update redis stuff

.gitignore

@@ -0,0 +1 @@
+temp.yaml

backup-cronjobs.yaml

@@ -17,7 +17,7 @@ spec:
                 - name: ETCDCTL_API
                   value: "3"
               command: ["/bin/sh"]
-              args: ["-c", "etcdctl --endpoints=https://127.0.0.1:2379 --cacert=/etc/kubernetes/pki/etcd/ca.crt --cert=/etc/kubernetes/pki/etcd/healthcheck-client.crt --key=/etc/kubernetes/pki/etcd/healthcheck-client.key snapshot save /backup/etcd/snapshot-$(date +%Y-%m-%d_%H-%M-%S_%Z).db"]
+              args: ["-c", "etcdctl --endpoints=https://127.0.0.1:2379 --cacert=/etc/kubernetes/pki/etcd/ca.crt --cert=/etc/kubernetes/pki/etcd/healthcheck-client.crt --key=/etc/kubernetes/pki/etcd/healthcheck-client.key snapshot save /backup/etcd/snapshot-$(printf \"%(%Y-%m-%d-%H:%M:%S_%Z)T\n\").db"]
               volumeMounts:
                 - mountPath: /etc/kubernetes/pki/etcd
                   name: etcd-certs
@@ -47,7 +47,7 @@ spec:
                 claimName: backups-nfs-pvc
 ---
 
-apiVersion: batch/v1beta1
+apiVersion: batch/v1
 kind: CronJob
 metadata:
   name: pg-bakcup

datadog-values.yaml

@@ -178,9 +178,8 @@ datadog:
   apm:
     # datadog.apm.enabled -- Enable this to enable APM and tracing, on port 8126
     ## ref: https://github.com/DataDog/docker-dd-agent#tracing-from-the-host
-    portEnabled: true
-    socketEnabled: false
-    enabled: true
+    portEnabled: false
+    socketEnabled: true
 
     # datadog.apm.port -- Override the trace Agent port
     ## Note: Make sure your client is sending to the same UDP port.

once-etcd-job.yaml

@@ -1,10 +1,11 @@
 apiVersion: batch/v1
 kind: Job
 metadata:
-  name: etcd-snapshot
+  name: etcd-snapshot-once
   namespace: default
 spec:
   backoffLimit: 3
+  ttlSecondsAfterFinished: 60
   template:
     spec:
       containers:
@@ -15,7 +16,7 @@ spec:
             - name: ETCDCTL_API
               value: "3"
           command: ["/bin/sh"]
-          args: ["-c", "etcdctl --endpoints=https://127.0.0.1:2379 --cacert=/etc/kubernetes/pki/etcd/ca.crt --cert=/etc/kubernetes/pki/etcd/healthcheck-client.crt --key=/etc/kubernetes/pki/etcd/healthcheck-client.key snapshot save /backup/etcd/snapshot-$(date +%Y-%m-%d_%H-%M-%S_%Z).db"]
+          args: ["-c", "etcdctl --endpoints=https://127.0.0.1:2379 --cacert=/etc/kubernetes/pki/etcd/ca.crt --cert=/etc/kubernetes/pki/etcd/healthcheck-client.crt --key=/etc/kubernetes/pki/etcd/healthcheck-client.key snapshot save /backup/etcd/snapshot-$(printf \"%(%Y-%m-%d-%H:%M:%S_%Z)T\n\").db"]
           volumeMounts:
             - mountPath: /etc/kubernetes/pki/etcd
               name: etcd-certs

prometheus-values.yaml

@@ -678,6 +678,8 @@ prometheus:
   #    verbs: [ "get", "list", "watch" ]
 
 grafana:
+  serviceMonitor:
+    enabled: true
   persistence:
     enabled: true
     storageClassName: manual
@@ -687,3 +689,10 @@ grafana:
   securityContext:
     fsGroup: 1000
     runAsUser: 1000
+
+kubeEtcd:
+  enabled: true
+  service:
+    enabled: true
+    port: 2381
+    targetPort: 2381

recovery.sh

@@ -56,3 +56,22 @@ kubectl -n kube-system apply -f https://raw.githubusercontent.com/coreos/flannel
 
 vim /etc/systemd/system/kubelet.service.d/10-kubeadm.conf
 # update KUBELET_CGROUP_ARGS=--cgroup-driver=systemd to KUBELET_CGROUP_ARGS=--cgroup-driver=cgroupfs
+
+
+## Add new nodes as control plane
+
+# first prepre certificate key, run this one the existing control plan
+kubeadm init phase upload-certs --upload-certs
+
+
+# run the following the node to be added
+kubeadm join 192.168.1.2:6443 --token xxx --discovery-token-ca-cert-hash sha256:xxx --control-plane --certificate-key xxx
+
+
+# disbale swap
+
+sudo swapoff -a
+sudo rm /swap.img
+vim /etc/fstab  # and remove swap
+# check
+sudo swapon --show