Compare commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
21e40a1774 | ||
|
|
bdc844872d | ||
|
|
299b6dc0bb | ||
|
|
9589e58ce6 |
@@ -134,6 +134,15 @@ answers on the port, gpu-turnstile just uses it instead of spawning
|
|||||||
instance already holds the port when you open the desktop app, the
|
instance already holds the port when you open the desktop app, the
|
||||||
desktop's server is the one that fails to bind.
|
desktop's server is the one that fails to bind.
|
||||||
|
|
||||||
|
One catch when gpu-turnstile runs as a service: the sandboxed service
|
||||||
|
account may not enter your user profile, so a ComfyUI install under
|
||||||
|
`C:\Users\...` (or `/home/...`) fails with "Access is denied".
|
||||||
|
`--install-service` fixes that automatically — it grants
|
||||||
|
`NT SERVICE\gpu-turnstile` recursive access to `COMFY_DIR` on Windows and
|
||||||
|
adds a `BindPaths=` to the systemd unit on Linux. Re-run it after changing
|
||||||
|
`COMFY_DIR`; or grant by hand from an admin shell:
|
||||||
|
`icacls "<COMFY_DIR>" /grant "NT SERVICE\gpu-turnstile:(OI)(CI)M" /T`.
|
||||||
|
|
||||||
## Game detection
|
## Game detection
|
||||||
|
|
||||||
Want to game on the same GPU without Ollama/ComfyUI squatting on the VRAM?
|
Want to game on the same GPU without Ollama/ComfyUI squatting on the VRAM?
|
||||||
|
|||||||
@@ -159,6 +159,14 @@ files are flagged in the startup log.
|
|||||||
- Its stdout/stderr is forwarded to the log at INFO. The health check
|
- Its stdout/stderr is forwarded to the log at INFO. The health check
|
||||||
skips the intentionally-stopped/starting states; a failed probe while
|
skips the intentionally-stopped/starting states; a failed probe while
|
||||||
the process is alive and was previously ready is logged as DOWN.
|
the process is alive and was previously ready is logged as DOWN.
|
||||||
|
- **Permissions**: the service account is sandboxed (Windows virtual
|
||||||
|
account, systemd `DynamicUser`), so a ComfyUI install inside a user
|
||||||
|
profile is off-limits by default. `--install-service` opens it up —
|
||||||
|
a recursive ACL grant for `NT SERVICE\gpu-turnstile` on Windows, a
|
||||||
|
`BindPaths=` in the unit on Linux — reading `COMFY_DIR` from the config
|
||||||
|
it installs. Re-run `--install-service` after changing `COMFY_DIR`, or
|
||||||
|
grant by hand (admin shell):
|
||||||
|
`icacls "<COMFY_DIR>" /grant "NT SERVICE\gpu-turnstile:(OI)(CI)M" /T`.
|
||||||
|
|
||||||
## Game detection (foreign GPU holders)
|
## Game detection (foreign GPU holders)
|
||||||
|
|
||||||
|
|||||||
@@ -518,14 +518,21 @@ func run(ctx context.Context, cfg config.Config, log *slog.Logger, logOut io.Wri
|
|||||||
if comfyCmdLine != "" {
|
if comfyCmdLine != "" {
|
||||||
if cfg.ComfyCmd == "" {
|
if cfg.ComfyCmd == "" {
|
||||||
// Derived from COMFY_DIR: flag a wrong-looking layout early,
|
// Derived from COMFY_DIR: flag a wrong-looking layout early,
|
||||||
// while the operator is still watching the startup log.
|
// while the operator is still watching the startup log. Inside
|
||||||
|
// a profile the service account may not enter, os.Stat fails
|
||||||
|
// with EACCES — that reads as "not found" but means "grant
|
||||||
|
// access", so say so.
|
||||||
python, script := supervise.ComfyLayout(runtime.GOOS, cfg.ComfyDir)
|
python, script := supervise.ComfyLayout(runtime.GOOS, cfg.ComfyDir)
|
||||||
for _, p := range []string{python, script} {
|
for _, p := range []string{python, script} {
|
||||||
if _, err := os.Stat(p); err != nil {
|
if _, err := os.Stat(p); err != nil {
|
||||||
|
if isPermission(err) {
|
||||||
|
log.Warn("COMFY_DIR: not accessible to the service account; grant access or re-run --install-service", "path", p)
|
||||||
|
} else {
|
||||||
log.Warn("COMFY_DIR: file not found; ComfyUI requests will fail until it exists", "path", p)
|
log.Warn("COMFY_DIR: file not found; ComfyUI requests will fail until it exists", "path", p)
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
}
|
||||||
var err error
|
var err error
|
||||||
comfySup, err = supervise.New("comfy", comfyCmdLine, cfg.ComfyDir, comfyClient.Probe, cfg.ComfyStartTimeout, log)
|
comfySup, err = supervise.New("comfy", comfyCmdLine, cfg.ComfyDir, comfyClient.Probe, cfg.ComfyStartTimeout, log)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
