One-node bed: SDK-by-version, rename, and the store/broker upgrade proofs #27
+11
-11
@@ -25,9 +25,9 @@
|
||||
# the gap is a named failure rather than an absence.
|
||||
#
|
||||
# hosting (public, routable) home (private, behind the access point)
|
||||
# novox 192.0.2.20 ── anchor ace 10.99.1.10 home server
|
||||
# substrate, registry, shanks 10.99.1.20 workstation
|
||||
# builder, control plane g14 10.99.1.30 workstation
|
||||
# anchor 192.0.2.20 ── anchor home-server 10.99.1.10 home server
|
||||
# substrate, registry, workstation 10.99.1.20 workstation
|
||||
# builder, control plane laptop 10.99.1.30 workstation
|
||||
#
|
||||
# EGRESS IS NOT OPTIONAL HERE. With nothing loaded, a sealed machine stops at the installer's first
|
||||
# pull. Every machine has a way out, and it is a SECOND path: each still reaches the rest of the
|
||||
@@ -41,7 +41,7 @@
|
||||
scenario: fresh-mesh
|
||||
|
||||
segments:
|
||||
# The routable segment. novox lives here; its public address is the broker endpoint every token
|
||||
# The routable segment. anchor lives here; its public address is the broker endpoint every token
|
||||
# carries and the overlay hub the home nodes dial.
|
||||
hosting:
|
||||
kind: public
|
||||
@@ -63,10 +63,10 @@ machines:
|
||||
# The anchor. Raised by the installer into a mesh of one, and then asked to build.
|
||||
#
|
||||
# Sized for what it actually does here: the store, the broker, the registry, TWO control planes
|
||||
# during the pivot, the builder, and a build workspace holding a Node toolchain image and an npm
|
||||
# cache. It is NOT sized for the whole novox service set, because this bed does not run one — it
|
||||
# during the pivot, the builder, and a build worksphome-server holding a Node toolchain image and an npm
|
||||
# cache. It is NOT sized for the whole anchor service set, because this bed does not run one — it
|
||||
# proves the machinery that would produce it.
|
||||
novox:
|
||||
anchor:
|
||||
at: { segment: hosting, address: [192.0.2.20] }
|
||||
egress: true
|
||||
inbound: allow
|
||||
@@ -77,21 +77,21 @@ machines:
|
||||
# Three machines that JOIN. Host binary and a token, nothing else — no bootstrap, no substrate,
|
||||
# no registry. They are deliberately small: what they are here to prove is that a joined machine
|
||||
# can be given a module the mesh built, which is a question about credentials and not about load.
|
||||
ace:
|
||||
home-server:
|
||||
at: { segment: home, address: [10.99.1.10] }
|
||||
egress: true
|
||||
inbound: allow
|
||||
memory: 4GiB
|
||||
cpus: 2
|
||||
disk: 25GiB
|
||||
shanks:
|
||||
workstation:
|
||||
at: { segment: home, address: [10.99.1.20] }
|
||||
egress: true
|
||||
inbound: allow
|
||||
memory: 3GiB
|
||||
cpus: 2
|
||||
disk: 20GiB
|
||||
g14:
|
||||
laptop:
|
||||
at: { segment: home, address: [10.99.1.30] }
|
||||
egress: true
|
||||
inbound: allow
|
||||
@@ -102,5 +102,5 @@ machines:
|
||||
# **No `images:` key, and that is the whole point of this file.** Anything a machine holds here, it
|
||||
# pulled or the mesh built. See the header.
|
||||
|
||||
place:
|
||||
plhome-server:
|
||||
all: [host, runtime]
|
||||
|
||||
@@ -0,0 +1,56 @@
|
||||
# ONE MACHINE, AND EVERYTHING A MESH HAS TO BE. Nothing is handed to it.
|
||||
#
|
||||
# The common case, and the one worth getting right first: a person with a single machine runs the
|
||||
# installer and ends up with a mesh that works. Not a mesh that *runs* — `17-raising-a-mesh` is
|
||||
# careful about that difference, and so is this scenario. Genesis ends with a substrate, a registry,
|
||||
# a built control plane and a builder, and a mesh in that state cannot produce anything and holds no
|
||||
# record of what it has. Calling that "up" is how the catalogue came to be missing from a test for
|
||||
# weeks without anything complaining.
|
||||
#
|
||||
# So the test driving this asks the harder question: can this machine, given nothing but a container
|
||||
# runtime and the host binary, end up holding
|
||||
#
|
||||
# - a substrate and a registry it pulled from the internet,
|
||||
# - a control plane it BUILT, and then rebuilt from its own repository through the module path,
|
||||
# - a builder that takes work over the broker,
|
||||
# - the shared base every module with code of its own stands on,
|
||||
# - a store of its own — the substrate's is the control plane's own plumbing, not a provider,
|
||||
# - a catalogue, so it can say what it has and what a change reaches,
|
||||
# - and a module of its own, built, provisioned and running.
|
||||
#
|
||||
# **There is no `images:` key, and that is the whole point of this file.** The four-machine scenario
|
||||
# next door loads thirty-four of the mesh's own images from the workstation because it does not
|
||||
# build them — a shape no real installation has. Here nothing is loaded. What the machine holds it
|
||||
# either pulled from the internet or made.
|
||||
#
|
||||
# EGRESS IS NOT OPTIONAL. With nothing loaded, a sealed machine stops at the installer's first pull.
|
||||
#
|
||||
# MESH_LAB_HOST_BINARY=.../mesh-host MESH_LAB_BOOTSTRAP_BINARY=.../mesh-bootstrap
|
||||
# MESH_LAB_BUNDLE=.../examples/substrate-first-node.lock
|
||||
# MESH_LAB_CATALOG=.../mesh-catalog/modules
|
||||
# MESH_LAB_SOURCE=<forge url> MESH_LAB_SOURCE_REF=<commit>
|
||||
scenario: one-node-mesh
|
||||
|
||||
segments:
|
||||
hosting:
|
||||
kind: public
|
||||
cidr: [192.0.2.0/24]
|
||||
|
||||
machines:
|
||||
# The address matters: the substrate template names the broker at a fixed address, and a token
|
||||
# carries that verbatim as the endpoint an enrolling node dials. With one machine, that machine
|
||||
# must BE it, or the mesh hands out an endpoint nothing answers on.
|
||||
#
|
||||
# Sized for what it actually does: the store, the broker, the registry, two control planes during
|
||||
# the pivot, the builder, a Node toolchain and an npm cache in the build workspace, and then every
|
||||
# core module it builds and runs on top of that.
|
||||
anchor:
|
||||
at: { segment: hosting, address: [192.0.2.10] }
|
||||
egress: true
|
||||
inbound: allow
|
||||
memory: 12GiB
|
||||
cpus: 6
|
||||
disk: 60GiB
|
||||
|
||||
place:
|
||||
all: [host, runtime]
|
||||
@@ -48,10 +48,10 @@ import { labIsUsable, destroyAll, substrateBundle } from "./harness.ts";
|
||||
import { genesis, type GenesisResult } from "./genesis.ts";
|
||||
|
||||
const SCENARIO = "fresh-mesh";
|
||||
const CONTROL = "novox";
|
||||
const HOME_NODES = ["ace", "shanks", "g14"];
|
||||
const CONTROL = "anchor";
|
||||
const HOME_NODES = ["home-server", "workstation", "laptop"];
|
||||
/** The joined machine asked to run a mesh-built module. Any of the three would do. */
|
||||
const SECOND = "ace";
|
||||
const SECOND = "home-server";
|
||||
|
||||
/** The anchor's public address — what every other machine dials, and what its own token must name. */
|
||||
const ANCHOR = "192.0.2.20";
|
||||
@@ -74,9 +74,30 @@ const BASE = { module: "mesh-tools", repo: "mesh-tools", path: "" };
|
||||
* record of, so it provides nothing to anything. A module asking for `amqp` is asking for a
|
||||
* provider in the graph, and this is it. No build: its image is upstream.
|
||||
*/
|
||||
const PROVIDER = { module: "lavinmq", repo: "mesh-catalog", path: "modules/lavinmq" };
|
||||
const PROVIDER = { module: "lavinmq", repo: "mesh-catalog", path: "modules/lavinmq", container: "mesh-lavinmq" };
|
||||
/**
|
||||
* The store, and the catalogue that cannot exist without it.
