Add KVM provider transport: SSH-forwarded libvirt connections and error classification

Per-host connection pool over SSH with the libvirt unix socket forwarded through the session, lazy dial and redial after disconnect, context cancellation for go-libvirt's context-less RPCs, handshake deadline and SSH keepalives. Error classification onto the provider taxonomy. Tested with a fake dialer and an in-process SSH server that forwards unix sockets. Step 3 of docs/plans/2026-09-04-1404-kvm-provider.md. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-10 19:13:51 +00:00
parent 162607dfe2
commit 6322184d50
7 changed files with 1059 additions and 2 deletions
@@ -0,0 +1,67 @@
+package kvm
+
+import (
+	"context"
+	"errors"
+	"fmt"
+	"io"
+	"testing"
+
+	libvirt "github.com/digitalocean/go-libvirt"
+
+	"gitea.home.hrajfrisbee.cz/kacerr/egress-proxies-operator/internal/provider"
+)
+
+func lvErr(code libvirt.ErrorNumber) error {
+	return libvirt.Error{Code: uint32(code), Message: code.String()}
+}
+
+func TestClassify(t *testing.T) {
+	t.Parallel()
+	tests := []struct {
+		name string
+		err  error
+		want error
+	}{
+		{"no domain", lvErr(libvirt.ErrNoDomain), provider.ErrNotFound},
+		{"no storage vol", lvErr(libvirt.ErrNoStorageVol), provider.ErrNotFound},
+		{"no storage pool", lvErr(libvirt.ErrNoStoragePool), provider.ErrPermanent},
+		{"xml error", lvErr(libvirt.ErrXMLError), provider.ErrPermanent},
+		{"xml detail", lvErr(libvirt.ErrXMLDetail), provider.ErrPermanent},
+		{"config unsupported", lvErr(libvirt.ErrConfigUnsupported), provider.ErrPermanent},
+		{"no support", lvErr(libvirt.ErrNoSupport), provider.ErrPermanent},
+		{"invalid arg", lvErr(libvirt.ErrInvalidArg), provider.ErrPermanent},
+		{"auth failed", lvErr(libvirt.ErrAuthFailed), provider.ErrPermanent},
+		{"access denied", lvErr(libvirt.ErrAccessDenied), provider.ErrPermanent},
+		{"operation invalid", lvErr(libvirt.ErrOperationInvalid), provider.ErrTransient},
+		{"operation failed", lvErr(libvirt.ErrOperationFailed), provider.ErrTransient},
+		{"internal error", lvErr(libvirt.ErrInternalError), provider.ErrTransient},
+		{"storage vol exists", lvErr(libvirt.ErrStorageVolExist), provider.ErrTransient},
+		{"wrapped libvirt error", fmt.Errorf("defining: %w", lvErr(libvirt.ErrNoDomain)), provider.ErrNotFound},
+		{"transport eof", io.EOF, provider.ErrTransient},
+		{"context cancelled", context.Canceled, provider.ErrTransient},
+		{"plain error", errors.New("ssh: handshake failed"), provider.ErrTransient},
+	}
+	for _, tc := range tests {
+		t.Run(tc.name, func(t *testing.T) {
+			t.Parallel()
+			if got := classify(tc.err); !errors.Is(got, tc.want) {
+				t.Errorf("classify(%v) = %v, want %v", tc.err, got, tc.want)
+			}
+		})
+	}
+}
+
+func TestHasCode(t *testing.T) {
+	t.Parallel()
+	err := fmt.Errorf("lookup: %w", lvErr(libvirt.ErrNoDomain))
+	if !hasCode(err, libvirt.ErrNoDomain) {
+		t.Error("hasCode(ErrNoDomain) = false through a wrap")
+	}
+	if hasCode(err, libvirt.ErrNoStorageVol) {
+		t.Error("hasCode(ErrNoStorageVol) = true for an ErrNoDomain error")
+	}
+	if hasCode(io.EOF, libvirt.ErrNoDomain) || isLibvirtError(io.EOF) {
+		t.Error("io.EOF classified as a libvirt error")
+	}
+}