c90f145a05
Add high-availability cluster support to the embedded NATS server (issue 0003a, first phase of decentralization). pkg/embeddednats: - ServerConfig gains ServerName (unique per node, required by JetStream RAFT) and an optional *ClusterConfig (cluster name, route host/port, peer route URLs, shared-secret Username/Password, and a mutual-TLS *tls.Config). applyClusterOpts maps it onto server.Options.Cluster + Routes. Nil Cluster keeps the legacy standalone server. pkg/busauth: - RouteTLSConfig builds the route layer's mutual-TLS config: the node presents its CA-signed certificate AND verifies the peer's certificate against the bus CA (RequireAndVerifyClientCert), reusing the issue-0001 CA. Routes authenticate NODES, never the client nkey authenticator. cmd/membershipd: - Cluster flags (--cluster-name/--server-name/--cluster-port/--routes/ --cluster-user/--cluster-pass/--route-tls-cert/-key/-ca) wire a node into the cluster. validateClusterConfig refuses a public cluster without a route secret and complete mutual route TLS, and rejects partial route-TLS flags (all-or-nothing). splitRoutes parses the CSV. Tests (DoD: golden + 2 edge + error path): - TestClusterForwardsAcrossNodes: 2-node cluster forwards a client subject from one node to a subscriber on the other. - TestClusterThreeNodesForward: 3-node (HA shape) cross-node forwarding. - TestClusterMutualTLSForwards: forwarding over mutual-TLS routes. - TestClusterRejectsBadRouteAuth: wrong cluster password -> no route. - TestClusterRejectsUnsignedNode: cert not signed by the bus CA -> no route. - TestClusterConfigPolicy / TestSplitRoutes: boot-guard + CSV parsing. Master stays green: standalone (no --cluster-name) is unchanged.
104 lines
4.2 KiB
Go
104 lines
4.2 KiB
Go
package main
|
|
|
|
import (
|
|
"fmt"
|
|
"net"
|
|
"strings"
|
|
|
|
"github.com/enmanuel/unibus/pkg/membership"
|
|
)
|
|
|
|
// splitRoutes parses the comma-separated --routes flag into a clean slice of
|
|
// route URLs, dropping empty entries and surrounding whitespace so a trailing
|
|
// comma or a spaced list does not yield a bogus empty route.
|
|
func splitRoutes(csv string) []string {
|
|
var out []string
|
|
for _, r := range strings.Split(csv, ",") {
|
|
if r = strings.TrimSpace(r); r != "" {
|
|
out = append(out, r)
|
|
}
|
|
}
|
|
return out
|
|
}
|
|
|
|
// isLoopbackBind reports whether the --bind value keeps the service reachable
|
|
// only from this host. An empty bind means "all interfaces" (public), and a
|
|
// hostname we cannot resolve to a loopback literal is treated as public — the
|
|
// conservative choice, so an unusual bind never silently slips past the guard.
|
|
func isLoopbackBind(bind string) bool {
|
|
switch bind {
|
|
case "localhost":
|
|
return true
|
|
case "":
|
|
return false // empty binds every interface
|
|
}
|
|
ip := net.ParseIP(bind)
|
|
if ip == nil {
|
|
return false // a hostname we can't classify: assume public
|
|
}
|
|
return ip.IsLoopback()
|
|
}
|
|
|
|
// validateBootConfig is the fail-open guard (audit H2). It refuses any startup
|
|
// configuration that would expose the bus without enforced authentication:
|
|
//
|
|
// - a non-loopback --bind without --bus-auth enforce (the data plane and
|
|
// control plane would both accept anyone), and
|
|
// - --tls-cert/--tls-key without --bus-auth enforce (TLS encrypts the channel
|
|
// but authenticates no one — encrypted access for everybody is still open).
|
|
//
|
|
// It is a pure function of the parsed flags so the command can fail fast at
|
|
// startup and tests can assert the policy without booting a server.
|
|
func validateBootConfig(bind string, mode membership.AuthMode, tlsCert, tlsKey string) error {
|
|
if !isLoopbackBind(bind) && mode != membership.AuthEnforce {
|
|
return fmt.Errorf(
|
|
"refusing to start: --bind %q is not loopback but --bus-auth is %q; a public bind requires --bus-auth enforce (or bind 127.0.0.1 for local dev)",
|
|
bind, mode)
|
|
}
|
|
if (tlsCert != "" || tlsKey != "") && mode != membership.AuthEnforce {
|
|
return fmt.Errorf(
|
|
"refusing to start: --tls-cert/--tls-key set but --bus-auth is %q; TLS without enforced auth is fail-open (encrypted channel, no authentication) — set --bus-auth enforce",
|
|
mode)
|
|
}
|
|
return nil
|
|
}
|
|
|
|
// validateClusterConfig guards the cluster route layer (issue 0003a). The route
|
|
// layer is a server-to-server trust boundary distinct from the client data
|
|
// plane: leaving it open lets anyone who reaches the route port join the cluster
|
|
// or inject messages into the whole bus (audit 0004, "auth of the cluster
|
|
// routes"). So on a public (non-loopback) bind, a cluster MUST carry both a
|
|
// shared route secret AND mutual route TLS. It is a pure function of the parsed
|
|
// flags. An empty clusterName means "no cluster" (standalone) and is always
|
|
// allowed.
|
|
//
|
|
// The three route-TLS paths are all-or-nothing (mutual TLS needs the node cert,
|
|
// its key, and the CA together), independent of the bind, so a partial TLS
|
|
// config never silently degrades to plaintext routes.
|
|
func validateClusterConfig(clusterName, bind, user, pass, rtCert, rtKey, rtCA string) error {
|
|
rtAny := rtCert != "" || rtKey != "" || rtCA != ""
|
|
rtAll := rtCert != "" && rtKey != "" && rtCA != ""
|
|
if rtAny && !rtAll {
|
|
return fmt.Errorf(
|
|
"refusing to start: --route-tls-cert/--route-tls-key/--route-tls-ca must be set together (mutual route TLS needs all three)")
|
|
}
|
|
if clusterName == "" {
|
|
return nil // standalone: no route layer to secure
|
|
}
|
|
if isLoopbackBind(bind) {
|
|
return nil // loopback cluster is dev-only and unreachable from outside
|
|
}
|
|
// Public cluster: demand a route secret and mutual route TLS.
|
|
if user == "" || pass == "" {
|
|
return fmt.Errorf(
|
|
"refusing to start: cluster %q on public bind %q requires --cluster-user and --cluster-pass; an unauthenticated route port lets anyone join the cluster",
|
|
clusterName, bind)
|
|
}
|
|
if !rtAll {
|
|
return fmt.Errorf(
|
|
"refusing to start: cluster %q on public bind %q requires mutual route TLS (--route-tls-cert/--route-tls-key/--route-tls-ca); plaintext routes expose server-to-server traffic and admit unsigned nodes",
|
|
clusterName, bind)
|
|
}
|
|
return nil
|
|
}
|