|
|||||||
@@ -6,7 +6,7 @@
|
|||||||
# ComfyUI --listen 0.0.0.0 --port 8189).
|
# ComfyUI --listen 0.0.0.0 --port 8189).
|
||||||
services:
|
services:
|
||||||
gpu-turnstile:
|
gpu-turnstile:
|
||||||
image: git.rambossek.at/public/gpu-turnstile:v0.1.10
|
image: git.rambossek.at/public/gpu-turnstile:v0.2.0
|
||||||
restart: unless-stopped
|
restart: unless-stopped
|
||||||
environment:
|
environment:
|
||||||
# Each consumer is enabled by setting its URL; leave one unset to
|
# Each consumer is enabled by setting its URL; leave one unset to
|
||||||
|
|||||||
@@ -45,3 +45,19 @@ func writeEnvFile(path, content string) error {
|
|||||||
}
|
}
|
||||||
return nil
|
return nil
|
||||||
}
|
}
|
||||||
|
|
||||||
|
// configuredValue reads one key from the env file the service will load, so
|
||||||
|
// the installers can adapt the sandbox to it (ACL grants, unit directives).
|
||||||
|
// "" when unset or unreadable.
|
||||||
|
func configuredValue(configPath, key string) string {
|
||||||
|
f, err := os.Open(configPath)
|
||||||
|
if err != nil {
|
||||||
|
return ""
|
||||||
|
}
|
||||||
|
defer f.Close()
|
||||||
|
values, err := config.ParseEnvFile(f)
|
||||||
|
if err != nil {
|
||||||
|
return ""
|
||||||
|
}
|
||||||
|
return values[key]
|
||||||
|
}
|
||||||
|
|||||||
@@ -62,8 +62,14 @@ func Run(run func(ctx context.Context) error) error {
|
|||||||
// filesystem is read-only except StateDirectory (the install dir, so
|
// filesystem is read-only except StateDirectory (the install dir, so
|
||||||
// self-updates can rewrite the binary), and the usual no-privilege-escalation
|
// self-updates can rewrite the binary), and the usual no-privilege-escalation
|
||||||
// directives apply. The proxy needs nothing but outbound TCP/UDP and the
|
// directives apply. The proxy needs nothing but outbound TCP/UDP and the
|
||||||
// notify socket, so it loses nothing.
|
// notify socket, so it loses nothing. A managed ComfyUI (comfyDir) gets a
|
||||||
func renderUnit(exePath, configPath string) string {
|
// BindPaths hole through ProtectHome/ProtectSystem: it reads its venv and
|
||||||
|
// writes output/temp/user data under COMFY_DIR.
|
||||||
|
func renderUnit(exePath, configPath, comfyDir string) string {
|
||||||
|
bind := ""
|
||||||
|
if comfyDir != "" {
|
||||||
|
bind = "BindPaths=" + comfyDir + "\n"
|
||||||
|
}
|
||||||
return fmt.Sprintf(`[Unit]
|
return fmt.Sprintf(`[Unit]
|
||||||
Description=gpu-turnstile GPU arbitration proxy for Ollama and ComfyUI
|
Description=gpu-turnstile GPU arbitration proxy for Ollama and ComfyUI
|
||||||
After=network-online.target
|
After=network-online.target
|
||||||
@@ -78,7 +84,7 @@ RestartSec=5s
|
|||||||
|
|
||||||
DynamicUser=yes
|
DynamicUser=yes
|
||||||
StateDirectory=%s
|
StateDirectory=%s
|
||||||
ProtectSystem=strict
|
%sProtectSystem=strict
|
||||||
ProtectHome=yes
|
ProtectHome=yes
|
||||||
PrivateTmp=yes
|
PrivateTmp=yes
|
||||||
NoNewPrivileges=yes
|
NoNewPrivileges=yes
|
||||||
@@ -100,7 +106,7 @@ SystemCallErrorNumber=EPERM
|
|||||||
|
|
||||||
[Install]
|
[Install]
|
||||||
WantedBy=multi-user.target
|
WantedBy=multi-user.target
|
||||||
`, exePath, configPath, Name)
|
`, exePath, configPath, Name, bind)
|
||||||
}
|
}
|
||||||
|
|
||||||
// copyFile copies src to dst, creating dst with the given mode.
