From 87a9f4eb25d996849e3dab7306cd27c4e5028aa6 Mon Sep 17 00:00:00 2001 From: Lemon-miaow Date: Tue, 22 Sep 2026 22:03:48 +0800 Subject: [PATCH] feat(build)/docs: make executor images configurable; document the build lane's real seams (#9, #10) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit - [registry] gains kaniko_image / trivy_image / build_cpu_limit / build_mem_limit overrides; empty keeps the compiled-in defaults. An air-gapped or mirrored install has no route to gcr.io/aquasec (the build egress policy allows only DNS + registry + package mirrors), so builds previously could not even start their executors. - deferred-seams: the uploads-context entry now records WHY a mount is impossible (PVCs cannot cross namespaces) and that the s3 lane also lacks credentials in the build Pod — options captured for the real fix. - troubleshooting 8e (executor ImagePullBackOff + the overrides), 13b rewritten (verified eviction refusal, 5m pressure-transition, image-GC recovery), 15 (upgrade/rollback runbook for Recreate). - Backup semantics decided and documented: a backup is the whole /data volume (worlds + config + plugins + cache) and a restore rolls all of it back — OpenAPI/README wording updated to match (same-tag images are still watched for regressions by the openapi parity gate). --- AUDIT-2026-09-22.md | 4 +- README.md | 2 +- README_EN.md | 2 +- cmd/felis/api.go | 8 +++ cmd/felis/api_test.go | 26 ++++++++ docs/deferred-seams.md | 14 +++- docs/openapi.yaml | 9 +-- docs/troubleshooting.md | 113 +++++++++++++++++++++++++-------- internal/config/config.go | 13 ++++ internal/config/config_test.go | 11 ++++ 10 files changed, 165 insertions(+), 37 deletions(-) diff --git a/AUDIT-2026-09-22.md b/AUDIT-2026-09-22.md index e9e08b3..73b3acc 100644 --- a/AUDIT-2026-09-22.md +++ b/AUDIT-2026-09-22.md @@ -19,14 +19,14 @@ IPv6-only 接入（`ssh -6 -i ~/.ssh/id_ed25519 root@fdb2:2c26:f4e4:0:21c:42ff:f | 19 | **reaper CronJob 渲染位置错误，永远无法调度**：`felis manifests` 把 CronJob 渲染到控制 ns，却引用 minecraft ns 的备份 PVC（Pod 不能跨 ns 挂 PVC：真机 `FailedScheduling: persistentvolumeclaim "felis-backups" not found`）；修正 ns 后又发现 ServerAccount 也不能跨 ns 使用（`serviceaccount "felis-reaper" not found`）。而 reaper 的 Role/RoleBinding 本就在 minecraft ns | 真机三层取证（PVC/SA/调度）| CronJob 与 SA、RoleBinding subject 全部移到 `MinecraftNamespace`（提交 `e4f2cff`+`c839454`）。**修复后完整演练通过**（见下） | | 6 | **默认安装无备份能力 + 回收链路不可达/不可用**：(a) 没有任何环节渲染归档 PVC，`FELIS_BACKUP_PVC` 永远为空 → backup/restore 恒 503；(b) bootstrap 从不下传 reaper 三旗标 → 官方安装路径根本无法启用回收；(c) 即便启用，stock k3s 的 `/` 布局不存在，且 k3s storage root 是 `0700 root:root`、reaper pod 以 uid 1000 运行 → 真机 `lstat /worlds/…: permission denied`（fail-closed 跳过，但纯空转）；(d) README 口径（“定时备份”）不实 | 真机全链路：默认渲染 PVC+env → 建服→marker→备份 202→jobs 端点 running→succeeded→改 marker→restore→读回原值 ✅；再建 resolvecheck 世界（20d idle，marker）→ CronJob 手动 Job：`evaluated=2 reaped=1`，归档含 marker、PVC+宿主目录回收、`world_backups` 得 `inactive_15d` 行、servers 行/CR 保留 ✅ | `platform/workloads.go` 渲染归档 PVC（minecraft ns、RWO 10Gi、默认 SC），`felis manifests --backup-pvc` 默认 `felis-backups`（`=` 空为显式关闭），bootstrap 统一下传 env/旗标并写 [archive] local_path；`resolveWorldDir` 新增精确 local-path 目录解析（读 PVC `spec.volumeName`，非 glob，杜绝陈旧 PV 目录顶替）；ReaperRole 增 `pvc:get`；bootstrap 设 `FELIS_WORLDS_HOST_PATH` 时给 uid 1000 授 traverse（setfacl/o+x）；README/故障手册改写。