From 48296a7cce313993dbde25a2f17928e44440e745 Mon Sep 17 00:00:00 2001
From: Scot Schuchert-Wells <6007097+scotwells@users.noreply.github.com>
Date: Fri, 30 Oct 2026 17:24:23 +0000
Subject: [PATCH] fix: install cell CRDs on the test cell

The e2e upstream cluster plays the cell, but only config/e2e is applied to
it, which carries config/crd and not config/crd/downstream. The cell
controller manager watches NetworkLoadBalancerBackendHealth, so with that
kind absent its watch cannot sync and the manager exits every two minutes.
A NetworkInterface delete that lands in a restart window is never seen by
the write-back controller, so the published copy is not collected within a
test's 120s window.

Key changes:
- add a cell-crds task that applies config/crd/downstream to the upstream
  cluster, the same set the hub and the downstream cluster already get
- run test-infra:cell-crds in test-infra:up before prepare-upstream deploys
  the cell

Co-authored-by: polylane[bot] <277585245+polylane[bot]@users.noreply.github.com>
---
 Taskfile.test-infra.yml | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/Taskfile.test-infra.yml b/Taskfile.test-infra.yml
index 3059b673..eb1a7648 100644
--- a/Taskfile.test-infra.yml
+++ b/Taskfile.test-infra.yml
@@ -164,6 +164,9 @@ tasks:
       - task: milo-bundle
       - task: nso-image
       - task: dns-crds
+      # The cell set has to be served on this cluster before the cell controller
+      # manager starts; it watches kinds that only this set installs.
+      - task: cell-crds
       - task: prepare-upstream
       # Everything that needs a certificate has to follow prepare-upstream.
       # Upstream cert-manager crashloops with "the Gateway API CRDs do not seem
@@ -427,6 +430,16 @@ tasks:
       - '{{.KUSTOMIZE}} build config/tools/locations-crds | kubectl --context {{.UPSTREAM_CTX}} apply -f -'
       - '{{.KUSTOMIZE}} build config/tools/locations-crds | kubectl --context {{.DOWNSTREAM_CTX}} apply -f -'
 
+  cell-crds:
+    desc: "Install on the upstream cluster (which plays the cell here) the NSO CRDs every cell carries: the same config/crd/downstream union karmada-up applies to the hub and downstream-crds to the downstream cluster."
+    cmds:
+      # The cell controller manager watches NetworkLoadBalancerBackendHealth on
+      # its local cluster. A kind it watches but the cluster does not serve fails
+      # cache sync, and the manager exits after the two-minute sync timeout.
+      - |
+        {{.KUSTOMIZE}} build --load-restrictor LoadRestrictionsNone config/crd/downstream | \
+          kubectl --context {{.UPSTREAM_CTX}} apply -f -
+
   external-dns:
     desc: "Install external-dns CRDs (DNSEndpoint) on the downstream cluster."
     cmds: