feat(P7): doctor ingress + docs + integration tests (REQ-177,178,179)

New 'orca doctor ingress' command: verifies podman orca-traefik container running, nft DNAT+SNAT, /etc/traefik/dynamic exists, step-ca root CA present. UAT signoff script: replaced assertion 36 (systemd → podman container), added assertions 40-46 (nft table, DNAT, SNAT, dynamic dir, step-ca CA, traefik.yml, doctor ingress pass). docs/ingress.md: R-024 podman traefik section — three topologies, container config, nft ruleset, doctor ingress, Dockerfile.traefik. TLS model updated (drop certResolver, tls:{} for v0.14, mTLS v0.15). ARCHITECTURE.md: v0.14 deltas section — R-024, three topologies, nft emitter changes, TLS model, migration 0009, new CLI. Integration tests (tests/ingress_bootstrap_test.go): nft postrouting + DNATTarget, priority -10, traefik TLS model (tls:{} no certResolver), image ref resolution, floating-IP LXC provisioning commands (pct create with hwaddr/ip/gw/features), MAC generation. ---ci--- project: orca phase: 7 milestone: v0.14 status: execute ---/ci---
2026-08-10 20:24:13 +00:00
parent 6e65eadaa5
commit ecdba833d9
5 changed files with 441 additions and 9 deletions
@@ -0,0 +1,115 @@
+// Package cli: doctor_ingress.go implements `orca doctor ingress`
+// (R-024, v0.14). The check verifies the podman traefik container is
+// running, nft DNAT+SNAT is applied, the dynamic config directory
+// exists, and the step-ca root CA is mounted.
+package cli
+
+import (
+	"context"
+	"fmt"
+	"strings"
+	"time"
+
+	"github.com/spf13/cobra"
+)
+
+var doctorIngressCmd = &cobra.Command{
+	Use:   "ingress",
+	Short: "Check the ingress stack (R-024: podman traefik + nft + CA)",
+	Long: `Verify the orca ingress data plane is healthy:
+  1. orca-traefik podman container is running
+  2. nft DNAT + SNAT masquerade applied
+  3. /etc/traefik/dynamic directory exists
+  4. step-ca root CA mounted at /etc/orca/step-ca-root.crt
+
+For remote peers, use --peer <name>.`,
+	RunE: func(cmd *cobra.Command, args []string) error {
+		ctx, cancel := context.WithTimeout(context.Background(), 30*time.Second)
+		defer cancel()
+		results := runIngressChecks(ctx)
+		if jsonOutput {
+			return printJSON(results)
+		}
+		allPass := true
+		for _, r := range results {
+			status := "✓"
+			if r.Result != "PASS" {
+				status = "✗"
+				allPass = false
+			}
+			fmt.Fprintf(cmd.OutOrStdout(), "%s %s: %s\n", status, r.Name, r.Message)
+		}
+		if !allPass {
+			return fmt.Errorf("ingress checks failed")
+		}
+		return nil
+	},
+}
+
+// ingressCheckResult is one line of `orca doctor ingress` output.
+type ingressCheckResult struct {
+	Name    string `json:"name"`
+	Result  string `json:"result"`
+	Message string `json:"message"`
+}
+
+func runIngressChecks(ctx context.Context) []ingressCheckResult {
+	t, err := nftTransportFromCtx()
+	if err != nil {
+		return []ingressCheckResult{{Name: "ingress:transport", Result: "FAIL", Message: err.Error()}}
+	}
+	peer := nftLeadPeer()
+	var results []ingressCheckResult
+
+	// 1. Check podman orca-traefik container is running.
+	out, err := t.Exec(ctx, peer, "podman inspect --format '{{.State.Running}}' orca-traefik 2>/dev/null")
+	if err != nil {
+		results = append(results, ingressCheckResult{Name: "ingress:container", Result: "FAIL", Message: fmt.Sprintf("podman inspect: %v", err)})
+	} else {
+		v := strings.TrimSpace(string(out))
+		if v == "true" {
+			results = append(results, ingressCheckResult{Name: "ingress:container", Result: "PASS", Message: "orca-traefik container running"})
+		} else if v == "false" {
+			results = append(results, ingressCheckResult{Name: "ingress:container", Result: "FAIL", Message: "orca-traefik container is stopped"})
+		} else {
+			results = append(results, ingressCheckResult{Name: "ingress:container", Result: "FAIL", Message: "orca-traefik container not found"})
+		}
+	}
+
+	// 2. Check nft DNAT + SNAT (reuse the nft table output).
+	tableOut, tableErr := t.Exec(ctx, peer, "nft list table inet orca-ingress 2>/dev/null")
+	if tableErr != nil {
+		results = append(results, ingressCheckResult{Name: "ingress:nft", Result: "FAIL", Message: "nft table orca-ingress missing"})
+	} else {
+		tableStr := string(tableOut)
+		hasDNAT := strings.Contains(tableStr, "dnat to")
+		hasSNAT := strings.Contains(tableStr, "masquerade")
+		if hasDNAT && hasSNAT {
+			results = append(results, ingressCheckResult{Name: "ingress:nft", Result: "PASS", Message: "nft DNAT + SNAT masquerade present"})
+		} else if hasDNAT {
+			results = append(results, ingressCheckResult{Name: "ingress:nft", Result: "WARN", Message: "DNAT present but SNAT masquerade missing"})
+		} else {
+			results = append(results, ingressCheckResult{Name: "ingress:nft", Result: "FAIL", Message: "nft DNAT missing"})
+		}
+	}
+
+	// 3. Check /etc/traefik/dynamic directory exists.
+	if _, err := t.Exec(ctx, peer, "test -d /etc/traefik/dynamic"); err != nil {
+		results = append(results, ingressCheckResult{Name: "ingress:dynamic-dir", Result: "FAIL", Message: "/etc/traefik/dynamic directory missing"})
+	} else {
+		results = append(results, ingressCheckResult{Name: "ingress:dynamic-dir", Result: "PASS", Message: "/etc/traefik/dynamic exists"})
+	}
+
+	// 4. Check step-ca root CA is mounted/present.
+	if _, err := t.Exec(ctx, peer, "test -f /etc/orca/step-ca-root.crt"); err != nil {
+		results = append(results, ingressCheckResult{Name: "ingress:ca", Result: "WARN", Message: "/etc/orca/step-ca-root.crt missing (TLS not configured)"})
+	} else {
+		results = append(results, ingressCheckResult{Name: "ingress:ca", Result: "PASS", Message: "step-ca root CA present"})
+	}
+
+	return results
+}
+
+func init() {
+	doctorCmd.AddCommand(doctorIngressCmd)
+}