fix: eliminate memory overcommit to prevent node OOM crashes

Set requests = limits (Guaranteed QoS) across LimitRange defaults and
explicit pod resources. Node2 crashed 2026-03-14 from 250% memory
overcommit (61GB limits on 24GB node).

Changes:
- LimitRange: default = defaultRequest for all 6 tiers
- Grafana: 3 → 2 replicas
- Grampsweb: document why replicas=0
- Prometheus: 1Gi/4Gi → 3Gi/3Gi
- OpenClaw: 512Mi/2Gi → 768Mi/768Mi
- Immich server: 256Mi/2Gi → 512Mi/512Mi
- Immich postgresql: 256Mi/1Gi → 512Mi/512Mi
- Calibre: 256Mi/1536Mi → 256Mi/256Mi
- Linkwarden: 256Mi/1536Mi → 768Mi/768Mi
- N8N: 256Mi/1Gi → 512Mi/512Mi
- MySQL cluster: 1Gi/3-4Gi → 2Gi/2Gi
- pg-cluster (CNPG): 512Mi/4Gi → 512Mi/512Mi
- DBaaS ResourceQuota limits.memory: 64Gi → 12Gi

[ci skip]
This commit is contained in:
Viktor Barzin 2026-03-14 16:01:41 +00:00
parent 27fa8ea18f
commit 2be858f616
10 changed files with 70 additions and 30 deletions

View file

@ -36,7 +36,7 @@ resource "kubernetes_resource_quota" "dbaas" {
hard = {
"requests.cpu" = "8"
"requests.memory" = "12Gi"
"limits.memory" = "64Gi"
"limits.memory" = "12Gi"
pods = "30"
}
}
@ -181,10 +181,10 @@ resource "helm_release" "mysql_cluster" {
resources = {
requests = {
cpu = "250m"
memory = "1Gi"
memory = "2Gi"
}
limits = {
memory = "4Gi"
memory = "2Gi"
}
}
@ -216,11 +216,11 @@ resource "helm_release" "mysql_cluster" {
name = "mysql"
resources = {
requests = {
memory = "1Gi"
memory = "2Gi"
cpu = "250m"
}
limits = {
memory = "3Gi"
memory = "2Gi"
}
}
}]
@ -229,21 +229,21 @@ resource "helm_release" "mysql_cluster" {
name = "fixdatadir"
resources = {
requests = { memory = "64Mi", cpu = "25m" }
limits = { memory = "256Mi" }
limits = { memory = "64Mi" }
}
},
{
name = "initconf"
resources = {
requests = { memory = "256Mi", cpu = "50m" }
limits = { memory = "1Gi" }
limits = { memory = "256Mi" }
}
},
{
name = "initmysql"
resources = {
requests = { memory = "512Mi", cpu = "250m" }
limits = { memory = "2Gi" }
limits = { memory = "512Mi" }
}
}
]
@ -842,7 +842,7 @@ resource "null_resource" "pg_cluster" {
image = "ghcr.io/cloudnative-pg/postgis:16"
storage_size = "20Gi"
storage_class = "iscsi-truenas"
memory_limit = "4Gi"
memory_limit = "512Mi"
}
@ -870,7 +870,7 @@ resource "null_resource" "pg_cluster" {
cpu: "50m"
memory: "512Mi"
limits:
memory: "4Gi"
memory: "512Mi"
EOF
EOT
}