upgraded to Flamenco 3.7
This commit is contained in:
@@ -0,0 +1,110 @@
|
||||
<!-- Generated by SpecStory -->
|
||||
|
||||
# Configure Launch Standard Worker for Flamenco 3.7 (2025-07-15 18:30Z)
|
||||
|
||||
_**User**_
|
||||
|
||||
@2025-05-12_16-04Z-technical-scripting-and-troubleshooting-discussion.md @2025-05-13_23-13Z-bypassing-password-prompts-in-script.md @2025-06-03_00-04Z-change-retry-function-to-infinite-retries.md @2025-05-14_15-49Z-cmd-worker-error-handling-and-retry-logic.md @2025-05-23_23-12Z-replace-remotecmd-with-remotesimplified.md I'm upgrading from Flamenco 3.6 to 3.7. CMD workers are working fine because they're directed to F:\software\Flamenco 3.7, and i9kf is working fine because I've installed flamenco 3.7 to that local path. Can we have Launch Standard Worker run the worker executable in F:\software\Flamenco 3.7 ?
|
||||
|
||||
---
|
||||
|
||||
_**Assistant**_
|
||||
|
||||
Yes, you can have the "Launch Standard Worker" option run the worker executable from `F:\software\Flamenco 3.7` for all systems, just like the CMD workers. Currently, the `Get-RemoteStandardWorkerCommand` function is set up to run the worker from `C:\Program Files\Blender Foundation\Flamenco 3.7` if it exists, but you want it to always use `F:\software\Flamenco 3.7\flamenco-worker.exe`.
|
||||
|
||||
**Here's what you need to do:**
|
||||
|
||||
- Update the `Get-RemoteStandardWorkerCommand` function so that it always sets the location to `F:\software\Flamenco 3.7` and runs `flamenco-worker.exe` from there, regardless of whether the directory exists in `C:\Program Files\...`.
|
||||
|
||||
---
|
||||
|
||||
**How to update:**
|
||||
|
||||
Replace the entire worker start block in `Get-RemoteStandardWorkerCommand` with the following:
|
||||
|
||||
```powershell
|
||||
# Start worker
|
||||
Write-Host "Starting Flamenco worker..." -ForegroundColor Cyan
|
||||
Set-Location 'F:\software\Flamenco 3.7'
|
||||
if (Test-Path 'flamenco-worker.exe') {
|
||||
Write-Host "Running flamenco-worker.exe..." -ForegroundColor Green
|
||||
# Run the worker and capture its exit code
|
||||
$workerProcess = Start-Process -FilePath '.\flamenco-worker.exe' -NoNewWindow -PassThru -Wait
|
||||
$exitCode = $workerProcess.ExitCode
|
||||
Write-Host "Flamenco worker process has terminated with exit code: $exitCode" -ForegroundColor Yellow
|
||||
exit $exitCode # Exit with the worker's exit code to trigger restart if needed
|
||||
} else {
|
||||
Write-Host "Error: flamenco-worker.exe not found in F:\software\Flamenco 3.7" -ForegroundColor Red
|
||||
exit 1 # Exit with error code to trigger restart
|
||||
}
|
||||
```
|
||||
|
||||
**Remove** the check for `C:\Program Files\Blender Foundation\Flamenco 3.7` entirely.
|
||||
|
||||
---
|
||||
|
||||
**Result:**
|
||||
- All "Standard Worker" launches will use the 3.7 executable from `F:\software\Flamenco 3.7`, just like your CMD workers.
|
||||
- This will ensure consistency across all your worker launches.
|
||||
|
||||
Would you like me to make this edit for you now?
|
||||
|
||||
---
|
||||
|
||||
_**User**_
|
||||
|
||||
each worker except for i9kf is printing:
|
||||
|
||||
2025-07-15T12:36:06-06:00 WRN unable to send sign-on request error="Post \"http://localhost:8888/api/v3/worker/sign-on\": dial tcp [::1]:8888: connectex: No connection could be made because the target machine actively refused it." manager=http://localhost:8888/
|
||||
|
||||
---
|
||||
|
||||
_**Assistant**_
|
||||
|
||||
The warning message:
|
||||
|
||||
```
|
||||
WRN unable to send sign-on request error="Post \"http://localhost:8888/api/v3/worker/sign-on\": dial tcp [::1]:8888: connectex: No connection could be made because the target machine actively refused it." manager=http://localhost:8888/
|
||||
```
|
||||
|
||||
means that the Flamenco worker is trying to connect to a Flamenco Manager at `http://localhost:8888/`, but nothing is listening on that port on the remote machine. This is a **network/configuration issue**, not a script or launcher bug.
|
||||
|
||||
### Why does this happen?
|
||||
|
||||
- **Each worker runs on its own machine.**
|
||||
- By default, the worker tries to connect to a manager at `localhost:8888` (i.e., itself).
|
||||
- Unless the Flamenco Manager is running on that same machine and on that port, the connection will fail.
|
||||
|
||||
### Why does i9kf work?
|
||||
|
||||
- On i9kf, you probably have the Flamenco Manager running locally, or the worker's config points to the correct manager address.
|
||||
|
||||
### Why do the others fail?
|
||||
|
||||
- On the other machines, the worker is trying to connect to `localhost:8888`, but the manager is not running there (or not on that port).
|
||||
|
||||
---
|
||||
|
||||
## How to Fix
|
||||
|
||||
You need to make sure that **each worker's configuration file** (`flamenco-worker.yaml`) points to the correct Flamenco Manager address (the actual host/IP where the manager is running, not `localhost`).
|
||||
|
||||
### Steps:
|
||||
|
||||
1. **Find the manager's real address.**
|
||||
- If the manager is running on i9kf, use its network name or IP, e.g., `http://i9kf:8888/` or `http://192.168.1.100:8888/`.
|
||||
|
||||
2. **Update the worker config on each machine:**
|
||||
- Open `flamenco-worker.yaml` (location is shown in the worker's startup log, e.g., `C:\Users\Nathan\AppData\Local\Blender Foundation\Flamenco\worker-2\flamenco-worker.yaml`).
|
||||
- Find the line like:
|
||||
```yaml
|
||||
manager: http://localhost:8888/
|
||||
```
|
||||
- Change it to:
|
||||
```yaml
|
||||
manager: http://i9kf:8888/
|
||||
```
|
||||
or whatever the
|
||||
|
||||
---
|
||||
|
||||
Reference in New Issue
Block a user