Files
mesh-controller/internal/catalogue/facts_test.go
T
jochen 51163b9f14 The mesh's names are written into the hosts file, not over it (hq 128)
/etc/hosts is the machine's: the distribution's localhost lines, the
operator's own entries, and marked blocks other tools maintain there.
Writing node-names whole replaced all of it the moment the private
network was taken, and every later write by those tools was lost at
the next machine joining. The node-names fact is now emitted with
into: "block", so the host owns only its marked region and keeps the
rest byte for byte. The region holds only the mesh's names: no header
claiming the file, no localhost, no 127.0.1.1 line — the floor was
never the mesh's to write. How a fact is written is a property of the
fact in the closed table; node-zones stays a whole file the mesh owns.

Sequencing: a host older than the block mode refuses the whole
declaration on an unknown into, so every host must be upgraded before
this controller is rolled out.
2026-09-26 23:46:51 +02:00

240 lines
11 KiB
Go

package catalogue
import (
"strings"
"testing"
)
// Keyed by the internal name, as the control plane hands them (issue 079).
var threeMachines = map[string]string{"homer.internal": "10.42.0.1", "marge.internal": "10.42.0.2", "bart.internal": ""}
// **`*.homer.internal` is homer. That is the whole rule.** And the suffix itself is local: a
// resolver that forwards what it cannot answer must not send a mesh name it does not know — a
// machine that left, a typo — to a public resolver (hal dnsmasq-app conversion, novox/hq
// 08-connectivity).
func TestEveryMachineIsAWildcardUnderItsOwnName(t *testing.T) {
out := nodeZones(Resolution{Node: "homer"}, threeMachines, "")
for _, want := range []string{
"local=/internal/",
"address=/homer.internal/10.42.0.1",
"address=/marge.internal/10.42.0.2",
} {
if !strings.Contains(out, want) {
t.Fatalf("missing %q:\n%s", want, out)
}
}
}
// A machine the mesh has a record for and cannot place is left out of both.
//
// **Not an oversight — the alternative is worse.** A name written with no address resolves to
// nothing, and a connection to that hangs. Leaving it out fails at once and says the name is
// unknown, which is a thing somebody can act on.
func TestAMachineWithNoAddressIsNotNamed(t *testing.T) {
for _, out := range []string{
nodeNames(Resolution{Node: "homer"}, threeMachines, ""),
nodeZones(Resolution{Node: "homer"}, threeMachines, ""),
} {
if strings.Contains(out, "bart") {
t.Fatalf("a machine with no address was named, so its name resolves to nothing:\n%s", out)
}
}
}
// A machine's own mesh name points at its address on the private network, not at loopback — or a
// service binding the name it was given is unreachable from everywhere else.
func TestAMachinesOwnNameIsItsMeshAddress(t *testing.T) {
out := nodeNames(Resolution{Node: "homer"}, threeMachines, "")
var line string
for _, l := range strings.Split(out, "\n") {
if strings.Contains(l, "homer.internal") {
line = l
}
}
if !strings.HasPrefix(line, "10.42.0.1") {
t.Fatalf("a machine's own mesh name is not its mesh address: %q", line)
}
}
// novox/hq issue 128: the names are the mesh's region of the machine's hosts file, and only that.
//
// **The loopback floor is the machine's now, not the mesh's.** It was written here while the mesh
// wrote the whole file. Written into a region, a `localhost` or a `127.0.1.1 homer` of the mesh's
// would stand beside the distribution's own — a second answer nobody could say the owner of, and
// one that goes when the mesh leaves. A header claiming the file would be a lie about the rest of
// it. And no line may look like the host's own markers, or the host would refuse the region.
func TestTheNamesAreOnlyTheMeshsRegionOfTheFile(t *testing.T) {
out := nodeNames(Resolution{Node: "homer"}, threeMachines, "")
want := "# The mesh's names. This region is replaced whenever a machine joins or leaves.\n" +
"10.42.0.1\thomer.internal\thomer\t# this machine\n" +
"10.42.0.2\tmarge.internal\tmarge\n"
if out != want {
t.Fatalf("the region is not exactly the mesh's names:\n%s\n--- want ---\n%s", out, want)
}
for _, floor := range []string{"localhost", "127.0.", "::1", "Generated by the mesh", "# BEGIN mesh ", "# END mesh "} {
if strings.Contains(out, floor) {
t.Fatalf("the region carries %q, which is not the mesh's to write:\n%s", floor, out)
}
}
}
// The hosts file is written into; the resolver's zones are written whole. A property of each fact,
// so a module asking for node-names at another path still does not get a file of the mesh's.
