Compare commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
fb9c9c3ee8 | ||
|
|
d53e626366 | ||
|
|
83b3d20e68 | ||
|
|
e030aa2387 | ||
|
|
c670bef4e1 | ||
|
|
45529bfec2 | ||
|
|
b1e9ccff6d | ||
|
|
cbcf0bcc93 | ||
|
|
6910f07d75 | ||
|
|
88037b33b7 | ||
|
|
422ad516d5 | ||
|
|
8431ecfb48 | ||
|
|
f107d68b2d | ||
|
|
1028193c8a | ||
|
|
f576287b51 | ||
|
|
6c6495f6d9 | ||
|
|
e6d48cf537 | ||
|
|
b8a766f234 | ||
|
|
9caea5bc32 | ||
|
|
df27cee7b7 | ||
|
|
d275e64ed3 | ||
|
|
1a628a4d22 | ||
|
|
b5196e974c | ||
|
|
5162c3b05f | ||
|
|
98fe8edf35 | ||
|
|
cbf50185d0 | ||
|
|
197258c88c | ||
|
|
a3b810f1f0 | ||
|
|
971a6d6d03 | ||
|
|
04a27caa43 | ||
|
|
6e90c2692d | ||
|
|
ced54d489f |
+166
-26
@@ -51,6 +51,43 @@ var builtFor = ""
|
|||||||
|
|
||||||
var version = "development build"
|
var version = "development build"
|
||||||
|
|
||||||
|
// runningVersion is this host's version: the directory it was delivered into, or the link-time stamp
|
||||||
|
// for one placed by hand.
|
||||||
|
//
|
||||||
|
// **From where it sits, not from its linker** (novox/hq ADR 0142): "It is unpacked into a directory
|
||||||
|
// named for its version, so it can read its own version from its path. The stamp goes, and with it the
|
||||||
|
// need for a build to know what it will be called."
|
||||||
|
//
|
||||||
|
// The mesh's toolchain does not stamp a version, on purpose — a build does not know what it will be
|
||||||
|
// called — so a delivered host read as "development build" and the mesh could not tell which host any
|
||||||
|
// machine ran (novox/hq 04-ISSUES/161, and 087 for why that matters). The path knows: a delivered host
|
||||||
|
// lives at `<libexec>/versions/<version>/<binary>`.
|
||||||
|
//
|
||||||
|
// A host placed by hand keeps its stamp, which is the honest answer for one the mesh did not deliver.
|
||||||
|
func runningVersion() string {
|
||||||
|
self, err := os.Executable()
|
||||||
|
if err != nil {
|
||||||
|
return version
|
||||||
|
}
|
||||||
|
return versionAt(self, version)
|
||||||
|
}
|
||||||
|
|
||||||
|
// versionAt is runningVersion's decision, with the executable's path and the link-time stamp given —
|
||||||
|
// so a test can ask it about a path without being that binary.
|
||||||
|
func versionAt(self, stamped string) string {
|
||||||
|
// .../versions/<version>/<binary> — the parent is the version, and its parent is the versions
|
||||||
|
// directory. Checked rather than assumed, so a binary somewhere else does not read a directory
|
||||||
|
// name as a version.
|
||||||
|
dir := filepath.Dir(self)
|
||||||
|
if filepath.Base(filepath.Dir(dir)) != upgrade.VersionsDirName {
|
||||||
|
return stamped
|
||||||
|
}
|
||||||
|
if name := filepath.Base(dir); name != "" && name != "." && name != string(filepath.Separator) {
|
||||||
|
return name
|
||||||
|
}
|
||||||
|
return stamped
|
||||||
|
}
|
||||||
|
|
||||||
const usage = `mesh-host — the node host
|
const usage = `mesh-host — the node host
|
||||||
|
|
||||||
profile what this machine can be asked to do
|
profile what this machine can be asked to do
|
||||||
@@ -254,7 +291,7 @@ func run(ctx context.Context, command string, opts options) error {
|
|||||||
return runLink(ctx, opts)
|
return runLink(ctx, opts)
|
||||||
|
|
||||||
case "version":
|
case "version":
|
||||||
fmt.Println(version)
|
fmt.Println(runningVersion())
|
||||||
return nil
|
return nil
|
||||||
|
|
||||||
case "", "help", "-h", "--help":
|
case "", "help", "-h", "--help":
|
||||||
@@ -420,10 +457,10 @@ func short(digest string) string {
|
|||||||
// them again — and everything the mesh declared read as no longer declared and removed. Even the
|
// them again — and everything the mesh declared read as no longer declared and removed. Even the
|
||||||
// very declaration the mesh last sent, applied from a file, would plan to remove the foundation.
|
// very declaration the mesh last sent, applied from a file, would plan to remove the foundation.
|
||||||
// `apply FILE` is for a machine the mesh has not spoken to, and is refused saying so.
|
// `apply FILE` is for a machine the mesh has not spoken to, and is refused saying so.
|
||||||
func refuseStale(known store.State, kept store.Declared, keptErr error, digest string, from provenance) error {
|
func refuseStale(known store.State, kept store.Declared, keptErr error, digest string, from provenance, sequence int64) error {
|
||||||
switch from {
|
switch from {
|
||||||
case fromDeclared:
|
case fromDeclared:
|
||||||
return nil
|
return refuseOlder(kept, keptErr, sequence)
|
||||||
case fromBundle:
|
case fromBundle:
|
||||||
if known.Genesis == nil || known.Genesis.Digest == digest {
|
if known.Genesis == nil || known.Genesis.Digest == digest {
|
||||||
return nil
|
return nil
|
||||||
@@ -520,7 +557,7 @@ func runApply(ctx context.Context, opts options, d *declaration.Declaration, raw
|
|||||||
if err := apply.CheckMode(known, d); err != nil {
|
if err := apply.CheckMode(known, d); err != nil {
|
||||||
return err
|
return err
|
||||||
}
|
}
|
||||||
if err := refuseStale(known, kept, keptErr, digest, from); err != nil {
|
if err := refuseStale(known, kept, keptErr, digest, from, d.Sequence); err != nil {
|
||||||
return err
|
return err
|
||||||
}
|
}
|
||||||
|
|
||||||
@@ -594,8 +631,8 @@ func runApply(ctx context.Context, opts options, d *declaration.Declaration, raw
|
|||||||
//
|
//
|
||||||
// A failure to record is reported and does not fail the apply. The apply worked; what is
|
// A failure to record is reported and does not fail the apply. The apply worked; what is
|
||||||
// lost is a rollback's ability to come back here, which is worse to hide than to say.
|
// lost is a rollback's ability to come back here, which is worse to hide than to say.
|
||||||
if version != "" {
|
if v := runningVersion(); v != "" {
|
||||||
if err := upgrade.RecordKnownGood(upgrade.KnownGoodPath(opts.state), version); err != nil {
|
if err := upgrade.RecordKnownGood(upgrade.KnownGoodPath(opts.state), v); err != nil {
|
||||||
fmt.Fprintf(os.Stderr,
|
fmt.Fprintf(os.Stderr,
|
||||||
"mesh-host: applied, but could not record %s as known-good: %v\n"+
|
"mesh-host: applied, but could not record %s as known-good: %v\n"+
|
||||||
" a rollback would have nothing to return to.\n", version, err)
|
" a rollback would have nothing to return to.\n", version, err)
|
||||||
@@ -706,15 +743,18 @@ func enrol(ctx context.Context, opts options) error {
|
|||||||
fmt.Printf(" signing key %s\n",
|
fmt.Printf(" signing key %s\n",
|
||||||
base64.StdEncoding.EncodeToString(token.Signer)[:16]+"...")
|
base64.StdEncoding.EncodeToString(token.Signer)[:16]+"...")
|
||||||
|
|
||||||
// The check that has to happen before this machine says anything.
|
// **The pin is checked by the connection that presents this token, not by a dial of our own**
|
||||||
conn, err := link.Dial(token.Broker, token.Fingerprint, opts.timeout)
|
// (novox/hq 04-ISSUES/146). This opened a raw TLS connection to the bus first, which worked
|
||||||
if err != nil {
|
// against the broker the mesh used to run and cannot work against the one it runs now: NATS
|
||||||
return err
|
// speaks its own protocol before it upgrades to TLS, so an immediate handshake is answered
|
||||||
}
|
// with a plaintext line and the enrolment failed with "first record does not look like a TLS
|
||||||
defer conn.Close()
|
// handshake" — on every node that has tried to join since the bus changed, which is why this
|
||||||
fmt.Println("\nthe broker presented the certificate this token pins")
|
// went unnoticed: none had.
|
||||||
|
//
|
||||||
conn.Close()
|
// What ADR 0004 requires still holds, and holds better: the client that presents the token
|
||||||
|
// carries the same pinned configuration, reads the server's greeting, upgrades, and the
|
||||||
|
// verification runs inside that handshake — so the one-time secret is sent only after the
|
||||||
|
// certificate has been checked, and nothing of this node's reaches an impostor.
|
||||||
|
|
||||||
mine, err := identity.Generate(*name)
|
mine, err := identity.Generate(*name)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
@@ -778,20 +818,23 @@ func enrol(ctx context.Context, opts options) error {
|
|||||||
// control plane cannot decide what a node should run without it, so it travels with the
|
// control plane cannot decide what a node should run without it, so it travels with the
|
||||||
// request instead of being asked for in a second round trip.
|
// request instead of being asked for in a second round trip.
|
||||||
detected := profile.Detect(ctx, profile.Default(nil), opts.timeout)
|
detected := profile.Detect(ctx, profile.Default(nil), opts.timeout)
|
||||||
reported := map[string]any{}
|
reported := profileAsReported(detected)
|
||||||
if raw, err := json.Marshal(detected); err == nil {
|
|
||||||
_ = json.Unmarshal(raw, &reported)
|
|
||||||
}
|
|
||||||
|
|
||||||
// Signed with the identity just generated, so the mesh can tell this machine from anyone else
|
// Signed with the identity just generated, so the mesh can tell this machine from anyone else
|
||||||
// who knows its public key (novox/hq issue 083).
|
// who knows its public key (novox/hq issue 083).
|
||||||
proof := mine.Sign(link.EnrolProof(token.Secret, mine.Public, mine.Overlay.Public,
|
proof := mine.Sign(link.EnrolProof(token.Secret, mine.Public, mine.Overlay.Public,
|
||||||
sealing.Public, serving.Public))
|
sealing.Public, serving.Public))
|
||||||
// The token says where to go and which certificate that address must present. It says nothing
|
// The token says where to go and which certificate that address must present. It says nothing
|
||||||
// about which bus is there, and does not need to: every token names the one the mesh runs on
|
// about which bus is there, and does not need to: there is one, and this host knows which
|
||||||
// today until the rollout (novox/hq ADR 0116 step 5), and that is what an empty Transport is.
|
// (novox/hq ADR 0131 — the mesh speaks to one seat and the old transport is gone).
|
||||||
|
//
|
||||||
|
// **It used to leave this empty** and mean "whatever the mesh runs today", which was true
|
||||||
|
// while two buses existed and became a refusal the moment one did: an empty transport is not
|
||||||
|
// the bus's name, so every enrolment ended at "this token is for the \"\" bus"
|
||||||
|
// (novox/hq 04-ISSUES/146). Nothing caught it because nothing had enrolled since the bus
|
||||||
|
// changed.
|
||||||
reply, err := link.Enrol(ctx,
|
reply, err := link.Enrol(ctx,
|
||||||
link.Approach{Address: token.Broker, Fingerprint: token.Fingerprint},
|
link.Approach{Address: token.Broker, Fingerprint: token.Fingerprint, Transport: link.OnNATS},
|
||||||
*name, token.Secret,
|
*name, token.Secret,
|
||||||
mine.Public, mine.Overlay.Public, sealing.Public, serving.Public, reported, proof, found,
|
mine.Public, mine.Overlay.Public, sealing.Public, serving.Public, reported, proof, found,
|
||||||
opts.timeout)
|
opts.timeout)
|
||||||
@@ -807,6 +850,13 @@ func enrol(ctx context.Context, opts options) error {
|
|||||||
Fingerprint: firstNonEmpty(reply.Fingerprint, token.Fingerprint),
|
Fingerprint: firstNonEmpty(reply.Fingerprint, token.Fingerprint),
|
||||||
Signer: firstNonEmpty2(reply.Signer, token.Signer),
|
Signer: firstNonEmpty2(reply.Signer, token.Signer),
|
||||||
Password: reply.Password,
|
Password: reply.Password,
|
||||||
|
// **Which bus this membership is for, said rather than left empty** (novox/hq
|
||||||
|
// 04-ISSUES/146). The link refuses a membership that names another bus, and an empty name
|
||||||
|
// is not this one's — so a node enrolled without it came up and reconnected for ever
|
||||||
|
// against its own record: "this membership is for \"\", and the mesh's bus is nats". The
|
||||||
|
// reply does not carry it because there is one bus and the host knows which (ADR 0131);
|
||||||
|
// what was missing was writing that down where the link reads it.
|
||||||
|
Transport: link.OnNATS,
|
||||||
}
|
}
|
||||||
if mine.Membership.Password == "" {
|
if mine.Membership.Password == "" {
|
||||||
// The mesh did not replace the token's secret, so it is still this node's broker
|
// The mesh did not replace the token's secret, so it is still this node's broker
|
||||||
@@ -1008,7 +1058,12 @@ func runLink(ctx context.Context, opts options) error {
|
|||||||
// standing before this machine leaves the one it is on (novox/hq design 28, task 5.2).
|
// standing before this machine leaves the one it is on (novox/hq design 28, task 5.2).
|
||||||
adoptDeliveredMembership(identity.Path(opts.state), &mine, say)
|
adoptDeliveredMembership(identity.Path(opts.state), &mine, say)
|
||||||
|
|
||||||
switch next, waiting, err := upgrade.Successor(upgrade.VersionsDir(""), version); {
|
// Asked with the version this host is RUNNING, read from where it sits — not the link-time
|
||||||
|
// stamp, which every delivered host carries as "development build". Asked with the stamp,
|
||||||
|
// a delivered host never matched the newest delivered version, so it stood aside on every
|
||||||
|
// push for ever, and standing aside cancels the report, so the mesh never heard from it
|
||||||
|
// again (novox/hq 04-ISSUES/163).
|
||||||
|
switch next, waiting, err := upgrade.Successor(upgrade.VersionsDir(""), runningVersion()); {
|
||||||
case err != nil:
|
case err != nil:
|
||||||
// Said, not fatal. A host that cannot read the delivered versions is still running this
|
// Said, not fatal. A host that cannot read the delivered versions is still running this
|
||||||
// machine correctly; what it has lost is the ability to be replaced.
|
// machine correctly; what it has lost is the ability to be replaced.
|
||||||
@@ -1246,6 +1301,21 @@ func applyDeclared(ctx context.Context, opts options, raw []byte, sched *apply.S
|
|||||||
return applyAndKeep(ctx, opts, raw, nil, sched, say)
|
return applyAndKeep(ctx, opts, raw, nil, sched, say)
|
||||||
}
|
}
|
||||||
|
|
||||||
|
// announceOr is what the apply writes its detail with, given what the caller has to say things with.
|
||||||
|
//
|
||||||
|
// **Never nil.** This argument was nil on the serving path, and nil is silence: everything the apply
|
||||||
|
// says — a file held, a container replaced, the found firewall retired — was visible when a person ran
|
||||||
|
// the one-shot command and discarded in the way the host actually runs (novox/hq 04-ISSUES/143).
|
||||||
|
//
|
||||||
|
// Named rather than written inline at the call site so both paths reach the apply the same way, and so
|
||||||
|
// a reader asking "where does the apply's output go" finds one answer.
|
||||||
|
func announceOr(say link.Announce) func(string) {
|
||||||
|
if say == nil {
|
||||||
|
return func(string) {}
|
||||||
|
}
|
||||||
|
return say
|
||||||
|
}
|
||||||
|
|
||||||
// applying serialises applies within this process.
|
// applying serialises applies within this process.
|
||||||
//
|
//
|
||||||
// **Two things apply here: the link and the reconcile loop**, and each reads the node's state,
|
// **Two things apply here: the link and the reconcile loop**, and each reads the node's state,
|
||||||
@@ -1308,8 +1378,18 @@ func applyAndKeep(ctx context.Context, opts options, raw []byte, signed *store.D
|
|||||||
|
|
||||||
// Declared, not carried. A declaration from the mesh removes only what the mesh previously
|
// Declared, not carried. A declaration from the mesh removes only what the mesh previously
|
||||||
// declared — never what this machine raised for itself from its bundle (04-ISSUES/010).
|
// declared — never what this machine raised for itself from its bundle (04-ISSUES/010).
