Files
gpu-turnstile/internal/config/config.go
T
mram bacb26772a Add LLM busy modes: wait (hang) or reject with Retry-After
LLM_BUSY_MODE=reject answers blocked LLM requests immediately with
LLM_BUSY_STATUS (default 503, 429 works) and Retry-After, so routers
like LiteLLM can cool down and retry instead of holding a hung
connection. The default wait mode now also sends Retry-After when
LLM_WAIT_TIMEOUT expires. Document the service account (LocalSystem
default, NT SERVICE virtual-account hardening) and the Program
Files / ProgramData install layout.
2026-09-20 21:43:03 +02:00

224 lines
6.0 KiB
Go

// Package config loads gpu-turnstile's configuration from environment
// variables and an optional .env-style config file.
package config
import (
"bufio"
"fmt"
"io"
"log/slog"
"strconv"
"strings"
"time"
)
// Config holds every gpu-turnstile setting.
type Config struct {
ListenOllama string
ListenComfy string
OllamaURL string
ComfyURL string
UnloadTimeout time.Duration
JobTimeout time.Duration
LLMWaitTimeout time.Duration
UnloadPollInterval time.Duration
HistoryPollInterval time.Duration
ProbeTimeout time.Duration
FreeTimeout time.Duration
WarmTimeout time.Duration
ShutdownTimeout time.Duration
BackoffInitial time.Duration
BackoffMax time.Duration
PromptCaptureLimit int64
AutoUpdate bool
UpdateInterval time.Duration
UpdateRepo string
UpdateAsset string
// LLMBusyMode is "wait" (hold requests until the lock is free or
// LLMWaitTimeout expires) or "reject" (immediately answer with
// LLMBusyStatus + Retry-After when an image job is active or pending).
LLMBusyMode string
LLMBusyStatus int
BusyRetryAfter int
WarmModel string
LogLevel slog.Level
LogJSON bool
LogFile string
}
// Defaults returns the configuration used when neither the environment nor
// a config file sets a value.
func Defaults() Config {
return Config{
ListenOllama: ":11434",
ListenComfy: ":8188",
OllamaURL: "http://127.0.0.1:11435",
ComfyURL: "http://127.0.0.1:8189",
UnloadTimeout: time.Minute,
JobTimeout: 15 * time.Minute,
LLMWaitTimeout: 10 * time.Minute,
UnloadPollInterval: 500 * time.Millisecond,
HistoryPollInterval: time.Second,
ProbeTimeout: 5 * time.Second,
FreeTimeout: 30 * time.Second,
WarmTimeout: 2 * time.Minute,
ShutdownTimeout: 10 * time.Second,
BackoffInitial: time.Second,
BackoffMax: time.Minute,
PromptCaptureLimit: 64 * 1024,
AutoUpdate: true,
UpdateInterval: 6 * time.Hour,
UpdateRepo: "https://git.rambossek.at/PUBLIC/gpu-turnstile",
UpdateAsset: "gpu-turnstile.exe",
LLMBusyMode: "wait",
LLMBusyStatus: 503,
BusyRetryAfter: 30,
LogLevel: slog.LevelWarn,
}
}
// ParseEnvFile parses a .env-style file: KEY=VALUE lines, blank lines and
// #-comments are ignored, no quoting. A line without '=' is an error.
func ParseEnvFile(r io.Reader) (map[string]string, error) {
values := make(map[string]string)
scanner := bufio.NewScanner(r)
scanner.Buffer(make([]byte, 64*1024), 1024*1024)
lineNo := 0
for scanner.Scan() {
lineNo++
line := strings.TrimSpace(scanner.Text())
if line == "" || strings.HasPrefix(line, "#") {
continue
}
key, value, ok := strings.Cut(line, "=")
if !ok {
return nil, fmt.Errorf("line %d: expected KEY=VALUE", lineNo)
}
key = strings.TrimSpace(key)
if key == "" {
return nil, fmt.Errorf("line %d: empty key", lineNo)
}
values[key] = strings.TrimSpace(value)
}
return values, scanner.Err()
}
func envDuration(getenv func(string) string, name string, dst *time.Duration) error {
v := getenv(name)
if v == "" {
return nil
}
d, err := time.ParseDuration(v)
if err != nil {
return fmt.Errorf("%s: %w", name, err)
}
*dst = d
return nil
}
// Load overlays values from getenv onto the Defaults. Unknown keys are
// ignored. Invalid values are fatal.
func Load(getenv func(string) string) (Config, error) {
cfg := Defaults()
for _, e := range []struct {
name string
dst *string
}{
{"LISTEN_OLLAMA", &cfg.ListenOllama},
{"LISTEN_COMFY", &cfg.ListenComfy},
{"OLLAMA_URL", &cfg.OllamaURL},
{"COMFY_URL", &cfg.ComfyURL},
{"WARM_MODEL", &cfg.WarmModel},
{"UPDATE_REPO", &cfg.UpdateRepo},
{"UPDATE_ASSET", &cfg.UpdateAsset},
{"LOG_FILE", &cfg.LogFile},
} {
if v := getenv(e.name); v != "" {
*e.dst = v
}
}
for _, e := range []struct {
name string
dst *time.Duration
}{
{"UNLOAD_TIMEOUT", &cfg.UnloadTimeout},
{"JOB_TIMEOUT", &cfg.JobTimeout},
{"LLM_WAIT_TIMEOUT", &cfg.LLMWaitTimeout},
{"UNLOAD_POLL_INTERVAL", &cfg.UnloadPollInterval},
{"HISTORY_POLL_INTERVAL", &cfg.HistoryPollInterval},
{"PROBE_TIMEOUT", &cfg.ProbeTimeout},
{"FREE_TIMEOUT", &cfg.FreeTimeout},
{"WARM_TIMEOUT", &cfg.WarmTimeout},
{"SHUTDOWN_TIMEOUT", &cfg.ShutdownTimeout},
{"BACKOFF_INITIAL", &cfg.BackoffInitial},
{"BACKOFF_MAX", &cfg.BackoffMax},
{"UPDATE_INTERVAL", &cfg.UpdateInterval},
} {
if err := envDuration(getenv, e.name, e.dst); err != nil {
return cfg, err
}
}
if v := getenv("PROMPT_CAPTURE_LIMIT"); v != "" {
n, err := strconv.ParseInt(v, 10, 64)
if err != nil || n < 0 {
return cfg, fmt.Errorf("PROMPT_CAPTURE_LIMIT: must be a non-negative integer (bytes)")
}
cfg.PromptCaptureLimit = n
}
if v := getenv("AUTO_UPDATE"); v != "" {
b, err := strconv.ParseBool(v)
if err != nil {
return cfg, fmt.Errorf("AUTO_UPDATE: must be a boolean (true/false)")
}
cfg.AutoUpdate = b
}
if v := getenv("LLM_BUSY_MODE"); v != "" {
if v != "wait" && v != "reject" {
return cfg, fmt.Errorf("LLM_BUSY_MODE: must be \"wait\" or \"reject\"")
}
cfg.LLMBusyMode = v
}
if v := getenv("LLM_BUSY_STATUS"); v != "" {
n, err := strconv.Atoi(v)
if err != nil || n < 400 || n > 599 {
return cfg, fmt.Errorf("LLM_BUSY_STATUS: must be an HTTP status in 400-599")
}
cfg.LLMBusyStatus = n
}
if v := getenv("BUSY_RETRY_AFTER"); v != "" {
n, err := strconv.Atoi(v)
if err != nil || n <= 0 {
return cfg, fmt.Errorf("BUSY_RETRY_AFTER: must be a positive integer (seconds)")
}
cfg.BusyRetryAfter = n
}
// LOGLEVEL is the canonical spelling; LOG_LEVEL is kept as an alias.
logLevelValue := getenv("LOGLEVEL")
if logLevelValue == "" {
logLevelValue = getenv("LOG_LEVEL")
}
if logLevelValue != "" {
var level slog.Level
if err := level.UnmarshalText([]byte(logLevelValue)); err != nil {
return cfg, fmt.Errorf("LOGLEVEL: %w", err)
}
cfg.LogLevel = level
}
switch strings.ToLower(getenv("LOG_FORMAT")) {
case "", "text":
case "json":
cfg.LogJSON = true
default:
return cfg, fmt.Errorf("LOG_FORMAT: must be \"text\" or \"json\"")
}
return cfg, nil
}