|
||||
*
|
||||
* Both were missing from this test entirely, and nothing complained, because nothing asked. A mesh
|
||||
* with no catalogue holds no module graph — it cannot say what it has, what a module is made of,
|
||||
* what a change reaches, or what must be rebuilt. It ran anyway, which is the point: "the mesh is
|
||||
* up" was being read off genesis finishing.
|
||||
*/
|
||||
const STORE = { module: "postgres", repo: "mesh-catalog", path: "modules/postgres", container: "mesh-postgres" };
|
||||
const CATALOGUE = { module: "mesh-catalog", repo: "mesh-catalog", path: "modules/mesh-catalog", container: "mesh-catalog" };
|
||||
/** The control plane, rebuilt from its own repository — the step that ends the installer's tenure. */
|
||||
const CONTROL_PLANE = { module: "mesh-control", repo: "mesh-control", path: "", container: "mesh-control" };
|
||||
/** Named once, because the step title is also how later steps say what they waited on. */
|
||||
const NEEDS = "the mesh runs a broker for that module to talk to";
|
||||
const GENESIS = "a bare machine becomes a mesh of one, raised by the installer";
|
||||
const BASE_BUILT = "the mesh builds the shared base from source";
|
||||
const STORE_RUNS = "the mesh builds and runs a store of its own";
|
||||
const CATALOGUE_RUNS = "the mesh builds and runs its own catalogue";
|
||||
const CONTROL_REBUILT = "the mesh rebuilds its own control plane from source";
|
||||
const MODULE_BUILT = "the mesh builds a module standing on that base";
|
||||
const ANCHOR_RUNS = "the anchor runs the module the mesh built";
|
||||
const JOINED = "three machines join the mesh, and reach it over its private network";
|
||||
const SECOND_RUNS = "a joined machine runs the module the mesh built";
|
||||
const MODULE = { module: "amqp-ping", repo: "mesh-catalog", path: "modules/amqp-ping" };
|
||||
|
||||
const capability = await labIsUsable();
|
||||
@@ -162,6 +183,34 @@ async function mesh(command: string, timeoutMs?: number): Promise<string> {
|
||||
return must(CONTROL, `docker exec mesh-control /mesh-control ${command}`, timeoutMs);
|
||||
}
|
||||
|
||||
/** A module the mesh has to make for itself: where its source is, and what it runs when it works. */
|
||||
interface CoreModule { module: string; repo: string; path: string; container: string }
|
||||
|
||||
/**
|
||||
* Build a module from source, install it, and wait for it to actually run.
|
||||
*
|
||||
* The whole sequence a module goes through, in one place because the mesh has to do it for several
|
||||
* before it is a mesh at all: register the manifest, build it from its repository and path, issue
|
||||
* the broker account its runtime needs, assign it, send it, and then ask the machine whether the
|
||||
* container is up.
|
||||
*
|
||||
* **The account is not optional and is not swallowed.** A module's runtime is a tool host: it
|
||||
* connects to the mesh's broker before doing anything. Without an account the mesh still fills the
|
||||
* secret the module declares it owns — with a generated value — so the container starts, fails to
|
||||
* parse a password as a credential document, and loops on a JSON syntax error mentioning no
|
||||
* missing account. That cost a step that reported PASS.
|
||||
*/
|
||||
async function bringUp(m: CoreModule): Promise<string> {
|
||||
await registerModule(m.module, resolve(catalogDir, m.module, "module.json"));
|
||||
const built = await mesh(
|
||||
`build ${forgeUrl(m.repo)} --path ${m.path} --ref ${refFor(m.repo)} --wait 1200s`, 1_500_000);
|
||||
assert.doesNotMatch(built, /failed/i, built);
|
||||
await mesh(`module issue ${m.module} --node ${CONTROL}`);
|
||||
await mesh(`assign ${CONTROL} ${m.module}`);
|
||||
await mesh(`push ${CONTROL}`, 600_000);
|
||||
return `${built}\n${await waitForContainer(CONTROL, m.container)}`;
|
||||
}
|
||||
|
||||
/**
|
||||
* Wait for one container, BY NAME, to be running.
|
||||
*
|
||||
@@ -262,7 +311,7 @@ before(async () => {
|
||||
//
|
||||
// The shared description, the same one `genesis-single` calls. The bundle is the TEMPLATE with
|
||||
// nothing held: no image is pre-resolved, because none is here to resolve to.
|
||||
await step("novox becomes a mesh of one, raised by the installer", null, async () => {
|
||||
await step("a bare machine becomes a mesh of one, raised by the installer", null, async () => {
|
||||
try {
|
||||
raised = await genesis({
|
||||
instanceId,
|
||||
@@ -289,41 +338,29 @@ before(async () => {
|
||||
return raised.report.join("\n");
|
||||
});
|
||||
|
||||
// ---- 2. JOINING -----------------------------------------------------------------------------
|
||||
// ---- 2..6. THE MESH BECOMES ONE --------------------------------------------------------------
|
||||
//
|
||||
// Host binary and a token. novox is NOT in this loop — the installer enrolled it, and enrolling
|
||||
// it again would offer the mesh a second identity for a node it already knows.
|
||||
await step("three machines join it across the household gateway",
|
||||
"novox becomes a mesh of one, raised by the installer", async () => {
|
||||
const said: string[] = [];
|
||||
for (const machine of HOME_NODES) {
|
||||
await mesh(`node add ${machine}`);
|
||||
const token = tokenFrom(await mesh(`token issue --node ${machine}`));
|
||||
const out = await must(machine, `${HOST_PATH} enrol --token ${quote(token)}`, 180_000);
|
||||
assert.match(out, new RegExp(`enrolled as ${machine}`), out);
|
||||
await must(machine, `nohup ${HOST_PATH} run > /var/log/mesh-host.log 2>&1 & sleep 3`);
|
||||
said.push(` ${machine} enrolled and running`);
|
||||
}
|
||||
const nodes = await mesh("node list");
|
||||
said.push(nodes.trim());
|
||||
return said.join("\n");
|
||||
});
|
||||
// **Joining used to be here, second, and that was the wrong order.** Three machines were enrolled
|
||||
// into a mesh that could not yet produce a single module, and the step was reported as though
|
||||
// something had been shown. They do join — reliably — but joining a mesh that can build nothing
|
||||
// proves only that enrolment works, which was never the doubtful part.
|
||||
//
|
||||
// `17-raising-a-mesh` says it plainly: genesis ends with a mesh of one that RUNS, and that is not
|
||||
// the same as a mesh that WORKS; what remains after the core modules are built is "adding
|
||||
// machines, and deciding what they run". So everything a mesh needs to be a mesh happens first,
|
||||
// and machines arrive at the end.
|
||||
|
||||
// ---- 3. THE MESH BUILDS THE SHARED BASE -----------------------------------------------------
|
||||
//
|
||||
// The toolchain and runtime every module with code of its own stands on. It is a module, and it
|
||||
// is built like one — cloned from the forge by the builder installing put here, compiled on the
|
||||
// machine, published into the mesh's own registry.
|
||||
await step("the mesh builds the shared base from source",
|
||||
"three machines join it across the household gateway", async () => {
|
||||
await step(BASE_BUILT, GENESIS, async () => {
|
||||
// Registered from the manifest the builder will also read, so what the mesh holds and what it
|
||||
// builds are the same description of the same module.
|
||||
//
|
||||
// **Not swallowed.** This call used to end in `.catch(() => {})`, on the reasoning that the
|
||||
// base might already be known. It hid a real failure — the manifest was being named at a path
|
||||
// inside a container that had never seen it — and the step passed anyway, because a base with
|
||||
// nothing to stand on builds whether or not the mesh has a record of it. The next step, which
|
||||
// needs that record, is where it surfaced.
|
||||
// nothing to stand on builds whether or not the mesh has a record of it.
|
||||
await registerModule(BASE.module, baseManifest);
|
||||
const built = await mesh(
|
||||
`build ${forgeUrl(BASE.repo)} --ref ${refFor(BASE.repo)} --wait 1200s`, 1_500_000);
|
||||
@@ -331,9 +368,39 @@ before(async () => {
|
||||
return built;
|
||||
});
|
||||
|
||||
// ---- 4. AND A MODULE STANDING ON IT ---------------------------------------------------------
|
||||
await step("the mesh builds a module standing on that base",
|
||||
"the mesh builds the shared base from source", async () => {
|
||||
// A store of its own. **Not the substrate's.** The installer raises a store for the control
|
||||
// plane to keep its own records in, the way it raises a broker — plumbing, not a module the mesh
|
||||
// has any record of, so it provides nothing to anything. A module that wants a database wants a
|
||||
// provider in the graph, and the catalogue below is the first thing to want one.
