feat(B): Traefik deployment to all nodes during init/join (REQ-165, REQ-167)

- internal/traefik/install.go: shared Traefik installer (download +
  systemd unit + dynamic dir). Default v3.3.0, configurable.
- orca init: installs Traefik on localhost (idempotent, non-fatal
  if offline)
- proxmox bootstrap: installs Traefik on PVE host + downloads LXC
  template (default ubuntu-24.04, --lxc-template flag)
- linux bootstrap: installs Traefik on worker
- emitter/traefik.go: directory provider (was single file);
  register pve-ct/pve-vm in RegisterTraefik
- --lxc-template flag on node join (default ubuntu-24.04)

---ci---
project: orca
milestone: v0.12.18
phase: B
status: complete
requirements:
  covered: [165, 167]
---/ci---
This commit is contained in:
Jon Chery
2026-08-10 16:09:48 +00:00
parent a6ceb13491
commit 0d44f97993
8 changed files with 146 additions and 4 deletions
+14
View File
@@ -208,6 +208,20 @@ func runInit(out interface{ Write([]byte) (int, error) }) error {
}
}
// Step 4d: Install Traefik on the lead node (REQ-165, Phase B).
// Traefik is the data-plane ingress. Idempotent.
if err := installTraefikLocal(); err != nil {
if !jsonOutput {
fmt.Fprintf(out, "Traefik install skipped: %v\n", err)
}
summary.Steps = append(summary.Steps, stepResult{Label: "traefik", Status: "skipped", Detail: err.Error()})
} else {
summary.Steps = append(summary.Steps, stepResult{Label: "traefik", Status: "ok", Detail: traefikVersion})
if !jsonOutput {
fmt.Fprintf(out, "Traefik installed: %s\n", traefikVersion)
}
}
// Step 5: OS detection.
osDetected := detectOS()
summary.OS = osDetected
+5 -2
View File
@@ -55,6 +55,7 @@ var (
joinSSHKey string
joinSSHPort int
joinHostKeyFP string
joinLXCTemplate string
proxmoxUser string
proxmoxRole string
leaveID string
@@ -186,6 +187,7 @@ func joinProxmox(cmd *cobra.Command) error {
SSHPort: joinSSHPort,
HostKeyFingerprint: joinHostKeyFP,
Logger: newLogger(),
LXCTemplate: joinLXCTemplate,
})
if err != nil {
return fmt.Errorf("proxmox bootstrap: %w", err)
@@ -250,7 +252,7 @@ func joinLinux(cmd *cobra.Command) error {
SSHPort: joinSSHPort,
HostKeyFingerprint: joinHostKeyFP,
Logger: newLogger(),
})
})
if err != nil {
return fmt.Errorf("linux bootstrap: %w", err)
}
@@ -510,7 +512,8 @@ func init() {
nodeJoinCmd.Flags().IntVar(&joinSSHPort, "ssh-port", 22, "SSH port for proxmox bootstrap (default 22)")
nodeJoinCmd.Flags().StringVar(&proxmoxUser, "proxmox-user", "orca", "Linux system user to create on the proxmox host (config-overridable)")
nodeJoinCmd.Flags().StringVar(&proxmoxRole, "proxmox-role", "OrcaOperator", "PVE custom role to create (config-overridable)")
nodeJoinCmd.Flags().StringVar(&joinHostKeyFP, "host-key-fingerprint", "", "SSH host key SHA256:base64 fingerprint (pre-pin; supersedes TOFU for --type proxmox)")
nodeJoinCmd.Flags().StringVar(&joinHostKeyFP, "host-key-fingerprint", "", "SSH host key SHA256:base64 fingerprint (pre-pin; supersedes TOFU for --type proxmox or --type linux)")
nodeJoinCmd.Flags().StringVar(&joinLXCTemplate, "lxc-template", "ubuntu-24.04", "LXC template for Proxmox (default ubuntu-24.04; alternatives: alpine-3.20, debian-12)")
