(WIP) monitoring: attempt at container alerts

.idea/alpina.iml

@@ -4,7 +4,7 @@
     <content url="file://$MODULE_DIR$">
       <excludeFolder url="file://$MODULE_DIR$/venv" />
     </content>
-    <orderEntry type="inheritedJdk" />
+    <orderEntry type="jdk" jdkName="Poetry (alpina) (4)" jdkType="Python SDK" />
     <orderEntry type="sourceFolder" forTests="false" />
   </component>
   <component name="PyDocumentationSettings">

.idea/jsonSchemas.xml

@@ -39,22 +39,6 @@
             </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>

.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)" project-jdk-type="Python SDK" />
+  <component name="ProjectRootManager" version="2" project-jdk-name="Poetry (alpina) (4)" project-jdk-type="Python SDK" />
 </project>

README.md

@@ -8,22 +8,6 @@ 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 

group_vars/alpina/vars.yml

@@ -24,6 +24,8 @@ 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 }}"

group_vars/alpina/vault.yml

@@ -1,88 +1,96 @@
 $ANSIBLE_VAULT;1.1;AES256
-66313038633762313266633234323232303734353935383962356166316262303532666530653432
+32653863663065353431636364373163613536643238613961666561653663633530646165643766
-6639323962333630623362663535306136633937316666610a393739383862626234636235626563
+3833323937353331313136633965393061616135366534660a333037383066303431623830313464
-39333239663065303536633839306530626132633136383236643430653037353032653938386565
+65346431633238666534373033663138353438313762326361666233353866663534363536643034
-6164623333306630620a663539643737393637653466643162383930376636653366333062346432
+3636323439316261630a623262336331663431633266336235653034323234383566323963623365
-35633666303436313139626337316337636335393636343137616661363030373264386534303762
+32626363626164373536663464643632393761346137623866633237643038306265636362626561
-32646336313635386439623932636537613365633561306165396535393862363764326436666337
+61313634353634373530383061393364613461303132326335316566326436633635633131643433
-65393363343230656635666666613139336432613563383730363030643630643861393035393033
+31376539396639326464333233643933373737313064363262323639363964643862633035396161
-30383866366563663337333330333132646631613764303261616336326439386133386431666233
+35643037636535623966626131393538643432396536643365383736636262356135373434376433
-61663866653839623634313836306362383066653135333535643630343939323235613963393837
+32316361343330303431376234323632323932376635343964383733633761326639393966383039
-38623439353038643130646664373063656130333533633936643066363030313534373038646166
+35646131343034663962363335373661323065663764396631343461383661663738386163323633
-37633739353562303631663565626636393136636332313932396237393866343762386565626164
+36303464646532633235663662666663343238633465663334326463383133643239666634653739
-63393932656533366137353864343238646234346461323162653465326334333136303333313362
+35396130393961303230396236303766336666643930626161333338326137663235323066663032
-33646362613436643733643763623337386661346531666136623635303166633838353132386264
+33376564373563323635356233616264313663373534333636643236393866613062656338353864
-66386136616531633138316631663437306130626665626333386137356431326334323361383737
+66386132663362363832366661646462316139353132626662663934336530386534376538633235
-37393465626264386336373936323564333031356562393239623636616338626563323065316634
+62653131653835323261373435373631396466353738306362616266616532313435323633613933
-31313461343030323637363432666130306338353934633164316332613065303237326234666264
+61646132346536323632643865326234356535346566346532383162393265613931343962303463
-35383666636236393030353732663866363738613463633832313336356637613838336263343330
+31636334343736666434353835633734396465653862613234386431306463326134613931646232
-34343061386539633635323565613061373930326665636361316636363232626239343233376238
+32353535663133623434643866336165616232613662336533383432633338373763643337616637
-36653834646132333938373637346633613365626636303836646435306166316138666139626134
+38323237646461376433316164646366383438316639633162303739383263656265633364303565
-36356663333237646234393437396334663366396630393562303536323866376432643539646264
+36643339356136653332666230633939636264306431636562323864373037623138363739616561
-36343433633563396363623435323466386337313762643136316665663936366232366233666165
+37613364653737353638646564323439646138646536636564303866636233616264383466656439
-31656531643230363231313166343461373462663536333165633432326634623435623762616665
+33646232653061616437656162353036313834616162313936353533393833313432656534343363
-63343534396232303266303062666563636432323739656434653138366437303030393535343930
+35636638326236646163323463356634326534623165306461316530353936646162323435633862
-38326562336338663565343762313132303138383461353034326638376230623232313365363038
+64396464303363323837316162353734626663643962303534336637336632333463393734383532
-38663830336131306336336162383335616132666239343931643838376165643063383034363761
+66616534666466393333386337363238383432643764373864613461363766333932333862363332
-62633034396163306539383039316164333664316566376436653432383837363437653766643933
+61313364613031376334326635636432346532613462613265643462636436663963323862353733