|
||||
await step(STORE_RUNS, BASE_BUILT, () => bringUp(STORE));
|
||||
|
||||
// And the catalogue, which was missing from this test altogether.
|
||||
//
|
||||
// Without it the mesh holds no module graph: it cannot say what it has, what a module is made
|
||||
// of, what a change to one reaches, or what must be rebuilt. A mesh in that state still runs,
|
||||
// which is exactly how its absence went unnoticed — "the mesh is up" was being read off the
|
||||
// installer finishing rather than off the mesh being able to answer anything.
|
||||
await step(CATALOGUE_RUNS, STORE_RUNS, () => bringUp(CATALOGUE));
|
||||
|
||||
// The control plane, rebuilt from its own repository and rolled out.
|
||||
//
|
||||
// The installer built it once, which is what got the mesh running. Building it again THROUGH THE
|
||||
// MODULE PATH — build, notice the version moved, roll it out — is a different claim: it is the
|
||||
// moment the mesh stops depending on the installer for anything, and the first time the thing
|
||||
// that performs an upgrade performs one on itself.
|
||||
await step(CONTROL_REBUILT, CATALOGUE_RUNS, async () => {
|
||||
const built = await mesh(
|
||||
`build ${forgeUrl(CONTROL_PLANE.repo)} --ref ${sourceRef} --wait 1200s`, 1_500_000);
|
||||
assert.doesNotMatch(built, /failed/i, built);
|
||||
const rolled = await mesh(`upgrade ${CONTROL_PLANE.module} roll-out`, 900_000);
|
||||
// Asked of the machine rather than believed from the command: the control plane that answers
|
||||
// afterwards is the one that has to be running for anything below this line to mean anything.
|
||||
await waitForContainer(CONTROL, CONTROL_PLANE.container);
|
||||
return `${built}\n${rolled}`;
|
||||
});
|
||||
|
||||
// ---- 7..8. SOMETHING TO RUN ---------------------------------------------------------------
|
||||
await step(MODULE_BUILT, CONTROL_REBUILT, async () => {
|
||||
await registerModule(MODULE.module, resolve(catalogDir, MODULE.module, "module.json"));
|
||||
const built = await mesh(
|
||||
`build ${forgeUrl(MODULE.repo)} --path ${MODULE.path} --ref ${refFor(MODULE.repo)} --wait 1200s`,
|
||||
@@ -347,61 +414,64 @@ before(async () => {
|
||||
return `${built}\n${builds}`;
|
||||
});
|
||||
|
||||
// ---- 4b. WHAT THE MODULE NEEDS --------------------------------------------------------------
|
||||
//
|
||||
// `amqp-ping` requires the `amqp` provision, and the mesh refused to place it: "nothing provides
|
||||
// amqp, wanted by amqp-ping". That refusal is correct and is the reason this step exists rather
|
||||
// than the reason to pick an easier module. **The substrate's broker is not a provider.** It is
|
||||
// raised by the installer as part of the bundle, so it is a running container and not a module
|
||||
// with something to offer — the mesh's own plumbing, not an entry in its graph. A module that
|
||||
// wants a broker wants one the mesh knows about.
|
||||
// than the reason to pick an easier module.
|
||||
//
|
||||
// `lavinmq` is that module. It was first added here on the belief that it needed no building —
|
||||
// its broker is an upstream image — and the mesh refused it: two of its three containers named a
|
||||
// placeholder digest, "which is never a real image". That was right. The broker is upstream, but
|
||||
// the module is not only the broker: it carries a run-once bootstrap that writes the broker's
|
||||
// its broker is an upstream image — and the mesh refused it again: two of its three containers
|
||||
// named a placeholder digest, "which is never a real image". Also right. The broker is upstream,
|
||||
// but the module is not only the broker: it carries a run-once bootstrap that writes the broker's
|
||||
// configuration, a provisioner that grants each consumer its own vhost and user, tools and an
|
||||
// event consumer. All of that is its own code and has to be built like anything else.
|
||||
await step(NEEDS, "the mesh builds a module standing on that base", async () => {
|
||||
await registerModule(PROVIDER.module, resolve(catalogDir, PROVIDER.module, "module.json"));
|
||||
const built = await mesh(
|
||||
`build ${forgeUrl(PROVIDER.repo)} --path ${PROVIDER.path} --ref ${refFor(PROVIDER.repo)} --wait 1200s`,
|
||||
1_500_000);
|
||||
assert.doesNotMatch(built, /failed/i, built);
|
||||
await mesh(`assign ${CONTROL} ${PROVIDER.module}`);
|
||||
// **Its account on the mesh's own broker, and not swallowed.** A module's runtime is a tool
|
||||
// host: it connects to the mesh broker before it does anything, and what it reads is a sealed
|
||||
// credential document. Without an account the mesh still fills the secret this module declares
|
||||
// it owns — with a generated value — so the container starts, fails to parse a password as a
|
||||
// credential, and crash-loops on a JSON syntax error that says nothing about the missing
|
||||
// account. Issuing it is not optional and neither is hearing that it failed.
|
||||
await mesh(`module issue ${PROVIDER.module} --node ${CONTROL}`);
|
||||
await mesh(`push ${CONTROL}`, 600_000);
|
||||
return waitForContainer(CONTROL, "mesh-lavinmq");
|
||||
});
|
||||
// event consumer, all of it its own code.
|
||||
await step(NEEDS, MODULE_BUILT, () => bringUp(PROVIDER));
|
||||
|
||||
// ---- 5. THE ANCHOR RUNS IT ------------------------------------------------------------------
|
||||
//
|
||||
// The machine that built it. This is the case every earlier proof covered, and it is here as the
|
||||
// control for step 6: if this fails, step 6's failure says nothing about fetching.
|
||||
await step("the anchor runs the module the mesh built", NEEDS, async () => {
|
||||
// control for the last step: if this fails, that one's failure says nothing about fetching.
|
||||
await step(ANCHOR_RUNS, NEEDS, async () => {
|
||||
await mesh(`module issue ${MODULE.module} --node ${CONTROL}`);
|
||||
await mesh(`assign ${CONTROL} ${MODULE.module}`);
|
||||
await mesh(`push ${CONTROL}`, 600_000);
|
||||
return waitForContainer(CONTROL, MODULE.module);
|
||||
});
|
||||
|
||||
// ---- 6. AND A MACHINE THAT DID NOT BUILD IT -------------------------------------------------
|
||||
// ---- 9. NOW MACHINES MAY ARRIVE ---------------------------------------------------------------
|
||||
//
|
||||
// **The thing nothing has ever checked.** ace did not build this image and has never seen it. To
|
||||
// run it, it must fetch it from the mesh's registry — and a joined node has no account there.
|
||||
// The mesh grants a consumer a credential for a database; it does not yet do so for the store
|
||||
// its own images live in (novox/hq issue 042).
|
||||
// Host binary and a token, and nothing else. The anchor is NOT in this loop — the installer
|
||||
// enrolled it, and enrolling it again would offer the mesh a second identity for a node it
|
||||
// already knows.
|
||||
//
|
||||
// Asked anyway, and asked LAST, so that when it fails the five steps above still stand as
|
||||
// evidence of what does work.
|
||||
await step(`a joined machine runs the module the mesh built`,
|
||||
"the anchor runs the module the mesh built", async () => {
|
||||
// And they are placed on the mesh's private network, which the earlier ordering never did. The
|
||||
// mesh refuses to bind a consumer to a provider on another machine when either is missing from
|
||||
// it — "they are not both on the private network" — so without this the last step fails for a
|
||||
// reason that has nothing to do with what it is asking.
|
||||
await step(JOINED, ANCHOR_RUNS, async () => {
|
||||
const said: string[] = [];
|
||||
await mesh(`overlay place ${CONTROL} --hub --endpoint ${ANCHOR}:51820 --site hosting`);
|
||||
for (const machine of HOME_NODES) {
|
||||
await mesh(`node add ${machine}`);
|
||||
const token = tokenFrom(await mesh(`token issue --node ${machine}`));
|
||||
const out = await must(machine, `${HOST_PATH} enrol --token ${quote(token)}`, 180_000);
|
||||
assert.match(out, new RegExp(`enrolled as ${machine}`), out);
|
||||
await must(machine, `nohup ${HOST_PATH} run > /var/log/mesh-host.log 2>&1 & sleep 3`);
|
||||
await mesh(`overlay place ${machine} --site home`);
|
||||
said.push(` ${machine} enrolled, running, and on the private network`);
|
||||
}
|
||||
said.push((await mesh("node list")).trim());
|
||||
said.push((await mesh("overlay show")).trim());
|
||||
return said.join("\n");
|
||||
});
|
||||
|
||||
// ---- 10. AND A MACHINE THAT DID NOT BUILD IT --------------------------------------------------
|
||||
//
|
||||
// **The thing nothing has ever checked.** This machine did not build the image and has never seen
|
||||
// it. To run it, it must fetch it from the mesh's registry — and a joined node has no account
|
||||
// there (novox/hq issue 042), nor any reason to trust a registry serving plain HTTP over the
|
||||
// network (issue 048). Both are open, and both are invisible on a mesh of one.
