pixa/internal/app/cache_max_bytes_internal_test.go

package app

import (
	"context"
	"database/sql"
	"errors"
	"log/slog"
	"os"
	"path/filepath"
	"strings"
	"testing"

	"github.com/prometheus/client_golang/prometheus"
	"go.uber.org/fx/fxtest"

	"sneak.berlin/go/pixa/internal/config"
	"sneak.berlin/go/pixa/internal/database"
	"sneak.berlin/go/pixa/internal/globals"
	"sneak.berlin/go/pixa/internal/logger"
)

// Static errors returned by the stub free-space probes below.
var (
	errTestStatfsFailed     = errors.New("statfs failed")
	errTestProbeNotExpected = errors.New("probe must not be called")
)

// newTestDB opens an in-memory database with pixa's schema, on one
// connection, as pixad's database has.
func newTestDB(t *testing.T) *sql.DB {
	t.Helper()

	db, err := sql.Open("sqlite", ":memory:")
	if err != nil {
		t.Fatalf("failed to open test db: %v", err)
	}

	db.SetMaxOpenConns(1)

	err = database.ApplyMigrations(context.Background(), db, nil)
	if err != nil {
		t.Fatalf("failed to apply migrations: %v", err)
	}

	t.Cleanup(func() { _ = db.Close() })

	return db
}

// TestCacheMaxBytesFromConfig checks the disk cache limit worked out from
// cache_max_bytes: omitted, it is the default from the free space; 0 turns
// the disk cache off; a positive value is the limit, unchanged.
func TestCacheMaxBytesFromConfig(t *testing.T) {
	t.Parallel()

	const oneGiB = 1 << 30

	cases := []struct {
		name                  string
		cacheMaxBytes         int64
		cacheMaxBytesExplicit bool
		wantMaxBytes          int64
	}{
		{
			name:                  "cache_max_bytes omitted",
			cacheMaxBytes:         0,
			cacheMaxBytesExplicit: false,
			// 75% of the 4 GiB the probe reports free
			wantMaxBytes: 3221225472,
		},
		{
			name:                  "cache_max_bytes: 0",
			cacheMaxBytes:         0,
			cacheMaxBytesExplicit: true,
			wantMaxBytes:          0,
		},
		{
			name:                  "cache_max_bytes: 1 GiB",
			cacheMaxBytes:         oneGiB,
			cacheMaxBytesExplicit: true,
			wantMaxBytes:          oneGiB,
		},
	}

	for _, tc := range cases {
		t.Run(tc.name, func(t *testing.T) {
			t.Parallel()

			cfg := &config.Config{
				StateDir:              t.TempDir(),
				CacheMaxBytes:         tc.cacheMaxBytes,
				CacheMaxBytesExplicit: tc.cacheMaxBytesExplicit,
			}

			got, err := cacheMaxBytes(t.Context(), cfg, newTestDB(t),
				slog.New(slog.DiscardHandler),
				func(string) (uint64, error) { return 4294967296, nil })
			if err != nil {
				t.Fatalf("cacheMaxBytes() error = %v", err)
			}

			t.Logf("MaxBytes = %d", got)

			if got != tc.wantMaxBytes {
				t.Errorf("MaxBytes = %d, want %d", got, tc.wantMaxBytes)
			}
		})
	}
}

// TestDiskCacheOffOnlyForExplicitZeroCacheMaxBytes builds and starts the
// cache once with cache_max_bytes omitted and once with cache_max_bytes:
// 0, and checks by whether the cache directories were created that the
// disk cache is on in the first case and off in the second.
func TestDiskCacheOffOnlyForExplicitZeroCacheMaxBytes(t *testing.T) {
	t.Parallel()

	cases := []struct {
		name                  string
		cacheMaxBytesExplicit bool
		wantDiskCache         bool
	}{
		{name: "cache_max_bytes omitted", cacheMaxBytesExplicit: false, wantDiskCache: true},
		{name: "cache_max_bytes: 0", cacheMaxBytesExplicit: true, wantDiskCache: false},
	}

	for _, tc := range cases {
		t.Run(tc.name, func(t *testing.T) {
			t.Parallel()

			stateDir := t.TempDir()
			cfg := &config.Config{
				SigningKey:            testSigningKey,
				StateDir:              stateDir,
				DBURL:                 "file:" + filepath.Join(stateDir, "state.sqlite3"),
				CacheMaxBytes:         0,
				CacheMaxBytesExplicit: tc.cacheMaxBytesExplicit,
			}

			lc := fxtest.NewLifecycle(t)

			log, err := logger.New(lc, logger.Params{Globals: &globals.Globals{}})
			if err != nil {
				t.Fatalf("logger.New() error = %v", err)
			}

			db, err := database.New(lc, database.Params{Logger: log, Config: cfg})
			if err != nil {
				t.Fatalf("database.New() error = %v", err)
			}

			_, err = newCache(lc, cfg, db, log, prometheus.NewRegistry())
			if err != nil {
				t.Fatalf("newCache() error = %v", err)
			}

			lc.RequireStart()
			t.Cleanup(lc.RequireStop)

