viktor/infra
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
infra/stacks
History
Viktor Barzin fffc2ed0ab fix node OOM: reduce memory overcommit ratio and add kubelet eviction thresholds 
LimitRange defaults had a 4-8x limit/request ratio causing the scheduler
to overpack nodes. When pods burst, nodes OOM-thrashed and became
unresponsive (k8s-node3 and k8s-node4 both went down today).

Changes:
- Increase default memory requests across all tiers (ratio now 2x):
  - core/cluster: 64Mi → 256Mi request (512Mi limit)
  - gpu: 256Mi → 1Gi request (2Gi limit)
  - edge/aux/fallback: 64Mi → 128Mi request (256Mi limit)
- Add kubelet memory reservation and eviction thresholds:
  - systemReserved: 512Mi, kubeReserved: 512Mi
  - evictionHard: 500Mi (was 100Mi), evictionSoft: 1Gi (was unset)
  - Applied to all nodes and future node template
2026-03-08 10:33:38 +00:00
..
actualbudget [ci skip] add Homepage gethomepage.dev annotations to all services 2026-03-07 20:39:54 +00:00
affine [ci skip] add Homepage gethomepage.dev annotations to all services 2026-03-07 20:39:54 +00:00
audiobookshelf [ci skip] add widgets for audiobookshelf, changedetection, prowlarr, headscale 2026-03-07 20:39:55 +00:00
blog [ci skip] add Homepage gethomepage.dev annotations to all services 2026-03-07 20:39:54 +00:00
calibre [ci skip] fix widget URLs: use correct k8s service ports 2026-03-07 20:39:56 +00:00
changedetection [ci skip] fix invalid Homepage dashboard icons for 9 services 2026-03-07 21:14:17 +00:00
city-guesser [ci skip] fix invalid Homepage dashboard icons for 9 services 2026-03-07 21:14:17 +00:00
coturn [ci skip] phase 5+6: update CI pipelines for SOPS, add sensitive=true to secret vars 2026-03-07 14:30:36 +00:00
cyberchef [ci skip] add Homepage gethomepage.dev annotations to all services 2026-03-07 20:39:54 +00:00
dashy [ci skip] phase 5+6: update CI pipelines for SOPS, add sensitive=true to secret vars 2026-03-07 14:30:36 +00:00
dawarich [ci skip] add Homepage gethomepage.dev annotations to all services 2026-03-07 20:39:54 +00:00
descheduler [ci skip] phase 5+6: update CI pipelines for SOPS, add sensitive=true to secret vars 2026-03-07 14:30:36 +00:00
diun [ci skip] phase 5+6: update CI pipelines for SOPS, add sensitive=true to secret vars 2026-03-07 14:30:36 +00:00
ebook2audiobook [ci skip] add Homepage gethomepage.dev annotations to all services 2026-03-07 20:39:54 +00:00
echo [ci skip] phase 5+6: update CI pipelines for SOPS, add sensitive=true to secret vars 2026-03-07 14:30:36 +00:00
excalidraw [ci skip] add Homepage gethomepage.dev annotations to all services 2026-03-07 20:39:54 +00:00
f1-stream [ci skip] fix invalid Homepage dashboard icons for 9 services 2026-03-07 21:14:17 +00:00
forgejo [ci skip] add Forgejo task pipeline for OpenClaw AI agent 2026-03-07 21:11:07 +00:00
freedify [ci skip] add Homepage gethomepage.dev annotations to all services 2026-03-07 20:39:54 +00:00
freshrss [ci skip] add widgets for qbittorrent, navidrome, nextcloud, freshrss, linkwarden, uptime-kuma 2026-03-07 20:39:55 +00:00
frigate [ci skip] fix broken Homepage widgets + add service API tokens to SOPS 2026-03-07 20:39:55 +00:00
grampsweb [ci skip] fix invalid Homepage dashboard icons for 9 services 2026-03-07 21:14:17 +00:00
hackmd [ci skip] add Homepage gethomepage.dev annotations to all services 2026-03-07 20:39:54 +00:00
health [ci skip] add Homepage gethomepage.dev annotations to all services 2026-03-07 20:39:54 +00:00
homepage add nginx caching proxy for Homepage widget API requests 2026-03-07 21:11:07 +00:00
immich [ci skip] fix widget issues: ports, Immich v2 API, Nextcloud trusted domains 2026-03-07 20:39:56 +00:00
infra fix node OOM: reduce memory overcommit ratio and add kubelet eviction thresholds 2026-03-08 10:33:38 +00:00
isponsorblocktv [ci skip] phase 5+6: update CI pipelines for SOPS, add sensitive=true to secret vars 2026-03-07 14:30:36 +00:00
jsoncrack [ci skip] add Homepage gethomepage.dev annotations to all services 2026-03-07 20:39:54 +00:00
k8s-dashboard [ci skip] add Homepage gethomepage.dev annotations to all services 2026-03-07 20:39:54 +00:00
kms [ci skip] add Homepage gethomepage.dev annotations to all services 2026-03-07 20:39:54 +00:00
