Compare commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
fe5988c536 | ||
|
|
ed5d467d90 | ||
|
|
228d0226dd | ||
|
|
6215ff0760 | ||
|
|
54812306be | ||
|
|
ce9e20fbbc | ||
|
|
878690697e | ||
|
|
ad97297576 | ||
|
|
683b1ed693 | ||
|
|
04f9f378b0 | ||
|
|
1c3f44a526 | ||
|
|
89e152dfe2 | ||
|
|
1ebad3786c | ||
|
|
f2f526a60a | ||
|
|
4b4c7e0e0d | ||
|
|
cec792ce9d | ||
|
|
338d033632 | ||
|
|
1be926cec4 | ||
|
|
2134768dfe | ||
|
|
ef825688ee | ||
|
|
77a14360df | ||
|
|
9be2fb4750 | ||
|
|
5a963aec10 | ||
|
|
45d1c28a28 | ||
|
|
a3e7683c63 | ||
|
|
da394b45e6 | ||
|
|
2f3bfda8c0 | ||
|
|
208388978a | ||
|
|
aa771616bb | ||
|
|
1513bbaac9 | ||
|
|
d6e49dbd68 | ||
|
|
3756bb3460 |
@@ -194,6 +194,9 @@ func answer(ctx context.Context, publisher builder.Publisher, on, workspace stri
|
||||
})
|
||||
}
|
||||
result.Against = built.Against
|
||||
for _, r := range built.Read {
|
||||
result.Read = append(result.Read, link.ReadRepository{Repository: r.Repository, Ref: r.Ref})
|
||||
}
|
||||
fmt.Fprintf(os.Stderr, " built %s from %s\n", built.Manifest.Module, short(built.Commit))
|
||||
}
|
||||
}
|
||||
|
||||
@@ -106,6 +106,9 @@ func buildOnce(ctx context.Context, args []string) error {
|
||||
Manifest: built.Manifest,
|
||||
Against: built.Against,
|
||||
}
|
||||
for _, r := range built.Read {
|
||||
out.Read = append(out.Read, readRepository{Repository: r.Repository, Ref: r.Ref})
|
||||
}
|
||||
for _, made := range built.Built {
|
||||
out.Made = append(out.Made, madeArtifact{Name: made.Name, Kind: made.Kind, Reference: made.Reference})
|
||||
}
|
||||
@@ -123,14 +126,21 @@ func buildOnce(ctx context.Context, args []string) error {
|
||||
// The same fields the mesh records for a build, so a reader comparing a genesis build against an
|
||||
// ordinary one is comparing the same thing said the same way.
|
||||
type onceResult struct {
|
||||
Module string `json:"module"`
|
||||
Commit string `json:"commit"`
|
||||
Repository string `json:"repository"`
|
||||
Path string `json:"path,omitempty"`
|
||||
Ref string `json:"ref,omitempty"`
|
||||
Manifest any `json:"manifest"`
|
||||
Made []madeArtifact `json:"made"`
|
||||
Against []string `json:"against,omitempty"`
|
||||
Module string `json:"module"`
|
||||
Commit string `json:"commit"`
|
||||
Repository string `json:"repository"`
|
||||
Path string `json:"path,omitempty"`
|
||||
Ref string `json:"ref,omitempty"`
|
||||
Manifest any `json:"manifest"`
|
||||
Made []madeArtifact `json:"made"`
|
||||
Against []string `json:"against,omitempty"`
|
||||
Read []readRepository `json:"read,omitempty"`
|
||||
}
|
||||
|
||||
// readRepository is a repository this build read source from besides the module's own.
|
||||
type readRepository struct {
|
||||
Repository string `json:"repository"`
|
||||
Ref string `json:"ref,omitempty"`
|
||||
}
|
||||
|
||||
type madeArtifact struct {
|
||||
|
||||
@@ -88,7 +88,7 @@ func reportsReaching(t *testing.T, open *stores, reachable []link.Reach, held ..
|
||||
if err := open.inventory.RecordSent(ctx, record.ID, digestOf(body)); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if err := (link.Enrolment{Inventory: open.inventory}).Heard(ctx, link.Report{
|
||||
if _, err := (link.Enrolment{Inventory: open.inventory}).Heard(ctx, link.Report{
|
||||
Node: "anchor", Applied: []string{"hello-web.x"}, Declared: digestOf(body),
|
||||
Firewall: "ufw", Held: held, Reachable: reachable,
|
||||
}); err != nil {
|
||||
|
||||
@@ -309,7 +309,7 @@ func converge(ctx context.Context, open *stores, node string, yes bool, digest s
|
||||
return "", err
|
||||
}
|
||||
derived := derivedFilter{rules: rules, foundation: with.Foundation, mesh: with.Mesh,
|
||||
outward: plan.PublicDomain != ""}
|
||||
outward: plan.PublicDomain != "", outwardLinks: with.OutwardLinks}
|
||||
preview, saw := previewOf(node, reported, derived, plan, taken, filter, runs[filter])
|
||||
preview += "\n\n preview " + saw
|
||||
if !yes {
|
||||
@@ -414,6 +414,18 @@ func previewOf(node string, reported inventory.Adoption, derived derivedFilter,
|
||||
b.WriteString(" not previewed: traffic the machine routes that is not a published port " +
|
||||
"(a tunnel, NAT in the found firewall) — the derived filter drops it unless a module " +
|
||||
"declares it\n")
|
||||
// Which links the filter constrains, said rather than left to the sentence above (novox/hq ADR
|
||||
// 0140). Everything arriving anywhere else is this machine's own guest and keeps working — which
|
||||
// is what a reader most wants to know, because the previous shape of this filter cut a machine's
|
||||
// guests off at the flip without saying so, and that is how this was found.
|
||||
if len(derived.outwardLinks) > 0 {
|
||||
b.WriteString(fmt.Sprintf(" it filters what arrives on: %s, and on the private network "+
|
||||
"— everything its own guests send keeps working\n",
|
||||
strings.Join(derived.outwardLinks, ", ")))
|
||||
} else {
|
||||
b.WriteString(" it has reported no link facing outside, so no filter can be composed " +
|
||||
"for it — the flip is refused until it reports one\n")
|
||||
}
|
||||
|
||||
isTaken := map[string]bool{}
|
||||
for _, m := range taken {
|
||||
@@ -473,6 +485,10 @@ type derivedFilter struct {
|
||||
// mesh is every address on the private network; outward says the machine faces outside.
|
||||
mesh []string
|
||||
outward bool
|
||||
// outwardLinks is the links this machine reported as facing outside it (novox/hq ADR 0140).
|
||||
// The filter constrains what arrives on them; everything arriving elsewhere is this machine's
|
||||
// own guest and is not filtered.
|
||||
outwardLinks []string
|
||||
}
|
||||
|
||||
// closesOutside is what a narrowing from everywhere to the private network is called: it closes.
|
||||
@@ -498,6 +514,12 @@ func (d derivedFilter) fate(r inventory.Reach) string {
|
||||
return "stays open — the mesh's own, from anywhere"
|
||||
}
|
||||
}
|
||||
// This machine's own guests ask it for an address and for names, and those two arrive here
|
||||
// (novox/hq ADR 0140). Admitted by the link they arrive on, so a listener bound anywhere but an
|
||||
// outward link keeps answering them.
|
||||
if (r.Protocol == "udp" && (r.Port == 53 || r.Port == 67)) || (r.Protocol == "tcp" && r.Port == 53) {
|
||||
return "stays open — this machine's own guests asking it for an address and for names"
|
||||
}
|
||||
for _, rule := range d.rules {
|
||||
if rule.Port != r.Port || rule.Protocol != r.Protocol {
|
||||
continue
|
||||
|
||||
@@ -149,6 +149,9 @@ func buildFrom(result link.BuildResult) inventory.Build {
|
||||
for _, ref := range result.Against {
|
||||
kept.Against = append(kept.Against, catalogue.Recorded(ref))
|
||||
}
|
||||
for _, r := range result.Read {
|
||||
kept.Read = append(kept.Read, inventory.ReadRepository{Repository: r.Repository, Ref: r.Ref})
|
||||
}
|
||||
var announced []inventory.Artifact
|
||||
for _, made := range result.Made {
|
||||
announced = append(announced, inventory.Artifact{
|
||||
|
||||
@@ -76,7 +76,10 @@ func run() error {
|
||||
return pinCommand(ctx, args[1:], true)
|
||||
case "unpin":
|
||||
return pinCommand(ctx, args[1:], false)
|
||||
case "migrate":
|
||||
// `prepare` is how the mesh asks any module to bring its state to the shape this version needs
|
||||
// (novox/hq ADR 0135), and the control plane answers it the same way as everything else — its
|
||||
// own schema is not a special case. `migrate` remains the word a person types.
|
||||
case "prepare", "migrate":
|
||||
return migrate(ctx)
|
||||
case "node":
|
||||
return nodeCommand(ctx, args[1:])
|
||||
@@ -138,12 +141,16 @@ func usage() {
|
||||
fmt.Fprint(os.Stderr, `mesh-controller — the control plane
|
||||
|
||||
migrate bring each context's schema up to date
|
||||
prepare the same, asked the way the mesh asks any module (ADR 0135)
|
||||
node add <name> [--adopted] create a node record; --adopted: the machine is in use
|
||||
node list the nodes this mesh knows about
|
||||
node show <name> what one machine reported it can do, and why
|
||||
node public-domain <name> the domain it composes its routed names under
|
||||
node public-domain <name> <d> ...set it to d
|
||||
node public-domain <name> --clear ...it faces the outside no longer
|
||||
node networks <name> the networks it routes for what it hosts
|
||||
node networks <name> <cidr>... ...set them; its filter forwards these too
|
||||
node networks <name> --clear ...only the container runtime's own
|
||||
token issue --node <name> a one-time right to join, for an existing record
|
||||
token issue --new <name> create the record and issue for it
|
||||
token issue ... --adopted ...for a machine in use, which joins adopted
|
||||
|
||||
@@ -69,12 +69,20 @@ func moduleCommand(ctx context.Context, args []string) error {
|
||||
repo := set.String("source", "", "where this module comes from")
|
||||
ref := set.String("ref", "", "the branch followed there")
|
||||
commit := set.String("commit", "", "the commit this manifest was read at")
|
||||
// **Where inside the repository the module is** (novox/hq ADR 0069). A module is a
|
||||
// repository *and* a directory, and a record that carries only the repository names a
|
||||
// module.json at its root — so every later build of it looks in the wrong place and fails
|
||||
// with "no module.json at its root". Nine modules on this mesh were registered that way
|
||||
// and none of them could be rebuilt (2026-09-28).
|
||||
path := set.String("path", "", "the module's directory inside that repository")
|
||||
self := set.Bool("self", false, "the source is a path on the forge holding the git seat")
|
||||
positionals, err := parseAround(set, args[1:])
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
if len(positionals) != 1 {
|
||||
return errors.New("module add <manifest.json> [--source <repo> --ref <branch> --commit <sha>]")
|
||||
return errors.New("module add <manifest.json> [--source <repo> [--self] [--path P] " +
|
||||
"--ref <branch> --commit <sha>]")
|
||||
}
|
||||
raw, err := os.ReadFile(positionals[0])
|
||||
if err != nil {
|
||||
@@ -84,23 +92,24 @@ func moduleCommand(ctx context.Context, args []string) error {
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
// Provenance together or not at all. A source with no commit cannot be compared against
|
||||
// anything, so it would record where the module came from and still never be able to say
|
||||
// the mesh is behind it — which is the one thing recording it is for.
|
||||
if (*repo == "") != (*commit == "") {
|
||||
return errors.New("--source and --commit go together: a source with no commit " +
|
||||
"cannot be compared against anything, and a commit with no source has nothing " +
|
||||
"to be compared with")
|
||||
from, err := whereItComesFrom(*repo, *ref, *commit, *path, *self)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
if err := inv.RegisterModule(ctx, m, inventory.Source{
|
||||
Repository: *repo, Ref: *ref, BuiltFrom: *commit,
|
||||
}); err != nil {
|
||||
if err := inv.RegisterModule(ctx, m, from); err != nil {
|
||||
return err
|
||||
}
|
||||
fmt.Printf("%s registered", m.Module)
|
||||
if *commit != "" {
|
||||
fmt.Printf(" from %s", short(*commit))
|
||||
}
|
||||
if *repo != "" && *path == "" {
|
||||
// Said, not refused: a module really at the root is the ordinary case for a repository
|
||||
// of its own. But a repository holding many modules and a record naming none of them is
|
||||
// a module nothing can rebuild, and the person adding it is the one who knows which.
|
||||
fmt.Printf("\n no directory inside %s, so it is built from that repository's root — "+
|
||||
"`--path` if the module lives in a directory there", *repo)
|
||||
}
|
||||
if len(m.Provides) > 0 {
|
||||
fmt.Printf(", providing %s", describeOffers(m.Provides))
|
||||
}
|
||||
@@ -602,3 +611,37 @@ func issueWith(ctx context.Context, inv *inventory.Inventory, m catalogue.Manife
|
||||
"machine holding mesh-broker\n")
|
||||
return nil
|
||||
}
|
||||
|
||||
// whereItComesFrom is the provenance a module handed over by hand records, and what a record must
|
||||
// say to be worth anything later.
|
||||
//
|
||||
// **A module is a repository and a directory inside it** (novox/hq ADR 0069). A record carrying only
|
||||
// the repository names a module.json at its root, so every later build of it looks in the wrong
|
||||
// place — nine modules on this mesh were registered that way and none of them could be rebuilt
|
||||
// (2026-09-28). The directory cannot be checked from here, because the control plane does not clone;
|
||||
// what can be checked is that the record is whole.
|
||||
func whereItComesFrom(repository, ref, commit, path string, self bool) (inventory.Source, error) {
|
||||
// Provenance together or not at all. A source with no commit cannot be compared against
|
||||
// anything, so it would record where the module came from and still never be able to say the
|
||||
// mesh is behind it — which is the one thing recording it is for.
|
||||
if (repository == "") != (commit == "") {
|
||||
return inventory.Source{}, errors.New("--source and --commit go together: a source with " +
|
||||
"no commit cannot be compared against anything, and a commit with no source has " +
|
||||
"nothing to be compared with")
|
||||
}
|
||||
// A directory or a forge with no repository is half a location, and the half it keeps is the
|
||||
// half nothing can be found with.
|
||||
if repository == "" && (path != "" || self) {
|
||||
return inventory.Source{}, errors.New("--path and --self say where inside a source and " +
|
||||
"which forge holds it, so they need --source: without one there is nothing for them " +
|
||||
"to be part of")
|
||||
}
|
||||
from := inventory.Source{Repository: repository, Ref: ref, BuiltFrom: commit, Path: path}
|
||||
if self {
|
||||
if err := onASeat(repository); err != nil {
|
||||
return inventory.Source{}, err
|
||||
}
|
||||
from.Seat = gitSeat
|
||||
}
|
||||
return from, nil
|
||||
}
|
||||
|
||||
@@ -66,6 +66,18 @@ func nodeCommand(ctx context.Context, args []string) error {
|
||||
// because the damage is already done by the time it prints.
|
||||
return publicDomain(ctx, inv, args[1:])
|
||||
|
||||
case "networks":
|
||||
// Removed by novox/hq ADR 0140, which superseded the record that added it. The filter no
|
||||
// longer names any network: it constrains what arrives from outside the machine and says
|
||||
// nothing about what did not, so there is no list to keep. Answered rather than met with
|
||||
// "unknown command", because this was the documented way to stop a flip cutting a machine's
|
||||
// containers off and somebody will reasonably still type it.
|
||||
return errors.New("`node networks` is gone (novox/hq ADR 0140). The filter constrains what " +
|
||||
"arrives from outside this machine and says nothing about traffic that did not, so no " +
|
||||
"network is named anywhere and nothing needs to be said to keep a machine's own " +
|
||||
"containers reaching outward. The machine reports which of its links face outside; see " +
|
||||
"`node show <name>`")
|
||||
|
||||
case "account":
|
||||
// The operator's login on this machine (novox/hq to-be 29): what a home-scoped file is
|
||||
// owned by and which account `ssh <node>` uses. Reports with no argument; sets with one;
|
||||
|
||||
@@ -189,13 +189,17 @@ func readPrivateKey(path string) (string, error) {
|
||||
func personIssue(ctx context.Context, args []string) error {
|
||||
set := flag.NewFlagSet("operator issue", flag.ContinueOnError)
|
||||
invokes := set.String("invokes", "", "the tools this person may call, comma-separated, or * for every one")
|
||||
if err := set.Parse(args); err != nil {
|
||||
// Flags on either side of the name, because the usage this command prints puts them after it —
|
||||
// and the standard parser stops at the first thing that is not a flag, so the order the command
|
||||
// documents was the one order it refused (2026-09-28).
|
||||
positionals, err := parseAround(set, args)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
if set.NArg() != 1 {
|
||||
if len(positionals) != 1 {
|
||||
return errors.New("operator issue <name> --invokes <tool,tool|*>")
|
||||
}
|
||||
name := set.Arg(0)
|
||||
name := positionals[0]
|
||||
if *invokes == "" {
|
||||
return errors.New(
|
||||
"say what this person may call: --invokes mesh-catalog.catalog_tools,gitea.repo_create, " +
|
||||
|
||||
@@ -106,3 +106,107 @@ func TestAMergeOlderThanTheLastLookIsHistory(t *testing.T) {
|
||||
t.Fatal("a merge or a source with no time on it was refused")
|
||||
}
|
||||
}
|
||||
|
||||
// A module as the catalogue holds it: built from a repository, at a directory inside it.
|
||||
func fromRepo(module, repository, path string) inventory.Entry {
|
||||
return inventory.Entry{
|
||||
Manifest: catalogue.Manifest{Module: module},
|
||||
Source: inventory.Source{Repository: repository, Path: path, Ref: "main"},
|
||||
}
|
||||
}
|
||||
|
||||
// A merge rebuilds the modules whose own directories it changed, and everything when what it changed
|
||||
// is shared. One repository holding many modules is the ordinary case here, and rebuilding all of
|
||||
// them for a change to one is what exhausted a registry's pull limit the first night this ran.
|
||||
func TestAMergeRebuildsTheModulesItChanged(t *testing.T) {
|
||||
const repo = "http://forge.internal:20000/novox/mesh-catalog.git"
|
||||
gitea := fromRepo("gitea", repo, "modules/gitea")
|
||||
keycloak := fromRepo("keycloak", repo, "modules/keycloak")
|
||||
known := []inventory.Entry{gitea, keycloak, fromRepo("plex", repo, "modules/plex")}
|
||||
candidates := []inventory.Entry{gitea, keycloak}
|
||||
merge := func(paths []string, truncated bool) link.SourceMoved {
|
||||
return link.SourceMoved{Owner: "novox", Repo: "mesh-catalog", Base: "main",
|
||||
Paths: paths, PathsTruncated: truncated}
|
||||
}
|
||||
named := func(entries []inventory.Entry) string {
|
||||
var names []string
|
||||
for _, e := range entries {
|
||||
names = append(names, e.Manifest.Module)
|
||||
}
|
||||
return strings.Join(names, ",")
|
||||
}
|
||||
for _, c := range []struct {
|
||||
what string
|
||||
m link.SourceMoved
|
||||
want string
|
||||
}{
|
||||
{"one module's own files", merge([]string{"modules/gitea/index.ts", "modules/gitea/client.ts"}, false), "gitea"},
|
||||
{"two modules' files", merge([]string{"modules/gitea/index.ts", "modules/keycloak/module.json"}, false), "gitea,keycloak"},
|
||||
{"a file they share", merge([]string{"tsconfig.json"}, false), "gitea,keycloak"},
|
||||
{"a module the mesh does not hold", merge([]string{"modules/plex/index.ts"}, false), ""},
|
||||
{"nothing said about the files", merge(nil, false), "gitea,keycloak"},
|
||||
{"more files than were listed", merge([]string{"modules/gitea/index.ts"}, true), "gitea,keycloak"},
|
||||
} {
|
||||
if got := named(whatTheMergeTouched(candidates, known, c.m)); got != c.want {
|
||||
t.Errorf("%s: rebuilt %q, wanted %q", c.what, got, c.want)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// A module whose recipe packages source from another repository is affected when that repository
|
||||
// moves — the manifest the mesh keeps says nothing about it, so the record of what the build read is
|
||||
// the only thing that can say so.
|
||||
func TestAModuleIsAffectedByTheRepositoryItPackages(t *testing.T) {
|
||||
m := link.SourceMoved{Owner: "novox", Repo: "mesh-controller", Base: "main",
|
||||
CloneURL: "http://forge.internal:20000/novox/mesh-controller.git"}
|
||||
for _, read := range [][]inventory.ReadRepository{
|
||||
{{Repository: "http://forge.internal:20000/novox/mesh-controller.git", Ref: "main"}},
|
||||
{{Repository: "novox/mesh-controller"}},
|
||||
{{Repository: "https://elsewhere.example/novox/other"}, {Repository: "novox/mesh-controller.git", Ref: "main"}},
|
||||
} {
|
||||
if !readsFrom(read, m) {
|
||||
t.Errorf("%+v was not matched by the merge", read)
|
||||
}
|
||||
}
|
||||
for _, read := range [][]inventory.ReadRepository{
|
||||
nil,
|
||||
{{Repository: "novox/mesh-host", Ref: "main"}},
|
||||
{{Repository: "novox/mesh-controller", Ref: "release"}},
|
||||
} {
|
||||
if readsFrom(read, m) {
|
||||
t.Errorf("%+v was matched by a merge that is not its", read)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// What a module handed over by hand records about where it came from, and what is refused.
|
||||
func TestWhatAHandedOverModuleRecordsAboutItsSource(t *testing.T) {
|
||||
// The whole location: a repository on the mesh's own forge, the directory inside it, the branch
|
||||
// and the commit the manifest was read at.
