dsh-web/internal/api/workspace_concurrency_test.go

package api

import (
	"errors"
	"fmt"
	"io"
	"net/http"
	"net/http/httptest"
	"os"
	"path/filepath"
	"strings"
	"sync"
	"testing"
	"time"

	"git.misaka.ren/m1saka/dsh-web/internal/store"
)

type pausedDownload struct {
	*httptest.ResponseRecorder
	started chan struct{}
	release chan struct{}
	once    sync.Once
}

func (w *pausedDownload) Write(p []byte) (int, error) {
	w.once.Do(func() { close(w.started) })
	<-w.release
	return w.ResponseRecorder.Write(p)
}

func TestSlowDownloadDoesNotHoldLifecycleLock(t *testing.T) {
	a, sid := runtimeTestAPI(t, func(w http.ResponseWriter, r *http.Request) { t.Error("unexpected Docker call") })
	for _, id := range []string{"one", "two"} {
		if err := a.s.AddInstance(store.Instance{ID: id, UID: "owner"}); err != nil {
			t.Fatal(err)
		}
		dir := filepath.Join(a.root, "workspaces/owner/instances", id, "home")
		if err := os.MkdirAll(dir, 0750); err != nil {
			t.Fatal(err)
		}
		if err := os.WriteFile(filepath.Join(dir, "file.txt"), []byte("content"), 0600); err != nil {
			t.Fatal(err)
		}
	}
	w := &pausedDownload{ResponseRecorder: httptest.NewRecorder(), started: make(chan struct{}), release: make(chan struct{})}
	done := make(chan struct{})
	go func() {
		defer close(done)
		a.workspace(w, runtimeRequest("GET", "/api/ws/download?instance=one&path=file.txt", "", sid))
	}()
	defer func() { close(w.release); <-done }()
	select {
	case <-w.started:
	case <-time.After(3 * time.Second):
		t.Fatal("download not started")
	}
	if a.instanceLocks.held() {
		t.Fatal("slow network holds instance lifecycle lock")
	}
	a.readersMu.Lock()
	active := a.workspaceReaders["one"]
	a.readersMu.Unlock()
	if active != 1 {
		t.Fatalf("lease count %d", active)
	}
	other := httptest.NewRecorder()
	otherDone := make(chan struct{})
	go func() {
		defer close(otherDone)
		a.workspace(other, runtimeRequest("GET", "/api/ws/tree?instance=two", "", sid))
	}()
	select {
	case <-otherDone:
	case <-time.After(3 * time.Second):
		t.Fatal("other instance blocked")
	}
	if other.Code != 200 {
		t.Fatalf("other instance: %d", other.Code)
	}
	proxyDone := make(chan struct{})
	proxyResponse := httptest.NewRecorder()
	go func() {
		defer close(proxyDone)
		a.proxy(proxyResponse, runtimeRequest("GET", "/dsh/missing/", "", sid))
	}()
	select {
	case <-proxyDone:
	case <-time.After(3 * time.Second):
		t.Fatal("proxy entry blocked by download")
	}
	if proxyResponse.Code != 404 {
		t.Fatalf("proxy status %d", proxyResponse.Code)
	}
	for _, action := range []string{"restore", "upgrade", "stop", ""} {
		method := "POST"
		if action == "" {
			method = "DELETE"
		}
		response := httptest.NewRecorder()
		url := "/api/instances/one"
		if action != "" {
			url += "/" + action
		}
		body := `{}`
		if action == "upgrade" {
			body = `{"image_id":"sha256:` + strings.Repeat("a", 64) + `"}`
		}
		a.instance(response, runtimeRequest(method, url, body, sid))
		if response.Code != 409 {
			t.Errorf("%s during download: %d %s", action, response.Code, response.Body.String())
		}
	}
}

func TestDirectoryEntryLimit(t *testing.T) {
	dir := t.TempDir()
	for i := 0; i <= maxDirectoryEntries; i++ {
		f, err := os.Create(filepath.Join(dir, fmt.Sprint(i)))
		if err != nil {
			t.Fatal(err)
		}
		f.Close()
	}
	root, err := os.OpenRoot(dir)
	if err != nil {
		t.Fatal(err)
	}
	defer root.Close()
	if _, err = readRootDir(root, "."); !errors.Is(err, errDirectoryLimit) {
		t.Fatalf("limit: %v", err)
	}
	if err = os.Remove(filepath.Join(dir, fmt.Sprint(maxDirectoryEntries))); err != nil {
		t.Fatal(err)
	}
	entries, err := readRootDir(root, ".")
	if err != nil || len(entries) != maxDirectoryEntries {
		t.Fatalf("boundary: %d %v", len(entries), err)
	}
}

type pausedUpload struct {
	started chan struct{}
	release chan struct{}
	once    sync.Once
}

func (r *pausedUpload) Read(p []byte) (int, error) {
	r.once.Do(func() { close(r.started) })
	<-r.release
	return 0, io.EOF
}
func (r *pausedUpload) Close() error { return nil }

