viktor/infra
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

llama-cpp: ignore_changes for keel/k8s-managed annotations

Browse source 
Every `tg apply` was reverting the annotations that keel patches when it
detects an upstream digest change — `keel.sh/match-tag` (Kyverno-stamped),
`keel.sh/update-time` (on the pod template; what actually triggers the
rollout), plus the K8s-managed `kubernetes.io/change-cause` and
`deployment.kubernetes.io/revision`. The revert forced a rollout, then
the next keel poll re-stamped the annotations, forcing another. With
llama-swap's ~10s cold-load on each pod recreate the user noticed.

Upstream `ghcr.io/mostlygeek/llama-swap:cuda` is a moving nightly tag —
keel still drives one legitimate rollout per day at ~07:25 UTC; this
patch stops the apply-driven extra rollouts on top of that.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
This commit is contained in:
Viktor Barzin 2026-05-24 09:01:17 +00:00
parent 67f8be4598
commit 0b1282a13c
1 changed files with 12 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

12
stacks/llama-cpp/main.tf
View file

@ -373,10 +373,22 @@ resource "kubernetes_deployment" "llama_swap" {
lifecycle {
ignore_changes = [
spec[0].template[0].spec[0].dns_config, # KYVERNO_LIFECYCLE_V1
metadata[0].annotations["keel.sh/match-tag"],
metadata[0].annotations["keel.sh/policy"],
metadata[0].annotations["keel.sh/trigger"],
metadata[0].annotations["keel.sh/pollSchedule"], # KYVERNO_LIFECYCLE_V2
spec[0].template[0].spec[0].container[0].image, # KEEL_IGNORE_IMAGE
# KEEL_LIFECYCLE_V1 — stop the apply→keel fight: every keel digest
# update patches `keel.sh/update-time` on the pod template and
# `kubernetes.io/change-cause` + bumps the K8s rollout revision on
# the Deployment. Without these ignore_changes, every `tg apply`
# reverts those, forcing a rollout, which keel then re-patches on
# the next 1h poll → llama-swap was rolling several times a day
# (~10s model-load downtime each). Upstream :cuda nightly cadence
# still triggers a legitimate daily rollout.
metadata[0].annotations["kubernetes.io/change-cause"],
metadata[0].annotations["deployment.kubernetes.io/revision"],
spec[0].template[0].metadata[0].annotations["keel.sh/update-time"],
]
}