nixos/kubernetes: Stabilize services startup across machines

by adding targets and curl wait loops to services to ensure services
are not started before their depended services are reachable.

Extra targets cfssl-online.target and kube-apiserver-online.target
syncronize starts across machines and node-online.target ensures
docker is restarted and ready to deploy containers on after flannel
has discussed the network cidr with apiserver.

Since flannel needs to be started before addon-manager to configure
the docker interface, it has to have its own rbac bootstrap service.

The curl wait loops within the other services exists to ensure that when
starting the service it is able to do its work immediately without
clobbering the log about failing conditions.

By ensuring kubernetes.target is only reached after starting the
cluster it can be used in the tests as a wait condition.

In kube-certmgr-bootstrap mkdir is needed for it to not fail to start.

The following is the relevant part of systemctl list-dependencies

default.target
● ├─certmgr.service
● ├─cfssl.service
● ├─docker.service
● ├─etcd.service
● ├─flannel.service
● ├─kubernetes.target
● │ ├─kube-addon-manager.service
● │ ├─kube-proxy.service
● │ ├─kube-apiserver-online.target
● │ │ ├─flannel-rbac-bootstrap.service
● │ │ ├─kube-apiserver-online.service
● │ │ ├─kube-apiserver.service
● │ │ ├─kube-controller-manager.service
● │ │ └─kube-scheduler.service
● │ └─node-online.target
● │   ├─node-online.service
● │   ├─flannel.target
● │   │ ├─flannel.service
● │   │ └─mk-docker-opts.service
● │   └─kubelet.target
● │     └─kubelet.service
● ├─network-online.target
● │ └─cfssl-online.target
● │   ├─certmgr.service
● │   ├─cfssl-online.service
● │   └─kube-certmgr-bootstrap.service

2 files changed, 7 insertions, 0 deletions

diff --git a/nixos/tests/kubernetes/dns.nix b/nixos/tests/kubernetes/dns.nix
index 46bcb01a52652..e7db0a58ab616 100644
--- a/nixos/tests/kubernetes/dns.nix
+++ b/nixos/tests/kubernetes/dns.nix
@@ -77,6 +77,7 @@ let
   singleNodeTest = {
     test = ''
       # prepare machine1 for test
+      $machine1->waitForUnit("kubernetes.target");
       $machine1->waitUntilSucceeds("kubectl get node machine1.${domain} | grep -w Ready");
       $machine1->waitUntilSucceeds("docker load < ${redisImage}");
       $machine1->waitUntilSucceeds("kubectl create -f ${redisPod}");
@@ -102,6 +103,8 @@ let
       # Node token exchange
       $machine1->waitUntilSucceeds("cp -f /var/lib/cfssl/apitoken.secret /tmp/shared/apitoken.secret");
       $machine2->waitUntilSucceeds("cat /tmp/shared/apitoken.secret | nixos-kubernetes-node-join");
+      $machine1->waitForUnit("kubernetes.target");
+      $machine2->waitForUnit("kubernetes.target");
 
       # prepare machines for test
       $machine1->waitUntilSucceeds("kubectl get node machine2.${domain} | grep -w Ready");
diff --git a/nixos/tests/kubernetes/rbac.nix b/nixos/tests/kubernetes/rbac.nix
index 3ce7adcd0d717..967fe506004fd 100644
--- a/nixos/tests/kubernetes/rbac.nix
+++ b/nixos/tests/kubernetes/rbac.nix
@@ -94,6 +94,8 @@ let
 
   singlenode = base // {
     test = ''
+      $machine1->waitForUnit("kubernetes.target");
+
       $machine1->waitUntilSucceeds("kubectl get node machine1.my.zyx | grep -w Ready");
 
       $machine1->waitUntilSucceeds("docker load < ${kubectlImage}");
@@ -116,6 +118,8 @@ let
       # Node token exchange
       $machine1->waitUntilSucceeds("cp -f /var/lib/cfssl/apitoken.secret /tmp/shared/apitoken.secret");
       $machine2->waitUntilSucceeds("cat /tmp/shared/apitoken.secret | nixos-kubernetes-node-join");
+      $machine1->waitForUnit("kubernetes.target");
+      $machine2->waitForUnit("kubernetes.target");
 
       $machine1->waitUntilSucceeds("kubectl get node machine2.my.zyx | grep -w Ready");