|
||||
from, err := whereItComesFrom("novox/mesh-catalog", "main", "c0ffee", "modules/gitea", true)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if from.Path != "modules/gitea" || from.Seat != "git" || from.Repository != "novox/mesh-catalog" {
|
||||
t.Fatalf("the source records as %+v", from)
|
||||
}
|
||||
// A manifest with no provenance at all is legitimate: fixing something in a hurry.
|
||||
if from, err := whereItComesFrom("", "", "", "", false); err != nil || from != (inventory.Source{}) {
|
||||
t.Fatalf("a manifest handed over with no provenance was refused: %+v, %v", from, err)
|
||||
}
|
||||
for _, c := range []struct {
|
||||
what string
|
||||
repository, ref, commit, path string
|
||||
self bool
|
||||
}{
|
||||
{what: "a source with no commit", repository: "novox/mesh-catalog", commit: ""},
|
||||
{what: "a commit with no source", commit: "c0ffee"},
|
||||
{what: "a directory inside nothing", path: "modules/gitea"},
|
||||
{what: "a forge holding nothing", self: true},
|
||||
{what: "an address given as a path on the forge", repository: "http://forge.internal:20000/novox/x.git", commit: "c0ffee", self: true},
|
||||
} {
|
||||
if _, err := whereItComesFrom(c.repository, c.ref, c.commit, c.path, c.self); err == nil {
|
||||
t.Errorf("%s was recorded as a source", c.what)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -640,13 +640,19 @@ func renderingFor(ctx context.Context, open *stores, node string,
|
||||
if err != nil {
|
||||
return catalogue.Rendering{}, inventory.Node{}, err
|
||||
}
|
||||
// Which of this machine's links face outside, which is what the derived filter is written
|
||||
// around (novox/hq ADR 0140). Reported by the machine, never set.
|
||||
outwardLinks, err := inv.OutwardLinksOf(ctx, node)
|
||||
if err != nil {
|
||||
return catalogue.Rendering{}, inventory.Node{}, err
|
||||
}
|
||||
return catalogue.Rendering{
|
||||
BusMembership: memberships[node],
|
||||
Settings: settings, Generators: gens, Grants: grants, Needed: needed, Ports: ports,
|
||||
Certificate: certificate, Authority: authority, Mesh: private, Names: names,
|
||||
Machines: machines,
|
||||
Suffix: overlay.Suffix(), MeshRange: meshRange, Accounts: accounts, Foundation: foundation,
|
||||
Kept: kept, Adopted: record.Adopted,
|
||||
Suffix: overlay.Suffix(), MeshRange: meshRange, TunnelInterface: overlay.Interface, Accounts: accounts, Foundation: foundation,
|
||||
Kept: kept, Adopted: record.Adopted, OutwardLinks: outwardLinks,
|
||||
Given: given, Taken: taken, Seats: seats, ArtifactStore: artifactStore, Built: built,
|
||||
BusUsers: busUsers,
|
||||
}, record, nil
|
||||
|
||||
@@ -162,7 +162,13 @@ func declare(ctx context.Context, args []string) error {
|
||||
return err
|
||||
}
|
||||
|
||||
server, err := connectLink(ctx, nil, nil, nil)
|
||||
// **With the inventory, so the bus is raised** (novox/hq ADR 0134, design 30). A module's
|
||||
// declaration and how it hears what it consumes move together: its consumer is derived from the
|
||||
// same records this declaration is composed from. Raised only when the control plane started
|
||||
// serving, a module that gained a `consumes` was sent a declaration it could act on and a
|
||||
// consumer that never delivered the event — and nothing anywhere said the two disagreed
|
||||
// (found on review, 2026-09-28). Everything the raise does is idempotent.
|
||||
server, err := connectLink(ctx, inv, nil, nil)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
+160
-20
@@ -232,29 +232,67 @@ func (f following) SourceMoved(ctx context.Context, m link.SourceMoved) error {
|
||||
if err != nil {
|
||||
return notNow(err)
|
||||
}
|
||||
var moved []inventory.Entry
|
||||
read, err := inv.ReadRepositories(ctx)
|
||||
if err != nil {
|
||||
return notNow(err)
|
||||
}
|
||||
|
||||
// Two kinds of module are affected by one merge, and they are affected differently.
|
||||
//
|
||||
// A module **built from** this repository and branch has moved: the mesh records the new commit
|
||||
// as what its source now has, and only what the merge actually changed is rebuilt. A module that
|
||||
// only **packages source from** it has not moved — its own source is somewhere else, at the
|
||||
// commit it already records — so it is rebuilt and its record left alone. Writing this commit as
|
||||
// its source would make it permanently behind a repository its manifest does not come from.
|
||||
var from, packaging []inventory.Entry
|
||||
already := 0
|
||||
for _, e := range entries {
|
||||
if !sourceIs(e.Source, m) {
|
||||
continue
|
||||
switch {
|
||||
case sourceIs(e.Source, m):
|
||||
if e.Source.BuiltFrom == m.Commit {
|
||||
already++
|
||||
continue
|
||||
}
|
||||
// **A merge older than the last look at the source is history, not a move.** The forge
|
||||
// announces what it finds merged, and an old merge surfacing late would otherwise move
|
||||
// the recorded head backwards and rebuild everything built from that repository, once
|
||||
// per old merge (2026-09-28).
|
||||
if isHistory(m.MergedAt, e.Source.Seen) {
|
||||
continue
|
||||
}
|
||||
from = append(from, e)
|
||||
case readsFrom(read[e.Manifest.Module], m):
|
||||
packaging = append(packaging, e)
|
||||
}
|
||||
if e.Source.BuiltFrom == m.Commit {
|
||||
continue
|
||||
}
|
||||
// **A merge older than the last look at the source is history, not a move.** The forge
|
||||
// announces what it finds merged, and an old merge surfacing late would otherwise move the
|
||||
// recorded head backwards and rebuild everything built from that repository, once per old
|
||||
// merge (2026-09-28).
|
||||
if isHistory(m.MergedAt, e.Source.Seen) {
|
||||
continue
|
||||
}
|
||||
if len(from) == 0 && len(packaging) == 0 {
|
||||
// "Already built from it" and "nothing reads it" are different facts, and reading the first
|
||||
// as the second sends somebody looking for a broken trigger when the mesh is up to date.
|
||||
if already > 0 {
|
||||
fmt.Printf("%s/%s merged into %s (%.8s); %d module(s) the mesh holds are already built "+
|
||||
"from it\n", m.Owner, m.Repo, m.Base, m.Commit, already)
|
||||
return nil
|
||||
}
|
||||
fmt.Printf("%s/%s merged into %s (%.8s); nothing the mesh holds reads it\n",
|
||||
m.Owner, m.Repo, m.Base, m.Commit)
|
||||
return nil
|
||||
}
|
||||
// The same judgement for the packaging kind, against the newest look at that repository by
|
||||
// anything built from it: they keep no record of it themselves, and a replayed old merge should
|
||||
// not rebuild them either.
|
||||
if isHistory(m.MergedAt, lastLookAt(entries, m)) {
|
||||
packaging = nil
|
||||
}
|
||||
touched := whatTheMergeTouched(from, entries, m)
|
||||
for _, e := range touched {
|
||||
if err := inv.SourceMoved(ctx, e.Manifest.Module, m.Commit); err != nil {
|
||||
return notNow(err)
|
||||
}
|
||||
moved = append(moved, e)
|
||||
}
|
||||
moved := append(append([]inventory.Entry{}, touched...), packaging...)
|
||||
if len(moved) == 0 {
|
||||
fmt.Printf("%s/%s merged into %s (%.8s); nothing the mesh holds is built from it\n",
|
||||
m.Owner, m.Repo, m.Base, m.Commit)
|
||||
fmt.Printf("%s/%s merged into %s (%.8s); it changed nothing any module the mesh holds is "+
|
||||
"built from\n", m.Owner, m.Repo, m.Base, m.Commit)
|
||||
return nil
|
||||
}
|
||||
against, err := inv.BuiltAgainst(ctx)
|
||||
@@ -268,6 +306,14 @@ func (f following) SourceMoved(ctx context.Context, m link.SourceMoved) error {
|
||||
}
|
||||
fmt.Printf("%s/%s merged into %s (%.8s); building %s\n",
|
||||
m.Owner, m.Repo, m.Base, m.Commit, strings.Join(names, ", "))
|
||||
if len(packaging) > 0 {
|
||||
var also []string
|
||||
for _, e := range packaging {
|
||||
also = append(also, e.Manifest.Module)
|
||||
}
|
||||
fmt.Printf(" %s package source from it, so they are rebuilt and their own source record "+
|
||||
"is left where it is\n", strings.Join(also, ", "))
|
||||
}
|
||||
var failed []string
|
||||
for _, e := range ordered {
|
||||
source := buildSource{Repository: e.Source.Repository, Seat: e.Source.Seat}
|
||||
@@ -293,16 +339,110 @@ func (f following) SourceMoved(ctx context.Context, m link.SourceMoved) error {
|
||||
// An empty recorded ref is the repository's default branch, which is what a merge into the base
|
||||
// branch of the forge's default means.
|
||||
func sourceIs(s inventory.Source, m link.SourceMoved) bool {
|
||||
want := strings.ToLower(m.Owner + "/" + m.Repo)
|
||||
repo := strings.ToLower(strings.TrimSuffix(s.Repository, ".git"))
|
||||
matches := repo == want || strings.HasSuffix(repo, "/"+want) ||
|
||||
(m.CloneURL != "" && strings.EqualFold(strings.TrimSuffix(s.Repository, ".git"), strings.TrimSuffix(m.CloneURL, ".git")))
|
||||
if !matches {
|
||||
if !sameRepository(s.Repository, m) {
|
||||
return false
|
||||
}
|
||||
return s.Ref == "" || s.Ref == m.Base
|
||||
}
|
||||
|
||||
// sameRepository is whether a recorded repository is the one a merge names, in either spelling it
|
||||
// may have been recorded in: a path on the git seat, or the URL it was cloned from.
|
||||
func sameRepository(repository string, m link.SourceMoved) bool {
|
||||
want := strings.ToLower(m.Owner + "/" + m.Repo)
|
||||
repo := strings.ToLower(strings.TrimSuffix(repository, ".git"))
|
||||
return repo == want || strings.HasSuffix(repo, "/"+want) ||
|
||||
(m.CloneURL != "" && repo == strings.ToLower(strings.TrimSuffix(m.CloneURL, ".git")))
|
||||
}
|
||||
|
||||
// readsFrom is whether a module's build read the repository a merge names: the second repository its
|
||||
// recipe packages source from. Its ref must be the branch that moved, or unset — the same rule a
|
||||
// module's own source follows.
|
||||
func readsFrom(read []inventory.ReadRepository, m link.SourceMoved) bool {
|
||||
for _, r := range read {
|
||||
if sameRepository(r.Repository, m) && (r.Ref == "" || r.Ref == m.Base) {
|
||||
return true
|
||||
}
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
// lastLookAt is the most recent look at this repository by anything built from it.
|
||||
func lastLookAt(entries []inventory.Entry, m link.SourceMoved) time.Time {
|
||||
var newest time.Time
|
||||
for _, e := range entries {
|
||||
if sameRepository(e.Source.Repository, m) && e.Source.Seen.After(newest) {
|
||||
newest = e.Source.Seen
|
||||
}
|
||||
}
|
||||
return newest
|
||||
}
|
||||
|
||||
// whatTheMergeTouched narrows the modules built from a repository to the ones the merge changed.
|
||||
//
|
||||
// **A change inside no module's own directory is a change to what they share.** The forge lists the
|
||||
// files a merge changed; a module is affected when one of them is inside its own directory, when it
|
||||
// is built from the repository's root — everything there is its source — or when some changed file
|
||||
// belongs to no module's directory at all, which is how a shared file, a build recipe or a
|
||||
// dependency at the root rebuilds everything built from that repository.
|
||||
//
|
||||
// A change inside *another* module's directory is that module's business and not this one's, even
|
||||
// when the mesh does not hold that module: `known` is every module this repository is known to hold,
|
||||
// whatever branch it was registered from. That is also the limit of this — a repository whose shared
|
||||
// code sits inside a directory the mesh has never seen a module in reads as shared, and everything
|
||||
// is rebuilt. Rebuilding too much is the safe direction: the fault this whole path exists for is a
|
||||
// mesh that believes it is current and is not (novox/hq 04-ISSUES/131).
|
||||
func whatTheMergeTouched(candidates, known []inventory.Entry, m link.SourceMoved) []inventory.Entry {
|
||||
// Nothing said about the files, or not all of them said: everything built from it is affected.
|
||||
if len(m.Paths) == 0 || m.PathsTruncated {
|
||||
return candidates
|
||||
}
|
||||
var dirs []string
|
||||
for _, e := range known {
|
||||
if e.Source.Path != "" && sameRepository(e.Source.Repository, m) {
|
||||
dirs = append(dirs, e.Source.Path)
|
||||
}
|
||||
}
|
||||
for _, p := range m.Paths {
|
||||
if !insideAny(p, dirs) {
|
||||
return candidates
|
||||
}
|
||||
}
|
||||
var out []inventory.Entry
|
||||
for _, e := range candidates {
|
||||
if e.Source.Path == "" || anyInside(m.Paths, e.Source.Path) {
|
||||
out = append(out, e)
|
||||
}
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
// inside is whether a changed file is in a directory: that directory itself, or under it.
|
||||
func inside(path, dir string) bool {
|
||||
dir = strings.Trim(dir, "/")
|
||||
path = strings.TrimPrefix(path, "/")
|
||||
return path == dir || strings.HasPrefix(path, dir+"/")
|
||||
}
|
||||
|
||||
// insideAny is whether a changed file is in any of these directories.
|
||||
func insideAny(path string, dirs []string) bool {
|
||||
for _, dir := range dirs {
|
||||
if inside(path, dir) {
|
||||
return true
|
||||
}
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
// anyInside is whether any of these changed files is in a directory.
|
||||
func anyInside(paths []string, dir string) bool {
|
||||
for _, p := range paths {
|
||||
if inside(p, dir) {
|
||||
return true
|
||||
}
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
// orderByBases is the entries with every base before what stands on it: a module whose build stood
|
||||
// on another's artifact comes after that module. Entries outside the set are not waited for — they
|
||||
// are not being rebuilt. Stable for what has no order between it.
|
||||
|
||||
@@ -66,6 +66,19 @@ func FromEnvironment() (Broker, error) {
|
||||
if err != nil {
|
||||
return Broker{}, err
|
||||
}
|
||||
// **One bus, one address** (novox/hq ADR 0131). Everything the mesh hands out — a token, a
|
||||
// machine's membership, a person's credential — must name the bus the control plane itself is
|
||||
// connected to; the setting above predates the move and, on a mesh that has moved, still names
|
||||
// the broker it moved from. The first person issued after the move was handed the retired
|
||||
// broker's port and could not connect to anything (2026-09-28).
|
||||
//
|
||||
// Read from the credential rather than from a second setting somebody keeps in step: the
|
||||
// control plane cannot be wrong about where it is connected.
|
||||
if bus, on, err := OnNATS(); err == nil && on {
|
||||
if where := strings.TrimPrefix(BareAddress(bus), "nats://"); where != "" {
|
||||
address = where
|
||||
}
|
||||
}
|
||||
return Broker{Address: address, Fingerprint: fingerprint}, nil
|
||||
}
|
||||
|
||||
|
||||
@@ -181,6 +181,14 @@ func PermissionsFor(p Principal) (Permissions, error) {
|
||||
for _, seat := range meshSeatsTheControllerUses {
|
||||
pub = append(pub, "mesh.seat."+seat+".accept.>")
|
||||
}
|
||||
// **And what the mesh says it did** (novox/hq ADR 0134). The control plane states its own
|
||||
// facts under the seat it holds, because a role's events belong to the role and keep their
|
||||
// address while the holder is replaced. Named one by one rather than as a whole namespace:
|
||||
// least authority, and a fact nothing states is authority nobody uses.
|
||||
for _, event := range ControllerStates {
|
||||
pub = append(pub, seatEventSubject(ControllerSeat, event))
|
||||
}
|
||||
|
||||
// Every module's tools: **the control plane is the way in** (novox/hq ADR 0095). A person
|
||||
// or an agent asks through it and every question passes one process where an audit
|
||||
// belongs — so it, alone among principals, may call any tool by name. The first `ask` on
|
||||
|
||||
@@ -0,0 +1,44 @@
|
||||
package broker_test
|
||||
|
||||
import (
|
||||
"slices"
|
||||
"testing"
|
||||
|
||||
"github.com/novox/mesh-controller/internal/broker"
|
||||
"github.com/novox/mesh-controller/internal/catalogue"
|
||||
"github.com/novox/mesh-controller/internal/link"
|
||||
)
|
||||
|
||||
// The facts the control plane states are named twice — in the grant that permits them and in the code
|
||||
// that states them — because `link` imports `broker` and the dependency cannot go the other way. So a
|
||||
// test keeps them agreeing: a subject the grant omits is refused at the moment the mesh has something
|
||||
// to say, and one the grant adds that nothing states is authority nobody uses.
|
||||
//
|
||||
// An external test package, because it may import both while neither imports the other.
|
||||
func TestTheFactsTheGrantPermitsAreTheFactsTheMeshStates(t *testing.T) {
|
||||
if broker.ControllerSeat != link.MeshControllerSeat {
|
||||
t.Fatalf("the grant is written for the %q seat and the mesh states its facts under %q",
|
||||
broker.ControllerSeat, link.MeshControllerSeat)
|
||||
}
|
||||
for _, event := range []string{link.KeyApplied, link.KeyRefused, link.KeyBuiltBefore} {
|
||||
if !slices.Contains(broker.ControllerStates, event) {
|
||||
t.Errorf("the mesh states %q and its account may not publish it", event)
|
||||
}
|
||||
}
|
||||
if len(broker.ControllerStates) != 3 {
|
||||
t.Errorf("the grant permits %v, which is more than the mesh states", broker.ControllerStates)
|
||||
}
|
||||
// **And the seat says it.** A seat carries the protocol of its role (novox/hq ADR 0129), so the
|
||||
// facts the control plane states are the seat's `emits` — which is what lets anything else declare
|
||||
// that it consumes them, and what the subject-agreement check reads to know they have an owner.
|
||||
var declared []string
|
||||
for _, seat := range catalogue.SeatsWithAProtocol() {
|
||||
if seat.Name == broker.ControllerSeat {
|
||||
declared = seat.Emits
|
||||
}
|
||||
}
|
||||
if !slices.Equal(declared, broker.ControllerStates) {
|
||||
t.Errorf("the %s seat emits %v and the grant permits %v", broker.ControllerSeat,
|
||||
declared, broker.ControllerStates)
|
||||
}
|
||||
}
|
||||
@@ -160,6 +160,17 @@ func Overlaps() []string {
|
||||
// ack subject is derived from (nats.go: `$JS.ACK.<stream>.controller.>`).
|
||||
const ControllerName = "controller"
|
||||
|
||||
// ControllerSeat is the role the control plane holds, and ControllerStates are the facts it states
|
||||
// under it (novox/hq ADR 0134).
|
||||
//
|
||||
// **Written here as well as in `link`, and a test keeps them agreeing.** `link` imports `broker`, so
|
||||
// `broker` cannot import `link`; a grant naming a subject the controller never publishes is authority
|
||||
// nobody uses, and a controller publishing one the grant omits is refused at the moment it has
|
||||
// something to say.
|
||||
const ControllerSeat = "mesh-controller"
|
||||
|
||||
var ControllerStates = []string{"applied", "refused", "built-before"}
|
||||
|
||||
// ControllerFollows are the events the controller reacts to: the catalogue saying a module's
|
||||
// current version moved, and a catalogue that has just started saying it may have missed builds.
|
||||
//
|
||||
|
||||
+1
-1
@@ -24,7 +24,7 @@ accounts {
|
||||
jetstream: enabled
|
||||
users = [
|
||||
{ user: "controller", password: "$2a$11$cccccccccccccccccccccc", permissions: {
|
||||
publish: { allow: ["$JS.ACK.CONTROL.controller.>", "$JS.ACK.EVENTS.controller.>", "$JS.API.>", "_INBOX.enrol.>", "mesh.control.>", "mesh.mod.*.tool.>", "mesh.node.>", "mesh.seat.mesh-build-machine.accept.>"] }
|
||||
publish: { allow: ["$JS.ACK.CONTROL.controller.>", "$JS.ACK.EVENTS.controller.>", "$JS.API.>", "_INBOX.enrol.>", "mesh.control.>", "mesh.mod.*.tool.>", "mesh.node.>", "mesh.seat.mesh-build-machine.accept.>", "mesh.seat.mesh-controller.event.applied", "mesh.seat.mesh-controller.event.built-before", "mesh.seat.mesh-controller.event.refused"] }
|
||||
subscribe: { allow: ["$JS.API.>", "_DELIVER.controller", "_DELIVER.controller.>", "_INBOX.controller.>", "mesh.control.>", "mesh.mod.gitea.event.pull.merged", "mesh.mod.mesh-catalog.event.catching-up", "mesh.mod.mesh-catalog.event.upgraded", "mesh.seat.mesh-build-machine.event.built"] }
|
||||
allow_responses: { max: 1, ttl: "1m" }
|
||||
} }
|
||||
|
||||
@@ -61,6 +61,12 @@ type Result struct {
|
||||
Commit string
|
||||
// Built is each artifact, for reporting.
|
||||
Built []catalogue.Built
|
||||
|
||||
// Read is every repository this build read source from besides the module's own — the second
|
||||
// repository an artifact's recipe names (ArtifactContext). Reported because the manifest the
|
||||
// mesh keeps carries no build section, so nothing else could say that a merge there is a
|
||||
// change to this module (novox/hq 04-ISSUES/131).
