scenarios/store-window.yml

@@ -0,0 +1,32 @@
+# The control plane's store restarting while a machine joins (novox/hq issue 083).
+#
+# Adopting the foundation's store — the first thing a control-node does, and the first thing a
+# migration does — recreates it, and for those seconds the control plane cannot write. A machine
+# enrolling then used to be refused, or worse, left with its token spent and no identity. This
+# raises the foundation on `anchor`, takes its store away, has `laptop` enrol into the gap and
+# brings the store back: the enrolment must complete on its own.
+scenario: store-window
+
+segments:
+  hosting:
+    kind: public
+    cidr: [192.0.2.0/24]
+
+machines:
+  anchor:
+    at: { segment: hosting, address: [192.0.2.10] }
+    egress: true
+    inbound: allow
+    memory: 3GiB
+    cpus: 2
+  laptop:
+    at: { segment: hosting, address: [192.0.2.20] }
+    egress: true
+    inbound: allow
+    memory: 1GiB
+
+images:
+  - mesh-controller:development
+
+place:
+  all: [host, runtime]

test/integration/store-window.test.ts

@@ -0,0 +1,198 @@
+/**
+ * **Nothing a machine sends while the store restarts is lost** (novox/hq issues 082, 083).
+ *
+ * The foundation's store is recreated when it is adopted, and for those seconds the control plane
+ * cannot write. This bed takes the store away on the control-node, has a second machine enrol into
+ * the gap, and brings the store back after the control plane has had to say "not now":
+ *
+ *   - a report arriving in the gap is held, and recorded when the store is back;
+ *   - the enrolment is answered "not now" while that report is held — not queued behind it — and
+ *     completes on its own when the store is back, with the keys it started with: the mesh holds
+ *     the very keys the machine generated;
+ *   - the machine then applies what it is pushed and is heard from.
+ *
+ * It needs a host binary and the foundation bundle:
+ *
+ *   MESH_LAB_HOST_BINARY=.../mesh-host
+ *   MESH_LAB_BUNDLE=.../examples/foundation-first-node.lock
+ */
+import { test, before, after } from "node:test";
+import assert from "node:assert/strict";
+import { existsSync } from "node:fs";
+import { loadScenario } from "../../src/declaration/parse.ts";
+import { raise } from "../../src/lifecycle/raise.ts";
+import { destroy, exec } from "../../src/lifecycle/operate.ts";
+import { hostBinaryPath, HOST_PATH } from "../../src/lifecycle/place.ts";
+import { labIsUsable, destroyAll, foundationBundle, onTheMachine } from "./harness.ts";
+import type { HeldImage } from "../../src/pinning.ts";
+
+const capability = await labIsUsable();
+const binary = hostBinaryPath();
+const bundle = process.env["MESH_LAB_BUNDLE"] ?? "";
+
+const skip = !capability.usable
+  ? `lab not usable: ${capability.why}`
+  : !binary || !existsSync(binary)
+    ? "MESH_LAB_HOST_BINARY is not set to a built mesh-host"
+    : !bundle || !existsSync(bundle)
+      ? "MESH_LAB_BUNDLE is not set to a foundation bundle (mesh-host examples/)"
+      : false;
+
+const SCENARIO = "store-window";
+let instanceId = "";
+let held: HeldImage[] = [];
+
+function quote(s: string): string {
+  return `'${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("anchor", `docker exec mesh-controller /mesh-controller ${command}`, timeoutMs);
+}
+
+function tokenFrom(said: string): string {
+  const found = said.split("\n").map((l) => l.trim()).find((l) => l.length > 100 && !l.includes(" "));
+  assert.ok(found, `no token in:\n${said}`);
+  return found;
+}
+
+async function until(what: string, within: number, check: () => Promise<boolean>, why: () => Promise<string>): Promise<void> {
+  const end = Date.now() + within;
+  while (Date.now() < end) {
+    if (await check()) return;
+    await new Promise((r) => setTimeout(r, 3000));
+  }