linkwarden [ci skip] fix widget URLs: use correct k8s service ports 2026-03-07 20:39:56 +00:00
matrix [ci skip] add Homepage gethomepage.dev annotations to all services 2026-03-07 20:39:54 +00:00
meshcentral [ci skip] add Homepage gethomepage.dev annotations to all services 2026-03-07 20:39:54 +00:00
n8n [ci skip] add Forgejo task pipeline for OpenClaw AI agent 2026-03-07 21:11:07 +00:00
navidrome [ci skip] fix widget URLs: use correct k8s service ports 2026-03-07 20:39:56 +00:00
netbox [ci skip] add Homepage gethomepage.dev annotations to all services 2026-03-07 20:39:54 +00:00
networking-toolbox [ci skip] fix Homepage icons for Tandoor, Listenarr, Networking Toolbox, Goldilocks 2026-03-07 21:29:51 +00:00
nextcloud [ci skip] fix widget issues: ports, Immich v2 API, Nextcloud trusted domains 2026-03-07 20:39:56 +00:00
ntfy [ci skip] add Homepage gethomepage.dev annotations to all services 2026-03-07 20:39:54 +00:00
ollama [ci skip] add Homepage gethomepage.dev annotations to all services 2026-03-07 20:39:54 +00:00
onlyoffice [ci skip] add Homepage gethomepage.dev annotations to all services 2026-03-07 20:39:54 +00:00
openclaw [ci skip] add Forgejo task pipeline for OpenClaw AI agent 2026-03-07 21:11:07 +00:00
osm_routing [ci skip] phase 5+6: update CI pipelines for SOPS, add sensitive=true to secret vars 2026-03-07 14:30:36 +00:00
owntracks [ci skip] add Homepage gethomepage.dev annotations to all services 2026-03-07 20:39:54 +00:00
paperless-ngx [ci skip] add widgets for audiobookshelf, changedetection, prowlarr, headscale 2026-03-07 20:39:55 +00:00
platform fix node OOM: reduce memory overcommit ratio and add kubelet eviction thresholds 2026-03-08 10:33:38 +00:00
plotting-book add iSCSI persistent volume for plotting-book SQLite database 2026-03-07 21:57:22 +00:00
poison-fountain [ci skip] fix invalid Homepage dashboard icons for 9 services 2026-03-07 21:14:17 +00:00
privatebin [ci skip] add Homepage gethomepage.dev annotations to all services 2026-03-07 20:39:54 +00:00
real-estate-crawler [ci skip] add Homepage gethomepage.dev annotations to all services 2026-03-07 20:39:54 +00:00
reloader [ci skip] phase 5+6: update CI pipelines for SOPS, add sensitive=true to secret vars 2026-03-07 14:30:36 +00:00
resume [ci skip] fix invalid Homepage dashboard icons for 9 services 2026-03-07 21:14:17 +00:00
rybbit [ci skip] add Homepage gethomepage.dev annotations to all services 2026-03-07 20:39:54 +00:00
send [ci skip] add liveness probe to Send deployment 2026-03-07 20:39:57 +00:00
servarr [ci skip] fix Homepage icons for Tandoor, Listenarr, Networking Toolbox, Goldilocks 2026-03-07 21:29:51 +00:00
shadowsocks [ci skip] phase 5+6: update CI pipelines for SOPS, add sensitive=true to secret vars 2026-03-07 14:30:36 +00:00
speedtest [ci skip] fix broken Homepage widgets + add service API tokens to SOPS 2026-03-07 20:39:55 +00:00
stirling-pdf [ci skip] add Homepage gethomepage.dev annotations to all services 2026-03-07 20:39:54 +00:00
tandoor [ci skip] fix Homepage icons for Tandoor, Listenarr, Networking Toolbox, Goldilocks 2026-03-07 21:29:51 +00:00
tor-proxy [ci skip] phase 5+6: update CI pipelines for SOPS, add sensitive=true to secret vars 2026-03-07 14:30:36 +00:00
trading-bot [ci skip] fix invalid Homepage dashboard icons for 9 services 2026-03-07 21:14:17 +00:00
travel_blog [ci skip] add Homepage gethomepage.dev annotations to all services 2026-03-07 20:39:54 +00:00
tuya-bridge [ci skip] fix invalid Homepage dashboard icons for 9 services 2026-03-07 21:14:17 +00:00
url [ci skip] add Homepage widget credentials for Authentik, Shlink, Home Assistant 2026-03-07 20:39:54 +00:00
wealthfolio [ci skip] fix Wealthfolio Homepage icon: wealthfolio.png → mdi-finance 2026-03-07 21:32:58 +00:00
webhook_handler [ci skip] add Homepage gethomepage.dev annotations to all services 2026-03-07 20:39:54 +00:00
whisper [ci skip] phase 5+6: update CI pipelines for SOPS, add sensitive=true to secret vars 2026-03-07 14:30:36 +00:00
woodpecker [ci skip] add Homepage gethomepage.dev annotations to all services 2026-03-07 20:39:54 +00:00
ytdlp [ci skip] add Homepage gethomepage.dev annotations to all services 2026-03-07 20:39:54 +00:00