|
||||
//
|
||||
// Asked anyway, and asked LAST, so that when it fails everything above still stands as evidence
|
||||
// of what does work.
|
||||
await step(SECOND_RUNS, JOINED, async () => {
|
||||
await mesh(`module issue ${MODULE.module} --node ${SECOND}`);
|
||||
await mesh(`assign ${SECOND} ${MODULE.module}`);
|
||||
await mesh(`push ${SECOND}`, 600_000);
|
||||
@@ -427,7 +497,7 @@ after(async () => {
|
||||
}, { timeout: 900_000 });
|
||||
|
||||
for (const name of [
|
||||
"novox becomes a mesh of one, raised by the installer",
|
||||
"a bare machine becomes a mesh of one, raised by the installer",
|
||||
"three machines join it across the household gateway",
|
||||
"the mesh builds the shared base from source",
|
||||
"the mesh builds a module standing on that base",
|
||||
|
||||
@@ -0,0 +1,649 @@
|
||||
/**
|
||||
* FOUR FRESH MACHINES, AND NOTHING HANDED TO THEM.
|
||||
*
|
||||
* The four-machine bed (`whole-mesh-full`) proves the mesh converges. It does so by loading
|
||||
* thirty-four of the mesh's own images onto its machines from the workstation, because it does not
|
||||
* build them — something beside the bed built them and copied them in. No real installation looks
|
||||
* like that, and the lab has been burned by exactly this shape before: it used to raise a registry
|
||||
* inside the scenario, and a bootstrap that only worked against that registry went green here and
|
||||
* would have failed on any bare machine.
|
||||
*
|
||||
* This bed hands over nothing. The scenario has no `images:` list at all. What the machines get is
|
||||
* a container runtime and the host binary — prerequisites of a machine, not parts of a mesh — and
|
||||
* from there:
|
||||
*
|
||||
* 1. novox is raised into a mesh of one by the installer, which BUILDS the control plane.
|
||||
* 2. ace, shanks and g14 JOIN it, across a household NAT, with a token and nothing else.
|
||||
* 3. The mesh builds the shared base from source, with its own builder.
|
||||
* 4. The mesh builds a real module standing on that base.
|
||||
* 5. The anchor runs it, pinned to a digest the mesh's own registry assigned.
|
||||
* 6. A JOINED machine runs it — which means pulling from a registry that asks who it is.
|
||||
*
|
||||
* Steps 1 and 2 are proven elsewhere and are here because the later ones need them. **Steps 3
|
||||
* through 6 are what this bed exists for**, and 6 is the one nothing has ever checked: genesis
|
||||
* puts the builder, the registry and everything they produce on ONE machine, so every earlier
|
||||
* proof of a mesh-built module running is a proof about the machine that built it. A second
|
||||
* machine has to fetch, and fetching needs an account nothing yet grants (novox/hq issue 042).
|
||||
*
|
||||
* Each step is recorded separately rather than allowed to throw, so a gap at 6 reports as a gap at
|
||||
* 6 instead of erasing the evidence for 3, 4 and 5.
|
||||
*
|
||||
* MESH_LAB_INCUS='sudo -n incus'
|
||||
* MESH_LAB_HOST_BINARY=.../mesh-host/mesh-host
|
||||
* MESH_LAB_BOOTSTRAP_BINARY=.../mesh-host/mesh-bootstrap
|
||||
* MESH_LAB_BUNDLE=.../mesh-host/examples/substrate-first-node.lock
|
||||
* MESH_LAB_CATALOG=.../mesh-catalog/modules
|
||||
* MESH_LAB_SOURCE=<forge>/mesh-control.git MESH_LAB_SOURCE_REF=<commit>
|
||||
* MESH_LAB_KEEP=1 to leave it standing afterwards
|
||||
*/
|
||||
import { test, before, after } from "node:test";
|
||||
import assert from "node:assert/strict";
|
||||
import { existsSync } from "node:fs";
|
||||
import { resolve } from "node:path";
|
||||
import { loadScenario } from "../../src/declaration/parse.ts";
|
||||
import { raise } from "../../src/lifecycle/raise.ts";
|
||||
import { destroy, exec, push } from "../../src/lifecycle/operate.ts";
|
||||
import { bootstrapBinaryPath, hostBinaryPath, HOST_PATH } from "../../src/lifecycle/place.ts";
|
||||
import { labIsUsable, destroyAll, substrateBundle } from "./harness.ts";
|
||||
import { genesis, type GenesisResult } from "./genesis.ts";
|
||||
import { incus } from "../../src/incus/client.ts";
|
||||
import { instanceNameOf } from "../../src/lifecycle/operate.ts";
|
||||
import { waitUntilAllUsable } from "../../src/lifecycle/ready.ts";
|
||||
|
||||
const SCENARIO = "one-node-mesh";
|
||||
const CONTROL = "anchor";
|
||||
|
||||
/** The anchor's public address — what every other machine dials, and what its own token must name. */
|
||||
const ANCHOR = "192.0.2.10";
|
||||
/** Where this mesh's registry answers, on the anchor's public address so a joined node can reach it. */
|
||||
const REGISTRY = `${ANCHOR}:5000`;
|
||||
|
||||
/**
|
||||
* The module built on top of the base, and the base it stands on.
|
||||
*
|
||||
* `amqp-ping` is deliberately small and deliberately REAL: its own TypeScript, compiled by the
|
||||
* shared toolchain, running on the shared runtime, talking to the broker. A module whose artifact
|
||||
* is a mirrored public image would pass every assertion below while skipping the whole of what is
|
||||
* under test (novox/hq SELF-UPGRADE-PLAN, rule 1).
|
||||
*/
|
||||
const BASE = { module: "mesh-tools", repo: "mesh-tools", path: "" };
|
||||
/**
|
||||
* What `amqp-ping` requires, and what the substrate does not supply.
|
||||
*
|
||||
* The installer raises a broker, but as a bundle resource — plumbing, not a module the mesh has a
|
||||
* record of, so it provides nothing to anything. A module asking for `amqp` is asking for a
|
||||
* provider in the graph, and this is it. No build: its image is upstream.
|
||||
*/
|
||||
const PROVIDER = { module: "lavinmq", repo: "mesh-catalog", path: "modules/lavinmq", container: "mesh-lavinmq" };
|
||||
/**
|
||||
* The store, and the catalogue that cannot exist without it.
|
||||
*
|
||||
* Both were missing from this test entirely, and nothing complained, because nothing asked. A mesh
|
||||
* with no catalogue holds no module graph — it cannot say what it has, what a module is made of,
|
||||
* what a change reaches, or what must be rebuilt. It ran anyway, which is the point: "the mesh is
|
||||
* up" was being read off genesis finishing.
|
||||
*/
|
||||
const STORE = { module: "postgres", repo: "mesh-catalog", path: "modules/postgres", container: "mesh-postgres" };
|
||||
const CATALOGUE = { module: "mesh-catalog", repo: "mesh-catalog", path: "modules/mesh-catalog", container: "mesh-catalog" };
|
||||
/** The control plane, rebuilt from its own repository — the step that ends the installer's tenure. */
|
||||
const CONTROL_PLANE = { module: "mesh-control", repo: "mesh-control", path: "", container: "mesh-control" };
|
||||
|
||||
/**
|
||||
* What this mesh must hold when it is finished, and what must be RUNNING on the machine.
|
||||
*
|
||||
* Written down as a list rather than checked one step at a time, because "is this a mesh" is a
|
||||
* question about the set. The three the build loop cannot produce for itself — the control plane,
|
||||
* the registry and the builder — are here too: they are carried in, and a mesh missing any of them
|
||||
* is not one.
