typhoon/bare-metal/container-linux/kubernetes/cl/controller.yaml.tmpl
Dalton Hubble 2837275265 Introduce cluster creation without local writes to asset_dir
* Allow generated assets (TLS materials, manifests) to be
securely distributed to controller node(s) via file provisioner
(i.e. ssh-agent) as an assets bundle file, rather than relying
on assets being locally rendered to disk in an asset_dir and
then securely distributed
* Change `asset_dir` from required to optional. Left unset,
asset_dir defaults to "" and no assets will be written to
files on the machine that runs terraform apply
* Enhancement: Managed cluster assets are kept only in Terraform
state, which supports different backends (GCS, S3, etcd, etc) and
optional encryption. terraform apply accesses state, runs in-memory,
and distributes sensitive materials to controllers without making
use of local disk (simplifies use in CI systems)
* Enhancement: Improve asset unpack and layout process to position
etcd certificates and control plane certificates more cleanly,
without unneeded secret materials

Details:

* Terraform file provisioner support for distributing directories of
contents (with unknown structure) has been limited to reading from a
local directory, meaning local writes to asset_dir were required.
https://github.com/poseidon/typhoon/issues/585 discusses the problem
and newer or upcoming Terraform features that might help.
* Observation: Terraform provisioner support for single files works
well, but iteration isn't viable. We're also constrained to Terraform
language features on the apply side (no extra plugins, no shelling out)
and CoreOS / Fedora tools on the receive side.
* Take a map representation of the contents that would have been splayed
out in asset_dir and pack/encode them into a single file format devised
for easy unpacking. Use an awk one-liner on the receive side to unpack.
In pratice, this has worked well and its rather nice that a single
assets file is transferred by file provisioner (all or none)

Rel: https://github.com/poseidon/terraform-render-bootstrap/pull/162
2019-12-05 01:24:50 -08:00

