # Datasource
+        PrometheusTemplate,
+        # Job
+        Template(
+            name='job',
+            label='Job',
+            dataSource='${datasource}',
+            query='label_values(node_uname_info, job)',
+        ),
+        # Instance
+        Template(
+            name='instance',
+            label='Instance',
+            dataSource='${datasource}',
+            query='label_values(node_uname_info{job="$job"}, instance)',
+        ),
+    ]),
+    panels=[
+        # CPU Basic
+        TimeSeries(
+            title='CPU Basic',
+            description='Basic CPU usage info',
+            unit=PERCENT_UNIT_FORMAT,
+            gridPos=GridPos(h=8, w=12, x=0, y=0),
+            lineWidth=1,
+            fillOpacity=30,
+            showPoints='never',
+            stacking={'mode': 'percent', 'group': 'A'},
+            tooltipMode='all',
+            tooltipSort='desc',
+            targets=[
+                Target(
+                    datasource='${datasource}',
+                    expr='sum(irate(node_cpu_seconds_total{instance="$instance",job="$job", mode="system"}[$__rate_interval])) / scalar(count(count(node_cpu_seconds_total{instance="$instance",job="$job"}) by (cpu)))',
+                    legendFormat='Busy System',
+                    refId='A',
+                ),
+                Target(
+                    datasource='${datasource}',
+                    expr='sum(irate(node_cpu_seconds_total{instance="$instance",job="$job", mode="user"}[$__rate_interval])) / scalar(count(count(node_cpu_seconds_total{instance="$instance",job="$job"}) by (cpu)))',
+                    legendFormat='Busy User',
+                    refId='B',
+                ),
+                Target(
+                    datasource='${datasource}',
+                    expr='sum(irate(node_cpu_seconds_total{instance="$instance",job="$job", mode="iowait"}[$__rate_interval])) / scalar(count(count(node_cpu_seconds_total{instance="$instance",job="$job"}) by (cpu)))',
+                    legendFormat='Busy Iowait',
+                    refId='C',
+                ),
+                Target(
+                    datasource='${datasource}',
+                    expr='sum(irate(node_cpu_seconds_total{instance="$instance",job="$job", mode=~".*irq"}[$__rate_interval])) / scalar(count(count(node_cpu_seconds_total{instance="$instance",job="$job"}) by (cpu)))',
+                    legendFormat='Busy IRQs',
+                    refId='D',
+                ),
+                Target(
+                    datasource='${datasource}',
+                    expr='sum(irate(node_cpu_seconds_total{instance="$instance",job="$job",  mode!="idle",mode!="user",mode!="system",mode!="iowait",mode!="irq",mode!="softirq"}[$__rate_interval])) / scalar(count(count(node_cpu_seconds_total{instance="$instance",job="$job"}) by (cpu)))',
+                    legendFormat='Busy Other',
+                    refId='E',
+                ),
+                Target(
+                    datasource='${datasource}',
+                    expr='sum(irate(node_cpu_seconds_total{instance="$instance",job="$job", mode="idle"}[$__rate_interval])) / scalar(count(count(node_cpu_seconds_total{instance="$instance",job="$job"}) by (cpu)))',
+                    legendFormat='Idle',
+                    refId='F',
+                ),
+            ],
+            # Extra JSON for the colors
+            extraJson=CPU_BASIC_COLORS,
+        ),
+        # Memory Basic
+        TimeSeries(
+            title='Memory Basic',
+            description='Basic memory usage',
+            unit=BYTES_IEC,
+            gridPos=GridPos(h=8, w=12, x=12, y=0),
+            lineWidth=1,
+            fillOpacity=30,
+            showPoints='never',
+            stacking={'mode': 'normal', 'group': 'A'},
+            tooltipMode='all',
+            tooltipSort='desc',
+            targets=[
+                Target(
+                    datasource='${datasource}',
+                    expr='node_memory_MemTotal_bytes{instance="$instance",job="$job"}',
+                    format='time_series',
+                    legendFormat='RAM Total',
+                    refId='A',
+                ),
+                Target(
+                    datasource='${datasource}',
+                    expr='node_memory_MemTotal_bytes{instance="$instance",job="$job"} - node_memory_MemFree_bytes{instance="$instance",job="$job"} - (node_memory_Cached_bytes{instance="$instance",job="$job"} + node_memory_Buffers_bytes{instance="$instance",job="$job"} + node_memory_SReclaimable_bytes{instance="$instance",job="$job"})',
+                    format='time_series',
+                    legendFormat='RAM Used',
+                    refId='B',
+                ),
+                Target(
+                    datasource='${datasource}',
+                    expr='node_memory_Cached_bytes{instance="$instance",job="$job"} + node_memory_Buffers_bytes{instance="$instance",job="$job"} + node_memory_SReclaimable_bytes{instance="$instance",job="$job"}',
+                    legendFormat='RAM Cache + Buffer',
+                    refId='C',
+                ),
+                Target(
+                    datasource='${datasource}',
+                    expr='node_memory_MemFree_bytes{instance="$instance",job="$job"}',
+                    legendFormat='RAM Free',
+                    refId='D',
+                ),
+                Target(
+                    datasource='${datasource}',
+                    expr='(node_memory_SwapTotal_bytes{instance="$instance",job="$job"} - node_memory_SwapFree_bytes{instance="$instance",job="$job"})',
+                    legendFormat='SWAP Used',
+                    refId='E',
+                ),
+            ],