-61333830653263306366306234653166636634333162386362333734626338333766363939643335
+38396261613332396633666130653262313234633132353264363266336231373535306532383661
-66613466626130363233393738663763636665656632336634333963636436643430613430316439
+65323530653531646339626537653433303332656535346639393466353133363833326236656231
-66333964636233613233393434633938333964376334346637303135346334653536393635393563
+33336265373463396135653730616266346331376461346433343464326238323034653330393732
-34316230353838626566326436323836373630356138323632383635663432336563316464633637
+36643432316662333633333036633761653031393433333338663633386264656535623534653463
-62316361323138653234616634633633326231626462313964326339353839663738656132393731
+36363565303333356361616539376532353066336137336134656465383364636361656664356439
-36353030633637373633376134373739646639623264346362363030383064323336346538356264
+65326334643631663665376530646433323439653864623964323363396561313663636538356536
-32373739616166633462623134353538363036323833393837393335396131316233373335356531
+63626336303862333364363166353437353163656238303765636662636137383337623563666264
-36613262303639633031306238376165366432653664613233663562326336303433646664616337
+66326633343230386638616438393436633431343264343231386563613935626430306337343533
-66356334633863383631376365383634326430623165383337336166326662623738383966663436
+66656366333332326131343661356236396430303832303834653530623639353036663436373862
-34343136326332626536653963656534336366376366326636353364333437383435633335313535
+61336437386338343965653563646664643438353232306231316564616462643236646239333062
-65343831333562616362373832666136633764303731323632333032376634636663626364373765
+38643461346639623964626438396631396139383332666130316635656530653136333662353566
-61306339306439666362656361653837313038616538646637383734386435646539303565366332
+36313261646330373963663032316662383137366436636534383366636362366435393036373264
-63366630303139623464323539303365393666333230646138393131336131626635333466333633
+34646537666462363531343335336638343038333633663862666163306662643634326533316561
-62393261313539363836643666343735653466616433396333326439663931663666333164643465
+61613235366233636530663462353066646530386265623534663336376364323237343936646134
-31393930343733313062643366643661313532636432616338666361623964303961363730643531
+31616563653864383565306439613932396562613835613562326264326535636630646666366335
-38613934646238666663336233356631323738663962336634623436613564616535623161303664
+36653631353961353933386236636534393636356334633336313333383238353838336335646630
-65366464636235356435333666643036316639646437376463366562346231386436663736633364
+63633365666530623562323634303935326362643762616532303531303139333565643835396163
-30316138393062363162353962313366323936323433396332383337326530326538653764336536
+36353130656365326435343130613234336637346461313639653133623933376163393935366266
-61646232313633626632643530636565376435343562663338613336353533666165613665323564
+66653337353732363038663164363663623266356366663637343466393836353965343730666362
-36396339383637643532633630613135653262306662383737353939636533646531656639643733
+38663636336265383331666666616535366334616431306164303738306436333364653765356662
-39353464336161623266646533633837373334336535663532646439316533393436333430653133
+37316433323563323431623164386337343563663538333435616333343433396236356363333262
-32353066386562653563313733343233303534396663656233656462636661356331346134306332
+61396664326234343136666331356465333233663135613839616334623033316362336162613731
-30633862643232333362353238633632336135623861383931653334333161623764333865613135
+38646530326538643337323838326563303130643934623939346635343331356531373235663937
-30633830636136306335646338613261616265653166393939306365306261313933363639363333
+62396530383365666439373632613633633233376139616138323033613135383330333132643839
-39303063633033336637306233326232373665623430386332333765326539653035336565313330
+65363833616337656662653462323436303531653635663739633366616532333761323238353764
-30343836336165313932626633326565356664393162363561326466623133313663616161383166
+39373836303735393165393435323139346661346135636138613731373165386533386333393364
-66646230383033336630363536623734653764333665383261663362633339356462626161373061
+32336265386334386338653734353565343733393931373436336233333031356531313739636666
-30316138653563616563303762663166366230313062626631623964323434663561303939333934
+61376234393631343236643137616631373564376132623534333939346162353662306661393438
-63313037386264653866373535643233666339663433616438363237613733633633363236396438
+32326566373934653463653737383131386431363664333535626361646637613632383132623533
-64353664333634396531346465623064626338613136666161666663323762333135316265326662
+32343465366562363765353366333330633631353936613930376631336538306230626632303966
-66376237316563333834383431323033366135383937383465666666613835303938393936303764
+31343936386535663165663066663862656439306363326337313561396132316338363930323632
-38636239303535326166363261386339356330366533323938333066386236396665356362383134
+33313061623534373338623931663934396339633564353533626639373837323832366132343538