|
||||
*/
|
||||
const MUST_HOLD = ["mesh-control", "registry", "builder", "mesh-tools", "postgres",
|
||||
"mesh-catalog", "lavinmq", "amqp-ping"];
|
||||
const MUST_RUN = ["mesh-control", "mesh-registry", "mesh-broker", "mesh-store",
|
||||
"mesh-postgres", "mesh-catalog", "mesh-lavinmq", "amqp-ping"];
|
||||
/** Named once, because the step title is also how later steps say what they waited on. */
|
||||
const NEEDS = "the mesh runs a broker for that module to talk to";
|
||||
const GENESIS = "a bare machine becomes a mesh of one, raised by the installer";
|
||||
const BASE_BUILT = "the mesh builds the shared base from source";
|
||||
const STORE_RUNS = "the mesh builds and runs a store of its own";
|
||||
const CATALOGUE_RUNS = "the mesh builds and runs its own catalogue";
|
||||
const CONTROL_REBUILT = "the mesh rebuilds its own control plane from source";
|
||||
const MODULE_BUILT = "the mesh builds a module standing on that base";
|
||||
const ANCHOR_RUNS = "the anchor runs the module the mesh built";
|
||||
const DESCRIBES = "the mesh can describe itself, and what it says is true";
|
||||
const NETWORK = "the machine's networking is what the modules asked for";
|
||||
const FOLLOWS = "a change to a module's source reaches the machine on its own";
|
||||
const SURVIVES = "the mesh comes back after the machine reboots";
|
||||
const MODULE = { module: "amqp-ping", repo: "mesh-catalog", path: "modules/amqp-ping" };
|
||||
|
||||
const capability = await labIsUsable();
|
||||
const binary = hostBinaryPath();
|
||||
const installer = bootstrapBinaryPath();
|
||||
const bundle = process.env["MESH_LAB_BUNDLE"] ?? "";
|
||||
const catalogDir = process.env["MESH_LAB_CATALOG"] ?? "";
|
||||
const source = process.env["MESH_LAB_SOURCE"] ?? "";
|
||||
const sourceRef = process.env["MESH_LAB_SOURCE_REF"] ?? "";
|
||||
const KEEP = !!process.env["MESH_LAB_KEEP"];
|
||||
const FIXED_ID = process.env["MESH_LAB_INSTANCE_ID"] ?? (KEEP ? "fresh-mesh-live" : undefined);
|
||||
|
||||
/**
|
||||
* Where a repository other than the control plane's lives.
|
||||
*
|
||||
* Derived from `MESH_LAB_SOURCE` by swapping the last path segment, because every one of these
|
||||
* repositories sits beside the others under the same owner on the same forge. Overridable, so a
|
||||
* forge that is arranged differently does not need this bed edited.
|
||||
*/
|
||||
function forgeUrl(repo: string): string {
|
||||
const override = process.env[`MESH_LAB_SOURCE_${repo.toUpperCase().replaceAll("-", "_")}`];
|
||||
if (override) return override;
|
||||
return source.replace(/[^/]+\.git$/, `${repo}.git`);
|
||||
}
|
||||
/**
|
||||
* What to build, per repository.
|
||||
*
|
||||
* A branch is acceptable for an ordinary build; only genesis insists on a commit (ADR 0071). Per
|
||||
* repository rather than one value for all of them, because a change under test usually lives in
|
||||
* one repository and the rest should be built from what everyone else has — building them all from
|
||||
* a feature branch would prove that branch against itself.
|
||||
*
|
||||
* MESH_LAB_BUILD_REF the default for every repository
|
||||
* MESH_LAB_BUILD_REF_MESH_CATALOG ...overridden for one
|
||||
*/
|
||||
function refFor(repo: string): string {
|
||||
const override = process.env[`MESH_LAB_BUILD_REF_${repo.toUpperCase().replaceAll("-", "_")}`];
|
||||
return override ?? process.env["MESH_LAB_BUILD_REF"] ?? "main";
|
||||
}
|
||||
|
||||
/**
|
||||
* The shared base's manifest, on this workstation.
|
||||
*
|
||||
* The base is a repository with a manifest at its root (novox/hq ADR 0069), so unlike the
|
||||
* catalogue's modules it is not under `MESH_LAB_CATALOG`. Derived from that path on the convention
|
||||
* that the checkouts sit beside each other, and overridable for a layout where they do not.
|
||||
*/
|
||||
const baseManifest = process.env["MESH_LAB_BASE_MANIFEST"] ??
|
||||
resolve(catalogDir, "..", "..", BASE.repo, "module.json");
|
||||
|
||||
const skip =
|
||||
!capability.usable ? capability.why :
|
||||
!binary ? "MESH_LAB_HOST_BINARY is not set to a built mesh-host" :
|
||||
!installer ? "MESH_LAB_BOOTSTRAP_BINARY is not set to a built mesh-bootstrap" :
|
||||
!source ? "MESH_LAB_SOURCE is not set to the repository the control plane is built from" :
|
||||
!sourceRef ? "MESH_LAB_SOURCE_REF is not set to the commit to build" :
|
||||
!bundle || !existsSync(bundle) ? "MESH_LAB_BUNDLE is not set to a substrate template" :
|
||||
!catalogDir || !existsSync(catalogDir) ? "MESH_LAB_CATALOG is not set to mesh-catalog/modules" :
|
||||
false;
|
||||
|
||||
let instanceId = "";
|
||||
let raised: GenesisResult;
|
||||
|
||||
// ---- talking to the machines ------------------------------------------------------------------
|
||||
|
||||
function quote(s: string): string {
|
||||
return `'${s.replaceAll("'", `'\\''`)}'`;
|
||||
}
|
||||
async function on(machine: string, command: string, timeoutMs?: number): Promise<{ out: string; ok: boolean }> {
|
||||
const { stdout } = await exec(instanceId, machine, [
|
||||
"sh", "-c", `exec 2>&1\n${command}\necho "__exit=$?"`,
|
||||
], timeoutMs);
|
||||
const marker = stdout.lastIndexOf("__exit=");
|
||||
if (marker < 0) return { out: stdout, ok: false };
|
||||
return { out: stdout.slice(0, marker), ok: stdout.slice(marker + 7).trim() === "0" };
|
||||
}
|
||||
async function must(machine: string, command: string, timeoutMs?: number): Promise<string> {
|
||||
const { out, ok } = await on(machine, command, timeoutMs);
|
||||
if (!ok) throw new Error(`${machine}: ${command}\n${out}`);
|
||||
return out;
|
||||
}
|
||||
async function mesh(command: string, timeoutMs?: number): Promise<string> {
|
||||
return must(CONTROL, `docker exec mesh-control /mesh-control ${command}`, timeoutMs);
|
||||
}
|
||||
|
||||
/**
|
||||
* Stop the machine and start it again, the way a power cut or a kernel upgrade would.
|
||||
*
|
||||
* There is no restart in the lab's own vocabulary, which is its own small finding: nothing had ever
|
||||
* needed one, because nothing had ever asked whether a mesh comes back.
|
||||
*/
|
||||
async function restartMachine(machine: string): Promise<void> {
|
||||
const name = await instanceNameOf(instanceId, machine);
|
||||
await incus(["restart", name], 180_000);
|
||||
await waitUntilAllUsable([name], 300, (m) => console.log(` restart: ${m}`));
|
||||
}
|
||||
|
||||
/** A module the mesh has to make for itself: where its source is, and what it runs when it works. */
|
||||
interface CoreModule { module: string; repo: string; path: string; container: string }
|
||||
|
||||
/**
|
||||
* Build a module from source, install it, and wait for it to actually run.
|
||||
*
|
||||
* The whole sequence a module goes through, in one place because the mesh has to do it for several
|
||||
* before it is a mesh at all: register the manifest, build it from its repository and path, issue
|
||||
* the broker account its runtime needs, assign it, send it, and then ask the machine whether the
|
||||
* container is up.
|
||||
*
|
||||
* **The account is not optional and is not swallowed.** A module's runtime is a tool host: it
|
||||
* connects to the mesh's broker before doing anything. Without an account the mesh still fills the
|
||||
* secret the module declares it owns — with a generated value — so the container starts, fails to
|
||||
* parse a password as a credential document, and loops on a JSON syntax error mentioning no
|
||||
* missing account. That cost a step that reported PASS.
