Compare commits

...
Author SHA1 Message Date
jschoubben 2c2eb51878 Only CONSUMER.INFO was missing from a machine's grants; the rest was already there 2026-09-28 01:17:40 +02:00
jschoubben aa2d0b51ea Golden: a machine's user may bind its consumer, ack, and hear its inbox 2026-09-28 01:17:15 +02:00
jschoubben 64d154d9d7 A machine may bind its consumer and hear the answer
Binding to a consumer asks the server about it and hears the answer on the
client's inbox; hearing a declaration acknowledges it. A machine's user was granted
none of that and was refused the first time one dialled a permissioned server:
"this node cannot read its declarations". Its inbox is its own prefix, which the
host now sets.
2026-09-28 01:16:46 +02:00
jschoubben ffa390f916 Merge pull request 'The mint leaves the control plane's old-bus secret alone' (#101) from fix/mint-leaves-the-control-planes-old-secret-alone into main 2026-09-27 23:08:35 +00:00
jschoubben 4d62e6caf1 The mint leaves the control plane's old-bus secret alone
The control plane is a module too, and its broker secret is the old bus's
credential it is still using while the mint runs. Writing the new bus's blob there
cut the mesh off from its own old bus mid-move. Its new-bus credential is the
controller principal's bus secret; the module principal is skipped.
2026-09-28 01:08:11 +02:00
jschoubben 386ae676ca Merge pull request 'The control plane mounts the bus secret it reads' (#100) from fix/the-controller-mounts-its-bus-secret into main 2026-09-27 23:03:42 +00:00
jschoubben f8a9c3d6bc The control plane mounts the bus secret it reads
MESH_BUS_NATS_FILE named /run/secrets/bus and nothing put a file there: the
manifest binds each secret explicitly, and the switch added the secret and the
variable but not the bind. Found live — the control plane came up on the new bus
and could not read its own credential.
2026-09-28 01:03:18 +02:00
jschoubben 83671fae5f Merge pull request 'The network map resolves each machine with the seat holders on record' (#99) from fix/the-network-map-knows-the-holders into main 2026-09-27 22:56:55 +00:00
jschoubben 9b715524a2 The network map resolves each machine with the seat holders on record
Without them, a machine running the next holder of a seat beside the current one
resolves as two holders, is refused, and drops out of the map — and with it the
address every other machine composes for what it offers. Found live: the control
node vanished from the private network the moment the new bus was assigned beside
the old one, and nothing on any machine could be composed.
2026-09-28 00:55:39 +02:00
jschoubben e06fc1ed16 Merge pull request 'The control plane speaks the new bus' (#98) from switch/the-controller-speaks-nats into main 2026-09-27 22:38:27 +00:00
jschoubben 13d7c5c5dd Merge pull request 'The mint names the bus by bare host, and can mint again' (#97) from fix/mint-bare-host-and-again into main 2026-09-27 22:37:36 +00:00
jschoubben 7b02feaebb The mint names the bus by bare host, and can mint again
BareAddress adds a scheme where none was, so the host it yielded carried one and
every URL built from it carried two. Caught before a push: the host is now taken
with no scheme and no port, and every URL adds its own. `rollout mint --again`
mints every credential afresh for exactly this case — a mint that was wrong before
anything received it.
2026-09-28 00:37:10 +02:00
jschoubben bd10e2c695 Merge pull request 'The mint finds the bus on the hub' (#96) from fix/mint-finds-the-bus-on-the-hub into main 2026-09-27 22:34:41 +00:00
jschoubben 4b209d944d The mint finds the bus on the hub
The map of who is where on the private network lists the machines placed around
the hub, not the hub — and the control node is the hub, and runs the new bus.
Found on the first live run: refused for having no address. The address every
machine already dials the current bus at is the same machine, so that host with
the new port is what they are told.
2026-09-28 00:34:17 +02:00
jschoubben 84024cbdb6 The control plane speaks the new bus
One environment variable moves it (design 25): MESH_BUS_NATS, read from the `bus`
secret `rollout mint` sealed to its machine, and the two that named the old bus go,
because being told about both is refused at start. Registered and built ahead of
the push that flips it, so the flip and the bus it flips to arrive in one
declaration — the same push that starts the new bus and hands this machine its
membership. Deliberately not merged until every credential is minted.
2026-09-28 00:31:57 +02:00
jschoubben ad2eed2f71 Merge pull request 'The move mints every credential and tells each machine its membership' (#95) from feat/the-move-mints-and-delivers into main 2026-09-27 22:30:58 +00:00
5 changed files with 65 additions and 14 deletions
+10 -1
View File
@@ -537,6 +537,15 @@ func onTheNetwork(ctx context.Context, inv *inventory.Inventory,
if err != nil {
return nil, err
}
// **With the seat holders on record**, or a machine running the next holder of a seat beside
// the current one resolves as two holders, is refused, and drops out of the map — taking the
// address every other machine composes for what it offers (novox/hq ADR 0131). Found live:
// the control node vanished from the private network the moment the new bus was assigned
// beside the old one.
holdings, err := inv.Holdings(ctx)
if err != nil {
return nil, err
}
var out []inventory.Overlay
for _, p := range places {
if p.Address == "" {
@@ -549,7 +558,7 @@ func onTheNetwork(ctx context.Context, inv *inventory.Inventory,
caps, _ := inv.ProfileOf(ctx, p.Name)
got, err := catalogue.Resolve(shelf, assigned,
catalogue.Node{Name: p.Name, Site: p.Site, Capabilities: caps},
catalogue.World{Unchecked: true})
catalogue.World{Unchecked: true, Holdings: holdings})
if err != nil {
continue
}
+43 -8
View File
@@ -33,14 +33,19 @@ import (
// ability to change things, not the services its modules are serving — measured on 2026-09-27, when
// a seat emptied mid-change and the control plane looped for two hours while every service stayed up.
const rolloutUsage = "rollout check | rollout mint | rollout --confirm"
const rolloutUsage = "rollout check | rollout mint [--again] | rollout --confirm"
func rolloutCommand(ctx context.Context, args []string) error {
switch {
case len(args) == 1 && args[0] == "check":
return rolloutCheck(ctx)
case len(args) == 1 && args[0] == "mint":
return rolloutMint(ctx)
return rolloutMint(ctx, false)
case len(args) == 2 && args[0] == "mint" && args[1] == "--again":
// Every credential minted afresh, whether or not one exists — for a mint that was wrong
// before anything was pushed. Afterwards nothing that received the old one still works,
// which is fine exactly when nothing received it.
return rolloutMint(ctx, true)
case len(args) == 1 && args[0] == "--confirm":
return errors.New(
"the rollout itself is not built yet: `rollout check` answers whether it could run, and " +
@@ -205,7 +210,7 @@ func notReadyOf(state broker.Readiness) []string { return broker.NotReady(state)
// why `rollout check` refuses until this has run. The bus's address is worked out here, from where
// the module that provides it is assigned, rather than read from this process's environment: this
// process is still on the old bus when this runs, and must be.
func rolloutMint(ctx context.Context) error {
func rolloutMint(ctx context.Context, again bool) error {
open, err := openStores(ctx)
if err != nil {
return err
@@ -243,11 +248,33 @@ func rolloutMint(ctx context.Context) error {
if err != nil {
return err
}
if onNetwork[busNode] == "" {
return fmt.Errorf("%s runs the new bus and has no address on the private network, so no machine "+
"could be told where it is", busNode)
busHost := onNetwork[busNode]
if busHost == "" {
// **The hub is not in that map.** The machine that took over the tunnel is where the current
// bus already answers, and every machine dials it at the address the mesh handed them — so
// when the new bus runs on the same machine, that address is the one to tell them, with the
// new port. Found live: the control node is the hub, and the map lists the machines placed
// around it.
// The host alone: no scheme (BareAddress adds one where none was, which is the wrong
// direction here — every URL built below adds its own) and no port.
