Compare commits

...
Author SHA1 Message Date
antje 139bd734f0 deps: luxfi/consensus v1.36.2 -> v1.36.3 — the v1.36.2 tag was re-pushed
Cold builds fail sumdb verification against the moved tag (downloaded
eKzasq4O... vs sealed IbeWQF1w...). v1.36.3 is the immutable successor;
never re-tag a published version.
2026-07-17 01:26:35 -07:00
antje 6e24fcfd28 mirror: skip hidden files — AppleDouble forks pass the extension check
._foo.png is a mac resource fork, not a render; 700+ of them poisoned a
library within an hour of the mirror going live.
2026-07-17 01:15:16 -07:00
antje 9e7931e81c render: poll window matches the dispatch cap; engine recycles after each render
The 10m local history poll undercut the 4h startToCloseTimeout the dispatcher
grants — live renders (observed 8-70m) were marked failed while still sampling;
only the mirror later delivered them. renderWindow now matches the cap.

The engine leaks ~58GB per render. The handler signals a recycle after each
COMPLETED render (never on timeout — the engine may still be sampling and the
mirror rescues late finishes); the supervisor restarts on the signal.
2026-07-17 01:09:39 -07:00
4 changed files with 32 additions and 4 deletions
+16 -1
View File
@@ -54,6 +54,10 @@ const (
heartbeatEvery = 30 * time.Second
claimPoll = 2 * time.Second
claimLeaseSecs = 120
// renderWindow matches the dispatch cap (studio gpu_dispatch sets
// startToCloseTimeout 14400s). The old 10m local poll undercut it and
// marked live renders failed while they kept sampling (observed 8-70m).
renderWindow = 4 * time.Hour
// localComfyUI is the studio render backend the studio.render handler drives.
localComfyUI = "http://127.0.0.1:8188"
// defaultStudioUploadURL is where finished render outputs are POSTed so they
@@ -848,7 +852,7 @@ func (w *worker) studioRenderHandler(ctx context.Context, input json.RawMessage)
return nil, fmt.Errorf("studio.render: no prompt_id in /prompt response")
}
// Poll history until the prompt shows up (completed).
deadline := time.Now().Add(10 * time.Minute)
deadline := time.Now().Add(renderWindow)
for time.Now().Before(deadline) {
select {
case <-ctx.Done():
@@ -872,6 +876,11 @@ func (w *worker) studioRenderHandler(ctx context.Context, input json.RawMessage)
if uerr != nil {
return nil, fmt.Errorf("studio.render: prompt %s rendered but gallery upload failed: %w", pr.PromptID, uerr)
}
// The engine leaks ~58GB per render; recycling after each completed
// render caps it at one render's worth. Boot (~20s) is noise next to
// 8-70m renders. Never recycle on the timeout path — the engine may
// still be sampling and the mirror rescues late finishes.
requestStudioRecycle()
return map[string]any{"promptId": pr.PromptID, "outputs": outputs, "gallery": gallery}, nil
}
}
@@ -1014,6 +1023,12 @@ func (w *worker) mirrorRenders(ctx context.Context, out io.Writer, dir, base str
if werr != nil || info == nil || info.IsDir() || !isImageFile(p) {
return nil
}
// Hidden files and AppleDouble forks (`._*`, `.DS_Store`) ride along with
// mac scp and are not renders — `._foo.png` passes the extension check
// but is a 4KB resource fork that poisons the library.
if strings.HasPrefix(filepath.Base(p), ".") {
return nil
}
rel, rerr := filepath.Rel(dir, p)
if rerr != nil {
return nil
+13
View File
@@ -107,6 +107,17 @@ func stopStudio(cmd *exec.Cmd) {
}
}
// studioRecycle carries at most one pending recycle request; the render
// handler signals it after each completed render (see gpu.go).
var studioRecycle = make(chan struct{}, 1)
func requestStudioRecycle() {
select {
case studioRecycle <- struct{}{}:
default:
}
}
// superviseStudio keeps the local render backend on :8188 alive until ctx
// ends. Quiet by design: one line per restart event, not a probe firehose.
func superviseStudio(ctx context.Context, dir string, out io.Writer) {
@@ -145,6 +156,8 @@ func superviseStudio(ctx context.Context, dir string, out io.Writer) {
_ = syscall.Kill(-cmd.Process.Pid, syscall.SIGTERM)
}
return
case <-studioRecycle:
restart("recycle")
case <-tick.C:
if studioHealthy(ctx) {
continue
+1 -1
View File
@@ -581,7 +581,7 @@ require (
github.com/luxfi/cache v1.3.1 // indirect
github.com/luxfi/compress v0.1.1 // indirect
github.com/luxfi/concurrent v0.1.1 // indirect
github.com/luxfi/consensus v1.36.2
github.com/luxfi/consensus v1.36.3
github.com/luxfi/container v0.2.1 // indirect
github.com/luxfi/corona v0.10.4 // indirect
github.com/luxfi/crypto v1.20.2
+2 -2
View File
@@ -1628,8 +1628,8 @@ github.com/luxfi/compress v0.1.1 h1:cQjRYQFRrw8HinjW1T8FmKgqdRwrFYDCdecc1t0i+uQ=
github.com/luxfi/compress v0.1.1/go.mod h1:d4CkRRmwPzafIp57Jxra3RmAmNwNwU8Oc0QBBRlTqGo=
github.com/luxfi/concurrent v0.1.1 h1:LkAmNXybOsAm97nFILqMDBp/YLgleuLmyGomFT7YNxU=
github.com/luxfi/concurrent v0.1.1/go.mod h1:GlkfiJtPBpatNxvROf7hkPi4gsnmdHGmqhDnVWFrkZE=
github.com/luxfi/consensus v1.36.2 h1:IbeWQF1wEcA/MNxe4fKniSICPndAGEysV/A3DZGMXFM=
github.com/luxfi/consensus v1.36.2/go.mod h1:m4aMFbKYxwM2X4oPYRjq4LmDSShfCgAHnhmxIGKDyFU=
github.com/luxfi/consensus v1.36.3 h1:pEfHf7asnIKQ2Dr2tWe5nKv/0lRRa/iAQ9IyevcRU3s=
github.com/luxfi/consensus v1.36.3/go.mod h1:m4aMFbKYxwM2X4oPYRjq4LmDSShfCgAHnhmxIGKDyFU=
github.com/luxfi/constants v1.6.2 h1:pXHdKIFbfE9qX4xOjq2LxYvagNhhNvspUVEbPcIEKfA=
github.com/luxfi/constants v1.6.2/go.mod h1:r0oH8C/+r/XFYBq1AJxt6zWRKKRKgDzrEMop/CCs9rI=
github.com/luxfi/container v0.2.1 h1:MTnfKXzS5+oxV5jKZerdOxSA6iMPaQI9/FWGufizzaw=