14642e3c7b
A managed box's IP was invisible in every operator surface because nothing reported one: HostMetrics carried node/cpu/mem/disk/load/uptime/temp/wrapper-sha and no address of any kind. The hub could not show a host's LAN IP anywhere. Two things that looked like the answer are traps, both checked before writing code: lan_resolver.host_ip is an OPTIONAL config value absent unless that feature is configured, and DeriveHostIP(local_api.listen_addr) returns 169.254.253.1 — since R-50 the local API binds a link-local address identical on every box. Both would have produced a confident wrong answer. New wire field addresses[], one entry per (interface, address). Deliberately iface+cidr rather than a single lan_ip: a Proxmox host legitimately holds several (management bridge, tailnet, WG tunnel) and picking one to call "the" LAN IP is a guess the agent is not entitled to make — silently wrong on a box whose bridge is not vmbr0. The agent reports what exists; the hub does the labelling. The filter is one predicate, chosen by MEASURING both demo hosts rather than by reasoning about interface names. IsGlobalUnicast() alone drops loopback, IPv6 link-local (one per bridge, pure noise) and IPv4 link-local (169.254/16 — exactly the island address above). It needs no veth/fwbr/tap denylist: that per-guest plumbing carries no IP at all and self-excludes, verified on both boxes. No new privilege and no block I/O — net.Interfaces() is a netlink/procfs read, so the sudoers fence is untouched and the health-check rule is honoured. The seam DEFAULTS to the real enumerator, inverting the nil-reporter-means-off convention: this stanza has no config gate, so a forgotten wiring call would have shipped it silently empty — the inert-seam failure recorded four times here. Cross-repo: the golden is duplicated byte-identically in felhom.eu and the contract test fails on top-level key drift, so both goldens moved together and addresses[0]'s key set is asserted bidirectionally. The field marshals as [], never null — the repo's own no-nulls invariant caught that on the first run. Tests +9; three red-proofs (global-unicast filter, down-interface guard, inert collectAddresses) each run, observed failing, and reverted.
215 lines
8.8 KiB
Go
215 lines
8.8 KiB
Go
package hub
|
|
|
|
import (
|
|
"errors"
|
|
"log/slog"
|
|
"strings"
|
|
"testing"
|
|
)
|
|
|
|
// The fixtures below are MEASURED, not invented: `ip -o addr show` on demo-felhom (N100) and
|
|
// demo-hp (HP t740) on 2026-07-31, transcribed verbatim including the interfaces that carry no
|
|
// address. That matters — the filter's claim that it needs no veth/fwbr denylist rests on those
|
|
// interfaces genuinely having nothing to report, and a hand-written fixture that omitted them would
|
|
// have proved the claim by assuming it.
|
|
|
|
// demoFelhomIfaces is demo-felhom's real interface table.
|
|
func demoFelhomIfaces() []ifaceAddrs {
|
|
return []ifaceAddrs{
|
|
{Name: "lo", Up: true, Loopback: true, CIDRs: []string{"127.0.0.1/8", "::1/128"}},
|
|
{Name: "enp1s0", Up: false}, // physical NIC, no address
|
|
{Name: "wlp2s0", Up: false}, // wifi, no address
|
|
{Name: "tailscale0", Up: true, CIDRs: []string{
|
|
"100.70.170.35/32", "fd7a:115c:a1e0::5236:aa24/128", "fe80::4197:26fc:ccba:b0d9/64"}},
|
|
{Name: "vmbr0", Up: true, CIDRs: []string{"192.168.0.162/24", "fe80::6a1d:efff:fe5d:a664/64"}},
|
|
{Name: "veth9201i0", Up: true}, // per-guest plumbing — no address
|
|
{Name: "veth9201i1", Up: true}, // per-guest plumbing — no address
|
|
{Name: "vmbr9", Up: true, CIDRs: []string{"169.254.253.1/30", "fe80::48d4:f6ff:fe05:2f98/64"}},
|
|
{Name: "wg-felhom", Up: true, CIDRs: []string{"10.77.0.2/32"}},
|
|
}
|
|
}
|
|
|
|
func hasAddr(got []HostAddress, iface, cidr string) bool {
|
|
for _, a := range got {
|
|
if a.Iface == iface && a.CIDR == cidr {
|
|
return true
|
|
}
|
|
}
|
|
return false
|
|
}
|
|
|
|
func flatten(got []HostAddress) string {
|
|
var b strings.Builder
|
|
for _, a := range got {
|
|
b.WriteString(a.Iface + "=" + a.CIDR + " ")
|
|
}
|
|
return b.String()
|
|
}
|
|
|
|
// The LAN address is the whole point of the feature — it must survive the filter.
|
|
// RED-PROOF 1: drop the `!p.Addr().IsGlobalUnicast()` continue → the vmbr9 + fe80 assertions below
|
|
// go red (the LAN one still passes, which is exactly why the negatives are asserted too).
|
|
func TestFilterHostAddresses_RealHost(t *testing.T) {
|
|
got := filterHostAddresses(demoFelhomIfaces())
|
|
|
|
// --- what MUST be there ---
|
|
if !hasAddr(got, "vmbr0", "192.168.0.162/24") {
|
|
t.Fatalf("the LAN address was filtered away — the feature reports nothing: %s", flatten(got))
|
|
}
|
|
if !hasAddr(got, "wg-felhom", "10.77.0.2/32") {
|
|
t.Errorf("the WireGuard address was filtered away: %s", flatten(got))
|
|
}
|
|
if !hasAddr(got, "tailscale0", "100.70.170.35/32") {
|
|
t.Errorf("the tailnet address was filtered away: %s", flatten(got))
|
|
}
|
|
|
|
// --- what MUST NOT be there, each for its own reason ---
|
|
for _, bad := range []struct{ iface, cidr, why string }{
|
|
{"lo", "127.0.0.1/8", "loopback is not an address of the host on any network"},
|
|
{"lo", "::1/128", "IPv6 loopback"},
|
|
{"vmbr9", "169.254.253.1/30", "the R-50 island literal — IDENTICAL on every box, so surfacing it is actively misleading"},
|
|
{"vmbr0", "fe80::6a1d:efff:fe5d:a664/64", "IPv6 link-local, one per bridge, pure noise"},
|
|
{"tailscale0", "fe80::4197:26fc:ccba:b0d9/64", "IPv6 link-local"},
|
|
} {
|
|
if hasAddr(got, bad.iface, bad.cidr) {
|
|
t.Errorf("%s %s must be filtered (%s); got: %s", bad.iface, bad.cidr, bad.why, flatten(got))
|
|
}
|
|
}
|
|
|
|
// The no-denylist claim: not one veth/physical interface contributed a row.
|
|
for _, a := range got {
|
|
if strings.HasPrefix(a.Iface, "veth") || a.Iface == "enp1s0" || a.Iface == "wlp2s0" {
|
|
t.Errorf("%s produced a row — the fixture says it has no address, so the filter invented one", a.Iface)
|
|
}
|
|
}
|
|
}
|
|
|
|
// demo-hp is different hardware (4 unused NICs, different ordering) and must filter identically —
|
|
// the rule is about address CLASS, not about one box's interface names.
|
|
func TestFilterHostAddresses_SecondHostFiltersIdentically(t *testing.T) {
|
|
got := filterHostAddresses([]ifaceAddrs{
|
|
{Name: "lo", Up: true, Loopback: true, CIDRs: []string{"127.0.0.1/8", "::1/128"}},
|
|
{Name: "enp2s0f0", Up: false}, {Name: "enp1s0f0", Up: false},
|
|
{Name: "enp1s0f1", Up: false}, {Name: "enp1s0f2", Up: false},
|
|
{Name: "enp1s0f3", Up: false}, {Name: "wlo1", Up: false},
|
|
{Name: "tailscale0", Up: true, CIDRs: []string{
|
|
"100.76.96.79/32", "fd7a:115c:a1e0::ce36:6051/128", "fe80::e06a:ce64:80e1:7821/64"}},
|
|
{Name: "vmbr0", Up: true, CIDRs: []string{"192.168.0.87/24", "fe80::7ed3:aff:fe77:d976/64"}},
|
|
{Name: "wg-felhom", Up: true, CIDRs: []string{"10.77.0.3/32"}},
|
|
{Name: "vmbr9", Up: true, CIDRs: []string{"169.254.253.1/30", "fe80::2484:92ff:fe7d:52a5/64"}},
|
|
{Name: "veth9201i0", Up: true}, {Name: "veth9201i1", Up: true},
|
|
})
|
|
if !hasAddr(got, "vmbr0", "192.168.0.87/24") {
|
|
t.Fatalf("demo-hp's LAN address was filtered away: %s", flatten(got))
|
|
}
|
|
if hasAddr(got, "vmbr9", "169.254.253.1/30") {
|
|
t.Errorf("demo-hp's island address leaked through: %s", flatten(got))
|
|
}
|
|
// The island address is byte-identical on both boxes — the strongest argument for excluding it.
|
|
if strings.Contains(flatten(got), "169.254.") {
|
|
t.Errorf("a link-local IPv4 survived: %s", flatten(got))
|
|
}
|
|
}
|
|
|
|
// A DOWN interface holding a stale address must not be reported as if the box were reachable there.
|
|
// RED-PROOF 2: drop `|| !i.Up` → this goes red.
|
|
func TestFilterHostAddresses_DownInterfaceExcluded(t *testing.T) {
|
|
got := filterHostAddresses([]ifaceAddrs{
|
|
{Name: "vmbr0", Up: true, CIDRs: []string{"192.168.0.162/24"}},
|
|
{Name: "vmbr1", Up: false, CIDRs: []string{"10.9.9.9/24"}},
|
|
})
|
|
if hasAddr(got, "vmbr1", "10.9.9.9/24") {
|
|
t.Errorf("a DOWN interface's address was reported: %s", flatten(got))
|
|
}
|
|
if len(got) != 1 {
|
|
t.Errorf("want exactly the one up interface, got: %s", flatten(got))
|
|
}
|
|
}
|
|
|
|
// Order must be deterministic, or every report diff shows phantom churn.