|
||||
Read []catalogue.ArtifactContext
|
||||
}
|
||||
|
||||
// GitCredential is the forge credential a clone may present when the server asks for one.
|
||||
@@ -220,7 +226,7 @@ func Build(ctx context.Context, run Runner, publish Publisher,
|
||||
}
|
||||
say("done", "%s at %s — %d artifact(s) pinned", manifest.Module, short(commit), len(built))
|
||||
return Result{Manifest: resolved, Commit: commit, Built: built,
|
||||
Against: against(within, manifest, stoodOn)}, nil
|
||||
Against: against(within, manifest, stoodOn), Read: readBy(manifest)}, nil
|
||||
}
|
||||
|
||||
// Log is where a build says what it is doing, step by step. Nil is silent — the tests pass none,
|
||||
@@ -1016,3 +1022,31 @@ func instructions(recipe string) []string {
|
||||
flush()
|
||||
return out
|
||||
}
|
||||
|
||||
// readBy is every repository other than the module's own that this build's recipes read source from,
|
||||
// each once and in a fixed order, so two builds of one commit report the same thing the same way.
|
||||
func readBy(manifest catalogue.Manifest) []catalogue.ArtifactContext {
|
||||
if manifest.Build == nil {
|
||||
return nil
|
||||
}
|
||||
seen := map[string]bool{}
|
||||
var out []catalogue.ArtifactContext
|
||||
for _, a := range manifest.Build.Artifacts {
|
||||
if a.Context == nil || a.Context.Repository == "" {
|
||||
continue
|
||||
}
|
||||
key := a.Context.Repository + "#" + a.Context.Ref
|
||||
if seen[key] {
|
||||
continue
|
||||
}
|
||||
seen[key] = true
|
||||
out = append(out, *a.Context)
|
||||
}
|
||||
sort.Slice(out, func(i, j int) bool {
|
||||
if out[i].Repository != out[j].Repository {
|
||||
return out[i].Repository < out[j].Repository
|
||||
}
|
||||
return out[i].Ref < out[j].Ref
|
||||
})
|
||||
return out
|
||||
}
|
||||
|
||||
@@ -180,6 +180,20 @@ func (r Registry) MirrorImage(ctx context.Context, from, repository string) (str
|
||||
if err != nil {
|
||||
return "", err
|
||||
}
|
||||
// **Already held is already mirrored.** A base is named by digest, and a digest this registry
|
||||
// holds under the module's repository is the same bytes whatever upstream would say — so
|
||||
// upstream is not asked. Asked every build, the public hub's anonymous pull limit was reached
|
||||
// on the first merge that rebuilt a whole catalogue (2026-09-28), and every module whose base
|
||||
// lives there failed on a copy it did not need.
|
||||
if strings.HasPrefix(where.reference, "sha256:") {
|
||||
held, err := r.has(ctx, "http://"+r.Address+"/v2/"+repository+"/manifests/"+where.reference, manifestAccept)
|
||||
if err != nil {
|
||||
return "", fmt.Errorf("asking %s whether it holds %s: %w", r.Address, from, err)
|
||||
}
|
||||
if held {
|
||||
return r.Address + "/" + repository + "@" + where.reference, nil
|
||||
}
|
||||
}
|
||||
src := &source{client: r.client()}
|
||||
digest, err := r.copyManifest(ctx, src, where, where.reference, repository)
|
||||
if err != nil {
|
||||
|
||||
@@ -103,6 +103,20 @@ func (m *theMeshsRegistry) handler() http.Handler {
|
||||
m.mu.Lock()
|
||||
defer m.mu.Unlock()
|
||||
switch {
|
||||
case r.Method == http.MethodHead && strings.Contains(r.URL.Path, "/manifests/"):
|
||||
// **As strictly as a real registry.** A manifest is answered only in a media type the
|
||||
// caller named; a request with no Accept is answered as if nothing were there. The fake
|
||||
// used to answer regardless, which is why it could not catch a check that asked without
|
||||
// one — and the mesh copied every base again (2026-09-28).
|
||||
if !strings.Contains(r.Header.Get("Accept"), "manifest") && !strings.Contains(r.Header.Get("Accept"), "index") {
|
||||
w.WriteHeader(http.StatusNotFound)
|
||||
return
|
||||
}
|
||||
if _, ok := m.manifests[r.URL.Path[strings.LastIndex(r.URL.Path, "/")+1:]]; ok {
|
||||
w.WriteHeader(http.StatusOK)
|
||||
} else {
|
||||
w.WriteHeader(http.StatusNotFound)
|
||||
}
|
||||
case r.Method == http.MethodHead && strings.Contains(r.URL.Path, "/blobs/"):
|
||||
if _, ok := m.blobs[r.URL.Path[strings.LastIndex(r.URL.Path, "/")+1:]]; ok {
|
||||
w.WriteHeader(http.StatusOK)
|
||||
@@ -219,3 +233,27 @@ func TestATagBeforeTheDigestIsNotPartOfTheRepository(t *testing.T) {
|
||||
t.Fatalf("got %+v", got)
|
||||
}
|
||||
}
|
||||
|
||||
// A base this registry already holds by digest is not asked of upstream at all: the public hub
|
||||
// limits anonymous pulls, and a catalogue rebuilt on one merge asked it once per module.
|
||||
func TestABaseAlreadyHeldIsNotAskedOfUpstream(t *testing.T) {
|
||||
src, indexDigest, _ := anUpstreamRegistry(t)
|
||||
dst := &theMeshsRegistry{blobs: map[string][]byte{}, manifests: map[string][]byte{}}
|
||||
dstServer := httptest.NewServer(dst.handler())
|
||||
defer dstServer.Close()
|
||||
address := strings.TrimPrefix(dstServer.URL, "http://")
|
||||
r := Registry{Address: address, HTTP: src.Client()}
|
||||
host := strings.TrimPrefix(src.URL, "http://")
|
||||
if _, err := r.MirrorImage(context.Background(), host+"/library/thing:latest", "hello-web/server"); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
// Upstream gone: the pinned base is answered from what the mesh holds.
|
||||
src.Close()
|
||||
reference, err := r.MirrorImage(context.Background(), host+"/library/thing@"+indexDigest, "hello-web/server")
|
||||
if err != nil {
|
||||
t.Fatalf("a base the registry holds was asked of an upstream that is gone: %v", err)
|
||||
}
|
||||
if reference != address+"/hello-web/server@"+indexDigest {
|
||||
t.Fatalf("pinned as %q", reference)
|
||||
}
|
||||
}
|
||||
|
||||
@@ -122,11 +122,23 @@ func (r Registry) PublishArchive(ctx context.Context, repository string, body []
|
||||
return final, nil
|
||||
}
|
||||
|
||||
func (r Registry) has(ctx context.Context, url string) (bool, error) {
|
||||
// has is whether this registry already holds what is at that URL.
|
||||
//
|
||||
// **A manifest HEAD must say what it accepts.** A registry answers a manifest request only in a media
|
||||
// type the caller named, and a bare HEAD — no Accept at all — is answered 404 for a manifest it holds
|
||||
// perfectly well. Measured against the mesh's own registry (2026-09-28): the same digest answered 200
|
||||
// with the manifest media types and 404 without them, so a check written without them concluded the
|
||||
// registry held nothing, copied every base again, and exhausted the public hub's pull limit. A blob
|
||||
// needs no Accept, which is why this went unnoticed: the same helper was right for blobs and wrong
|
||||
// for manifests.
|
||||
func (r Registry) has(ctx context.Context, url string, accept ...string) (bool, error) {
|
||||
request, err := http.NewRequestWithContext(ctx, http.MethodHead, url, nil)
|
||||
if err != nil {
|
||||
return false, err
|
||||
}
|
||||
for _, media := range accept {
|
||||
request.Header.Add("Accept", media)
|
||||
}
|
||||
response, err := r.client().Do(request)
|
||||
if err != nil {
|
||||
return false, fmt.Errorf("cannot reach the registry at %s: %w", r.Address, err)
|
||||
|
||||
@@ -179,3 +179,24 @@ func TestTheBasesABuildWasHandedAreWhatItStoodOn(t *testing.T) {
|
||||
t.Fatalf("the bases the build was handed were not what it stood on: %v", got)
|
||||
}
|
||||
}
|
||||
|
||||
// What a build read besides its module's own repository is the second repository its recipes name,
|
||||
// each once: a module that packages source living elsewhere is affected when that source moves.
|
||||
func TestWhatABuildReadIsTheRepositoriesItsRecipesName(t *testing.T) {
|
||||
elsewhere := catalogue.ArtifactContext{Repository: "http://forge.internal:20000/novox/mesh-controller.git", Ref: "main"}
|
||||
manifest := catalogue.Manifest{
|
||||
Module: "builder",
|
||||
Build: &catalogue.Build{Artifacts: []catalogue.Artifact{
|
||||
{Name: "server", Kind: catalogue.ArtifactImage, From: "Dockerfile", Context: &elsewhere},
|
||||
{Name: "tools", Kind: catalogue.ArtifactImage, From: "Dockerfile", Context: &elsewhere},
|
||||
{Name: "config", Kind: catalogue.ArtifactArchive, From: "etc"},
|
||||
}},
|
||||
}
|
||||
read := readBy(manifest)
|
||||
if len(read) != 1 || read[0] != elsewhere {
|
||||
t.Fatalf("the repositories this build read are %+v", read)
|
||||
}
|
||||
if readBy(catalogue.Manifest{Module: "gitea", Build: &catalogue.Build{}}) != nil {
|
||||
t.Fatal("a module whose recipes name no other repository read one")
|
||||
}
|
||||
}
|
||||
|
||||
@@ -59,7 +59,11 @@ func anchorRendering(adopted bool) Rendering {
|
||||
Values: map[string]any{ExposeSetting: map[string]any{"5000": FromEverywhere}}}}},
|
||||
Mesh: []string{"10.42.0.1"},
|
||||
Foundation: []int{5671},
|
||||
Adopted: adopted,
|
||||
// What the machine reported faces outside, which every rule in the filter is written
|
||||
// around (novox/hq ADR 0140).
|
||||
OutwardLinks: []string{"eth0"},
|
||||
TunnelInterface: "mesh0",
|
||||
Adopted: adopted,
|
||||
// Genesis takes the foundation's modules.
|
||||
Taken: map[string]bool{"postgres": true, "lavinmq": true},
|
||||
}
|
||||
@@ -575,11 +579,13 @@ func TestAGivenMachineSideReachesTheFilterTheOpeningAndTheConsumer(t *testing.T)
|
||||
}
|
||||
r := Resolution{Node: "anchor", Modules: []Manifest{forge}}
|
||||
with := Rendering{
|
||||
Ports: map[string]map[int]int{"forge": portsAsThePlanWould(forge, given)},
|
||||
Given: map[string]map[int]int{"forge": given},
|
||||
Mesh: []string{"10.77.0.1"},
|
||||
Adopted: true,
|
||||
Taken: map[string]bool{"forge": true},
|
||||
Ports: map[string]map[int]int{"forge": portsAsThePlanWould(forge, given)},
|
||||
Given: map[string]map[int]int{"forge": given},
|
||||
Mesh: []string{"10.77.0.1"},
|
||||
Adopted: true,
|
||||
OutwardLinks: []string{"eth0"},
|
||||
TunnelInterface: "mesh0",
|
||||
Taken: map[string]bool{"forge": true},
|
||||
}
|
||||
|
||||
// What the runtime is handed: the machine's own port on the outside, the container's within.
|
||||
@@ -660,9 +666,11 @@ func TestALongFormPortIsOpenedWhereTheManifestPublishesIt(t *testing.T) {
|
||||
forge := aForge()
|
||||
r := Resolution{Node: "anchor", Modules: []Manifest{forge}}
|
||||
composed, err := r.Compose(Rendering{
|
||||
Ports: map[string]map[int]int{"forge": portsAsThePlanWould(forge, nil)},
|
||||
Mesh: []string{"10.77.0.1"},
|
||||
Adopted: true,
|
||||
Ports: map[string]map[int]int{"forge": portsAsThePlanWould(forge, nil)},
|
||||
Mesh: []string{"10.77.0.1"},
|
||||
Adopted: true,
|
||||
OutwardLinks: []string{"eth0"},
|
||||
TunnelInterface: "mesh0",
|
||||
})
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
|
||||
@@ -153,6 +153,26 @@ func (b *Build) problems(module string) []string {
|
||||
"%s: %q is a bundle and says no language, so nothing can choose a compiler "+
|
||||
"for it", module, a.Name))
|
||||
}
|
||||
// **A system, for a language that compiles to a binary** (novox/hq ADR 0142). A binary
|
||||
// is pinned to one operating system at link time so a host refuses to touch a machine
|
||||
// it was not built for (novox/hq ADR 0005); an artifact that says nothing would be
|
||||
// compiled for whatever the build machine happened to be, which reads as portable and
|
||||
// is not.
|
||||
if compiled := compilesToABinary(a.Language); compiled && strings.TrimSpace(a.System) == "" {
|
||||
problems = append(problems, fmt.Sprintf(
|
||||
"%s: %q is compiled to a binary and says no system, so it would be built for "+
|
||||
"whatever the build machine happens to be. Declare one artifact per "+
|
||||
"system: %s", module, a.Name, spokenSystems()))
|
||||
} else if !compiled && strings.TrimSpace(a.System) != "" {
|
||||
problems = append(problems, fmt.Sprintf(
|
||||
"%s: %q names the system %q and is written in %q, which compiles to code that "+
|
||||
"runs anywhere — a system that decides nothing reads as though it did",
|
||||
module, a.Name, a.System, a.Language))
|
||||
} else if compiled && !knownSystem(a.System) {
|
||||
problems = append(problems, fmt.Sprintf(
|
||||
"%s: %q is built for %q, and a system is %s",
|
||||
module, a.Name, a.System, spokenSystems()))
|
||||
}
|
||||
} else {
|
||||
if a.From == "" {
|
||||
problems = append(problems, fmt.Sprintf(
|
||||
@@ -193,3 +213,42 @@ func oneOrOther(n int) string {
|
||||
}
|
||||
return "them"
|
||||
}
|
||||
|
||||
// Systems the mesh builds binaries for, which is the set a host may be pinned to (novox/hq ADR 0005).
|
||||
//
|
||||
// **A closed list, and the host's own, not the compiler's.** These are not the values a Go toolchain
|
||||
// would call an operating system — the difference between two of them is a C library, not a kernel.
|
||||
// They are what a machine reports itself to be and what a host is linked to refuse, so the list that
|
||||
// matters is the one the host understands.
|
||||
var systems = []string{"alpine", "android", "arch"}
|
||||
|
||||
// knownSystem is whether the mesh builds for it.
|
||||
func knownSystem(system string) bool {
|
||||
want := strings.ToLower(strings.TrimSpace(system))
|
||||
for _, s := range systems {
|
||||
if s == want {
|
||||
return true
|
||||
}
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
// spokenSystems is the list as a refusal says it, so a reader is one edit from right.
|
||||
func spokenSystems() string {
|
||||
return strings.Join(systems, ", ")
|
||||
}
|
||||
|
||||
// compilesToABinary is whether this language's bundle is a binary for one operating system rather
|
||||
// than code that runs wherever its interpreter does.
|
||||
//
|
||||
// **Asked of the language, not of the artifact.** A module says what it is written in; what that
|
||||
// implies is the mesh's to know, exactly as the compiler is (novox/hq ADR 0142). Asking the artifact
|
||||
// would let two artifacts in one language disagree about whether they are portable.
|
||||
func compilesToABinary(language string) bool {
|
||||
switch strings.ToLower(strings.TrimSpace(language)) {
|
||||
case "go":
|
||||
return true
|
||||
default:
|
||||
return false
|
||||
}
|
||||
}
|
||||
|
||||
@@ -0,0 +1,82 @@
|
||||
package catalogue
|
||||
|
||||
import (
|
||||
"strings"
|
||||
"testing"
|
||||
)
|
||||
|
||||
// bundleFor is a manifest whose one artifact is a bundle in the given language and system.
|
||||
func bundleFor(language, system string) Manifest {
|
||||
return Manifest{Module: "a-component", Build: &Build{Artifacts: []Artifact{
|
||||
{Name: "binary", Kind: ArtifactBundle, Language: language, System: system},
|
||||
}}}
|
||||
}
|
||||
|
||||
func problemsOf(t *testing.T, m Manifest) string {
|
||||
t.Helper()
|
||||
return strings.Join(m.Build.problems(m.Module), "\n")
|
||||
}
|
||||
|
||||
// **A language that compiles to a binary must say which system.**
|
||||
//
|
||||
// A binary is pinned to one operating system at link time, so a host refuses to touch a machine it
|
||||
// was not built for. An artifact that says nothing would be compiled for whatever the build machine
|
||||
// happened to be — which reads as portable and is not, and is the fault this check exists for.
|
||||
func TestABinaryMustSayWhichSystemItIsFor(t *testing.T) {
|
||||
got := problemsOf(t, bundleFor("go", ""))
|
||||
if !strings.Contains(got, "says no system") {
|
||||
t.Fatalf("a compiled bundle with no system was accepted:\n%s", got)
|
||||
}
|
||||
// And the refusal names what it could have said, so a reader is one edit from right.
|
||||
for _, system := range []string{"alpine", "android", "arch"} {
|
||||
if !strings.Contains(got, system) {
|
||||
t.Fatalf("the refusal does not name %q as a choice:\n%s", system, got)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func TestABinaryThatNamesASystemIsAccepted(t *testing.T) {
|
||||
if got := problemsOf(t, bundleFor("go", "arch")); got != "" {
|
||||
t.Fatalf("a compiled bundle naming a system was refused:\n%s", got)
|
||||
}
|
||||
}
|
||||
|
||||
// A system the mesh does not build for is refused where it is written. These are the host's own
|
||||
// names, not a compiler's: the difference between two of them is a C library rather than a kernel,
|
||||
// so a value that looks like an operating system to a toolchain is still wrong here.
|
||||
func TestASystemTheMeshDoesNotBuildForIsRefused(t *testing.T) {
|
||||
for _, wrong := range []string{"linux", "debian", "darwin"} {
|
||||
got := problemsOf(t, bundleFor("go", wrong))
|
||||
if !strings.Contains(got, "and a system is") {
|
||||
t.Fatalf("%q was accepted as a system:\n%s", wrong, got)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// **And a language that runs anywhere must not name one.** A system that decides nothing reads as
|
||||
// though it did, which is the same fault as a restriction that restricts nothing (novox/hq ADR 0045).
|
||||
func TestAPortableBundleMayNotNameASystem(t *testing.T) {
|
||||
got := problemsOf(t, bundleFor("typescript", "arch"))
|
||||
if !strings.Contains(got, "runs anywhere") {
|
||||
t.Fatalf("a portable bundle was allowed to name a system:\n%s", got)
|
||||
}
|
||||
}
|
||||
|
||||
func TestAPortableBundleNamingNoSystemIsAccepted(t *testing.T) {
|
||||
if got := problemsOf(t, bundleFor("typescript", "")); got != "" {
|
||||
t.Fatalf("an ordinary bundle was refused:\n%s", got)
|
||||
}
|
||||
}
|
||||
|
||||
// One component, one artifact per system: the shape the mesh's own binaries are declared in, and the
|
||||
// reason the target is the artifact's rather than the recipe's.
|
||||
func TestOneArtifactPerSystemIsAccepted(t *testing.T) {
|
||||
m := Manifest{Module: "the-host", Build: &Build{Artifacts: []Artifact{
|
||||
{Name: "arch", Kind: ArtifactBundle, Language: "go", System: "arch"},
|
||||
{Name: "alpine", Kind: ArtifactBundle, Language: "go", System: "alpine"},
|
||||
{Name: "android", Kind: ArtifactBundle, Language: "go", System: "android"},
|
||||
}}}
|
||||
if got := problemsOf(t, m); got != "" {
|
||||
t.Fatalf("one artifact per system was refused:\n%s", got)
|
||||
}
|
||||
}
|
||||
@@ -124,6 +124,16 @@ type Rendering struct {
|
||||
// nothing on this node keeps them, or the mesh has no operator key.
|
||||
Kept *KeptExport
|
||||
|
||||
// OutwardLinks is the links this machine reported as facing outside it, which the filter is
|
||||
// written around (novox/hq ADR 0140). Empty means the machine has not said, and the mesh
|
||||
// composes no filter for it rather than writing a rule around a link with no name.
|
||||
OutwardLinks []string
|
||||
|
||||
// TunnelInterface is the interface the mesh's private network runs on, named here rather than
|
||||
// imported because the overlay package rests on this one. Traffic arriving on it is the mesh's,
|
||||
// not this machine's own guest, so the filter admits it only by a rule.
|
||||
TunnelInterface string
|
||||
|
||||
// Foundation is the ports the mesh itself needs reachable on every machine, which no module
|
||||
// declares because the foundation is not a module (novox/hq 04-ISSUES/051 and 052). The broker
|
||||
// is the one that matters: a machine dials it to enrol, and a firewall derived only from
|
||||
@@ -345,7 +355,21 @@ func (r Resolution) compose(with Rendering, owner map[string]string) ([]map[stri
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
filtering := AsNftables(rules, with.Mesh, r.PublicDomain != "", with.Foundation)
|
||||
// **A machine that has not said which links face outside is sent no filter** (novox/hq ADR
|
||||
// 0140). The whole chain is written around those links: with none, the rule that lets this
|
||||
// machine's own guests keep working would name an empty set, which nftables refuses, and a rule
|
||||
// set that does not load is a machine filtering nothing while its unit reports success. Refused
|
||||
// here, where a person reads it, rather than on the machine — and the machine keeps the filter
|
||||
// it already has.
