* GCP network

* Add worker templates

* Region group

* Cosmetic

* GCP nat for workers

* Network

* Google services

* Deploy talos
This commit is contained in:
Serge
2021-08-01 14:39:09 +03:00
committed by GitHub
parent c5acd0b29c
commit e482be34ad
23 changed files with 2502 additions and 0 deletions

6
gcp-zonal/.gitignore vendored Normal file
View File

@@ -0,0 +1,6 @@
#
_cfgs/
templates/controlplane.yaml
*.patch
#
gcloud.json

29
gcp-zonal/Makefile Normal file
View File

@@ -0,0 +1,29 @@
create-lb:
terraform init
terraform apply -auto-approve -target=google_compute_address.api
create-config:
talosctl gen config --output-dir _cfgs --with-docs=false --with-examples=false talos-k8s-hezner https://127.0.0.1:6443
create-templates:
@yq ea -P '. as $$item ireduce ({}; . * $$item )' _cfgs/controlplane.yaml templates/controlplane.yaml.tpl > templates/controlplane.yaml
@echo 'podSubnets: "10.32.0.0/12"' > _cfgs/tfstate.vars
@echo 'serviceSubnets: "10.200.0.0/22"' >> _cfgs/tfstate.vars
@yq eval '.cluster.network.dnsDomain' _cfgs/init.yaml | awk '{ print "domain: "$$1}' >> _cfgs/tfstate.vars
@yq eval '.cluster.clusterName' _cfgs/init.yaml | awk '{ print "cluster_name: "$$1}' >> _cfgs/tfstate.vars
@yq eval '.machine.token' _cfgs/init.yaml | awk '{ print "tokenmachine: "$$1}' >> _cfgs/tfstate.vars
@yq eval '.cluster.token' _cfgs/init.yaml | awk '{ print "token: "$$1}' >> _cfgs/tfstate.vars
@yq eval '.cluster.ca.crt' _cfgs/init.yaml | awk '{ print "ca: "$$1}' >> _cfgs/tfstate.vars
@yq eval -j '{"kubernetes": .}' _cfgs/tfstate.vars > terraform.tfvars.json
create-controlplane:
terraform apply -target=null_resource.controlplane
create-infrastructure:
cd modules/worker && terraform init
terraform apply
templates-update:
helm template --namespace=kube-system --version=1.10.3 -f deployments/cilium.yaml cilium cilium/cilium > deployments/cilium_result.yaml

14
gcp-zonal/auth.tf Normal file
View File

@@ -0,0 +1,14 @@
provider "google" {
project = var.project_id
region = var.region
credentials = "gcloud.json"
}
provider "google-beta" {
project = var.project_id
region = var.region
credentials = "gcloud.json"
}
data "google_client_config" "default" {}

29
gcp-zonal/common.tf Normal file
View File

@@ -0,0 +1,29 @@
data "google_client_openid_userinfo" "terraform" {}
resource "google_os_login_ssh_public_key" "terraform" {
project = var.project_id
user = data.google_client_openid_userinfo.terraform.email
key = file("~/.ssh/terraform.pub")
}
# resource "google_compute_image" "talos" {
# name = "talos"
# description = "Talos v0.11.3"
# raw_disk {
# source = "https://github.com/talos-systems/talos/releases/download/v0.11.3/gcp-amd64.tar.gz"
# }
# guest_os_features {
# type = "VIRTIO_SCSI_MULTIQUEUE"
# }
# guest_os_features {
# type = "MULTI_IP_SUBNET"
# }
# }
data "google_compute_image" "talos" {
project = var.project_id
family = "talos"
}

49
gcp-zonal/database.tf Normal file
View File

@@ -0,0 +1,49 @@
# resource "random_id" "db_name" {
# byte_length = 4
# }
# resource "google_sql_database_instance" "default" {
# project = var.project_id
# name = "${var.cluster_name}-db-${random_id.db_name.hex}"
# database_version = "POSTGRES_12"
# region = var.region
# deletion_protection = false
# settings {
# tier = "db-f1-micro"
# # availability_type = "REGIONAL"
# disk_size = 10
# disk_type = "PD_HDD"
# ip_configuration {
# ipv4_enabled = false
# private_network = google_compute_network.network.id
# require_ssl = true
# }
# backup_configuration {
# enabled = false
# }
# location_preference {
# zone = var.zones[0]
# }
# }
# timeouts {
# create = "15m"
# update = "15m"
# delete = "15m"
# }
# lifecycle {
# ignore_changes = [
# settings[0].disk_size
# ]
# }
# depends_on = [google_service_networking_connection.private_vpc_connection]
# }

