fix: restore pvc-autoresizer by allow-listing kubelet_volume_stats_available_bytes
The Prometheus scrape config for the kubernetes-nodes job kept capacity_bytes + used_bytes but dropped available_bytes. pvc-autoresizer computes utilization from available/capacity, so without that metric it was silent for every PVC in the cluster — including mailserver, which filled to 89% (1.7G/2.0G) and started rejecting all inbound mail with '452 4.3.1 Insufficient system storage' (15+ hours, all real senders: Brevo, Gmail, Facebook). Also bumps the floors of mailserver (2Gi -> 5Gi, limit 10Gi) and forgejo (15Gi -> 30Gi) PVCs to recover from the immediate outage, and adds ignore_changes on requests.storage so future autoresizer expansions don't cause TF drift.
This commit is contained in:
parent
352586f711
commit
9d5da4d8e0
3 changed files with 19 additions and 4 deletions
|
|
@ -293,7 +293,7 @@ resource "kubernetes_persistent_volume_claim" "data_encrypted" {
|
|||
annotations = {
|
||||
"resize.topolvm.io/threshold" = "80%"
|
||||
"resize.topolvm.io/increase" = "100%"
|
||||
"resize.topolvm.io/storage_limit" = "5Gi"
|
||||
"resize.topolvm.io/storage_limit" = "10Gi"
|
||||
}
|
||||
}
|
||||
spec {
|
||||
|
|
@ -301,10 +301,16 @@ resource "kubernetes_persistent_volume_claim" "data_encrypted" {
|
|||
storage_class_name = "proxmox-lvm-encrypted"
|
||||
resources {
|
||||
requests = {
|
||||
storage = "2Gi"
|
||||
storage = "5Gi"
|
||||
}
|
||||
}
|
||||
}
|
||||
lifecycle {
|
||||
# pvc-autoresizer expands this PVC up to storage_limit; ignore drift on
|
||||
# requests.storage. To bump the floor manually: temporarily remove this
|
||||
# block, apply the new size, re-add the block, apply again.
|
||||
ignore_changes = [spec[0].resources[0].requests]
|
||||
}
|
||||
}
|
||||
|
||||
resource "kubernetes_deployment" "mailserver" {
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue