Compare commits
1
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
  jakman85andClaude Opus 5.5
|
759a0e51c8 |
No files matched your search
@@ -77,42 +77,6 @@ spec:
|
||||
requests:
|
||||
storage: 1Gi
|
||||
---
|
||||
# act_runner config file — DELTAS ONLY. act_runner v0.6.1 LoadDefault()
|
||||
# (internal/pkg/config/config.go) unmarshals this file onto a ZERO Config and then fills every
|
||||
# unset field with the same default it uses when there is no file at all, so a file holding
|
||||
# only `runner.capacity` changes exactly that and nothing else. Do NOT paste in the output of
|
||||
# `act_runner generate-config`: that example is NOT the defaults. Its `runner.labels` would
|
||||
# OVERRIDE the registered labels in /data/.runner (daemon.go: config labels win when non-empty)
|
||||
# and repoint ubuntu-latest at a different job image; its `force_pull: true` differs from the
|
||||
# no-file default (false); and its sample `envs` would be injected into every job.
|
||||
#
|
||||
# Using a file also makes act_runner IGNORE the legacy GITEA_RUNNER_CAPACITY / _FILE /
|
||||
# _ENVIRON / _ENV_FILE / GITEA_DEBUG / GITEA_TRACE env vars (deprecated.go). None of them is
|
||||
# set on this Deployment; the GITEA_INSTANCE_URL / _REGISTRATION_TOKEN / _NAME / _LABELS env
|
||||
# below is consumed by the image's run.sh for registration, not by that legacy path.
|
||||
#
|
||||
# A ConfigMap edit alone does NOT restart the runner (it reads the file once at start). If a
|
||||
# future change touches ONLY this ConfigMap, also bump the Deployment's pod template (e.g. the
|
||||
# config-revision annotation below) or the new value stays inert until the next restart.
|
||||
apiVersion: v1
|
||||
kind: ConfigMap
|
||||
metadata:
|
||||
name: act-runner-config
|
||||
namespace: gitea-actions
|
||||
labels:
|
||||
app.kubernetes.io/name: act-runner
|
||||
data:
|
||||
config.yaml: |
|
||||
runner:
|
||||
# Two concurrent jobs (default 1). Measured 2026-11-08: queue wait ~1s normally, but
|
||||
# 29-759s whenever gate / images / renovate runs collide (run 472 waited 759s behind a
|
||||
# renovate burst). Both jobs share the ONE dind daemon below; act_runner names each job's
|
||||
# containers GITEA-ACTIONS-TASK-<task id> and creates a network per job, so they do not
|
||||
# collide. Workflow `concurrency:` groups are enforced by Gitea server-side and are
|
||||
# unaffected: gate.yml's gate-<ref> group still cancels a superseded run on the SAME ref,
|
||||
# and renovate's group still serialises renovate. The dind resources are sized for TWO jobs.
|
||||
capacity: 2
|
||||
---
|
||||
apiVersion: apps/v1
|
||||
kind: Deployment
|
||||
metadata:
|
||||
@@ -131,10 +95,6 @@ spec:
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/name: act-runner
|
||||
annotations:
|
||||
# Bump when act-runner-config changes without any other pod-template change, so the
|
||||
# Deployment rolls and act_runner re-reads its config (see the ConfigMap header).
|
||||
homelab.keithjackson.dev/act-runner-config-revision: "1" # capacity 2
|
||||
spec:
|
||||
# CI holds no cluster credentials — do not mount a SA token into the runner or
|
||||
# (via the shared netns) the job containers (R-SEC-02, docs/14).
|
||||
@@ -186,23 +146,12 @@ spec:
|
||||
mountPath: /certs
|
||||
- name: dind-storage
|
||||
mountPath: /var/lib/docker
|
||||
# Sized for runner.capacity: 2. Every job's containers run UNDER this daemon, so this
|
||||
# container's cgroup carries the whole CI workload. Measured 2026-11-08 (Prometheus,
|
||||
# capacity 1): peak CPU 0.69 core (1m rate, 30d), peak working set 447Mi (30d), 0 OOMs.
|
||||
# cpu request 2: two jobs at today's peak is ~1.4 core, and the gate is being
|
||||
# parallelised, so per-job demand rises. The request is what the CFS share is
|
||||
# weighted by under contention (100m was a 1/20 share); NO cpu limit, deliberately,
|
||||
# so an idle node's spare cores are still usable. k3s-prod-2 (8 CPU) had 2945m
|
||||
# requested; +1.9 core = ~4.85 (61%), and prod-1/prod-3 fit too if it reschedules.
|
||||
# memory request 1Gi / limit 4Gi: two jobs at today's peak is ~0.9Gi. An OOM kill here
|
||||
# takes down dockerd and with it BOTH running jobs, so the limit carries ~4x headroom
|
||||
# over that for the parallelised gate. Nodes have ~31Gi allocatable.
|
||||
resources:
|
||||
requests:
|
||||
cpu: "2"
|
||||
memory: 1Gi
|
||||
cpu: 100m
|
||||
memory: 256Mi
|
||||
limits:
|
||||
memory: 4Gi
|
||||
memory: 2Gi
|
||||
startupProbe:
|
||||
exec:
|
||||
command:
|
||||
@@ -246,36 +195,23 @@ spec:
|
||||
value: /certs/client
|
||||
- name: DOCKER_TLS_VERIFY
|
||||
value: "1"
|
||||
# The image's run.sh passes `--config <this>` to BOTH `act_runner register` and
|
||||
# `act_runner daemon` when CONFIG_FILE is set (act_runner v0.6.1 scripts/run.sh).
|
||||
- name: CONFIG_FILE
|
||||
value: /etc/act_runner/config.yaml
|
||||
volumeMounts:
|
||||
- name: data
|
||||
mountPath: /data
|
||||
- name: certs
|
||||
mountPath: /certs
|
||||
readOnly: true
|
||||
- name: config
|
||||
mountPath: /etc/act_runner
|
||||
readOnly: true
|
||||
# Measured 2026-11-08 at capacity 1: peak CPU 0.24 core, peak working set 314Mi (30d)
|
||||
# against the old 512Mi limit. It holds per-task state, log buffers and the embedded
|
||||
# actions/cache server for every concurrent task, so the limit is doubled for capacity 2.
|
||||
resources:
|
||||
requests:
|
||||
cpu: 100m
|
||||
memory: 256Mi
|
||||
memory: 128Mi
|
||||
limits:
|
||||
memory: 1Gi
|
||||
memory: 512Mi
|
||||
volumes:
|
||||
- name: data
|
||||
persistentVolumeClaim:
|
||||
claimName: act-runner-data
|
||||
- name: certs
|
||||
emptyDir: {}
|
||||
- name: config
|
||||
configMap:
|
||||
name: act-runner-config
|
||||
- name: dind-storage
|
||||
emptyDir: {}
|
||||
@@ -0,0 +1,65 @@
|
||||
---
|
||||
date: 2026-11-08
|
||||
branch: chore/renovate-config-cleanup
|
||||
title: Renovate config — hand-migrate the docker key, track gitea/runner, keep HelmRelease range lower bounds
|
||||
---
|
||||
|
||||
## What changed
|
||||
|
||||
- **`renovate.json5`: the deprecated top-level `"docker": {"enabled": true}` is hand-migrated** to
|
||||
`packageRules[0] = {"matchCategories": ["docker"], "enabled": true}`, the exact shape Renovate's
|
||||
own migration produced on `origin/renovate/migrate-config` (PR #139). Its comment moved with it.
|
||||
This replaces #139, which was closed because its rewrite deleted every comment in the file. No
|
||||
other comment was removed or reflowed (diff is additions plus the moved block).
|
||||
- **`gitea/runner` added to the blast-radius rule** beside `gitea/act_runner`, with a comment:
|
||||
act_runner was renamed upstream to gitea/runner after 0.6.1; Renovate does not follow renames,
|
||||
so the actual image migration is a separate manual PR.
|
||||
- **Two new packageRules for flux/helm `>=A <B` ranges:** `rangeStrategy: "bump"`, plus
|
||||
`matchUpdateTypes: ["bump"] -> enabled: false`, so in-range releases (which Flux adopts on its
|
||||
own) do not become PRs. Cause of the bug, from the 44.167.0 source: rangeStrategy is unset
|
||||
(`auto`); the flux manager has no `getRangeStrategy`/`updateLockedDependency`, so
|
||||
`lib/modules/manager/index.ts getRangeStrategy` resolves `auto` to `replace`; helm versioning is
|
||||
the npm api verbatim, and npm `getNewValue` under `replace` turns `>=1.12.0 <1.13.0` into
|
||||
`<1.14.0` (what PRs #131, #130 and #115 did).
|
||||
- **`platform/headlamp/helmrelease.yaml`: `version: "<0.47.0"` -> `">=0.46.0 <0.47.0"`**, comment
|
||||
refreshed. The live chart is 0.46.0, so the set of installable charts is unchanged.
|
||||
|
||||
## What I verified
|
||||
|
||||
- **Semantic diff of #139:** I parsed `renovate.json5` on `origin/renovate/migrate-config` and on its
|
||||
parent `5b484f6` with json5 (the copy inside the renovate image). With `docker` removed from the
|
||||
parent and `packageRules[0]` removed from the migrated file, the two are identical. So the only
|
||||
change was `{"matchCategories":["docker"],"enabled":true}`, inserted at packageRules[0].
|
||||
- **Validator, `ghcr.io/renovatebot/renovate:44.167.0`** (the tag that `.gitea/workflows/renovate.yaml`
|
||||
pins as `container.image`): `renovate-config-validator` gives `Config validated successfully`
|
||||
(rc 0), and so does `--strict` (rc 0), both as a file path and in repo mode. **`--strict` on
|
||||
origin/main's file gives rc 1** and prints the `docker` migration diff. Nothing is left to migrate.
|
||||
- **`getNewValue` called in the 44.167.0 image** (helm versioning), currentValue
|
||||
`>=1.12.0 <1.13.0`, newVersion 1.13.0: replace `<1.14.0`, widen `>=1.12.0 <1.14.0`,
|
||||
bump `>=1.13.0 <1.14.0`, pin/update-lockfile `<1.14.0`. On `<0.47.0`, bump returns the value
|
||||
unchanged, so it would never propose anything for that range. That is why the rule is scoped to
|
||||
the `>=A <B` shape.
|
||||
- **Local dry run** (`--platform=local`, `RENOVATE_DRY_RUN=lookup`, 44.167.0, live chart repos)
|
||||
against a fixture repo of four HelmReleases under `platform/`:
|
||||
- With this branch's config: `No config migration necessary`. longhorn `>=1.9.0 <1.10.0` ->
|
||||
`>=1.13.0 <1.14.0` (minor). kube-prometheus-stack `>=88.0.0 <89.0.0` -> `>=93.1.0 <94.0.0`
|
||||
(major). The in-range bump `>=88.6.5 <89.0.0` was dropped (`Filtered out 1 disabled update(s)`).
|
||||
headlamp `>=0.46.0 <0.47.0` and `<0.47.0`: no update.
|
||||
- Control run with origin/main's config: `Config migration necessary`, longhorn -> `<1.14.0`,
|
||||
kube-prometheus-stack -> `<94.0.0`. This reproduces the reported bug.
|
||||
- Live headlamp HelmRelease (read-only kubectl, k3s-prod): spec `<0.47.0`, history chartVersion
|
||||
`0.46.0`, Ready `True`.
|
||||
|
||||
## What I did NOT verify
|
||||
|
||||
- **I have not seen a real scheduled Renovate run against this repo with this config.** The claim that
|
||||
Renovate stops reopening the migrate-config PR rests on the validator and on `No config migration
|
||||
necessary` in the local dry run, not on the Gitea bot. After merge, watch the next run, and if
|
||||
`renovate/migrate-config` is still on the remote, delete it.
|
||||
- **Under bump, the new lower bound is the release Renovate proposes**, e.g. `>=1.13.2 <1.14.0`, not
|
||||
`>=1.13.0`. Flux still installs the newest release in the window. Ranges with other shapes keep the
|
||||
default `replace`: `3.9.x`, `~`, ceiling-only, and exact pins.
|
||||
- **The open PRs #131, #115 and any others still carry unbounded `<X` values.** They were generated
|
||||
under the old strategy, and Renovate should rebase or regenerate them under bump on its next run.
|
||||
I have not checked that it does.
|
||||
- The gitea/runner rename itself (a new image reference and any config changes) is not done here.