+  assert.fail(`${what} did not happen within ${Math.round(within / 1000)}s:\n${await why()}`);
+}
+
+before(async () => {
+  if (skip) return;
+  const raised = await raise(loadScenario(`scenarios/${SCENARIO}.yml`), {
+    onProgress: (m) => console.log(`raise: ${m}`),
+  });
+  instanceId = raised.instanceId;
+  held = raised.images;
+
+  await must("anchor", `cat > /tmp/foundation.lock <<'MESHBUNDLE'\n${foundationBundle(bundle, raised.images)}\nMESHBUNDLE`);
+  await must("anchor", `${HOST_PATH} apply /tmp/foundation.lock`, 600_000);
+  const up = await must("anchor", `docker ps --format '{{.Names}}'`);
+  for (const c of ["mesh-store", "mesh-broker", "mesh-controller"]) {
+    assert.match(up, new RegExp(c), `the foundation did not raise ${c}:\n${up}`);
+  }
+  await mesh("node add anchor");
+  const own = tokenFrom(await mesh("token issue --node anchor"));
+  await must("anchor", `${HOST_PATH} enrol --token ${quote(own)}`);
+  await must("anchor", `nohup ${HOST_PATH} run > /var/log/mesh-host.log 2>&1 & sleep 3`);
+}, { timeout: 1_800_000 });
+
+after(async () => {
+  if (process.env["MESH_LAB_KEEP"]) { console.log(`MESH_LAB_KEEP set — leaving ${instanceId} standing`); return; }
+  if (instanceId) await destroy(instanceId);
+  await destroyAll(`${SCENARIO}-`);
+}, { timeout: 600_000 });
+
+test("a machine enrolling while the store is away joins when it comes back, with the keys it started with", {
+  skip, timeout: 900_000,
+}, async () => {
+  await mesh("node add laptop");
+  const token = tokenFrom(await mesh("token issue --node laptop"));
+
+  // A report that will arrive in the gap: the anchor is pushed a step that takes ten seconds, so
+  // its report lands after the store has gone.
+  const sleeper = onTheMachine("alpine", held);
+  await must("anchor", `printf %s '{"module":"slow","version":"1","resources":[` +
+    `{"id":"step","type":"container","name":"slow-step","image":"${sleeper}","run-once":true,` +
+    `"args":["sh","-c","sleep 10"]}]}' > /tmp/slow.json`);
+  await must("anchor", `docker cp /tmp/slow.json mesh-controller:/slow.json`);
+  await mesh("module add /slow.json");
+  await mesh("assign anchor slow");
+  await mesh("push anchor");
+
+  // The store goes away, as it does when the foundation is adopted; the broker stays, so the
+  // report and the enrolment reach the control plane and the control plane cannot write.
+  await must("anchor", `docker stop mesh-store`);
+  await until("the anchor's report arriving in the gap and being held", 120_000,
+    async () => /could not keep anchor's report .*holding it/.test((await on("anchor", `docker logs mesh-controller 2>&1`)).out),
+    async () => `--- controller ---\n${(await on("anchor", `docker logs --tail 30 mesh-controller 2>&1`)).out}\n` +
+      `--- anchor host ---\n${(await on("anchor", `tail -10 /var/log/mesh-host.log`)).out}`);
+
+  // The machine enrols into the gap. In the background: it will be told "not now" and keep asking.
+  await must("laptop", `nohup sh -c ${quote(`${HOST_PATH} enrol --token ${quote(token)} > /tmp/enrol.log 2>&1; ` +
+    `echo "exit=$?" >> /tmp/enrol.log`)} > /dev/null 2>&1 & sleep 1`);
+
+  // The control plane said "not now" at least once, while the anchor's report was held — so the
+  // gap was hit, and the enrolment was answered rather than queued behind what the store owed.
+  await until("the control plane asking the machine to enrol again", 90_000,
+    async () => /asked "laptop" to enrol again/.test((await on("anchor", `docker logs mesh-controller 2>&1`)).out),
+    async () => `--- controller ---\n${(await on("anchor", `docker logs --tail 30 mesh-controller 2>&1`)).out}\n` +
+      `--- laptop enrol ---\n${(await on("laptop", `cat /tmp/enrol.log`)).out}`);
+
+  // The store comes back; the enrolment completes on its own, with nothing done by hand.
+  await must("anchor", `docker start mesh-store`);
+  await until("the enrolment completing", 150_000,
+    async () => /exit=/.test((await on("laptop", `cat /tmp/enrol.log`)).out),
+    async () => `--- laptop enrol ---\n${(await on("laptop", `cat /tmp/enrol.log`)).out}\n` +
+      `--- controller ---\n${(await on("anchor", `docker logs --tail 30 mesh-controller 2>&1`)).out}`);
+  const said = (await on("laptop", `cat /tmp/enrol.log`)).out;
+  assert.match(said, /exit=0/, `the enrolment did not complete after the store came back:\n${said}`);
+  assert.match(said, /enrolled as laptop/, `the machine was not enrolled as laptop:\n${said}`);
+
+  // The mesh holds the very keys the machine generated at the start: its identity is the live key,
+  // and its sealing key is the one on its record.
+  const identity = said.match(/generated this node's identity: (\S+)/)?.[1];
+  const sealing = said.match(/generated this node's sealing key:\s+(\S+)/)?.[1];
+  assert.ok(identity && sealing, `the enrolment did not say which keys it generated:\n${said}`);
+  const nodeId = (await must("anchor", `docker exec mesh-store psql -U postgres -d inventory -qAt ` +
+    `-c "select id from node where name = 'laptop'"`)).trim();
+  const live = (await must("anchor", `docker exec mesh-store psql -U postgres -d identity -qAt ` +
+    `-c "select encode(public, 'base64') from node_key where node = '${nodeId}' and revoked is null"`)).trim();
+  assert.equal(live, identity, `the mesh's live key for laptop is not the one it generated`);
+  const sealedTo = (await must("anchor", `docker exec mesh-store psql -U postgres -d inventory -qAt ` +
+    `-c "select sealing_key from node where name = 'laptop'"`)).trim();
+  assert.equal(sealedTo, sealing, `the mesh's sealing key for laptop is not the one it generated`);
+
+  // The report held through the gap was recorded once the store was back.
+  await until("the anchor's held report being recorded", 60_000,
+    async () => {
+      const r = await on("anchor", `docker exec mesh-controller /mesh-controller status --json`);
+      if (!r.ok) return false;
+      const state = JSON.parse(r.out) as { reported: { node: string; outcome: string; current: boolean }[] };
+      return state.reported.some((w) => w.node === "anchor" && w.outcome === "applied" && w.current);
+    },
+    async () => (await on("anchor", `docker logs --tail 20 mesh-controller 2>&1`)).out);
+
+  // And the machine is a working member: pushed something, it applies it and is heard from.
+  await must("laptop", `nohup ${HOST_PATH} run > /var/log/mesh-host.log 2>&1 & sleep 3`);
+  await must("anchor", `printf %s '{"module":"marker","version":"1","resources":[` +
+    `{"id":"marker","type":"file","path":"/etc/store-window","content":"joined\\\\n","mode":"0644"}]}' > /tmp/marker.json`);
+  await must("anchor", `docker cp /tmp/marker.json mesh-controller:/marker.json`);
+  await mesh("module add /marker.json");
+  await mesh("assign laptop marker");
+  await mesh("push laptop");
+  await until("the machine applying what it was pushed", 120_000,
+    async () => (await on("laptop", `grep -q joined /etc/store-window`)).ok,
+    async () => (await on("laptop", `tail -20 /var/log/mesh-host.log`)).out);
+  await until("the mesh hearing the machine's report", 120_000,
+    async () => {
+      const r = await on("anchor", `docker exec mesh-controller /mesh-controller status --json`);
+      if (!r.ok) return false;
+      const state = JSON.parse(r.out) as { reported: { node: string; outcome: string; current: boolean }[] };
+      return state.reported.some((w) => w.node === "laptop" && w.outcome === "applied" && w.current);
+    },
+    async () => (await on("anchor", `docker exec mesh-controller /mesh-controller status 2>&1`)).out);
+});