_, _, host := broker.CredentialIn(known.Address)
if host == "" {
host = known.Address
}
if _, after, hasScheme := strings.Cut(host, "://"); hasScheme {
host = after
}
host = strings.TrimSpace(host)
if i := strings.LastIndex(host, ":"); i > 0 && !strings.Contains(host[i:], "]") {
host = host[:i]
}
if host == "" {
return fmt.Errorf("%s runs the new bus and has no address on the private network, and the "+
"current bus's address is unknown too, so no machine could be told where it is", busNode)
}
busHost = host
}
busAddress := onNetwork[busNode] + ":4222"
busAddress := busHost + ":4222"
records, err := inv.BusRecords(ctx)
if err != nil {
@@ -273,7 +300,7 @@ func rolloutMint(ctx context.Context) error {
var machines, modules, skipped int
for _, p := range users {
if !wanted[p.Username()] {
if !again && !wanted[p.Username()] {
continue
}
switch p.Kind {
@@ -313,6 +340,14 @@ func rolloutMint(ctx context.Context) error {
machines++
case broker.KindModule:
if p.Module == "mesh-controller" {
// The control plane is a module too, and its `broker` secret is the old bus's
// credential it is still using while this runs. Writing the new bus's blob there
// cut the mesh off from its own old bus mid-move (2026-09-28). Its new-bus credential
// is the controller principal's `bus` secret above; nothing else is needed here.
skipped++
continue
}
m, inShelf := shelf[p.Module]
if !inShelf {
skipped++
+8 -1
View File
@@ -244,7 +244,14 @@ func PermissionsFor(p Principal) (Permissions, error) {
case KindNode:
// A host publishes its own node's control traffic and subscribes its own declaration —
// and nothing of any other node's.
pub = []string{"mesh.control." + p.Node + ".>"}
// And binding to its consumer, which asks the server about it (CONSUMER.INFO) — the one
// thing the host does that nothing granted. Found the first time a machine dialled a
// permissioned server: "this node cannot read its declarations" (2026-09-28). The ack and
// the inbox are granted below with every principal's.
pub = []string{
"mesh.control." + p.Node + ".>",
"$JS.API.CONSUMER.INFO.NODES." + p.Node,
}
sub = []string{"mesh.node." + p.Node + ".declare"}
case KindModule:
+1 -1
View File
@@ -32,7 +32,7 @@ accounts {
subscribe: { allow: ["_INBOX.enrol.one.>"] }
} }
{ user: "node.one", password: "$2a$11$nnnnnnnnnnnnnnnnnnnnnn", permissions: {
publish: { allow: ["$JS.ACK.NODES.one.>", "mesh.control.one.>"] }
publish: { allow: ["$JS.ACK.NODES.one.>", "$JS.API.CONSUMER.INFO.NODES.one", "mesh.control.one.>"] }
subscribe: { allow: ["_INBOX.node.one.>", "mesh.node.one.declare"] }
} }
{ user: "one.telegram", password: "$2a$11$tttttttttttttttttttttt", permissions: {
+3 -3
View File
@@ -47,15 +47,14 @@
"MESH_STORE_INVENTORY_FILE": "/run/secrets/inventory",
"MESH_STORE_IDENTITY_FILE": "/run/secrets/identity",
"MESH_STORE_LICENCES_FILE": "/run/secrets/licences",
"MESH_BROKER_AMQP_FILE": "/run/secrets/broker",
"MESH_BROKER_MANAGEMENT_FILE": "/run/secrets/broker-management",
"MESH_BROKER_ADDRESS_FILE": "/run/secrets/broker-address",
"MESH_STORE_INVENTORY_PORT": "${seat:mesh-store:5432}",
"MESH_STORE_IDENTITY_PORT": "${seat:mesh-store:5432}",
"MESH_STORE_LICENCES_PORT": "${seat:mesh-store:5432}",
"MESH_BROKER_AMQP_PORT": "${seat:mesh-broker:5672}",
"MESH_BROKER_MANAGEMENT_PORT": "${seat:mesh-broker:15672}",
"MESH_BROKER_ADDRESS_PORT": "${seat:mesh-broker:5671}"
"MESH_BROKER_ADDRESS_PORT": "${seat:mesh-broker:5671}",
"MESH_BUS_NATS_FILE": "/run/secrets/bus"
},
"volumes": [
"/var/lib/mesh-broker-tls:/broker-tls:ro",
@@ -63,6 +62,7 @@
"/var/lib/mesh/mesh-controller/identity:/run/secrets/identity:ro",
"/var/lib/mesh/mesh-controller/licences:/run/secrets/licences:ro",
"/var/lib/mesh/mesh-controller/broker:/run/secrets/broker:ro",
"/var/lib/mesh/mesh-controller/bus:/run/secrets/bus:ro",
"/var/lib/mesh/mesh-controller/broker-management:/run/secrets/broker-management:ro",
"/var/lib/mesh/mesh-controller/broker-address:/run/secrets/broker-address:ro"
],