|
||||||
|
// **What the apply says goes to the console, which is the journal when this runs as a service.**
|
||||||
|
//
|
||||||
|
// It was nil, and nil is silence. The one-shot path has always passed a real one, so every detail
|
||||||
|
// the apply produces — a file held, a container replaced, the found firewall retired — was visible
|
||||||
|
// when a person ran it by hand and discarded in the way the host actually runs. Measured: after a
|
||||||
|
// machine was converged and its found firewall was not retired, what the host decided was
|
||||||
|
// unrecoverable, because it had said it to nobody (novox/hq 04-ISSUES/143).
|
||||||
|
//
|
||||||
|
// `say` already reaches stdout, and the launcher's unit sends that to the journal, so this needs
|
||||||
|
// no new mechanism — only for the argument to be passed.
|
||||||
outcome, updated, applyErr := apply.ApplyKeeping(ctx, built, declared, known, store.OriginDeclared,
|
outcome, updated, applyErr := apply.ApplyKeeping(ctx, built, declared, known, store.OriginDeclared,
|
||||||
apply.ExecRunner, nil, sealOpener(opts.state), apply.KeepIn(filepath.Dir(opts.state)))
|
apply.ExecRunner, announceOr(say), sealOpener(opts.state), apply.KeepIn(filepath.Dir(opts.state)))
|
||||||
|
|
||||||
// The mode the mesh said, recorded whichever way the apply went: the declaration is kept
|
// The mode the mesh said, recorded whichever way the apply went: the declaration is kept
|
||||||
// either way, and the node is held to it from the next reconcile (novox/hq ADR 0100).
|
// either way, and the node is held to it from the next reconcile (novox/hq ADR 0100).
|
||||||
@@ -1335,7 +1415,8 @@ func applyAndKeep(ctx context.Context, opts options, raw []byte, signed *store.D
|
|||||||
sched.Sync(declared, held)
|
sched.Sync(declared, held)
|
||||||
}
|
}
|
||||||
|
|
||||||
report := link.Report{Carried: carriedPorts(updated), Declared: digestOf(raw), Host: version}
|
report := link.Report{Carried: carriedPorts(updated), Declared: digestOf(raw), Host: runningVersion(),
|
||||||
|
Profile: profileAsReported(profile.Detect(ctx, profile.Default(nil), opts.timeout))}
|
||||||
// Which of this machine's links face outside, for the filter the mesh writes around them
|
// Which of this machine's links face outside, for the filter the mesh writes around them
|
||||||
// (novox/hq ADR 0140). Reported whatever the node's mode: a converged node's filter needs it,
|
// (novox/hq ADR 0140). Reported whatever the node's mode: a converged node's filter needs it,
|
||||||
// and an adopted one becomes converged without a further round trip. A machine that cannot read
|
// and an adopted one becomes converged without a further round trip. A machine that cannot read
|
||||||
@@ -1349,7 +1430,15 @@ func applyAndKeep(ctx context.Context, opts options, raw []byte, signed *store.D
|
|||||||
// node never reads as converged (novox/hq ADR 0100).
|
// node never reads as converged (novox/hq ADR 0100).
|
||||||
for _, h := range updated.Held {
|
for _, h := range updated.Held {
|
||||||
report.Held = append(report.Held, link.Held{ID: h.ID, Module: h.Module, Kind: h.Kind,
|
report.Held = append(report.Held, link.Held{ID: h.ID, Module: h.Module, Kind: h.Kind,
|
||||||
Target: h.Target, Since: h.Since, Changed: h.Changed, Kept: h.Kept})
|
Target: h.Target, Since: h.Since, Changed: h.Changed, Kept: h.Kept, Facts: factsAsReported(h.Facts)})
|
||||||
|
}
|
||||||
|
// And what runs here that nobody asked for (novox/hq ADR 0163).
|
||||||
|
if strays, err := apply.Strays(ctx, apply.ExecRunner, updated); err != nil {
|
||||||
|
fmt.Fprintf(os.Stderr, "mesh-host: applied, and could not list what else runs here: %v\n", err)
|
||||||
|
} else {
|
||||||
|
for _, s := range strays {
|
||||||
|
report.Strays = append(report.Strays, link.Stray{Kind: s.Kind, Name: s.Name, Detail: s.Detail})
|
||||||
|
}
|
||||||
}
|
}
|
||||||
if declared.Adoption != nil {
|
if declared.Adoption != nil {
|
||||||
if updated.Firewall != nil {
|
if updated.Firewall != nil {
|
||||||
@@ -1518,3 +1607,54 @@ func adoptDeliveredMembership(identityPath string, mine *identity.Identity, say
|
|||||||
say(fmt.Sprintf("moving to the %s bus at %s — restarting to dial it", next.Transport, next.Broker))
|
say(fmt.Sprintf("moving to the %s bus at %s — restarting to dial it", next.Transport, next.Broker))
|
||||||
os.Exit(0)
|
os.Exit(0)
|
||||||
}
|
}
|
||||||
|
|
||||||
|
// refuseOlder refuses a declaration from the mesh that is older than the one this node holds.
|
||||||
|
//
|
||||||
|
// **By sequence, not by arrival** (novox/hq 04-ISSUES/107). What the host kept is the last thing
|
||||||
|
// the mesh said, signed; a declaration whose sequence is lower was composed before it, whatever
|
||||||
|
// order they arrived in — a backlog drained after the node was away, or a broker that split a burst.
|
||||||
|
// Applying it would make the machine into something the mesh had already moved past, which is the
|
||||||
|
// incident of issue 104 by another door.
|
||||||
|
//
|
||||||
|
// Only when both sides claim an order. A declaration with no sequence is one an older controller
|
||||||
|
// sent, and one kept with no sequence is one this host received before it understood them; in either
|
||||||
|
// case there is no order to compare, and refusing on a guess would strand the node the moment the
|
||||||
|
// controller is older than the host. Equal is the same declaration again, which reconciling is for.
|
||||||
|
func refuseOlder(kept store.Declared, keptErr error, sequence int64) error {
|
||||||
|
if sequence == 0 || keptErr != nil {
|
||||||
|
return nil
|
||||||
|
}
|
||||||
|
last, err := declaration.ParseTrusted(kept.Declaration)
|
||||||
|
if err != nil || last.Sequence == 0 {
|
||||||
|
return nil
|
||||||
|
}
|
||||||
|
if sequence < last.Sequence {
|
||||||
|
return fmt.Errorf("this declaration is older than what the mesh last said to this node: it "+
|
||||||
|
"is sequence %d, and the one kept here is %d. It arrived late — a backlog, or a broker "+
|
||||||
|
"that split a burst — and applying it would make this machine into something the mesh has "+
|
||||||
|
"already moved past. Refused whole; nothing was applied", sequence, last.Sequence)
|
||||||
|
}
|
||||||
|
return nil
|
||||||
|
}
|
||||||
|
|
||||||
|
// profileAsReported is the profile as the mesh reads it — the same bytes enrolment sends, so a
|
||||||
|
// report's profile and an enrolment's are one shape on the controller's side (novox/hq ADR 0161).
|
||||||
|
func profileAsReported(detected profile.Profile) map[string]any {
|
||||||
|
reported := map[string]any{}
|
||||||
|
if raw, err := json.Marshal(detected); err == nil {
|
||||||
|
_ = json.Unmarshal(raw, &reported)
|
||||||
|
}
|
||||||
|
return reported
|
||||||
|
}
|
||||||
|
|
||||||
|
// factsAsReported is a held thing's facts as the mesh reads them: the same bytes the host keeps.
|
||||||
|
func factsAsReported(f *store.Facts) map[string]any {
|
||||||
|
if f == nil {
|
||||||
|
return nil
|
||||||
|
}
|
||||||
|
out := map[string]any{}
|
||||||
|
if raw, err := json.Marshal(f); err == nil {
|
||||||
|
_ = json.Unmarshal(raw, &out)
|
||||||
|
}
|
||||||
|
return out
|
||||||
|
}
|
||||||
|
|||||||
@@ -568,3 +568,28 @@ func TestAConvergedMachineSaysItsOutwardLinksUnasked(t *testing.T) {
|
|||||||
t.Fatal("a refused report is offered as news about the machine")
|
t.Fatal("a refused report is offered as news about the machine")
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
|
// **A host running as a service says what its apply did.**
|
||||||
|
//
|
||||||
|
// The serving path passed nil where the apply writes its detail, and nil is silence. The one-shot path
|
||||||
|
// has always passed a real function, so everything the apply says was visible when a person ran it by
|
||||||
|
// hand and discarded in the way the host actually runs. Measured before this was written: a machine was
|
||||||
|
// converged, its found firewall was not retired, and what the host decided was unrecoverable because it
|
||||||
|
// had been said to nobody (novox/hq 04-ISSUES/143).
|
||||||
|
//
|
||||||
|
// This asserts only that the apply's log is never nil and that a line reaches what the caller gave.
|
||||||
|
// **It cannot catch the fault it was written for** — a call site passing nil directly — because that is
|
||||||
|
// wiring, and wiring is only proved by running the thing. That proof is a deployed host whose journal
|
||||||
|
// carries the apply's detail, which is how this fix was verified.
|
||||||
|
func TestTheApplysLogIsNeverNil(t *testing.T) {
|
||||||
|
if announceOr(nil) == nil {
|
||||||
|
t.Fatal("a host with nowhere to say things got a nil log, which the apply will call")
|
||||||
|
}
|
||||||
|
announceOr(nil)("this goes nowhere and must not panic")
|
||||||
|
|
||||||
|
var said []string
|
||||||
|
announceOr(func(line string) { said = append(said, line) })(" disabled ufw")
|
||||||
|
if len(said) != 1 || !strings.Contains(said[0], "disabled ufw") {
|
||||||
|
t.Fatalf("the apply's detail did not reach the caller's announce: %v", said)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|||||||
@@ -0,0 +1,58 @@
|
|||||||
|
package main
|
||||||
|
|
||||||
|
import (
|
||||||
|
"encoding/json"
|
||||||
|
"strings"
|
||||||
|
"testing"
|
||||||
|
|
||||||
|
"github.com/novox/mesh-host/internal/store"
|
||||||
|
)
|
||||||
|
|
||||||
|
// A declaration carries no order, so a host cannot tell an older one from a newer (novox/hq
|
||||||
|
// 04-ISSUES/107). Its only identity was the digest of its bytes: "not the last" could be said,
|
||||||
|
// "older" could not.
|
||||||
|
|
||||||
|
func keptWith(t *testing.T, sequence int64) store.Declared {
|
||||||
|
t.Helper()
|
||||||
|
body, err := json.Marshal(map[string]any{
|
||||||
|
"declaration": 1, "resources": []any{}, "owns_nothing": true, "sequence": sequence,
|
||||||
|
})
|
||||||
|
if err != nil {
|
||||||
|
t.Fatal(err)
|
||||||
|
}
|
||||||
|
return store.Declared{Declaration: body, Signature: []byte("x")}
|
||||||
|
}
|
||||||
|
|
||||||
|
func TestAnOlderDeclarationFromTheMeshIsRefused(t *testing.T) {
|
||||||
|
err := refuseOlder(keptWith(t, 7), nil, 5)
|
||||||
|
if err == nil {
|
||||||
|
t.Fatal("sequence 5 was accepted over a kept 7")
|
||||||
|
}
|
||||||
|
if !strings.Contains(err.Error(), "older") || !strings.Contains(err.Error(), "nothing was applied") {
|
||||||
|
t.Fatalf("the refusal does not say what it is: %v", err)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
func TestANewerOrEqualDeclarationIsNot(t *testing.T) {
|
||||||
|
if err := refuseOlder(keptWith(t, 7), nil, 8); err != nil {
|
||||||
|
t.Fatalf("sequence 8 was refused over a kept 7: %v", err)
|
||||||
|
}
|
||||||
|
// Equal is the same declaration again, which reconciling is for.
|
||||||
|
if err := refuseOlder(keptWith(t, 7), nil, 7); err != nil {
|
||||||
|
t.Fatalf("the same sequence was refused: %v", err)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
func TestNoOrderClaimedMeansNoOrderCompared(t *testing.T) {
|
||||||
|
// An older controller sends none; a host that received before it understood them kept none.
|
||||||
|
// Refusing on a guess would strand a node the moment the controller is older than the host.
|
||||||
|
if err := refuseOlder(keptWith(t, 7), nil, 0); err != nil {
|
||||||
|
t.Fatalf("a declaration claiming no order was refused: %v", err)
|
||||||
|
}
|
||||||
|
if err := refuseOlder(keptWith(t, 0), nil, 3); err != nil {
|
||||||
|
t.Fatalf("a declaration was refused against a kept one that claimed no order: %v", err)
|
||||||
|
}
|
||||||
|
if err := refuseOlder(store.Declared{}, store.ErrNothingDeclared, 3); err != nil {
|
||||||
|
t.Fatalf("a first declaration was refused: %v", err)
|
||||||
|
}
|
||||||
|
}
|
||||||
@@ -0,0 +1,48 @@
|
|||||||
|
package main
|
||||||
|
|
||||||
|
import (
|
||||||
|
"os"
|
||||||
|
"path/filepath"
|
||||||
|
"testing"
|
||||||
|
)
|
||||||
|
|
||||||
|
// A component's version comes from where it sits, not from its linker (novox/hq ADR 0142). The mesh's
|
||||||
|
// toolchain stamps no version — a build does not know what it will be called — so a delivered host
|
||||||
|
// read as "development build" and the mesh could not tell which host a machine ran (04-ISSUES/161).
|
||||||
|
|
||||||
|
func TestADeliveredHostReadsItsVersionFromItsPath(t *testing.T) {
|
||||||
|
// A delivered host lives at <libexec>/versions/<version>/<binary>.
|
||||||
|
dir := t.TempDir()
|
||||||
|
versioned := filepath.Join(dir, "versions", "637f65559d16")
|
||||||
|
if err := os.MkdirAll(versioned, 0o755); err != nil {
|
||||||
|
t.Fatal(err)
|
||||||
|
}
|
||||||
|
self := filepath.Join(versioned, "nox-mesh-host")
|
||||||
|
if err := os.WriteFile(self, []byte("#!/bin/sh\n"), 0o755); err != nil {
|
||||||
|
t.Fatal(err)
|
||||||
|
}
|
||||||
|
if got := versionAt(self, "development build"); got != "637f65559d16" {
|
||||||
|
t.Fatalf("a delivered host read its version as %q", got)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
func TestAHostPlacedByHandKeepsItsStamp(t *testing.T) {
|
||||||
|
// The honest answer for one the mesh did not deliver — and every machine is in that state until
|
||||||
|
// a delivery reaches it.
|
||||||
|
if got := versionAt("/usr/bin/nox-mesh-host", "04a27ca"); got != "04a27ca" {
|
||||||
|
t.Fatalf("a hand-placed host read its version as %q", got)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
func TestADirectoryThatIsNotAVersionIsNotReadAsOne(t *testing.T) {
|
||||||
|
// A binary sitting anywhere else must not have its parent directory's name read as a version.
|
||||||
|
for _, path := range []string{
|
||||||
|
"/opt/somewhere/nox-mesh-host",
|
||||||
|
"/usr/lib/nox-mesh-host/launch",
|
||||||
|
"/home/someone/build/nox-mesh-host",
|
||||||
|
} {
|
||||||
|
if got := versionAt(path, "the stamp"); got != "the stamp" {
|
||||||
|
t.Fatalf("%s read its version as %q", path, got)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
@@ -127,12 +127,21 @@
|
|||||||
{
|
{
|
||||||
"id": "bus-certificate",
|
"id": "bus-certificate",
|
||||||
"type": "action",
|
"type": "action",
|
||||||
"command": ["docker", "run", "--rm", "--entrypoint", "sh", "-v", "mesh-broker-tls:/tls",
|
// **The mesh makes its own** (novox/hq 04-ISSUES/146). This ran `openssl` inside the
|
||||||
"192.0.2.250:5000/nats@sha256:b83efabe3e7def1e0a4a31ec6e078999bb17c80363f881df35edc70fcb6bb927",
|
// broker's image while the broker was one that carried it; the bus that replaced it has a
|
||||||
"-c", "test -f /tls/tls.crt || (openssl req -x509 -newkey rsa:2048 -nodes -keyout /tls/tls.key -out /tls/tls.crt -days 3650 -subj '/CN=mesh-broker' -addext 'subjectAltName=DNS:mesh-broker,IP:127.0.0.1' >/dev/null 2>&1 && chmod 644 /tls/tls.crt && chmod 600 /tls/tls.key)"],
|
// shell and no openssl, and no other image the bundle names has one either. So the program
|
||||||
"verify": ["docker", "run", "--rm", "--entrypoint", "sh", "-v", "mesh-broker-tls:/tls",
|
// that needs the certificate writes it — already on this machine, since the schema step ran
|
||||||
"192.0.2.250:5000/nats@sha256:b83efabe3e7def1e0a4a31ec6e078999bb17c80363f881df35edc70fcb6bb927",
|
// it, and asking nothing of the image it writes into. Self-signed on purpose: a host pins
|
||||||
"-c", "test -s /tls/tls.crt && openssl x509 -in /tls/tls.crt -noout"]
|
// this server's exact certificate (novox/hq ADR 0004), and at this moment there is no mesh
|
||||||
|
// to ask an authority of.
