feat(queue): replace PocketBase polling with Asynq + Redis
Some checks failed
CI / Docker / caddy (pull_request) Failing after 50s
CI / Check ui (pull_request) Successful in 1m5s
Release / Check ui (push) Successful in 45s
Release / Test backend (push) Successful in 1m29s
CI / Docker / ui (pull_request) Successful in 1m28s
Release / Docker / backend (push) Successful in 3m14s
CI / Test backend (pull_request) Failing after 42s
CI / Docker / backend (pull_request) Has been skipped
CI / Docker / runner (pull_request) Has been skipped
Release / Docker / caddy (push) Successful in 6m48s
Release / Docker / ui (push) Successful in 2m8s
Release / Docker / runner (push) Successful in 2m51s
Release / Upload source maps (push) Failing after 53s
Release / Gitea Release (push) Has been skipped

Introduce a Redis-backed Asynq task queue so the runner consumes TTS
jobs pushed by the backend instead of polling PocketBase.

- backend/internal/asynqqueue: Producer and Consumer wrappers
- backend/internal/runner: AsynqRunner mux, per-instance Prometheus
  registry (fixes duplicate-collector panic in tests), redisConnOpt
- backend/internal/config: REDIS_ADDR / REDIS_PASSWORD env vars
- backend/cmd/{backend,runner}/main.go: wire Redis when env set; fall
  back to legacy poll mode when unset
- Caddyfile: caddy-l4 TCP proxy for redis.libnovel.cc:6380 → homelab
- caddy/Dockerfile: add --with github.com/mholt/caddy-l4
- docker-compose.yml: Caddy exposes 6380, backend/runner get Redis env
- homelab/runner/docker-compose.yml: Redis sidecar, runner depends_on
- homelab/otel/grafana: Grafana dashboards (backend, catalogue, runner)
  and alerting rules / contact-points provisioning
This commit is contained in:
Admin
2026-03-28 14:32:40 +05:00
parent 98e4a87432
commit fe1a933fd0
21 changed files with 1869 additions and 47 deletions

View File

@@ -34,6 +34,7 @@ import (
"github.com/libnovel/backend/internal/pockettts"
"github.com/libnovel/backend/internal/scraper"
"github.com/libnovel/backend/internal/taskqueue"
"github.com/prometheus/client_golang/prometheus"
)
// Config tunes the runner behaviour.
@@ -41,6 +42,7 @@ type Config struct {
// WorkerID uniquely identifies this runner instance in PocketBase records.
WorkerID string
// PollInterval is how often the runner checks for new tasks.
// Only used in PocketBase-polling mode (RedisAddr == "").
PollInterval time.Duration
// MaxConcurrentScrape limits simultaneous book-scrape goroutines.
MaxConcurrentScrape int
@@ -50,9 +52,11 @@ type Config struct {
OrchestratorWorkers int
// HeartbeatInterval is how often active tasks PATCH their heartbeat_at
// timestamp to signal they are still alive. Defaults to 30s when 0.
// Only used in PocketBase-polling mode.
HeartbeatInterval time.Duration
// StaleTaskThreshold is how old a heartbeat must be (or absent) before the
// task is considered orphaned and reset to pending. Defaults to 2m when 0.
// Only used in PocketBase-polling mode.
StaleTaskThreshold time.Duration
// CatalogueRefreshInterval is how often the runner walks the full catalogue,
// scrapes per-book metadata, downloads covers, and re-indexes everything in
@@ -66,6 +70,15 @@ type Config struct {
// MetricsAddr is the HTTP listen address for the /metrics endpoint.
// Defaults to ":9091". Set to "" to disable.
MetricsAddr string
// RedisAddr is the address of the Redis instance used for Asynq task
// dispatch. When set the runner switches from PocketBase-polling mode to
// Asynq ServeMux mode (immediate task delivery, no polling).
// Supports plain "host:port" or a full "rediss://..." URL.
// When empty the runner falls back to PocketBase polling.
RedisAddr string
// RedisPassword is the Redis AUTH password.
// Not required when RedisAddr is a full URL that includes credentials.
RedisPassword string
}
// Dependencies are the external services the runner depends on.
@@ -99,6 +112,8 @@ type Runner struct {
cfg Config
deps Dependencies
metricsRegistry *prometheus.Registry
// Atomic task counters — read by /metrics without locking.
tasksRunning atomic.Int64
tasksCompleted atomic.Int64
@@ -139,15 +154,18 @@ func New(cfg Config, deps Dependencies) *Runner {
if deps.SearchIndex == nil {
deps.SearchIndex = meili.NoopClient{}
}
return &Runner{cfg: cfg, deps: deps, startedAt: time.Now()}
return &Runner{cfg: cfg, deps: deps, startedAt: time.Now(), metricsRegistry: prometheus.NewRegistry()}
}
// Run starts the poll loop and the metrics HTTP server, blocking until ctx is
// cancelled.
// Run starts the worker loop and the metrics HTTP server, blocking until ctx
// is cancelled.
//
// When cfg.RedisAddr is set the runner uses Asynq (immediate task delivery).
// Otherwise it falls back to PocketBase polling (legacy mode).
func (r *Runner) Run(ctx context.Context) error {
r.deps.Log.Info("runner: starting",
"worker_id", r.cfg.WorkerID,
"poll_interval", r.cfg.PollInterval,
"mode", r.mode(),
"max_scrape", r.cfg.MaxConcurrentScrape,
"max_audio", r.cfg.MaxConcurrentAudio,
"catalogue_refresh_interval", r.cfg.CatalogueRefreshInterval,
@@ -164,6 +182,23 @@ func (r *Runner) Run(ctx context.Context) error {
}()
}
if r.cfg.RedisAddr != "" {
return r.runAsynq(ctx)
}
return r.runPoll(ctx)
}
// mode returns a short string describing the active dispatch mode.
func (r *Runner) mode() string {
if r.cfg.RedisAddr != "" {
return "asynq"
}
return "poll"
}
// runPoll is the legacy PocketBase-polling dispatch loop.
// Used when cfg.RedisAddr is empty.
func (r *Runner) runPoll(ctx context.Context) error {
scrapeSem := make(chan struct{}, r.cfg.MaxConcurrentScrape)
audioSem := make(chan struct{}, r.cfg.MaxConcurrentAudio)
var wg sync.WaitGroup
@@ -181,6 +216,8 @@ func (r *Runner) Run(ctx context.Context) error {
r.deps.Log.Info("runner: skipping initial catalogue refresh (RUNNER_SKIP_INITIAL_CATALOGUE_REFRESH=true)")
}
r.deps.Log.Info("runner: poll mode active", "poll_interval", r.cfg.PollInterval)
// Run one poll immediately on startup, then on each tick.
for {
r.poll(ctx, scrapeSem, audioSem, &wg)