提交 `fd33fd0`+`2b87a5a` | | 8 | **磁盘打满灾难链**：DiskPressure → kubelet 驱逐控制面（无 PriorityClass 保护）→ 镜像被 GC（无外网、registry 空）→ 全部 ImagePullBackOff；释放后数分钟才恢复调度。恢复依赖人工 `docker save | k3s ctr images import -` | 三轮真机 drill（原缺陷复现 + 两轮修复验证）：①自定义 1e6 类：游戏 pod 先走、控制面随后仍被驱逐（kubelet 日志逐条列出 ranked/evicted），随后镜像被 GC → ErrImagePull；②内建 `system-cluster-critical`（2e9）：填盘至 1.7G free，kubelet 对 felis-api/operator/registry 全部报 **“cannot evict a critical pod”**，三者在整个 DiskPressure 期间保持 Running；游戏 pod（0）被驱逐；③释放磁盘后：`DiskPressure` 经 ~5 分钟（`eviction-pressure-transition-period`）转 False——即“恢复慢”的主因；被 GC 的游戏镜像按 runbook 重导入后 25s 恢复 ✅ | 控制面四类 pod 挂内建 `system-cluster-critical`（用户自定义类值上限 1e9，达不到 2e9 临界阈值；preemption 保留=管理面可调度，已记录权衡）；troubleshooting §13b 固化事件链、5 分钟条件过渡与镜像恢复路径。提交见下 | +| 9 | **升级策略 Recreate**：单副本 + Recreate：任何控制面升级=停机；坏升级（错 tag）中断约 95s 且需人工 `rollout undo`（无自动回滚） | 复核部署模板（Recreate + 单副本 + 无 leader election 的注释理由成立） | 不改策略（Recreate 是对无 leader election 的正确取舍），改为固化 runbook：troubleshooting §15 = 升级即重跑安装器；停机窗口=rollout 时长；坏镜像在安装器 180s 等待内以 `kubectl describe` 诊断呈现；回滚 `kubectl rollout undo`（镜像被 GC 时先按 §13b 重导入）。提交见下 | +| 10 | **备份语义**：归档包含整个 /data（jar、libraries、cache），167MB；是否符合 world backup 定位待评估 | 真机 tar 清单（cache/、config/、eula.txt、server.properties、jar）+ 恢复语义（overlay+prune） | 评估结论：**整卷备份是正确语义**（回滚=整服状态回滚，含配置/插件），保留行为；文档化：troubleshooting §10「backup contains」+ OpenAPI/README 口径改为“整服数据卷”。提交见下 | ## 待决策台账（未修） | # | 主题 | 说明 | |---|------|------| | 7 | 异步失败不可感知 | backup/restore 失败后无状态出口：restore 行不变、backup 无行；只有集群侧 Job/日志可查。建议状态字段或 `?failed` 查询 | -| 9 | 升级策略 Recreate | 单副本 + Recreate：任何控制面升级=停机；坏升级（实测错 tag）服务中断约 95s 且需人工 `rollout undo`（无自动回滚）。建议 runbook/文档化 | -| 10 | 备份语义 | 归档包含整个 /data（jar、libraries、cache），167MB；是否符合"world backup"定位待评估 | | 11 | PG 断连表现 | 会话查询失败报 401 而非 503（fail-closed 但误导；用户以为没登录） | | 12 | ready 门滞后 | 容器 Ready 后 6~10s 内 API 仍 409 not_running | | 13 | setup token 截断 | 43 字符 token + 长域名，80 列终端下 TUI 截断显示（复现：tmux 80 列） | diff --git a/README.md b/README.md index 22b690a..2fc292c 100644 --- a/README.md +++ b/README.md @@ -17,7 +17,7 @@ A Kubernetes-driven Minecraft server hosting platform — one command to deploy, - **即开即玩**：玩家尝试连接时自动唤醒服务器，空闲后自动休眠，像游戏主机一样省资源。 - **Web 控制面板**：浏览器中查看服务器状态、在线玩家与资源用量，管理备份与恢复。 -- **备份与恢复**：一键把世界打包进集群内的归档库，支持从任意备份点回滚；默认安装就已启用（归档 PVC 与路径由安装器一并生成）。 +- **备份与恢复**：一键把整服数据（世界、配置、插件/模组，即整个 /data 卷）打包进集群内的归档库，支持从任意备份点回滚；默认安装就已启用（归档 PVC 与路径由安装器一并生成）。 - **智慧回收（可选开启）**：超过 15 天无人游玩的世界自动备份后删除，释放磁盘空间；安装时设置 `FELIS_WORLDS_HOST_PATH`（k3s 默认 `/var/lib/rancher/k3s/storage`）即启用每日回收，不设置则不删任何世界。 - **多核心支持**：兼容 Paper、Fabric、Forge、NeoForge，经由 Velocity 代理统一入口。 - **模组自助提交**：玩家自行上传模组包，服主审批通过后自动构建并部署。 diff --git a/README_EN.md b/README_EN.md index ed8d9fc..bd731f5 100644 --- a/README_EN.md +++ b/README_EN.md @@ -17,7 +17,7 @@ Table of Contents - **Wake on Join**: Servers start automatically when a player connects, and stop when idle — like hibernate for your server. - **Web Dashboard**: Monitor server status, online players, and resource usage from your browser, with backup and restore management. -- **Backup & Restore**: One-click world snapshots into the cluster's archive store, with rollback from any backup point — enabled by default (the installer renders the archive PVC and its path). +- **Backup & Restore**: One-click snapshots of a server's whole data volume (worlds, config, plugins/mods — the entire /data volume) into the cluster's archive