|
// copyFile copies src to dst, creating dst with the given mode.
|
||||||
@@ -125,7 +131,9 @@ func copyFile(src, dst string, mode os.FileMode) error {
|
|||||||
// sure /etc/gpu-turnstile.env exists (copied from the given config file if
|
// sure /etc/gpu-turnstile.env exists (copied from the given config file if
|
||||||
// provided), writes the hardened unit, then enables and starts it. With
|
// provided), writes the hardened unit, then enables and starts it. With
|
||||||
// copyBin=false the current executable location and config path are
|
// copyBin=false the current executable location and config path are
|
||||||
// registered as-is instead. Needs root.
|
// registered as-is instead. When the config sets COMFY_DIR, the unit gets a
|
||||||
|
// BindPaths= for it so the sandboxed service can reach the managed ComfyUI
|
||||||
|
// even under /home. Needs root.
|
||||||
//
|
//
|
||||||
// Re-running install converges an existing unit instead of failing: it is
|
// Re-running install converges an existing unit instead of failing: it is
|
||||||
// stopped first if active, the installed binary is replaced only when the
|
// stopped first if active, the installed binary is replaced only when the
|
||||||
@@ -186,7 +194,7 @@ func Install(configPath string, copyBin bool, version string) error {
|
|||||||
cfg = abs
|
cfg = abs
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
rendered := renderUnit(exe, cfg)
|
rendered := renderUnit(exe, cfg, configuredValue(cfg, "COMFY_DIR"))
|
||||||
if old, _ := os.ReadFile(unitPath); string(old) != rendered {
|
if old, _ := os.ReadFile(unitPath); string(old) != rendered {
|
||||||
if err := os.WriteFile(unitPath, []byte(rendered), 0o644); err != nil {
|
if err := os.WriteFile(unitPath, []byte(rendered), 0o644); err != nil {
|
||||||
return fmt.Errorf("write %s (run as root): %w", unitPath, err)
|
return fmt.Errorf("write %s (run as root): %w", unitPath, err)
|
||||||
|
|||||||
@@ -8,7 +8,7 @@ import (
|
|||||||
)
|
)
|
||||||
|
|
||||||
func TestRenderUnit(t *testing.T) {
|
func TestRenderUnit(t *testing.T) {
|
||||||
unit := renderUnit("/var/lib/gpu-turnstile/gpu-turnstile", "/etc/gpu-turnstile.env")
|
unit := renderUnit("/var/lib/gpu-turnstile/gpu-turnstile", "/etc/gpu-turnstile.env", "")
|
||||||
for _, want := range []string{
|
for _, want := range []string{
|
||||||
"Type=notify",
|
"Type=notify",
|
||||||
"WatchdogSec=30s",
|
"WatchdogSec=30s",
|
||||||
@@ -26,4 +26,12 @@ func TestRenderUnit(t *testing.T) {
|
|||||||
t.Fatalf("unit missing %q:\n%s", want, unit)
|
t.Fatalf("unit missing %q:\n%s", want, unit)
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
if strings.Contains(unit, "BindPaths") {
|
||||||
|
t.Fatalf("unit without COMFY_DIR must not bind anything:\n%s", unit)
|
||||||
|
}
|
||||||
|
|
||||||
|
unit = renderUnit("/var/lib/gpu-turnstile/gpu-turnstile", "/etc/gpu-turnstile.env", "/home/gpu/ComfyUI")
|
||||||
|
if !strings.Contains(unit, "BindPaths=/home/gpu/ComfyUI\n") {
|
||||||
|
t.Fatalf("unit with COMFY_DIR must bind it:\n%s", unit)
|
||||||
|
}
|
||||||
}
|
}
|
||||||
|
|||||||
@@ -24,8 +24,6 @@ import (
|
|||||||
"golang.org/x/sys/windows"
|
"golang.org/x/sys/windows"
|
||||||
"golang.org/x/sys/windows/svc"
|
"golang.org/x/sys/windows/svc"
|
||||||
"golang.org/x/sys/windows/svc/mgr"
|
"golang.org/x/sys/windows/svc/mgr"
|
||||||
|
|
||||||
"gpu-turnstile/internal/config"
|
|
||||||
)
|
)
|
||||||
|
|
||||||
// Name is the Windows service name.
|
// Name is the Windows service name.