func TestOnlyTheNamesAreWrittenIntoASharedFile(t *testing.T) {
m := Manifest{Module: "resolver", Facts: map[string]string{
FactNodeZones: "/etc/mesh-resolver/nodes.conf", FactNodeNames: "/etc/hosts",
}}
given, err := FactsInto(m, Resolution{Node: "homer"}, threeMachines, threeMachines, "")
if err != nil {
t.Fatal(err)
}
if len(given) != 2 {
t.Fatalf("expected two files, got %v", given)
}
for _, f := range given {
switch f["path"] {
case "/etc/hosts":
if f["into"] != "block" {
t.Errorf("the hosts file is written over rather than into: %v", f)
}
case "/etc/mesh-resolver/nodes.conf":
// The mesh owns the resolver's zones; nothing else writes there.
if into, set := f["into"]; set {
t.Errorf("the zones file is written into (%v), and it is the mesh's whole", into)
}
if !strings.HasPrefix(f["content"].(string), "# Generated by the mesh.") {
t.Errorf("the zones file lost its header: %v", f["content"])
}
default:
t.Errorf("a file nobody asked for: %v", f)
}
}
}
// A module says where it wants a fact, and is given a file.
func TestAModuleIsGivenTheFactsItAskedFor(t *testing.T) {
m := Manifest{Module: "dnsmasq", Facts: map[string]string{FactNodeZones: "/etc/mesh/zones.conf"}}
given, err := FactsInto(m, Resolution{Node: "homer"}, threeMachines, threeMachines, "")
if err != nil {
t.Fatal(err)
}
if len(given) != 1 {
t.Fatalf("expected one file, got %d", len(given))
}
if given[0]["path"] != "/etc/mesh/zones.conf" || given[0]["type"] != "file" {
t.Fatalf("not written where it was asked for: %v", given[0])
}
if !strings.Contains(given[0]["content"].(string), "homer.internal") {
t.Fatalf("the file does not hold the fact: %v", given[0]["content"])
}
}
// **Asking for a fact the mesh does not have is refused here, not on a machine.** A daemon that
// starts, reads a file nobody wrote, and answers no queries is a much worse way to find out.
func TestAskingForAFactTheMeshDoesNotHaveIsRefused(t *testing.T) {
m := Manifest{Module: "dnsmasq", Facts: map[string]string{"the-weather": "/etc/weather"}}
_, err := FactsInto(m, Resolution{}, nil, nil, "")
if err == nil {
t.Fatal("a module asked for something nobody computes and was given nothing, silently")
}
for _, known := range []string{FactNodeNames, FactNodeZones} {
if !strings.Contains(err.Error(), known) {
t.Fatalf("the refusal does not say what would have worked: %v", err)
}
}
}
// And a relative path is refused, or a module decides where the mesh writes on a machine.
func TestAFactMustBeAskedForAtAnAbsolutePath(t *testing.T) {
m := Manifest{Module: "dnsmasq", Facts: map[string]string{FactNodeNames: "etc/hosts"}}
if _, err := FactsInto(m, Resolution{}, nil, nil, ""); err == nil {
t.Fatal("a relative path was accepted")
}
}
// **The names the control plane hands a resolution are already internal names** — `homer.internal`,
// the same map every container gets as its hosts. Appending the suffix again wrote
// `homer.internal.internal` into every hosts file and every resolver's zones, and the large mesh
// bed's name test was the first to read it back. Either key gives the same files.
