test/integration/store-window.test.ts

@@ -5,9 +5,10 @@
  * 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":
  *
- *   - the enrolment completes on its own, with the keys it started with — the host asked again
- *     while the mesh said it could not answer, and the token was not spent until it could;
- *   - the control plane really did say "not now", so the gap was hit, not missed;
+ *   - 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:
@@ -22,7 +23,8 @@ 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 } from "./harness.ts";
+import { labIsUsable, destroyAll, foundationBundle, onTheMachine } from "./harness.ts";
+import type { HeldImage } from "../../src/pinning.ts";
 
 const capability = await labIsUsable();
 const binary = hostBinaryPath();
@@ -38,6 +40,7 @@ const skip = !capability.usable
 
 const SCENARIO = "store-window";
 let instanceId = "";
+let held: HeldImage[] = [];
 
 function quote(s: string): string {
   return `'${s.replaceAll("'", `'\\''`)}'`;
@@ -83,6 +86,7 @@ before(async () => {
     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);
@@ -108,15 +112,31 @@ test("a machine enrolling while the store is away joins when it comes back, with
   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":"${sleeper}","run-once":true,` +
+    `"args":["sh","-c","sleep 10"]}]}' > /tmp/slow.json`);
+  await must("anchor", `docker cp /tmp/slow.json mesh-controller:/slow.json`);
+  await mesh("module add /slow.json");
+  await mesh("assign anchor slow");
+  await mesh("push anchor");
+
   // The store goes away, as it does when the foundation is adopted; the broker stays, so the
-  // enrolment reaches the control plane and the control plane cannot write.
+  // report and the enrolment reach the control plane and the control plane cannot write.
   await must("anchor", `docker stop mesh-store`);
+  await until("the anchor's report arriving in the gap and being held", 120_000,
+    async () => /could not keep anchor's report .*holding it/.test((await on("anchor", `docker logs mesh-controller 2>&1`)).out),
+    async () => `--- controller ---\n${(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 — so the gap was hit, not missed.
+  // 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${(await on("anchor", `docker logs --tail 30 mesh-controller 2>&1`)).out}\n` +
@@ -132,16 +152,29 @@ test("a machine enrolling while the store is away joins when it comes back, with
   assert.match(said, /exit=0/, `the enrolment did not complete after the store came back:\n${said}`);
   assert.match(said, /enrolled as laptop/, `the machine was not enrolled as laptop:\n${said}`);
 
-  // Enrolled with the keys it generated at the start — one attempt, not a new identity — and the
-  // mesh holds its sealing key, which it recorded only once the store was back.
-  const generated = said.match(/generated this node's identity: (\S+)/);
-  assert.ok(generated, `the enrolment did not say which identity it generated:\n${said}`);
-  assert.equal((said.match(/generated this node's identity:/g) ?? []).length, 1,
-    `the machine generated more than one identity:\n${said}`);
-  const recorded = await must("anchor",
-    `docker exec mesh-store psql -U postgres -d inventory -qAt ` +
-      `-c "select name from node where sealing_key is not null order by name"`);
-  assert.match(recorded, /(^|\n)laptop(\n|$)/, `the mesh holds no sealing key for laptop:\n${recorded}`);
+  // 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`);