|
||||
if filters := r.filtersHere(); filters != "" && len(with.OutwardLinks) == 0 {
|
||||
return nil, fmt.Errorf(
|
||||
"%s cannot be sent a filter: it has not reported which of its links face outside, and "+
|
||||
"every rule in the chain is written around them. It reports that on each apply; "+
|
||||
"`node show %s` says whether it has. Until then %s is not sent, and the machine "+
|
||||
"keeps the filter it has", r.Node, r.Node, filters)
|
||||
}
|
||||
filtering := AsNftables(rules, with.Mesh, r.PublicDomain != "", with.Foundation,
|
||||
with.OutwardLinks, with.TunnelInterface)
|
||||
|
||||
var out []map[string]any
|
||||
for _, m := range r.Modules {
|
||||
@@ -623,6 +647,9 @@ func (r Resolution) compose(with Rendering, owner map[string]string) ([]map[stri
|
||||
// one of them as its environment without saying so (ADR 0086, issue 041).
|
||||
secretFiles := secretFilesOf(resources)
|
||||
|
||||
// Which of this module's resources its preparation runs before, if it prepares anything.
|
||||
prepareBefore := preparationTarget(m)
|
||||
|
||||
for _, unsettled := range resources {
|
||||
resource, err := ApplySettings(unsettled, with.Settings[m.Module])
|
||||
if err != nil {
|
||||
@@ -708,6 +735,18 @@ func (r Resolution) compose(with Rendering, owner map[string]string) ([]map[stri
|
||||
if renamed := reflectsRenamed(m.Module, resource["reload-on"]); renamed != nil {
|
||||
copied["reload-on"] = renamed
|
||||
}
|
||||
// **A version prepares its state before it runs** (novox/hq ADR 0135). Derived from the
|
||||
// module's own resource rather than declared beside it: what prepares the state is the
|
||||
// module's own code, so what it is given has to be what that code is given — and a
|
||||
// second resource written by hand is a second copy to drift from the first. Placed
|
||||
// immediately before it, because a run-once step stops everything the declaration
|
||||
// places after it (ADR 0052), which is how a version whose preparation failed does not
|
||||
// serve.
|
||||
if prepareBefore != "" && fmt.Sprint(resource["id"]) == prepareBefore {
|
||||
step := prepared(copied)
|
||||
owner[fmt.Sprint(step["id"])] = m.Module
|
||||
out = append(out, step)
|
||||
}
|
||||
owner[fmt.Sprint(copied["id"])] = m.Module
|
||||
out = append(out, copied)
|
||||
}
|
||||
@@ -837,6 +876,17 @@ func mapping(written string) (outer, inner int, address string, ok bool) {
|
||||
return outer, inner, strings.Join(parts[:len(parts)-2], ":"), true
|
||||
}
|
||||
|
||||
// filtersHere is the module on this node that loads the machine's packet filter, or empty when none
|
||||
// does. Named rather than counted: a refusal that says which module is one step from acted on.
|
||||
func (r Resolution) filtersHere() string {
|
||||
for _, m := range r.Modules {
|
||||
if m.Filtering != nil {
|
||||
return m.Module
|
||||
}
|
||||
}
|
||||
return ""
|
||||
}
|
||||
|
||||
// Rules is the rule set this node's filter is derived from: every module's listens, what was
|
||||
// computed for this machine, and each module's per-node exposure. The same answer whether the node
|
||||
// is adopted or converged — the one loads it as a filter, the other declares it as openings.
|
||||
@@ -1610,3 +1660,76 @@ func atMachinePort(serves map[string]any, module string, ports map[string]map[in
|
||||
func AtPublishedPort(values map[string]any, module string, published map[int]int) map[string]any {
|
||||
return atMachinePort(values, module, map[string]map[int]int{module: published})
|
||||
}
|
||||
|
||||
// PreparationArgument is how the mesh asks a module to prepare its state: one word, to the module's
|
||||
// own program, whatever that program is (novox/hq ADR 0135).
|
||||
//
|
||||
// **One word for every kind of module.** A module built as a Go binary receives it as its argument;
|
||||
// one built as a bundle receives it through the runtime, whose entry takes the same word. So the
|
||||
// mesh has one way of asking and a module has one way of answering, and neither learns the other's
|
||||
// shape.
|
||||
const PreparationArgument = "prepare"
|
||||
|
||||
// preparationTarget is the resource a module's preparation runs before: its own workload.
|
||||
//
|
||||
// The first container carrying an artifact this module built, and not itself a step — that is the
|
||||
// thing that runs the module's code, and therefore the thing whose state must be ready. Empty when
|
||||
// the module prepares nothing, or when nothing it declares could run its code.
|
||||
//
|
||||
// **A module with two own workloads gates the first of them.** Five modules in the catalogue declare
|
||||
// more than one container of their own, none of them preparing anything today. If one ever does and
|
||||
// its second workload shares the state, the gate is in front of the first — stated here because the
|
||||
// alternative is a field asking an author to restate what the mesh can see.
|
||||
func preparationTarget(m Manifest) string {
|
||||
if !m.Prepares {
|
||||
return ""
|
||||
}
|
||||
for _, r := range m.Resources {
|
||||
if fmt.Sprint(r["type"]) != "container" || !ownArtifact(r, m.Module) {
|
||||
continue
|
||||
}
|
||||
if once, _ := r["run-once"].(bool); once {
|
||||
continue
|
||||
}
|
||||
return fmt.Sprint(r["id"])
|
||||
}
|
||||
return ""
|
||||
}
|
||||
|
||||
// ownArtifact is whether a resource runs something this module built, in either spelling a manifest
|
||||
// may be in: naming the artifact, before a build resolved it, or carrying the reference a build
|
||||
// recorded — this mesh's own store, under this module's name.
|
||||
func ownArtifact(resource map[string]any, module string) bool {
|
||||
if named, _ := resource["artifact"].(string); named != "" {
|
||||
return true
|
||||
}
|
||||
image, _ := resource["image"].(string)
|
||||
return strings.HasPrefix(image, ArtifactStoreScheme+module+"/")
|
||||
}
|
||||
|
||||
// prepared is the module's own resource as the step that prepares its state: the same image, the same
|
||||
// context, run to completion with the mesh's preparation argument.
|
||||
//
|
||||
// Three things are taken away rather than copied, each because the step runs while the version it
|
||||
// prepares for is still running. A published port cannot be bound twice, and a step that tried would
|
||||
// fail for a reason that has nothing to do with the state. A fixed address cannot be held twice, for
|
||||
// the same reason. And a cadence is what a step is the opposite of: a container runs once and gates,
|
||||
// or on a schedule, or stays up, never two (ADR 0053).
|
||||
func prepared(from map[string]any) map[string]any {
|
||||
step := map[string]any{}
|
||||
for k, v := range from {
|
||||
step[k] = v
|
||||
}
|
||||
// **A hyphen, not a dot.** A resource's id is `<module>.<its own id>`, and a module's name may
|
||||
// itself contain a dot (`novox.be`), so the module is everything before the *last* dot — which
|
||||
// only works if what the mesh derives adds no dot of its own.
|
||||
step["id"] = fmt.Sprint(from["id"]) + "-prepare"
|
||||
step["name"] = fmt.Sprint(from["name"]) + "-prepare"
|
||||
step["run-once"] = true
|
||||
step["args"] = []any{PreparationArgument}
|
||||
delete(step, "ports")
|
||||
delete(step, "ip")
|
||||
delete(step, "schedule")
|
||||
delete(step, "reload-on")
|
||||
return step
|
||||
}
|
||||
|
||||
@@ -230,7 +230,23 @@ const SSHPort = 22
|
||||
// It is a floor for the same reason ssh is. A machine nobody can reach is a machine nobody can
|
||||
// repair; a machine the mesh cannot reach is a machine the mesh cannot manage. Neither is a thing
|
||||
// any module asks for, and neither may be derived away.
|
||||
func AsNftables(rules []Rule, mesh []string, outward bool, foundation []int) string {
|
||||
func AsNftables(rules []Rule, mesh []string, outward bool, foundation []int,
|
||||
outwardLinks []string, tunnel string) string {
|
||||
// The links that are not this machine's own: the ones facing outside, and the mesh's tunnel.
|
||||
// Traffic arriving on any of them is admitted only by a rule below; traffic arriving anywhere
|
||||
// else is this machine's own guest and is not something the mesh has a position on.
|
||||
//
|
||||
// The tunnel is named here deliberately. Treating it as "not outside" would make a port nothing
|
||||
// declares reachable from every machine in the mesh, which is the derivation abandoned.
|
||||
quoted := make([]string, 0, len(outwardLinks)+1)
|
||||
for _, link := range outwardLinks {
|
||||
quoted = append(quoted, fmt.Sprintf("%q", link))
|
||||
}
|
||||
if tunnel != "" {
|
||||
quoted = append(quoted, fmt.Sprintf("%q", tunnel))
|
||||
}
|
||||
inward := strings.Join(quoted, ", ")
|
||||
|
||||
var b strings.Builder
|
||||
b.WriteString("# Computed by the mesh from what is assigned to this node.\n")
|
||||
b.WriteString("# Edits are lost on the next declaration; change a module's listens instead.\n\n")
|
||||
@@ -252,6 +268,22 @@ func AsNftables(rules []Rule, mesh []string, outward bool, foundation []int) str
|
||||
b.WriteString("\t\ticmp type echo-request accept\n")
|
||||
b.WriteString("\t\ticmpv6 type { echo-request, nd-neighbor-solicit, nd-neighbor-advert, nd-router-advert } accept\n")
|
||||
|
||||
// **What this machine's own guests must be able to ask it** (novox/hq ADR 0140). A guest gets
|
||||
// its address and its names from this machine, over the link it is on, and those two questions
|
||||
// arrive at the input chain like any other. Denied, the guest never gets an address and never
|
||||
// resolves a name — which is not "a closed port" but a network that does not work at all, and it
|
||||
// is this machine's own guest asking.
|
||||
//
|
||||
// Asked for by the link it arrives on rather than by the address it comes from, for the reason
|
||||
// the forward chain below no longer names an address: a range describes one machine and goes
|
||||
// stale in silence. Anything arriving from outside, or over the tunnel, is not a guest of this
|
||||
// machine and asks through a port somebody declared, like everything else.
|
||||
if len(inward) > 0 {
|
||||
b.WriteString("\t\t# this machine's own guests asking it for an address and for names\n")
|
||||
b.WriteString(fmt.Sprintf("\t\tiifname != { %s } udp dport { 53, 67 } accept\n", inward))
|
||||
b.WriteString(fmt.Sprintf("\t\tiifname != { %s } tcp dport 53 accept\n", inward))
|
||||
}
|
||||
|
||||
// **ssh, always, and not because a module asked.**
|
||||
//
|
||||
// Every other line in this chain is derived from what is assigned here, which is the whole
|
||||
@@ -361,19 +393,36 @@ func AsNftables(rules []Rule, mesh []string, outward bool, foundation []int) str
|
||||
// about the ports most worth protecting. Rehearsed on three machines: loading these rules
|
||||
// refused a port on the host and left a published container port reachable (novox/hq issue 047).
|
||||
//
|
||||
// The way through is the one the system being replaced already used: deny by default here, and
|
||||
// then explicitly allow the runtime's own networks, so containers keep working while everything
|
||||
// else has to be asked for.
|
||||
// **What it constrains is traffic arriving from OUTSIDE this machine, and nothing else**
|
||||
// (novox/hq ADR 0140).
|
||||
//
|
||||
// It used to deny everything here and then allow the machine's own containers back by naming
|
||||
// the address ranges they sit on — two ranges fixed in this file and the rest recorded per
|
||||
// machine. Every way of keeping that list correct failed. A constant describes one machine. A
|
||||
// recorded range goes stale in silence and cannot tell a network the mesh made from one a
|
||||
// predecessor left behind. Generating it from the modules would have put half this rule set on
|
||||
// the machine.
|
||||
//
|
||||
// The list should not exist, because the mesh has no position on a container reaching outward:
|
||||
// that is not a port opened to anybody. So traffic that did not arrive from outside is accepted
|
||||
// in one line, and what did arrive from outside is allowed only where a rule below admits it.
|
||||
//
|
||||
// The tunnel is not "not outside". Accepting everything off it would make a port nothing
|
||||
// declares reachable from any machine in the mesh, which is the derivation abandoned — so it is
|
||||
// named here beside the outward links, and traffic arriving on it meets the rules below like
|
||||
// anything else.
|
||||
b.WriteString("\tchain forward {\n")
|
||||
b.WriteString("\t\ttype filter hook forward priority filter; policy drop;\n")
|
||||
b.WriteString("\t\tct state established,related accept\n")
|
||||
b.WriteString("\t\tct state invalid drop\n")
|
||||
b.WriteString("\n")
|
||||
// What the container runtime created. Without these, denying by default stops every container
|
||||
// on the machine — which is exactly the failure the absent chain was avoiding, avoided properly.
|
||||
for _, network := range runtimeNetworks {
|
||||
b.WriteString(fmt.Sprintf("\t\t# %s\n", network.why))
|
||||
b.WriteString(fmt.Sprintf("\t\tip saddr %s accept\n", network.cidr))
|
||||
// Only when there is a link to name. An empty set is a line nftables refuses, and a rule set
|
||||
// that does not load is a machine filtering nothing while its unit reports success — so the
|
||||
// chain denies rather than renders nonsense. Composing a declaration for a machine that has
|
||||
// named none is refused upstream, so this is a floor and not a path anything travels.
|
||||
if inward != "" {
|
||||
b.WriteString("\t\t# this machine's own guests reaching outward: not a port opened to anybody\n")
|
||||
b.WriteString(fmt.Sprintf("\t\tiifname != { %s } accept\n", inward))
|
||||
}
|
||||
|
||||
if len(rules) > 0 {
|
||||
@@ -430,18 +479,6 @@ func AsNftables(rules []Rule, mesh []string, outward bool, foundation []int) str
|
||||
return b.String()
|
||||
}
|
||||
|
||||
// runtimeNetworks are the container runtime's own networks, which must keep working when the
|
||||
// forward chain denies by default.
|
||||
//
|
||||
// Taken from what the system being replaced allows, which has been carrying this machine's traffic
|
||||
// for months: the runtime's bridge range and the range its compose files are given. A machine whose
|
||||
// runtime is configured with something else needs this to say so — which is a thing the mesh cannot
|
||||
// derive and a reason this list is named here rather than computed.
|
||||
var runtimeNetworks = []struct{ cidr, why string }{
|
||||
{"172.16.0.0/12", "the container runtime's bridge networks"},
|
||||
{"192.168.128.0/17", "the networks its compose files are given"},
|
||||
}
|
||||
|
||||
// byFamily splits addresses into the two nftables understands separately.
|
||||
//
|
||||
// `ip saddr` and `ip6 saddr` are different matches, and one set holding both families is a syntax
|
||||
|
||||
@@ -19,7 +19,7 @@ func TestTheBrokersPortIsOpenedThoughNoModuleDeclaresIt(t *testing.T) {
|
||||
// A machine on the private network, with one ordinary module rule, and nothing that mentions
|
||||
// the broker — which is every machine.
|
||||
rules := []Rule{{Port: 8080, From: FromMesh, Because: []string{"some-module"}}}
|
||||
out := AsNftables(rules, []string{"10.42.0.1"}, false, []int{brokerPort})
|
||||
out := AsNftables(rules, []string{"10.42.0.1"}, false, []int{brokerPort}, nil, "mesh0")
|
||||
|
||||
if !strings.Contains(out, "tcp dport 5671 accept") {
|
||||
t.Fatalf("the broker's port is not opened, so no machine could enrol:\n%s", out)
|
||||
@@ -48,7 +48,7 @@ func TestTheBrokersPortIsOpenedThoughNoModuleDeclaresIt(t *testing.T) {
|
||||
// And a mesh that was never told about a broker still gets a ruleset, rather than an empty one or
|
||||
// a panic. A control plane in that state cannot issue tokens either, which is where it surfaces.
|
||||
func TestNoBrokerMeansNoFoundationRuleRatherThanNoRuleset(t *testing.T) {
|
||||
out := AsNftables(nil, []string{"10.42.0.1"}, false, nil)
|
||||
out := AsNftables(nil, []string{"10.42.0.1"}, false, nil, nil, "mesh0")
|
||||
if !strings.Contains(out, "table inet mesh") {
|
||||
t.Fatalf("no ruleset at all:\n%s", out)
|
||||
}
|
||||
|
||||
@@ -79,7 +79,7 @@ func TestTwoModulesWantingOnePortAreBothNamed(t *testing.T) {
|
||||
t.Fatalf("a module that wanted this port open is not named: %+v", rules[0])
|
||||
}
|
||||
// The consequence, which is the reason this matters: removing web must not read as closing 443.
|
||||
nft := AsNftables(rules, nil, false, nil)
|
||||
nft := AsNftables(rules, nil, false, nil, nil, "mesh0")
|
||||
if !strings.Contains(nft, "web") || !strings.Contains(nft, "board") {
|
||||
t.Fatalf("the rendered rule set does not name both sources:\n%s", nft)
|
||||
}
|
||||
@@ -107,7 +107,7 @@ func TestAPortOpenToEveryoneIsNotAlsoRestrictedToTheMesh(t *testing.T) {
|
||||
func TestWhatNoModuleDeclaredIsClosed(t *testing.T) {
|
||||
nft := AsNftables(mustFilter(t, Resolution{Modules: []Manifest{
|
||||
{Module: "web", Listens: []Listening{{Port: 443, From: FromEverywhere}}},
|
||||
}}, nil), []string{"198.51.100.2"}, false, nil)
|
||||
}}, nil), []string{"198.51.100.2"}, false, nil, nil, "mesh0")
|
||||
// Naming the chain, not just the policy: the forward chain drops too, and an assertion on
|
||||
// "policy drop" alone passes while the input chain accepts everything. It did, once, here.
|
||||
if !strings.Contains(nft, "type filter hook input priority filter; policy drop;") {
|
||||
@@ -134,7 +134,7 @@ func TestWhatNoModuleDeclaredIsClosed(t *testing.T) {
|
||||
// `flush ruleset` would do the first and not the second: it empties every table on the machine,
|
||||
// including the ones the container runtime writes for its bridges.
|
||||
func TestReloadingReplacesOnlyTheMeshsOwnRules(t *testing.T) {
|
||||
nft := AsNftables(nil, nil, false, nil)
|
||||
nft := AsNftables(nil, nil, false, nil, nil, "mesh0")
|
||||
if strings.Contains(nft, "flush ruleset") {
|
||||
t.Fatalf("loading the rule set empties every table on the machine:\n%s", nft)
|
||||
}
|
||||
@@ -160,22 +160,122 @@ func TestReloadingReplacesOnlyTheMeshsOwnRules(t *testing.T) {
|
||||
// So the chain exists and denies by default, and the runtime's own networks are allowed explicitly
|
||||
// — which is how the system being replaced has been doing it on these machines for months.
|
||||
func TestWhatIsForwardedIsGovernedToo(t *testing.T) {
|
||||
nft := AsNftables(nil, []string{"198.51.100.2"}, false, nil)
|
||||
nft := AsNftables(nil, []string{"198.51.100.2"}, false, nil, nil, "mesh0")
|
||||
if !strings.Contains(nft, "hook forward priority filter; policy drop") {
|
||||
t.Fatalf("forwarded traffic is not governed, so container ports are open:\n%s", nft)
|
||||
}
|
||||
}
|
||||
|
||||
// And containers keep working, which is the whole reason the chain was left out before.
|
||||
func TestTheRuntimesOwnNetworksKeepWorking(t *testing.T) {
|
||||
nft := AsNftables(nil, []string{"198.51.100.2"}, false, nil)
|
||||
for _, network := range []string{"172.16.0.0/12", "192.168.128.0/17"} {
|
||||
if !strings.Contains(nft, "ip saddr "+network+" accept") {
|
||||
t.Fatalf("%s is not allowed, so denying by default stops every container:\n%s", network, nft)
|
||||
// And this machine's own guests keep working, which is the whole reason the chain was left out
|
||||
// before — by not being mentioned (novox/hq ADR 0140).
|
||||
//
|
||||
// It used to be done by naming the address ranges they sit on: two fixed here and the rest recorded
|
||||
// per machine. That list broke a workstation's containers at a flip and could not be made correct,
|
||||
// because a range describes one machine and cannot tell a network the mesh made from one a
|
||||
// predecessor left behind. What replaced it is a single line about the links traffic arrives on.
|
||||
func TestThisMachinesOwnGuestsKeepWorkingWithoutBeingNamed(t *testing.T) {
|
||||
nft := AsNftables(nil, []string{"198.51.100.2"}, false, nil, []string{"eth0"}, "mesh0")
|
||||
if !strings.Contains(nft, `iifname != { "eth0", "mesh0" } accept`) {
|
||||
t.Fatalf("what did not arrive from outside is not accepted, so this machine's own guests "+
|
||||
"reach nothing:\n%s", nft)
|
||||
}
|
||||
}
|
||||
|
||||
// No address of a machine's own networks appears anywhere in a rendered filter.
|
||||
//
|
||||
// This is the assertion that fails against the previous behaviour, and it is why it is written on
|
||||
// the text rather than on an outcome: the two ranges were a constant in this file, so nothing but
|
||||
// reading the output catches one creeping back in.
|
||||
func TestNoNetworkOfTheMachinesOwnIsNamed(t *testing.T) {
|
||||
nft := AsNftables(nil, []string{"198.51.100.2"}, false, nil, []string{"eth0"}, "mesh0")
|
||||
for _, gone := range []string{"172.16.0.0/12", "192.168.128.0/17", "saddr 192.168", "saddr 172."} {
|
||||
if strings.Contains(nft, gone) {
|
||||
t.Fatalf("%q is named, and a range describes one machine and goes stale in silence:\n%s",
|
||||
gone, nft)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// **The tunnel is constrained, not treated as inside.**
|
||||
//
|
||||
// Accepting everything arriving over the private network would make a port nothing declares
|
||||
// reachable from every machine in the mesh — the derivation abandoned, and a rule that reads as a
|
||||
// restriction while restricting nothing. So the tunnel is named beside the outward links, and
|
||||
// traffic arriving on it meets the declared rules like anything else.