|
|
func TestFilterHostAddresses_DeterministicOrder(t *testing.T) {
|
|
a := filterHostAddresses(demoFelhomIfaces())
|
|
// Same facts, opposite enumeration order.
|
|
rev := demoFelhomIfaces()
|
|
for i, j := 0, len(rev)-1; i < j; i, j = i+1, j-1 {
|
|
rev[i], rev[j] = rev[j], rev[i]
|
|
}
|
|
b := filterHostAddresses(rev)
|
|
if flatten(a) != flatten(b) {
|
|
t.Errorf("interface-table order changed the report:\n a=%s\n b=%s", flatten(a), flatten(b))
|
|
}
|
|
}
|
|
|
|
// A host with nothing routable yields [] and never nil — an absent key and "no addresses" must not
|
|
// look alike on the wire.
|
|
func TestFilterHostAddresses_EmptyIsNonNil(t *testing.T) {
|
|
got := filterHostAddresses([]ifaceAddrs{{Name: "lo", Up: true, Loopback: true, CIDRs: []string{"127.0.0.1/8"}}})
|
|
if got == nil {
|
|
t.Fatal("filter returned nil — it would marshal as null, not []")
|
|
}
|
|
if len(got) != 0 {
|
|
t.Errorf("want no addresses, got %s", flatten(got))
|
|
}
|
|
}
|
|
|
|
// A malformed entry is skipped, never fatal — one bad address must not cost the report the others.
|
|
func TestFilterHostAddresses_MalformedSkipped(t *testing.T) {
|
|
got := filterHostAddresses([]ifaceAddrs{
|
|
{Name: "vmbr0", Up: true, CIDRs: []string{"not-an-address", "192.168.0.162/24"}},
|
|
})
|
|
if len(got) != 1 || !hasAddr(got, "vmbr0", "192.168.0.162/24") {
|
|
t.Errorf("a malformed sibling address broke the good one: %s", flatten(got))
|
|
}
|
|
}
|
|
|
|
// --- the WIRING half: the collector must actually call the filter ---
|
|
|
|
// The seam defaults to the REAL enumerator, so a forgotten wiring call cannot make this inert.
|
|
// RED-PROOF 3: replace the collectAddresses body with `return []HostAddress{}` → red.
|
|
func TestCollectAddresses_UsesTheInjectedEnumerator(t *testing.T) {
|
|
c := &Collector{logger: slog.Default()}
|
|
c.addrEnum = func() ([]ifaceAddrs, error) { return demoFelhomIfaces(), nil }
|
|
got := c.collectAddresses()
|
|
if !hasAddr(got, "vmbr0", "192.168.0.162/24") {
|
|
t.Fatalf("the collector did not run the filter over the enumerator's output: %s", flatten(got))
|
|
}
|
|
}
|
|
|
|
// An enumeration failure degrades to [] and a WARN — never a failed report.
|
|
func TestCollectAddresses_EnumerationErrorDegrades(t *testing.T) {
|
|
c := &Collector{logger: slog.Default()}
|
|
c.addrEnum = func() ([]ifaceAddrs, error) { return nil, errors.New("netlink is unhappy") }
|
|
got := c.collectAddresses()
|
|
if got == nil {
|
|
t.Fatal("an enumeration error produced nil, which marshals as null")
|
|
}
|
|
if len(got) != 0 {
|
|
t.Errorf("want [] on error, got %s", flatten(got))
|
|
}
|
|
}
|
|
|
|
// The production enumerator must return SOMETHING on the machine running the tests, and must not
|
|
// panic. This is the only test that touches the real network stack; it asserts the contract
|
|
// (non-nil, no error, loopback correctly flagged) rather than any specific address, because the
|
|
// test host's addresses are not ours to predict.
|
|
func TestSystemInterfaces_ProductionEnumeratorWorks(t *testing.T) {
|
|
ifaces, err := systemInterfaces()
|
|
if err != nil {
|
|
t.Fatalf("systemInterfaces: %v", err)
|
|
}
|
|
if len(ifaces) == 0 {
|
|
t.Fatal("no interfaces at all — even a container has lo")
|
|
}
|
|
var sawLoopback bool
|
|
for _, i := range ifaces {
|
|
if i.Loopback {
|
|
sawLoopback = true
|
|
}
|
|
}
|
|
if !sawLoopback {
|
|
t.Error("no interface reported the loopback flag — the flag mapping is wrong")
|
|
}
|
|
// And the filter must survive real input without panicking.
|
|
_ = filterHostAddresses(ifaces)
|
|
}
|