|
||||||
|
// `--user 0:0` because the volume is root's and this image runs as nobody, which is right
|
||||||
|
// for the long-running control plane and wrong for a one-shot writing into a fresh volume.
|
||||||
|
"command": ["docker", "run", "--rm", "--user", "0:0", "-v", "mesh-broker-tls:/tls",
|
||||||
|
"192.0.2.250:5000/mesh-controller@sha256:c67db38439ff0aee242b467486765467bb95801f52175fc5727cc4e437338ace",
|
||||||
|
"broker", "certificate", "--into", "/tls"],
|
||||||
|
"verify": ["docker", "run", "--rm", "--user", "0:0", "-v", "mesh-broker-tls:/tls",
|
||||||
|
"192.0.2.250:5000/mesh-controller@sha256:c67db38439ff0aee242b467486765467bb95801f52175fc5727cc4e437338ace",
|
||||||
|
"broker", "certificate", "--check", "--into", "/tls"]
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"id": "bus-conf-dir",
|
"id": "bus-conf-dir",
|
||||||
@@ -152,7 +161,7 @@
|
|||||||
"type": "file",
|
"type": "file",
|
||||||
"path": "/var/lib/mesh-bus-conf/accounts.conf",
|
"path": "/var/lib/mesh-bus-conf/accounts.conf",
|
||||||
"mode": "0600",
|
"mode": "0600",
|
||||||
"content": "// The first user list, carried by the installer because at genesis there is no mesh to\n// compose one. A bootstrap credential, rotated with the store's and replaced by the\n// controller's own composition from its first start onward.\naccounts {\n MESH {\n jetstream: enabled\n users = [\n { user: \"controller\", password: \"$2a$10$AHqJgOifIVbU41KmATiMhuXFs8xa7Wl2HuN4UVBCXdN2jIQzjqApy\", permissions: {\n publish: { allow: [\"$JS.API.>\", \"$JS.ACK.CONTROL.controller.>\", \"$JS.ACK.EVENTS.controller.>\", \"_INBOX.enrol.>\", \"mesh.control.>\", \"mesh.mod.*.tool.>\", \"mesh.node.>\", \"mesh.seat.mesh-build-machine.accept.>\", \"mesh.seat.mesh-controller.event.applied\", \"mesh.seat.mesh-controller.event.built-before\", \"mesh.seat.mesh-controller.event.refused\"] }\n subscribe: { allow: [\"$JS.API.>\", \"_DELIVER.controller\", \"_DELIVER.controller.>\", \"_INBOX.controller.>\", \"mesh.control.>\", \"mesh.mod.mesh-catalog.event.catching-up\", \"mesh.mod.mesh-catalog.event.upgraded\", \"mesh.mod.gitea.event.pull.merged\", \"mesh.seat.mesh-build-machine.event.built\"] }\n allow_responses: { max: 1, ttl: \"1m\" }\n } }\n ]\n }\n}\n"
|
"content": "// The first user list, carried by the installer because at genesis there is no mesh to\n// compose one. A bootstrap credential, rotated with the store's and replaced by the\n// controller's own composition from its first start onward.\naccounts {\n MESH {\n jetstream: enabled\n users = [\n { user: \"controller\", password: \"$2a$10$AHqJgOifIVbU41KmATiMhuXFs8xa7Wl2HuN4UVBCXdN2jIQzjqApy\", permissions: {\n publish: { allow: [\"$JS.ACK.CONTROL.controller.>\", \"$JS.ACK.EVENTS.controller.>\", \"$JS.API.>\", \"_INBOX.enrol.>\", \"mesh.assignment.>\", \"mesh.control.>\", \"mesh.mod.*.tool.>\", \"mesh.node.>\", \"mesh.seat.mesh-build-machine.accept.>\", \"mesh.seat.mesh-controller.event.applied\", \"mesh.seat.mesh-controller.event.built-before\", \"mesh.seat.mesh-controller.event.refused\"] }\n subscribe: { allow: [\"$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\", \"mesh.seat.mesh-controller.tool.>\"] }\n allow_responses: { max: 1, ttl: \"1m\" }\n } }\n ]\n }\n}\n"
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"id": "broker",
|
"id": "broker",
|
||||||
|
|||||||
+41
-7
@@ -20,6 +20,7 @@ import (
|
|||||||
"os"
|
"os"
|
||||||
"os/exec"
|
"os/exec"
|
||||||
"path/filepath"
|
"path/filepath"
|
||||||
|
"slices"
|
||||||
"sort"
|
"sort"
|
||||||
"strconv"
|
"strconv"
|
||||||
"strings"
|
"strings"
|
||||||
@@ -230,6 +231,18 @@ func ApplyKeeping(
|
|||||||
protecting = append(protecting, orphan)
|
protecting = append(protecting, orphan)
|
||||||
continue
|
continue
|
||||||
}
|
}
|
||||||
|
// **A module the mesh left out is not a module the mesh removed** (novox/hq ADR 0163, rule
|
||||||
|
// 6): its resources are absent because a setting stored for it cannot compose, and the
|
||||||
|
// mesh said so by name. What the host wrote for it stays as it is, recorded, until the
|
||||||
|
// module is declared again or unassigned.
|
||||||
|
if module, left := d.LeftOutModuleOf(orphan.ID); left {
|
||||||
|
report.Outcomes = append(report.Outcomes, Outcome{
|
||||||
|
ID: orphan.ID, Type: orphan.Type, Target: orphan.Target,
|
||||||
|
Action: "unchanged", Detail: "kept: " + module + " was left out of this declaration by the mesh, not removed",
|
||||||
|
})
|
||||||
|
log(fmt.Sprintf(" kept %s (%s): %s was left out of this declaration by the mesh, not removed", orphan.ID, orphan.Target, module))
|
||||||
|
continue
|
||||||
|
}
|
||||||
orphans = append(orphans, orphan)
|
orphans = append(orphans, orphan)
|
||||||
}
|
}
|
||||||
ordered := d.Resources
|
ordered := d.Resources
|
||||||
@@ -270,6 +283,11 @@ func ApplyKeeping(
|
|||||||
if declared[h.ID] {
|
if declared[h.ID] {
|
||||||
continue
|
continue
|
||||||
}
|
}
|
||||||
|
if slices.Contains(d.LeftOut, h.Module) {
|
||||||
|
// Left out, not unassigned (ADR 0163, rule 6): still held for the module, as the
|
||||||
|
// mesh asked.
|
||||||
|
continue
|
||||||
|
}
|
||||||
known.Release(h.ID)
|
known.Release(h.ID)
|
||||||
report.Outcomes = append(report.Outcomes, Outcome{ID: h.ID, Type: h.Kind, Target: h.Target,
|
report.Outcomes = append(report.Outcomes, Outcome{ID: h.ID, Type: h.Kind, Target: h.Target,
|
||||||
Action: "forgotten", Detail: "no longer declared; left as found"})
|
Action: "forgotten", Detail: "no longer declared; left as found"})
|
||||||
@@ -1501,13 +1519,15 @@ func containerSpecReading(r *declaration.Container, declares, reads map[string]s
|
|||||||
for _, a := range r.Args {
|
for _, a := range r.Args {
|
||||||
b.WriteString("arg " + a + "\n")
|
b.WriteString("arg " + a + "\n")
|
||||||
}
|
}
|
||||||
// **The mesh's names are part of what a container is** (novox/hq 04-ISSUES/135). A container
|
// **A container's declared names are part of what it is** (novox/hq 04-ISSUES/135). What is
|
||||||
// resolves every other machine and every public name through the entries the mesh gives it at
|
// here is what the module declared for itself and nothing else: the mesh's own names are no
|
||||||
// creation, and nothing re-reads them afterwards — so a container left alone when the roster
|
// longer written into a container (ADR 0148) — they were once, every container got the whole
|
||||||
// moved is one that cannot reach anything by name, for ever, while every check reports it
|
// roster at creation and nothing re-read it, so one left alone when the roster moved could not
|
||||||
// running. That is exactly what happened when this mesh's overlay range changed: one container
|
// reach anything by name for as long as it ran while every check reported it running; and once
|
||||||
// whose image and files never changed kept an address five days out of date and restarted
|
// the roster was in this digest so that could be caught, one name moving anywhere replaced
|
||||||
// 2286 times against a database it could no longer find.
|
// every container in the mesh (04-ISSUES/151). A container resolves a mesh name through the
|
||||||
|
// machine's resolver at the moment it asks. What a module declares does not move when the
|
||||||
|
// roster does, so hashing it costs nothing and catches a manifest that changed.
|
||||||
//
|
//
|
||||||
// Sorted, so the digest does not move for a reordering nobody made.
|
// Sorted, so the digest does not move for a reordering nobody made.
|
||||||
hosts := append([]string(nil), r.Hosts...)
|
hosts := append([]string(nil), r.Hosts...)
|
||||||
@@ -1524,6 +1544,11 @@ func containerSpecReading(r *declaration.Container, declares, reads map[string]s
|
|||||||
if r.IP != "" {
|
if r.IP != "" {
|
||||||
b.WriteString("ip " + r.IP + "\n")
|
b.WriteString("ip " + r.IP + "\n")
|
||||||
}
|
}
|
||||||
|
// The networks it also joins are part of what it is (ADR 0163, rule 4): kept or let go, the
|
||||||
|
// container is recreated, and a neighbour's reach changes with it.
|
||||||
|
for _, n := range r.Networks {
|
||||||
|
b.WriteString("also-on " + n + "\n")
|
||||||
|
}
|
||||||
// The cadence is part of what was declared, so a changed schedule is a changed spec — the marker
|
// The cadence is part of what was declared, so a changed schedule is a changed spec — the marker
|
||||||
// moves and the install is reported "updated" and re-established. Added only when present, so no
|
// moves and the install is reported "updated" and re-established. Added only when present, so no
|
||||||
// ordinary container's or run-once step's digest moves for a field it does not set.
|
// ordinary container's or run-once step's digest moves for a field it does not set.
|
||||||
@@ -1764,6 +1789,15 @@ func applyContainer(ctx context.Context, r *declaration.Container, run Runner,
|
|||||||
if after.Spec != want {
|
if after.Spec != want {
|
||||||
return out, fmt.Errorf("container %s is not the one that was declared after creating it", r.Name)
|
return out, fmt.Errorf("container %s is not the one that was declared after creating it", r.Name)
|
||||||
}
|
}
|
||||||
|
// The found networks a per-machine setting keeps for it (novox/hq ADR 0163, rule 4), joined
|
||||||
|
// once it runs: a runtime starts a container on one network, and the others are connected.
|
||||||
|
// Refused, not skipped, when one cannot be joined — a neighbour that was promised to keep
|
||||||
|
// reaching this container by name would silently not.
|
||||||
|
for _, n := range r.Networks {
|
||||||
|
if _, err := run(ctx, cri, "network", "connect", n, r.Name); err != nil {
|
||||||
|
return out, fmt.Errorf("container %s could not join the kept network %s: %w", r.Name, n, err)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
out.Action = "created"
|
out.Action = "created"
|
||||||
if existed {
|
if existed {
|
||||||
|
|||||||
@@ -0,0 +1,97 @@
|
|||||||
|
package apply
|
||||||
|
|
||||||
|
import (
|
||||||
|
"context"
|
||||||
|
"os"
|
||||||
|
"path/filepath"
|
||||||
|
"strings"
|
||||||
|
"testing"
|
||||||
|
|
||||||
|
"github.com/novox/mesh-host/internal/store"
|
||||||
|
)
|
||||||
|
|
||||||
|
// A take is a comparison (novox/hq ADR 0163): while a module's container is held, the host reports
|
||||||
|
// the found image and its age beside the declared one, the networks and who else is on them, the
|
||||||
|
// mounts and the ports — and says when the declared image is the older.
|
||||||
|
func TestAHeldContainerCarriesTheFactsATakeCompares(t *testing.T) {
|
||||||
|
dir, page, m := predecessor(t)
|
||||||
|
m.containers["hello-web"].image = "web:1.27"
|
||||||
|
m.containers["hello-web"].imageID = "sha256:found"
|
||||||
|
m.containers["hello-web"].networks = []string{"predecessor_default"}
|
||||||
|
m.containers["hello-web"].mounts = []string{"/srv/web:/data"}
|
||||||
|
m.containers["hello-web"].ports = []string{"80/tcp>0.0.0.0:8080"}
|
||||||
|
m.images = map[string]string{"sha256:found": "2026-09-17T10:00:00Z", pinned: "2026-08-20T10:00:00Z"}
|
||||||
|
m.members = map[string][]string{"predecessor_default": {"hello-web", "office", "db"}}
|
||||||
|
|
||||||
|
_, state := applyAdopted(t, adopted(t, untakenWeb, webResources(page)), store.State{}, m, dir)
|
||||||
|
h, ok := state.HeldAt("hello-web.server")
|
||||||
|
if !ok || h.Facts == nil {
|
||||||
|
t.Fatalf("a held container carries no facts: %+v", h)
|
||||||
|
}
|
||||||
|
f := h.Facts
|
||||||
|
if f.Image != "web:1.27" || f.ImageCreated != "2026-09-17T10:00:00Z" {
|
||||||
|
t.Errorf("the found image and its age: %+v", f)
|
||||||
|
}
|
||||||
|
if f.DeclaredImage != pinned || f.DeclaredImageCreated != "2026-08-20T10:00:00Z" || !f.Downgrade {
|
||||||
|
t.Errorf("the declared image, its age, and that it is a downgrade: %+v", f)
|
||||||
|
}
|
||||||
|
if got := f.Networks["predecessor_default"]; len(got) != 2 || got[0] != "db" || got[1] != "office" {
|
||||||
|
t.Errorf("the neighbours on the found network, without the container itself: %v", f.Networks)
|
||||||
|
}
|
||||||
|
if len(f.Mounts) != 1 || f.Mounts[0] != "/srv/web:/data" || len(f.Ports) != 1 || f.Ports[0] != "80/tcp>0.0.0.0:8080" {
|
||||||
|
t.Errorf("mounts and ports as found: %+v", f)
|
||||||
|
}
|
||||||
|
// And the held file carries how the declared content differs from what was found.
|
||||||
|
p, ok := state.HeldAt("hello-web.page")
|
||||||
|
if !ok || p.Facts == nil || !p.Facts.Differs {
|
||||||
|
t.Fatalf("a held file that differs from the declared content does not say so: %+v", p)
|
||||||
|
}
|
||||||
|
joined := strings.Join(p.Facts.Difference, "\n")
|
||||||
|
if !strings.Contains(joined, "- the predecessor's page") || !strings.Contains(joined, "+ the mesh's page") {
|
||||||
|
t.Errorf("the difference does not show what is lost and what is new: %q", joined)
|
||||||
|
}
|
||||||
|
_ = os.Remove(filepath.Join(dir, "unused"))
|
||||||
|
}
|
||||||
|
|
||||||
|
// A declared image not yet on the machine leaves its age unknown and the comparison undecided.
|
||||||
|
func TestAnImageNotYetPulledLeavesTheDowngradeUndecided(t *testing.T) {
|
||||||
|
dir, page, m := predecessor(t)
|
||||||
|
m.containers["hello-web"].image = "web:1.27"
|
||||||
|
m.containers["hello-web"].imageID = "sha256:found"
|
||||||
|
m.images = map[string]string{"sha256:found": "2026-09-17T10:00:00Z"}
|
||||||
|
_, state := applyAdopted(t, adopted(t, untakenWeb, webResources(page)), store.State{}, m, dir)
|
||||||
|
h, _ := state.HeldAt("hello-web.server")
|
||||||
|
if h.Facts == nil || h.Facts.DeclaredImageCreated != "" || h.Facts.Downgrade {
|
||||||
|
t.Fatalf("an unknown declared age decided a downgrade: %+v", h.Facts)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
func TestTheDifferenceIsWhatIsLostAndWhatIsNew(t *testing.T) {
|
||||||
|
differs, lines := differenceOf("a\nprivate scope: local\nb\n", "a\nb\nupstream: public\n")
|
||||||
|
if !differs || len(lines) != 2 || lines[0] != "- private scope: local" || lines[1] != "+ upstream: public" {
|
||||||
|
t.Fatalf("got %v %v", differs, lines)
|
||||||
|
}
|
||||||
|
if differs, lines := differenceOf("same\n", "same\n"); differs || lines != nil {
|
||||||
|
t.Fatalf("identical content differs: %v %v", differs, lines)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
// What runs on the machine that the mesh neither wrote nor holds is reported (ADR 0163).