|
||||
func TestTheTunnelIsConstrainedLikeAnOutwardLink(t *testing.T) {
|
||||
nft := AsNftables(nil, []string{"198.51.100.2"}, false, nil, []string{"eth0"}, "mesh0")
|
||||
line := `iifname != { "eth0", "mesh0" } accept`
|
||||
if !strings.Contains(nft, line) {
|
||||
t.Fatalf("the tunnel is not constrained, so an undeclared port is reachable from any "+
|
||||
"machine in the mesh:\n%s", nft)
|
||||
}
|
||||
}
|
||||
|
||||
// A machine with two links facing outside has both constrained. Asserted on the one line, because a
|
||||
// rule covering one and not the other would leave a machine filtering half of what reaches it.
|
||||
func TestEveryOutwardLinkIsConstrained(t *testing.T) {
|
||||
nft := AsNftables(nil, []string{"198.51.100.2"}, false, nil, []string{"eth0", "wlan0"}, "mesh0")
|
||||
if !strings.Contains(nft, `iifname != { "eth0", "wlan0", "mesh0" } accept`) {
|
||||
t.Fatalf("not every outward link is constrained:\n%s", nft)
|
||||
}
|
||||
}
|
||||
|
||||
// A guest asks its host for an address and for names, and those two arrive at the input chain. Asked
|
||||
// for by the link they arrive on, so a resolver bound anywhere but an outward link keeps answering.
|
||||
func TestGuestsMayAskTheirHostForAnAddressAndNames(t *testing.T) {
|
||||
nft := AsNftables(nil, []string{"198.51.100.2"}, false, nil, []string{"eth0"}, "mesh0")
|
||||
for _, want := range []string{
|
||||
`iifname != { "eth0", "mesh0" } udp dport { 53, 67 } accept`,
|
||||
`iifname != { "eth0", "mesh0" } tcp dport 53 accept`,
|
||||
} {
|
||||
if !strings.Contains(nft, want) {
|
||||
t.Fatalf("a guest cannot ask its host for an address or a name, which is not a closed "+
|
||||
"port but a network that does not work:\n%s", nft)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// With no link named at all the chain denies rather than rendering an empty set, which nftables
|
||||
// refuses — and a rule set that does not load is a machine filtering nothing while its unit reports
|
||||
// success. Composing a declaration for such a machine is refused upstream; this is the floor.
|
||||
func TestNoLinkNamedRendersNoCatchAllRatherThanAnEmptySet(t *testing.T) {
|
||||
nft := AsNftables(nil, []string{"198.51.100.2"}, false, nil, nil, "")
|
||||
if strings.Contains(nft, "{ }") || strings.Contains(nft, "iifname != {}") {
|
||||
t.Fatalf("an empty set is rendered, which nftables refuses:\n%s", nft)
|
||||
}
|
||||
if !strings.Contains(nft, "hook forward priority filter; policy drop") {
|
||||
t.Fatalf("the forward chain does not deny:\n%s", nft)
|
||||
}
|
||||
}
|
||||
|
||||
// A machine that has not said which links face outside is sent no filter, and the refusal names the
|
||||
// module that would have loaded it so the reader knows what is being withheld.
|
||||
func TestAMachineThatNamedNoOutwardLinkIsSentNoFilter(t *testing.T) {
|
||||
r := Resolution{Node: "anchor", Modules: []Manifest{
|
||||
{Module: "nftables", Filtering: &Filtering{Into: "/etc/mesh/filter.nft"}},
|
||||
{Module: "web", Listens: []Listening{{Port: 443, From: FromEverywhere}}},
|
||||
}}
|
||||
_, err := r.Declaration(Rendering{Mesh: []string{"198.51.100.2"}, TunnelInterface: "mesh0"})
|
||||
if err == nil {
|
||||
t.Fatal("a machine that named no outward link was sent a filter written around none")
|
||||
}
|
||||
for _, want := range []string{"anchor", "nftables", "face outside"} {
|
||||
if !strings.Contains(err.Error(), want) {
|
||||
t.Fatalf("the refusal does not say %q: %v", want, err)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// And a machine that names none but loads no filter is not refused: there is nothing to write.
|
||||
func TestAMachineWithNoFilterModuleIsNotRefused(t *testing.T) {
|
||||
r := Resolution{Node: "anchor", Modules: []Manifest{
|
||||
{Module: "web", Listens: []Listening{{Port: 443, From: FromEverywhere}}},
|
||||
}}
|
||||
if _, err := r.Declaration(Rendering{Mesh: []string{"198.51.100.2"}}); err != nil {
|
||||
t.Fatalf("a machine that loads no filter was refused one: %v", err)
|
||||
}
|
||||
}
|
||||
|
||||
// A published port is matched by what the client asked for, not by where the packet ends up.
|
||||
//
|
||||
// The runtime rewrites the destination before this chain sees it, so a rule naming the published
|
||||
@@ -183,7 +283,7 @@ func TestTheRuntimesOwnNetworksKeepWorking(t *testing.T) {
|
||||
func TestAPublishedPortIsMatchedByWhatWasAskedFor(t *testing.T) {
|
||||
nft := AsNftables(mustFilter(t, Resolution{Modules: []Manifest{
|
||||
{Module: "web", Listens: []Listening{{Port: 8080, From: FromEverywhere}}},
|
||||
}}, nil), []string{"198.51.100.2"}, false, nil)
|
||||
}}, nil), []string{"198.51.100.2"}, false, nil, nil, "mesh0")
|
||||
if !strings.Contains(nft, "ct original proto-dst 8080 accept") {
|
||||
t.Fatalf("the forwarded rule does not match the port a client asked for:\n%s", nft)
|
||||
}
|
||||
@@ -193,7 +293,7 @@ func TestAPublishedPortIsMatchedByWhatWasAskedFor(t *testing.T) {
|
||||
func TestAMeshScopedPortIsMeshScopedWhenForwarded(t *testing.T) {
|
||||
nft := AsNftables(mustFilter(t, Resolution{Modules: []Manifest{
|
||||
{Module: "store", Listens: []Listening{{Port: 5432, From: FromMesh}}},
|
||||
}}, nil), []string{"198.51.100.2"}, false, nil)
|
||||
}}, nil), []string{"198.51.100.2"}, false, nil, nil, "mesh0")
|
||||
if !strings.Contains(nft, "ip saddr { 198.51.100.2 } ct original proto-dst 5432 accept") {
|
||||
t.Fatalf("a mesh-only port is reachable from anywhere once forwarded:\n%s", nft)
|
||||
}
|
||||
@@ -203,7 +303,7 @@ func TestAMeshScopedPortIsMeshScopedWhenForwarded(t *testing.T) {
|
||||
func TestFromTheMeshIsTheNodesTheMeshKnows(t *testing.T) {
|
||||
nft := AsNftables(mustFilter(t, Resolution{Modules: []Manifest{
|
||||
{Module: "store", Listens: []Listening{{Port: 5432, From: FromMesh}}},
|
||||
}}, nil), []string{"198.51.100.2", "198.51.100.3"}, false, nil)
|
||||
}}, nil), []string{"198.51.100.2", "198.51.100.3"}, false, nil, nil, "mesh0")
|
||||
if !strings.Contains(nft, "ip saddr { 198.51.100.2, 198.51.100.3 } tcp dport 5432 accept") {
|
||||
t.Fatalf("a mesh-scoped port was not restricted to the mesh's addresses:\n%s", nft)
|
||||
}
|
||||
@@ -213,7 +313,7 @@ func TestFromTheMeshIsTheNodesTheMeshKnows(t *testing.T) {
|
||||
func TestAMeshPortOnANodeWithNoMeshIsClosedAndSaysSo(t *testing.T) {
|
||||
nft := AsNftables(mustFilter(t, Resolution{Modules: []Manifest{
|
||||
{Module: "store", Listens: []Listening{{Port: 5432, From: FromMesh}}},
|
||||
}}, nil), nil, false, nil)
|
||||
}}, nil), nil, false, nil, nil, "mesh0")
|
||||
if strings.Contains(nft, "dport 5432 accept") {
|
||||
t.Fatalf("a port meant for the mesh was opened to everything:\n%s", nft)
|
||||
}
|
||||
@@ -226,7 +326,7 @@ func TestAMeshPortOnANodeWithNoMeshIsClosedAndSaysSo(t *testing.T) {
|
||||
func TestAMachineScopedPortIsNotOpened(t *testing.T) {
|
||||
nft := AsNftables(mustFilter(t, Resolution{Modules: []Manifest{
|
||||
{Module: "cache", Listens: []Listening{{Port: 6379, From: FromMachine}}},
|
||||
}}, nil), []string{"198.51.100.2"}, false, nil)
|
||||
}}, nil), []string{"198.51.100.2"}, false, nil, nil, "mesh0")
|
||||
if strings.Contains(nft, "dport 6379 accept") {
|
||||
t.Fatalf("a port for this machine only was opened to the network:\n%s", nft)
|
||||
}
|
||||
@@ -238,7 +338,8 @@ func TestTheModuleAskingForTheRuleSetGetsEveryModulesPorts(t *testing.T) {
|
||||
{Module: "firewall", Filtering: &Filtering{Into: "/etc/mesh/filter.nft"}},
|
||||
{Module: "web", Listens: []Listening{{Port: 443, From: FromEverywhere}}},
|
||||
}}
|
||||
out, err := r.Declaration(Rendering{Mesh: []string{"198.51.100.2"}})
|
||||
out, err := r.Declaration(Rendering{Mesh: []string{"198.51.100.2"},
|
||||
OutwardLinks: []string{"eth0"}, TunnelInterface: "mesh0"})
|
||||
if err != nil {
|
||||
t.Fatalf("declaration: %v", err)
|
||||
}
|
||||
@@ -268,7 +369,7 @@ func TestAskingForTheRuleSetWithNowhereToPutItIsRefused(t *testing.T) {
|
||||
func TestAMeshOnBothAddressFamiliesRendersBoth(t *testing.T) {
|
||||
nft := AsNftables(mustFilter(t, Resolution{Modules: []Manifest{
|
||||
{Module: "store", Listens: []Listening{{Port: 5432, From: FromMesh}}},
|
||||
}}, nil), []string{"198.51.100.2", "2001:db8::2"}, false, nil)
|
||||
}}, nil), []string{"198.51.100.2", "2001:db8::2"}, false, nil, nil, "mesh0")
|
||||
if !strings.Contains(nft, "ip saddr { 198.51.100.2 } tcp dport 5432 accept") {
|
||||
t.Fatalf("the machines with v4 addresses were dropped:\n%s", nft)
|
||||
}
|
||||
@@ -296,7 +397,8 @@ func TestWhatTheMeshComputesIsAppliedBeforeWhatTheModuleDeclared(t *testing.T) {
|
||||
"restart-on": []any{"filtering"}},
|
||||
},
|
||||
}}}
|
||||
out, err := r.Declaration(Rendering{Mesh: []string{"198.51.100.2"}})
|
||||
out, err := r.Declaration(Rendering{Mesh: []string{"198.51.100.2"},
|
||||
OutwardLinks: []string{"eth0"}, TunnelInterface: "mesh0"})
|
||||
if err != nil {
|
||||
t.Fatalf("declaration: %v", err)
|
||||
}
|
||||
@@ -672,7 +774,7 @@ func TestExposureRefusesAPortNotListenedOnAndABadSource(t *testing.T) {
|
||||
// loading the rules lives on conntrack until it drops, and then the machine is reached from a
|
||||
// rescue console (novox/hq issue 047).
|
||||
func TestSSHIsOpenFromTheMeshEvenWhenNothingIsAssigned(t *testing.T) {
|
||||
nft := AsNftables(nil, []string{"198.51.100.2", "198.51.100.3"}, false, nil)
|
||||
nft := AsNftables(nil, []string{"198.51.100.2", "198.51.100.3"}, false, nil, nil, "mesh0")
|
||||
if !strings.Contains(nft, "ip saddr { 198.51.100.2, 198.51.100.3 } tcp dport 22 accept") {
|
||||
t.Fatalf("ssh is not open to the mesh, so a machine can lock everyone out:\n%s", nft)
|
||||
}
|
||||
@@ -685,7 +787,7 @@ func TestSSHIsOpenFromTheMeshEvenWhenNothingIsAssigned(t *testing.T) {
|
||||
// And from outside as well, on a machine that faces outward — because that is the way in when the
|
||||
// private network is the thing that broke.
|
||||
func TestSSHIsOpenFromOutsideOnAMachineThatFacesIt(t *testing.T) {
|
||||
nft := AsNftables(nil, []string{"198.51.100.2"}, true, nil)
|
||||
nft := AsNftables(nil, []string{"198.51.100.2"}, true, nil, nil, "mesh0")
|
||||
if !strings.Contains(nft, "\t\ttcp dport 22 accept") {
|
||||
t.Fatalf("a machine reachable from outside does not answer ssh there:\n%s", nft)
|
||||
}
|
||||
@@ -697,7 +799,7 @@ func TestSSHIsOpenFromOutsideOnAMachineThatFacesIt(t *testing.T) {
|
||||
// to narrow the rule to, so narrowing it shuts the port entirely — on the first machine anybody
|
||||
// adopts, reached over the network, closed by the act of adopting it.
|
||||
func TestSSHIsNeverLeftWithoutARule(t *testing.T) {
|
||||
nft := AsNftables(nil, nil, false, nil)
|
||||
nft := AsNftables(nil, nil, false, nil, nil, "mesh0")
|
||||
if !strings.Contains(nft, "tcp dport 22 accept") {
|
||||
t.Fatalf("a machine with no mesh addresses has no ssh rule, so adopting it locks it:\n%s", nft)
|
||||
}
|
||||
|
||||
@@ -225,6 +225,19 @@ type Manifest struct {
|
||||
// subscription to the queue it writes to (design 29 §2).
|
||||
Uses []string `json:"uses,omitempty"`
|
||||
|
||||
// Prepares says this module has state that must be brought to the shape this version needs
|
||||
// before this version runs, and that the module's own code does it (novox/hq ADR 0135).
|
||||
//
|
||||
// **A word, not an arrangement.** The mesh runs the module's own program in its preparation
|
||||
// mode, in the module's own context — every binding, credential and setting its code receives,
|
||||
// because it *is* its code. Nothing here names a container, a command, a mount or a variable:
|
||||
// the module already said all of that once, and a second copy is a second thing to drift.
|
||||
//
|
||||
// **Declared, never inferred.** The control plane cannot read what is inside an artifact, so a
|
||||
// module that ships a migration and does not say this breaks on its first upgrade. That is
|
||||
// stated in the record rather than guarded here, because nothing mechanical can guard it.
|
||||
Prepares bool `json:"prepares,omitempty"`
|
||||
|
||||
// Tools are the tools this module answers — request and reply, awaited.
|
||||
//
|
||||
// **New, and not `serves`**, which this manifest already uses for the facts a consumer needs
|
||||
@@ -558,6 +571,21 @@ type Artifact struct {
|
||||
// image built from this same module's own repository, the same as every other artifact.
|
||||
Context *ArtifactContext `json:"context,omitempty"`
|
||||
|
||||
// System is the operating system this artifact is compiled for, for a bundle whose output is a
|
||||
// binary rather than portable code (novox/hq ADR 0142).
|
||||
//
|
||||
// **Named by the artifact, not by the recipe.** A toolchain deliberately accepts nothing from
|
||||
// the module — anything a module could override there it would be writing a Dockerfile to
|
||||
// override — and yet a compiled binary is per operating system, pinned at link time so a host
|
||||
// refuses to touch a machine it was not built for (novox/hq ADR 0005). The way out is that the
|
||||
// target is a property of the artifact: one artifact declared per system, one build each, and
|
||||
// the recipe stays the mesh's.
|
||||
//
|
||||
// Empty for a bundle whose output runs anywhere, which is every interpreted language, and for
|
||||
// every other kind. A bundle in a language that compiles to a binary must say one, because
|
||||
// "compiled for whatever the build machine happened to be" is the fault this exists to prevent.
|
||||
System string `json:"system,omitempty"`
|
||||
|
||||
// Language is what this module's code is written in, for a bundle.
|
||||
//
|
||||
// **Declared, never guessed.** Inferring it from what files happen to be present makes a
|
||||
@@ -1276,6 +1304,17 @@ func ParseManifest(raw []byte) (Manifest, error) {
|
||||
"program that reads what the mesh delivered and reconciles",
|
||||
m.Module, r["id"]))
|
||||
}
|
||||
// **A module that prepares its state must have code the mesh can run** (novox/hq ADR 0135). The
|
||||
// preparation is the module's own program in its preparation mode, so it is derived from the
|
||||
// resource that runs that program — and a module declaring none has asked for something the mesh
|
||||
// cannot compose. Said here, where the manifest is read, rather than by a declaration that
|
||||
// quietly prepares nothing.
|
||||
if m.Prepares && preparationTarget(m) == "" {
|
||||
problems = append(problems, fmt.Sprintf(
|
||||
"%s says it prepares its state, and declares no container running an artifact it built — "+
|
||||
"the preparation is this module's own program, so there has to be one for the mesh to "+
|
||||
"run it in", m.Module))
|
||||
}
|
||||
// **A run-once container is a step the host runs to completion** (novox/hq ADR 0052). It is a
|
||||
// boolean modifier on the container shape — the host runs the container, requires it to exit 0,
|
||||
// and starts whatever the declaration places after it only once it has. A value that is not a
|
||||
|
||||
@@ -0,0 +1,141 @@
|
||||
package catalogue
|
||||
|
||||
import (
|
||||
"encoding/json"
|
||||
"fmt"
|
||||
"strings"
|
||||
"testing"
|
||||
)
|
||||
|
||||
// A module version prepares its state before it runs (novox/hq ADR 0135).
|
||||
//
|
||||
// What the mesh derives is the module's own resource, run once with one word, placed immediately in
|
||||
// front of the thing it prepares for. What matters in these tests is that the derivation is a copy
|
||||
// rather than a second description: the failure it replaces was a hand-written step repeating six
|
||||
// fields of the resource it preceded, each free to drift from it.
|
||||
|
||||
func aPreparingModule() Manifest {
|
||||
return Manifest{
|
||||
Module: "gitea",
|
||||
Prepares: true,
|
||||
Resources: []map[string]any{
|
||||
{"id": "state", "type": "directory", "path": "/var/lib/gitea", "mode": "0700"},
|
||||
{"id": "server", "type": "container", "name": "mesh-gitea-server",
|
||||
"image": "gitea/gitea@" + digest, "ports": []any{"3000:3000"}},
|
||||
{"id": "runtime", "type": "container", "name": "mesh-gitea",
|
||||
"image": ArtifactStoreScheme + "gitea/runtime@" + digest, "network": "host",
|
||||
"env": map[string]any{"MESH_GITEA_STATE_DIR": "/run/state"},
|
||||
"volumes": []any{"/var/lib/gitea:/run/state:ro"},
|
||||
"ports": []any{"9000:9000"}},
|
||||
},
|
||||
}
|
||||
}
|
||||
|
||||
func declaredFor(t *testing.T, m Manifest) []map[string]any {
|
||||
t.Helper()
|
||||
// The manifest as the mesh holds it: a build resolved the module's own artifact into the
|
||||
// reference it recorded, which is also how the composition knows whose code a resource runs.
|
||||
out, err := Resolution{Node: "anchor", Modules: []Manifest{m}}.Declaration(
|
||||
Rendering{ArtifactStore: "anchor.internal:5100"})
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
func idsOf(resources []map[string]any) []string {
|
||||
var ids []string
|
||||
for _, r := range resources {
|
||||
ids = append(ids, fmt.Sprint(r["id"]))
|
||||
}
|
||||
return ids
|
||||
}
|
||||
|
||||
// The step runs the module's own code, and comes immediately before it — not before the upstream
|
||||
// server the module packages, which may be the very thing the state lives in.
|
||||
func TestThePreparationRunsTheModulesOwnCodeAndComesRightBeforeIt(t *testing.T) {
|
||||
out := declaredFor(t, aPreparingModule())
|
||||
ids := idsOf(out)
|
||||
at := -1
|
||||
for i, id := range ids {
|
||||
if id == "gitea.runtime-prepare" {
|
||||
at = i
|
||||
}
|
||||
}
|
||||
if at < 0 {
|
||||
t.Fatalf("nothing prepares this module's state: %v", ids)
|
||||
}
|
||||
// A module's name may contain a dot, so a resource's module is everything before the last one —
|
||||
// which the derived id must not add to, or a machine reads the wrong owner from it.
|
||||
if strings.Count("gitea.runtime-prepare", ".") != 1 {
|
||||
t.Fatal("the derived id adds a dot, so what owns it cannot be read from it")
|
||||
}
|
||||
if ids[at+1] != "gitea.runtime" {
|
||||
t.Fatalf("the preparation is not immediately before the module's own code: %v", ids)
|
||||
}
|
||||
for _, id := range ids[:at] {
|
||||
if id == "gitea.runtime" {
|
||||
t.Fatalf("the module's own code runs before its state is prepared: %v", ids)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// It is given exactly what the module's own code is given. Asserted field by field against the
|
||||
// resource it was derived from, because writing it twice is the fault this replaces.