|
||||
@@ -1,155 +0,0 @@
|
||||
---
|
||||
date: 2026-11-08
|
||||
branch: feat/runner-capacity-2
|
||||
title: act_runner runs two jobs at once, and dind is sized for two
|
||||
---
|
||||
|
||||
## What changed
|
||||
|
||||
`apps/wave-1/gitea-actions.yaml` only. That file is a **hand-owned** non-catalog unit
|
||||
(`EXTRA_UNITS["gitea-actions"]` in `catalog/render.py`): the renderer only decides which wave
|
||||
it lands in, it does not generate its bytes, and `ci/render-golden.sh` compares only files the
|
||||
catalog renders. So it is edited in place, and no re-render was needed or run.
|
||||
|
||||
1. **New ConfigMap `act-runner-config`** holding a config file with ONE key,
|
||||
`runner.capacity: 2`, mounted read-only at `/etc/act_runner/` and selected with
|
||||
`CONFIG_FILE=/etc/act_runner/config.yaml`. The image's `run.sh` (act_runner v0.6.1) turns
|
||||
that into `--config` for both `register` and `daemon`.
|
||||
- Deltas only, on evidence: v0.6.1 `LoadDefault()` unmarshals the file onto a zero Config and
|
||||
then applies the same defaults as the no-file path, so the other settings are unchanged.
|
||||
- The `generate-config` example was deliberately NOT used. Its `runner.labels` would override
|
||||
the registered labels in `/data/.runner` and repoint `ubuntu-latest` at
|
||||
`docker.gitea.com/runner-images`. Its `force_pull: true` is not the default. Its sample `envs`
|
||||
would be injected into every job.
|
||||
- With a file present, act_runner ignores the legacy `GITEA_RUNNER_CAPACITY` /
|
||||
`_FILE` / `_ENVIRON` / `_ENV_FILE` / `GITEA_DEBUG` / `GITEA_TRACE` env vars. None of
|
||||
them is set on this Deployment.
|
||||
2. **Pod-template annotation `homelab.keithjackson.dev/act-runner-config-revision: "1"`.**
|
||||
act_runner reads its config once, at start, so a change to the ConfigMap alone would never
|
||||
take effect. Bump this annotation whenever you change only the ConfigMap.
|
||||
3. **dind resources:** requests `cpu 100m -> 2` and `memory 256Mi -> 1Gi`; limit
|
||||
`memory 2Gi -> 4Gi`. There is still no CPU limit, on purpose.
|
||||
4. **runner resources:** request `memory 128Mi -> 256Mi`, limit `memory 512Mi -> 1Gi`. CPU stays
|
||||
at `100m`.
|
||||
|
||||
Why these sizes. Measured 2026-11-08 through Prometheus, at capacity 1:
|
||||
|
||||
| container | peak CPU (1m rate, 30d) | peak working set (30d) | OOM events (7d) |
|
||||
|---|---|---|---|
|
||||
| dind | 0.69 core | 447 MiB | 0 |
|
||||
| runner | 0.24 core | 314 MiB | 0 |
|
||||
|
||||
At the moment of measurement the pod was idle (`top`: dind 1m/138Mi, runner 1m/83Mi), on
|
||||
k3s-prod-2.
|
||||
|
||||
- **CPU request 2.** Two jobs at today's peak is about 1.4 cores. The gate is being parallelised
|
||||
in other work, so each job will use more than that. The request sets dind's CFS weight under
|
||||
contention; at 100m it got a 1/20 share. With no limit, dind can still use spare cores on an
|
||||
idle node.
|
||||
- **Memory 1Gi / 4Gi.** Two jobs at today's peak is about 0.9 GiB. If dind is OOM-killed,
|
||||
dockerd goes down and takes both running jobs with it, so the limit is about 4x that.
|
||||
- **Runner limit 512Mi -> 1Gi.** Its 30-day peak was already 61% of the old limit, and with
|
||||
capacity 2 it holds state for two tasks.
|
||||
|
||||
Scheduling headroom: CPU requests per node were measured with `describe node`. The pod's total
|
||||
CPU request goes from 200m to 2100m (+1.9 cores).