|
||||||
|
func TestStraysAreWhatRunsHereThatNobodyAsked(t *testing.T) {
|
||||||
|
m := &machine{containers: map[string]*fakeContainer{
|
||||||
|
"hello-web": {id: "ours", running: true, image: "web:1"},
|
||||||
|
"gitea-old": {id: "left-behind", running: true, image: "gitea:1.22"},
|
||||||
|
"held-thing": {id: "found", running: true, image: "x:1"},
|
||||||
|
}}
|
||||||
|
known := store.State{
|
||||||
|
Resources: []store.Applied{{ID: "hello-web.server", Type: "container", Target: "hello-web"}},
|
||||||
|
Held: []store.Held{{ID: "other.server", Kind: "container", Target: "held-thing"}},
|
||||||
|
}
|
||||||
|
strays, err := Strays(context.Background(), m.run, known)
|
||||||
|
if err != nil {
|
||||||
|
t.Fatal(err)
|
||||||
|
}
|
||||||
|
if len(strays) != 1 || strays[0].Name != "gitea-old" || !strings.Contains(strays[0].Detail, "gitea:1.22") {
|
||||||
|
t.Fatalf("strays: %+v", strays)
|
||||||
|
}
|
||||||
|
}
|
||||||
+125
-4
@@ -8,6 +8,7 @@ import (
|
|||||||
"fmt"
|
"fmt"
|
||||||
"os"
|
"os"
|
||||||
"path/filepath"
|
"path/filepath"
|
||||||
|
"sort"
|
||||||
"strings"
|
"strings"
|
||||||
"syscall"
|
"syscall"
|
||||||
"time"
|
"time"
|
||||||
@@ -433,6 +434,32 @@ type foundContainer struct {
|
|||||||
id string
|
id string
|
||||||
running bool
|
running bool
|
||||||
spec string
|
spec string
|
||||||
|
// What a take compares (novox/hq ADR 0163): the image and its id, the networks the container
|
||||||
|
// is on, its mounts and its published ports — empty from a runtime (or a test's fake) that
|
||||||
|
// answers the short form.
|
||||||
|
image string
|
||||||
|
imageID string
|
||||||
|
networks []string
|
||||||
|
mounts []string
|
||||||
|
ports []string
|
||||||
|
}
|
||||||
|
|
||||||
|
// foundFormat is what inspectFound asks the runtime for, tab-separated: the three a hold has
|
||||||
|
// always needed, then the facts a take compares.
|
||||||
|
const foundFormat = "{{.Id}}\t{{.State.Running}}\t{{index .Config.Labels \"" + specLabel + "\"}}" +
|
||||||
|
"\t{{.Config.Image}}\t{{.Image}}" +
|
||||||
|
"\t{{range $k, $v := .NetworkSettings.Networks}}{{$k}},{{end}}" +
|
||||||
|
"\t{{range .Mounts}}{{.Source}}:{{.Destination}},{{end}}" +
|
||||||
|
"\t{{range $p, $b := .NetworkSettings.Ports}}{{$p}}{{range $b}}>{{.HostIp}}:{{.HostPort}}{{end}},{{end}}"
|
||||||
|
|
||||||
|
func splitList(s string) []string {
|
||||||
|
var out []string
|
||||||
|
for _, part := range strings.Split(s, ",") {
|
||||||
|
if part = strings.TrimSpace(part); part != "" {
|
||||||
|
out = append(out, part)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
return out
|
||||||
}
|
}
|
||||||
|
|
||||||
// inspectFound reads a container by name the way a hold needs it: its id, whether it runs, and
|
// inspectFound reads a container by name the way a hold needs it: its id, whether it runs, and
|
||||||
@@ -451,8 +478,7 @@ func inspectFound(ctx context.Context, name string, run Runner) (foundContainer,
|
|||||||
if err != nil {
|
if err != nil {
|
||||||
return foundContainer{}, false, fmt.Errorf("%w, so nothing can be said about %q", err, name)
|
return foundContainer{}, false, fmt.Errorf("%w, so nothing can be said about %q", err, name)
|
||||||
}
|
}
|
||||||
out, err := run(ctx, cri, "container", "inspect", "--format",
|
out, err := run(ctx, cri, "container", "inspect", "--format", foundFormat, name)
|
||||||
"{{.Id}}\t{{.State.Running}}\t{{index .Config.Labels \""+specLabel+"\"}}", name)
|
|
||||||
if err != nil {
|
if err != nil {
|
||||||
if absent(err) {
|
if absent(err) {
|
||||||
return foundContainer{}, false, nil
|
return foundContainer{}, false, nil
|
||||||
@@ -466,14 +492,100 @@ func inspectFound(ctx context.Context, name string, run Runner) (foundContainer,
|
|||||||
name, err)
|
name, err)
|
||||||
}
|
}
|
||||||
parts := strings.Split(strings.TrimSpace(out), "\t")
|
parts := strings.Split(strings.TrimSpace(out), "\t")
|
||||||
for len(parts) < 3 {
|
for len(parts) < 8 {
|
||||||
parts = append(parts, "")
|
parts = append(parts, "")
|
||||||
}
|
}
|
||||||
spec := strings.TrimSpace(parts[2])
|
spec := strings.TrimSpace(parts[2])
|
||||||
if spec == "<no value>" {
|
if spec == "<no value>" {
|
||||||
spec = ""
|
spec = ""
|
||||||
}
|
}
|
||||||
return foundContainer{id: strings.TrimSpace(parts[0]), running: parts[1] == "true", spec: spec}, true, nil
|
return foundContainer{id: strings.TrimSpace(parts[0]), running: parts[1] == "true", spec: spec,
|
||||||
|
image: strings.TrimSpace(parts[3]), imageID: strings.TrimSpace(parts[4]),
|
||||||
|
networks: splitList(parts[5]), mounts: splitList(parts[6]), ports: splitList(parts[7])}, true, nil
|
||||||
|
}
|
||||||
|
|
||||||
|
// factsOf is what a take would compare for a found container (novox/hq ADR 0163): the found
|
||||||
|
// image and when it was made, the networks and who else is on them, mounts and ports — beside
|
||||||
|
// what the module declares, and the declared image's date when that image is on the machine.
|
||||||
|
// Every question the runtime cannot answer leaves its fact empty; a preview says so rather than
|
||||||
|
// guesses.
|
||||||
|
func factsOf(ctx context.Context, seen foundContainer, res *declaration.Container, run Runner) *Facts {
|
||||||
|
cri, err := containerRuntime(ctx, run)
|
||||||
|
if err != nil {
|
||||||
|
return nil
|
||||||
|
}
|
||||||
|
f := &store.Facts{Image: seen.image, Mounts: seen.mounts, Ports: seen.ports,
|
||||||
|
DeclaredImage: res.Image, DeclaredPorts: res.Ports, DeclaredVolumes: res.Volumes}
|
||||||
|
if seen.imageID != "" {
|
||||||
|
if out, err := run(ctx, cri, "image", "inspect", "--format", "{{.Created}}", seen.imageID); err == nil {
|
||||||
|
f.ImageCreated = strings.TrimSpace(out)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
if res.Image != "" {
|
||||||
|
if out, err := run(ctx, cri, "image", "inspect", "--format", "{{.Created}}", res.Image); err == nil {
|
||||||
|
f.DeclaredImageCreated = strings.TrimSpace(out)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
if found, err := time.Parse(time.RFC3339Nano, f.ImageCreated); err == nil {
|
||||||
|
if declared, err := time.Parse(time.RFC3339Nano, f.DeclaredImageCreated); err == nil {
|
||||||
|
f.Downgrade = declared.Before(found)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
for _, network := range seen.networks {
|
||||||
|
if f.Networks == nil {
|
||||||
|
f.Networks = map[string][]string{}
|
||||||
|
}
|
||||||
|
var members []string
|
||||||
|
if out, err := run(ctx, cri, "network", "inspect", "--format",
|
||||||
|
"{{range .Containers}}{{.Name}},{{end}}", network); err == nil {
|
||||||
|
for _, m := range splitList(out) {
|
||||||
|
if m != res.Name {
|
||||||
|
members = append(members, m)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
sort.Strings(members)
|
||||||
|
f.Networks[network] = members
|
||||||
|
}
|
||||||
|
return (*Facts)(f)
|
||||||
|
}
|
||||||
|
|
||||||
|
// Facts is store.Facts, named here so hold's callers read as one vocabulary.
|
||||||
|
type Facts = store.Facts
|
||||||
|
|
||||||
|
// differenceOf is how a found file differs from the declared content: the lines only the found
|
||||||
|
// file has, marked -, then the lines only the declared content has, marked +, in their own order,
|
||||||
|
// bounded so a report stays a report. Not a diff tool's output: the question a take answers is
|
||||||
|
// "what would be lost and what would be new", and that is these two lists.
|
||||||
|
func differenceOf(found, declared string) (bool, []string) {
|
||||||
|
if found == declared {
|
||||||
|
return false, nil
|
||||||
|
}
|
||||||
|
const bound = 40
|
||||||
|
count := func(s string) map[string]int {
|
||||||
|
out := map[string]int{}
|
||||||
|
for _, line := range strings.Split(s, "\n") {
|
||||||
|
out[line]++
|
||||||
|
}
|
||||||
|
return out
|
||||||
|
}
|
||||||
|
inFound, inDeclared := count(found), count(declared)
|
||||||
|
var out []string
|
||||||
|
add := func(mark, s string, other map[string]int) {
|
||||||
|
seen := map[string]int{}
|
||||||
|
for _, line := range strings.Split(s, "\n") {
|
||||||
|
seen[line]++
|
||||||
|
if seen[line] > other[line] && len(out) < bound {
|
||||||
|
out = append(out, mark+" "+line)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
add("-", found, inDeclared)
|
||||||
|
add("+", declared, inFound)
|
||||||
|
if len(out) >= bound {
|
||||||
|
out = append(out, "… and more")
|
||||||
|
}
|
||||||
|
return true, out
|
||||||
}
|
}
|
||||||
|
|
||||||
// absent is whether a runtime said the thing is not there, rather than failing to answer. Its own
|
// absent is whether a runtime said the thing is not there, rather than failing to answer. Its own
|
||||||
@@ -540,6 +652,12 @@ func hold(ctx context.Context, sys system.System, r declaration.Resource, module
|
|||||||
} else if digestOf(string(content)) != h.Digest {
|
} else if digestOf(string(content)) != h.Digest {
|
||||||
changed = "rewritten"
|
changed = "rewritten"
|
||||||
}
|
}
|
||||||
|
// What a take would replace it with, and how that differs (novox/hq ADR 0163): a
|
||||||
|
// file declared whole is compared whole; one written into is not replaced at all.
|
||||||
|
if res.Into == "" {
|
||||||
|
differs, lines := differenceOf(string(content), res.Content)
|
||||||
|
h.Facts = &Facts{Differs: differs, Difference: lines}
|
||||||
|
}
|
||||||
}
|
}
|
||||||
case *declaration.Directory:
|
case *declaration.Directory:
|
||||||
info, err := os.Lstat(res.Path)
|
info, err := os.Lstat(res.Path)
|
||||||
@@ -628,6 +746,9 @@ func hold(ctx context.Context, sys system.System, r declaration.Resource, module
|
|||||||
case h.Running && !seen.running:
|
case h.Running && !seen.running:
|
||||||
changed = "stopped"
|
changed = "stopped"
|
||||||
}
|
}
|
||||||
|
if exists {
|
||||||
|
h.Facts = factsOf(ctx, seen, res, run)
|
||||||
|
}
|
||||||
default:
|
default:
|
||||||
return out, h, fmt.Errorf("a %s cannot be held", r.Kind())
|
return out, h, fmt.Errorf("a %s cannot be held", r.Kind())
|
||||||
}
|
}
|
||||||
|
|||||||
@@ -5,6 +5,7 @@ import (
|
|||||||
"errors"
|
"errors"
|
||||||
"os"
|
"os"
|
||||||
"path/filepath"
|
"path/filepath"
|
||||||
|
"sort"
|
||||||
"strings"
|
"strings"
|
||||||
"testing"
|
"testing"
|
||||||
|
|
||||||
@@ -18,7 +19,11 @@ import (
|
|||||||
// label when a host made it. Every command it is asked is written down.
|
// label when a host made it. Every command it is asked is written down.
|
||||||
type machine struct {
|
type machine struct {
|
||||||
containers map[string]*fakeContainer
|
containers map[string]*fakeContainer
|
||||||
asked []string
|
// images is what `image inspect --format {{.Created}}` answers per image or id; members is
|
||||||
|
// what `network inspect` lists per network (ADR 0163).
|
||||||
|
images map[string]string
|
||||||
|
members map[string][]string
|
||||||
|
asked []string
|
||||||
// wgUp is what `wg show interfaces` answers: the tunnels up on the machine.
|
// wgUp is what `wg show interfaces` answers: the tunnels up on the machine.
|
||||||
wgUp string
|
wgUp string
|
||||||
// handshakes is what `wg show <interface> latest-handshakes` answers, and handshakesFail the
|
// handshakes is what `wg show <interface> latest-handshakes` answers, and handshakesFail the
|
||||||
@@ -97,6 +102,9 @@ type fakeContainer struct {
|
|||||||
id string
|
id string
|
||||||
running bool
|
running bool
|
||||||
spec string
|
spec string
|
||||||
|
// What a take compares (ADR 0163), answered in the long inspect form when set.
|
||||||
|
image, imageID string
|
||||||
|
networks, mounts, ports []string
|
||||||
}
|
}
|
||||||
|
|
||||||
func (m *machine) run(_ context.Context, name string, args ...string) (string, error) {
|
func (m *machine) run(_ context.Context, name string, args ...string) (string, error) {
|
||||||
@@ -140,9 +148,38 @@ func (m *machine) run(_ context.Context, name string, args ...string) (string, e
|
|||||||
running = "true"
|
running = "true"
|
||||||
}
|
}
|
||||||
if strings.HasPrefix(args[3], "{{.Id}}") {
|
if strings.HasPrefix(args[3], "{{.Id}}") {
|
||||||
return c.id + "\t" + running + "\t" + c.spec + "\n", nil
|
line := c.id + "\t" + running + "\t" + c.spec
|
||||||
|
if c.image != "" {
|
||||||
|
line += "\t" + c.image + "\t" + c.imageID + "\t" + strings.Join(c.networks, ",") + "," +
|
||||||
|
"\t" + strings.Join(c.mounts, ",") + "," + "\t" + strings.Join(c.ports, ",") + ","
|
||||||
|
}
|
||||||
|
return line + "\n", nil
|
||||||
}
|
}
|
||||||
return running + "\t" + c.spec + "\n", nil
|
return running + "\t" + c.spec + "\n", nil
|
||||||
|
case "image":
|
||||||
|
if len(args) > 1 && args[1] == "inspect" {
|
||||||
|
if created, ok := m.images[args[len(args)-1]]; ok {
|
||||||
|
return created + "\n", nil
|
||||||
|
}
|
||||||
|
return "", errors.New("no such image")
|
||||||
|
}
|
||||||
|
return "", nil
|
||||||
|
case "network":
|
||||||
|
if len(args) > 1 && args[1] == "inspect" {
|
||||||
|
return strings.Join(m.members[args[len(args)-1]], ",") + ",\n", nil
|
||||||
|
}
|
||||||
|
return "", nil
|
||||||
|
case "ps":
|
||||||
|
var lines []string
|
||||||
|
for name, c := range m.containers {
|
||||||
|
state := "exited"
|
||||||
|
if c.running {
|
||||||
|
state = "running"
|
||||||
|
}
|
||||||
|
lines = append(lines, name+"\t"+c.image+"\t"+state)
|
||||||
|
}
|
||||||
|
sort.Strings(lines)
|
||||||
|
return strings.Join(lines, "\n") + "\n", nil
|
||||||
case "rm":
|
case "rm":
|
||||||
delete(m.containers, args[len(args)-1])
|
delete(m.containers, args[len(args)-1])
|
||||||
return "", nil
|
return "", nil
|
||||||
|
|||||||
@@ -0,0 +1,136 @@
|
|||||||
|
package apply
|
||||||
|
|
||||||
|
import (
|
||||||
|
"context"
|
||||||
|
"errors"
|
||||||
|
"strings"
|
||||||
|
"testing"
|
||||||
|
|
||||||
|
"github.com/novox/mesh-host/internal/declaration"
|
||||||
|
"github.com/novox/mesh-host/internal/store"
|
||||||
|
)
|
||||||
|
|
||||||
|
// A taken container keeps a found network by a per-machine setting (novox/hq ADR 0163, rule 4):
|
||||||
|
// joined once it runs, part of its spec, and refused when it cannot be joined.
