1
0
Fork 0
mirror of https://github.com/poseidon/typhoon synced 2024-06-01 20:36:08 +02:00
typhoon/bare-metal/fedora-coreos/kubernetes/fcc/controller.yaml

223 lines
8.5 KiB
YAML
Raw Normal View History

---
variant: fcos
version: 1.0.0
systemd:
units:
- name: etcd-member.service
enabled: true
contents: |
[Unit]
Description=etcd (System Container)
Documentation=https://github.com/coreos/etcd
Wants=network-online.target network.target
After=network-online.target
[Service]
# https://github.com/opencontainers/runc/pull/1807
# Type=notify
# NotifyAccess=exec
Type=exec
Restart=on-failure
RestartSec=10s
TimeoutStartSec=0
LimitNOFILE=40000
ExecStartPre=/bin/mkdir -p /var/lib/etcd
ExecStartPre=-/usr/bin/podman rm etcd
#--volume $${NOTIFY_SOCKET}:/run/systemd/notify \
ExecStart=/usr/bin/podman run --name etcd \
--env-file /etc/etcd/etcd.env \
--network host \
--volume /var/lib/etcd:/var/lib/etcd:rw,Z \
--volume /etc/ssl/etcd:/etc/ssl/certs:ro,Z \
quay.io/coreos/etcd:v3.4.7
ExecStop=/usr/bin/podman stop etcd
[Install]
WantedBy=multi-user.target
- name: docker.service
enabled: true
- name: wait-for-dns.service
enabled: true
contents: |
[Unit]
Description=Wait for DNS entries
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 (System Container)
Wants=rpc-statd.service
[Service]
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/calico
ExecStartPre=/bin/mkdir -p /var/lib/kubelet/volumeplugins
ExecStartPre=/usr/bin/bash -c "grep 'certificate-authority-data' /etc/kubernetes/kubeconfig | awk '{print $2}' | base64 -d > /etc/kubernetes/ca.crt"
ExecStartPre=-/usr/bin/podman rm kubelet
ExecStart=/usr/bin/podman run --name kubelet \
--privileged \
--pid host \
--network host \
--volume /etc/kubernetes:/etc/kubernetes:ro,z \
--volume /usr/lib/os-release:/etc/os-release:ro \
--volume /etc/ssl/certs:/etc/ssl/certs:ro \
--volume /lib/modules:/lib/modules:ro \
--volume /run:/run \
--volume /sys/fs/cgroup:/sys/fs/cgroup:ro \
--volume /sys/fs/cgroup/systemd:/sys/fs/cgroup/systemd \
--volume /etc/pki/tls/certs:/usr/share/ca-certificates:ro \
--volume /var/lib/calico:/var/lib/calico:ro \
--volume /var/lib/docker:/var/lib/docker \
--volume /var/lib/kubelet:/var/lib/kubelet:rshared,z \
--volume /var/log:/var/log \
--volume /var/run/lock:/var/run/lock:z \
--volume /opt/cni/bin:/opt/cni/bin:z \
--volume /etc/iscsi:/etc/iscsi \
--volume /sbin/iscsiadm:/sbin/iscsiadm \
quay.io/poseidon/kubelet:v1.18.2 \
--anonymous-auth=false \
--authentication-token-webhook \
--authorization-mode=Webhook \
--cgroup-driver=systemd \
--cgroups-per-qos=true \
--enforce-node-allocatable=pods \
--client-ca-file=/etc/kubernetes/ca.crt \
--cluster_dns=${cluster_dns_service_ip} \
--cluster_domain=${cluster_domain_suffix} \
--cni-conf-dir=/etc/kubernetes/cni/net.d \
--exit-on-lock-contention \
--healthz-port=0 \
--hostname-override=${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/podman stop kubelet
Delegate=yes
Restart=always
RestartSec=10
[Install]
WantedBy=multi-user.target
- name: kubelet.path
enabled: true
contents: |
[Unit]
Description=Watch for kubeconfig
[Path]
PathExists=/etc/kubernetes/kubeconfig
[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
ExecStart=/usr/bin/podman run --name bootstrap \
--network host \
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 07:10:55 +01:00
--volume /etc/kubernetes/bootstrap-secrets:/etc/kubernetes/secrets:ro,Z \
--volume /opt/bootstrap/assets:/assets:ro,Z \
--volume /opt/bootstrap/apply:/apply:ro,Z \
--entrypoint=/apply \
quay.io/poseidon/kubelet:v1.18.2
ExecStartPost=/bin/touch /opt/bootstrap/bootstrap.done
ExecStartPost=-/usr/bin/podman stop bootstrap
storage:
directories:
- path: /etc/kubernetes
- path: /opt/bootstrap
files:
- path: /etc/hostname
mode: 0644
contents:
inline:
${domain_name}
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 07:10:55 +01:00
- path: /opt/bootstrap/layout
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/
rm -rf assets auth static-manifests tls manifests-networking
- path: /opt/bootstrap/apply
mode: 0544
contents:
inline: |
#!/bin/bash -e
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 07:10:55 +01:00
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
contents:
inline: |
fs.inotify.max_user_watches=16184
- path: /etc/systemd/system.conf.d/accounting.conf
contents:
inline: |
[Manager]
DefaultCPUAccounting=yes
DefaultMemoryAccounting=yes
DefaultBlockIOAccounting=yes
- path: /etc/etcd/etcd.env
mode: 0644
contents:
inline: |
# TODO: Use a systemd dropin once podman v1.4.5 is avail.
NOTIFY_SOCKET=/run/systemd/notify
ETCD_NAME=${etcd_name}
ETCD_DATA_DIR=/var/lib/etcd
ETCD_ADVERTISE_CLIENT_URLS=https://${domain_name}:2379
ETCD_INITIAL_ADVERTISE_PEER_URLS=https://${domain_name}:2380
ETCD_LISTEN_CLIENT_URLS=https://0.0.0.0:2379
ETCD_LISTEN_PEER_URLS=https://0.0.0.0:2380
ETCD_LISTEN_METRICS_URLS=http://0.0.0.0:2381
ETCD_INITIAL_CLUSTER=${etcd_initial_cluster}
ETCD_STRICT_RECONFIG_CHECK=true
ETCD_TRUSTED_CA_FILE=/etc/ssl/certs/etcd/server-ca.crt
ETCD_CERT_FILE=/etc/ssl/certs/etcd/server.crt
ETCD_KEY_FILE=/etc/ssl/certs/etcd/server.key
ETCD_CLIENT_CERT_AUTH=true
ETCD_PEER_TRUSTED_CA_FILE=/etc/ssl/certs/etcd/peer-ca.crt
ETCD_PEER_CERT_FILE=/etc/ssl/certs/etcd/peer.crt
ETCD_PEER_KEY_FILE=/etc/ssl/certs/etcd/peer.key
ETCD_PEER_CLIENT_CERT_AUTH=true
passwd:
users:
- name: core
ssh_authorized_keys:
- ${ssh_authorized_key}