chore: make ssh+cli connections reuse one SSH connection via control socket. Fix image push

pkg/client/connector/sshcli.go

@@ -4,6 +4,8 @@ import (
 	"context"
 	"fmt"
 	"net"
+	"os"
+	"path/filepath"
 	"strconv"
 
 	"github.com/docker/cli/cli/connhelper/commandconn"
@@ -18,26 +20,72 @@ import (
 type SSHCLIConnector struct {
 	config SSHConnectorConfig
 	conn   net.Conn
+	// Path to SSH control socket for connection reuse.
+	controlSockPath string
 }
 
 func NewSSHCLIConnector(cfg *SSHConnectorConfig) *SSHCLIConnector {
-	return &SSHCLIConnector{config: *cfg}
+	return &SSHCLIConnector{
+		config:          *cfg,
+		controlSockPath: controlSocketPath(),
+	}
+}
+
+// controlSocketPath returns a unique control socket path for the SSH connection.
+// Returns an empty string if unable to find or create a suitable path.
+func controlSocketPath() string {
+	// %C is expanded by `ssh` to a hash of user, local and remote hostnames, port, and the contents
+	// of the ProxyJump option. This ensures that shared connections are uniquely identified.
+	sockName := fmt.Sprintf("uc_control_%%C.sock")
+
+	// Prefer XDG_RUNTIME_DIR if set, fall back to ~/.ssh if it exists.
+	if dir := os.Getenv("XDG_RUNTIME_DIR"); dir != "" {
+		return filepath.Join(dir, sockName)
+	}
+	if home, err := os.UserHomeDir(); err == nil {
+		sshDir := filepath.Join(home, ".ssh")
+		if fi, sErr := os.Stat(sshDir); sErr == nil && fi.IsDir() {
+			return filepath.Join(sshDir, sockName)
+		}
+	}
+
+	// Last resort: create a subdirectory in temp with restricted permissions.
+	tmpDir := filepath.Join(os.TempDir(), fmt.Sprintf("uncloud-%d", os.Getuid()))
+	path := filepath.Join(tmpDir, sockName)
+	if len(path)-2+40 < 104 { // 40 chars for %C hash, 104 is typical UNIX socket path limit
+		if err := os.MkdirAll(tmpDir, 0o700); err == nil {
+			return path
+		}
+	}
+
+	return ""
 }
 
 // sshCLIDialer implements proxy.ContextDialer by spawning SSH processes with -W flag.
 type sshCLIDialer struct {
 	config SSHConnectorConfig
+	// Shared control socket path from SSHCLIConnector for connection reuse.
+	controlSockPath string
 }
 
 // buildDialArgs constructs SSH command arguments for -W flag dialing.
 func (d *sshCLIDialer) buildDialArgs(address string) []string {
-	args := []string{}
+	var args []string
+
+	if d.controlSockPath != "" {
+		// Try to reuse the existing control connection without initiating a new one.
+		// Falls back to direct connection if the control socket is not available.
+		args = append(args, "-o", "ControlMaster=no")
+		args = append(args, "-o", "ControlPath="+d.controlSockPath)
+	}
 
 	// Add connection timeout to fail fast when node is down.
 	args = append(args, "-o", "ConnectTimeout=5")
+	// Disable pseudo-terminal allocation to prevent SSH from executing as a login shell.
+	args = append(args, "-T")
 
-	// Add port if non-standard.
-	if d.config.Port != 0 && d.config.Port != 22 {
+	// Add port if specified.
+	if d.config.Port != 0 {
 		args = append(args, "-p", strconv.Itoa(d.config.Port))
 	}
 
@@ -49,8 +97,8 @@ func (d *sshCLIDialer) buildDialArgs(address string) []string {
 	// Add -W flag for stdin/stdout forwarding to target address.
 	args = append(args, "-W", address)
 
-	// Add user@host.
-	args = append(args, d.config.User+"@"+d.config.Host)
+	// Add [user@]host destination.
+	args = append(args, d.config.Destination())
 
 	return args
 }
@@ -65,28 +113,28 @@ func (d *sshCLIDialer) DialContext(ctx context.Context, network, address string)
 	// Build SSH command arguments.
 	args := d.buildDialArgs(address)
 