|
||||
func TestThePreparationIsGivenWhatTheModuleIsGiven(t *testing.T) {
|
||||
out := declaredFor(t, aPreparingModule())
|
||||
declared := byID(out)
|
||||
step, workload := declared["gitea.runtime-prepare"], declared["gitea.runtime"]
|
||||
if step == nil || workload == nil {
|
||||
t.Fatalf("expected both, got %v", idsOf(out))
|
||||
}
|
||||
for _, field := range []string{"image", "network", "env", "volumes", "type"} {
|
||||
if fmt.Sprint(step[field]) != fmt.Sprint(workload[field]) {
|
||||
t.Errorf("the preparation's %s is %v and the module's is %v", field, step[field], workload[field])
|
||||
}
|
||||
}
|
||||
if once, _ := step["run-once"].(bool); !once {
|
||||
t.Error("the preparation is not a step, so nothing waits for it and nothing is gated by it")
|
||||
}
|
||||
if fmt.Sprint(step["args"]) != fmt.Sprint([]any{PreparationArgument}) {
|
||||
t.Errorf("the preparation is asked for as %v", step["args"])
|
||||
}
|
||||
if fmt.Sprint(step["name"]) == fmt.Sprint(workload["name"]) {
|
||||
t.Error("the preparation and the workload have one name, so one removes the other")
|
||||
}
|
||||
// A published port cannot be bound twice, and the version being replaced is still running.
|
||||
if _, published := step["ports"]; published {
|
||||
t.Errorf("the preparation publishes a port the running version holds: %v", step["ports"])
|
||||
}
|
||||
}
|
||||
|
||||
// A module that says nothing about preparing gets nothing, which is most modules.
|
||||
func TestAModuleThatPreparesNothingGetsNoStep(t *testing.T) {
|
||||
m := aPreparingModule()
|
||||
m.Prepares = false
|
||||
for _, id := range idsOf(declaredFor(t, m)) {
|
||||
if id == "gitea.runtime-prepare" {
|
||||
t.Fatal("a module that prepares nothing was given a preparation")
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// A module whose own code the mesh cannot find has nothing to ask, and saying so where the manifest
|
||||
// is read beats a declaration that quietly prepares nothing.
|
||||
func TestAModuleThatPreparesAndRunsNoneOfItsOwnCodeIsRefused(t *testing.T) {
|
||||
m := Manifest{
|
||||
Module: "gitea",
|
||||
Prepares: true,
|
||||
Resources: []map[string]any{
|
||||
// Only the upstream server it packages: nothing here runs gitea's own code.
|
||||
{"id": "server", "type": "container", "name": "mesh-gitea-server", "image": "gitea/gitea@" + digest},
|
||||
},
|
||||
}
|
||||
raw, err := json.Marshal(m)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if _, err := ParseManifest(raw); err == nil {
|
||||
t.Fatal("a module that prepares its state with nothing of its own to run was accepted")
|
||||
}
|
||||
}
|
||||
@@ -12,5 +12,5 @@ func TestPrintRehearsalRuleset(t *testing.T) {
|
||||
rules := mustFilter(t, Resolution{Modules: []Manifest{
|
||||
{Module: "pub", Listens: []Listening{{Port: 8099, From: FromMesh, Why: "the thing it serves"}}},
|
||||
}}, nil)
|
||||
t.Log("\n" + AsNftables(rules, []string{"192.0.2.20"}, true, nil))
|
||||
t.Log("\n" + AsNftables(rules, []string{"192.0.2.20"}, true, nil, nil, "mesh0"))
|
||||
}
|
||||
|
||||
@@ -48,7 +48,11 @@ type Seat struct {
|
||||
//
|
||||
// In the order a person reads it: the mesh's own, then a node's.
|
||||
var defaultSeats = []Seat{
|
||||
{Name: "mesh-controller", Scope: ScopeMesh, Decision: "novox/hq ADR 0079"},
|
||||
// The control plane states what it did under the seat it holds (novox/hq ADR 0134): a role's
|
||||
// events belong to the role, so they keep their address while the holder is replaced. No accepts,
|
||||
// so no work queue is raised for it — only what its holder may say.
|
||||
{Name: "mesh-controller", Scope: ScopeMesh, Decision: "novox/hq ADR 0079",
|
||||
Emits: []string{"applied", "refused", "built-before"}},
|
||||
{Name: "mesh-store", Scope: ScopeMesh, Delivers: "postgres-database", Decision: "novox/hq ADR 0079"},
|
||||
// **Delivers the mesh's own bus, not `amqp`.** Those were the same word until
|
||||
// ADR 0127 separated them: `amqp` is a backing service a module may require, and this seat is
|
||||
|
||||
@@ -36,12 +36,21 @@ type Build struct {
|
||||
// Against is every artifact this build stood on, as references rather than module names —
|
||||
// what makes a build edge derived rather than declared (ADR 0009).
|
||||
Against []string
|
||||
// Read is every repository this build read source from besides the module's own (novox/hq
|
||||
// 04-ISSUES/131), at the ref it read.
|
||||
Read []ReadRepository
|
||||
// Failed is the builder's own words, empty when it worked.
|
||||
Failed string
|
||||
Made []Artifact
|
||||
At time.Time
|
||||
}
|
||||
|
||||
// ReadRepository is a repository a build read source from besides the module's own.
|
||||
type ReadRepository struct {
|
||||
Repository string `json:"repository"`
|
||||
Ref string `json:"ref,omitempty"`
|
||||
}
|
||||
|
||||
// Artifact is one thing a build published.
|
||||
type Artifact struct {
|
||||
Name string `json:"name"`
|
||||
@@ -66,17 +75,21 @@ func (i *Inventory) RecordBuild(ctx context.Context, b Build) error {
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
read, err := json.Marshal(b.Read)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
var module *string
|
||||
if b.Module != "" {
|
||||
module = &b.Module
|
||||
}
|
||||
_, err = i.store.Pool().Exec(ctx,
|
||||
`insert into build (id, repository, ref, module, commit_hash, built_on, failed, made,
|
||||
source_path, manifest, built_against)
|
||||
values ($1, $2, $3, $4, $5, $6, $7, $8, $9, $10, $11)
|
||||
source_path, manifest, built_against, built_contexts)
|
||||
values ($1, $2, $3, $4, $5, $6, $7, $8, $9, $10, $11, $12)
|
||||
on conflict (id) do nothing`,
|
||||
b.ID, b.Repository, b.Ref, module, b.Commit, b.On, b.Failed, made,
|
||||
b.Path, manifestOrNil(b.Manifest), against)
|
||||
b.Path, manifestOrNil(b.Manifest), against, read)
|
||||
return err
|
||||
}
|
||||
|
||||
@@ -199,6 +212,44 @@ func (i *Inventory) BuiltAgainst(ctx context.Context) (map[string][]string, erro
|
||||
return against, rows.Err()
|
||||
}
|
||||
|
||||
// ReadRepositories is what each module's newest successful build read source from besides its own
|
||||
// repository, by module name.
|
||||
//
|
||||
// The mirror of BuiltAgainst, and derived the same way and for the same reason: a merge into a
|
||||
// repository a module only packages is a change to that module, and the manifest the mesh keeps
|
||||
// carries nothing that would say so (novox/hq 04-ISSUES/131).
|
||||
func (i *Inventory) ReadRepositories(ctx context.Context) (map[string][]ReadRepository, error) {
|
||||
rows, err := i.store.Pool().Query(ctx,
|
||||
`select distinct on (module) module, built_contexts
|
||||
from build
|
||||
where module is not null and module <> '' and failed = ''
|
||||
order by module, at desc`)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
defer rows.Close()
|
||||
|
||||
read := map[string][]ReadRepository{}
|
||||
for rows.Next() {
|
||||
var module string
|
||||
var raw []byte
|
||||
if err := rows.Scan(&module, &raw); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
if len(raw) == 0 {
|
||||
continue
|
||||
}
|
||||
var of []ReadRepository
|
||||
if err := json.Unmarshal(raw, &of); err != nil {
|
||||
continue
|
||||
}
|
||||
if len(of) > 0 {
|
||||
read[module] = of
|
||||
}
|
||||
}
|
||||
return read, rows.Err()
|
||||
}
|
||||
|
||||
// manifestOrNil keeps the difference between "declared nothing" and "predates this being kept".
|
||||
//
|
||||
// A build recorded before the mesh kept manifests has no manifest, and that is not the same as one
|
||||
|
||||
@@ -136,3 +136,36 @@ func ids(builds []Build) []string {
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
// What a build read besides its module's own repository comes back for the newest build of each
|
||||
// module, and only for builds that worked. Nothing recorded is absent rather than empty, which is how
|
||||
// a build made before the mesh kept this is told from one that read nothing (novox/hq 04-ISSUES/131).
|
||||
func TestWhatABuildReadComesBackForTheNewestBuildOfEachModule(t *testing.T) {
|
||||
inv := fresh(t)
|
||||
ctx := context.Background()
|
||||
older := aBuild("older", "builder", "")
|
||||
older.Read = []ReadRepository{{Repository: "novox/mesh-controller", Ref: "release"}}
|
||||
newer := aBuild("newer", "builder", "")
|
||||
newer.Read = []ReadRepository{{Repository: "novox/mesh-controller", Ref: "main"}}
|
||||
plain := aBuild("plain", "gitea", "")
|
||||
failed := aBuild("failed", "route-proxy", "cannot clone")
|
||||
failed.Read = []ReadRepository{{Repository: "novox/mesh-controller", Ref: "main"}}
|
||||
for _, b := range []Build{older, newer, plain, failed} {
|
||||
if err := inv.RecordBuild(ctx, b); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
}
|
||||
read, err := inv.ReadRepositories(ctx)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if len(read["builder"]) != 1 || read["builder"][0].Ref != "main" {
|
||||
t.Fatalf("the newest build's reading is %+v", read["builder"])
|
||||
}
|
||||
if _, has := read["gitea"]; has {
|
||||
t.Fatalf("a build that read nothing but its own repository reads as %+v", read["gitea"])
|
||||
}
|
||||
if _, has := read["route-proxy"]; has {
|
||||
t.Fatal("a failed build's reading was kept as what that module reads")
|
||||
}
|
||||
}
|
||||
|
||||
@@ -30,12 +30,12 @@ func TestRefusedAndFailedAreDifferentSituations(t *testing.T) {
|
||||
refuser := nodeNamed(t, inv, "refuser")
|
||||
failer := nodeNamed(t, inv, "failer")
|
||||
|
||||
if err := inv.RecordDoing(ctx, refuser, Doing{
|
||||
if _, err := inv.RecordDoing(ctx, refuser, Doing{
|
||||
Outcome: OutcomeRefused, Refused: "resource \"x\": a file needs a path",
|
||||
}); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if err := inv.RecordDoing(ctx, failer, Doing{
|
||||
if _, err := inv.RecordDoing(ctx, failer, Doing{
|
||||
Outcome: OutcomeFailed,
|
||||
Failed: []FailedResource{{ID: "svc", Error: "unit not found"}},
|
||||
Applied: 4,
|
||||
@@ -70,7 +70,7 @@ func TestAMachineDoingWhatItWasToldIsNotOnTheList(t *testing.T) {
|
||||
inv := fresh(t)
|
||||
ctx := context.Background()
|
||||
id := nodeNamed(t, inv, "fine")
|
||||
if err := inv.RecordDoing(ctx, id, Doing{Outcome: OutcomeApplied, Applied: 6}); err != nil {
|
||||
if _, err := inv.RecordDoing(ctx, id, Doing{Outcome: OutcomeApplied, Applied: 6}); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
wrong, err := inv.NotDoingWhatTheyWereTold(ctx)
|
||||
@@ -97,12 +97,12 @@ func TestTheLastReportReplacesTheOneBefore(t *testing.T) {
|
||||
inv := fresh(t)
|
||||
ctx := context.Background()
|
||||
id := nodeNamed(t, inv, "recovered")
|
||||
if err := inv.RecordDoing(ctx, id, Doing{
|
||||
if _, err := inv.RecordDoing(ctx, id, Doing{
|
||||
Outcome: OutcomeFailed, Failed: []FailedResource{{ID: "a", Error: "no"}},
|
||||
}); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if err := inv.RecordDoing(ctx, id, Doing{Outcome: OutcomeApplied, Applied: 3}); err != nil {
|
||||
if _, err := inv.RecordDoing(ctx, id, Doing{Outcome: OutcomeApplied, Applied: 3}); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
wrong, err := inv.NotDoingWhatTheyWereTold(ctx)
|
||||
@@ -141,7 +141,7 @@ func TestWhatANodeSaidGoesWhenTheNodeDoes(t *testing.T) {
|
||||
inv := fresh(t)
|
||||
ctx := context.Background()
|
||||
id := nodeNamed(t, inv, "leaving")
|
||||
if err := inv.RecordDoing(ctx, id, Doing{Outcome: OutcomeFailed}); err != nil {
|
||||
if _, err := inv.RecordDoing(ctx, id, Doing{Outcome: OutcomeFailed}); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if _, err := inv.store.Pool().Exec(ctx, `delete from node where name = 'leaving'`); err != nil {
|
||||
@@ -257,7 +257,7 @@ func TestTheSameFailureReportedAgainIsCountedNotRestarted(t *testing.T) {
|
||||
id := nodeNamed(t, inv, "looping")
|
||||
same := Doing{Outcome: OutcomeFailed, Failed: []FailedResource{{ID: "img", Error: "no such image"}}}
|
||||
|
||||
if err := inv.RecordDoing(ctx, id, same); err != nil {
|
||||
if _, err := inv.RecordDoing(ctx, id, same); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
first, _, err := inv.DoingOf(ctx, "looping")
|
||||
@@ -269,7 +269,7 @@ func TestTheSameFailureReportedAgainIsCountedNotRestarted(t *testing.T) {
|
||||
}
|
||||
|
||||
for range StuckAfter - 1 {
|
||||
if err := inv.RecordDoing(ctx, id, same); err != nil {
|
||||
if _, err := inv.RecordDoing(ctx, id, same); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
}
|
||||
@@ -287,7 +287,7 @@ func TestTheSameFailureReportedAgainIsCountedNotRestarted(t *testing.T) {
|
||||
// The same resource failing with different words — a duration, a counter — is still the same
|
||||
// failure: it is the resource that loops, not the sentence.
|
||||
reworded := Doing{Outcome: OutcomeFailed, Failed: []FailedResource{{ID: "img", Error: "no such image (after 31s)"}}}
|
||||
if err := inv.RecordDoing(ctx, id, reworded); err != nil {
|
||||
if _, err := inv.RecordDoing(ctx, id, reworded); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
still, _, err := inv.DoingOf(ctx, "looping")
|
||||
@@ -300,7 +300,7 @@ func TestTheSameFailureReportedAgainIsCountedNotRestarted(t *testing.T) {
|
||||
|
||||
// A different failure is a new situation, not a longer one.
|
||||
other := Doing{Outcome: OutcomeFailed, Failed: []FailedResource{{ID: "svc", Error: "unit not found"}}}
|
||||
if err := inv.RecordDoing(ctx, id, other); err != nil {
|
||||
if _, err := inv.RecordDoing(ctx, id, other); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
changed, _, err := inv.DoingOf(ctx, "looping")
|
||||
@@ -312,7 +312,7 @@ func TestTheSameFailureReportedAgainIsCountedNotRestarted(t *testing.T) {
|
||||
}
|
||||
|
||||
// And a clean apply clears it: the machine is doing what it was told, since nothing.
|
||||
if err := inv.RecordDoing(ctx, id, Doing{Outcome: OutcomeApplied, Applied: 2}); err != nil {
|
||||
if _, err := inv.RecordDoing(ctx, id, Doing{Outcome: OutcomeApplied, Applied: 2}); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
fine, _, err := inv.DoingOf(ctx, "looping")
|
||||
@@ -324,7 +324,7 @@ func TestTheSameFailureReportedAgainIsCountedNotRestarted(t *testing.T) {
|
||||
}
|
||||
|
||||
// The list of what is wrong carries the count, so `status` can say it.
|
||||
if err := inv.RecordDoing(ctx, id, same); err != nil {
|
||||
if _, err := inv.RecordDoing(ctx, id, same); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
wrong, err := inv.NotDoingWhatTheyWereTold(ctx)
|
||||
|
||||
@@ -0,0 +1,13 @@
|
||||
-- A build says which repositories it read, so a merge can find everything it affects.
|
||||
--
|
||||
-- A module is built from the one repository the mesh records — where its module.json lives — and some
|
||||
-- modules' recipes reach into a second for the source they package: the packaging and the source are
|
||||
-- allowed to live apart (catalogue's ArtifactContext). That second repository is named in the manifest
|
||||
-- the build read, and the manifest the mesh *keeps* carries no build section, so nothing on the mesh
|
||||
-- could say that a merge into the other repository is a change to this module at all. Two modules are
|
||||
-- built from the control plane's own repository, and neither had ever been rebuilt when it moved
|
||||
-- (novox/hq 04-ISSUES/131).
|
||||
--
|
||||
-- Nullable, like the two derived columns beside it: null is a build recorded before the mesh kept
|
||||
-- this, which is not the same as a build that read nothing but its module's own repository.
|
||||
alter table build add column built_contexts jsonb;
|
||||
@@ -0,0 +1,19 @@
|
||||
-- The networks a machine routes for what it hosts, beyond the container runtime's own defaults.
|
||||
--
|
||||
-- novox/hq ADR 0137. The derived packet filter denies forwarding by default and then allows the
|
||||
-- container runtime's two default pools, named in the controller's code with a comment saying that
|
||||
-- a machine configured otherwise "needs this to say so" — and no way to say it. So the filter was
|
||||
-- correct only on a machine whose runtime used the defaults, and silently wrong on any other.
|
||||
--
|
||||
-- Measured on 2026-09-28: flipping a workstation to the derived filter cut egress for five of its
|
||||
-- container networks and for every network its test beds create, because those are allocated from
|
||||
-- ranges the two defaults do not cover. Nothing reported a fault; the containers simply could not
|
||||
-- reach anything.
|
||||
--
|
||||
-- A node-level fact, beside the node's public domain and for the same reason: it is a property of
|
||||
-- the machine, not of whichever module happens to load the filter today. Swapping that module must
|
||||
-- not lose it.
|
||||
--
|
||||
-- Null for a machine that routes nothing but the runtime's defaults, which is the ordinary case and
|
||||
-- what every machine held before this column existed.
|
||||
alter table node add column routed_networks jsonb;
|
||||
@@ -0,0 +1,26 @@
|
||||
-- Which of a machine's links face outside it, replacing the networks it was told to say it routes.
|
||||
--
|
||||
-- novox/hq ADR 0140, superseding 0137 and 0139. The derived filter blocked everything passing
|
||||
-- through a machine and then allowed the machine's own containers back by naming the address ranges
|
||||
-- they sit on: two ranges fixed in the controller's source, the rest recorded by 0043's column.
|
||||
--
|
||||
-- Every route to a correct list fails. A constant describes one machine. A recorded range goes stale
|
||||
-- in silence, and cannot tell a network the mesh made from one a predecessor left behind — measured
|
||||
-- on the control-node, where six ranges fall outside the constants and two of the six belong to
|
||||
-- services the mesh does not run. Generating the list from the modules put half the rule set on the
|
||||
-- machine.
|
||||
--
|
||||
-- The list should not exist, because the mesh has no position on a container reaching outward: that
|
||||
-- is not a port opened to anybody. The filter constrains what arrives from OUTSIDE the machine and
|
||||
-- says nothing about what did not, which needs one fact instead of a list — which links "outside"
|
||||
-- arrives on.
|
||||
--
|
||||
-- Reported by the machine on every apply, never recorded by hand, so it cannot go stale. Null for a
|
||||
-- machine that has not reported yet; the mesh composes no filter for such a machine and leaves the
|
||||
-- one it has, because a rule written around a link with no name is a rule set that does not load.
|
||||
alter table node add column outward_links jsonb;
|
||||
|
||||
-- What 0043 recorded is not migrated into it. The ranges answered a question that no longer exists,
|
||||
-- and every machine that named one keeps working without it: the traffic those ranges allowed is now
|
||||
-- allowed by not having arrived from outside.
|
||||
alter table node drop column routed_networks;
|
||||
+84
-18
@@ -518,6 +518,61 @@ func (i *Inventory) PublicDomainOf(ctx context.Context, name string) (string, er
|
||||
return *domain, nil
|
||||
}
|
||||
|
||||
// RecordOutwardLinks keeps the links a machine reported as facing outside it.
|
||||
//
|
||||
// A reported fact, not a setting (novox/hq ADR 0140). It replaces the networks a machine used to be
|
||||
// told to say it routes: the filter blocked everything passing through and then allowed the machine's
|
||||
// own containers back by naming their address ranges, and every way of keeping that list correct
|
||||
// failed — a constant describes one machine, and a recorded range goes stale in silence. The filter
|
||||
// now constrains what arrives from outside and says nothing about what did not, and the one thing it
|
||||
// needs is which links "outside" arrives on. The machine reads that from its own routing table on
|
||||
// every apply, so it cannot go stale and nobody types it.
|
||||
//
|
||||
// An empty list clears it, which is what a machine with no route off itself reports. The mesh then
|
||||
// composes no filter for that machine at all.
|
||||
func (i *Inventory) RecordOutwardLinks(ctx context.Context, id string, links []string) error {
|
||||
var kept []string
|
||||
for _, name := range links {
|
||||
if name = strings.TrimSpace(name); name != "" {
|
||||
kept = append(kept, name)
|
||||
}
|
||||
}
|
||||
if len(kept) == 0 {
|
||||
_, err := i.store.Pool().Exec(ctx,
|
||||
`update node set outward_links = null where id = $1`, id)
|
||||
return err
|
||||
}
|
||||
body, err := json.Marshal(kept)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
_, err = i.store.Pool().Exec(ctx,
|
||||
`update node set outward_links = $2 where id = $1`, id, string(body))
|
||||
return err
|
||||
}
|
||||
|
||||
// OutwardLinksOf is the links a machine reported as facing outside it, empty when it has reported
|
||||
// none — which is a machine the mesh composes no filter for.