store, with rollback from any backup point — enabled by default (the installer renders the archive PVC and its path). - **World Reaper** (opt in): Worlds idle for more than 15 days are automatically backed up and removed to free disk space. Enable it by setting `FELIS_WORLDS_HOST_PATH` at install time (on k3s: `/var/lib/rancher/k3s/storage`); without it, no world is ever deleted. - **Multi-core Support**: Compatible with Paper, Fabric, Forge, and NeoForge, federated behind a Velocity proxy. - **Modpack Submission**: Players submit custom modpacks; admin approval triggers automatic build and deployment. diff --git a/cmd/felis/api.go b/cmd/felis/api.go index 5588bac..23eb9a3 100644 --- a/cmd/felis/api.go +++ b/cmd/felis/api.go @@ -402,6 +402,14 @@ func buildConfig(cfg *config.Config) build.Config { return build.Config{ Namespace: cfg.Registry.BuildNamespace, RegistryURL: cfg.Registry.URL, + // Empty overrides fall back to the build package's defaults, so an + // install that has not imported kaniko/trivy keeps the compiled-in refs + // (and fails loudly on pull rather than silently building with the wrong + // image). + KanikoImage: cfg.Registry.KanikoImage, + TrivyImage: cfg.Registry.TrivyImage, + CPULimit: cfg.Registry.BuildCPULimit, + MemLimit: cfg.Registry.BuildMemLimit, } } diff --git a/cmd/felis/api_test.go b/cmd/felis/api_test.go index 755489e..ca6e752 100644 --- a/cmd/felis/api_test.go +++ b/cmd/felis/api_test.go @@ -44,6 +44,32 @@ func TestAuthSourcesFromConfig(t *testing.T) { } } +// TestBuildConfig_ProjectsOverrides pins the [registry] overrides reaching the +// build subsystem: unset fields must stay EMPTY (the build package's compiled-in +// defaults apply there, not here), and set fields must pass through verbatim — +// an air-gapped install points these at its imported mirrors. +func TestBuildConfig_ProjectsOverrides(t *testing.T) { + empty := buildConfig(&config.Config{}) + if empty.KanikoImage != "" || empty.TrivyImage != "" || empty.CPULimit != "" || empty.MemLimit != "" { + t.Errorf("empty registry config must project empty overrides (defaults live in internal/build), got %+v", empty) + } + full := buildConfig(&config.Config{Registry: config.RegistryConfig{ + URL: "registry.felis.svc:5000", + BuildNamespace: "felis-build", + KanikoImage: "reg/kaniko:v1", + TrivyImage: "reg/trivy:v1", + BuildCPULimit: "1", + BuildMemLimit: "2Gi", + }}) + if full.KanikoImage != "reg/kaniko:v1" || full.TrivyImage != "reg/trivy:v1" || + full.CPULimit != "1" || full.MemLimit != "2Gi" { + t.Errorf("registry overrides did not reach build.Config: %+v", full) + } + if full.Namespace != "felis-build" || full.RegistryURL != "registry.felis.svc:5000" { + t.Errorf("namespace/registry url must keep projecting: %+v", full) + } +} + // TestNewAPIServerSetsHardenedTimeouts pins the gosec-G112 hardening on every // felis-api listener: the shared factory must bound the header and idle phases // (Slowloris + idle-connection exhaustion) while leaving WriteTimeout UNSET, because diff --git a/docs/deferred-seams.md b/docs/deferred-seams.md index 7c53a6b..cc41e29 100644 --- a/docs/deferred-seams.md +++ b/docs/deferred-seams.md @@ -44,7 +44,19 @@ A grep across `*.md` and `*.go` returns both sets; only the Go ones are seams. apply is under way. - `internal/submit/blobstore.go:40` — the uploads