View File

@@ -0,0 +1,60 @@
---
k8sServiceHost: "172.16.0.231"
k8sServicePort: "6443"
agent:
enabled: true
operator:
enabled: true
replicas: 1
prometheus:
enabled: false
identityAllocationMode: crd
cni:
install: true
ipam:
mode: "kubernetes"
tunnel: "vxlan"
autoDirectNodeRoutes: false
hostFirewall: true
kubeProxyReplacement: strict
healthChecking: true
ipv4:
enabled: true
ipv6:
enabled: false
hostServices:
enabled: false
hostPort:
enabled: true
nodePort:
enabled: false
externalIPs:
enabled: true
k8s:
requireIPv4PodCIDR: true
requireIPv6PodCIDR: false
prometheus:
enabled: true
encryption:
enabled: false
resources:
# limits:
# cpu: 4000m
# memory: 4Gi
requests:
cpu: 100m
memory: 128Mi

View File

@@ -0,0 +1,844 @@
---
# Source: cilium/templates/cilium-agent-serviceaccount.yaml
apiVersion: v1
kind: ServiceAccount
metadata:
name: "cilium"
namespace: kube-system
---
# Source: cilium/templates/cilium-operator-serviceaccount.yaml
apiVersion: v1
kind: ServiceAccount
metadata:
name: "cilium-operator"
namespace: kube-system
---
# Source: cilium/templates/cilium-configmap.yaml
apiVersion: v1
kind: ConfigMap
metadata:
name: cilium-config
namespace: kube-system
data:
# Identity allocation mode selects how identities are shared between cilium
# nodes by setting how they are stored. The options are "crd" or "kvstore".
# - "crd" stores identities in kubernetes as CRDs (custom resource definition).
# These can be queried with:
# kubectl get ciliumid
# - "kvstore" stores identities in a kvstore, etcd or consul, that is
# configured below. Cilium versions before 1.6 supported only the kvstore
# backend. Upgrades from these older cilium versions should continue using
# the kvstore by commenting out the identity-allocation-mode below, or
# setting it to "kvstore".
identity-allocation-mode: crd
cilium-endpoint-gc-interval: "5m0s"
# If you want to run cilium in debug mode change this value to true
debug: "false"
# The agent can be put into the following three policy enforcement modes
# default, always and never.
# https://docs.cilium.io/en/latest/policy/intro/#policy-enforcement-modes
enable-policy: "default"
# If you want metrics enabled in all of your Cilium agents, set the port for
# which the Cilium agents will have their metrics exposed.
# This option deprecates the "prometheus-serve-addr" in the
# "cilium-metrics-config" ConfigMap
# NOTE that this will open the port on ALL nodes where Cilium pods are
# scheduled.
prometheus-serve-addr: ":9090"
# Port to expose Envoy metrics (e.g. "9095"). Envoy metrics listener will be disabled if this
# field is not set.
proxy-prometheus-port: "9095"
# Enable IPv4 addressing. If enabled, all endpoints are allocated an IPv4
# address.
enable-ipv4: "true"
# Enable IPv6 addressing. If enabled, all endpoints are allocated an IPv6
# address.
enable-ipv6: "false"
# Users who wish to specify their own custom CNI configuration file must set
# custom-cni-conf to "true", otherwise Cilium may overwrite the configuration.
custom-cni-conf: "false"
enable-bpf-clock-probe: "true"
# If you want cilium monitor to aggregate tracing for packets, set this level
# to "low", "medium", or "maximum". The higher the level, the less packets
# that will be seen in monitor output.
monitor-aggregation: medium
# The monitor aggregation interval governs the typical time between monitor
# notification events for each allowed connection.
#
# Only effective when monitor aggregation is set to "medium" or higher.
monitor-aggregation-interval: 5s
# The monitor aggregation flags determine which TCP flags which, upon the
# first observation, cause monitor notifications to be generated.
#
# Only effective when monitor aggregation is set to "medium" or higher.
monitor-aggregation-flags: all
# Specifies the ratio (0.0-1.0) of total system memory to use for dynamic
# sizing of the TCP CT, non-TCP CT, NAT and policy BPF maps.
bpf-map-dynamic-size-ratio: "0.0025"
# bpf-policy-map-max specifies the maximum number of entries in endpoint
# policy map (per endpoint)
bpf-policy-map-max: "16384"
# bpf-lb-map-max specifies the maximum number of entries in bpf lb service,
# backend and affinity maps.
bpf-lb-map-max: "65536"
# bpf-lb-bypass-fib-lookup instructs Cilium to enable the FIB lookup bypass
# optimization for nodeport reverse NAT handling.
bpf-lb-external-clusterip: "false"
# Pre-allocation of map entries allows per-packet latency to be reduced, at
# the expense of up-front memory allocation for the entries in the maps. The
# default value below will minimize memory usage in the default installation;
# users who are sensitive to latency may consider setting this to "true".
#
# This option was introduced in Cilium 1.4. Cilium 1.3 and earlier ignore
# this option and behave as though it is set to "true".
#
# If this value is modified, then during the next Cilium startup the restore
# of existing endpoints and tracking of ongoing connections may be disrupted.
# As a result, reply packets may be dropped and the load-balancing decisions
# for established connections may change.
#
# If this option is set to "false" during an upgrade from 1.3 or earlier to
# 1.4 or later, then it may cause one-time disruptions during the upgrade.
preallocate-bpf-maps: "false"
# Regular expression matching compatible Istio sidecar istio-proxy
# container image names
sidecar-istio-proxy-image: "cilium/istio_proxy"
# Name of the cluster. Only relevant when building a mesh of clusters.
cluster-name: default
# Unique ID of the cluster. Must be unique across all conneted clusters and
# in the range of 1 and 255. Only relevant when building a mesh of clusters.
cluster-id: ""
# Encapsulation mode for communication between nodes
# Possible values:
# - disabled
# - vxlan (default)
# - geneve
tunnel: vxlan
# Enables L7 proxy for L7 policy enforcement and visibility
enable-l7-proxy: "true"
# wait-bpf-mount makes init container wait until bpf filesystem is mounted
wait-bpf-mount: "false"
enable-ipv4-masquerade: "true"
enable-ipv6-masquerade: "true"
enable-bpf-masquerade: "true"
enable-xt-socket-fallback: "true"
install-iptables-rules: "true"
install-no-conntrack-iptables-rules: "false"
auto-direct-node-routes: "false"
enable-bandwidth-manager: "false"
enable-local-redirect-policy: "false"
enable-host-firewall: "true"
kube-proxy-replacement: "strict"
kube-proxy-replacement-healthz-bind-address: ""
enable-health-check-nodeport: "true"
node-port-bind-protection: "true"
enable-auto-protect-node-port-range: "true"
enable-session-affinity: "true"
k8s-require-ipv4-pod-cidr: "true"
k8s-require-ipv6-pod-cidr: "false"
enable-endpoint-health-checking: "true"
enable-health-checking: "true"
enable-well-known-identities: "false"
enable-remote-node-identity: "true"
operator-api-serve-addr: "127.0.0.1:9234"
# Enable Hubble gRPC service.
enable-hubble: "true"
# UNIX domain socket for Hubble server to listen to.
hubble-socket-path: "/var/run/cilium/hubble.sock"
# An additional address for Hubble server to listen to (e.g. ":4244").
hubble-listen-address: ":4244"
hubble-disable-tls: "false"