|
||||
func (i *Inventory) OutwardLinksOf(ctx context.Context, name string) ([]string, error) {
|
||||
var body []byte
|
||||
err := i.store.Pool().QueryRow(ctx,
|
||||
`select outward_links from node where name = $1`, name).Scan(&body)
|
||||
if errors.Is(err, pgx.ErrNoRows) {
|
||||
return nil, fmt.Errorf("%w: %s", ErrNoSuchNode, name)
|
||||
}
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
if len(body) == 0 {
|
||||
return nil, nil
|
||||
}
|
||||
var links []string
|
||||
if err := json.Unmarshal(body, &links); err != nil {
|
||||
return nil, fmt.Errorf("the outward links recorded for %s are not a list: %w", name, err)
|
||||
}
|
||||
return links, nil
|
||||
}
|
||||
|
||||
// RecordOverlayKey keeps the public half a node generated.
|
||||
func (i *Inventory) RecordOverlayKey(ctx context.Context, node, key string) error {
|
||||
if strings.TrimSpace(key) == "" {
|
||||
@@ -670,31 +725,39 @@ func sameFailure(a, b Doing) bool {
|
||||
// a clean apply clears both (novox/hq 04-ISSUES/065). The previous row is read first and the
|
||||
// comparison made here, so "the same" is a rule this package states rather than a jsonb equality
|
||||
// that would restart the count on a changed word in an error.
|
||||
func (i *Inventory) RecordDoing(ctx context.Context, node string, d Doing) error {
|
||||
// **And whether this report was news**, which is what makes a fact about it worth stating (novox/hq
|
||||
// ADR 0134). A machine reconciles continuously and reports each time; the same outcome about the same
|
||||
// declaration is the same state said again, and a fact per report would be a fact per minute per
|
||||
// machine that tells nobody anything. Read here because the previous row is read here anyway.
|
||||
func (i *Inventory) RecordDoing(ctx context.Context, node string, d Doing) (news bool, err error) {
|
||||
failed, err := json.Marshal(d.Failed)
|
||||
if err != nil {
|
||||
return err
|
||||
return false, err
|
||||
}
|
||||
var before Doing
|
||||
var beforeFailed []byte
|
||||
found := i.store.Pool().QueryRow(ctx,
|
||||
`select outcome, refused, failed, failing_since, failures, coalesce(declared,'')
|
||||
from node_report where node = $1`,
|
||||
node).Scan(&before.Outcome, &before.Refused, &beforeFailed, &before.Since, &before.Times,
|
||||
&before.Declared)
|
||||
switch {
|
||||
case errors.Is(found, pgx.ErrNoRows):
|
||||
news = true
|
||||
case found != nil:
|
||||
return false, found
|
||||
default:
|
||||
if err := json.Unmarshal(beforeFailed, &before.Failed); err != nil {
|
||||
return false, err
|
||||
}
|
||||
news = before.Outcome != d.Outcome || before.Declared != d.Declared || !sameFailure(before, d)
|
||||
}
|
||||
var since *time.Time
|
||||
times := 0
|
||||
if d.Outcome != OutcomeApplied {
|
||||
var before Doing
|
||||
var beforeFailed []byte
|
||||
err := i.store.Pool().QueryRow(ctx,
|
||||
`select outcome, refused, failed, failing_since, failures from node_report where node = $1`,
|
||||
node).Scan(&before.Outcome, &before.Refused, &beforeFailed, &before.Since, &before.Times)
|
||||
switch {
|
||||
case errors.Is(err, pgx.ErrNoRows):
|
||||
case err != nil:
|
||||
return err
|
||||
default:
|
||||
if err := json.Unmarshal(beforeFailed, &before.Failed); err != nil {
|
||||
return err
|
||||
}
|
||||
}
|
||||
now := time.Now()
|
||||
since, times = &now, 1
|
||||
if err == nil && sameFailure(before, d) && before.Since != nil {
|
||||
if found == nil && sameFailure(before, d) && before.Since != nil {
|
||||
since, times = before.Since, before.Times+1
|
||||
}
|
||||
}
|
||||
@@ -707,7 +770,10 @@ func (i *Inventory) RecordDoing(ctx context.Context, node string, d Doing) error
|
||||
declared = excluded.declared,
|
||||
failing_since = excluded.failing_since, failures = excluded.failures`,
|
||||
node, d.Outcome, d.Refused, failed, d.Applied, d.Declared, since, times)
|
||||
return err
|
||||
if err != nil {
|
||||
return false, err
|
||||
}
|
||||
return news, nil
|
||||
}
|
||||
|
||||
// NotDoingWhatTheyWereTold is every machine whose last report was not a clean apply.
|
||||
|
||||
@@ -88,10 +88,23 @@ type BuildResult struct {
|
||||
// (novox/hq ADR 0009). The catalogue turns these into edges; nothing else need care.
|
||||
Against []string `json:"against,omitempty"`
|
||||
|
||||
// Read is every repository this build read source from besides the module's own. A module whose
|
||||
// recipe packages source that lives elsewhere is affected when that repository moves, and the
|
||||
// manifest the mesh keeps says nothing about it (novox/hq 04-ISSUES/131).
|
||||
Read []ReadRepository `json:"read,omitempty"`
|
||||
|
||||
// Failed is why, when it did.
|
||||
Failed string `json:"failed,omitempty"`
|
||||
}
|
||||
|
||||
// ReadRepository is a repository a build read source from besides the module's own, at the branch,
|
||||
// tag or commit it read. Spelled here as well as in the catalogue and the inventory, for the reason
|
||||
// MadeArtifact is: one direction of dependency.
|
||||
type ReadRepository struct {
|
||||
Repository string `json:"repository"`
|
||||
Ref string `json:"ref,omitempty"`
|
||||
}
|
||||
|
||||
// MadeArtifact is one thing a build produced, as a person would want it reported.
|
||||
type MadeArtifact struct {
|
||||
Name string `json:"name"`
|
||||
|
||||
@@ -30,6 +30,11 @@ type Bus interface {
|
||||
// (design 29 §4, the *state* shape).
|
||||
PublishDeclaration(ctx context.Context, node string, body []byte) error
|
||||
|
||||
// PublishSeatEvent states a fact under a role's own name, for the holder of that role. A
|
||||
// module's event is addressed to the module; a role's is addressed to the role, so it keeps
|
||||
// meaning when the holder changes (novox/hq ADR 0121, ADR 0129).
|
||||
PublishSeatEvent(ctx context.Context, seat, event string, body []byte) error
|
||||
|
||||
// AskTool sends one question to a module's tool and awaits one answer. A tool nobody serves
|
||||
// must say so **at once** rather than after the whole wait: the difference between "that
|
||||
// module is down" and "that tool is slow" is the first thing a person asking wants.
|
||||
@@ -81,6 +86,13 @@ func EventSubject(source, key string) string {
|
||||
return "mesh.mod." + source + ".event." + key
|
||||
}
|
||||
|
||||
// SeatEventSubject is where a role's own event lands. Derived from the role, never from its holder:
|
||||
// a fact about the build machine or about the control plane keeps its address when the module holding
|
||||
// that role is replaced (novox/hq ADR 0121, ADR 0129).
|
||||
func SeatEventSubject(seat, event string) string {
|
||||
return "mesh.seat." + seat + ".event." + event
|
||||
}
|
||||
|
||||
// DeclareSubject is where one node's declaration lands. Last-per-subject on the NODES stream, so
|
||||
// a node that was away gets exactly the current one and a replayed older one is refused by
|
||||
// sequence — the wire-level answer to novox/hq issue 107.
|
||||
@@ -112,6 +124,27 @@ func (b OverNATS) PublishEvent(ctx context.Context, key, source, node string, bo
|
||||
return nil
|
||||
}
|
||||
|
||||
// PublishSeatEvent states a role's own fact. Same envelope as a module's event and a different
|
||||
// address: the source header is the role, because that is what the fact is about.
|
||||
func (b OverNATS) PublishSeatEvent(ctx context.Context, seat, event string, body []byte) error {
|
||||
id, err := eventID()
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
h := nats.Header{}
|
||||
h.Set("x-event-id", id)
|
||||
h.Set("x-source", seat)
|
||||
_, err = b.JS.PublishMsg(&nats.Msg{
|
||||
Subject: SeatEventSubject(seat, event),
|
||||
Header: h,
|
||||
Data: body,
|
||||
}, nats.MsgId(id), nats.Context(ctx))
|
||||
if err != nil {
|
||||
return fmt.Errorf("stating %s of the %s seat: %w", event, seat, err)
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
func (b OverNATS) PublishDeclaration(ctx context.Context, node string, body []byte) error {
|
||||
_, err := b.JS.Publish(DeclareSubject(node), body, nats.Context(ctx))
|
||||
if err != nil {
|
||||
|
||||
+27
-13
@@ -265,7 +265,7 @@ func (e Enrolment) Outstanding(ctx context.Context, node string) (string, error)
|
||||
return e.Inventory.Outstanding(ctx, node)
|
||||
}
|
||||
|
||||
func (e Enrolment) Heard(ctx context.Context, report Report) (err error) {
|
||||
func (e Enrolment) Heard(ctx context.Context, report Report) (news bool, err error) {
|
||||
// A store that could not be asked right now is said as such, so the report is kept for
|
||||
// another attempt rather than acknowledged and lost (novox/hq issue 082).
|
||||
defer func() {
|
||||
@@ -274,11 +274,11 @@ func (e Enrolment) Heard(ctx context.Context, report Report) (err error) {
|
||||
}
|
||||
}()
|
||||
if report.Node == "" {
|
||||
return errors.New("a report named no node")
|
||||
return false, errors.New("a report named no node")
|
||||
}
|
||||
node, err := e.Inventory.NodeByName(ctx, report.Node)
|
||||
if err != nil {
|
||||
return err
|
||||
return false, err
|
||||
}
|
||||
|
||||
// What an adopted node holds, which firewall it found, and what is reachable on it (novox/hq
|
||||
@@ -298,7 +298,18 @@ func (e Enrolment) Heard(ctx context.Context, report Report) (err error) {
|
||||
Port: r.Port, By: r.By, Published: r.Published, ContainerPort: r.ContainerPort})
|
||||
}
|
||||
if err := e.Inventory.RecordAdoption(ctx, node.ID, held, report.Firewall, reachable); err != nil {
|
||||
return err
|
||||
return false, err
|
||||
}
|
||||
}
|
||||
// Which of its links face outside (novox/hq ADR 0140), whenever it says so. Recorded on every
|
||||
// report that carries it, adopted or converged, because the filter the mesh composes is written
|
||||
// around it — and never cleared by a report that carries none, which is every bare word that the
|
||||
// node is there. A machine whose routing table it could not read reports nothing rather than
|
||||
// guessing, and keeps whatever it last said; a machine with genuinely no route off itself is one
|
||||
// the mesh composes no filter for at all.
|
||||
if len(report.Outward) > 0 {
|
||||
if err := e.Inventory.RecordOutwardLinks(ctx, node.ID, report.Outward); err != nil {
|
||||
return false, err
|
||||
}
|
||||
}
|
||||
// What it says about the tunnel it carried (novox/hq ADR 0105), whenever it says it.
|
||||
@@ -308,7 +319,7 @@ func (e Enrolment) Heard(ctx context.Context, report Report) (err error) {
|
||||
Peers: report.Tunnel.Peers, State: report.Tunnel.State, Note: report.Tunnel.Note,
|
||||
Kept: report.Tunnel.Kept,
|
||||
}); err != nil {
|
||||
return err
|
||||
return false, err
|
||||
}
|
||||
}
|
||||
// A node taking a found tunnel's key after enrolment (novox/hq ADR 0105). Verified against the
|
||||
@@ -317,9 +328,9 @@ func (e Enrolment) Heard(ctx context.Context, report Report) (err error) {
|
||||
// does not verify or is stale — a refusal, not "not now", so the node hears why.
|
||||
if report.Rekey != nil {
|
||||
if err := e.rekey(ctx, node, *report.Rekey); err != nil {
|
||||
return err
|
||||
return false, err
|
||||
}
|
||||
return e.Inventory.Seen(ctx, node.ID)
|
||||
return false, e.Inventory.Seen(ctx, node.ID)
|
||||
}
|
||||
|
||||
// A bare word that a node is there is not an account of what the machine did or holds: it
|
||||
@@ -334,7 +345,7 @@ func (e Enrolment) Heard(ctx context.Context, report Report) (err error) {
|
||||
if report.Superseded != "" {
|
||||
log.Printf("%s set aside declaration %s for the newer %s", report.Node, report.Declared, report.Superseded)
|
||||
}
|
||||
return e.Inventory.Seen(ctx, node.ID)
|
||||
return false, e.Inventory.Seen(ctx, node.ID)
|
||||
}
|
||||
// What it did is kept whichever way it went. Until this, a refusal or a failure moved
|
||||
// last_seen and the reason went to a log line, so "which machine is not doing what it was
|
||||
@@ -361,17 +372,20 @@ func (e Enrolment) Heard(ctx context.Context, report Report) (err error) {
|
||||
// on top of it (novox/hq ADR 0038). Kept even when the declaration was refused: what the
|
||||
// machine carries is true regardless of what it thought of the last thing it was sent.
|
||||
if err := e.Inventory.RecordCarried(ctx, report.Node, report.Carried); err != nil {
|
||||
return err
|
||||
return false, err
|
||||
}
|
||||
if err := e.Inventory.RecordDoing(ctx, node.ID, doing); err != nil {
|
||||
return err
|
||||
// **Whether this is news** is the store's answer: it holds the previous report, and a machine
|
||||
// that reconciles every minute says the same thing until something changes (novox/hq ADR 0134).
|
||||
news, err = e.Inventory.RecordDoing(ctx, node.ID, doing)
|
||||
if err != nil {
|
||||
return false, err
|
||||
}
|
||||
|
||||
// A refusal, a failure, or a bare word that the node is there — none of them is an account of
|
||||
// what the machine holds, so each moves last_seen and nothing else. Recording a partial list
|
||||
// as though it were the whole would tell a rebuilding node to remove what it still has.
|
||||
if report.Refused != "" || len(report.Failed) > 0 || report.Applied == nil {
|
||||
return e.Inventory.Seen(ctx, node.ID)
|
||||
return news, e.Inventory.Seen(ctx, node.ID)
|
||||
}
|
||||
return e.Inventory.RecordOwned(ctx, node.ID, report.Applied)
|
||||
return news, e.Inventory.RecordOwned(ctx, node.ID, report.Applied)
|
||||
}
|
||||
|
||||
@@ -49,6 +49,39 @@ func eventID() (string, error) {
|
||||
return hex.EncodeToString(raw), nil
|
||||
}
|
||||
|
||||
// MeshControllerSeat is the role the control plane holds, and therefore where its own facts live: a
|
||||
// role's events belong to the role, not to whichever container is holding it today (novox/hq ADR 0121,
|
||||
// ADR 0129). It is what makes them addressable while the control plane itself is being replaced.
|
||||
const MeshControllerSeat = "mesh-controller"
|
||||
|
||||
// The facts the mesh states about its own work (novox/hq ADR 0134).
|
||||
const (
|
||||
// KeyApplied: a machine now runs what it was sent.
|
||||
KeyApplied = "applied"
|
||||
// KeyRefused: a machine did not take what it was sent, and why.
|
||||
KeyRefused = "refused"
|
||||
// KeyBuiltBefore: a build the mesh already held, for a catalogue that asked what it missed. Not
|
||||
// `built` — that is the build machine's, said as it happens, and a replay is neither.
|
||||
KeyBuiltBefore = "built-before"
|
||||
)
|
||||
|
||||
// Applied is what a machine now runs, as the mesh states it.
|
||||
type Applied struct {
|
||||
Node string `json:"node"`
|
||||
Declared string `json:"declared,omitempty"`
|
||||
// Resources is how many the machine applied, not which: the list is the machine's own account
|
||||
// of itself and belongs in the records, not in a fact every listener has to read past.
|
||||
Resources int `json:"resources"`
|
||||
}
|
||||
|
||||
// Refused is a machine that would not take what it was sent.
|
||||
type Refused struct {
|
||||
Node string `json:"node"`
|
||||
Declared string `json:"declared,omitempty"`
|
||||
Refused string `json:"refused,omitempty"`
|
||||
Failed map[string]string `json:"failed,omitempty"`
|
||||
}
|
||||
|
||||
// KeyModuleBuilt is what the builder announces when it has built something. The catalogue places
|
||||
// it in the module graph; nothing else need care.
|
||||
const KeyModuleBuilt = "module.builder.built"
|
||||
@@ -130,6 +163,16 @@ type SourceMoved struct {
|
||||
HTMLURL string `json:"html_url"`
|
||||
// MergedAt is when the forge merged it, RFC 3339. What decides whether this is news.
|
||||
MergedAt string `json:"merged_at"`
|
||||
|
||||
// Paths are the files the merge changed, from the repository's root. Empty means the forge said
|
||||
// nothing about them, and every module built from the repository is treated as affected.
|
||||
Paths []string `json:"paths,omitempty"`
|
||||
|
||||
// PathsTruncated says the merge changed more files than the forge was asked to list, so Paths is
|
||||
// a beginning rather than the whole change — and again, everything is treated as affected. Said
|
||||
// rather than inferred from a round number, because "this is all of it" and "this is as much as
|
||||
// I asked for" are the difference between rebuilding a module and leaving it stale.
|
||||
PathsTruncated bool `json:"paths_truncated,omitempty"`
|
||||
}
|
||||
|
||||
type Upgraded struct {
|
||||
|
||||
@@ -22,7 +22,7 @@ func heardFrom(t *testing.T, report link.Report) (*inventory.Inventory, inventor
|
||||
if _, err := inv.AddNode(ctx, report.Node); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if err := (link.Enrolment{Inventory: inv}).Heard(ctx, report); err != nil {
|
||||
if _, err := (link.Enrolment{Inventory: inv}).Heard(ctx, report); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
doing, said, err := inv.DoingOf(ctx, report.Node)
|
||||
@@ -103,7 +103,7 @@ func TestABareAliveDoesNotWipeTheDeclarationThatSaysANodeIsCurrent(t *testing.T)
|
||||
if err := inv.RecordSent(ctx, node.ID, digest); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if err := (link.Enrolment{Inventory: inv}).Heard(ctx, link.Report{
|
||||
if _, err := (link.Enrolment{Inventory: inv}).Heard(ctx, link.Report{
|
||||
Node: "anchor", Applied: []string{"a", "b"}, Declared: digest, Carried: []int{5432},
|
||||
}); err != nil {
|
||||
t.Fatal(err)
|
||||
@@ -126,7 +126,7 @@ func TestABareAliveDoesNotWipeTheDeclarationThatSaysANodeIsCurrent(t *testing.T)
|
||||
}
|
||||
|
||||
// Now the node says only that it is there, as it does every minute.
|
||||
if err := (link.Enrolment{Inventory: inv}).Heard(ctx, link.Report{Node: "anchor"}); err != nil {
|
||||
if _, err := (link.Enrolment{Inventory: inv}).Heard(ctx, link.Report{Node: "anchor"}); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if !currentOf("anchor") {
|
||||
@@ -162,7 +162,7 @@ func TestAFailureDoesNotBecomeTheAccountOfWhatTheMachineHolds(t *testing.T) {
|
||||
if err := inv.RecordOwned(ctx, node.ID, []string{"one", "two", "three"}); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if err := (link.Enrolment{Inventory: inv}).Heard(ctx, link.Report{
|
||||
if _, err := (link.Enrolment{Inventory: inv}).Heard(ctx, link.Report{
|
||||
Node: "workstation", Applied: []string{"one"}, Failed: map[string]string{"two": "no"},
|
||||
}); err != nil {
|
||||
t.Fatal(err)
|
||||
@@ -200,13 +200,13 @@ func TestWhatAnAdoptedNodeHoldsIsKeptAndAnAliveWordDoesNotWipeIt(t *testing.T) {
|
||||
}
|
||||
check("after the report")
|
||||
|
||||
if err := (link.Enrolment{Inventory: inv}).Heard(ctx, link.Report{Node: "anchor"}); err != nil {
|
||||
if _, err := (link.Enrolment{Inventory: inv}).Heard(ctx, link.Report{Node: "anchor"}); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
check("after an alive word")
|
||||
|
||||
// A reconcile report carrying only adoption is recorded, though it applied nothing.
|
||||
if err := (link.Enrolment{Inventory: inv}).Heard(ctx, link.Report{Node: "anchor",
|
||||
if _, err := (link.Enrolment{Inventory: inv}).Heard(ctx, link.Report{Node: "anchor",
|
||||
Firewall: "ufw"}); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
|
||||
@@ -170,6 +170,20 @@ type Report struct {
|
||||
// Firewall is the firewall found on the machine — "ufw" or "none" — and empty on a node that
|
||||
// was never asked, which is every converged one.
|
||||
Firewall string `json:"firewall,omitempty"`
|
||||
|
||||
// Outward is the links on this machine that face outside it — the ones carrying a default route
|
||||
// (novox/hq ADR 0140). Every node reports it, adopted or converged, because the filter the mesh
|
||||
// composes for it is written around these and nothing else.
|
||||
//
|
||||
// **It replaces a list of addresses.** The filter used to block everything passing through the
|
||||
// machine and then allow the machine's own containers back by naming the ranges they sit on. A
|
||||
// range describes one machine and goes stale in silence; the link carrying the default route is
|
||||
// read afresh on every report and does not change when a module is added or removed.
|
||||
//
|
||||
// Empty means the machine has not said. The mesh composes no filter for such a machine and
|
||||
// leaves the one it has: a rule written around a link with no name is a rule set that does not
|
||||
// load, and that is a machine filtering nothing while its unit reports success.
|
||||
Outward []string `json:"outward,omitempty"`
|
||||
// Reachable is what can be reached on the machine now: every listening socket and every
|
||||
// published container port. Only an adopted node reports it; it is what converging previews.
