From d04523accdd24d04640ad8de057e36ae06e7efd3 Mon Sep 17 00:00:00 2001 From: Josh Creek <8179928+jcreek@users.noreply.github.com> Date: Tue, 1 Sep 2026 19:10:10 +0100 Subject: [PATCH] feat(multiplayer): package observability resources --- deploy/observability/kustomization.yaml | 6 ++++++ multiplayer-next.md | 2 +- scripts/verify_observability_manifests.py | 9 +++++++++ 3 files changed, 16 insertions(+), 1 deletion(-) create mode 100644 deploy/observability/kustomization.yaml diff --git a/deploy/observability/kustomization.yaml b/deploy/observability/kustomization.yaml new file mode 100644 index 00000000..b1131326 --- /dev/null +++ b/deploy/observability/kustomization.yaml @@ -0,0 +1,6 @@ +apiVersion: kustomize.config.k8s.io/v1beta1 +kind: Kustomization +resources: + - prometheus-rules.yaml + - prometheus-service-monitor.yaml + - prometheus-allocator-service-monitor.yaml diff --git a/multiplayer-next.md b/multiplayer-next.md index b4fad52e..e160b14f 100644 --- a/multiplayer-next.md +++ b/multiplayer-next.md @@ -1251,7 +1251,7 @@ the local/CI/community transport, not a silent production fallback. | 8.49 `[D:8.25,8.26,8.28,8.29,8.30,8.31,8.35,8.36]` | **IN PROGRESS.** `scripts/verify_kind_agones.sh` creates a disposable kind cluster, installs pinned Agones, loads the real `game-server` image, applies the Fleet in an explicitly separate Agones-only supervisor/UDP readiness mode, and verifies readiness plus allocation of a dynamic UDP endpoint; `.github/workflows/agones-integration.yml` runs it for infrastructure changes and on demand | The cloud-free runner is committed and fails clearly when Docker/kind/Helm are unavailable. CI/live evidence for production control-plane registration, roster/no-show, both readiness stages, races, multi-match node, result-pending reconciliation, drain, and rollback remains open | | 8.50 `[D:8.25,8.37,8.43,8.49]` | **IN PROGRESS.** `make verify-chaos-recovery` provides a disposable PostgreSQL + real testkit API + real maintenance flow: it restarts the API, injects a stale allocation, and verifies no-penalty requeue plus a durable participant-targeted lifecycle event | The API-restart/stalled-allocation slice is implemented and documented; 100 ms RTT/jitter/loss, matcher/client restart, game-pod death, node drain, Redis failover, control-plane loss, and live chaos evidence remain | | 8.51 `[D:8.17,8.18,8.30,8.31,8.45]` | **IN PROGRESS.** The opt-in `make verify-multiplayer-load` gate drives 10,000 real HTTP queue-create requests through the service with 256 in flight and records p95/p99, plus 100 concurrent proposal formations through the real matcher/domain path; the handler and in-process ownership boundary are exercised without weakening normal tests | Local API load passes at p95 <250 ms in normal and race runs, and the matcher forms 100 unique proposals; PostgreSQL saturation, durable matcher fencing under load, forecast launch concurrency x2, and replica scaling remain live infrastructure gates | -| 8.52 `[D:8.32,8.34,8.45,8.51]` | **IN PROGRESS.** Allocator supports both an opt-in per-replica fixed-window quota (`--allocation-quota` / `--allocation-quota-window`) and an optional PostgreSQL-backed EU/NA quota table consumed inside the serializable allocation transaction before any provider call; idempotent replays do not double-count. The allocator now exposes bounded EU/NA Prometheus counters at an explicit `/metrics` listener (`--metrics-addr`), including quota denials; the checked-in rule warns on regional denial activity, and hardened Kubernetes Deployment/Service/ServiceMonitor/PDB/placement resources provide the provisioning, health, rollout, disruption, discovery, and failure-domain-spreading contract | Normal/race/vet tests cover local quota exhaustion, window reset, region isolation, invalid input, atomic concurrent consumption, bounded metrics labels, read-only endpoint behavior, and hardened deployment/network policy/lifecycle/PDB/placement invariants; migration/SQL and manifest coverage define the shared quota/metrics boundaries; real image digest/secrets, measured regional cost model, threshold tuning, and denial-of-wallet rehearsal remain | +| 8.52 `[D:8.32,8.34,8.45,8.51]` | **IN PROGRESS.** Allocator supports both an opt-in per-replica fixed-window quota (`--allocation-quota` / `--allocation-quota-window`) and an optional PostgreSQL-backed EU/NA quota table consumed inside the serializable allocation transaction before any provider call; idempotent replays do not double-count. The allocator now exposes bounded EU/NA Prometheus counters at an explicit `/metrics` listener (`--metrics-addr`), including quota denials; the checked-in rule warns on regional denial activity, and hardened Kubernetes Deployment/Service/ServiceMonitor/PDB/placement resources plus an observability Kustomization provide the provisioning, health, rollout, disruption, discovery, and failure-domain-spreading contract | Normal/race/vet tests cover local quota exhaustion, window reset, region isolation, invalid input, atomic concurrent consumption, bounded metrics labels, read-only endpoint behavior, and hardened deployment/network policy/lifecycle/PDB/placement invariants; migration/SQL and manifest coverage define the shared quota/metrics boundaries; real image digest/secrets, measured regional cost model, threshold tuning, and denial-of-wallet rehearsal remain | | 8.53 `[D:7.8,8.13,8.38,8.45,8.46,8.48,8.49,8.50,8.51,8.52]` | **IN PROGRESS.** `scripts/verify_release_gate.py` provides a fail-closed promotion check for the ordered development → internal → casual canary → casual → provisional ranked → ranked stages, requiring an evidence report for SLO, security, cost, rollback, EU+NA playtests, and both legacy gates | Validator and adversarial tests cover skipped stages, unknown stages, missing gates, non-boolean gate values, and blank release IDs; the actual reports, production rollback rehearsal, regional playtests, and live promotion remain open | Implementation invariants for every task above: diff --git a/scripts/verify_observability_manifests.py b/scripts/verify_observability_manifests.py index 957ab477..a7343b7e 100644 --- a/scripts/verify_observability_manifests.py +++ b/scripts/verify_observability_manifests.py @@ -14,12 +14,21 @@ DEFAULT_DIRECTORY = ROOT / "deploy" / "observability" def verify(directory: Path, service_path: Path) -> None: + kustomization = (directory / "kustomization.yaml").read_text() monitor = (directory / "prometheus-service-monitor.yaml").read_text() rules = (directory / "prometheus-rules.yaml").read_text() service = service_path.read_text() allocator_monitor = (directory / "prometheus-allocator-service-monitor.yaml").read_text() allocator_service = (ROOT / "deploy/k8s/base/allocator-service.yaml").read_text() + for resource in ( + "prometheus-rules.yaml", + "prometheus-service-monitor.yaml", + "prometheus-allocator-service-monitor.yaml", + ): + if resource not in kustomization: + raise ValueError(f"observability Kustomization omits {resource}") + if "kind: ServiceMonitor" not in monitor: raise ValueError("ServiceMonitor resource is missing") if "apiVersion: monitoring.coreos.com/v1" not in monitor: