jordan/rdev
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: Use FQDN for k8s service hostnames and remove broken commonLabels

Browse Source 
Short-form DNS names (e.g. postgres.databases.svc) fail to resolve in
new pods due to k8s DNS search domain limitations. Switch all service
hostnames to FQDNs (*.svc.cluster.local).

Remove commonLabels from kustomization.yaml — it injected labels into
all selectors including NetworkPolicy egress rules (blocking DNS to
CoreDNS) and Deployment selectors (causing immutability errors).

Add OTEL_EXPORTER_OTLP_ENDPOINT env var to deployment YAML so the
telemetry collector endpoint uses the FQDN without requiring a binary
rebuild.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
This commit is contained in:
jordan 2026-01-31 20:46:04 -07:00
parent 8282d60c69
commit f6ced22e06
7 changed files with 17 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
cmd/rdev-api/config.go
View File

@ -63,13 +63,13 @@ type InfraConfig struct {
WoodpeckerWebhookSecret string
// CockroachDB provisioner (for project databases)
CRDBHost string // e.g., "cockroachdb-public.databases.svc"
CRDBHost string // e.g., "cockroachdb-public.databases.svc.cluster.local"
CRDBPort int // e.g., 26257
CRDBUser string // e.g., "root" (insecure mode)
CRDBSSLMode string // e.g., "disable" (insecure) or "verify-full" (production)
// Redis provisioner (for project cache)
RedisHost string // e.g., "redis.threesix.svc"
RedisHost string // e.g., "redis.databases.svc.cluster.local"
RedisPort int // e.g., 6379
RedisPassword string // admin password for ACL management
}
@ -77,7 +77,7 @@ type InfraConfig struct {
func loadConfig() Config {
return Config{
Port: envutil.GetEnvInt("PORT", 8080),
DBHost: envutil.GetEnv("DB_HOST", "postgres.databases.svc"),
DBHost: envutil.GetEnv("DB_HOST", "postgres.databases.svc.cluster.local"),
DBPort: envutil.GetEnvInt("DB_PORT", 5432),
DBUser: envutil.GetEnv("DB_USER", "appuser"),
DBPassword: os.Getenv("DB_PASSWORD"),
@ -154,11 +154,11 @@ func loadInfraConfig(ctx context.Context, store port.CredentialStore, cfg Config
WoodpeckerWebhookSecret: getOrFallback(domain.CredKeyWoodpeckerWebhookSecret, cfg.WoodpeckerWebhookSecret),
// CockroachDB and Redis provisioners (env-only for now)
CRDBHost: os.Getenv("CRDB_HOST"), // e.g., "cockroachdb-public.databases.svc"
CRDBHost: os.Getenv("CRDB_HOST"), // e.g., "cockroachdb-public.databases.svc.cluster.local"
CRDBPort: envutil.GetEnvInt("CRDB_PORT", 26257),
CRDBUser: envutil.GetEnv("CRDB_USER", "root"),
CRDBSSLMode: envutil.GetEnv("CRDB_SSL_MODE", "disable"),
RedisHost: os.Getenv("REDIS_HOST"), // e.g., "redis.threesix.svc"
RedisHost: os.Getenv("REDIS_HOST"), // e.g., "redis.databases.svc.cluster.local"
RedisPort: envutil.GetEnvInt("REDIS_PORT", 6379),
RedisPassword: os.Getenv("REDIS_PASSWORD"),
}

3
deployments/k8s/base/kustomization.yaml
View File

@ -27,6 +27,3 @@ resources:
- pdb.yaml
- network-policy.yaml
commonLabels:
app.kubernetes.io/managed-by: kustomize
app.kubernetes.io/part-of: rdev