-37323066666233633035666262366133396134633165633633386233633166313465623335626536
+63373862663137306665383732303863343564343830636233613139666631626532373938386663
-37333931666135333638306665633539613362646633623831386538646262383565396633323037
+35646331646462356639383964373732393866653963643832633661323430323430613330633364
-39306561666238643438616238356632633165343732663261663836623333356165343663613239
+35343262366362646165383032333236623863656264353964623136643631326135623538306261
-35303436633666376637366233323662613933313234646265633738663561386664333462656238
+37393839343331653665356131343063316232303963636462653238333466636334616435666463
-39393662633037663764663639396132636337323636633631353565616666663463393663373465
+65636662383930353238623130363834616137643830633261646338363435343839633565303562
-35373731643164373065623138346432396661613065303230386634393864336333356134366464
+37623231396163346464303464333962336261353634396236613132306464643764356265656137
-30653438653933323839326539613038326461623735393361346230333835326631356134376366
+32373263613964396430646332666235303634373431643939623963633334326135626565656662
-32626230643163393932356231623365653832333237353237303438616439323463376539333236
+30646166303732643562653166633232666635343665616665653566316632303861613861313333
-64663166306536353262613731373136633432376564636331396435313735616638306363643762
+38393636663137333231613239353661656338333536656563616237343234623031363535666637
-61623038633564356165353562336462396138313534393636653233373732343437383632313266
+61343662663965663161666436366630366432363733663537613064386130326466343366383232
-66343434633431383162633135313639656666386139306165343536333265623633373062363038
+32363662343561666665323565356163383932336361656132373263363239636666613461366339
-36326236366130303034633339626235353661316237613232333432336264373131376364323334
+31323264393866386239353333386161643330343262366666323533303737373163313262313766
-34343039623165663861363463323466333863333764663439366233636132656238363961623463
+61303638366263346232353134333431613730386431623235323537323962666133613939353762
-66363336633061363237623238383338323430616261303430313535396666636165356166363166
+63326361633630323937353163383930626336663365626532613031623532393932316138353335
-38376363396636643239636238666532396537623737623538383130623239666630376661303536
+32363262393764663135393466616639373965313238323935383531633434633038663437646662
-36613334663164303361366165653964323132393135376666646663323538653066326461333932
+31633265373937316533373332316132363061386133356231623230393739326464333761336338
-65663730626164636334626264393539623637313661383963663733383636363663386665386332
+38626234646164616265633061346239363164376532383834356435346232653065326362343363
-65363735646633613762343230653731646261653937633032383332653264643532386263333865
+39613532356166633133626563643238373661323937353635343464666339323561326136623366
-31373435313230346336616230306336643763613439666365303363613865313331366537316431
+62633637656462376136633963653263346565366563646533373431613761616231653739613537
-35613439643036663136303164626134646332333465383264353036353564333035633262303166
+32343332356435393635363837396463613165626337346235303363613764306132343539333836
-34393138343463646532323136623562386237376333636531626561393633376238393138303239
+63386633626332396339383165303166653334663239313066666632356165643161356262346230
-66386365303166383736323435336432383634616239353565623962333939373266376632333734
+32636365636364663466343939663538386439343336303537636230306263643534653339313538
-62356230323531316564316439376137346431636462303062333933303965616232313739643665
+31373165363962373337636138336561336638633762373363646139366339323031313664306534
-33653962333037306333363534313933666163393465306534653837303164346333333665353032
+30623130663037323839666166323162393065643535663866383062356330633137343239316436
-66336333656335353239356232383561663831323763376663666365383834353166373461383631
+32303132393739653363376138633430313832383165663366626436653033663637616664346632
-38666665343036353437323961636534303537386266303133356465633262393132333134663034
+63633439663734393236343265323533633639316133323336373064633138363266316135363335
-66303939393562633363373131303730663634303162396565656266613163646331333230306234
+31336637666331333139306537333565333064666433653730633430336261656665613263663937
-37366137323230613331623239383765383230633134306466633839363765633961626265356365
+64313230656333373838346439623061393164393239393934306336373063303934663334353532
-623166373834383030373932623664303765
+31313637623466313835313566616161376230343532653561343364383133653736646338303631
+36356164303630303433356332343630616465383831623036383833393330663566616333653161
+63393361643266323336393962663263323338633634633033393762656139393665353630633637
+39386462303731396261613961613238616237373332656361303139633763303837653765623464
+64333565666532653864383861333433353731343161613231383836353966353636373762306132
+35333536373939656638356333383135313231306433656536383933623634653263353434393238
+32323037666135316337633465666335376332326633346665643333656139386465353134356636
+36333434303538326135346539313734393939353163316666366438613133333464623732666438
+663934323030303937623038343662646163

