mram
bacb26772a
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.
164 lines
7.8 KiB
Markdown
164 lines
7.8 KiB
Markdown
# gpu-turnstile
|
||
|
||
GPU arbitration proxy for Ollama + ComfyUI. One consumer GPU is shared by an
|
||
LLM server (Ollama) and an image generator (ComfyUI); gpu-turnstile sits in
|
||
front of both and guarantees the GPU is always in exactly one of three states:
|
||
`idle`, `llm` (N ≥ 1 Ollama requests in flight), or `image` (exactly one
|
||
ComfyUI job, Ollama models unloaded). See [SPEC.md](SPEC.md) for the full
|
||
design.
|
||
|
||
gpu-turnstile listens on the ports the services normally use; the actual
|
||
services run one port higher (Ollama on 11435, ComfyUI on 8189).
|
||
|
||
```
|
||
LiteLLM / Open WebUI ──► :11434 ─┐ ┌─► Ollama :11435
|
||
├── gpu-turnstile (1 lock) ──┤
|
||
Open WebUI / n8n ────► :8188 ───┘ └─► ComfyUI :8189
|
||
```
|
||
|
||
- LLM endpoints (`/api/generate`, `/api/chat`, `/api/embed`, `/v1/*`) take the
|
||
LLM lock: concurrent requests allowed, but blocked while an image job is
|
||
active or waiting (image priority). Blocked requests either hang until the
|
||
lock is free (`LLM_BUSY_MODE=wait`, default) or fail immediately with 503
|
||
(or 429) + `Retry-After` (`LLM_BUSY_MODE=reject`) — the latter lets routers
|
||
like LiteLLM cool down and retry instead of holding a hung connection.
|
||
- `POST /prompt` on the ComfyUI listener takes the image lock: new LLM
|
||
requests block, in-flight LLMs drain, Ollama models are unloaded, the prompt
|
||
is forwarded, and the lock is held until the job finishes and ComfyUI frees
|
||
its VRAM.
|
||
- Everything else (including websockets and all streaming) passes through
|
||
transparently and unbuffered.
|
||
|
||
## Configuration
|
||
|
||
Configuration comes from environment variables and/or an `.env`-style
|
||
config file (`KEY=VALUE` lines, `#` comments). File lookup order:
|
||
`-config <path>` flag, then `GPU_TURNSTILE_CONFIG`, then
|
||
`gpu-turnstile.env` next to the executable. Process environment variables
|
||
override file values. Invalid values fail at startup.
|
||
|
||
| Var | Default | Meaning |
|
||
|---|---|---|
|
||
| `LISTEN_OLLAMA` | `:11434` | Ollama-facing listener |
|
||
| `LISTEN_COMFY` | `:8188` | ComfyUI-facing listener |
|
||
| `OLLAMA_URL` | `http://127.0.0.1:11435` | Ollama upstream |
|
||
| `COMFY_URL` | `http://127.0.0.1:8189` | ComfyUI upstream |
|
||
| `UNLOAD_TIMEOUT` | `60s` | Wait for Ollama to unload before an image job |
|
||
| `JOB_TIMEOUT` | `15m` | Wait for a ComfyUI job to finish |
|
||
| `LLM_WAIT_TIMEOUT` | `10m` | Max lock wait for an LLM request before 503 (wait mode) |
|
||
| `LLM_BUSY_MODE` | `wait` | `wait` = hold blocked LLM requests; `reject` = fail them immediately |
|
||
| `LLM_BUSY_STATUS` | `503` | HTTP status for rejected LLM requests in reject mode (400–599, e.g. 429) |
|
||
| `BUSY_RETRY_AFTER` | `30` | Seconds sent as `Retry-After` on busy responses (both modes) |
|
||
| `WARM_MODEL` | _(empty)_ | Model to reload after an image job (off by default) |
|
||
| `LOGLEVEL` | `warn` | `info` logs every request (colored arrows in text mode), `debug` adds lock transitions. `LOG_LEVEL` works as an alias |
|
||
| `LOG_FORMAT` | `text` | `json` for structured JSON logs |
|
||
| `LOG_FILE` | _(empty)_ | Append logs to this file instead of stderr |
|
||
| `UNLOAD_POLL_INTERVAL` | `500ms` | `/api/ps` poll interval while unloading |
|
||
| `HISTORY_POLL_INTERVAL` | `1s` | `/history/<id>` poll interval while a job runs |
|
||
| `PROBE_TIMEOUT` | `5s` | Startup probe of both upstreams |
|
||
| `FREE_TIMEOUT` | `30s` | `POST /free` call after an image job |
|
||
| `WARM_TIMEOUT` | `2m` | Warm-model reload after an image job |
|
||
| `SHUTDOWN_TIMEOUT` | `10s` | Graceful shutdown on SIGINT/SIGTERM |
|
||
| `BACKOFF_INITIAL` | `1s` | First retry wait when an upstream refuses a connection |
|
||
| `BACKOFF_MAX` | `60s` | Cap for the exponential retry backoff |
|
||
| `PROMPT_CAPTURE_LIMIT` | `65536` | Bytes of the `/prompt` response buffered to find `prompt_id` (pass-through is unaffected) |
|
||
| `AUTO_UPDATE` | `true` | Poll the Gitea releases API for signed updates |
|
||
| `UPDATE_INTERVAL` | `6h` | Auto-update check interval |
|
||
| `UPDATE_REPO` | `https://git.rambossek.at/PUBLIC/gpu-turnstile` | Repository checked for releases |
|
||
| `UPDATE_ASSET` | `gpu-turnstile.exe` | Release asset to download |
|
||
|
||
## Observability
|
||
|
||
- `GET /healthz` (both listeners): `{"state":"idle|llm|image","llm_inflight":N,"image_pending":B}`
|
||
- `GET /metrics` (Ollama listener): Prometheus text format — `gpu_turnstile_state`,
|
||
`gpu_turnstile_llm_inflight`, `gpu_turnstile_image_pending`,
|
||
`gpu_turnstile_image_jobs_total`, `gpu_turnstile_lock_wait_seconds`
|
||
(histogram, `kind="llm|image"`), `gpu_turnstile_unload_seconds`.
|
||
- Logs: startup logs the version and every setting (visible even at the
|
||
default `warn` level). With `LOGLEVEL=info` or `debug`, every request
|
||
logs a `-->` incoming line and a `<--` response line with status and
|
||
duration — ANSI-colored (cyan incoming; green/yellow/red by status
|
||
class) in text mode, which renders in `docker compose logs` on Windows
|
||
Terminal. Set `NO_COLOR` to disable colors.
|
||
|
||
## Build and run
|
||
|
||
```sh
|
||
go build ./cmd/gpu-turnstile
|
||
./gpu-turnstile
|
||
```
|
||
|
||
### Run natively on Windows (primary deployment)
|
||
|
||
Download `gpu-turnstile.exe` from a release, put a `gpu-turnstile.env`
|
||
next to it, and run it — or install it as a Windows service from an
|
||
elevated shell:
|
||
|
||
```sh
|
||
gpu-turnstile.exe service install # auto-start service, recovery = restart
|
||
gpu-turnstile.exe service remove
|
||
```
|
||
|
||
The service uses the config file (services have no convenient
|
||
environment); set `LOG_FILE` in it since there is no console.
|
||
|
||
Suggested layout: `C:\Program Files\gpu-turnstile\` for the exe and
|
||
`gpu-turnstile.env`, logs under `C:\ProgramData\gpu-turnstile\` via
|
||
`LOG_FILE`. The service runs as `LocalSystem` by default, which can write
|
||
the install directory for self-updates. For least privilege, run it as the
|
||
virtual account `NT SERVICE\gpu-turnstile` and grant write access to just
|
||
those two directories.
|
||
|
||
**Auto-update is on by default**: the binary checks the repo's latest
|
||
release on startup and every `UPDATE_INTERVAL`, verifies the Ed25519
|
||
signature of the download against the public key embedded at build time,
|
||
and — once the GPU lock is idle — restarts the service onto the new
|
||
version. Disable with `AUTO_UPDATE=false`. Releases are signed by CI with
|
||
OpenSSL; the matching public key lives in `internal/update/pubkey.go`
|
||
(one-time setup: `openssl genpkey -algorithm ed25519 -out private.pem`,
|
||
`openssl pkey -in private.pem -pubout -out public.pem`; private key goes
|
||
to the `SIGNING_KEY` repo secret, public key is committed).
|
||
|
||
### Docker
|
||
|
||
```sh
|
||
docker build -t gpu-turnstile .
|
||
docker run --rm -p 11434:11434 -p 8188:8188 \
|
||
-e OLLAMA_URL=http://<workstation-ip>:11435 \
|
||
-e COMFY_URL=http://<workstation-ip>:8189 \
|
||
gpu-turnstile
|
||
```
|
||
|
||
Releases are built by Gitea Actions (`.gitea/workflows/ci.yml`): every push
|
||
runs `go vet` and `go test -race`, and pushing a semantic-version tag
|
||
`vX.Y.Z` publishes the container image
|
||
(`git.rambossek.at/<owner>/gpu-turnstile:vX.Y.Z` plus `:latest`) and a
|
||
signed Windows binary attached to a Gitea release. Nothing is built from
|
||
branches.
|
||
|
||
The registry login needs one repository secret (Settings → Actions →
|
||
Secrets): `REGISTRY_TOKEN` — an access token with `write:package` scope.
|
||
The automatic `GITEA_TOKEN` cannot push packages.
|
||
|
||
## Development
|
||
|
||
```sh
|
||
go vet ./...
|
||
go test -race ./...
|
||
```
|
||
|
||
Go 1.23+; the only external dependency is `golang.org/x/sys` (Windows
|
||
service integration, unused in the Linux build). Layout:
|
||
|
||
```
|
||
cmd/gpu-turnstile/main.go wiring, config, listeners, service + updater
|
||
internal/lock/ two-mode lock (LLM readers / image writer, FIFO)
|
||
internal/ollama/ ps / unload / warm client
|
||
internal/comfy/ history poll / free client
|
||
internal/proxy/ handlers for both listeners
|
||
internal/metrics/ Prometheus exposition, no dependencies
|
||
internal/config/ env + .env file configuration
|
||
internal/update/ signed auto-updater
|
||
internal/service/ Windows service integration
|
||
```
|