PUBLIC/gpu-turnstile
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 6 Wiki Activity

Periodic upstream health checks (HEALTH_INTERVAL, default 30s); log down/recovered transitions

Browse Source
This commit is contained in:
mram
2026-09-21 13:14:18 +02:00
parent 5e7a042cad
commit 232f5b61f2
5 changed files with 53 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files
SPEC.md
+2 -1
View File
@@ -147,7 +147,8 @@ override file values. A missing file is fine; a malformed one is fatal.
| `LOG_FILE` | `` | append logs to this file instead of stderr (useful as a service) |
| `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 |
| `PROBE_TIMEOUT` | `5s` | startup probe of both upstreams (also the per-probe health check timeout) |
| `HEALTH_INTERVAL` | `30s` | periodic probe of enabled upstreams; status changes (down/recovered) are logged |
| `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 |