PVC is mounted into felis-api but not into the Kaniko build Pod, so a submitted context is durable at the derived - location without yet being readable by the build that consumes it. + location without yet being readable by the build that consumes it. Audited + 2026-09-22: this is not a missing volume line — a PVC cannot cross namespaces + (uploads live in the control namespace; build Pods run in `felis-build`), so the + fix is a transport, not a mount. The `s3://` lane does not close it either: the + build Job carries no AWS credentials (no env, and the weak SA's token is + deliberately unmounted, so no IAM either). Options on the table: (a) object + storage with credentials plumbed into the build Pod as a per-build Secret plus an + egress allowance; (b) a context-handoff PVC/Job pair in `felis-build` fed from + the API side; (c) a node-local path both sides mount (single-node only, and it + hands an arbitrary Dockerfile a filesystem view — needs its own security review). + Kaniko/Trivy images are external-only by default; `[registry] kaniko_image / + trivy_image / build_cpu_limit / build_mem_limit` now override them for mirrored + or air-gapped installs. ## Built; only its I/O is unverifiable from this repo diff --git a/docs/openapi.yaml b/docs/openapi.yaml index 63ea9c5..a626616 100644 --- a/docs/openapi.yaml +++ b/docs/openapi.yaml @@ -2771,11 +2771,12 @@ paths: post: tags: [backups] operationId: backupNow - summary: Back up a server's world on demand (owner-or-admin; server must be stopped). + summary: Back up a server's data volume on demand (owner-or-admin; server must be stopped). description: >- - Snapshots the server's world into the archive store as a first-class - world_backups row (reason "manual"), restorable later like an inactivity - backup. The world PVC is RWO and held by a running server, so the server must + Snapshots the server's whole data volume (worlds, config, plugins/mods, + jars, libraries — not just world folders) into the archive store as a + first-class world_backups row (reason "manual"), restorable later like an + inactivity backup. A restore replaces the volume with the archive. The world PVC is RWO and held by a running server, so the server must be fully stopped first (409 not_stopped otherwise). The backup runs asynchronously as a Job, so success is 202 (backing_up). x-felis-face: [external] diff --git a/docs/troubleshooting.md b/docs/troubleshooting.md index e910be8..6730585 100644 --- a/docs/troubleshooting.md +++ b/docs/troubleshooting.md @@ -391,6 +391,32 @@ Inspect: kubectl logs -n felis-build job/ ``` +### 8e. Build Pods never start: executor images and air-gapped installs + +The build Job runs Kaniko and Trivy from external registries by default +(`gcr.io/kaniko-project/executor:latest`, `aquasec/trivy:latest`). On a box whose +build namespace cannot reach those registries (the egress policy allows only +DNS, the internal registry and `--package-cidr` mirrors — and an air-gapped box +has no route at all), the Pods sit in `ImagePullBackOff`/`ErrImagePull` and the +build stays `building` until its deadline. Point the overrides at images the box +CAN pull — typically imports into the node's containerd, pushed through the +internal registry — in `felis.toml`: + +```toml +[registry] +url = "registry.felis.svc:5000" +build_namespace = "felis-build" +kaniko_image = "registry.felis.svc:5000/mirror/kaniko:v1.23.2" +trivy_image = "registry.felis.svc:5000/mirror/trivy:0.58.1" +build_cpu_limit = "2" +build_mem_limit = "4Gi" +``` + +then restart `felis-api` (it renders the Job from this config). Unset fields keep +the defaults. Note the user-modpack context topologies are a separate, +still-open seam (see `docs/deferred-seams.md`); this section only makes the +executors reachable. + --- ## 9. Registry push/pull failures (spec §15) @@ -426,6 +452,16 @@ reaps a world only when `now - last_active_at > 15d` (`inactive_15d`); the 15-da deadline is **hard-fixed in code** (only `warn_before` / `retention` / `max_local_bytes` are configurable from `felis.toml [archive]`). +### What a "backup" contains + +A backup tars the server's ENTIRE data volume — the same volume the server mounts +at `/data`: world folders, `server.properties`, plugins/mods, configs, jars, +libraries, logs and cache, not just the `world/` directory. A restore replaces the +volume's contents with the archive (files added since the backup are pruned), so a +restore also rolls config/plugin changes back. Sizes are dominated by +libraries/cache on stock Paper servers (~170MB for a fresh instance before any +world growth) — do not size the archive PVC as if only world data were stored. + ### The backup-before-delete invariant The reap sequence (all [GO-TESTED] hermetically) preserves the world unless a @@ -583,8 +619,8 @@ A full disk is the one failure this platform cannot ride out by itself, because the images exist only in the node's containerd (air-gapped by design), so a GC'd image has no pull source. -Eviction. Every control-plane pod (api, operator, reaper, registry) runs under -the BUILT-IN `system-cluster-critical` PriorityClass (value 2e9). Kubelet's +**Eviction.** Every control-plane pod (api, operator, reaper, registry) runs +under the BUILT-IN `system-cluster-critical` PriorityClass (value 2e9). Kubelet's node-pressure eviction refuses to touch those pods — the log shows *"Eviction manager: cannot evict a critical pod"* for each of them — while game-server pods at the default priority 0 are evicted first. A drill that filled @@ -596,39 +632,32 @@ critical threshold. The built-in class allows preemption (its policy is fixed), so a control-plane pod that cannot fit may preempt a game pod — deliberate: the management plane must be placeable. -The pressure condition clears slowly. After you free space, the node can stay -`DiskPressure:True` for up to ~5 minutes (`--eviction-pressure-transition-period` -defaults to 5m, to stop the condition flapping); pods that need scheduling wait -for it. This is the bulk of the "recovery takes minutes" observation, not a -stuck node. +**The pressure condition clears slowly.** After you free space, the node can stay +`DiskPressure:True` for up to ~5 minutes +(`--eviction-pressure-transition-period` defaults to 5m, to stop the condition +flapping); pods that need scheduling wait for it. This is the bulk of the +"recovery takes minutes" observation, not a stuck node. -But the *game* images can still be GC'd. If game pods were evicted, the kubelet -may garbage-collect their images (unused > 2 minutes under imagefs pressure), and -those pods then sit in `ImagePullBackOff` after recovery — re-import as above -(`docker save felis-limbo:demo felis-lobby:demo | k3s ctr images import -`, then -delete the stuck pods). Verified: both system servers returned to Running in -~25s after the import. +**The images may be gone.