			_, err = os.Stat(filepath.Join(stateDir, "cache", "variants"))
			gotDiskCache := err == nil

			if gotDiskCache != tc.wantDiskCache {
				t.Errorf("cache directories created = %v, want %v",
					gotDiskCache, tc.wantDiskCache)
			}
		})
	}
}

// TestDefaultCacheMaxBytesCountsWhatTheCacheHolds verifies that the
// default limit is 75% of the free space plus what the cache already
// holds, so a cache filled to its limit keeps that limit across a
// restart instead of shrinking to 75% of the space left free.
func TestDefaultCacheMaxBytesCountsWhatTheCacheHolds(t *testing.T) {
	t.Parallel()

	cfg := &config.Config{StateDir: t.TempDir()}
	db := newTestDB(t)
	log := slog.New(slog.DiscardHandler)

	// Empty cache, 4 GiB free -> 3 GiB default.
	got, err := cacheMaxBytes(t.Context(), cfg, db, log,
		func(string) (uint64, error) { return 4294967296, nil })
	if err != nil {
		t.Fatalf("cacheMaxBytes returned error: %v", err)
	}

	t.Logf("default for an empty cache with 4 GiB free: %d", got)

	if got != 3221225472 {
		t.Errorf("default for an empty cache = %d, want 3221225472 (75%% of 4 GiB)",
			got)
	}

	// The cache now holds those 3 GiB, which leaves 1 GiB free.
	_, err = db.ExecContext(t.Context(),
		`INSERT INTO variant_content (cache_key, size_bytes) VALUES (?, ?)`,
		"aabbccdd0001", 3221225472,
	)
	if err != nil {
		t.Fatalf("failed to insert variant accounting row: %v", err)
	}

	got, err = cacheMaxBytes(t.Context(), cfg, db, log,
		func(string) (uint64, error) { return 1073741824, nil })
	if err != nil {
		t.Fatalf("cacheMaxBytes returned error: %v", err)
	}

	t.Logf("default for a cache holding 3 GiB with 1 GiB free: %d", got)

	if got != 3221225472 {
		t.Errorf("default for a cache holding 3 GiB with 1 GiB free = %d, "+
			"want 3221225472 (75%% of 1 GiB + 3 GiB)", got)
	}
}

// TestDefaultCacheMaxBytesPropagatesProbeError verifies that a failing
// free-space probe produces an error naming cache_max_bytes, instead of
// a silently wrong default.
func TestDefaultCacheMaxBytesPropagatesProbeError(t *testing.T) {
	t.Parallel()

	_, err := cacheMaxBytes(t.Context(), &config.Config{StateDir: t.TempDir()},
		newTestDB(t), slog.New(slog.DiscardHandler),
		func(string) (uint64, error) { return 0, errTestStatfsFailed })
	if err == nil {
		t.Fatal("probe failure must produce an error, got nil")
	}

	t.Logf("got expected error: %v", err)

	if !strings.Contains(err.Error(), "cache_max_bytes") {
		t.Errorf("error %q does not name cache_max_bytes", err.Error())
	}
}

// TestDefaultCacheMaxBytesProbesTheCacheDirectory verifies that with
// cache_max_bytes omitted the limit is the computed default, and that the
// probe is pointed at <state_dir>/cache/, which must be created first so
// statfs measures the right filesystem.
func TestDefaultCacheMaxBytesProbesTheCacheDirectory(t *testing.T) {
	t.Parallel()

	stateDir := t.TempDir()
	wantCacheDir := filepath.Join(stateDir, "cache")

	var probedPath string

	// 4 GiB free -> 3 GiB default.
	probe := func(path string) (uint64, error) {
		probedPath = path

		info, err := os.Stat(path)
		if err != nil || !info.IsDir() {
			t.Errorf("cache directory %q was not created before probing: info=%v err=%v",
				path, info, err)
		}

		return 4294967296, nil
	}

	got, err := cacheMaxBytes(t.Context(), &config.Config{StateDir: stateDir},
		newTestDB(t), slog.New(slog.DiscardHandler), probe)
	if err != nil {
		t.Fatalf("cacheMaxBytes returned error: %v", err)
	}

	if got != 3221225472 {
		t.Errorf("MaxBytes = %d, want computed default 3221225472", got)
	}

	if probedPath != wantCacheDir {
		t.Errorf("free space probed at %q, want cache directory %q",
			probedPath, wantCacheDir)
	}
}

// TestExplicitCacheMaxBytesIsKept verifies that an explicit
// cache_max_bytes is kept exactly as given and the free-space probe is
// never consulted.
func TestExplicitCacheMaxBytesIsKept(t *testing.T) {
	t.Parallel()

	probe := func(string) (uint64, error) {
		t.Error("free-space probe must not be consulted for explicit values")

		return 0, errTestProbeNotExpected
	}

	cfg := &config.Config{
		StateDir:              t.TempDir(),
		CacheMaxBytes:         1024,
		CacheMaxBytesExplicit: true,
	}

	got, err := cacheMaxBytes(t.Context(), cfg, newTestDB(t),
		slog.New(slog.DiscardHandler), probe)
	if err != nil {
		t.Fatalf("cacheMaxBytes returned error: %v", err)
	}

	if got != 1024 {
		t.Errorf("MaxBytes = %d, want explicit 1024 (no floor, no recompute)", got)
	}
}