|
||||
|
||||
| node | CPU requested now | after the change | allocatable |
|
||||
|---|---|---|---|
|
||||
| prod-2 (current) | 2945m | ~4845m (61%) | 8 |
|
||||
| prod-1 | 3175m | ~5075m | 8 |
|
||||
| prod-3 | 3840m | ~5740m (72%) | 8 |
|
||||
|
||||
The pod fits on any of the three if the RWO PVC moves it.
|
||||
|
||||
Concurrency semantics. Workflow `concurrency:` groups are enforced by Gitea on the server, not by
|
||||
the runner, so capacity does not change them:
|
||||
|
||||
- `gate.yml` `gate-${{ github.ref }}` with cancel-in-progress still cancels a superseded run on
|
||||
the same ref.
|
||||
- `renovate` (group `renovate`, no cancel) and `images-${{ github.ref }}` still serialise
|
||||
themselves.
|
||||
|
||||
What capacity 2 does change: runs on *different* refs (a PR gate next to a renovate or images
|
||||
run, or two PRs) now run side by side instead of queueing. The required check
|
||||
`gate / gate (pull_request)` is still one job per PR head, and gate.yml's other job
|
||||
(`conformance`) is `if: false`, so it never runs.
|
||||
|
||||
Both jobs share one dockerd. act_runner gives each task its own container prefix
|
||||
(`GITEA-ACTIONS-TASK-<task id>`) and its own network, and no workflow uses fixed container names
|
||||
or host ports.
|
||||
|
||||
## What I verified
|
||||
|
||||
- **Source of truth.** `catalog/render.py` `EXTRA_UNITS` places `gitea-actions.yaml` by
|
||||
anchor/offset only. `ci/render-golden.sh` iterates over rendered files only, so this file is
|
||||
outside render==golden. No `--emit-waves` was run.
|
||||
- **act_runner v0.6.1 behaviour, read in its source** (tag v0.6.1):
|
||||
- `config.LoadDefault()` treats a partial file as described above.
|
||||
- `daemon.go`: config labels override `.runner` labels only when non-empty.
|
||||
- `poller.go`: a semaphore of `cfg.Runner.Capacity` bounds concurrent tasks.
|
||||
- `runner.go`: per-task container name prefix.
|
||||
- The image's `run.sh`, read from `gitea/act_runner:0.6.1`, honours `CONFIG_FILE`.
|
||||
- **The live pod has no config file today.** `/data` holds only `.runner` and `lost+found`.
|
||||
`act_runner --version` reports v0.6.1. No LimitRange or ResourceQuota exists in
|
||||
`gitea-actions`.
|
||||
- **Resource numbers.** All figures above come from read-only `kubectl top`, `describe node` and
|
||||
Prometheus queries against k3s-prod.
|
||||
- **dind disk.** The emptyDir sits on the node's 11.8G ephemeral filesystem: 4.0G used, 7.2G
|
||||
free. Image cache is 2.18GB, which is the one `catthehacker/ubuntu:act-22.04` image. Two
|
||||
concurrent jobs share that image.
|
||||
- **Embedded config.** It parses as YAML to `{'runner': {'capacity': 2}}`. The only `$` in the
|
||||
manifest is the existing `${BASE_DOMAIN}`, so nothing new is exposed to Flux postBuild
|
||||
envsubst.
|
||||
- **Approval policy.** `apps/wave-1/` matches no `sensitive_paths` glob in
|
||||
`infra/gitea/approval-policy.json`, so this PR merges on a green gate alone.
|
||||
- **Local gate.** Pinned toolbox, run from the worktree on the committed tree. The rc and skipped
|
||||
stages are given in the PR description.
|
||||
|
||||
## What I did NOT verify
|
||||
|
||||
- **UNVERIFIED: that the runner actually starts with the config and runs two jobs at once.**
|
||||
Nothing is applied until Flux reconciles `main`.
|
||||
- **Capacity cannot be seen through Gitea's API.** act_runner v0.6.1 does not report capacity to
|
||||
Gitea: `Declare` sends only version and labels. `GET /api/v1/admin/actions/runners` therefore
|
||||
cannot show "capacity 2". Concurrency has to be observed instead.
|
||||
- **UNVERIFIED: whether the parallelised gate fits in these sizes.** That gate has not landed.
|
||||
Re-measure after it does, with
|
||||
`max_over_time(sum by (container)(rate(container_cpu_usage_seconds_total{namespace="gitea-actions"}[1m]))[7d:30s])`.
|
||||
- **Rollout cancels in-flight jobs.** The rollout restarts the runner pod (strategy Recreate,
|
||||
`shutdown_timeout: 0s`), and any job running at that moment is cancelled, possibly including
|
||||
the `push`-to-main gate run triggered by this very merge. Re-run it if that happens.
|
||||
- **dind disk is not bounded by a limit.** With two jobs it holds two jobs' workspaces and layers
|
||||
on the same 11.8G node filesystem. I did not add an `ephemeral-storage` limit, because an
|
||||
eviction would kill both jobs. Watch kubelet DiskPressure on the runner's node.
|
||||
- **Stale comments in sensitive paths.** `.gitea/workflows/gate.yml` (line ~52) and
|
||||
`.gitea/workflows/README.md` (line ~86) still say "`act_runner` runs at capacity 1". I left
|
||||
them alone because `.gitea/**` is a sensitive path and editing them would put this PR behind
|
||||
human approval. Fix them in a separate PR.
|
||||
|
||||
### Operator post-merge checklist
|
||||
|
||||
1. Flux applied it:
|
||||
`kubectl --context k3s-prod -n flux-system get kustomization apps-wave-1 -o jsonpath='{.status.lastAppliedRevision}'`
|
||||
equals the merge commit.
|
||||
2. The pod restarted with the config:
|
||||
- `kubectl --context k3s-prod -n gitea-actions get pod -l app.kubernetes.io/name=act-runner`
|
||||
shows a new pod, 2/2 Running.
|
||||
- `kubectl ... exec deploy/act-runner -c runner -- cat /etc/act_runner/config.yaml` shows
|
||||
`capacity: 2`.
|
||||
- `kubectl ... exec deploy/act-runner -c runner -- ps` shows `act_runner daemon --config /etc/act_runner/config.yaml`.
|
||||
- The logs show "declare successfully" with the two expected labels (`ubuntu-latest`,
|
||||
`homelab` -> `catthehacker/ubuntu:act-22.04`). That confirms the labels did not change.
|
||||
3. The runner is registered and online:
|
||||
- `GET /api/v1/admin/actions/runners` lists `incluster-dind`, online, with the same ID as
|
||||
before (no duplicate row).
|
||||
- Capacity is NOT shown there; see above.
|
||||
4. Concurrency is real: trigger two runs on different refs (e.g. two PR gates, or a PR gate plus a
|
||||
`workflow_dispatch` of renovate). Then either:
|
||||
- in `GET /api/v1/repos/Home-Network/home-network-k3s-impl/actions/tasks`, confirm their
|
||||
`run_started_at` .. `updated_at` windows overlap; or
|
||||
- check
|
||||
`docker --host=tcp://127.0.0.1:2376 --tlsverify ... ps` in the dind container lists two
|
||||
`GITEA-ACTIONS-TASK-*` container sets at once.
|
||||
5. Resources: `kubectl --context k3s-prod -n gitea-actions describe pod` shows dind requests
|
||||
cpu 2 / memory 1Gi, limit memory 4Gi, and runner limit memory 1Gi.
|
||||
@@ -40,7 +40,11 @@ spec:
|
||||
# values (-session-ttl + the -oidc-* args from the externalSecret; useCookie stays default-false
|
||||
# so `-oidc-use-cookie` is NOT emitted) is supported by the v0.41.0 backend. Renovate maintains
|
||||
# within 0.41.x; the appVersion continues to pin the Headlamp image.
|
||||
version: "<0.47.0"
|
||||
# 2026-11-08: NOW 0.46.x. PR #130 (Renovate, default rangeStrategy `replace`) rewrote
|
||||
# `>=0.41.0 <0.42.0` to the unbounded-below `<0.47.0`; the lower bound is restored here at the
|
||||
# chart that was live when it merged (0.46.0). renovate.json5 now bumps `>=A <B` ranges as a window,
|
||||
# so the next widen PR proposes `>=0.47.x <0.48.0` rather than `<0.48.0`.
|
||||
version: ">=0.46.0 <0.47.0"
|
||||
sourceRef:
|
||||
kind: HelmRepository
|
||||
name: headlamp
|
||||
|
||||
+63
-10
@@ -37,6 +37,8 @@
|
||||
// renovate-config-validator /tmp/renovate.json5
|
||||
// (Not `--strict`: that also fails on a pending migration of the pre-existing top-level
|
||||
// `"docker": {"enabled": true}` block at the bottom, which is a warning, not an error.)
|
||||
// RESOLVED 2026-11-08: that block is now hand-migrated to the first packageRule (`matchCategories:
|
||||
// ["docker"]`), the exact shape Renovate's own migration produced, so no migration is pending.
|
||||
//
|
||||
// `regex` vs `custom.regex` in enabledManagers, RESOLVED FROM SOURCE (Renovate 39.264.0 and
|
||||
// later): both work. lib/config/migrations/custom/enabled-managers-migration.ts rewrites
|
||||
@@ -196,6 +198,22 @@
|
||||
}
|
||||
],
|
||||
"packageRules": [
|
||||
// The `docker` manager (Dockerfiles, docker-compose) and the `kubernetes` manager above were
|
||||
// BOTH previously `enabled: false`, solely so Renovate would not fight Flux image-automation
|
||||
// over a running tag. That controller was never enabled and never will be here (see _comment),
|
||||
// so the only thing those two flags were achieving was leaving every plain `image:` tag in the
|
||||
// repo unmanaged. `docker` is left out of enabledManagers because this repo contains no
|
||||
// Dockerfile that ships to the cluster; `kubernetes` is now ON and is the one that matters.
|
||||
// MOVED HERE 2026-11-08 from a top-level `"docker": {"enabled": true}` key, which Renovate
|
||||
// deprecated (the top-level language objects became `matchCategories` rules). Hand-migrated to
|
||||
// the exact output of Renovate's own config migration (branch renovate/migrate-config, PR #139:
|
||||
// a json5 semantic diff of that file against its parent shows THIS rule, inserted at
|
||||
// packageRules[0], as the ONLY change). #139 itself was closed unmerged because its rewrite
|
||||
// dropped every comment in this file. With nothing left to migrate, Renovate stops reopening it.
|
||||
{
|
||||
"matchCategories": ["docker"],
|
||||
"enabled": true
|
||||
},
|
||||
{
|
||||
"description": "Auto-merge the allowed low-risk classes on green CI \u2014 no human authoring (R-UPD-02). The Gitea merge gate (make -C ci gate) is the required check.",
|
||||
"matchUpdateTypes": [
|
||||
@@ -252,6 +270,11 @@
|
||||
// Keycloak's (the IdP) included, now that imageName is tracked.
|
||||
"gitea/gitea",
|
||||
"gitea/act_runner",
|
||||
// ADDED 2026-11-08. act_runner was RENAMED upstream to gitea/runner after 0.6.1
|
||||
// (https://gitea.com/gitea/runner/releases). Renovate does not follow a rename — it will
|
||||
// never propose gitea/act_runner -> gitea/runner — so that migration is a manual PR. Listed
|
||||
// now so the new name is blast-radius from its first reference, not after an auto-merge.
|
||||
"gitea/runner",
|
||||
"ghcr.io/cloudnative-pg/postgresql"
|
||||
],
|
||||
"automerge": false,
|
||||
@@ -368,6 +391,45 @@
|
||||
"automerge": false,
|
||||
"addLabels": ["needs-review", "range-widen"]
|
||||
},
|
||||
// ADDED 2026-11-08 — KEEP THE LOWER BOUND WHEN A MINOR-LOCKED RANGE MOVES. MEASURED PROBLEM:
|
||||
// PRs #131 (longhorn), #130 (headlamp) and #115 (kube-prometheus-stack) turned
|
||||
// `">=1.12.0 <1.13.0"` into `"<1.14.0"` — an UNBOUNDED-below range that also admits every
|
||||
// older chart (and #130 merged: platform/headlamp/helmrelease.yaml carried `<0.47.0`). WHY,
|
||||
// from the 44.167.0 source this file is validated against: no rangeStrategy is set, so it is
|
||||
// `auto`; the flux manager has no getRangeStrategy and no updateLockedDependency, so
|
||||
// lib/modules/manager/index.ts getRangeStrategy resolves `auto` -> `replace`. The helm
|
||||
// datasource's defaultVersioning is `helm`, which is the npm versioning api verbatim
|
||||
// (lib/modules/versioning/helm/index.ts: `api = { ...npm }`), and npm getNewValue under
|
||||
// `replace` rewrites `>=A <B` to just `<C`. Calling that getNewValue in the 44.167.0 image for
|
||||
// currentValue `>=1.12.0 <1.13.0`, newVersion 1.13.0:
|
||||
// replace -> `<1.14.0` widen -> `>=1.12.0 <1.14.0` bump -> `>=1.13.0 <1.14.0`
|
||||
// Only `bump` keeps a one-minor window. (widen keeps the bound but grows the window by a minor
|
||||
// on every PR — the opposite of minor-locking.) Under bump the new lower bound is the release
|
||||
// proposed (e.g. 1.13.2 -> `>=1.13.2 <1.14.0`); Flux still picks the newest that satisfies it.
