From 4d79c56d6759bb4102cf23afdc4344c16435ff7a Mon Sep 17 00:00:00 2001 From: Junwei Zhao Date: Mon, 21 Mar 2022 18:28:26 +1100 Subject: [PATCH] update redis stuff --- .gitignore | 1 + backup-cronjobs.yaml | 4 ++-- datadog-values.yaml | 5 ++--- once-etcd-job.yaml | 5 +++-- prometheus-values.yaml | 9 +++++++++ recovery.sh | 19 +++++++++++++++++++ 6 files changed, 36 insertions(+), 7 deletions(-) create mode 100644 .gitignore diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..f4156f9 --- /dev/null +++ b/.gitignore @@ -0,0 +1 @@ +temp.yaml diff --git a/backup-cronjobs.yaml b/backup-cronjobs.yaml index ddb126f..dfe4632 100644 --- a/backup-cronjobs.yaml +++ b/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 diff --git a/datadog-values.yaml b/datadog-values.yaml index e7c9cd6..41aea35 100644 --- a/datadog-values.yaml +++ b/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. diff --git a/once-etcd-job.yaml b/once-etcd-job.yaml index 0c8cb33..998f72a 100644 --- a/once-etcd-job.yaml +++ b/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 diff --git a/prometheus-values.yaml b/prometheus-values.yaml index 5a2476a..1112002 100644 --- a/prometheus-values.yaml +++ b/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 diff --git a/recovery.sh b/recovery.sh index 3c8a0ce..b737688 100644 --- a/recovery.sh +++ b/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