|
||||
*/
|
||||
async function bringUp(m: CoreModule): Promise<string> {
|
||||
await registerModule(m.module, resolve(catalogDir, m.module, "module.json"));
|
||||
const built = await mesh(
|
||||
`build ${forgeUrl(m.repo)} --path ${m.path} --ref ${refFor(m.repo)} --wait 1200s`, 1_500_000);
|
||||
assert.doesNotMatch(built, /failed/i, built);
|
||||
await mesh(`module issue ${m.module} --node ${CONTROL}`);
|
||||
await mesh(`assign ${CONTROL} ${m.module}`);
|
||||
await mesh(`push ${CONTROL}`, 600_000);
|
||||
return `${built}\n${await waitForContainer(CONTROL, m.container)}`;
|
||||
}
|
||||
|
||||
/**
|
||||
* Wait for one container, BY NAME, to be running.
|
||||
*
|
||||
* **Named exactly, because substring matching passed a step that had failed.** Waiting for "a
|
||||
* container whose name contains lavinmq" was satisfied by the broker — `lavinmq`, up and healthy —
|
||||
* while the thing actually under test, the module's own runtime `mesh-lavinmq`, was crash-looping
|
||||
* beside it. The step went green and the fault was found by reading `docker ps` by hand.
|
||||
*/
|
||||
async function waitForContainer(node: string, container: string, seconds = 200): Promise<string> {
|
||||
const deadline = Date.now() + seconds * 1_000;
|
||||
let last = "";
|
||||
while (Date.now() < deadline) {
|
||||
const ps = (await on(node, `docker ps -a --format '{{.Names}}\t{{.Status}}'`)).out;
|
||||
last = ps;
|
||||
const line = ps.split("\n").find((l) => l.split("\t")[0]?.trim() === container);
|
||||
if (line && /^Up /.test(line.split("\t")[1]?.trim() ?? "")) return ps;
|
||||
await new Promise((r) => setTimeout(r, 5_000));
|
||||
}
|
||||
const logs = (await on(node, `docker logs --tail 15 ${container} 2>&1`)).out;
|
||||
throw new Error(
|
||||
`${container} is not running on ${node}.\n\ncontainers:\n${last}\n\nwhat it said:\n${logs}`);
|
||||
}
|
||||
|
||||
/**
|
||||
* Register a module from a manifest on this workstation.
|
||||
*
|
||||
* **The control plane runs in a container, so a file on the machine is not a file it can open.**
|
||||
* Pushing the manifest to the machine and naming that path got `no such file or directory` from
|
||||
* inside mesh-control, which is correct and was briefly mistaken for a missing manifest. It is
|
||||
* copied the last step of the way with `docker cp`.
|
||||
*
|
||||
* **Into the root, not into /tmp.** The control plane's image is a minimal one and has no `/tmp`
|
||||
* to copy into — `docker cp` says so in those words. `/` is the one directory every image has.
|
||||
*/
|
||||
async function registerModule(module: string, manifest: string): Promise<string> {
|
||||
assert.ok(existsSync(manifest), `no manifest for ${module} at ${manifest}`);
|
||||
const onMachine = `/tmp/${module}.json`;
|
||||
const inContainer = `/${module}.json`;
|
||||
await push(instanceId, CONTROL, manifest, onMachine);
|
||||
await must(CONTROL, `docker cp ${onMachine} mesh-control:${inContainer}`);
|
||||
return mesh(`module add ${inContainer}`);
|
||||
}
|
||||
function tokenFrom(said: string): string {
|
||||
const found = said.split("\n").map((l) => l.trim()).find((l) => l.length > 100 && !l.includes(" "));
|
||||
assert.ok(found, `no token in:\n${said}`);
|
||||
return found;
|
||||
}
|
||||
|
||||
// ---- steps, recorded rather than thrown --------------------------------------------------------
|
||||
|
||||
interface Step { ok: boolean; why: string; said: string }
|
||||
const steps = new Map<string, Step>();
|
||||
const order: string[] = [];
|
||||
|
||||
/** Run a step, remember what it said, and never throw. A step whose predecessor failed is skipped. */
|
||||
async function step(name: string, after_: string | null, fn: () => Promise<string>): Promise<void> {
|
||||
order.push(name);
|
||||
if (after_ && !steps.get(after_)?.ok) {
|
||||
steps.set(name, { ok: false, why: `not attempted — "${after_}" did not succeed`, said: "" });
|
||||
console.log(`SKIPPED ${name}`);
|
||||
return;
|
||||
}
|
||||
console.log(`\n======== ${name} ========`);
|
||||
try {
|
||||
const said = await fn();
|
||||
steps.set(name, { ok: true, why: "", said });
|
||||
console.log(`OK ${name}`);
|
||||
} catch (err) {
|
||||
const why = (err as Error).message;
|
||||
steps.set(name, { ok: false, why, said: "" });
|
||||
console.log(`FAILED ${name}\n${why.split("\n").slice(0, 25).join("\n")}`);
|
||||
}
|
||||
}
|
||||
|
||||
function report(name: string): string {
|
||||
const s = steps.get(name);
|
||||
if (!s) return `${name}: never ran`;
|
||||
const lines = order.map((n) => {
|
||||
const it = steps.get(n);
|
||||
return ` ${it?.ok ? "PASS" : "FAIL"} ${n}`;
|
||||
});
|
||||
return `${s.why}\n\nWhere this bed got to:\n${lines.join("\n")}`;
|
||||
}
|
||||
|
||||
before(async () => {
|
||||
if (skip) return;
|
||||
|
||||
const bed = await raise(loadScenario(`scenarios/${SCENARIO}.yml`), {
|
||||
onProgress: (m) => console.log(`raise: ${m}`),
|
||||
...(FIXED_ID ? { instanceId: FIXED_ID } : {}),
|
||||
});
|
||||
instanceId = bed.instanceId;
|
||||
console.log(`INSTANCE ${instanceId}${KEEP ? " (KEEP — will be left standing)" : ""}`);
|
||||
console.log(`NOTHING WAS LOADED: this scenario names no images. Every image on every machine ` +
|
||||
`below was pulled from the internet or built by the mesh.`);
|
||||
|
||||
// ---- 1. GENESIS -----------------------------------------------------------------------------
|
||||
//
|
||||
// The shared description, the same one `genesis-single` calls. The bundle is the TEMPLATE with
|
||||
// nothing held: no image is pre-resolved, because none is here to resolve to.
|
||||
await step("a bare machine becomes a mesh of one, raised by the installer", null, async () => {
|
||||
try {
|
||||
raised = await genesis({
|
||||
instanceId,
|
||||
node: CONTROL,
|
||||
installer: installer as string,
|
||||
catalogDir,
|
||||
// The broker's advertised address, corrected.
|
||||
//
|
||||
// The template hardcodes 192.0.2.10:5671 — the address of the anchor in the single-machine
|
||||
// bed. A token carries this verbatim as the endpoint an enrolling node dials, so on a mesh
|
||||
// whose anchor is somewhere else every node, including this one, would enrol against an
|
||||
// address nothing answers on. The installer refuses to guess it and says so, which is
|
||||
// right: it does not know what this machine is called from outside.
|
||||
bundleTemplate: substrateBundle(bundle, []).replaceAll("192.0.2.10:5671", `${ANCHOR}:5671`),
|
||||
registry: REGISTRY,
|
||||
source,
|
||||
sourceRef,
|
||||
log: (m) => console.log(m),
|
||||
});
|
||||
} catch (err) {
|
||||
throw new Error(`the installer never ran: ${(err as Error).message}`);
|
||||
}
|
||||
if (!raised.ok) throw new Error(`${raised.step || "no step named"}: ${raised.why}\n\n${raised.report.join("\n")}`);
|
||||
return raised.report.join("\n");
|
||||
});
|
||||
|
||||
// ---- 2..6. THE MESH BECOMES ONE --------------------------------------------------------------
|
||||
//
|
||||
// **Joining used to be here, second, and that was the wrong order.** Three machines were enrolled
|
||||
// into a mesh that could not yet produce a single module, and the step was reported as though
|
||||
// something had been shown. They do join — reliably — but joining a mesh that can build nothing
|
||||
// proves only that enrolment works, which was never the doubtful part.
|
||||
//
|
||||
// `17-raising-a-mesh` says it plainly: genesis ends with a mesh of one that RUNS, and that is not
|
||||
// the same as a mesh that WORKS; what remains after the core modules are built is "adding
|
||||
// machines, and deciding what they run". So everything a mesh needs to be a mesh happens first,
|
||||
// and machines arrive at the end.
|
||||
|
||||
// The toolchain and runtime every module with code of its own stands on. It is a module, and it
|
||||
// is built like one — cloned from the forge by the builder installing put here, compiled on the
|
||||
// machine, published into the mesh's own registry.
|
||||
await step(BASE_BUILT, GENESIS, async () => {
|
||||
// Registered from the manifest the builder will also read, so what the mesh holds and what it
|
||||
// builds are the same description of the same module.
|
||||
//
|
||||
// **Not swallowed.** This call used to end in `.catch(() => {})`, on the reasoning that the
|
||||
// base might already be known. It hid a real failure — the manifest was being named at a path
|
||||
// inside a container that had never seen it — and the step passed anyway, because a base with
|
||||
// nothing to stand on builds whether or not the mesh has a record of it.
|
||||
await registerModule(BASE.module, baseManifest);
|
||||
const built = await mesh(
|
||||
`build ${forgeUrl(BASE.repo)} --ref ${refFor(BASE.repo)} --wait 1200s`, 1_500_000);
|
||||
assert.doesNotMatch(built, /failed/i, built);
|
||||
return built;
|
||||
});
|
||||
|
||||
// A store of its own. **Not the substrate's.** The installer raises a store for the control
|
||||
// plane to keep its own records in, the way it raises a broker — plumbing, not a module the mesh
|
||||
// has any record of, so it provides nothing to anything. A module that wants a database wants a
|
||||
// provider in the graph, and the catalogue below is the first thing to want one.
|
||||
await step(STORE_RUNS, BASE_BUILT, () => bringUp(STORE));
|
||||
|
||||
// And the catalogue, which was missing from this test altogether.
|
||||
//
|
||||
// Without it the mesh holds no module graph: it cannot say what it has, what a module is made
|
||||
// of, what a change to one reaches, or what must be rebuilt. A mesh in that state still runs,
|
||||
// which is exactly how its absence went unnoticed — "the mesh is up" was being read off the
|
||||
// installer finishing rather than off the mesh being able to answer anything.
|
||||
await step(CATALOGUE_RUNS, STORE_RUNS, () => bringUp(CATALOGUE));
|
||||
|
||||
// The control plane, rebuilt from its own repository and rolled out.
|
||||
//
|
||||
// The installer built it once, which is what got the mesh running. Building it again THROUGH THE
|
||||
// MODULE PATH — build, notice the version moved, roll it out — is a different claim: it is the
|
||||
// moment the mesh stops depending on the installer for anything, and the first time the thing
|
||||
// that performs an upgrade performs one on itself.
|
||||
await step(CONTROL_REBUILT, CATALOGUE_RUNS, async () => {
|
||||
const built = await mesh(
|
||||
`build ${forgeUrl(CONTROL_PLANE.repo)} --ref ${sourceRef} --wait 1200s`, 1_500_000);
|
||||
assert.doesNotMatch(built, /failed/i, built);
|
||||
const rolled = await mesh(`upgrade ${CONTROL_PLANE.module} roll-out`, 900_000);
|
||||
// Asked of the machine rather than believed from the command: the control plane that answers
|
||||
// afterwards is the one that has to be running for anything below this line to mean anything.
|
||||
await waitForContainer(CONTROL, CONTROL_PLANE.container);
|
||||
return `${built}\n${rolled}`;
|
||||
});
|
||||
|
||||
// ---- 7..8. SOMETHING TO RUN ---------------------------------------------------------------
|
||||
await step(MODULE_BUILT, CONTROL_REBUILT, async () => {
|
||||
await registerModule(MODULE.module, resolve(catalogDir, MODULE.module, "module.json"));
|
||||
const built = await mesh(
|
||||
`build ${forgeUrl(MODULE.repo)} --path ${MODULE.path} --ref ${refFor(MODULE.repo)} --wait 1200s`,
|
||||
1_500_000);
|
||||
assert.doesNotMatch(built, /failed/i, built);
|
||||
// The point of the whole step: what came out is named by a digest this mesh's registry
|
||||
// assigned, not by a placeholder and not by a tag.
|
||||
const builds = await mesh(`builds ${MODULE.module}`);
|
||||
assert.match(builds, /sha256:[0-9a-f]{12}/,
|
||||
`the build recorded no digest — the module is not pinned to anything this registry serves:\n${builds}`);
|
||||
return `${built}\n${builds}`;
|
||||
});
|
||||
|
||||
// `amqp-ping` requires the `amqp` provision, and the mesh refused to place it: "nothing provides
|
||||
// amqp, wanted by amqp-ping". That refusal is correct and is the reason this step exists rather
|
||||
// than the reason to pick an easier module.
|
||||
//
|
||||
// `lavinmq` is that module. It was first added here on the belief that it needed no building —
|
||||
// its broker is an upstream image — and the mesh refused it again: two of its three containers
|
||||
// named a placeholder digest, "which is never a real image". Also right. The broker is upstream,
|
||||
// but the module is not only the broker: it carries a run-once bootstrap that writes the broker's
|
||||
// configuration, a provisioner that grants each consumer its own vhost and user, tools and an
|
||||
// event consumer, all of it its own code.
|
||||
await step(NEEDS, MODULE_BUILT, () => bringUp(PROVIDER));
|
||||
|
||||
// The machine that built it. This is the case every earlier proof covered, and it is here as the
|
||||
// control for the last step: if this fails, that one's failure says nothing about fetching.
|
||||
await step(ANCHOR_RUNS, NEEDS, async () => {
|
||||
await mesh(`module issue ${MODULE.module} --node ${CONTROL}`);
|
||||
await mesh(`assign ${CONTROL} ${MODULE.module}`);
|
||||
await mesh(`push ${CONTROL}`, 600_000);
|
||||
return waitForContainer(CONTROL, MODULE.module);
|
||||
});
|
||||
|
||||
// ---- 9. IT CAN DESCRIBE ITSELF ---------------------------------------------------------------
|
||||
//
|
||||
// **Presence is not function, and this step exists because I kept confusing them.** A container
|
||||
// being up was taken as the catalogue working; a name containing "lavinmq" was taken as the
|
||||
// module running. The mesh holds a graph — nodes, what each is assigned, what capabilities each
|
||||
// has, which claims are occupied, what each module is configured with, which provisions exist and
|
||||
// who holds them — and none of it was ever asked a question.
|
||||
await step(DESCRIBES, ANCHOR_RUNS, async () => {
|
||||
const said: string[] = [];
|
||||
|
||||
// The mesh's own verdict on itself. Nothing wrong, nothing waiting, nothing behind.
|
||||
const state = JSON.parse(await mesh("status --json")) as {
|
||||
wrong: { node: string; outcome: string; refused?: string }[];
|
||||
waiting: { node: string }[];
|
||||
reported: { node: string; outcome: string; current: boolean }[];
|
||||
};
|
||||
assert.equal(state.wrong.length, 0,
|
||||
`the mesh reports something wrong:\n${JSON.stringify(state.wrong, null, 2)}`);
|
||||
assert.equal(state.waiting.length, 0,
|
||||
`the mesh is waiting on a node:\n${JSON.stringify(state.waiting, null, 2)}`);
|
||||
const node = state.reported.find((r) => r.node === CONTROL);
|
||||
assert.ok(node, `the mesh does not report the only machine it has:\n${JSON.stringify(state)}`);
|
||||
assert.equal(node.outcome, "applied", `${CONTROL} did not apply what it was sent: ${node.outcome}`);
|
||||
assert.ok(node.current, `${CONTROL} is not running what the mesh would send it`);
|
||||
said.push(` status one node, applied, current, nothing wrong`);
|
||||
|
||||
// Every module a mesh has to hold, including the three it cannot build for itself.
|
||||
const modules = await mesh("module list");
|
||||
for (const m of MUST_HOLD) {
|
||||
assert.match(modules, new RegExp(`^${m}\\b`, "m"),
|
||||
`the mesh holds no ${m}. A mesh without it is not finished:\n${modules}`);
|
||||
}
|
||||
said.push(` module list ${MUST_HOLD.length} modules, all present`);
|
||||
|
||||
// What the machine would be sent, and what it names. **No placeholder may survive here** — a
|
||||
// digest of all zeroes is never a real image, and a declaration carrying one reaches a machine
|
||||
// that will try to fetch it.
|
||||
const plan = await mesh(`plan ${CONTROL} --json`);
|
||||
assert.doesNotMatch(plan, /sha256:0{64}/,
|
||||
`the machine's own plan names a placeholder digest, which is never a real image`);
|
||||
assert.match(plan, /sha256:[0-9a-f]{64}/, `the plan pins nothing by digest at all`);
|
||||
said.push(` plan every image pinned, no placeholders`);
|
||||
|
||||
// And the catalogue, ASKED rather than observed. These five questions are what it exists for.