|
||||
// Scoped to the bounded `>=A <B` shape only: on a ceiling-only range like `<0.47.0` bump
|
||||
// returns the value unchanged, so Renovate would silently propose NOTHING for it, ever.
|
||||
{
|
||||
"description": "ADDED 2026-11-08. HelmRelease `version: \">=A <B\"` ranges move as a whole window (rangeStrategy bump), so a range-widen PR yields `>=1.13.0 <1.14.0`, not `<1.14.0`. See the comment above for the measured cause.",
|
||||
"matchManagers": ["flux"],
|
||||
"matchDatasources": ["helm"],
|
||||
"matchCurrentValue": "/^>=\\S+ <\\S+$/",
|
||||
"rangeStrategy": "bump"
|
||||
},
|
||||
// ...AND DO NOT LET bump ADD NOISE. Under bump Renovate also raises the lower bound for a
|
||||
// release ALREADY INSIDE the range (lib/workers/repository/process/lookup/generate.ts sets
|
||||
// isBump; e.g. 1.12.5 against `>=1.12.0 <1.13.0` -> `>=1.12.5 <1.13.0`), which `replace` never
|
||||
// proposed. Flux already installs that release with no PR, and the range-widen rule above
|
||||
// would hold every one for review. util/package-rules/update-types.ts matches isBump as
|
||||
// updateType `bump`, so exactly those updates are switched off here; out-of-range moves are
|
||||
// ordinary minor/major updates and are unaffected.
|
||||
{
|
||||
"description": "ADDED 2026-11-08. No PR for a chart release the HelmRelease range already admits — Flux adopts it on its own.",
|
||||
"matchManagers": ["flux"],
|
||||
"matchDatasources": ["helm"],
|
||||
"matchCurrentValue": "/^>=\\S+ <\\S+$/",
|
||||
"matchUpdateTypes": ["bump"],
|
||||
"enabled": false
|
||||
},
|
||||
{
|
||||
"description": "ADDED 2026-10-30. velero-plugin-for-aws is pinned to a RELEASE CANDIDATE (v1.14.3-rc.2) and Renovate proposed NOTHING for it, although v1.14.3 and v1.14.4 are stable on Docker Hub. Docker versioning treats everything after the first `-` as a compatibility SUFFIX, so only other `*-rc.2` tags qualify and the RC is a fossil forever. Semver versioning reads it as a prerelease, and a prerelease upgrades to the stable release.",
|
||||
"matchPackageNames": ["velero/velero-plugin-for-aws"],
|
||||
@@ -439,14 +501,5 @@
|
||||
"conformance/tests/**",
|
||||
"platform/image-automation/per-service/**",
|
||||
"platform/kyverno/tests/**"
|
||||
],
|
||||
// The `docker` manager (Dockerfiles, docker-compose) and the `kubernetes` manager above were
|
||||
// BOTH previously `enabled: false`, solely so Renovate would not fight Flux image-automation
|
||||
// over a running tag. That controller was never enabled and never will be here (see _comment),
|
||||
// so the only thing those two flags were achieving was leaving every plain `image:` tag in the
|
||||
// repo unmanaged. `docker` is left out of enabledManagers because this repo contains no
|
||||
// Dockerfile that ships to the cluster; `kubernetes` is now ON and is the one that matters.
|
||||
"docker": {
|
||||
"enabled": true
|
||||
}
|
||||
]
|
||||
}
|
||||
Reference in new issue
Block a user