func TestNamesKeyedByInternalNameAreNotSuffixedTwice(t *testing.T) {
internal := map[string]string{"homer.internal": "10.42.0.1", "marge.internal": "10.42.0.2"}
bare := map[string]string{"homer": "10.42.0.1", "marge": "10.42.0.2"}
if a, b := nodeZones(Resolution{Node: "homer"}, internal, ""), nodeZones(Resolution{Node: "homer"}, bare, ""); a != b {
t.Fatalf("the zones differ by how the names were keyed:\n%s\n---\n%s", a, b)
}
if a, b := nodeNames(Resolution{Node: "homer"}, internal, ""), nodeNames(Resolution{Node: "homer"}, bare, ""); a != b {
t.Fatalf("the hosts differ by how the names were keyed:\n%s\n---\n%s", a, b)
}
zones := nodeZones(Resolution{Node: "homer"}, internal, "")
if strings.Contains(zones, "internal.internal") || !strings.Contains(zones, "address=/homer.internal/10.42.0.1") {
t.Fatalf("the zones carry a doubled suffix or miss the name:\n%s", zones)
}
hosts := nodeNames(Resolution{Node: "homer"}, internal, "")
if !strings.Contains(hosts, "10.42.0.1\thomer.internal\thomer\t# this machine") {
t.Fatalf("the hosts line for the machine itself is not name, bare name and the mark:\n%s", hosts)
}
}
// The suffix the control plane composed the names with is the one the facts write — an operator
// who chose another does not get `.internal` appended to it.
func TestTheFactsWriteTheSuffixTheNamesWereComposedWith(t *testing.T) {
names := map[string]string{"homer.lan": "10.42.0.1"}
zones := nodeZones(Resolution{Node: "homer"}, names, "lan")
if !strings.Contains(zones, "address=/homer.lan/10.42.0.1") || strings.Contains(zones, "internal") {
t.Fatalf("the zones do not carry the operator's suffix as given:\n%s", zones)
}
if !strings.Contains(zones, "local=/lan/") {
t.Fatalf("the local domain is not the operator's suffix, so its names would leak upstream:\n%s", zones)
}
hosts := nodeNames(Resolution{Node: "homer"}, names, "lan")
if !strings.Contains(hosts, "10.42.0.1\thomer.lan\thomer\t# this machine") {
t.Fatalf("the hosts line does not carry the operator's suffix as given:\n%s", hosts)
}
}
// novox/hq 04-ISSUES/111: the map the control plane hands a resolution holds every name the mesh
// serves — the machines, and the names it was told to route to whichever machine serves them. A
// container's hosts wants all of it. A resolver's zones want only the machines: told the mesh's
// suffix is its own, it answers authoritatively for everything under it and forwards nothing, so a
// routed name written there with the suffix appended is a name nobody will ever ask for, standing
// beside the machines and looking as real.
func TestTheResolverIsToldTheMachinesAndNotTheNamesTheMeshMerelyServes(t *testing.T) {
machines := map[string]string{"homer.internal": "10.42.0.1", "marge.internal": "10.42.0.2"}
every := map[string]string{
"homer.internal": "10.42.0.1", "marge.internal": "10.42.0.2",
"drive.example.test": "10.42.0.1", "git.example.test": "10.42.0.2",
}
m := Manifest{Module: "resolver", Facts: map[string]string{
FactNodeZones: "/etc/zones.conf", FactNodeNames: "/etc/hosts",
}}
given, err := FactsInto(m, Resolution{Node: "homer"}, every, machines, "")
if err != nil {
t.Fatal(err)
}
by := map[string]string{}
for _, f := range given {
by[f["path"].(string)] = f["content"].(string)
}
zones := by["/etc/zones.conf"]
for _, machine := range []string{"address=/homer.internal/10.42.0.1", "address=/marge.internal/10.42.0.2"} {
if !strings.Contains(zones, machine) {
t.Fatalf("the resolver was not told %q:\n%s", machine, zones)
}
}
for _, served := range []string{"drive.example.test", "git.example.test"} {
if strings.Contains(zones, served) {
t.Fatalf("the resolver was told %q, a name the mesh serves rather than a machine:\n%s", served, zones)
}
}
// And the hosts file is the other way about: every name, so a container reaching a routed name
// finds the machine serving it.
hosts := by["/etc/hosts"]
for _, name := range []string{"homer.internal", "drive.example.test", "git.example.test"} {
if !strings.Contains(hosts, name) {
t.Fatalf("a container would not resolve %q from its hosts:\n%s", name, hosts)
}
}
}