roles/alpina/templates/services/monitoring/.env.alertmanager.j2

@@ -0,0 +1 @@
+DISCORD_WEBHOOK={{ alertmanager_discord_webhook }}

roles/alpina/templates/services/monitoring/Dockerfile

@@ -4,10 +4,6 @@ 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

roles/alpina/templates/services/monitoring/alertmanager_config/alertmanager.yml.j2

@@ -0,0 +1,68 @@
+# 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#}

roles/alpina/templates/services/monitoring/docker-compose.yml.j2

@@ -60,6 +60,8 @@ 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 }}"
@@ -72,6 +74,19 @@ services:
       - {{ 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
@@ -85,11 +100,6 @@ 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

roles/alpina/templates/services/monitoring/grafana_config/dashboards/alpina.yaml

@@ -3,7 +3,7 @@ apiVersion: 1
 providers:
   - name: "Grafana"
     org_id: 1
-    folder: "Alpina"
+    folder: "Services"
     type: "file"
     options:
       path: "/etc/grafana/provisioning/dashboards"

roles/alpina/templates/services/monitoring/grafana_config/dashboards/common.py

@@ -1,27 +0,0 @@
-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',
-        }

roles/alpina/templates/services/monitoring/grafana_config/dashboards/containers.dashboard.py

@@ -5,21 +5,28 @@ from grafanalib.core import (
 )
 from grafanalib.formatunits import BYTES_IEC, SECONDS, BYTES_SEC_IEC
 
-from common import LokiTarget, PrometheusTemplate
+prom_datasource='prometheus'
-
-prom_datasource='${datasource}'
 loki_datasource='loki'
 
+# 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',
+        }
+
 dashboard = Dashboard(
     title='Containers',
     uid='containers',
     description='Data for compose projects from default Prometheus datasource collected by Cadvisor',
     tags=[
-        'linux',
+        'example'
-        'docker',
     ],
     templating=Templating(list=[
-        PrometheusTemplate,
         Template(
             name='compose_project',
             label='Compose Project',
@@ -37,6 +44,7 @@ dashboard = Dashboard(
             includeAll=True,
             multi=True,
             refresh=REFRESH_ON_TIME_RANGE_CHANGE,
+
         ),
         Template(
             name='logs_query',
@@ -48,6 +56,7 @@ 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),
@@ -67,14 +76,13 @@ 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,
@@ -85,6 +93,7 @@ dashboard = Dashboard(
             ],
         ),
         TimeSeries(
+            id=3,
             title='Container Network Traffic',
             unit=BYTES_SEC_IEC,
             gridPos=GridPos(h=8, w=12, x=0, y=8),
@@ -109,6 +118,7 @@ dashboard = Dashboard(
             ],
         ),
         Logs(
+            id=4,
             title='',
             gridPos=GridPos(h=8, w=12, x=12, y=8),
             showLabels=True,
@@ -117,12 +127,13 @@ dashboard = Dashboard(
             prettifyLogMessage=True,
             dedupStrategy='numbers',
             targets=[
-                LokiTarget(
+                LokiTarget(),
-                    loki_datasource=loki_datasource,
+                # Target(
-                    expr='{compose_project=~"$compose_project", container_name=~"$container_name"} |= `$logs_query`',
+                #     datasource=loki_datasource,
-                    legendFormat='{{ container_name }}',
+                #     expr='{compose_project=~"$compose_project", container_name=~"$container_name"} |= `$logs_query`',
-                    refId='A',
+                #     legendFormat='{{ container_name }}',
-                ),
+                #     refId='A',
+                # ),
             ],
         ),
     ],

roles/alpina/templates/services/monitoring/grafana_config/dashboards/node.dashboard.py

@@ -1,139 +0,0 @@
-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()

roles/alpina/templates/services/monitoring/grafana_config/dashboards/node_consts.py

@@ -1,487 +0,0 @@
-# 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"
-                        }
-                    }
-                ]
-            }
-        ]
-    }
-}

roles/alpina/templates/services/monitoring/grafana_config/datasources/alpina.yaml.j2

@@ -15,6 +15,18 @@ 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

roles/alpina/templates/services/monitoring/loki_config/loki-config.yaml.j2

@@ -17,6 +17,13 @@ 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
@@ -26,5 +33,5 @@ schema_config:
       store: tsdb
 
 # TODO: Figure this out
-# ruler:
+ruler:
-#   alertmanager_url: http://localhost:9093
+  alertmanager_url: http://localhost:9093

roles/alpina/templates/services/monitoring/prometheus_config/container.alerts.yml

@@ -0,0 +1,23 @@
+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

roles/alpina/templates/services/monitoring/prometheus_config/demo.alerts.yml.j2

@@ -0,0 +1,20 @@
+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 }}'}}%.'

roles/alpina/templates/services/monitoring/prometheus_config/prometheus.yml.j2

@@ -5,6 +5,11 @@ global:
   external_labels:
     monitor: "{{ ansible_host }}"
 
+alerting:
+  alertmanagers:
+    - static_configs:
+        - targets: ["alertmanager:9093"]
+
 scrape_configs:
   - job_name: "prometheus"
     static_configs:
@@ -38,6 +43,7 @@ scrape_configs:
           - 'demo.promlabs.com:10002'
 
 rule_files:
+  - "/etc/prometheus/container.alerts.yml"
   - "/etc/prometheus/extra/rules/*.yml"
   - "/etc/prometheus/extra/rules/*.json"
 

services.yml

@@ -5,11 +5,10 @@
   post_tasks:
     - name: Docker prune objects
       docker_prune:
-        containers: true
+        containers: yes
-        # Keep images for building grafana
+        images: yes
-        images: true
         images_filters:
-          until: "720h"
+          dangling: false
         networks: true
         volumes: true
-        builder_cache: false
+        builder_cache: true