server: skip local unix sockets that cannot be bound (#12000)

server: skip default local unix sockets that cannot be bound

weed server fatally exited during S3, filer, or SFTP startup when the default /tmp/seaweedfs-<svc>-<port>.sock path could not be removed or bound. On shared hosts (e.g. CI runners where another user's weed left a socket in the sticky /tmp directory) a stale socket file turns into 'operation not permitted' and kills the whole server, even though the TCP listeners are unaffected. Warn and skip the unix socket listener instead, matching how the gRPC local socket already degrades. An explicitly configured -localSocket path still fails fast, since a co-located S3 server may be configured to dial the filer through it.

weed/command/filer.go

@@ -525,19 +525,27 @@ func (fo *FilerOptions) startFiler() {
 	var socketServer *http.Server
 	if runtime.GOOS != "windows" {
 		localSocket := *fo.localSocket
-		if localSocket == "" {
+		explicit := localSocket != ""
+		if !explicit {
 			localSocket = fmt.Sprintf("/tmp/seaweedfs-filer-%d.sock", *fo.port)
 		}
 		if err := os.Remove(localSocket); err != nil && !os.IsNotExist(err) {
-			glog.Fatalf("Failed to remove %s, error: %s", localSocket, err.Error())
+			if explicit {
+				glog.Fatalf("Failed to remove %s, error: %s", localSocket, err.Error())
+			}
+			glog.Warningf("Failed to remove %s, error: %s", localSocket, err.Error())
 		}
 		filerSocketListener, err := net.Listen("unix", localSocket)
 		if err != nil {
-			glog.Fatalf("Failed to listen on %s: %v", localSocket, err)
+			if explicit {
+				glog.Fatalf("Failed to listen on %s: %v", localSocket, err)
+			}
+			glog.Errorf("Failed to listen on %s, skipping local socket server: %v", localSocket, err)
+		} else {
+			socketServer = newHttpServer(defaultHandler, nil)
+			httpServers = append(httpServers, socketServer)
+			go socketServer.Serve(filerSocketListener)
 		}
-		socketServer = newHttpServer(defaultHandler, nil)
-		httpServers = append(httpServers, socketServer)
-		go socketServer.Serve(filerSocketListener)
 	}
 
 	if viper.GetString("https.filer.key") != "" {

weed/command/s3.go

@@ -429,23 +429,31 @@ func (s3opt *S3Options) startS3Server() bool {
 
 	if runtime.GOOS != "windows" {
 		localSocket := *s3opt.localSocket
-		if localSocket == "" {
+		explicit := localSocket != ""
+		if !explicit {
 			localSocket = fmt.Sprintf("/tmp/seaweedfs-s3-%d.sock", *s3opt.port)
 		}
 		if err := os.Remove(localSocket); err != nil && !os.IsNotExist(err) {
-			glog.Fatalf("Failed to remove %s, error: %s", localSocket, err.Error())
+			if explicit {
+				glog.Fatalf("Failed to remove %s, error: %s", localSocket, err.Error())
+			}
+			glog.Warningf("Failed to remove %s, error: %s", localSocket, err.Error())
 		}
 		s3SocketListener, err := net.Listen("unix", localSocket)
 		if err != nil {
-			glog.Fatalf("Failed to listen on %s: %v", localSocket, err)
-		}
-		socketServer := newHttpServer(router, nil)
-		httpServers = append(httpServers, socketServer)
-		go func() {
-			if err := socketServer.Serve(s3SocketListener); err != nil && err != http.ErrServerClosed {
-				glog.Fatalf("Failed to start S3 http server: %v", err)
+			if explicit {
+				glog.Fatalf("Failed to listen on %s: %v", localSocket, err)
 			}
-		}()
+			glog.Errorf("Failed to listen on %s, skipping local socket server: %v", localSocket, err)
+		} else {
+			socketServer := newHttpServer(router, nil)
+			httpServers = append(httpServers, socketServer)
+			go func() {
+				if err := socketServer.Serve(s3SocketListener); err != nil && err != http.ErrServerClosed {
+					glog.Errorf("Failed to start S3 http server on %s: %v", localSocket, err)
+				}
+			}()
+		}
 	}
 
 	listenAddress := fmt.Sprintf("%s:%d", *s3opt.bindIp, *s3opt.port)

weed/command/sftp.go

@@ -180,20 +180,28 @@ func (sftpOpt *SftpOptions) startSftpServer() bool {
 	// Set up Unix socket if on non-Windows platforms
 	if runtime.GOOS != "windows" {
 		localSocket := *sftpOpt.localSocket
-		if localSocket == "" {
+		explicit := localSocket != ""
+		if !explicit {
 			localSocket = fmt.Sprintf("/tmp/seaweedfs-sftp-%d.sock", *sftpOpt.port)
 		}
 		if err := os.Remove(localSocket); err != nil && !os.IsNotExist(err) {
-			glog.Fatalf("Failed to remove %s, error: %s", localSocket, err.Error())
+			if explicit {
+				glog.Fatalf("Failed to remove %s, error: %s", localSocket, err.Error())
+			}
+			glog.Warningf("Failed to remove %s, error: %s", localSocket, err.Error())
 		}
 		go func() {
 			// start on local unix socket
 			sftpSocketListener, err := net.Listen("unix", localSocket)
 			if err != nil {
-				glog.Fatalf("Failed to listen on %s: %v", localSocket, err)
+				if explicit {
+					glog.Fatalf("Failed to listen on %s: %v", localSocket, err)
+				}
+				glog.Errorf("Failed to listen on %s, skipping local socket server: %v", localSocket, err)
+				return
 			}
 			if err := service.Serve(sftpSocketListener); err != nil {
-				glog.Fatalf("Failed to serve SFTP on socket %s: %v", localSocket, err)
+				glog.Errorf("Failed to serve SFTP on socket %s: %v", localSocket, err)
 			}
 		}()
 	}