hubble-tls-cert-file: /var/lib/cilium/tls/hubble/server.crt
hubble-tls-key-file: /var/lib/cilium/tls/hubble/server.key
hubble-tls-client-ca-files: /var/lib/cilium/tls/hubble/client-ca.crt
ipam: "kubernetes"
disable-cnp-status-updates: "true"
cgroup-root: "/run/cilium/cgroupv2"
---
# Source: cilium/templates/cilium-agent-clusterrole.yaml
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
name: cilium
rules:
- apiGroups:
- networking.k8s.io
resources:
- networkpolicies
verbs:
- get
- list
- watch
- apiGroups:
- discovery.k8s.io
resources:
- endpointslices
verbs:
- get
- list
- watch
- apiGroups:
- ""
resources:
- namespaces
- services
- nodes
- endpoints
verbs:
- get
- list
- watch
- apiGroups:
- ""
resources:
- pods
- pods/finalizers
verbs:
- get
- list
- watch
- update
- delete
- apiGroups:
- ""
resources:
- nodes
verbs:
- get
- list
- watch
- update
- apiGroups:
- ""
resources:
- nodes
- nodes/status
verbs:
- patch
- apiGroups:
- apiextensions.k8s.io
resources:
- customresourcedefinitions
verbs:
# Deprecated for removal in v1.10
- create
- list
- watch
- update
# This is used when validating policies in preflight. This will need to stay
# until we figure out how to avoid "get" inside the preflight, and then
# should be removed ideally.
- get
- apiGroups:
- cilium.io
resources:
- ciliumnetworkpolicies
- ciliumnetworkpolicies/status
- ciliumnetworkpolicies/finalizers
- ciliumclusterwidenetworkpolicies
- ciliumclusterwidenetworkpolicies/status
- ciliumclusterwidenetworkpolicies/finalizers
- ciliumendpoints
- ciliumendpoints/status
- ciliumendpoints/finalizers
- ciliumnodes
- ciliumnodes/status
- ciliumnodes/finalizers
- ciliumidentities
- ciliumidentities/finalizers
- ciliumlocalredirectpolicies
- ciliumlocalredirectpolicies/status
- ciliumlocalredirectpolicies/finalizers
- ciliumegressnatpolicies
verbs:
- '*'
---
# Source: cilium/templates/cilium-operator-clusterrole.yaml
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
name: cilium-operator
rules:
- apiGroups:
- ""
resources:
# to automatically delete [core|kube]dns pods so that are starting to being
# managed by Cilium
- pods
verbs:
- get
- list
- watch
- delete
- apiGroups:
- discovery.k8s.io
resources:
- endpointslices
verbs:
- get
- list
- watch
- apiGroups:
- ""
resources:
- services
verbs:
- get
- list
- watch
- apiGroups:
- ""
resources:
# to perform LB IP allocation for BGP
- services/status
verbs:
- update
- apiGroups:
- ""
resources:
# to perform the translation of a CNP that contains `ToGroup` to its endpoints
- services
- endpoints
# to check apiserver connectivity
- namespaces
verbs:
- get
- list
- watch
- apiGroups:
- cilium.io
resources:
- ciliumnetworkpolicies
- ciliumnetworkpolicies/status
- ciliumnetworkpolicies/finalizers
- ciliumclusterwidenetworkpolicies
- ciliumclusterwidenetworkpolicies/status
- ciliumclusterwidenetworkpolicies/finalizers
- ciliumendpoints
- ciliumendpoints/status
- ciliumendpoints/finalizers
- ciliumnodes
- ciliumnodes/status
- ciliumnodes/finalizers
- ciliumidentities
- ciliumidentities/status
- ciliumidentities/finalizers
- ciliumlocalredirectpolicies
- ciliumlocalredirectpolicies/status
- ciliumlocalredirectpolicies/finalizers
verbs:
- '*'
- apiGroups:
- apiextensions.k8s.io
resources:
- customresourcedefinitions
verbs:
- create
- get
- list
- update
- watch
# For cilium-operator running in HA mode.
#
# Cilium operator running in HA mode requires the use of ResourceLock for Leader Election
# between multiple running instances.
# The preferred way of doing this is to use LeasesResourceLock as edits to Leases are less
# common and fewer objects in the cluster watch "all Leases".
- apiGroups:
- coordination.k8s.io
resources:
- leases
verbs:
- create
- get
- update
---
# Source: cilium/templates/cilium-agent-clusterrolebinding.yaml
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
name: cilium
roleRef:
apiGroup: rbac.authorization.k8s.io
kind: ClusterRole
name: cilium
subjects:
- kind: ServiceAccount
name: "cilium"
namespace: kube-system
---
# Source: cilium/templates/cilium-operator-clusterrolebinding.yaml
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
name: cilium-operator
roleRef:
apiGroup: rbac.authorization.k8s.io
kind: ClusterRole
name: cilium-operator
subjects:
- kind: ServiceAccount
name: "cilium-operator"
namespace: kube-system
---
# Source: cilium/templates/cilium-agent-service.yaml
kind: Service
apiVersion: v1
metadata:
name: cilium-agent
namespace: kube-system
annotations:
prometheus.io/scrape: 'true'
prometheus.io/port: "9095"
labels:
k8s-app: cilium
spec:
clusterIP: None
type: ClusterIP
ports:
- name: envoy-metrics
port: 9095
protocol: TCP
targetPort: envoy-metrics
selector:
k8s-app: cilium
---
# Source: cilium/templates/cilium-agent-daemonset.yaml
apiVersion: apps/v1
kind: DaemonSet
metadata:
labels:
k8s-app: cilium
name: cilium
namespace: kube-system
spec:
selector:
matchLabels:
k8s-app: cilium
updateStrategy:
rollingUpdate:
maxUnavailable: 2
type: RollingUpdate
template:
metadata:
annotations:
prometheus.io/port: "9090"
prometheus.io/scrape: "true"
# This annotation plus the CriticalAddonsOnly toleration makes
# cilium to be a critical pod in the cluster, which ensures cilium
# gets priority scheduling.
# https://kubernetes.io/docs/tasks/administer-cluster/guaranteed-scheduling-critical-addon-pods/
scheduler.alpha.kubernetes.io/critical-pod: ""
labels:
k8s-app: cilium
spec:
affinity:
nodeAffinity:
requiredDuringSchedulingIgnoredDuringExecution:
nodeSelectorTerms:
- matchExpressions:
- key: kubernetes.io/os
operator: In
values:
- linux
- matchExpressions:
- key: beta.kubernetes.io/os
operator: In
values:
- linux
podAntiAffinity:
requiredDuringSchedulingIgnoredDuringExecution:
- labelSelector:
matchExpressions:
- key: k8s-app
operator: In
values:
- cilium
topologyKey: kubernetes.io/hostname
containers:
- args:
- --config-dir=/tmp/cilium/config-map
command:
- cilium-agent
startupProbe:
httpGet:
host: '127.0.0.1'
path: /healthz
port: 9876
scheme: HTTP
httpHeaders:
- name: "brief"
value: "true"
failureThreshold: 105
periodSeconds: 2
successThreshold: 1
livenessProbe:
httpGet:
host: '127.0.0.1'
path: /healthz
port: 9876
scheme: HTTP
httpHeaders:
- name: "brief"
value: "true"
failureThreshold: 10
periodSeconds: 30
successThreshold: 1
timeoutSeconds: 5
readinessProbe:
httpGet:
host: '127.0.0.1'
path: /healthz
port: 9876
scheme: HTTP
httpHeaders:
- name: "brief"
value: "true"
failureThreshold: 3
periodSeconds: 30
successThreshold: 1
timeoutSeconds: 5
env:
- name: K8S_NODE_NAME
valueFrom:
fieldRef:
apiVersion: v1
fieldPath: spec.nodeName
- name: CILIUM_K8S_NAMESPACE
valueFrom:
fieldRef:
apiVersion: v1
fieldPath: metadata.namespace
- name: CILIUM_CLUSTERMESH_CONFIG
value: /var/lib/cilium/clustermesh/
- name: CILIUM_CNI_CHAINING_MODE
valueFrom:
configMapKeyRef:
key: cni-chaining-mode
name: cilium-config
optional: true
- name: CILIUM_CUSTOM_CNI_CONF
valueFrom:
configMapKeyRef:
key: custom-cni-conf
name: cilium-config
optional: true
- name: KUBERNETES_SERVICE_HOST
