scrabble-game/loadtest/cmd/loadtest/main.go

// Command loadtest is the reusable load harness. It seeds a large account
// population with pre-created sessions directly in the backend Postgres, then drives
// virtual players through the gateway edge protocol (real games assembled via
// invitations, legal moves generated locally by the embedded solver), and a
// gateway-hammer that verifies the rate limiter. It prints a trip-report summary.
//
// Run it as a one-shot container on the contour's docker network so it reaches
// postgres:5432 and gateway:8081 directly:
//
//	docker run --rm --network scrabble-internal \
//	  -e POSTGRES_PASSWORD=... -v /path/to/dawg:/dawg scrabble-loadtest run
package main

import (
	"context"
	"errors"
	"flag"
	"fmt"
	"log/slog"
	"os"
	"os/signal"
	"strconv"
	"strings"
	"syscall"
	"time"

	"scrabble/loadtest/internal/edge"
	"scrabble/loadtest/internal/moves"
	"scrabble/loadtest/internal/report"
	"scrabble/loadtest/internal/scenario"
	"scrabble/loadtest/internal/seed"
)

func main() {
	log := slog.New(slog.NewTextHandler(os.Stderr, &slog.HandlerOptions{Level: slog.LevelInfo}))
	if len(os.Args) < 2 {
		usage()
		os.Exit(2)
	}
	ctx, stop := signal.NotifyContext(context.Background(), os.Interrupt, syscall.SIGTERM)
	defer stop()

	var err error
	switch os.Args[1] {
	case "run":
		err = cmdRun(ctx, log, os.Args[2:])
	case "cleanup":
		err = cmdCleanup(ctx, log, os.Args[2:])
	default:
		usage()
		os.Exit(2)
	}
	if err != nil {
		log.Error("loadtest failed", "cmd", os.Args[1], "err", err)
		os.Exit(1)
	}
}

func usage() {
	fmt.Fprintln(os.Stderr, "usage: loadtest <run|cleanup> [flags]")
	fmt.Fprintln(os.Stderr, "  run      seed accounts, drive the realistic ramp + gateway-hammer, print the report")
	fmt.Fprintln(os.Stderr, "  cleanup  delete everything the harness seeded (matched by marker)")
}

func cmdRun(ctx context.Context, log *slog.Logger, args []string) error {
	fs := flag.NewFlagSet("run", flag.ExitOnError)
	gateway := fs.String("gateway", env("LOADTEST_GATEWAY_URL", "http://gateway:8081"), "gateway base URL")
	dsn := fs.String("dsn", env("LOADTEST_DSN", defaultDSN()), "backend Postgres DSN")
	dawgDir := fs.String("dawg", env("LOADTEST_DAWG_DIR", "/dawg"), "directory holding the committed *.dawg files")
	durable := fs.Int("durable", 10000, "durable accounts to seed")
	guest := fs.Int("guest", 1000, "guest accounts to seed")
	stepsStr := fs.String("steps", "50,200,500", "comma-separated concurrent-player ramp steps")
	stepDur := fs.Duration("step-dur", 12*time.Minute, "hold time per ramp step")
	gpp := fs.Int("games-per-player", 0, "target concurrent games per player (0 => random 3..5)")
	tick := fs.Duration("tick", 800*time.Millisecond, "per-player operation cadence")
	secProb := fs.Float64("secondary-prob", 0.08, "chance per tick of a non-move operation")
	hammerWorkers := fs.Int("hammer-workers", 20, "gateway-hammer concurrent callers (0 disables)")
	hammerDur := fs.Duration("hammer-dur", 15*time.Second, "gateway-hammer duration")
	reset := fs.Bool("reset", false, "delete prior harness rows before seeding")
	doCleanup := fs.Bool("cleanup", false, "delete harness rows after the run")
	if err := fs.Parse(args); err != nil {
		return err
	}
	steps, err := parseSteps(*stepsStr)
	if err != nil {
		return err
	}

	reg, err := moves.Open(*dawgDir)
	if err != nil {
		return err
	}
	defer reg.Close()

	sd, err := seed.New(ctx, *dsn)
	if err != nil {
		return err
	}
	defer sd.Close()

	if *reset {
		n, err := sd.Cleanup(ctx)
		if err != nil {
			return err
		}
		log.Info("reset", "accounts_removed", n)
	}

	log.Info("seeding", "durable", *durable, "guest", *guest)
	pool, err := sd.Seed(ctx, *durable, *guest)
	if err != nil {
		return err
	}
	log.Info("seeded", "durable", len(pool.Durables), "guest", len(pool.Guests))

	rec := report.New()
	drv := scenario.NewDriver(edge.New(*gateway), reg, rec, log)
	cfg := scenario.RealisticConfig{
		Steps: steps, StepDur: *stepDur, GamesPerPlayer: *gpp,
		Tick: *tick, SecondaryProb: *secProb,
	}
	if err := drv.RunRealistic(ctx, pool, cfg); err != nil && !errors.Is(err, context.Canceled) {
		return err
	}

	if *hammerWorkers > 0 && ctx.Err() == nil && len(pool.Durables) > 0 {
		drv.Hammer(ctx, pool.Durables[0], scenario.HammerConfig{Workers: *hammerWorkers, Duration: *hammerDur})
	}

	fmt.Println("\n==== R2 load-test report ====")
	fmt.Println(rec.Summary())

	if *doCleanup {
		n, err := sd.Cleanup(context.WithoutCancel(ctx))
		if err != nil {
			return err
		}
		log.Info("cleanup", "accounts_removed", n)
	}
	return nil
}

func cmdCleanup(ctx context.Context, log *slog.Logger, args []string) error {
	fs := flag.NewFlagSet("cleanup", flag.ExitOnError)
	dsn := fs.String("dsn", env("LOADTEST_DSN", defaultDSN()), "backend Postgres DSN")
	if err := fs.Parse(args); err != nil {
		return err
	}
	sd, err := seed.New(ctx, *dsn)
	if err != nil {
		return err
	}
	defer sd.Close()
	n, err := sd.Cleanup(ctx)
	if err != nil {
		return err
	}
	log.Info("cleanup", "accounts_removed", n)
	return nil
}

// defaultDSN builds the backend Postgres DSN from the standard POSTGRES_* env the
// contour uses, pinning the backend schema.
func defaultDSN() string {
	return fmt.Sprintf("postgres://%s:%s@%s:5432/%s?sslmode=disable&search_path=backend",
		env("POSTGRES_USER", "scrabble"), os.Getenv("POSTGRES_PASSWORD"),
		env("POSTGRES_HOST", "postgres"), env("POSTGRES_DB", "scrabble"))
}

// env returns the environment variable key or def when it is unset/empty.
func env(key, def string) string {
	if v := os.Getenv(key); v != "" {
		return v
	}
	return def
}

// parseSteps parses a comma-separated list of positive ramp step sizes.
func parseSteps(s string) ([]int, error) {
	parts := strings.Split(s, ",")
	steps := make([]int, 0, len(parts))
	for _, p := range parts {
		n, err := strconv.Atoi(strings.TrimSpace(p))
		if err != nil || n <= 0 {
			return nil, fmt.Errorf("invalid ramp steps %q", s)
		}
		steps = append(steps, n)
	}
	if len(steps) == 0 {
		return nil, fmt.Errorf("no ramp steps")
	}
	return steps, nil
}