From 231fe79332db8662ecefae84cac58f055d1a997b Mon Sep 17 00:00:00 2001
From: Kris <krousey@google.com>
Date: Wed, 9 May 2018 11:11:09 -0700
Subject: [PATCH] Uncordon the node after upgrade

Previous logic was relying on the node to recreate the node API object
and, as a side-effect, uncordon itself. A change went in that no
longer ensures the node recreates itself, so the bug in this logic was exposed.
---
 cluster/gce/upgrade.sh | 18 ++++++++++++------
 1 file changed, 12 insertions(+), 6 deletions(-)

diff --git a/cluster/gce/upgrade.sh b/cluster/gce/upgrade.sh
index cff430bd684..905eabe528e 100755
--- a/cluster/gce/upgrade.sh
+++ b/cluster/gce/upgrade.sh
@@ -342,15 +342,21 @@ function do-single-node-upgrade() {
     sleep 1
   done
 
-  # Wait for the node to not have SchedulingDisabled=True and also to have
-  # Ready=True.
+  # Uncordon the node.
+  echo "== Uncordon ${instance}. == " >&2
+  local uncordon_rc
+  "${KUBE_ROOT}/cluster/kubectl.sh" uncordon "${instance}" \
+    && uncordon_rc=$? || uncordon_rc=$?
+  if [[ "${uncordon_rc}" != 0 ]]; then
+    echo "== FAILED to uncordon ${instance} =="
+    return ${uncordon_rc}
+  fi
+  
+  # Wait for the node to have Ready=True.
   echo "== Waiting for ${instance} to become ready. ==" >&2
   while true; do
-    local cordoned=$("${KUBE_ROOT}/cluster/kubectl.sh" get node "${instance}" --output='jsonpath={.status.conditions[?(@.type == "SchedulingDisabled")].status}')
     local ready=$("${KUBE_ROOT}/cluster/kubectl.sh" get node "${instance}" --output='jsonpath={.status.conditions[?(@.type == "Ready")].status}')
-    if [[ "${cordoned}" == 'True' ]]; then
-      echo "Node ${instance} is still not ready: SchedulingDisabled=${ready}"
-    elif [[ "${ready}" != 'True' ]]; then
+    if [[ "${ready}" != 'True' ]]; then
       echo "Node ${instance} is still not ready: Ready=${ready}"
     else
       echo "Node ${instance} Ready=${ready}"