value: "172.16.0.231"
- name: KUBERNETES_SERVICE_PORT
value: "6443"
image: "quay.io/cilium/cilium:v1.10.3@sha256:8419531c5d3677158802882bdfe2297915c43f2ebe3649551aaac22de9f6d565"
imagePullPolicy: IfNotPresent
lifecycle:
postStart:
exec:
command:
- "/cni-install.sh"
- "--enable-debug=false"
- "--cni-exclusive=true"
preStop:
exec:
command:
- /cni-uninstall.sh
resources:
requests:
cpu: 100m
memory: 128Mi
name: cilium-agent
ports:
- containerPort: 9090
hostPort: 9090
name: prometheus
protocol: TCP
- containerPort: 9095
hostPort: 9095
name: envoy-metrics
protocol: TCP
securityContext:
capabilities:
add:
- NET_ADMIN
- SYS_MODULE
privileged: true
volumeMounts:
- mountPath: /sys/fs/bpf
name: bpf-maps
- mountPath: /var/run/cilium
name: cilium-run
- mountPath: /host/opt/cni/bin
name: cni-path
- mountPath: /host/etc/cni/net.d
name: etc-cni-netd
- mountPath: /var/lib/cilium/clustermesh
name: clustermesh-secrets
readOnly: true
- mountPath: /tmp/cilium/config-map
name: cilium-config-path
readOnly: true
# Needed to be able to load kernel modules
- mountPath: /lib/modules
name: lib-modules
readOnly: true
- mountPath: /run/xtables.lock
name: xtables-lock
- mountPath: /var/lib/cilium/tls/hubble
name: hubble-tls
readOnly: true
hostNetwork: true
initContainers:
# Required to mount cgroup2 filesystem on the underlying Kubernetes node.
# We use nsenter command with host's cgroup and mount namespaces enabled.
- name: mount-cgroup
env:
- name: CGROUP_ROOT
value: /run/cilium/cgroupv2
- name: BIN_PATH
value: /opt/cni/bin
command:
- sh
- -c
# The statically linked Go program binary is invoked to avoid any
# dependency on utilities like sh and mount that can be missing on certain
# distros installed on the underlying host. Copy the binary to the
# same directory where we install cilium cni plugin so that exec permissions
# are available.
- 'cp /usr/bin/cilium-mount /hostbin/cilium-mount && nsenter --cgroup=/hostproc/1/ns/cgroup --mount=/hostproc/1/ns/mnt "${BIN_PATH}/cilium-mount" $CGROUP_ROOT; rm /hostbin/cilium-mount'
image: "quay.io/cilium/cilium:v1.10.3@sha256:8419531c5d3677158802882bdfe2297915c43f2ebe3649551aaac22de9f6d565"
imagePullPolicy: IfNotPresent
volumeMounts:
- mountPath: /hostproc
name: hostproc
- mountPath: /hostbin
name: cni-path
securityContext:
privileged: true
- command:
- /init-container.sh
env:
- name: CILIUM_ALL_STATE
valueFrom:
configMapKeyRef:
key: clean-cilium-state
name: cilium-config
optional: true
- name: CILIUM_BPF_STATE
valueFrom:
configMapKeyRef:
key: clean-cilium-bpf-state
name: cilium-config
optional: true
- name: CILIUM_WAIT_BPF_MOUNT
valueFrom:
configMapKeyRef:
key: wait-bpf-mount
name: cilium-config
optional: true
- name: KUBERNETES_SERVICE_HOST
value: "172.16.0.231"
- name: KUBERNETES_SERVICE_PORT
value: "6443"
image: "quay.io/cilium/cilium:v1.10.3@sha256:8419531c5d3677158802882bdfe2297915c43f2ebe3649551aaac22de9f6d565"
imagePullPolicy: IfNotPresent
name: clean-cilium-state
securityContext:
capabilities:
add:
- NET_ADMIN
privileged: true
volumeMounts:
- mountPath: /sys/fs/bpf
name: bpf-maps
mountPropagation: HostToContainer
# Required to mount cgroup filesystem from the host to cilium agent pod
- mountPath: /run/cilium/cgroupv2
name: cilium-cgroup
mountPropagation: HostToContainer
- mountPath: /var/run/cilium
name: cilium-run
resources:
requests:
cpu: 100m
memory: 100Mi
restartPolicy: Always
priorityClassName: system-node-critical
serviceAccount: "cilium"
serviceAccountName: "cilium"
terminationGracePeriodSeconds: 1
tolerations:
- operator: Exists