|
||||||
@@ -106,10 +104,12 @@ func (h *handler) Execute(_ []string, requests <-chan svc.ChangeRequest, status
|
|||||||
// the service after 5s on failure — this is also what brings up a staged
|
// the service after 5s on failure — this is also what brings up a staged
|
||||||
// update after the updater exits with a non-zero code. After registering,
|
// update after the updater exits with a non-zero code. After registering,
|
||||||
// the virtual account is granted modify access to the install and data
|
// the virtual account is granted modify access to the install and data
|
||||||
// directories (self-updates rewrite the exe), and read access to the
|
// directories (self-updates rewrite the exe), read access to the
|
||||||
// config file if it lives elsewhere. The grants must come after
|
// config file if it lives elsewhere, and — when the config sets COMFY_DIR —
|
||||||
// CreateService: the virtual account's SID only exists once the service is
|
// recursive modify access to the managed ComfyUI's install tree, which may
|
||||||
// registered.
|
// live inside a user profile the account otherwise cannot enter. The grants
|
||||||
|
// must come after CreateService: the virtual account's SID only exists once
|
||||||
|
// the service is registered.
|
||||||
//
|
//
|
||||||
// Re-running install on an existing service converges instead of failing:
|
// Re-running install on an existing service converges instead of failing:
|
||||||
// the service is stopped first if running (so the binary can be replaced),
|
// the service is stopped first if running (so the binary can be replaced),
|
||||||
@@ -146,6 +146,7 @@ func Install(configPath string, copyBin bool, version string) error {
|
|||||||
if st, qErr := s.Query(); qErr == nil &&
|
if st, qErr := s.Query(); qErr == nil &&
|
||||||
(st.State == svc.Running || st.State == svc.StartPending) {
|
(st.State == svc.Running || st.State == svc.StartPending) {
|
||||||
wasRunning = true
|
wasRunning = true
|
||||||
|
fmt.Println("stopping the running gpu-turnstile service")
|
||||||
if err := stopAndWait(s); err != nil {
|
if err := stopAndWait(s); err != nil {
|
||||||
return err
|
return err
|
||||||
}
|
}
|
||||||
@@ -161,6 +162,7 @@ func Install(configPath string, copyBin bool, version string) error {
|
|||||||
}
|
}
|
||||||
installedExe := filepath.Join(installDir, "gpu-turnstile.exe")
|
installedExe := filepath.Join(installDir, "gpu-turnstile.exe")
|
||||||
if same, _ := sameFileContent(exe, installedExe); !same {
|
if same, _ := sameFileContent(exe, installedExe); !same {
|
||||||
|
fmt.Printf("installing %s\n", installedExe)
|
||||||
if err := copyFile(exe, installedExe); err != nil {
|
if err := copyFile(exe, installedExe); err != nil {
|
||||||
return fmt.Errorf("copy binary to %s: %w", installedExe, err)
|
return fmt.Errorf("copy binary to %s: %w", installedExe, err)
|
||||||
}
|
}
|
||||||
@@ -208,6 +210,7 @@ func Install(configPath string, copyBin bool, version string) error {
|
|||||||
// Best effort: start now instead of waiting for the next boot. A
|
// Best effort: start now instead of waiting for the next boot. A
|
||||||
// missing config (no consumer URLs) fails the start; the service stays
|
// missing config (no consumer URLs) fails the start; the service stays
|
||||||
// registered and can be started once the config exists.
|
// registered and can be started once the config exists.
|
||||||
|
fmt.Println("starting the gpu-turnstile service")
|
||||||
s.Start()
|
s.Start()
|
||||||
return nil
|
return nil
|
||||||
}
|
}
|
||||||
@@ -243,6 +246,7 @@ func Install(configPath string, copyBin bool, version string) error {
|
|||||||
return err
|
return err
|
||||||
}
|
}
|
||||||
if wasRunning {
|
if wasRunning {
|
||||||
|
fmt.Println("starting the gpu-turnstile service")
|
||||||
if err := s.Start(); err != nil {
|
if err := s.Start(); err != nil {
|
||||||
return fmt.Errorf("start service: %w", err)
|
return fmt.Errorf("start service: %w", err)
|
||||||
}
|
}
|
||||||
@@ -354,7 +358,7 @@ func grantAll(exe, configPath string) error {
|
|||||||
return err
|
return err
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
if logFile := configuredLogFile(configPath); logFile != "" {
|
if logFile := configuredValue(configPath, "LOG_FILE"); logFile != "" {
|
||||||
dir := filepath.Dir(logFile)
|
dir := filepath.Dir(logFile)
|
||||||
if err := os.MkdirAll(dir, 0o755); err == nil {
|
if err := os.MkdirAll(dir, 0o755); err == nil {
|
||||||
if err := grantAccess(dir, "(OI)(CI)(M)"); err != nil {
|
if err := grantAccess(dir, "(OI)(CI)(M)"); err != nil {
|
||||||
@@ -362,6 +366,17 @@ func grantAll(exe, configPath string) error {
|
|||||||
}
|
}
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
// A managed ComfyUI whose install lives somewhere the virtual account
|
||||||
|
// may not go (a user profile) needs an explicit grant — recursively,
|
||||||
|
// since ComfyUI also writes output/temp/user data next to its code. A
|
||||||
|
// missing directory is skipped: the startup warning covers it.