|
||||||
|
func TestAContainerJoinsTheNetworksItKeeps(t *testing.T) {
|
||||||
|
var ran []string
|
||||||
|
connectFails := false
|
||||||
|
run := func(_ context.Context, name string, args ...string) (string, error) {
|
||||||
|
if name != "docker" {
|
||||||
|
return "", errors.New("not installed")
|
||||||
|
}
|
||||||
|
ran = append(ran, strings.Join(args, " "))
|
||||||
|
switch args[0] {
|
||||||
|
case "info":
|
||||||
|
return "29.0.0\n", nil
|
||||||
|
case "container":
|
||||||
|
if len(ran) > 2 {
|
||||||
|
return "true\t" + specOfLast, nil
|
||||||
|
}
|
||||||
|
return "false\t\n", errors.New("no such container")
|
||||||
|
case "run":
|
||||||
|
return "deadbeef\n", nil
|
||||||
|
case "network":
|
||||||
|
if connectFails {
|
||||||
|
return "", errors.New("network predecessor_default not found")
|
||||||
|
}
|
||||||
|
}
|
||||||
|
return "", nil
|
||||||
|
}
|
||||||
|
d := parseTrusted(t, `{"declaration":1,"resources":[
|
||||||
|
{"id":"app","type":"container","name":"app","image":"`+pinned+`",
|
||||||
|
"networks":["predecessor_default"]}
|
||||||
|
]}`)
|
||||||
|
specOfLast = containerSpec(d.Resources[0].(*declaration.Container), inputs{})
|
||||||
|
alone := *d.Resources[0].(*declaration.Container)
|
||||||
|
alone.Networks = nil
|
||||||
|
if specOfLast == containerSpec(&alone, inputs{}) {
|
||||||
|
t.Fatal("the kept network is not part of the container's spec: kept or let go, the container would be left alone")
|
||||||
|
}
|
||||||
|
report, _, err := Apply(context.Background(), archHost(t), d, store.State{}, store.OriginCarried, run, nil, nil)
|
||||||
|
if err != nil {
|
||||||
|
t.Fatal(err)
|
||||||
|
}
|
||||||
|
joined := false
|
||||||
|
for i, line := range ran {
|
||||||
|
if line == "network connect predecessor_default app" {
|
||||||
|
joined = true
|
||||||
|
if ran[i-1] != "container inspect --format {{.State.Running}}\t{{index .Config.Labels \""+specLabel+"\"}} app" &&
|
||||||
|
!strings.HasPrefix(ran[i-1], "container inspect") {
|
||||||
|
t.Errorf("joined before the container was read back as running: %v", ran)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
if !joined || report.Outcomes[0].Action != "created" {
|
||||||
|
t.Fatalf("the container did not join the kept network: %v\n%+v", ran, report.Outcomes)
|
||||||
|
}
|
||||||
|
|
||||||
|
connectFails, ran = true, nil
|
||||||
|
if _, _, err := Apply(context.Background(), archHost(t), d, store.State{}, store.OriginCarried, run, nil, nil); err == nil ||
|
||||||
|
!strings.Contains(err.Error(), "could not join the kept network predecessor_default") {
|
||||||
|
t.Fatalf("a network that cannot be joined was passed over: %v", err)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
var specOfLast string
|
||||||
|
|
||||||
|
// A module the mesh left out of a declaration is not a module the mesh removed (novox/hq ADR 0163,
|
||||||
|
// rule 6): what the host wrote for it stays, recorded and said; what it holds for it stays held.
|
||||||
|
// A module simply absent is removed as it always was.
|
||||||
|
func TestALeftOutModuleIsNeitherRemovedNorForgotten(t *testing.T) {
|
||||||
|
var removed []string
|
||||||
|
gone := map[string]bool{}
|
||||||
|
run := func(_ context.Context, name string, args ...string) (string, error) {
|
||||||
|
if name != "docker" {
|
||||||
|
return "", nil
|
||||||
|
}
|
||||||
|
switch args[0] {
|
||||||
|
case "info":
|
||||||
|
return "29.0.0\n", nil
|
||||||
|
case "rm":
|
||||||
|
removed = append(removed, args[len(args)-1])
|
||||||
|
gone[args[len(args)-1]] = true
|
||||||
|
case "container":
|
||||||
|
if gone[args[len(args)-1]] {
|
||||||
|
return "", errors.New("no such container")
|
||||||
|
}
|
||||||
|
return "true\tspec", nil
|
||||||
|
}
|
||||||
|
return "", nil
|
||||||
|
}
|
||||||
|
known := store.State{
|
||||||
|
Resources: []store.Applied{
|
||||||
|
{ID: "web.server", Type: "container", Target: "web", Origin: store.OriginDeclared},
|
||||||
|
{ID: "old.server", Type: "container", Target: "old", Origin: store.OriginDeclared},
|
||||||
|
},
|
||||||
|
Held: []store.Held{{ID: "web.page", Module: "web", Kind: "file", Target: "/srv/web/index.html"}},
|
||||||
|
}
|
||||||
|
d := parse(t, `{"declaration":1,"left_out":["web"],"resources":[
|
||||||
|
{"id":"notes.conf","type":"file","path":"`+t.TempDir()+`/notes.conf","content":"x"}
|
||||||
|
]}`)
|
||||||
|
report, state, err := Apply(context.Background(), archHost(t), d, known, store.OriginDeclared, run, nil, nil)
|
||||||
|
if err != nil {
|
||||||
|
t.Fatal(err)
|
||||||
|
}
|
||||||
|
if len(removed) != 1 || removed[0] != "old" {
|
||||||
|
t.Fatalf("removed %v; only the module that is absent goes", removed)
|
||||||
|
}
|
||||||
|
if _, kept := state.At("container", "web"); !kept {
|
||||||
|
t.Fatal("the left-out module's record was forgotten")
|
||||||
|
}
|
||||||
|
if _, held := state.HeldAt("web.page"); !held {
|
||||||
|
t.Fatal("the left-out module's hold was released")
|
||||||
|
}
|
||||||
|
said := false
|
||||||
|
for _, o := range report.Outcomes {
|
||||||
|
if o.ID == "web.server" && o.Action == "unchanged" && strings.Contains(o.Detail, "web was left out of this declaration by the mesh") {
|
||||||
|
said = true
|
||||||
|
}
|
||||||
|
if o.ID == "web.server" && o.Action != "unchanged" {
|
||||||
|
t.Errorf("the left-out module's container was %s", o.Action)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
if !said {
|
||||||
|
t.Fatalf("keeping the left-out module's container was not said: %+v", report.Outcomes)
|
||||||
|
}
|
||||||
|
}
|
||||||
@@ -0,0 +1,54 @@
|
|||||||
|
package apply
|
||||||
|
|
||||||
|
import (
|
||||||
|
"context"
|
||||||
|
"sort"
|
||||||
|
"strings"
|
||||||
|
|
||||||
|
"github.com/novox/mesh-host/internal/declaration"
|
||||||
|
"github.com/novox/mesh-host/internal/store"
|
||||||
|
)
|
||||||
|
|
||||||
|
// Strays is what runs on the machine that the mesh neither wrote nor holds (novox/hq ADR 0163):
|
||||||
|
// every container the runtime has that no record names and no hold names. The question nothing
|
||||||
|
// answered on 2026-09-23, when a renamed resource left its old container running for a day; asked
|
||||||
|
// on every apply now, and reported, so a thing left behind is seen the day it is left.
|
||||||
|
//
|
||||||
|
// Containers only, today. A listener nobody declared is harder to attribute to a thing, and the
|
||||||
|
// machine's own services are not strays; that account is issue 160's.
|
||||||
|
func Strays(ctx context.Context, run Runner, known store.State) ([]store.Stray, error) {
|
||||||
|
cri, err := containerRuntime(ctx, run)
|
||||||
|
if err != nil {
|
||||||
|
return nil, nil // a machine with no runtime has no containers to stray
|
||||||
|
}
|
||||||
|
out, err := run(ctx, cri, "ps", "-a", "--format", "{{.Names}}\t{{.Image}}\t{{.State}}")
|
||||||
|
if err != nil {
|
||||||
|
return nil, err
|
||||||
|
}
|
||||||
|
ours := map[string]bool{}
|
||||||
|
for _, r := range known.Resources {
|
||||||
|
if declaration.Type(r.Type) == declaration.TypeContainer {
|
||||||
|
ours[r.Target] = true
|
||||||
|
}
|
||||||
|
}
|
||||||
|
for _, h := range known.Held {
|
||||||
|
if h.Kind == string(declaration.TypeContainer) {
|
||||||
|
ours[h.Target] = true
|
||||||
|
}
|
||||||
|
}
|
||||||
|
var strays []store.Stray
|
||||||
|
for _, line := range strings.Split(strings.TrimSpace(out), "\n") {
|
||||||
|
parts := strings.Split(line, "\t")
|
||||||
|
name := strings.TrimSpace(parts[0])
|
||||||
|
if name == "" || ours[name] {
|
||||||
|
continue
|
||||||
|
}
|
||||||
|
detail := ""
|
||||||
|
if len(parts) > 2 {
|
||||||
|
detail = strings.TrimSpace(parts[1]) + ", " + strings.TrimSpace(parts[2])
|
||||||
|
}
|
||||||
|
strays = append(strays, store.Stray{Kind: string(declaration.TypeContainer), Name: name, Detail: detail})
|
||||||
|
}
|
||||||
|
sort.Slice(strays, func(i, j int) bool { return strays[i].Name < strays[j].Name })
|
||||||
|
return strays, nil
|
||||||
|
}
|
||||||
@@ -0,0 +1,79 @@
|
|||||||
|
package bootstrap
|
||||||
|
|
||||||
|
import (
|
||||||
|
"context"
|
||||||
|
"encoding/json"
|
||||||
|
"os"
|
||||||
|
"path/filepath"
|
||||||
|
"strings"
|
||||||
|
"testing"
|
||||||
|
"time"
|
||||||
|
)
|
||||||
|
|
||||||
|
// What genesis raises, it raises as the module that succeeds it declares — name, data directory
|
||||||
|
// and image — so the module adopts it by the found rule that already exists (novox/hq ADR 0163,
|
||||||
|
// rule 7; issue 090). The network is the one difference left: the bootstrap forge runs on the
|
||||||
|
// machine's network to reach the store on its loopback, and a take says so.
|
||||||
|
func TestGenesisRaisesTheForgeAsTheModuleDeclaresIt(t *testing.T) {
|
||||||
|
var ran [][]string
|
||||||
|
run := func(_ context.Context, name string, args ...string) (string, error) {
|
||||||
|
if name == "docker" && args[0] == "container" {
|
||||||
|
return "", nil // not raised yet
|
||||||
|
}
|
||||||
|
ran = append(ran, append([]string{name}, args...))
|
||||||
|
return "", nil
|
||||||
|
}
|
||||||
|
if err := raiseGiteaServer(context.Background(), run, time.Second, "pw", DefaultPorts(), quietly); err != nil {
|
||||||
|
t.Fatal(err)
|
||||||
|
}
|
||||||
|
var raised []string
|
||||||
|
for _, r := range ran {
|
||||||
|
if r[0] == "docker" && r[1] == "run" {
|
||||||
|
raised = r
|
||||||
|
}
|
||||||
|
}
|
||||||
|
line := strings.Join(raised, " ")
|
||||||
|
for _, want := range []string{"--name gitea ", "--volume " + giteaDataDir + ":/data", " " + giteaImage} {
|
||||||
|
if !strings.Contains(line+" ", want) {
|
||||||
|
t.Errorf("the forge is not raised with %q: %s", want, line)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
if giteaBootstrap != ForgeModule {
|
||||||
|
t.Errorf("the bootstrap forge is %q and the module names its container %q", giteaBootstrap, ForgeModule)
|
||||||
|
}
|
||||||
|
|
||||||
|
// Against the module's own manifest, where the catalogue is checked out beside this repository.
|
||||||
|
var manifest []byte
|
||||||
|
for _, candidate := range []string{"../../../mesh-catalog/modules/gitea/module.json", "../../../../../mesh-catalog/modules/gitea/module.json"} {
|
||||||
|
if raw, err := os.ReadFile(filepath.Clean(candidate)); err == nil {
|
||||||
|
manifest = raw
|
||||||
|
break
|
||||||
|
}
|
||||||
|
}
|
||||||
|
if manifest == nil {
|
||||||
|
t.Skip("the catalogue is not beside this checkout; the module's pin is not compared")
|
||||||
|
}
|
||||||
|
var m struct {
|
||||||
|
Resources []struct {
|
||||||
|
ID, Type, Name, Image string
|
||||||
|
Volumes []string
|
||||||
|
} `json:"resources"`
|
||||||
|
}
|
||||||
|
if err := json.Unmarshal(manifest, &m); err != nil {
|
||||||
|
t.Fatal(err)
|
||||||
|
}
|
||||||
|
for _, r := range m.Resources {
|
||||||
|
if r.Type != "container" || r.ID != "server" {
|
||||||
|
continue
|
||||||
|
}
|
||||||
|
if r.Name != giteaBootstrap {
|
||||||
|
t.Errorf("the module names its container %q; genesis raises %q", r.Name, giteaBootstrap)
|
||||||
|
}
|
||||||
|
if r.Image != giteaImage {
|
||||||
|
t.Errorf("the module pins %s; genesis raises %s — the two must move together", r.Image, giteaImage)
|
||||||
|
}
|
||||||
|
if len(r.Volumes) != 1 || !strings.HasSuffix(r.Volumes[0], ":/data") {
|
||||||
|
t.Errorf("the module mounts %v; genesis mounts %s:/data", r.Volumes, giteaDataDir)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
@@ -91,7 +91,7 @@ func TestARerunOfGenesisIsNotAMachineInUse(t *testing.T) {
|
|||||||
if err := store.Save(o.State, store.State{Resources: []store.Applied{{ID: "store", Type: "container", Target: "mesh-store"}}}); err != nil {
|
if err := store.Save(o.State, store.State{Resources: []store.Applied{{ID: "store", Type: "container", Target: "mesh-store"}}}); err != nil {
|
||||||
t.Fatal(err)
|
t.Fatal(err)
|
||||||
}
|
}
|
||||||
m := inUseRunner{ps: "mesh-gitea-server\t\n", ss: servingSockets}
|
m := inUseRunner{ps: giteaBootstrap + "\t\n", ss: servingSockets}
|
||||||
if err := RefuseAMachineInUse(context.Background(), o, m.run, quietly); err != nil {
|
if err := RefuseAMachineInUse(context.Background(), o, m.run, quietly); err != nil {
|
||||||
t.Errorf("what an earlier genesis raised was counted as a machine in use: %v", err)
|
t.Errorf("what an earlier genesis raised was counted as a machine in use: %v", err)
|
||||||
}
|
}
|
||||||
|
|||||||
@@ -25,11 +25,24 @@ const (
|
|||||||
// foundationStore is the foundation's postgres container — the mesh's own memory, raised from the
|
// foundationStore is the foundation's postgres container — the mesh's own memory, raised from the
|
||||||
// bundle. gitea's bootstrap database lives here too, so a mesh runs one postgres (issue 051).
|
// bundle. gitea's bootstrap database lives here too, so a mesh runs one postgres (issue 051).
|
||||||
foundationStore = "mesh-store"
|
foundationStore = "mesh-store"
|
||||||
// giteaBootstrap is the gitea server raised directly at genesis, before gitea is a module.
|
// giteaBootstrap is the gitea server raised directly at genesis, before gitea is a module —
|
||||||
giteaBootstrap = "mesh-gitea-server"
|
// under the name the gitea MODULE declares for its container, so the module finds it and holds
|
||||||
// giteaImage is the same upstream image the gitea module runs, pinned identically so the module
|
// it rather than raising a second forge beside it (novox/hq ADR 0163, rule 7; issue 090).
|
||||||
// adopts the running server rather than replacing it.
|
giteaBootstrap = "gitea"
|
||||||
giteaImage = "gitea/gitea@sha256:dfc61e347c8b582df918f4556401bf2cecdfbdb56c5282ae9488dd76fca3e41c"
|
// giteaImage is the image the gitea module declares for that container, pinned to the same
|
||||||
|
// digest, so taking the module over is not a downgrade and not an upgrade. **Moves with the
|
||||||
|
// module's pin**: the two are compared by a take, and a difference is said there — but a
|
||||||
|
// genesis that raised an older image than the module declares would be taken over as an
|
||||||
|
// upgrade on first push, which a forge holding the mesh's packages must not have done to it
|
||||||
|
// unannounced. Checked in TestGenesisRaisesTheForgeAsTheModuleDeclaresIt against the module's
|
||||||
|
// manifest where the catalogue is beside this checkout.
|
||||||
|
giteaImage = "gitea/gitea@sha256:87a67ee09d3ae0d1df5fda5dcda3e2a1f9236a45b0a59025d6e00e46adc43bef"
|
||||||
|
// giteaDataDir is where the module's `data` directory resolves on a machine with the default
|
||||||
|
// layout (<data root>/<module>/<id>, novox/hq ADR 0112): mounted at /data as the module mounts
|
||||||
|
// it, so the repositories, attachments and indexes the bootstrap forge accumulates are the
|
||||||
|
// module's the day it is taken — before this, the forge had no volume and its data was the
|
||||||
|
// container's, lost with it.
