cozos commented on code in PR #38246:
URL: https://github.com/apache/beam/pull/38246#discussion_r3114760190
##########
sdks/python/container/boot.go:
##########
@@ -314,23 +314,47 @@ func launchSDKProcess() error {
var wg sync.WaitGroup
wg.Add(len(workerIds))
- for _, workerId := range workerIds {
- go func(workerId string) {
- defer wg.Done()
-
- bufLogger := tools.NewBufferedLogger(logger)
- errorCount := 0
- for {
- childPids.mu.Lock()
- if childPids.canceled {
- childPids.mu.Unlock()
- return
- }
- logger.Printf(ctx, "Executing Python (worker
%v): python %v", workerId, strings.Join(args, " "))
- cmd :=
StartCommandEnv(map[string]string{"WORKER_ID": workerId}, os.Stdin, bufLogger,
bufLogger, "python", args...)
- childPids.v = append(childPids.v,
cmd.Process.Pid)
- childPids.mu.Unlock()
-
+for _, workerId := range workerIds {
+ go func(workerId string) {
+ defer wg.Done()
+
+ workerCtx := grpcx.WriteWorkerID(ctx, workerId)
+
+ // Create a separate logger per worker so that each worker initializes
+ // its own Fn logging stream with the correct worker_id metadata.
+ // Shared loggers would reuse the first stream and cause incorrect
+ // portability_worker_id attribution across workers.
+ workerLogger := &tools.Logger{
+ Endpoint: *loggingEndpoint,
+ }
+
+ bufLogger := tools.NewBufferedLogger(workerLogger)
+
+ errorCount := 0
+ for {
+ childPids.mu.Lock()
+ if childPids.canceled {
+ childPids.mu.Unlock()
+ return
+ }
+
+ workerLogger.Printf(workerCtx,
+ "Executing Python (worker %v): python %v",
+ workerId,
+ strings.Join(args, " "),
+ )
+
+ cmd := StartCommandEnv(
+ map[string]string{"WORKER_ID": workerId},
+ os.Stdin,
+ bufLogger,
+ bufLogger,
Review Comment:
@tvalentyn I just noticed that the process stderr/stdout is output as debug
logs via `FlushAtDebug` in
https://github.com/apache/beam/blob/25370f50b39f2703ee1a15780b76fa52464fc581/sdks/go/container/tools/buffered_logging.go#L69
Is it possible to either
1. Make this default `FlushAtInfo`
2. Or let users configure this to the log level they desire?
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