nodeLeaveCmd.Flags().StringVar(&leaveID, "id", "", "node id")
nodeListCmd.Flags().BoolVar(&nodeWatch, "watch", false, "stream nodes until Ctrl-C (table refresh or --json per-event)")
+11
View File
@@ -0,0 +1,11 @@
package cli
import (
"git.cloudinit.dev/coreci/orca/internal/traefik"
)
var traefikVersion = traefik.DefaultVersion
func installTraefikLocal() error {
return traefik.InstallLocal(traefikVersion)
}
+3 -1
View File
@@ -124,6 +124,8 @@ func RegisterTraefik(reg *Registry) {
reg.Register("service:process", e)
reg.Register("service:podman", e)
reg.Register("service:wasm", e)
reg.Register("service:pve-ct", e)
reg.Register("service:pve-vm", e)
}
// renderTraefikYAML renders the Traefik dynamic-config YAML for the
@@ -288,7 +290,7 @@ func renderTraefikStaticYAML(o TraefikStaticOpts) string {
b.WriteString(fmt.Sprintf(" address: %q\n", "127.0.0.1:8081"))
b.WriteString("\nproviders:\n")
b.WriteString(" file:\n")
b.WriteString(fmt.Sprintf(" filename: %q\n", "/etc/traefik/dynamic/orca.yml"))
b.WriteString(fmt.Sprintf(" directory: %q\n", traefikDynamicDir))
b.WriteString(" watch: true\n")
b.WriteString("\nlog:\n")
b.WriteString(" level: INFO\n")
+1 -1
View File
@@ -375,7 +375,7 @@ func TestTraefikEmitter_RenderStaticConfigHybrid(t *testing.T) {
`address: "127.0.0.1:8081"`,
"providers:",
"file:",
`filename: "/etc/traefik/dynamic/orca.yml"`,
`directory: "/etc/traefik/dynamic"`,
"watch: true",
"log:",
"level: INFO",
+15
View File
@@ -34,6 +34,7 @@ import (
"git.cloudinit.dev/coreci/orca/internal/certpaths"
"git.cloudinit.dev/coreci/orca/internal/proxmox"
"git.cloudinit.dev/coreci/orca/internal/security"
"git.cloudinit.dev/coreci/orca/internal/traefik"
)
// DefaultSSHUser is the default SSH username for the initial connection.
@@ -156,6 +157,20 @@ func BootstrapLinux(ctx context.Context, opts Options) (*Result, error) {
}
opts.Logger.Info("linux bootstrap: user created", "user", opts.OrcaUser)
// Step 4d: Install Traefik on the remote host (REQ-165, Phase B).
// Traefik is the data-plane ingress; SSH is control plane only.
sshExecFn := func(cmd string) ([]byte, error) {
session, err := client.NewSession()
if err != nil {
return nil, err
}
defer session.Close()
return session.CombinedOutput(cmd)
}
if err := traefik.InstallRemote("", sshExecFn); err != nil {
opts.Logger.Warn("linux bootstrap: traefik install failed", "err", err)
}
// Step 5: Create the drift-events directory.
if err := sshExec(client, fmt.Sprintf(
"mkdir -p ~%s/drift-events && chown %s:%s ~%s/drift-events",
+19
View File
@@ -38,6 +38,7 @@ import (
"git.cloudinit.dev/coreci/orca/internal/certpaths"
"git.cloudinit.dev/coreci/orca/internal/security"
"git.cloudinit.dev/coreci/orca/internal/traefik"
)
// DefaultProxmoxUser is the default Linux system user created on the
@@ -82,6 +83,9 @@ type Options struct {
HostKeyFingerprint string
// Logger receives audit-log entries. If nil, slog.Default() is used.
Logger *slog.Logger
// LXCTemplate is the LXC template to download during bootstrap
// (default "ubuntu-24.04"; alternatives: "alpine-3.20", "debian-12").
