src/lifecycle/egress.ts

@@ -76,6 +76,19 @@ export async function confirmEgress(
       );
     }
     log(`  ${machine} reaches the internet over its uplink (${UPSTREAM} answered ${code})`);
+
+    // **Now that the path is proven, stop one dropped packet from costing a whole run.**
+    //
+    // The check above deliberately uses the uplink alone, because proving that path is the point
+    // of it. What follows is a different concern: a bed runs for hours after this, pulling images
+    // on four machines at once, and the uplink's resolver is a single server under exactly that
+    // load. Three runs have died at a lookup timeout well after this check passed — not because
+    // the path was broken, but because one query went unanswered.
+    //
+    // So the uplink stays first and keeps being used; public resolvers are appended behind it, and
+    // the retry is tightened so a silent server costs seconds rather than the step. A broken uplink
+    // still fails the check above, before any of this.
+    await resilientResolver(name);
   }
 }
 
@@ -117,6 +130,23 @@ async function reaches(name: string, waitSeconds: number): Promise<string | null
  * machine with egress that is the uplink by construction, since every scenario range is routed
  * explicitly and nothing else defaults.
  */
+/**
+ * Keep the uplink as the resolver and give it company.
+ *
+ * Appended rather than replacing: the uplink is still asked first and still proves the modelled
+ * path. The fallbacks only answer when it does not, which under a four-machine image pull is a
+ * thing that happens and has ended three runs.
+ */
+async function resilientResolver(name: string): Promise<void> {
+  await incus([
+    "exec", name, "--", "sh", "-c",
+    `via=$(ip -4 route show default | awk '{print $3}' | head -n1); ` +
+      `{ [ -n "$via" ] && printf 'nameserver %s\\n' "$via"; ` +
+      `printf 'nameserver 1.1.1.1\\nnameserver 8.8.8.8\\n'; ` +
+      `printf 'options timeout:2 attempts:3\\n'; } > /etc/resolv.conf; true`,
+  ], 30_000);
+}
+
 async function pointResolverAtTheUplink(name: string): Promise<void> {
   await incus([
     "exec", name, "--", "sh", "-c",