+            # Extra JSON for the colors
+            extraJson=MEMORY_BASIC_COLORS,
+        ),
+        # TODO: Network Basic
+        # TODO: Disk Basic
+    ],
+).auto_panel_ids()
--- a/roles/alpina/templates/services/monitoring/grafana_config/dashboards/node_consts.py
+++ b/roles/alpina/templates/services/monitoring/grafana_config/dashboards/node_consts.py
@@ -0,0 +1,487 @@
+# TODO: Question life decisions (I'm not sure if this is good)
+
+CPU_BASIC_COLORS = {
+    "fieldConfig": {
+        "overrides": [
+            {
+                "matcher": {
+                    "id": "byName",
+                    "options": "Busy Iowait"
+                },
+                "properties": [
+                    {
+                        "id": "color",
+                        "value": {
+                            "fixedColor": "#890F02",
+                            "mode": "fixed"
+                        }
+                    }
+                ]
+            },
+            {
+                "matcher": {
+                    "id": "byName",
+                    "options": "Idle"
+                },
+                "properties": [
+                    {
+                        "id": "color",
+                        "value": {
+                            "fixedColor": "#052B51",
+                            "mode": "fixed"
+                        }
+                    }
+                ]
+            },
+            {
+                "matcher": {
+                    "id": "byName",
+                    "options": "Busy Iowait"
+                },
+                "properties": [
+                    {
+                        "id": "color",
+                        "value": {
+                            "fixedColor": "#890F02",
+                            "mode": "fixed"
+                        }
+                    }
+                ]
+            },
+            {
+                "matcher": {
+                    "id": "byName",
+                    "options": "Idle"
+                },
+                "properties": [
+                    {
+                        "id": "color",
+                        "value": {
+                            "fixedColor": "#7EB26D",
+                            "mode": "fixed"
+                        }
+                    }
+                ]
+            },
+            {
+                "matcher": {
+                    "id": "byName",
+                    "options": "Busy System"
+                },
+                "properties": [
+                    {
+                        "id": "color",
+                        "value": {
+                            "fixedColor": "#EAB839",
+                            "mode": "fixed"
+                        }
+                    }
+                ]
+            },
+            {
+                "matcher": {
+                    "id": "byName",
+                    "options": "Busy User"
+                },
+                "properties": [
+                    {
+                        "id": "color",
+                        "value": {
+                            "fixedColor": "#0A437C",
+                            "mode": "fixed"
+                        }
+                    }
+                ]
+            },
+            {
+                "matcher": {
+                    "id": "byName",
+                    "options": "Busy Other"
+                },
+                "properties": [
+                    {
+                        "id": "color",
+                        "value": {
+                            "fixedColor": "#6D1F62",
+                            "mode": "fixed"
+                        }
+                    }
+                ]
+            }
+        ]
+    },
+}
+
+MEMORY_BASIC_COLORS = {
+    "fieldConfig": {
+        "overrides": [
+            {
+                "matcher": {
+                    "id": "byName",
+                    "options": "Apps"
+                },
+                "properties": [
+                    {
+                        "id": "color",
+                        "value": {
+                            "fixedColor": "#629E51",
+                            "mode": "fixed"
+                        }
+                    }
+                ]
+            },
+            {
+                "matcher": {
+                    "id": "byName",
+                    "options": "Buffers"
+                },
+                "properties": [
+                    {
+                        "id": "color",
+                        "value": {
+                            "fixedColor": "#614D93",
+                            "mode": "fixed"
+                        }
+                    }
+                ]
+            },
+            {
+                "matcher": {
+                    "id": "byName",
+                    "options": "Cache"
+                },
+                "properties": [
+                    {
+                        "id": "color",
+                        "value": {
+                            "fixedColor": "#6D1F62",
+                            "mode": "fixed"
+                        }
+                    }
+                ]
+            },
+            {
+                "matcher": {
+                    "id": "byName",
+                    "options": "Cached"
+                },
+                "properties": [
+                    {
+                        "id": "color",
+                        "value": {
+                            "fixedColor": "#511749",
+                            "mode": "fixed"
+                        }
+                    }
+                ]
+            },
+            {
+                "matcher": {
+                    "id": "byName",
+                    "options": "Committed"
+                },
+                "properties": [
+                    {
+                        "id": "color",
+                        "value": {
+                            "fixedColor": "#508642",
+                            "mode": "fixed"
+                        }
+                    }
+                ]
+            },
+            {
+                "matcher": {
+                    "id": "byName",
+                    "options": "Free"
+                },
+                "properties": [
+                    {
+                        "id": "color",
+                        "value": {
+                            "fixedColor": "#0A437C",
+                            "mode": "fixed"
+                        }
+                    }
+                ]
+            },
+            {
+                "matcher": {
+                    "id": "byName",
+                    "options": "Hardware Corrupted - Amount of RAM that the kernel identified as corrupted / not working"
+                },
+                "properties": [
+                    {
+                        "id": "color",
+                        "value": {
+                            "fixedColor": "#CFFAFF",
+                            "mode": "fixed"
+                        }
+                    }
+                ]
+            },
+            {
+                "matcher": {
+                    "id": "byName",
+                    "options": "Inactive"
+                },
+                "properties": [
+                    {
+                        "id": "color",
+                        "value": {
+                            "fixedColor": "#584477",
+                            "mode": "fixed"
+                        }
+                    }
+                ]
+            },
+            {
+                "matcher": {
+                    "id": "byName",
+                    "options": "PageTables"
+                },
+                "properties": [
+                    {
+                        "id": "color",
+                        "value": {
+                            "fixedColor": "#0A50A1",
+                            "mode": "fixed"
+                        }
+                    }
+                ]
+            },
+            {
+                "matcher": {
+                    "id": "byName",
+                    "options": "Page_Tables"
+                },
+                "properties": [
+                    {
+                        "id": "color",
+                        "value": {
+                            "fixedColor": "#0A50A1",
+                            "mode": "fixed"
+                        }
+                    }
+                ]
+            },
+            {
+                "matcher": {
+                    "id": "byName",
+                    "options": "RAM_Free"
+                },
+                "properties": [
+                    {
+                        "id": "color",
+                        "value": {
+                            "fixedColor": "#E0F9D7",
+                            "mode": "fixed"
+                        }
+                    }
+                ]
+            },
+            {
+                "matcher": {
+                    "id": "byName",
+                    "options": "SWAP Used"
+                },
+                "properties": [
+                    {
+                        "id": "color",
+                        "value": {
+                            "fixedColor": "#BF1B00",
+                            "mode": "fixed"
+                        }
+                    }
+                ]
+            },
+            {
+                "matcher": {
+                    "id": "byName",
+                    "options": "Slab"
+                },
+                "properties": [
+                    {
+                        "id": "color",
+                        "value": {
+                            "fixedColor": "#806EB7",
+                            "mode": "fixed"
+                        }
+                    }
+                ]
+            },
+            {
+                "matcher": {
+                    "id": "byName",
+                    "options": "Slab_Cache"
+                },
+                "properties": [
+                    {
+                        "id": "color",
+                        "value": {
+                            "fixedColor": "#E0752D",
+                            "mode": "fixed"
+                        }
+                    }
+                ]
+            },
+            {
+                "matcher": {
+                    "id": "byName",
+                    "options": "Swap"
+                },
+                "properties": [
+                    {
+                        "id": "color",
+                        "value": {
+                            "fixedColor": "#BF1B00",
+                            "mode": "fixed"
+                        }
+                    }
+                ]
+            },
+            {
+                "matcher": {
+                    "id": "byName",
+                    "options": "Swap Used"
+                },
+                "properties": [
+                    {
+                        "id": "color",
+                        "value": {
+                            "fixedColor": "#BF1B00",
+                            "mode": "fixed"
+                        }
+                    }
+                ]
+            },
+            {
+                "matcher": {
+                    "id": "byName",
+                    "options": "Swap_Cache"
+                },
+                "properties": [
+                    {
+                        "id": "color",
+                        "value": {
+                            "fixedColor": "#C15C17",
+                            "mode": "fixed"
+                        }
+                    }
+                ]
+            },
+            {
+                "matcher": {
+                    "id": "byName",
+                    "options": "Swap_Free"
+                },
+                "properties": [
+                    {
+                        "id": "color",
+                        "value": {
+                            "fixedColor": "#2F575E",
+                            "mode": "fixed"
+                        }
+                    }
+                ]
+            },
+            {
+                "matcher": {
+                    "id": "byName",
+                    "options": "Unused"
+                },
+                "properties": [
+                    {
+                        "id": "color",
+                        "value": {
+                            "fixedColor": "#EAB839",
+                            "mode": "fixed"
+                        }
+                    }
+                ]
+            },
+            {
+                "matcher": {
+                    "id": "byName",
+                    "options": "RAM Total"
+                },
+                "properties": [
+                    {
+                        "id": "color",
+                        "value": {
+                            "fixedColor": "#E0F9D7",
+                            "mode": "fixed"
+                        }
+                    },
+                    {
+                        "id": "custom.fillOpacity",
+                        "value": 0
+                    },
+                    {
+                        "id": "custom.stacking",
+                        "value": {
+                            "group": False,
+                            "mode": "normal"
+                        }
+                    }
+                ]
+            },
+            {
+                "matcher": {
+                    "id": "byName",
+                    "options": "RAM Cache + Buffer"
+                },
+                "properties": [
+                    {
+                        "id": "color",
+                        "value": {
+                            "fixedColor": "#052B51",
+                            "mode": "fixed"
+                        }
+                    }
+                ]
+            },
+            {
+                "matcher": {
+                    "id": "byName",
+                    "options": "RAM Free"
+                },
+                "properties": [
+                    {
+                        "id": "color",
+                        "value": {
+                            "fixedColor": "#7EB26D",
+                            "mode": "fixed"
+                        }
+                    }
+                ]
+            },
+            {
+                "matcher": {
+                    "id": "byName",
+                    "options": "Available"
+                },
+                "properties": [
+                    {
+                        "id": "color",
+                        "value": {
+                            "fixedColor": "#DEDAF7",
+                            "mode": "fixed"
+                        }
+                    },
+                    {
+                        "id": "custom.fillOpacity",
+                        "value": 0
+                    },
+                    {
+                        "id": "custom.stacking",
+                        "value": {
+                            "group": False,
+                            "mode": "normal"
+                        }
+                    }
+                ]
+            }
+        ]
+    }
+}
--- a/roles/alpina/templates/services/monitoring/grafana_config/datasources/alpina.yaml.j2
+++ b/roles/alpina/templates/services/monitoring/grafana_config/datasources/alpina.yaml.j2
@@ -15,18 +15,6 @@ datasources:
    url: http://prometheus:9090
    editable: false

-  - name: Alertmanager
-    type: alertmanager
-    access: proxy
-    uid: alertmanager
-    url: http://alertmanager:9093
-    jsonData:
-      # Valid options for implementation include mimir, cortex and prometheus
-      implementation: prometheus
-      # Whether Grafana should send alert instances to this Alertmanager
-      handleGrafanaManagedAlerts: true
-    editable: false
-
  - name: InfluxDB
    type: influxdb
    access: proxy
--- a/roles/alpina/templates/services/monitoring/loki_config/loki-config.yaml.j2
+++ b/roles/alpina/templates/services/monitoring/loki_config/loki-config.yaml.j2
@@ -17,13 +17,6 @@ common:

 schema_config:
  configs:
-    - from: 2020-10-24
-      store: boltdb-shipper
-      object_store: filesystem
-      schema: v12
-      index:
-        prefix: index_
-        period: 24h
    - from: 2024-10-18
      index:
        period: 24h
@@ -33,5 +26,5 @@ schema_config:
      store: tsdb

 # TODO: Figure this out
-ruler:
-  alertmanager_url: http://localhost:9093
+# ruler:
+#   alertmanager_url: http://localhost:9093
--- a/roles/alpina/templates/services/monitoring/prometheus_config/container.alerts.yml
+++ b/roles/alpina/templates/services/monitoring/prometheus_config/container.alerts.yml
@@ -1,23 +0,0 @@
-groups:
-  - name: qbit-low-traffic
-    interval: 1m
-    rules:
-      - alert: QbitLowTraffic
-        expr: |
-          rate(container_network_transmit_bytes_total{name=~"gluetun"}[1m]) < 1024
-        for: 2m
-        labels:
-          severity: warning
-        annotations:
-          title: 'Low traffic on qBit'
-          description: |
-            The traffic on qBittorrent is lower than 1KiB/s for 2 minutes.