|
||||||
|
giteaDataDir = "/var/lib/gitea/data"
|
||||||
// packagesOrg is the npm owner: every module consumes `@novox/*` from this gitea org.
|
// packagesOrg is the npm owner: every module consumes `@novox/*` from this gitea org.
|
||||||
packagesOrg = "novox"
|
packagesOrg = "novox"
|
||||||
// packagesTeam is the org team whose members may read and write the org's packages.
|
// packagesTeam is the org team whose members may read and write the org's packages.
|
||||||
@@ -262,9 +275,13 @@ func raiseGiteaServer(ctx context.Context, run Runner, timeout time.Duration, db
|
|||||||
"run", "-d", "--name", giteaBootstrap,
|
"run", "-d", "--name", giteaBootstrap,
|
||||||
// Host network, like the control plane: it reaches the foundation store on the machine's
|
// Host network, like the control plane: it reaches the foundation store on the machine's
|
||||||
// loopback (where the store publishes 5432) and answers on the machine's own 3000, which is
|
// loopback (where the store publishes 5432) and answers on the machine's own 3000, which is
|
||||||
// where mesh-bootstrap and the builder's build containers look for it.
|
// where mesh-bootstrap and the builder's build containers look for it. The module runs
|
||||||
|
// bridged and publishes its ports; that is the one difference a take still has to say
|
||||||
|
// (ADR 0163, rule 7) — the data, the name and the image are the module's already.
|
||||||
"--network", "host",
|
"--network", "host",
|
||||||
"--restart", "unless-stopped",
|
"--restart", "unless-stopped",
|
||||||
|
// The module's data directory, so what the forge accumulates is the module's when taken.
|
||||||
|
"--volume", giteaDataDir + ":/data",
|
||||||
}, env...)
|
}, env...)
|
||||||
args = append(args, giteaImage)
|
args = append(args, giteaImage)
|
||||||
|
|
||||||
|
|||||||
@@ -940,6 +940,13 @@ type Container struct {
|
|||||||
// its siblings can name before any of them can resolve anything.
|
// its siblings can name before any of them can resolve anything.
|
||||||
Dns []string `json:"dns,omitempty"`
|
Dns []string `json:"dns,omitempty"`
|
||||||
|
|
||||||
|
// Networks are networks this container also joins once created, by name — a found network a
|
||||||
|
// per-machine setting keeps for a taken container (novox/hq ADR 0163, rule 4), so a
|
||||||
|
// neighbour that resolves it there keeps resolving it until the neighbour is taken too.
|
||||||
|
// Joined after creation, because a runtime starts a container on one network; part of the
|
||||||
|
// container's spec, so a network kept or let go recreates it.
|
||||||
|
Networks []string `json:"networks,omitempty"`
|
||||||
|
|
||||||
// IP is this container's address on its network, passed to the runtime unchanged.
|
// IP is this container's address on its network, passed to the runtime unchanged.
|
||||||
//
|
//
|
||||||
// Only meaningful on a user-defined network, and refused by the runtime elsewhere. Exists for
|
// Only meaningful on a user-defined network, and refused by the runtime elsewhere. Exists for
|
||||||
@@ -1032,6 +1039,16 @@ func (c *Container) validate(where string, _ bool) []string {
|
|||||||
"static address anywhere but a user-defined one")
|
"static address anywhere but a user-defined one")
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
for _, n := range c.Networks {
|
||||||
|
problems = append(problems, (&Network{Name: n}).validate(where+": networks", false)...)
|
||||||
|
if n == c.Network {
|
||||||
|
problems = append(problems, where+": networks names "+n+", which is already the container's network")
|
||||||
|
}
|
||||||
|
}
|
||||||
|
if len(c.Networks) > 0 && (c.RunOnce || c.Schedule != "") {
|
||||||
|
problems = append(problems, where+": networks is for a container that keeps running; a step "+
|
||||||
|
"runs and exits, and joins nothing afterwards")
|
||||||
|
}
|
||||||
return append(problems, checkImage(where, c.Image)...)
|
return append(problems, checkImage(where, c.Image)...)
|
||||||
}
|
}
|
||||||
|
|
||||||
@@ -1137,6 +1154,41 @@ type Declaration struct {
|
|||||||
// converged node — which is every node the mesh raised before adoption existed, and so the
|
// converged node — which is every node the mesh raised before adoption existed, and so the
|
||||||
// only form an older controller ever sends (novox/hq ADR 0100).
|
// only form an older controller ever sends (novox/hq ADR 0100).
|
||||||
Adoption *Adoption
|
Adoption *Adoption
|
||||||
|
|
||||||
|
// Sequence orders this declaration against every other the mesh has sent this node: each
|
||||||
|
// send is one higher than the last, assigned under the control plane's hold on the node
|
||||||
|
// (novox/hq 04-ISSUES/107). Zero is a declaration that carries no order — every one an older
|
||||||
|
// controller sent, and the bundle genesis applies — and a host makes no ordering claim about
|
||||||
|
// one of those.
|
||||||
|
//
|
||||||
|
// **The one property a declaration needs that its signature does not give it.** A signature
|
||||||
|
// says the mesh sent this; it cannot say the mesh sent it AFTER the one the host is holding.
|
||||||
|
// Before this, "older" was inferred from arrival within a batch and a 750ms window, and a
|
||||||
|
// backlog longer than the batch, or a slow broker, applied a declaration the mesh had already
|
||||||
|
// superseded.
|
||||||
|
Sequence int64
|
||||||
|
|
||||||
|
// LeftOut names the modules of this machine's set the mesh left out of this declaration,
|
||||||
|
// because a setting stored for one cannot compose with its definition (novox/hq ADR 0163,
|
||||||
|
// rule 6). A machine is told everything or nothing about what it IS told; this is what it is
|
||||||
|
// not told, said. The host keeps what it holds for a left-out module and touches none of
|
||||||
|
// what it wrote for it — its resources are absent from the declaration, and absence would
|
||||||
|
// otherwise read as removal.
|
||||||
|
LeftOut []string
|
||||||
|
}
|
||||||
|
|
||||||
|
// LeftOutModuleOf says which left-out module a recorded resource belongs to, if any: its id is the
|
||||||
|
// module's name, a dot, and the module's own id for it. A module's name may contain a dot, so the
|
||||||
|
// longest left-out name that prefixes the id wins; a false match keeps a thing an apply would
|
||||||
|
// otherwise remove, which is the conservative mistake.
|
||||||
|
func (d *Declaration) LeftOutModuleOf(id string) (string, bool) {
|
||||||
|
best := ""
|
||||||
|
for _, m := range d.LeftOut {
|
||||||
|
if strings.HasPrefix(id, m+".") && len(m) > len(best) {
|
||||||
|
best = m
|
||||||
|
}
|
||||||
|
}
|
||||||
|
return best, best != ""
|
||||||
}
|
}
|
||||||
|
|
||||||
// Adoption is a node's mode, as the controller records it: the node is adopted, and these are
|
// Adoption is a node's mode, as the controller records it: the node is adopted, and these are
|
||||||
@@ -1274,6 +1326,11 @@ type envelope struct {
|
|||||||
// a bug quietly strip a machine.
|
// a bug quietly strip a machine.
|
||||||
OwnsNothing bool `json:"owns_nothing,omitempty"`
|
OwnsNothing bool `json:"owns_nothing,omitempty"`
|
||||||
Resources []json.RawMessage `json:"resources"`
|
Resources []json.RawMessage `json:"resources"`
|
||||||
|
// Sequence is optional on the wire, so a controller that does not send one is still
|
||||||
|
// understood: absent reads as zero, which is "no ordering claimed" rather than "first".
|
||||||
|
Sequence int64 `json:"sequence,omitempty"`
|
||||||
|
// LeftOut is optional on the wire too, and absent when nothing was left out (ADR 0163).
|
||||||
|
LeftOut []string `json:"left_out,omitempty"`
|
||||||
}
|
}
|
||||||
|
|
||||||
func parse(raw []byte, allowActions bool) (*Declaration, error) {
|
func parse(raw []byte, allowActions bool) (*Declaration, error) {
|
||||||
@@ -1290,8 +1347,20 @@ func parse(raw []byte, allowActions bool) (*Declaration, error) {
|
|||||||
env.Version, Version)}}
|
env.Version, Version)}}
|
||||||
}
|
}
|
||||||
|
|
||||||
d := &Declaration{Version: env.Version, For: env.For, Adoption: env.Adoption}
|
d := &Declaration{Version: env.Version, For: env.For, Adoption: env.Adoption, Sequence: env.Sequence,
|
||||||
|
LeftOut: env.LeftOut}
|
||||||
var problems []string
|
var problems []string
|
||||||
|
if len(env.LeftOut) > 0 && allowActions {
|
||||||
|
// The bundle is carried with the binary and leaves nothing out: which module a setting
|
||||||
|
// stopped composing for is the mesh's record (ADR 0163).
|
||||||
|
problems = append(problems, "a carried bundle says modules were left out, and only the "+
|
||||||
|
"mesh can say that")
|
||||||
|
}
|
||||||
|
for _, m := range env.LeftOut {
|
||||||
|
if strings.TrimSpace(m) == "" {
|
||||||
|
problems = append(problems, "left_out names a module with no name")
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
if len(env.Resources) == 0 && !env.OwnsNothing {
|
if len(env.Resources) == 0 && !env.OwnsNothing {
|
||||||
problems = append(problems, "no resources. An empty declaration is a mistake, not a "+
|
problems = append(problems, "no resources. An empty declaration is a mistake, not a "+
|
||||||
|
|||||||
@@ -464,3 +464,43 @@ func TestAnExplicitlyEmptyDeclarationIsAccepted(t *testing.T) {
|
|||||||
t.Fatalf("an unmarked empty declaration must still be refused; got %v", err)
|
t.Fatalf("an unmarked empty declaration must still be refused; got %v", err)
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
|
// A container's kept networks are names, not its own network, and not for a step (novox/hq ADR
|
||||||
|
// 0163, rule 4); and the mesh may say which modules it left out, which a carried bundle may not.
|
||||||
|
func TestKeptNetworksAndLeftOutModulesAreReadStrictly(t *testing.T) {
|
||||||
|
pinnedImage := "postgres@sha256:" + strings.Repeat("a", 64)
|
||||||
|
d, err := Parse([]byte(`{"declaration":1,"left_out":["web"],"resources":[
|
||||||
|
{"id":"app","type":"container","name":"app","image":"` + pinnedImage + `","networks":["predecessor_default"]}
|
||||||
|
]}`))
|
||||||
|
if err != nil {
|
||||||
|
t.Fatal(err)
|
||||||
|
}
|
||||||
|
if got := d.Resources[0].(*Container).Networks; len(got) != 1 || got[0] != "predecessor_default" {
|
||||||
|
t.Fatalf("the kept network was not read: %v", got)
|
||||||
|
}
|
||||||
|
if m, left := d.LeftOutModuleOf("web.server"); !left || m != "web" {
|
||||||
|
t.Fatalf("web.server is not web's: %q %v", m, left)
|
||||||
|
}
|
||||||
|
if _, left := d.LeftOutModuleOf("webapp.server"); left {
|
||||||
|
t.Fatal("webapp.server was taken for web's")
|
||||||
|
}
|
||||||
|
for name, raw := range map[string]string{
|
||||||
|
"a bad network name": `{"declaration":1,"resources":[
|
||||||
|
{"id":"app","type":"container","name":"app","image":"` + pinnedImage + `","networks":["a/b"]}]}`,
|
||||||
|
"its own network": `{"declaration":1,"resources":[
|
||||||
|
{"id":"app","type":"container","name":"app","image":"` + pinnedImage + `","network":"own","networks":["own"]}]}`,
|
||||||
|
"a step": `{"declaration":1,"resources":[
|
||||||
|
{"id":"app","type":"container","name":"app","image":"` + pinnedImage + `","run-once":true,"networks":["x"]}]}`,
|
||||||
|
"a nameless module": `{"declaration":1,"left_out":[""],"resources":[
|
||||||
|
{"id":"app","type":"container","name":"app","image":"` + pinnedImage + `"}]}`,
|
||||||
|
} {
|
||||||
|
if _, err := Parse([]byte(raw)); err == nil {
|
||||||
|
t.Errorf("%s was accepted", name)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
if _, err := ParseTrusted([]byte(`{"declaration":1,"left_out":["web"],"resources":[
|
||||||
|
{"id":"app","type":"container","name":"app","image":"` + pinnedImage + `"}]}`)); err == nil ||
|
||||||
|
!strings.Contains(err.Error(), "only the mesh can say that") {
|
||||||
|
t.Fatalf("a carried bundle leaving modules out was accepted: %v", err)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|||||||
@@ -3,6 +3,7 @@ package link
|
|||||||
import (
|
import (
|
||||||
"context"
|
"context"
|
||||||
"crypto/rand"
|
"crypto/rand"
|
||||||
|
"crypto/sha256"
|
||||||
"encoding/hex"
|
"encoding/hex"
|
||||||
"errors"
|
"errors"
|
||||||
"fmt"
|
"fmt"
|
||||||
@@ -63,8 +64,15 @@ func presentNats(_ context.Context, to Approach, node, secret string,
|
|||||||
// subscribe its own inbox and nothing else (design 25 §6). The secret is its password, the same
|
// subscribe its own inbox and nothing else (design 25 §6). The secret is its password, the same
|
||||||
// string the request claims, so the server proves somebody holds the token and the request
|
// string the request claims, so the server proves somebody holds the token and the request
|
||||||
// proves the same thing to the controller without it having to ask the server who connected.
|
// proves the same thing to the controller without it having to ask the server who connected.
|
||||||
|
// **Its own inbox space, because that is the only one it may listen in** (novox/hq
|
||||||
|
// 04-ISSUES/146). A JetStream publish waits for the stream's acknowledgement on an inbox the
|
||||||
|
// client picks, and the client's default is `_INBOX.<random>` — which this user may not
|
||||||
|
// subscribe to, so the enrolment failed with a permissions violation on a subject nobody had
|
||||||
|
// chosen. The permission is `_INBOX.enrol.<node>.>` (design 25 §6), so the client is told to
|
||||||
|
// pick its inboxes there; the reply address below is in the same space for the same reason.
|
||||||
conn, err := nats.Connect(natsURL(to.Address),
|
conn, err := nats.Connect(natsURL(to.Address),
|
||||||
nats.Secure(config),
|
nats.Secure(config),
|
||||||
|
nats.CustomInboxPrefix("_INBOX.enrol."+node),
|
||||||
nats.UserInfo("enrol."+node, secret),
|
nats.UserInfo("enrol."+node, secret),
|
||||||
nats.Name("mesh-host/enrol/"+node),
|
nats.Name("mesh-host/enrol/"+node),
|
||||||
nats.Timeout(timeout),
|
nats.Timeout(timeout),
|
||||||
@@ -124,7 +132,19 @@ func (a *natsAsking) Ask(ctx context.Context, request []byte, wait time.Duration
|
|||||||
defer cancel()
|
defer cancel()
|
||||||
// Into the stream and awaited: an enrolment the bus never accepted must fail here rather than be
|
// Into the stream and awaited: an enrolment the bus never accepted must fail here rather than be
|
||||||
// assumed, because the node has nothing else to go on.
|
// assumed, because the node has nothing else to go on.
|
||||||
if _, err := a.js.Publish(EnrolSubject, addressed, nats.Context(publish)); err != nil {
|
//
|
||||||
|
// **Once, however many times it is sent** (novox/hq 04-ISSUES/146). The client re-publishes when
|
||||||
|
// an acknowledgement is slow, and the mesh enrolled the machine on each copy — minting a second
|
||||||
|
// credential, which replaced the first, which is the one the node had already been given. The
|
||||||
|
// machine then reconnected for ever as a user whose password the mesh had rotated out from under
|
||||||
|
// it, and the controller's log said "enrolled anchor" twice in the same second.
|
||||||
|
//
|
||||||
|
// The id is the message: the same bytes carry the same id, so the stream discards the client's
|
||||||
|
// own retry, and a genuine second attempt — which carries a new reply address — is a different
|
||||||
|
// message and is let through.
|
||||||
|
sum := sha256.Sum256(addressed)
|
||||||
|
if _, err := a.js.Publish(EnrolSubject, addressed,
|
||||||
|
nats.MsgId(hex.EncodeToString(sum[:])), nats.Context(publish)); err != nil {
|
||||||
return nil, fmt.Errorf("cannot ask the mesh to enrol this node: %w", err)
|
return nil, fmt.Errorf("cannot ask the mesh to enrol this node: %w", err)
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|||||||
@@ -0,0 +1,46 @@
|
|||||||
|
package link
|
||||||
|
|
||||||
|
import (
|
||||||
|
"strings"
|
||||||
|
"testing"
|
||||||
|
)
|
||||||
|
|
||||||
|
// The count that did not add up was the only symptom sixteen held resources had, and reading it meant
|
||||||
|
// opening the node's state file by hand (novox/hq 04-ISSUES/125). The line that says what an apply did
|
||||||
|
// says what it did not, too.