func TestSlowUploadDoesNotHoldLifecycleLock(t *testing.T) {
	a, sid := runtimeTestAPI(t, func(w http.ResponseWriter, r *http.Request) { t.Error("unexpected Docker call") })
	if err := a.s.AddInstance(store.Instance{ID: "one", UID: "owner"}); err != nil {
		t.Fatal(err)
	}
	if _, err := a.s.DB.Exec("UPDATE users SET quota=? WHERE id='owner'", 1<<30); err != nil {
		t.Fatal(err)
	}
	if err := os.MkdirAll(filepath.Join(a.root, "workspaces/owner/instances/one/home"), 0750); err != nil {
		t.Fatal(err)
	}
	body := &pausedUpload{started: make(chan struct{}), release: make(chan struct{})}
	r := runtimeRequest("POST", "/api/ws/upload?instance=one", "", sid)
	r.Body = body
	r.Header.Set("Content-Type", "multipart/form-data; boundary=test")
	done := make(chan struct{})
	go func() { defer close(done); a.workspace(httptest.NewRecorder(), r) }()
	defer func() { close(body.release); <-done }()
	select {
	case <-body.started:
	case <-time.After(3 * time.Second):
		t.Fatal("upload not reading body")
	}
	if a.instanceLocks.held() {
		t.Fatal("slow upload holds instance lock")
	}
	if a.userLocks.held() {
		t.Fatal("slow upload holds user write lock")
	}
}

func TestWorkspaceErrorResponseReleasesLocks(t *testing.T) {
	a, sid := runtimeTestAPI(t, func(w http.ResponseWriter, r *http.Request) { t.Error("unexpected Docker call") })
	if err := a.s.AddInstance(store.Instance{ID: "one", UID: "owner"}); err != nil {
		t.Fatal(err)
	}
	if err := os.MkdirAll(filepath.Join(a.root, "workspaces/owner/instances/one/home"), 0750); err != nil {
		t.Fatal(err)
	}
	w := &pausedDownload{ResponseRecorder: httptest.NewRecorder(), started: make(chan struct{}), release: make(chan struct{})}
	done := make(chan struct{})
	go func() {
		defer close(done)
		a.workspace(w, runtimeRequest("GET", "/api/ws/tree?instance=one&path=missing", "", sid))
	}()
	defer func() { close(w.release); <-done }()
	select {
	case <-w.started:
	case <-time.After(3 * time.Second):
		t.Fatal("response not started")
	}
	if a.userLocks.held() {
		t.Fatal("error response holds user write lock")
	}
	if a.instanceLocks.held() {
		t.Fatal("error response holds instance lock")
	}
	a.readersMu.Lock()
	leases := len(a.workspaceReaders)
	a.readersMu.Unlock()
	if leases != 0 {
		t.Fatal("response retains lease")
	}
}

// A restore or upgrade holds its instance and user locks for minutes; that
// must never block file operations or lifecycle actions of other users.
func TestLongMutationDoesNotBlockOtherUsers(t *testing.T) {
	a, _ := runtimeTestAPI(t, func(w http.ResponseWriter, r *http.Request) {
		switch {
		case r.Method == "POST" && strings.HasSuffix(r.URL.Path, "/stop"):
			w.WriteHeader(http.StatusNoContent)
		case r.Method == "GET" && strings.HasSuffix(r.URL.Path, "/json"):
			writeJSON(w, map[string]any{"Id": "cid-two", "State": map[string]any{"Status": "exited", "Running": false}})
		default:
			t.Errorf("unexpected Docker call %s %s", r.Method, r.URL.Path)
		}
	})
	if err := a.s.CreateUser(store.User{ID: "other", Username: "other"}, "unused"); err != nil {
		t.Fatal(err)
	}
	otherSid, _, err := a.s.Session("other")
	if err != nil {
		t.Fatal(err)
	}
	registerTestAccess(t, a, otherSid)
	if err := a.s.AddInstance(store.Instance{ID: "one", UID: "owner"}); err != nil {
		t.Fatal(err)
	}
	if err := a.s.AddInstance(store.Instance{ID: "two", UID: "other", ContainerID: "cid-two", Status: "running", Created: time.Now()}); err != nil {
		t.Fatal(err)
	}
	for _, dir := range []string{"workspaces/owner/instances/one/home", "workspaces/other/instances/two/home"} {
		if err := os.MkdirAll(filepath.Join(a.root, dir), 0750); err != nil {
			t.Fatal(err)
		}
	}
	// Simulate a mutation paused mid-flight (restore/upgrade state).
	inst := a.instanceLocks.Acquire("one")
	defer inst.Release()
	user := a.userLocks.Acquire("owner")
	defer user.Release()

	treeDone := make(chan *httptest.ResponseRecorder, 1)
	go func() {
		w := httptest.NewRecorder()
		a.workspace(w, runtimeRequest("GET", "/api/ws/tree?instance=two", "", otherSid))
		treeDone <- w
	}()
	select {
	case w := <-treeDone:
		if w.Code != 200 {
			t.Fatalf("other user tree: %d %s", w.Code, w.Body.String())
		}
	case <-time.After(3 * time.Second):
		t.Fatal("other user file operation blocked by long mutation")
	}
	stopDone := make(chan *httptest.ResponseRecorder, 1)
	go func() {
		w := httptest.NewRecorder()
		a.instance(w, runtimeRequest("POST", "/api/instances/two/stop", "", otherSid))
		stopDone <- w
	}()
	select {
	case w := <-stopDone:
		if w.Code != 200 {
			t.Fatalf("other instance stop: %d %s", w.Code, w.Body.String())
		}
	case <-time.After(3 * time.Second):
		t.Fatal("other instance lifecycle blocked by long mutation")
	}
	// The same user's mutation is still serialized by the user lock.
	blocked := make(chan struct{})
	go func() {
		user := a.userLocks.Acquire("owner")
		user.Release()
		close(blocked)
	}()
	select {
	case <-blocked:
		t.Fatal("owner lock not held during mutation")
	case <-time.After(300 * time.Millisecond):
	}
}