-
-            Last value was x bytes/s.
-
-            [Grafana Dashboard](https://grafana.{{ domain }}/d/containers?orgId=1)
-            [View in Grafana](https://grafana.{{ domain }}/d/containers?orgId=1&viewPanel=3)
-
-          __dashboard__uid: 'containers'
-          __orgId__: 1
-          __panelId__: 3
--- a/roles/alpina/templates/services/monitoring/prometheus_config/demo.alerts.yml.j2
+++ b/roles/alpina/templates/services/monitoring/prometheus_config/demo.alerts.yml.j2
@@ -1,20 +0,0 @@
-groups:
-  - name: demo-service-alerts
-    rules:
-      - alert: DemoServiceHighErrorRate
-        expr: |
-          (
-            sum without(status, instance) (
-              rate(demo_api_request_duration_seconds_count{status=~"5..",job="demo"}[1m])
-            )
-          /
-            sum without(status, instance) (
-              rate(demo_api_request_duration_seconds_count{job="demo"}[1m])
-            ) * 100 > 0.5
-          )
-        for: 1m
-        labels:
-          severity: critical
-        annotations:
-          title: 'High 5xx rate for {{'{{ $labels.method }}'}} on {{'{{ $labels.path }}'}}'
-          description: 'The 5xx error rate for path {{'{{ $labels.path }}'}} with method {{'{{ $labels.method }}'}} in {{'{{ $labels.job }}'}} is {{'{{ printf "%.2f" $value }}'}}%.'
--- a/roles/alpina/templates/services/monitoring/prometheus_config/prometheus.yml.j2
+++ b/roles/alpina/templates/services/monitoring/prometheus_config/prometheus.yml.j2
@@ -5,11 +5,6 @@ global:
  external_labels:
    monitor: "{{ ansible_host }}"

-alerting:
-  alertmanagers:
-    - static_configs:
-        - targets: ["alertmanager:9093"]
-
 scrape_configs:
  - job_name: "prometheus"
    static_configs:
@@ -35,15 +30,7 @@ scrape_configs:
    static_configs:
      - targets: ["promtail:9080"]

-  - job_name: 'demo'
-    static_configs:
-      - targets:
-          - 'demo.promlabs.com:10000'
-          - 'demo.promlabs.com:10001'
-          - 'demo.promlabs.com:10002'
-
 rule_files:
-  - "/etc/prometheus/container.alerts.yml"
  - "/etc/prometheus/extra/rules/*.yml"
  - "/etc/prometheus/extra/rules/*.json"

--- a/services.yml
+++ b/services.yml
@@ -5,10 +5,11 @@
  post_tasks:
    - name: Docker prune objects
      docker_prune:
-        containers: yes
-        images: yes
+        containers: true
+        # Keep images for building grafana
+        images: true
        images_filters:
-          dangling: false
+          until: "720h"
        networks: true
        volumes: true
-        builder_cache: true
+        builder_cache: false
Author	SHA1	Message	Date
Yuri Tatishchev	3006e3e424	monitoring: container, node dashboard improvements; separate common.py logic	2024-10-30 18:24:34 -07:00
Yuri Tatishchev	0e43a68754	monitoring: add grafanalib, containers dashboard	2024-10-30 18:24:28 -07:00
Yuri Tatishchev	fc6e485a61	refactor: separate templating for j2 and normal files	2024-10-30 18:11:26 -07:00
Yuri Tatishchev	dd0330c85a	monitoring: loki, cadvisor config optimizations	2024-10-23 15:35:54 -07:00
Yuri Tatishchev	40fbdc414e	monitoring: update loki schema	2024-10-22 23:16:41 -07:00
				`@@ -1 +0,0 @@`
				`DISCORD_WEBHOOK={{ alertmanager_discord_webhook }}`