|
||||||
|
|
||||||
|
func TestTheApplyLineSaysWhatItHeldAndForWhichModule(t *testing.T) {
|
||||||
|
got := heldNote([]Held{
|
||||||
|
{ID: "ca", Module: "route-proxy", Kind: "directory"},
|
||||||
|
{ID: "certs", Module: "route-proxy", Kind: "directory"},
|
||||||
|
{ID: "server", Module: "route-proxy", Kind: "container"},
|
||||||
|
{ID: "mail", Module: "mailu", Kind: "container"},
|
||||||
|
})
|
||||||
|
if !strings.Contains(got, "4 held") {
|
||||||
|
t.Fatalf("the count of what was held is not in the line: %q", got)
|
||||||
|
}
|
||||||
|
// The module is the thing an operator can act on: `take` takes a module.
|
||||||
|
if !strings.Contains(got, "route-proxy: 3") || !strings.Contains(got, "mailu: 1") {
|
||||||
|
t.Fatalf("the line does not break the holds down by module: %q", got)
|
||||||
|
}
|
||||||
|
// Ordered, so two machines holding the same things read the same and a diff of two reports is
|
||||||
|
// about what changed.
|
||||||
|
if strings.Index(got, "mailu") > strings.Index(got, "route-proxy") {
|
||||||
|
t.Fatalf("modules are not in a stated order: %q", got)
|
||||||
|
}
|
||||||
|
// It says why, because "held" alone reads as a failure and this is correct behaviour.
|
||||||
|
if !strings.Contains(got, "taken") {
|
||||||
|
t.Fatalf("the line does not say a hold ends when the module is taken: %q", got)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
func TestAnApplyThatHeldNothingSaysNothingExtra(t *testing.T) {
|
||||||
|
// A converged machine holds nothing, which is most applies. Reporting "0 held" on every one of
|
||||||
|
// them is how a line stops being read.
|
||||||
|
if got := heldNote(nil); got != "" {
|
||||||
|
t.Fatalf("an apply with no holds added %q to its line", got)
|
||||||
|
}
|
||||||
|
if got := heldNote([]Held{}); got != "" {
|
||||||
|
t.Fatalf("an apply with no holds added %q to its line", got)
|
||||||
|
}
|
||||||
|
}
|
||||||
@@ -110,6 +110,15 @@ type Report struct {
|
|||||||
// and the mesh's up in its place, and where the found configuration's original was kept.
|
// and the mesh's up in its place, and where the found configuration's original was kept.
|
||||||
Tunnel *CarriedTunnel `json:"tunnel,omitempty"`
|
Tunnel *CarriedTunnel `json:"tunnel,omitempty"`
|
||||||
|
|
||||||
|
// Strays is what runs on the machine that the mesh neither wrote nor holds (novox/hq ADR
|
||||||
|
// 0163): containers nobody declared and nobody holds, the ones a cutover leaves behind.
|
||||||
|
Strays []Stray `json:"strays,omitempty"`
|
||||||
|
|
||||||
|
// Profile is what this machine can do, detected again by the apply that reports (novox/hq
|
||||||
|
// ADR 0161) — the same shape enrolment sends — so a capability gained or lost since enrolment,
|
||||||
|
// a network manager switched, reaches the mesh at the next push rather than never.
|
||||||
|
Profile map[string]any `json:"profile,omitempty"`
|
||||||
|
|
||||||
// Host is the version of the host that produced this report (novox/hq ADR 0141).
|
// Host is the version of the host that produced this report (novox/hq ADR 0141).
|
||||||
//
|
//
|
||||||
// Without it nothing can say a machine is behind, so "every machine current with its source"
|
// Without it nothing can say a machine is behind, so "every machine current with its source"
|
||||||
@@ -200,6 +209,16 @@ type Held struct {
|
|||||||
Changed string `json:"changed,omitempty"`
|
Changed string `json:"changed,omitempty"`
|
||||||
// Kept is where a file's original was kept.
|
// Kept is where a file's original was kept.
|
||||||
Kept string `json:"kept,omitempty"`
|
Kept string `json:"kept,omitempty"`
|
||||||
|
// Facts is the found thing beside what the module declares — what a take compares (novox/hq
|
||||||
|
// ADR 0163). The same shape the host keeps; the controller reads it as data.
|
||||||
|
Facts map[string]any `json:"facts,omitempty"`
|
||||||
|
}
|
||||||
|
|
||||||
|
// A Stray is a container the mesh neither wrote nor holds (ADR 0163).
|
||||||
|
type Stray struct {
|
||||||
|
Kind string `json:"kind"`
|
||||||
|
Name string `json:"name"`
|
||||||
|
Detail string `json:"detail,omitempty"`
|
||||||
}
|
}
|
||||||
|
|
||||||
// Reach is one thing reachable on the machine: a listening socket, or a published container port.
|
// Reach is one thing reachable on the machine: a listening socket, or a published container port.
|
||||||
|
|||||||
@@ -0,0 +1,50 @@
|
|||||||
|
package link
|
||||||
|
|
||||||
|
import (
|
||||||
|
"encoding/json"
|
||||||
|
"testing"
|
||||||
|
"time"
|
||||||
|
)
|
||||||
|
|
||||||
|
// The drain picked the last to arrive. A backlog longer than the batch, or a broker that split a
|
||||||
|
// burst, delivered a superseded declaration last (novox/hq 04-ISSUES/107).
|
||||||
|
|
||||||
|
func sequenced(t *testing.T, n int64) *said {
|
||||||
|
t.Helper()
|
||||||
|
inner, err := json.Marshal(map[string]any{"declaration": 1, "resources": []any{}, "sequence": n})
|
||||||
|
if err != nil {
|
||||||
|
t.Fatal(err)
|
||||||
|
}
|
||||||
|
body, err := json.Marshal(Signed{Declaration: inner, Signature: []byte("s")})
|
||||||
|
if err != nil {
|
||||||
|
t.Fatal(err)
|
||||||
|
}
|
||||||
|
return &said{body: body}
|
||||||
|
}
|
||||||
|
|
||||||
|
func TestTheDrainKeepsTheHighestSequenceNotTheLastToArrive(t *testing.T) {
|
||||||
|
waiting := make(chan Declaration, 8)
|
||||||
|
waiting <- sequenced(t, 9)
|
||||||
|
waiting <- sequenced(t, 4) // arrived last, composed earlier
|
||||||
|
latest, aside := newest(waiting, sequenced(t, 8), 30*time.Millisecond)
|
||||||
|
if got := sequenceOf(latest.Body()); got != 9 {
|
||||||
|
t.Fatalf("the drain kept sequence %d, and 9 was waiting", got)
|
||||||
|
}
|
||||||
|
if len(aside) != 2 {
|
||||||
|
t.Fatalf("%d set aside, wanted 2 (the 8 and the late 4)", len(aside))
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
func TestWithoutSequencesTheLastToArriveStillWins(t *testing.T) {
|
||||||
|
// The behaviour this had before, kept for a controller that sends no order.
|
||||||
|
apply, aside := newest(arriving("two", "three"), &said{body: []byte("one")}, 30*time.Millisecond)
|
||||||
|
if string(apply.Body()) != "three" || len(aside) != 2 {
|
||||||
|
t.Fatalf("applied %q with %d set aside", apply.Body(), len(aside))
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
func TestAnUnreadableBodyClaimsNoOrder(t *testing.T) {
|
||||||
|
if got := sequenceOf([]byte("not json")); got != 0 {
|
||||||
|
t.Fatalf("garbage claimed sequence %d", got)
|
||||||
|
}
|
||||||
|
}
|
||||||
+14
-3
@@ -73,8 +73,19 @@ func PinnedConfig(pin string) (*tls.Config, error) {
|
|||||||
}, nil
|
}, nil
|
||||||
}
|
}
|
||||||
|
|
||||||
// Dial opens a TLS connection to the broker, refusing anything but the pinned certificate.
|
// dialPinned completes a TLS handshake against an address, refusing anything but the pinned
|
||||||
func Dial(address, pin string, timeout time.Duration) (*tls.Conn, error) {
|
// certificate.
|
||||||
|
//
|
||||||
|
// **Not how the bus is reached, and it used to be** (novox/hq 04-ISSUES/146). Enrolment opened one
|
||||||
|
// of these before it said anything, which was right while the broker answered TLS immediately and
|
||||||
|
// wrong the moment the mesh moved to a bus that speaks its own protocol first. The pin itself was
|
||||||
|
// never the problem — PinnedConfig is what the NATS client is given, and the verification runs
|
||||||
|
// inside the handshake that client performs.
|
||||||
|
//
|
||||||
|
// It stays here because this is where the pin is proven: the tests beside it run a real TLS server
|
||||||
|
// and assert that a wrong certificate is refused before a byte of application data is sent. What it
|
||||||
|
// must not become again is something a caller uses to reach the bus.
|
||||||
|
func dialPinned(address, pin string, timeout time.Duration) (*tls.Conn, error) {
|
||||||
config, err := PinnedConfig(pin)
|
config, err := PinnedConfig(pin)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
return nil, err
|
return nil, err
|
||||||
@@ -86,7 +97,7 @@ func Dial(address, pin string, timeout time.Duration) (*tls.Conn, error) {
|
|||||||
if errors.Is(err, ErrWrongCertificate) {
|
if errors.Is(err, ErrWrongCertificate) {
|
||||||
return nil, err
|
return nil, err
|
||||||
}
|
}
|
||||||
return nil, fmt.Errorf("cannot reach the broker at %s: %w", address, err)
|
return nil, fmt.Errorf("cannot reach %s: %w", address, err)
|
||||||
}
|
}
|
||||||
return conn, nil
|
return conn, nil
|
||||||
}
|
}
|
||||||
|
|||||||
@@ -63,7 +63,7 @@ func server(t *testing.T) (address string, fingerprint string) {
|
|||||||
|
|
||||||
func TestTheRightBrokerIsAccepted(t *testing.T) {
|
func TestTheRightBrokerIsAccepted(t *testing.T) {
|
||||||
address, pin := server(t)
|
address, pin := server(t)
|
||||||
conn, err := Dial(address, pin, 5*time.Second)
|
conn, err := dialPinned(address, pin, 5*time.Second)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
t.Fatalf("the broker its token describes was refused: %v", err)
|
t.Fatalf("the broker its token describes was refused: %v", err)
|
||||||
}
|
}
|
||||||
@@ -76,7 +76,7 @@ func TestADifferentBrokerIsRefused(t *testing.T) {
|
|||||||
address, _ := server(t)
|
address, _ := server(t)
|
||||||
_, other := server(t)
|
_, other := server(t)
|
||||||
|
|
||||||
_, err := Dial(address, other, 5*time.Second)
|
_, err := dialPinned(address, other, 5*time.Second)
|
||||||
if err == nil {
|
if err == nil {
|
||||||
t.Fatal("a broker presenting a different certificate was accepted")
|
t.Fatal("a broker presenting a different certificate was accepted")
|
||||||
}
|
}
|
||||||
@@ -130,7 +130,7 @@ func TestNothingIsSentToTheWrongBroker(t *testing.T) {
|
|||||||
|
|
||||||
// A pin for a certificate this server does not have.
|
// A pin for a certificate this server does not have.
|
||||||
_, elsewhere := server(t)
|
_, elsewhere := server(t)
|
||||||
if _, err := Dial(listener.Addr().String(), elsewhere, 5*time.Second); err == nil {
|
if _, err := dialPinned(listener.Addr().String(), elsewhere, 5*time.Second); err == nil {
|
||||||
t.Fatal("the impostor was accepted")
|
t.Fatal("the impostor was accepted")
|
||||||
}
|
}
|
||||||
if n := <-received; n > 0 {
|
if n := <-received; n > 0 {
|
||||||
@@ -160,7 +160,7 @@ func TestAnUnreachableBrokerIsAnOrdinaryFailure(t *testing.T) {
|
|||||||
address := listener.Addr().String()
|
address := listener.Addr().String()
|
||||||
listener.Close()
|
listener.Close()
|
||||||
|
|
||||||
_, err = Dial(address, pin, 2*time.Second)
|
_, err = dialPinned(address, pin, 2*time.Second)
|
||||||
if err == nil {
|
if err == nil {
|
||||||
t.Fatal("dialling a closed port succeeded")
|
t.Fatal("dialling a closed port succeeded")
|
||||||
}
|
}
|
||||||
|
|||||||
+67
-2
@@ -6,6 +6,8 @@ import (
|
|||||||
"encoding/json"
|
"encoding/json"
|
||||||
"errors"
|
"errors"
|
||||||
"fmt"
|
"fmt"
|
||||||
|
"sort"
|
||||||
|
"strings"
|
||||||
"time"
|
"time"
|
||||||
)
|
)
|
||||||
|
|
||||||
@@ -250,9 +252,11 @@ func Run(ctx context.Context, m Membership, apply Applier, say Announce, timeout
|
|||||||
case report.Refused != "":
|
case report.Refused != "":
|
||||||
say("refused a declaration: " + report.Refused)
|
say("refused a declaration: " + report.Refused)
|
||||||
case len(report.Failed) > 0:
|
case len(report.Failed) > 0:
|
||||||
say(fmt.Sprintf("applied %d and failed: %v", len(report.Applied), report.Failed))
|
say(fmt.Sprintf("applied %d and failed: %v%s",
|
||||||
|
len(report.Applied), report.Failed, heldNote(report.Held)))
|
||||||
default:
|
default:
|
||||||
say(fmt.Sprintf("applied %d resource(s)", len(report.Applied)))
|
say(fmt.Sprintf("applied %d resource(s)%s",
|
||||||
|
len(report.Applied), heldNote(report.Held)))
|
||||||
}
|
}
|
||||||
publishReport(ctx, link, m, report, say, timeout)
|
publishReport(ctx, link, m, report, say, timeout)
|
||||||
// Settled after the report is published. A node that dies between applying and
|
// Settled after the report is published. A node that dies between applying and
|
||||||
@@ -296,6 +300,16 @@ func newest(arriving <-chan Declaration, first Declaration, window time.Duration
|
|||||||
if !ok {
|
if !ok {
|
||||||
return latest, superseded
|
return latest, superseded
|
||||||
}
|
}
|
||||||
|
// **By sequence when both carry one, by arrival when either does not** (novox/hq
|
||||||
|
// 04-ISSUES/107). Arrival is what this window had to go on, and it is wrong exactly
|
||||||
|
// when it matters — a backlog drained out of order. A declaration that says where it
|
||||||
|
// stands is believed over when it turned up; one that does not is the older
|
||||||
|
// controller's, and arrival is all there is.
|
||||||
|
if sequenceOf(next.Body()) < sequenceOf(latest.Body()) &&
|
||||||
|
sequenceOf(next.Body()) > 0 && sequenceOf(latest.Body()) > 0 {
|
||||||
|
superseded = append(superseded, next)
|
||||||
|
continue
|
||||||
|
}
|
||||||
superseded = append(superseded, latest)
|
superseded = append(superseded, latest)
|
||||||
latest = next
|
latest = next
|
||||||
case <-time.After(window):
|
case <-time.After(window):
|
||||||
@@ -304,6 +318,24 @@ func newest(arriving <-chan Declaration, first Declaration, window time.Duration
|
|||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
|
// sequenceOf is the order a signed declaration claims, or zero when it claims none or cannot be
|
||||||
|
// read. Read from the envelope alone; the signature is verified later, when the winner is applied,
|
||||||
|
// and a forged message that lied about its sequence would only set aside real ones — which are
|
||||||
|
// reported as set aside, and the next push sends the current one again.
|
||||||
|
func sequenceOf(body []byte) int64 {
|
||||||
|
var signed Signed
|
||||||
|
if err := json.Unmarshal(body, &signed); err != nil {
|
||||||
|
return 0
|
||||||
|
}
|
||||||
|
var d struct {
|
||||||
|
Sequence int64 `json:"sequence"`
|
||||||
|
}
|
||||||
|
if err := json.Unmarshal(signed.Declaration, &d); err != nil {
|
||||||
|
return 0
|
||||||
|
}
|
||||||
|
return d.Sequence
|
||||||
|
}
|
||||||
|
|
||||||
// declaredIn is the id a signed declaration carries, for a report about one that was not applied.
|
// declaredIn is the id a signed declaration carries, for a report about one that was not applied.
|
||||||
// Empty if the message is not one — a forged or garbled message is refused by handleBody when its
|
// Empty if the message is not one — a forged or garbled message is refused by handleBody when its
|
||||||
// turn comes; here it is only named.
|
// turn comes; here it is only named.
|
||||||
@@ -392,3 +424,36 @@ func publishAlive(ctx context.Context, bus Bus, m Membership, say Announce,
|
|||||||
say("could not tell the mesh this node is here: " + err.Error())
|
say("could not tell the mesh this node is here: " + err.Error())
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
|
// heldNote is what this apply did NOT do, for the line that says what it did.