|
||||||
|
if comfyDir := configuredValue(configPath, "COMFY_DIR"); comfyDir != "" {
|
||||||
|
if _, err := os.Stat(comfyDir); err == nil {
|
||||||
|
if err := grantAccessTree(comfyDir, "(OI)(CI)(M)"); err != nil {
|
||||||
|
return err
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
return nil
|
return nil
|
||||||
}
|
}
|
||||||
|
|
||||||
@@ -466,28 +481,35 @@ func RelaunchElevated(args []string) (int, error) {
|
|||||||
// grantAccess gives the virtual account the icacls permission set (e.g.
|
// grantAccess gives the virtual account the icacls permission set (e.g.
|
||||||
// "(OI)(CI)(M)") on path.
|
// "(OI)(CI)(M)") on path.
|
||||||
func grantAccess(path, perms string) error {
|
func grantAccess(path, perms string) error {
|
||||||
out, err := exec.Command("icacls", path, "/grant", virtualAccount+":"+perms).CombinedOutput()
|
return runIcacls(path, perms, false)
|
||||||
|
}
|
||||||
|
|
||||||
|
// grantAccessTree is grantAccess with /T: the ACE is applied to the
|
||||||
|
// existing tree, not just inherited by children created later. Needed when
|
||||||
|
// the tree already exists, e.g. a ComfyUI install in a user profile. On a
|
||||||
|
// large tree (a venv has tens of thousands of files) this takes minutes,
|
||||||
|
// so it says what it is doing instead of looking hung.
|
||||||
|
func grantAccessTree(path, perms string) error {
|
||||||
|
return runIcacls(path, perms, true)
|
||||||
|
}
|
||||||
|
|
||||||
|
func runIcacls(path, perms string, recursive bool) error {
|
||||||
|
args := []string{path, "/grant", virtualAccount + ":" + perms}
|
||||||
|
if recursive {
|
||||||
|
fmt.Printf("granting %s modify access to %s (large trees can take minutes)\n", virtualAccount, path)
|
||||||
|
args = append(args, "/T")
|
||||||
|
}
|
||||||
|
start := time.Now()
|
||||||
|
out, err := exec.Command("icacls", args...).CombinedOutput()
|
||||||
if err != nil {
|
if err != nil {
|
||||||
return fmt.Errorf("grant %s access to %s: %w (%s)", virtualAccount, path, err, strings.TrimSpace(string(out)))
|
return fmt.Errorf("grant %s access to %s: %w (%s)", virtualAccount, path, err, strings.TrimSpace(string(out)))
|
||||||
}
|
}
|
||||||
|
if recursive {
|
||||||
|
fmt.Printf("access granted in %s\n", time.Since(start).Round(time.Second))
|
||||||
|
}
|
||||||
return nil
|
return nil
|
||||||
}
|
}
|
||||||
|
|
||||||
// configuredLogFile reads LOG_FILE from the config file so the installer
|
|
||||||
// can pre-create and ACL the log directory. "" when unset or unreadable.
|
|
||||||
func configuredLogFile(configPath string) string {
|
|
||||||
f, err := os.Open(configPath)
|
|
||||||
if err != nil {
|
|
||||||
return ""
|
|
||||||
}
|
|
||||||
defer f.Close()
|
|
||||||
values, err := config.ParseEnvFile(f)
|
|
||||||
if err != nil {
|
|
||||||
return ""
|
|
||||||
}
|
|
||||||
return values["LOG_FILE"]
|
|
||||||
}
|
|
||||||
|
|
||||||
// RestartIfRunning restarts the service when it is installed and running
|
// RestartIfRunning restarts the service when it is installed and running
|
||||||
// (used after a forced update staged a new binary). Reports whether a
|
// (used after a forced update staged a new binary). Reports whether a
|
||||||
// restart happened. A service that is not installed or not running is not
|
// restart happened. A service that is not installed or not running is not
|
||||||
|
|||||||
Reference in New Issue
Block a user