9
deployments/k8s/base/rdev-api.yaml
View File

@ -69,7 +69,7 @@ spec:
- name: PORT
value: "8080"
- name: DB_HOST
value: "postgres.databases.svc"
value: "postgres.databases.svc.cluster.local"
- name: DB_PORT
value: "5432"
- name: DB_USER
@ -123,7 +123,7 @@ spec:
key: WOODPECKER_API_TOKEN
# CockroachDB for project database provisioning
- name: CRDB_HOST
value: "cockroachdb-public.databases.svc"
value: "cockroachdb-public.databases.svc.cluster.local"
- name: CRDB_PORT
value: "26257"
- name: CRDB_USER
@ -132,7 +132,7 @@ spec:
value: "disable"
# Redis for project cache provisioning
- name: REDIS_HOST
value: "redis.databases.svc"
value: "redis.databases.svc.cluster.local"
- name: REDIS_PORT
value: "6379"
- name: REDIS_PASSWORD
@ -140,6 +140,9 @@ spec:
secretKeyRef:
name: redis-credentials
key: REDIS_PASSWORD
# OpenTelemetry
- name: OTEL_EXPORTER_OTLP_ENDPOINT
value: "otel-collector.observability.svc.cluster.local:4317"
imagePullSecrets:
- name: ghcr-secret

2
internal/adapter/cockroach/provisioner.go
View File

@ -27,7 +27,7 @@ type Provisioner struct {
// Config holds CockroachDB provisioner configuration.
type Config struct {
Host string // e.g., "cockroachdb-public.databases.svc"
Host string // e.g., "cockroachdb-public.databases.svc.cluster.local"
Port int // e.g., 26257
User string // e.g., "root" (for insecure mode)
SSLMode string // e.g., "disable" (for insecure mode)

2
internal/db/postgres.go
View File

@ -30,7 +30,7 @@ type Config struct {
// DefaultConfig returns config from environment defaults.
func DefaultConfig() Config {
return Config{
Host: "postgres.databases.svc",
Host: "postgres.databases.svc.cluster.local",
Port: 5432,
User: "appuser",
Password: "",

6
internal/telemetry/telemetry.go
View File

@ -4,7 +4,7 @@
// Traces are exported to an OpenTelemetry collector (e.g., otel-collector in k8s).
//
// Configuration via environment variables:
// - OTEL_EXPORTER_OTLP_ENDPOINT: Collector endpoint (default: otel-collector.observability.svc:4317)
// - OTEL_EXPORTER_OTLP_ENDPOINT: Collector endpoint (default: otel-collector.observability.svc.cluster.local:4317)
// - OTEL_SERVICE_NAME: Service name for traces (default: rdev-api)
// - OTEL_SERVICE_VERSION: Service version (default: unknown)
// - OTEL_SERVICE_NAMESPACE: Namespace (default: rdev)
@ -33,7 +33,7 @@ import (
// Config holds telemetry configuration.
type Config struct {
// Endpoint is the OTLP collector endpoint (gRPC).
// Default: otel-collector.observability.svc:4317
// Default: otel-collector.observability.svc.cluster.local:4317
Endpoint string
// ServiceName identifies this service in traces.
@ -63,7 +63,7 @@ type Config struct {
// DefaultConfig returns configuration with defaults applied.
func DefaultConfig() Config {
return Config{
Endpoint: envutil.GetEnv("OTEL_EXPORTER_OTLP_ENDPOINT", "otel-collector.observability.svc:4317"),
Endpoint: envutil.GetEnv("OTEL_EXPORTER_OTLP_ENDPOINT", "otel-collector.observability.svc.cluster.local:4317"),
ServiceName: envutil.GetEnv("OTEL_SERVICE_NAME", "rdev-api"),
ServiceVersion: envutil.GetEnv("OTEL_SERVICE_VERSION", "unknown"),
ServiceNamespace: envutil.GetEnv("OTEL_SERVICE_NAMESPACE", "rdev"),

2
internal/telemetry/telemetry_test.go
View File

@ -21,7 +21,7 @@ func TestDefaultConfig(t *testing.T) {
cfg := DefaultConfig()
if cfg.Endpoint != "otel-collector.observability.svc:4317" {
if cfg.Endpoint != "otel-collector.observability.svc.cluster.local:4317" {
t.Errorf("expected default endpoint, got %s", cfg.Endpoint)
}
if cfg.ServiceName != "rdev-api" {