200 lines
8.3 KiB
Cheetah

---
systemd:
units:
- name: etcd-member.service
enable: true
dropins:
- name: 40-etcd-cluster.conf
contents: |
[Service]
Environment="ETCD_IMAGE_TAG=v3.4.3"
Environment="ETCD_NAME=${etcd_name}"
Environment="ETCD_ADVERTISE_CLIENT_URLS=https://${domain_name}:2379"
Environment="ETCD_INITIAL_ADVERTISE_PEER_URLS=https://${domain_name}:2380"
Environment="ETCD_LISTEN_CLIENT_URLS=https://0.0.0.0:2379"
Environment="ETCD_LISTEN_PEER_URLS=https://0.0.0.0:2380"
Environment="ETCD_LISTEN_METRICS_URLS=http://0.0.0.0:2381"
Environment="ETCD_INITIAL_CLUSTER=${etcd_initial_cluster}"
Environment="ETCD_STRICT_RECONFIG_CHECK=true"
Environment="ETCD_SSL_DIR=/etc/ssl/etcd"
Environment="ETCD_TRUSTED_CA_FILE=/etc/ssl/certs/etcd/server-ca.crt"
Environment="ETCD_CERT_FILE=/etc/ssl/certs/etcd/server.crt"
Environment="ETCD_KEY_FILE=/etc/ssl/certs/etcd/server.key"
Environment="ETCD_CLIENT_CERT_AUTH=true"
Environment="ETCD_PEER_TRUSTED_CA_FILE=/etc/ssl/certs/etcd/peer-ca.crt"
Environment="ETCD_PEER_CERT_FILE=/etc/ssl/certs/etcd/peer.crt"
Environment="ETCD_PEER_KEY_FILE=/etc/ssl/certs/etcd/peer.key"
Environment="ETCD_PEER_CLIENT_CERT_AUTH=true"
- name: docker.service
enable: true
- name: locksmithd.service
mask: true
- name: kubelet.path
enable: true
contents: |
[Unit]
Description=Watch for kubeconfig
[Path]
PathExists=/etc/kubernetes/kubeconfig
[Install]
WantedBy=multi-user.target
- name: wait-for-dns.service
enable: true
contents: |
[Unit]
Description=Wait for DNS entries
Wants=systemd-resolved.service
Before=kubelet.service
[Service]
Type=oneshot
RemainAfterExit=true
ExecStart=/bin/sh -c 'while ! /usr/bin/grep '^[^#[:space:]]' /etc/resolv.conf > /dev/null; do sleep 1; done'
[Install]
RequiredBy=kubelet.service
RequiredBy=etcd-member.service
- name: kubelet.service
contents: |
[Unit]
Description=Kubelet via Hyperkube
Wants=rpc-statd.service
[Service]
EnvironmentFile=/etc/kubernetes/kubelet.env
Environment="RKT_RUN_ARGS=--uuid-file-save=/var/cache/kubelet-pod.uuid \
--volume=resolv,kind=host,source=/etc/resolv.conf \
--mount volume=resolv,target=/etc/resolv.conf \
--volume var-lib-cni,kind=host,source=/var/lib/cni \
--mount volume=var-lib-cni,target=/var/lib/cni \
--volume var-lib-calico,kind=host,source=/var/lib/calico \
--mount volume=var-lib-calico,target=/var/lib/calico \
--volume opt-cni-bin,kind=host,source=/opt/cni/bin \
--mount volume=opt-cni-bin,target=/opt/cni/bin \
--volume var-log,kind=host,source=/var/log \
--mount volume=var-log,target=/var/log \
--volume iscsiconf,kind=host,source=/etc/iscsi/ \
--mount volume=iscsiconf,target=/etc/iscsi/ \
--volume iscsiadm,kind=host,source=/usr/sbin/iscsiadm \
--mount volume=iscsiadm,target=/sbin/iscsiadm \
--insecure-options=image"
Environment=KUBELET_CGROUP_DRIVER=${cgroup_driver}
ExecStartPre=/bin/mkdir -p /etc/kubernetes/cni/net.d
ExecStartPre=/bin/mkdir -p /etc/kubernetes/manifests
ExecStartPre=/bin/mkdir -p /opt/cni/bin
ExecStartPre=/bin/mkdir -p /var/lib/cni
ExecStartPre=/bin/mkdir -p /var/lib/calico
ExecStartPre=/bin/mkdir -p /var/lib/kubelet/volumeplugins
ExecStartPre=/usr/bin/bash -c "grep 'certificate-authority-data' /etc/kubernetes/kubeconfig | awk '{print $2}' | base64 -d > /etc/kubernetes/ca.crt"
ExecStartPre=-/usr/bin/rkt rm --uuid-file=/var/cache/kubelet-pod.uuid
ExecStart=/usr/lib/coreos/kubelet-wrapper \
--anonymous-auth=false \
--authentication-token-webhook \
--authorization-mode=Webhook \
--cgroup-driver=$${KUBELET_CGROUP_DRIVER} \
--client-ca-file=/etc/kubernetes/ca.crt \
--cluster_dns=${cluster_dns_service_ip} \
--cluster_domain=${cluster_domain_suffix} \
--cni-conf-dir=/etc/kubernetes/cni/net.d \
--exit-on-lock-contention \
--hostname-override=${domain_name} \
--kubeconfig=/etc/kubernetes/kubeconfig \
--lock-file=/var/run/lock/kubelet.lock \
--network-plugin=cni \
--node-labels=node.kubernetes.io/master \
--node-labels=node.kubernetes.io/controller="true" \
--pod-manifest-path=/etc/kubernetes/manifests \
--read-only-port=0 \
--register-with-taints=node-role.kubernetes.io/master=:NoSchedule \
--volume-plugin-dir=/var/lib/kubelet/volumeplugins
ExecStop=-/usr/bin/rkt stop --uuid-file=/var/cache/kubelet-pod.uuid
Restart=always
RestartSec=10
[Install]
WantedBy=multi-user.target
- name: bootstrap.service
contents: |
[Unit]
Description=Kubernetes control plane
ConditionPathExists=!/opt/bootstrap/bootstrap.done
[Service]
Type=oneshot
RemainAfterExit=true
WorkingDirectory=/opt/bootstrap
ExecStartPre=-/usr/bin/bash -c 'set -x && [ -n "$(ls /opt/bootstrap/assets/manifests-*/* 2>/dev/null)" ] && mv /opt/bootstrap/assets/manifests-*/* /opt/bootstrap/assets/manifests && rm -rf /opt/bootstrap/assets/manifests-*'
ExecStart=/usr/bin/rkt run \
--trust-keys-from-https \
--volume config,kind=host,source=/etc/kubernetes/bootstrap-secrets \
--mount volume=config,target=/etc/kubernetes/secrets \
--volume assets,kind=host,source=/opt/bootstrap/assets \
--mount volume=assets,target=/assets \
--volume script,kind=host,source=/opt/bootstrap/apply \
--mount volume=script,target=/apply \
--insecure-options=image \
docker://k8s.gcr.io/hyperkube:v1.16.3 \
--net=host \
--dns=host \
--exec=/apply
ExecStartPost=/bin/touch /opt/bootstrap/bootstrap.done
[Install]
WantedBy=multi-user.target
storage:
files:
- path: /etc/kubernetes/kubelet.env
filesystem: root
mode: 0644
contents:
inline: |
KUBELET_IMAGE_URL=docker://k8s.gcr.io/hyperkube
KUBELET_IMAGE_TAG=v1.16.3
- path: /etc/hostname
filesystem: root
mode: 0644
contents:
inline:
${domain_name}
- path: /opt/bootstrap/layout
filesystem: root
mode: 0544
contents:
inline: |
#!/bin/bash -e
mkdir -p -- auth tls/etcd tls/k8s static-manifests manifests/coredns manifests-networking
awk '/#####/ {filename=$2; next} {print > filename}' assets
mkdir -p /etc/ssl/etcd/etcd
mkdir -p /etc/kubernetes/bootstrap-secrets
mv tls/etcd/{peer*,server*} /etc/ssl/etcd/etcd/
mv tls/etcd/etcd-client* /etc/kubernetes/bootstrap-secrets/
chown -R etcd:etcd /etc/ssl/etcd
chmod -R 500 /etc/ssl/etcd
mv auth/kubeconfig /etc/kubernetes/bootstrap-secrets/
mv tls/k8s/* /etc/kubernetes/bootstrap-secrets/
sudo mkdir -p /etc/kubernetes/manifests
sudo mv static-manifests/* /etc/kubernetes/manifests/
sudo mkdir -p /opt/bootstrap/assets
sudo mv manifests /opt/bootstrap/assets/manifests
sudo mv manifests-networking /opt/bootstrap/assets/manifests-networking
rm -rf assets auth static-manifests tls
- path: /opt/bootstrap/apply
filesystem: root
mode: 0544
contents:
inline: |
#!/bin/bash -e
export KUBECONFIG=/etc/kubernetes/secrets/kubeconfig
until kubectl version; do
echo "Waiting for static pod control plane"
sleep 5
done
until kubectl apply -f /assets/manifests -R; do
echo "Retry applying manifests"
sleep 5
done
- path: /etc/sysctl.d/max-user-watches.conf
filesystem: root
contents:
inline: |
fs.inotify.max_user_watches=16184
passwd:
users:
- name: core
ssh_authorized_keys:
- ${ssh_authorized_key}