** If pods were evicted, the kubelet can garbage-collect +their images (unused > 2 minutes under imagefs pressure). Those pods then sit in +`ImagePullBackOff`/`ErrImagePull` for a tag that plainly exists — +`k3s ctr images ls` shows it missing. Recovery: -Symptoms of the image-GC stage: pods stuck `ImagePullBackOff`/`ErrImagePull` -with `kubectl describe pod` showing a pull attempt for a tag that plainly -exists (`k3s ctr images ls` will show it missing — the kubelet GC removed it -under imagefs pressure). - -Recovery: - -1. Free disk on the node (`df -h /var/lib/rancher`, the biggest consumers are +1. Free disk on the node (`df -h /var/lib/rancher`; the biggest consumers are `k3s ctr images ls -q` and the world/backup PVCs under `/var/lib/rancher/k3s/storage`). -2. Re-import the images by re-running the installer (it rebuilds imports from +2. Re-import the images by re-running the installer (it rebuilds/re-imports from the local Docker store, which the kubelet GC does not touch): `curl -fsSL | sudo bash` (or `sudo felis setup`), then `kubectl -n felis rollout status deploy/felis-api`. -3. Delete now-unschedulable stuck pods so they retry with the re-imported image. +3. Delete the stuck pods so they retry against the re-imported image. -If the API itself is down and you only need the images back without a full -installer run: `docker save felis: | k3s ctr images import -` restores one -image from the Docker store (that store is deliberately a second copy; treat it -as the recovery path, not as free space). +For a single image without a full installer run: +`docker save felis: | k3s ctr images import -` — the Docker store is +deliberately a second copy; treat it as the recovery path, not as free space. +Verified end to end in the drill: `docker save felis-limbo:demo +felis-lobby:demo | k3s ctr images import -` plus pod deletion had both system +servers Running ~25s later. --- @@ -648,6 +677,32 @@ All four mandated metrics have real producers; scrape them when triaging: --- +## 15. Control-plane upgrades, and rolling back a bad one + +There is no in-place updater: an upgrade is re-running the installer +(`curl -fsSL | sudo bash`, or `sudo felis setup`), which +rebuilds/re-imports the image and re-applies the bundle. Two properties of the +control plane matter when you do: + +- Both Deployments use strategy **Recreate** (single replica, no leader election: + two overlapping instances would fight over the same cluster). An upgrade takes + the panel/API down for the rollout window — seconds normally, longer if the new + image still has to be imported. +- If the new pod cannot start (bad tag, missing image), the installer's rollout + wait fails after 180s and prints `kubectl describe` diagnostics: you see + `ErrImagePull`/`ImagePullBackOff` there instead of a silent hang. + +Roll back with: + +``` +kubectl -n felis rollout undo deploy/felis-api +kubectl -n felis rollout status deploy/felis-api +``` + +(the same for `felis-operator` and `registry`). `rollout undo` returns to the +previous ReplicaSet, whose image is normally still on the node; if it was GC'd +(§13b), re-import