-	// Create connection using commandconn.
+	// Create connection using docker's commandconn.
 	conn, err := commandconn.New(ctx, "ssh", args...)
 	if err != nil {
-		return nil, fmt.Errorf("SSH connection to %s@%s for dialing %s: %w", d.config.User, d.config.Host, address, err)
+		return nil, fmt.Errorf("SSH connection to %s for dialing %s: %w", d.config.Destination(), address, err)
 	}
 
 	return conn, nil
 }
 
 func (c *SSHCLIConnector) Connect(ctx context.Context) (*grpc.ClientConn, error) {
-	// Build SSH command arguments.
-	args := c.buildSSHArgs()
+	if c.conn == nil {
+		args := c.buildSSHArgs()
 
-	// Create connection using commandconn.
-	conn, err := commandconn.New(ctx, "ssh", args...)
-	if err != nil {
-		return nil, fmt.Errorf("SSH connection to %s@%s: %w", c.config.User, c.config.Host, err)
+		// Create connection using docker's commandconn.
+		conn, err := commandconn.New(ctx, "ssh", args...)
+		if err != nil {
+			return nil, fmt.Errorf("SSH connection to %s: %w", c.config.Destination(), err)
+		}
+		c.conn = conn
 	}
-	c.conn = conn
 
-	// Create gRPC client over the connection.
-	// Use a custom dialer that returns our existing connection.
+	// Create gRPC client over the connection. Use a custom dialer that returns our existing connection.
 	grpcConn, err := grpc.NewClient(
 		"passthrough:///", // Dummy target since we're using a custom dialer.
 		grpc.WithTransportCredentials(insecure.NewCredentials()),
@@ -103,15 +151,32 @@ func (c *SSHCLIConnector) Connect(ctx context.Context) (*grpc.ClientConn, error)
 	return grpcConn, nil
 }
 
-// buildSSHArgs constructs the SSH command arguments.
+// buildSSHArgs constructs the SSH command arguments to run `uncloudd dial-stdio` on the remote machine reusing
+// the established connection via control socket.
 func (c *SSHCLIConnector) buildSSHArgs() []string {
-	args := []string{}
+	var args []string
+
+	// Add control socket options for connection reuse if available.
+	if c.controlSockPath != "" {
+		args = append(args, "-o", "ControlMaster=auto")
+		args = append(args, "-o", "ControlPath="+c.controlSockPath)
+
+		// Keep the established connection alive for a short duration after the last session closes to allow reuse.
+		controlPersist := "10m"
+		// Override the default duration with the UNCLOUD_SSH_CONTROL_PERSIST env variable.
+		if v := os.Getenv("UNCLOUD_SSH_CONTROL_PERSIST"); v != "" {
+			controlPersist = v
+		}
+		args = append(args, "-o", "ControlPersist="+controlPersist)
+	}
 
 	// Add connection timeout to fail fast when node is down.
 	args = append(args, "-o", "ConnectTimeout=5")
+	// Disable pseudo-terminal allocation to prevent SSH from executing as a login shell.
+	args = append(args, "-T")
 
-	// Add port if non-standard.
-	if c.config.Port != 0 && c.config.Port != 22 {
+	// Add port if specified.
+	if c.config.Port != 0 {
 		args = append(args, "-p", strconv.Itoa(c.config.Port))
 	}
 
@@ -120,8 +185,8 @@ func (c *SSHCLIConnector) buildSSHArgs() []string {
 		args = append(args, "-i", c.config.KeyPath)
 	}
 
-	// Add user@host.
-	args = append(args, c.config.User+"@"+c.config.Host)
+	// Add [user@]host destination.
+	args = append(args, c.config.Destination())
 
 	// Add remote command: uncloudd dial-stdio
 	args = append(args, "uncloudd", "dial-stdio")
@@ -141,7 +206,8 @@ func (c *SSHCLIConnector) Dialer() (proxy.ContextDialer, error) {
 	}
 
 	return &sshCLIDialer{
-		config: c.config,
+		config:          c.config,
+		controlSockPath: c.controlSockPath,
 	}, nil
 }