|
||||
Reachable []Reach `json:"reachable,omitempty"`
|
||||
|
||||
@@ -154,10 +154,47 @@ func (n *natsInbound) deliver(ctx context.Context, act func(context.Context, Con
|
||||
m.seq = meta.Sequence.Stream
|
||||
m.delivered = meta.NumDelivered
|
||||
}
|
||||
// **Work that outlives the acknowledgement window says so while it runs.**
|
||||
//
|
||||
// The bus waits a fixed time to be told a message was taken, and then hands it to whoever
|
||||
// consumes next — which is right for a consumer that died and wrong for one that is busy.
|
||||
// Acting on a merge builds every module the merge changed: minutes of work against a
|
||||
// thirty-second window. So the same merge was handed over again while the first build was
|
||||
// still running, and again after that — on 2026-09-28 one merge ran the mesh's whole
|
||||
// catalogue five times over and exhausted a public registry's pull limit.
|
||||
//
|
||||
// Here rather than in each handler, because the window belongs to the transport and every
|
||||
// handler would otherwise have to remember it. It changes nothing about a handler that
|
||||
// dies: a message is kept alive only while this goroutine is, so a controller that stops
|
||||
// stops saying so, and the bus redelivers exactly as it should.
|
||||
working := make(chan struct{})
|
||||
defer close(working)
|
||||
go stillWorking(msg, working)
|
||||
}
|
||||
act(ctx, m)
|
||||
}
|
||||
|
||||
// heartbeatWhileWorking is how often a handler still running tells the bus so — comfortably inside
|
||||
// the shortest acknowledgement window the mesh gives any of its consumers.
|
||||
const heartbeatWhileWorking = 10 * time.Second
|
||||
|
||||
// stillWorking keeps one message alive until the work on it returns.
|
||||
//
|
||||
// An error is not worth reporting: what the bus does when it is not told is redeliver, which is
|
||||
// exactly what happens if this fails, and the handler's own outcome is the thing worth logging.
|
||||
func stillWorking(msg *nats.Msg, done <-chan struct{}) {
|
||||
tick := time.NewTicker(heartbeatWhileWorking)
|
||||
defer tick.Stop()
|
||||
for {
|
||||
select {
|
||||
case <-done:
|
||||
return
|
||||
case <-tick.C:
|
||||
_ = msg.InProgress()
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// kindOfSubject is how this transport's addressing becomes what the mesh calls a message.
|
||||
//
|
||||
// By subject, which is the only thing the server enforces: a body claiming to be a report does not
|
||||
|
||||
@@ -86,14 +86,15 @@ type counted struct {
|
||||
heard []Report
|
||||
}
|
||||
|
||||
func (c *counted) Heard(_ context.Context, r Report) error {
|
||||
func (c *counted) Heard(_ context.Context, r Report) (bool, error) {
|
||||
c.mu.Lock()
|
||||
defer c.mu.Unlock()
|
||||
if c.err != nil {
|
||||
return c.err
|
||||
return false, c.err
|
||||
}
|
||||
c.heard = append(c.heard, r)
|
||||
return nil
|
||||
// News, so what the mesh states about a report is exercised wherever a report is.
|
||||
return true, nil
|
||||
}
|
||||
|
||||
func (c *counted) refusing(err error) {
|
||||
@@ -207,11 +208,11 @@ type sentAndHeardSafely struct {
|
||||
heard []Report
|
||||
}
|
||||
|
||||
func (s *sentAndHeardSafely) Heard(_ context.Context, r Report) error {
|
||||
func (s *sentAndHeardSafely) Heard(_ context.Context, r Report) (bool, error) {
|
||||
s.mu.Lock()
|
||||
defer s.mu.Unlock()
|
||||
s.heard = append(s.heard, r)
|
||||
return nil
|
||||
return true, nil
|
||||
}
|
||||
|
||||
func (s *sentAndHeardSafely) Outstanding(context.Context, string) (string, error) {
|
||||
@@ -395,3 +396,164 @@ func TestEverySubjectTheControllerFollowsDecodesToAKind(t *testing.T) {
|
||||
t.Error("a subject nobody follows decoded to a kind")
|
||||
}
|
||||
}
|
||||
|
||||
// **A handler slower than the acknowledgement window is not handed its message again.**
|
||||
//
|
||||
// The bus waits a fixed time to be told a message was taken and then redelivers, which is right for
|
||||
// a consumer that died and wrong for one that is busy. Acting on a merge builds modules — minutes
|
||||
// against a thirty-second window — and the same merge was handed over five times while the first
|
||||
// build was still running (2026-09-28). Here the window is two seconds and the work takes six.
|
||||
func TestNatsWorkSlowerThanTheWindowIsNotHandedOverAgain(t *testing.T) {
|
||||
js := aBus(t)
|
||||
// The controller's own consumer, with a window short enough to outlive in a test.
|
||||
if err := js.EnsureConsumer(broker.Consumer{
|
||||
Name: broker.ControllerName, Stream: "CONTROL", Push: true, AckWaitSeconds: 2,
|
||||
Why: "a window short enough to outlive in a test",
|
||||
}); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
var mu sync.Mutex
|
||||
handled := 0
|
||||
slow := make(chan struct{})
|
||||
s, stop := servingOn(t, js, nil)
|
||||
defer stop()
|
||||
s.listener = slowly{func() {
|
||||
mu.Lock()
|
||||
handled++
|
||||
first := handled == 1
|
||||
mu.Unlock()
|
||||
if first {
|
||||
time.Sleep(6 * time.Second)
|
||||
close(slow)
|
||||
}
|
||||
}}
|
||||
|
||||
body, err := json.Marshal(Report{Node: "anchor", Declared: "d1", Applied: []string{"store"}})
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if _, err := js.Context().Publish(ReportSubject("anchor"), body); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
select {
|
||||
case <-slow:
|
||||
case <-time.After(30 * time.Second):
|
||||
t.Fatal("the slow work never finished")
|
||||
}
|
||||
// A moment for a redelivery to arrive, if the bus were going to send one.
|
||||
time.Sleep(3 * time.Second)
|
||||
mu.Lock()
|
||||
defer mu.Unlock()
|
||||
if handled != 1 {
|
||||
t.Fatalf("one report was handled %d times, so slow work is run again while it is running", handled)
|
||||
}
|
||||
}
|
||||
|
||||
// slowly is a listener that runs whatever it was given.
|
||||
type slowly struct{ work func() }
|
||||
|
||||
func (s slowly) Heard(context.Context, Report) (bool, error) { s.work(); return true, nil }
|
||||
|
||||
// **The mesh says what it applied** (novox/hq ADR 0134), under the seat the control plane holds — and
|
||||
// says nothing when a report is the same state said again, which is what a machine reconciling every
|
||||
// minute sends.
|
||||
func TestNatsTheMeshSaysWhatAMachineApplied(t *testing.T) {
|
||||
js := aBus(t)
|
||||
heard := make(chan *nats.Msg, 4)
|
||||
sub, err := js.Conn().Subscribe(SeatEventSubject(MeshControllerSeat, ">"), func(m *nats.Msg) {
|
||||
heard <- m
|
||||
})
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
defer sub.Unsubscribe() //nolint:errcheck // the subscription dies with the connection
|
||||
|
||||
_, stop := servingOn(t, js, &counted{})
|
||||
defer stop()
|
||||
|
||||
// A report that changed something: the store says it was news.
|
||||
body, err := json.Marshal(Report{Node: "anchor", Declared: "d1", Applied: []string{"store", "broker"}})
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if _, err := js.Context().Publish(ReportSubject("anchor"), body); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
select {
|
||||
case m := <-heard:
|
||||
if m.Subject != SeatEventSubject(MeshControllerSeat, KeyApplied) {
|
||||
t.Fatalf("the mesh stated %q", m.Subject)
|
||||
}
|
||||
var said Applied
|
||||
if err := json.Unmarshal(m.Data, &said); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if said.Node != "anchor" || said.Declared != "d1" || said.Resources != 2 {
|
||||
t.Fatalf("it said %+v", said)
|
||||
}
|
||||
case <-time.After(10 * time.Second):
|
||||
t.Fatal("the mesh said nothing about a machine that now runs something else")
|
||||
}
|
||||
|
||||
// A refusal is its own fact, with the reason in it rather than only in a log.
|
||||
refusal, err := json.Marshal(Report{Node: "anchor", Declared: "d2",
|
||||
Failed: map[string]string{"gitea.server": "no such image"}})
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if _, err := js.Context().Publish(ReportSubject("anchor"), refusal); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
select {
|
||||
case m := <-heard:
|
||||
if m.Subject != SeatEventSubject(MeshControllerSeat, KeyRefused) {
|
||||
t.Fatalf("a refusal was stated as %q", m.Subject)
|
||||
}
|
||||
var said Refused
|
||||
if err := json.Unmarshal(m.Data, &said); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if said.Failed["gitea.server"] == "" {
|
||||
t.Fatalf("the refusal does not say which resource or why: %+v", said)
|
||||
}
|
||||
case <-time.After(10 * time.Second):
|
||||
t.Fatal("the mesh said nothing about a machine that refused what it was sent")
|
||||
}
|
||||
}
|
||||
|
||||
// And a report that is not news is not a fact. A machine reconciles every minute; a fact per report
|
||||
// would be a fact per minute per machine, which is a stream nobody reads.
|
||||
func TestNatsAReportThatIsNotNewsIsNotStated(t *testing.T) {
|
||||
js := aBus(t)
|
||||
heard := make(chan *nats.Msg, 4)
|
||||
sub, err := js.Conn().Subscribe(SeatEventSubject(MeshControllerSeat, ">"), func(m *nats.Msg) {
|
||||
heard <- m
|
||||
})
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
defer sub.Unsubscribe() //nolint:errcheck // the subscription dies with the connection
|
||||
|
||||
// A store that records the report and says it was nothing new — which is what the mesh's own
|
||||
// store says about a machine repeating itself.
|
||||
_, stop := servingOn(t, js, sameAgain{})
|
||||
defer stop()
|
||||
|
||||
body, err := json.Marshal(Report{Node: "anchor", Declared: "d1", Applied: []string{"store"}})
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if _, err := js.Context().Publish(ReportSubject("anchor"), body); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
select {
|
||||
case m := <-heard:
|
||||
t.Fatalf("the mesh stated %q about a machine that changed nothing", m.Subject)
|
||||
case <-time.After(3 * time.Second):
|
||||
}
|
||||
}
|
||||
|
||||
// sameAgain records a report and says it was the same state said again.
|
||||
type sameAgain struct{}
|
||||
|
||||
func (sameAgain) Heard(context.Context, Report) (bool, error) { return false, nil }
|
||||
|
||||
@@ -60,7 +60,7 @@ func TestASignedRekeyMovesTheHubOntoItsTunnel(t *testing.T) {
|
||||
rekey := &link.Rekey{Previous: ownKey, OverlayKey: tunnelKey, Tunnel: theTunnel()}
|
||||
rekey.Proof = ed25519.Sign(private, link.RekeyProof("anchor", ownKey, tunnelKey, theTunnel()))
|
||||
|
||||
if err := e.Heard(ctx, link.Report{Node: "anchor", Rekey: rekey}); err != nil {
|
||||
if _, err := e.Heard(ctx, link.Report{Node: "anchor", Rekey: rekey}); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
placed, err := e.Inventory.Overlays(ctx)
|
||||
@@ -77,7 +77,7 @@ func TestASignedRekeyMovesTheHubOntoItsTunnel(t *testing.T) {
|
||||
_ = hub
|
||||
|
||||
// Replayed, it is stale: the previous key it names is no longer the node's.
|
||||
err = e.Heard(ctx, link.Report{Node: "anchor", Rekey: rekey})
|
||||
_, err = e.Heard(ctx, link.Report{Node: "anchor", Rekey: rekey})
|
||||
if err == nil || !strings.Contains(err.Error(), "previous overlay key") {
|
||||
t.Fatalf("a replayed rekey was accepted: %v", err)
|
||||
}
|
||||
@@ -93,7 +93,7 @@ func TestARekeySignedByAnotherKeyIsRefusedAndChangesNothing(t *testing.T) {
|
||||
rekey := &link.Rekey{Previous: ownKey, OverlayKey: tunnelKey, Tunnel: theTunnel()}
|
||||
rekey.Proof = ed25519.Sign(stranger, link.RekeyProof("anchor", ownKey, tunnelKey, theTunnel()))
|
||||
|
||||
err = e.Heard(ctx, link.Report{Node: "anchor", Rekey: rekey})
|
||||
_, err = e.Heard(ctx, link.Report{Node: "anchor", Rekey: rekey})
|
||||
if err == nil || !strings.Contains(err.Error(), "not signed by anchor's identity key") {
|
||||
t.Fatalf("a rekey signed by a stranger was accepted: %v", err)
|
||||
}
|
||||
@@ -111,7 +111,7 @@ func TestARekeySignedByAnotherKeyIsRefusedAndChangesNothing(t *testing.T) {
|
||||
other := theTunnel()
|
||||
other.Port = 51820
|
||||
moved.Proof = ed25519.Sign(mustPrivate(t, e, "anchor"), link.RekeyProof("anchor", ownKey, tunnelKey, other))
|
||||
if err := e.Heard(ctx, link.Report{Node: "anchor", Rekey: moved}); err == nil {
|
||||
if _, err := e.Heard(ctx, link.Report{Node: "anchor", Rekey: moved}); err == nil {
|
||||
t.Fatal("a proof over another tunnel was accepted")
|
||||
}
|
||||
}
|
||||
|
||||
@@ -9,12 +9,12 @@ import (
|
||||
|
||||
type heardWith struct{ err error }
|
||||
|
||||
func (h heardWith) Heard(context.Context, Report) error { return h.err }
|
||||
func (h heardWith) Heard(context.Context, Report) (bool, error) { return h.err == nil, h.err }
|
||||
|
||||
// switchable answers with whatever it is set to — the store away, then back.
|
||||
type switchable struct{ err error }
|
||||
|
||||
func (h *switchable) Heard(context.Context, Report) error { return h.err }
|
||||
func (h *switchable) Heard(context.Context, Report) (bool, error) { return h.err == nil, h.err }
|
||||
|
||||
func aReport(node, declared string) Report {
|
||||
return Report{Node: node, Declared: declared, Applied: []string{"store"}}
|
||||
|
||||
+64
-5
@@ -29,7 +29,12 @@ type Enroller interface {
|
||||
// Listener is what the controller does with a report. Separate from Enroller so the two can be
|
||||
// given independently, and so a server that only sends declarations needs neither.
|
||||
type Listener interface {
|
||||
Heard(ctx context.Context, report Report) error
|
||||
// Heard records what a node said, and says whether it was **news** — a machine that now runs
|
||||
// something else, or refuses something it did not refuse before. A machine reconciles
|
||||
// continuously and reports each time, so what is news is the store's answer rather than the
|
||||
// bus's: only this side has the previous report to compare with. What the mesh states about it
|
||||
// is the server's (novox/hq ADR 0134).
|
||||
Heard(ctx context.Context, report Report) (news bool, err error)
|
||||
}
|
||||
|
||||
// Recorder keeps what builders say.
|
||||
@@ -257,7 +262,7 @@ func (s *Server) heartbeat(m Control) {
|
||||
return
|
||||
}
|
||||
if s.listener != nil {
|
||||
if err := s.listener.Heard(context.Background(), Report{Node: alive.Node}); err != nil {
|
||||
if _, err := s.listener.Heard(context.Background(), Report{Node: alive.Node}); err != nil {
|
||||
s.log.Printf("could not record that %s is here: %v", alive.Node, err)
|
||||
}
|
||||
}
|
||||
@@ -291,7 +296,7 @@ func (s *Server) reported(ctx context.Context, m Control) {
|
||||
return
|
||||
}
|
||||
|
||||
err := s.listener.Heard(context.Background(), report)
|
||||
news, err := s.listener.Heard(context.Background(), report)
|
||||
switch s.decide(ctx, m, what, declaredIn, outstanding, err) {
|
||||
case Hold:
|
||||
// Held, not settled, while the store cannot take it: the node reports an apply once,
|
||||
@@ -307,6 +312,13 @@ func (s *Server) reported(ctx context.Context, m Control) {
|
||||
// node whose recovery copy is silently older than it looks.
|
||||
s.log.Printf("could not record %s's report: %v", report.Node, err)
|
||||
}
|
||||
// **And the mesh says what it did** (novox/hq ADR 0134). Only when the report was news: a
|
||||
// machine reports every convergence, and a fact per report would be a fact per minute per
|
||||
// machine saying nothing. Stated after it is recorded, so nothing is announced that the
|
||||
// mesh does not hold.
|
||||
if err == nil && news {
|
||||
s.saysWhatItDid(ctx, report)
|
||||
}
|
||||
}
|
||||
|
||||
switch {
|
||||
@@ -334,7 +346,8 @@ func (s *Server) reported(ctx context.Context, m Control) {
|
||||
// whenever it arrives, which is the behaviour the mesh has had all along.
|
||||
func staleAgainst(report Report) string {
|
||||
if report.Rekey != nil || report.Tunnel != nil || len(report.Held) > 0 ||
|
||||
report.Firewall != "" || len(report.Reachable) > 0 || len(report.Carried) > 0 {
|
||||
report.Firewall != "" || len(report.Reachable) > 0 || len(report.Carried) > 0 ||
|
||||
len(report.Outward) > 0 {
|
||||
return ""
|
||||
}
|
||||
return report.Declared
|
||||
@@ -460,7 +473,19 @@ func (s *Server) catchingUp(ctx context.Context, m Control) {
|
||||
sent := 0
|
||||
for _, a := range announcements {
|
||||
a.Replay = true
|
||||
if err := EmitEvent(ctx, s.bus, KeyModuleBuilt, "control-plane", "", a); err != nil {
|
||||
// Under the control plane's own seat (novox/hq ADR 0134). It used to be published as a
|
||||
// module's event from a module called "control-plane", which does not exist — so the
|
||||
// controller's own account refused it, every catalogue that asked what it missed was
|
||||
// answered with nothing, and its graph kept the gap (found 2026-09-28).
|
||||
body, err := json.Marshal(a)
|
||||
if err != nil {
|
||||
// A body that cannot be written is this program's fault, not the bus's, and publishing
|
||||
// an empty one would put a fact on the mesh that says nothing.
|
||||
s.log.Printf("cannot re-announce %s at %s: %v", a.Module, short(a.Commit), err)
|
||||
_ = m.Took()
|
||||
return
|
||||
}
|
||||
if err := s.bus.PublishSeatEvent(ctx, MeshControllerSeat, KeyBuiltBefore, body); err != nil {
|
||||
// Said and abandoned rather than retried: the catalogue asks again every time it
|
||||
// starts, and half a graph delivered twice is no better than half delivered once.
|
||||
s.log.Printf("replaying %s at %s failed, and the rest is abandoned: %v",
|
||||
@@ -551,3 +576,37 @@ func (s *Server) sourceMoved(ctx context.Context, m Control) {
|
||||
}
|
||||
_ = m.Took()
|
||||
}
|
||||
|
||||
// saysWhatItDid states what a machine now runs, or what it would not take, as a fact on the bus
|
||||
// (novox/hq ADR 0134).
|
||||
//
|
||||
// **The control plane speaks, as the holder of its seat.** A node's report is control traffic only
|
||||
// this process may read, so the chain from a merge to a machine went dark exactly where it touched
|
||||
// one: nothing said which version a machine runs, or that it refused to. The facts are second-hand
|
||||
// on purpose — one emitter, one ordering — and a machine that cannot reach the bus produces none, so
|
||||
// absence is not health.
|
||||
//
|
||||
// A failure to state a fact is logged and nothing else: the report is recorded, which is the part
|
||||
// that must not be lost, and the next change says the same thing again.
|
||||
func (s *Server) saysWhatItDid(ctx context.Context, report Report) {
|
||||
if s.bus == nil {
|
||||
return
|
||||
}
|
||||
event, body := KeyApplied, any(Applied{
|
||||
Node: report.Node, Declared: report.Declared, Resources: len(report.Applied),
|
||||
})
|
||||
if report.Refused != "" || len(report.Failed) > 0 {
|
||||
event, body = KeyRefused, Refused{
|
||||
Node: report.Node, Declared: report.Declared,
|
||||
Refused: report.Refused, Failed: report.Failed,
|
||||
}
|
||||
}
|
||||
raw, err := json.Marshal(body)
|
||||
if err != nil {
|
||||
s.log.Printf("could not say what %s did: %v", report.Node, err)
|
||||
return
|
||||
}
|
||||
if err := s.bus.PublishSeatEvent(ctx, MeshControllerSeat, event, raw); err != nil {
|
||||
s.log.Printf("could not say that %s %s: %v", report.Node, event, err)
|
||||
}
|
||||
}
|
||||
|
||||
@@ -23,12 +23,12 @@ type sentAndHeard struct {
|
||||
err error
|
||||
}
|
||||
|
||||
func (s *sentAndHeard) Heard(_ context.Context, r Report) error {
|
||||
func (s *sentAndHeard) Heard(_ context.Context, r Report) (bool, error) {
|
||||
if s.err != nil {
|
||||
return s.err
|
||||
return false, s.err
|
||||
}
|
||||
s.heard = append(s.heard, r)
|
||||
return nil
|
||||
return true, nil
|
||||
}
|
||||
|
||||
func (s *sentAndHeard) Outstanding(context.Context, string) (string, error) { return s.sent, nil }
|
||||
|
||||
@@ -27,6 +27,7 @@
|
||||
"bus": "/var/lib/mesh/mesh-controller/bus"
|
||||
},
|
||||
"secrets-owner": "65534:65534",
|
||||
"prepares": true,
|
||||
"resources": [
|
||||
{
|
||||
"id": "mesh-state",
|
||||
|
||||
Reference in New Issue
Block a user