it first. + ## Quick reference: symptom → section | Symptom | Section | @@ -663,10 +718,12 @@ All four mandated metrics have real producers; scrape them when triaging: | Local password login rejected | §5c | | Internal callers 401 (service token) | §6 | | Link/claim 400/409/412/403/404 | §7 | -| Build push 400 / SA denied / egress hang / Failed | §8 | +| Build push 400 / SA denied / egress hang / Failed / executor ImagePullBackOff | §8, §8e | | Registry push/pull unreachable | §9 | | World deleted unexpectedly / backup skipped | §10 | | Idle auto-stop not firing; player count 0 | §11 | | A config field seems ignored | §12 | | PVC left behind after delete | §13 | +| Node out of disk; pods evicted / ImagePullBackOff | §13b | | Which metric to scrape | §14 | +| Upgrade / roll back a bad control-plane image | §15 | diff --git a/internal/config/config.go b/internal/config/config.go index af73030..b2e557f 100644 --- a/internal/config/config.go +++ b/internal/config/config.go @@ -119,6 +119,19 @@ type K8sConfig struct { type RegistryConfig struct { URL string `toml:"url"` BuildNamespace string `toml:"build_namespace"` + // KanikoImage / TrivyImage / BuildCPULimit / BuildMemLimit override the + // build subsystem's compiled-in defaults (gcr.io/kaniko-project/executor and + // aquasec/trivy, 2 CPU / 4Gi per build container). The defaults assume the + // build namespace can reach those registries; on an air-gapped or mirrored + // install there IS no such reach (the build egress policy allows only DNS, + // the internal registry and explicit package mirrors), so the operator must + // point these at whatever their box can actually pull — typically images + // imported into the node's containerd alongside the felis image. Empty keeps + // the default. + KanikoImage string `toml:"kaniko_image"` + TrivyImage string `toml:"trivy_image"` + BuildCPULimit string `toml:"build_cpu_limit"` + BuildMemLimit string `toml:"build_mem_limit"` // UserUploadsContext is the object-store base under which a user-submitted // modpack's Kaniko build context is pinned. It belongs to the §16 build // subsystem's input domain (the build-context store), introduced by the diff --git a/internal/config/config_test.go b/internal/config/config_test.go index 9156585..d6d69a4 100644 --- a/internal/config/config_test.go +++ b/internal/config/config_test.go @@ -47,6 +47,10 @@ metallb_pool = "192.0.2.200-250" [registry] url = "registry.felis.svc:5000" build_namespace = "felis-build" +kaniko_image = "registry.felis.svc:5000/mirror/kaniko:v1.23.2" +trivy_image = "registry.felis.svc:5000/mirror/trivy:0.58.1" +build_cpu_limit = "1" +build_mem_limit = "2Gi" [archive] store = "tarLocal" @@ -84,6 +88,13 @@ func TestLoadValid(t *testing.T) { if cfg.Archive.S3.Bucket != "felis-backups" { t.Errorf("s3 bucket = %q", cfg.Archive.S3.Bucket) } + if cfg.Registry.KanikoImage != "registry.felis.svc:5000/mirror/kaniko:v1.23.2" || + cfg.Registry.TrivyImage != "registry.felis.svc:5000/mirror/trivy:0.58.1" { + t.Errorf("build image overrides = %q / %q", cfg.Registry.KanikoImage, cfg.Registry.TrivyImage) + } + if cfg.Registry.BuildCPULimit != "1" || cfg.Registry.BuildMemLimit != "2Gi" { + t.Errorf("build resource overrides = %q / %q", cfg.Registry.BuildCPULimit, cfg.Registry.BuildMemLimit) + } } func TestLoadAppliesDefaults(t *testing.T) {