|
||||||
|
//
|
||||||
|
// **A count that does not add up is the only symptom a held resource had** (novox/hq 04-ISSUES/125).
|
||||||
|
// An adopted node keeps what it found until its module is taken (ADR 0100), and that is correct — but
|
||||||
|
// it was recorded only in the node's own state file. On the edge cut-over the mesh sent 346 resources,
|
||||||
|
// the journal said it applied 330, and nothing anywhere said which sixteen or why. Reading it took
|
||||||
|
// opening state.json by hand; not reading it took every public name on the machine down, because the
|
||||||
|
// operator had four green surfaces and a discrepancy nobody could interpret.
|
||||||
|
//
|
||||||
|
// So the line that reports the apply carries it. Grouped by module and ordered by name, because the
|
||||||
|
// sentence an operator needs is "route-proxy is assigned and not taken", and the module is the thing
|
||||||
|
// they can act on — `take` is the verb, and it takes a module.
|
||||||
|
func heldNote(held []Held) string {
|
||||||
|
if len(held) == 0 {
|
||||||
|
return ""
|
||||||
|
}
|
||||||
|
byModule := map[string]int{}
|
||||||
|
for _, h := range held {
|
||||||
|
byModule[h.Module]++
|
||||||
|
}
|
||||||
|
names := make([]string, 0, len(byModule))
|
||||||
|
for name := range byModule {
|
||||||
|
names = append(names, name)
|
||||||
|
}
|
||||||
|
sort.Strings(names)
|
||||||
|
parts := make([]string, 0, len(names))
|
||||||
|
for _, name := range names {
|
||||||
|
parts = append(parts, fmt.Sprintf("%s: %d", name, byModule[name]))
|
||||||
|
}
|
||||||
|
return fmt.Sprintf(", %d held until their module is taken (%s)",
|
||||||
|
len(held), strings.Join(parts, ", "))
|
||||||
|
}
|
||||||
|
|||||||
@@ -20,6 +20,14 @@ const (
|
|||||||
// state: whether one IS running. Assignment needs the first.
|
// state: whether one IS running. Assignment needs the first.
|
||||||
CapSeat = "seat"
|
CapSeat = "seat"
|
||||||
CapPrivileged = "privileged"
|
CapPrivileged = "privileged"
|
||||||
|
|
||||||
|
// The network manager this machine runs, one capability per dialect (novox/hq ADR 0161): the
|
||||||
|
// uplink seat's holder declares its own, so the holder for a manager the machine does not run
|
||||||
|
// is refused the way any missing capability is, naming it. Active, not installed — a machine
|
||||||
|
// may have two of these on disk and runs one.
|
||||||
|
CapUplinkNetworkManager = "uplink-networkmanager"
|
||||||
|
CapUplinkSystemdNetworkd = "uplink-systemd-networkd"
|
||||||
|
CapUplinkDhcpcd = "uplink-dhcpcd"
|
||||||
)
|
)
|
||||||
|
|
||||||
// commandCapability is the shape most detectors take: run something, and treat a working
|
// commandCapability is the shape most detectors take: run something, and treat a working
|
||||||
@@ -202,6 +210,21 @@ func Default(runner Runner) []Detector {
|
|||||||
why: "asks the kernel for interfaces — needs the module, not just the tool",
|
why: "asks the kernel for interfaces — needs the module, not just the tool",
|
||||||
runner: runner,
|
runner: runner,
|
||||||
},
|
},
|
||||||
|
commandCapability{
|
||||||
|
name: CapUplinkNetworkManager, command: "systemctl", args: []string{"is-active", "NetworkManager.service"},
|
||||||
|
why: "asks the init whether NetworkManager is running — the dialect the uplink seat's holder must speak",
|
||||||
|
runner: runner,
|
||||||
|
},
|
||||||
|
commandCapability{
|
||||||
|
name: CapUplinkSystemdNetworkd, command: "systemctl", args: []string{"is-active", "systemd-networkd.service"},
|
||||||
|
why: "asks the init whether systemd-networkd is running — the dialect the uplink seat's holder must speak",
|
||||||
|
runner: runner,
|
||||||
|
},
|
||||||
|
commandCapability{
|
||||||
|
name: CapUplinkDhcpcd, command: "systemctl", args: []string{"is-active", "dhcpcd.service"},
|
||||||
|
why: "asks the init whether dhcpcd is running — the dialect the uplink seat's holder must speak",
|
||||||
|
runner: runner,
|
||||||
|
},
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|||||||
@@ -0,0 +1,39 @@
|
|||||||
|
package profile
|
||||||
|
|
||||||
|
import (
|
||||||
|
"context"
|
||||||
|
"errors"
|
||||||
|
"testing"
|
||||||
|
)
|
||||||
|
|
||||||
|
// The uplink seat's holder must be the dialect the machine runs (novox/hq ADR 0161): the profile
|
||||||
|
// names the network manager found active, one capability per manager, and nothing for one that is
|
||||||
|
// merely installed.
|
||||||
|
func TestTheProfileNamesTheNetworkManagerThatIsRunning(t *testing.T) {
|
||||||
|
runner := func(_ context.Context, name string, args ...string) (string, error) {
|
||||||
|
if name == "systemctl" && len(args) == 2 && args[0] == "is-active" {
|
||||||
|
if args[1] == "NetworkManager.service" {
|
||||||
|
return "active\n", nil
|
||||||
|
}
|
||||||
|
return "inactive\n", errors.New("exit status 3")
|
||||||
|
}
|
||||||
|
return "", errors.New("not here")
|
||||||
|
}
|
||||||
|
var have []Detector
|
||||||
|
for _, d := range Default(Runner(runner)) {
|
||||||
|
switch d.Name() {
|
||||||
|
case CapUplinkNetworkManager, CapUplinkSystemdNetworkd, CapUplinkDhcpcd:
|
||||||
|
have = append(have, d)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
if len(have) != 3 {
|
||||||
|
t.Fatalf("expected a detector per manager, found %d", len(have))
|
||||||
|
}
|
||||||
|
for _, d := range have {
|
||||||
|
v := d.Detect(context.Background())
|
||||||
|
want := d.Name() == CapUplinkNetworkManager
|
||||||
|
if v.Present != want {
|
||||||
|
t.Errorf("%s: present=%v, want %v (%s)", d.Name(), v.Present, want, v.Detail)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
@@ -0,0 +1,29 @@
|
|||||||
|
package store
|
||||||
|
|
||||||
|
import "testing"
|
||||||
|
|
||||||
|
// A resource whose target moves leaves what the host wrote under the old target on record as a
|
||||||
|
// former one, undeclared by construction, so the next apply removes it (novox/hq issue 097, ADR 0163).
|
||||||
|
func TestARecordWhoseTargetMovedKeepsTheFormerTargetToRemove(t *testing.T) {
|
||||||
|
s := State{}
|
||||||
|
s.Record(Applied{ID: "gitea.server", Type: "container", Target: "mesh-gitea", Origin: OriginDeclared})
|
||||||
|
s.Record(Applied{ID: "gitea.server", Type: "container", Target: "gitea", Origin: OriginDeclared})
|
||||||
|
if len(s.Resources) != 2 {
|
||||||
|
t.Fatalf("a moved target produced %d record(s): %+v", len(s.Resources), s.Resources)
|
||||||
|
}
|
||||||
|
orphans := s.Orphans(map[string]bool{"gitea.server": true}, OriginDeclared)
|
||||||
|
if len(orphans) != 1 || orphans[0].Target != "mesh-gitea" || !IsFormer(orphans[0].ID) {
|
||||||
|
t.Fatalf("the former target is not an orphan to remove: %+v", orphans)
|
||||||
|
}
|
||||||
|
s.Forget(orphans[0].ID)
|
||||||
|
if len(s.Resources) != 1 || s.Resources[0].Target != "gitea" {
|
||||||
|
t.Fatalf("forgetting the former target touched the current one: %+v", s.Resources)
|
||||||
|
}
|
||||||
|
// The same target again is not a move; a carried record is not the host's to remove.
|
||||||
|
s.Record(Applied{ID: "gitea.server", Type: "container", Target: "gitea", Origin: OriginDeclared})
|
||||||
|
s.Record(Applied{ID: "bundle", Type: "file", Target: "/a"})
|
||||||
|
s.Record(Applied{ID: "bundle", Type: "file", Target: "/b"})
|
||||||
|
if len(s.Resources) != 2 {
|
||||||
|
t.Fatalf("an unmoved or carried record grew the list: %+v", s.Resources)
|
||||||
|
}
|
||||||
|
}
|
||||||
@@ -18,6 +18,7 @@ import (
|
|||||||
"os"
|
"os"
|
||||||
"path/filepath"
|
"path/filepath"
|
||||||
"sort"
|
"sort"
|
||||||
|
"strings"
|
||||||
"time"
|
"time"
|
||||||
)
|
)
|
||||||
|
|
||||||
@@ -274,6 +275,41 @@ type Held struct {
|
|||||||
// reverted: that is how a predecessor still writing is caught.
|
// reverted: that is how a predecessor still writing is caught.
|
||||||
Changed string `json:"changed,omitempty"`
|
Changed string `json:"changed,omitempty"`
|
||||||
ChangedAt time.Time `json:"changed_at,omitempty"`
|
ChangedAt time.Time `json:"changed_at,omitempty"`
|
||||||
|
// Facts is what a take would compare: the found thing beside what the module declares
|
||||||
|
// (novox/hq ADR 0163). Read fresh on every apply while held, so the controller's preview
|
||||||
|
// speaks of the machine as it is.
|
||||||
|
Facts *Facts `json:"facts,omitempty"`
|
||||||
|
}
|
||||||
|
|
||||||
|
// Facts is a held thing beside what its module declares — what a take compares (ADR 0163).
|
||||||
|
type Facts struct {
|
||||||
|
// A found container: the image it runs and when that image was made; the networks it is on
|
||||||
|
// and the other containers on each; what it mounts; what it publishes.
|
||||||
|
Image string `json:"image,omitempty"`
|
||||||
|
ImageCreated string `json:"image_created,omitempty"`
|
||||||
|
Networks map[string][]string `json:"networks,omitempty"`
|
||||||
|
Mounts []string `json:"mounts,omitempty"`
|
||||||
|
Ports []string `json:"ports,omitempty"`
|
||||||
|
// What the module declares for it, and the declared image's creation date when the image
|
||||||
|
// is on the machine already.
|
||||||
|
DeclaredImage string `json:"declared_image,omitempty"`
|
||||||
|
DeclaredImageCreated string `json:"declared_image_created,omitempty"`
|
||||||
|
DeclaredPorts []string `json:"declared_ports,omitempty"`
|
||||||
|
DeclaredVolumes []string `json:"declared_volumes,omitempty"`
|
||||||
|
// Downgrade is true when both creation dates are known and the declared image is the older.
|
||||||
|
Downgrade bool `json:"downgrade,omitempty"`
|
||||||
|
// A found file: whether the declared content differs from what was found, and how, as lines
|
||||||
|
// only in the found file (-) and lines only in the declared one (+), bounded.
|
||||||
|
Differs bool `json:"differs,omitempty"`
|
||||||
|
Difference []string `json:"difference,omitempty"`
|
||||||
|
}
|
||||||
|
|
||||||
|
// A Stray is something running on the machine that the mesh neither wrote nor holds
|
||||||
|
// (novox/hq ADR 0163): the answer to "what is here that nobody asked for".
|
||||||
|
type Stray struct {
|
||||||
|
Kind string `json:"kind"`
|
||||||
|
Name string `json:"name"`
|
||||||
|
Detail string `json:"detail,omitempty"`
|
||||||
}
|
}
|
||||||
|
|
||||||
// Recorded reports whether this host has a record, of any origin, of putting something of this
|
// Recorded reports whether this host has a record, of any origin, of putting something of this
|
||||||
@@ -462,6 +498,20 @@ func Save(path string, s State) error {
|
|||||||
func (s *State) Record(a Applied) {
|
func (s *State) Record(a Applied) {
|
||||||
for i, existing := range s.Resources {
|
for i, existing := range s.Resources {
|
||||||
if existing.ID == a.ID {
|
if existing.ID == a.ID {
|
||||||
|
// A resource whose target moved leaves what the host wrote under the old target
|
||||||
|
// behind — a container under the old name, a file at the old path. Rewriting the
|
||||||
|
// record would erase the only trace of it (novox/hq issue 097, ADR 0163), so the old
|
||||||
|
// target stays on record as a former one, undeclared by construction, until the next
|
||||||
|
// apply removes it the way it removes anything the host wrote and no longer declares.
|
||||||
|
// What was found is held, never recorded here, and so never removed by this.
|
||||||
|
if originOf(existing) == OriginDeclared && existing.Target != "" && a.Target != "" &&
|
||||||
|
existing.Target != a.Target && existing.Type == a.Type {
|
||||||
|
former := existing
|
||||||
|
former.ID = FormerID(existing.ID, existing.Target)
|
||||||
|
s.Resources[i] = a
|
||||||
|
s.Resources = append(s.Resources, former)
|
||||||
|
return
|
||||||
|
}
|
||||||
s.Resources[i] = a
|
s.Resources[i] = a
|
||||||
return
|
return
|
||||||
}
|
}
|
||||||
@@ -469,6 +519,13 @@ func (s *State) Record(a Applied) {
|
|||||||
s.Resources = append(s.Resources, a)
|
s.Resources = append(s.Resources, a)
|
||||||
}
|
}
|
||||||
|
|
||||||
|
// FormerID names the record of a resource's former target: the resource's id and the target it
|
||||||
|
// had, so the record is distinct from the current one and is never what a declaration names.
|
||||||
|
func FormerID(id, target string) string { return id + "@former:" + target }
|
||||||
|
|
||||||
|
// IsFormer says whether a record names a former target.
|
||||||
|
func IsFormer(id string) bool { return strings.Contains(id, "@former:") }
|
||||||
|
|
||||||
// Forget drops a resource from what the node owns.
|
// Forget drops a resource from what the node owns.
|
||||||
func (s *State) Forget(id string) {
|
func (s *State) Forget(id string) {
|
||||||
kept := s.Resources[:0]
|
kept := s.Resources[:0]
|
||||||
|
|||||||
+32
File diff suppressed because one or more lines are too long
@@ -0,0 +1,48 @@
|
|||||||
|
package packaging_test
|
||||||
|
|
||||||
|
import (
|
||||||
|
"encoding/json"
|
||||||
|
"os"
|
||||||
|
"testing"
|
||||||
|
)
|
||||||
|
|
||||||
|
// The mesh delivers the launcher, so the manifest carries a copy of it (novox/hq 04-ISSUES/142).
|
||||||
|
//
|
||||||
|
// **Two copies of one script is a drift waiting to happen**, and the only reason to accept it is that
|
||||||
|
// a file resource is written atomically — temp file, then rename — while an archive writes in place
|
||||||
|
// with truncate. The running launcher keeps the inode it was started from and the next start picks up
|
||||||
|
// the new one; unpacking an archive over it would truncate the file a running shell is reading.
|
||||||
|
//
|
||||||
|
// So: two copies, and this is the check that they are the same one.
|
||||||
|
func TestTheManifestCarriesTheLauncherExactly(t *testing.T) {
|
||||||
|
onDisk, err := os.ReadFile("nox-mesh-host-launch")
|
||||||
|
if err != nil {
|
||||||
|
t.Fatal(err)
|
||||||
|
}
|
||||||
|
raw, err := os.ReadFile("../module.json")
|
||||||
|
if err != nil {
|
||||||
|
t.Fatal(err)
|
||||||
|
}
|
||||||
|
var manifest struct {
|
||||||
|
Resources []struct {
|
||||||
|
ID string `json:"id"`
|
||||||
|
Content string `json:"content"`
|
||||||
|
} `json:"resources"`
|
||||||
|
}
|
||||||
|
if err := json.Unmarshal(raw, &manifest); err != nil {
|
||||||
|
t.Fatal(err)
|
||||||
|
}
|
||||||
|
for _, r := range manifest.Resources {
|
||||||
|
if r.ID != "launcher" {
|
||||||
|
continue
|
||||||
|
}
|
||||||
|
if r.Content != string(onDisk) {
|
||||||
|
t.Fatal("the launcher the mesh would deliver is not the launcher in this repository. " +
|
||||||
|
"Copy packaging/nox-mesh-host-launch into module.json's `launcher` resource — the " +
|
||||||
|
"machines run what the manifest says, and this file is what gets reviewed")
|
||||||
|
}
|
||||||
|
return
|
||||||
|
}
|
||||||
|
t.Fatal("module.json declares no `launcher` resource, so nothing delivers the launcher and a " +
|
||||||
|
"delivered host version is never started")
|
||||||
|
}
|
||||||
Reference in New Issue
Block a user