LXCTemplate string
}
// Result is the outcome of a successful bootstrap.
@@ -243,6 +247,21 @@ func BootstrapProxmox(ctx context.Context, opts Options) (*Result, error) {
return nil, fmt.Errorf("validate sudoers: %w", err)
}
// Step 9a: Install Traefik on the Proxmox host (REQ-165, Phase B).
// Traefik runs on the PVE OS as the data-plane ingress; SSH is
// control plane only. Idempotent: skips if binary already exists.
if err := traefik.InstallRemote("", runRemote); err != nil {
log.Warn("proxmox.traefik_install_failed", "err", err)
}
// Step 9b: Download default LXC template (REQ-167, Phase C).
// Default: ubuntu-24.04. Configurable via --lxc-template.
template := opts.LXCTemplate
if template == "" {
template = "ubuntu-24.04"
}
_, _ = runRemote(fmt.Sprintf("pveam download local %s 2>/dev/null || true", shellQuote(template)))
log.Info("proxmox.bootstrap_ok",
slog.String("event", "proxmox.bootstrap_ok"),
slog.String("host", opts.Host),
+78
View File
@@ -0,0 +1,78 @@
package traefik
import (
"fmt"
"os/exec"
"strings"
)
const DefaultVersion = "v3.3.0"
func downloadURL(version string) string {
return fmt.Sprintf("https://github.com/traefik/traefik/releases/download/%s/traefik_%s_linux_amd64.tar.gz", version, version)
}
func InstallLocal(version string) error {
if version == "" {
version = DefaultVersion
}
if _, err := exec.LookPath("traefik"); err == nil {
ensureDirs()
return nil
}
url := downloadURL(version)
cmd := exec.Command("bash", "-c",
fmt.Sprintf(`curl -fsSL %s | tar -xzf - -C /usr/local/bin/ traefik && chmod +x /usr/local/bin/traefik`, url))
if out, err := cmd.CombinedOutput(); err != nil {
return fmt.Errorf("download traefik %s: %w (output: %s)", version, err, string(out))
}
ensureDirs()
writeSystemdUnit()
_ = exec.Command("systemctl", "daemon-reload").Run()
_ = exec.Command("systemctl", "enable", "--now", "orca-traefik").Run()
return nil
}
type RemoteExecFunc func(cmd string) ([]byte, error)
func InstallRemote(version string, execFn RemoteExecFunc) error {
if version == "" {
version = DefaultVersion
}
if out, err := execFn("command -v traefik"); err == nil && len(strings.TrimSpace(string(out))) > 0 {
_, _ = execFn("mkdir -p /etc/traefik/dynamic")
return nil
}
url := downloadURL(version)
installCmd := fmt.Sprintf(`curl -fsSL %s | tar -xzf - -C /usr/local/bin/ traefik && chmod +x /usr/local/bin/traefik && mkdir -p /etc/traefik/dynamic`, url)
if out, err := execFn(installCmd); err != nil {
return fmt.Errorf("download traefik on remote: %w (output: %s)", err, string(out))
}
unit := systemdUnitContent()
_, _ = execFn(fmt.Sprintf(`echo '%s' > /etc/systemd/system/orca-traefik.service`, unit))
_, _ = execFn("systemctl daemon-reload && systemctl enable --now orca-traefik")
return nil
}
func ensureDirs() {
_ = exec.Command("mkdir", "-p", "/etc/traefik/dynamic").Run()
}
func writeSystemdUnit() {
_ = exec.Command("bash", "-c", fmt.Sprintf(`echo '%s' > /etc/systemd/system/orca-traefik.service`, systemdUnitContent())).Run()
}
func systemdUnitContent() string {
return `[Unit]
Description=Orca Traefik Data Plane
After=network.target
[Service]
Type=simple
ExecStart=/usr/local/bin/traefik --configFile=/etc/traefik/traefik.yml
Restart=on-failure
RestartSec=5s
[Install]
WantedBy=multi-user.target`
}