|
||||
const ask = async (tool: string, args = "{}") =>
|
||||
must(CONTROL, `docker exec mesh-catalog mesh-tools invoke mesh-catalog ${tool} ${quote(args)}`,
|
||||
120_000);
|
||||
|
||||
const held = await ask("catalog_modules");
|
||||
for (const m of MUST_HOLD) {
|
||||
if (m === "registry" || m === "builder" || m === "mesh-control") continue; // carried, not built here
|
||||
assert.ok(held.includes(m), `the catalogue does not know about ${m}:\n${held}`);
|
||||
}
|
||||
assert.doesNotMatch(held, /sha256:0{64}/, `the catalogue holds a placeholder version`);
|
||||
said.push(` catalog_modules every built module, each with a version this mesh made`);
|
||||
|
||||
const provides = await ask("catalog_provides", JSON.stringify({ provision: "amqp" }));
|
||||
assert.ok(provides.includes(PROVIDER.module),
|
||||
`the catalogue cannot say what provides amqp, which is the question it exists to answer:\n${provides}`);
|
||||
said.push(` catalog_provides amqp is answered by ${PROVIDER.module}`);
|
||||
|
||||
const stale = await ask("catalog_stale");
|
||||
said.push(` catalog_stale ${stale.trim().slice(0, 120)}`);
|
||||
return said.join("\n");
|
||||
});
|
||||
|
||||
// ---- 10. AND ITS NETWORKING IS WHAT WAS ASKED FOR ---------------------------------------------
|
||||
//
|
||||
// **Left out of this test entirely until it was pointed out**, which is hard to defend: the
|
||||
// firewall is generated from what modules declare they listen on, and a firewall that opens the
|
||||
// wrong set is either a service nobody can reach or a port nobody meant to publish. Neither shows
|
||||
// up as a failed container.
|
||||
await step(NETWORK, DESCRIBES, async () => {
|
||||
const said: string[] = [];
|
||||
|
||||
const ruleset = (await on(CONTROL, `nft list table inet mesh 2>&1`)).out;
|
||||
assert.match(ruleset, /chain input/, `the mesh's own firewall table is not there:\n${ruleset}`);
|
||||
// Closed by default, or the rules below decide nothing.
|
||||
assert.match(ruleset, /policy drop/, `the firewall does not default to closed:\n${ruleset}`);
|
||||
// The floor: a machine that cannot be reached over ssh is a machine nobody can repair.
|
||||
assert.match(ruleset, /\b22\b/, `ssh is not allowed anywhere in the ruleset`);
|
||||
// What a module actually declared. The registry says it listens on 5000 for the mesh.
|
||||
assert.match(ruleset, /\b5000\b/,
|
||||
`the registry declares it listens on 5000 and nothing opened it:\n${ruleset}`);
|
||||
said.push(` firewall default closed, ssh open, declared ports open`);
|
||||
|
||||
// The names the mesh writes for itself. A consumer reaching a provider by its `.internal`
|
||||
// address depends on this file, and on it reaching inside containers.
|
||||
const hosts = (await on(CONTROL, `cat /etc/hosts`)).out;
|
||||
assert.match(hosts, /\.internal/, `the mesh wrote no .internal names:\n${hosts}`);
|
||||
said.push(` names ${(hosts.match(/[a-z0-9-]+\.internal/g) ?? []).join(" ")}`);
|
||||
|
||||
// The networks the declarations asked for, rather than whatever the runtime had lying around.
|
||||
const networks = (await on(CONTROL, `docker network ls --format '{{.Name}}'`)).out;
|
||||
for (const wanted of ["lavinmq", "amqp-ping"]) {
|
||||
assert.match(networks, new RegExp(`^${wanted}$`, "m"),
|
||||
`the ${wanted} module declares a network and none exists:\n${networks}`);
|
||||
}
|
||||
said.push(` networks module networks present`);
|
||||
return said.join("\n");
|
||||
});
|
||||
|
||||
// ---- 11. A CHANGE REACHES THE MACHINE ON ITS OWN ----------------------------------------------
|
||||
//
|
||||
// The whole point of the mesh, and the capability the migration depends on: move a module's
|
||||
// source and the running copy follows, with nobody driving the steps. Everything above is
|
||||
// machinery; this is what the machinery is for.
|
||||
await step(FOLLOWS, NETWORK, async () => {
|
||||
const before = await mesh(`builds ${MODULE.module}`);
|
||||
const wasPinned = before.match(/sha256:[0-9a-f]{64}/)?.[0] ?? "";
|
||||
assert.ok(wasPinned, `nothing is pinned to rebuild from:\n${before}`);
|
||||
|
||||
// The mesh is told its copy is older than the source. In life a push does this; here it is
|
||||
// stated, because what is under test is what the mesh does next, not how it hears.
|
||||
const head = (await must(CONTROL, `git ls-remote ${forgeUrl(MODULE.repo)} ` +
|
||||
`${refFor(MODULE.repo)} | cut -f1`, 120_000)).trim();
|
||||
assert.match(head, /^[0-9a-f]{40}$/, `could not read the source's head: ${head}`);
|
||||
await mesh(`module moved ${MODULE.module} ${head}`);
|
||||
|
||||
const behind = await mesh(`status`);
|
||||
assert.match(behind, /behind|build --behind/,
|
||||
`the mesh does not report a module behind its source:\n${behind}`);
|
||||
|
||||
await mesh(`build --behind --wait 1200s`, 1_500_000);
|
||||
const rolled = await mesh(`upgrade ${MODULE.module} roll-out`, 900_000);
|
||||
await waitForContainer(CONTROL, MODULE.module);
|
||||
|
||||
const after = await mesh(`builds ${MODULE.module}`);
|
||||
assert.match(after, /sha256:[0-9a-f]{64}/, `nothing was pinned after the rebuild:\n${after}`);
|
||||
return `${behind}\n${rolled}\n${after}`;
|
||||
});
|
||||
|
||||
// ---- 12. AND IT SURVIVES THE MACHINE STOPPING -------------------------------------------------
|
||||
//
|
||||
// **Never once tested.** A mesh that works until the machine reboots is a demonstration, not
|
||||
// something to move real services onto — and the installer is explicit that a host started the
|
||||
// way the lab starts it does not survive a reboot, which makes this the check that says whether
|
||||
// that matters.
|
||||
await step(SURVIVES, FOLLOWS, async () => {
|
||||
await restartMachine(CONTROL);
|
||||
const missing: string[] = [];
|
||||
for (const container of MUST_RUN) {
|
||||
try {
|
||||
await waitForContainer(CONTROL, container, 240);
|
||||
} catch {
|
||||
missing.push(container);
|
||||
}
|
||||
}
|
||||
const ps = (await on(CONTROL, `docker ps -a --format '{{.Names}}\t{{.Status}}'`)).out;
|
||||
assert.equal(missing.length, 0,
|
||||
`after a reboot these are not running: ${missing.join(", ")}\n\ncontainers:\n${ps}`);
|
||||
return ps;
|
||||
});
|
||||
|
||||
console.log(`\n================ WHAT THIS MESH DID FOR ITSELF ================`);
|
||||
for (const n of order) console.log(` ${steps.get(n)?.ok ? "PASS" : "FAIL"} ${n}`);
|
||||
}, { timeout: 7_200_000 });
|
||||
|
||||
after(async () => {
|
||||
if (KEEP) {
|
||||
console.log(`\nLEFT STANDING: ${instanceId} — not destroyed (MESH_LAB_KEEP).`);
|
||||
return;
|
||||
}
|
||||
if (instanceId) await destroy(instanceId);
|
||||
await destroyAll(`${SCENARIO}-`);
|
||||
}, { timeout: 900_000 });
|
||||
|
||||
for (const name of [
|
||||
GENESIS,
|
||||
BASE_BUILT,
|
||||
STORE_RUNS,
|
||||
CATALOGUE_RUNS,
|
||||
CONTROL_REBUILT,
|
||||
MODULE_BUILT,
|
||||
NEEDS,
|
||||
ANCHOR_RUNS,
|
||||
DESCRIBES,
|
||||
NETWORK,
|
||||
FOLLOWS,
|
||||
SURVIVES,
|
||||
]) {
|
||||
test(name, { skip, timeout: 60_000 }, () => {
|
||||
assert.ok(steps.get(name)?.ok, report(name));
|
||||
});
|
||||
}
|
||||
Reference in New Issue
Block a user