volumes:
# To keep state between restarts / upgrades
- hostPath:
path: /var/run/cilium
type: DirectoryOrCreate
name: cilium-run
# To keep state between restarts / upgrades for bpf maps
- hostPath:
path: /sys/fs/bpf
type: DirectoryOrCreate
name: bpf-maps
# To mount cgroup2 filesystem on the host
- hostPath:
path: /proc
type: Directory
name: hostproc
# To keep state between restarts / upgrades for cgroup2 filesystem
- hostPath:
path: /run/cilium/cgroupv2
type: DirectoryOrCreate
name: cilium-cgroup
# To install cilium cni plugin in the host
- hostPath:
path: /opt/cni/bin
type: DirectoryOrCreate
name: cni-path
# To install cilium cni configuration in the host
- hostPath:
path: /etc/cni/net.d
type: DirectoryOrCreate
name: etc-cni-netd
# To be able to load kernel modules
- hostPath:
path: /lib/modules
name: lib-modules
# To access iptables concurrently with other processes (e.g. kube-proxy)
- hostPath:
path: /run/xtables.lock
type: FileOrCreate
name: xtables-lock
# To read the clustermesh configuration
- name: clustermesh-secrets
secret:
defaultMode: 420
optional: true
secretName: cilium-clustermesh
# To read the configuration from the config map
- configMap:
name: cilium-config
name: cilium-config-path
- name: hubble-tls
projected:
sources:
- secret:
name: hubble-server-certs
items:
- key: ca.crt
path: client-ca.crt
- key: tls.crt
path: server.crt
- key: tls.key
path: server.key
optional: true
---
# Source: cilium/templates/cilium-operator-deployment.yaml
apiVersion: apps/v1
kind: Deployment
metadata:
labels:
io.cilium/app: operator
name: cilium-operator
name: cilium-operator
namespace: kube-system
spec:
# See docs on ServerCapabilities.LeasesResourceLock in file pkg/k8s/version/version.go
# for more details.
replicas: 1
selector:
matchLabels:
io.cilium/app: operator
name: cilium-operator
strategy:
rollingUpdate:
maxSurge: 1
maxUnavailable: 1
type: RollingUpdate
template:
metadata:
annotations:
labels:
io.cilium/app: operator
name: cilium-operator
spec:
# In HA mode, cilium-operator pods must not be scheduled on the same
# node as they will clash with each other.
affinity:
podAntiAffinity:
requiredDuringSchedulingIgnoredDuringExecution:
- labelSelector:
matchExpressions:
- key: io.cilium/app
operator: In
values:
- operator
topologyKey: kubernetes.io/hostname
containers:
- args:
- --config-dir=/tmp/cilium/config-map
- --debug=$(CILIUM_DEBUG)
command:
- cilium-operator-generic
env:
- name: K8S_NODE_NAME
valueFrom:
fieldRef:
apiVersion: v1
fieldPath: spec.nodeName
- name: CILIUM_K8S_NAMESPACE
valueFrom:
fieldRef:
apiVersion: v1
fieldPath: metadata.namespace
- name: CILIUM_DEBUG
valueFrom:
configMapKeyRef:
key: debug
name: cilium-config
optional: true
- name: KUBERNETES_SERVICE_HOST
value: "172.16.0.231"
- name: KUBERNETES_SERVICE_PORT
value: "6443"
image: "quay.io/cilium/operator-generic:v1.10.3@sha256:337ebf27eae4fbad51cc4baf9110b3ec6753320dd33075bc136e2a1865be5eb5"
imagePullPolicy: IfNotPresent
name: cilium-operator
livenessProbe:
httpGet:
host: '127.0.0.1'
path: /healthz
port: 9234
scheme: HTTP
initialDelaySeconds: 60
periodSeconds: 10
timeoutSeconds: 3
volumeMounts:
- mountPath: /tmp/cilium/config-map
name: cilium-config-path
readOnly: true
hostNetwork: true
restartPolicy: Always
priorityClassName: system-cluster-critical
serviceAccount: "cilium-operator"
serviceAccountName: "cilium-operator"
tolerations:
- operator: Exists
volumes:
# To read the configuration from the config map
- configMap:
name: cilium-config
name: cilium-config-path

View File

@@ -0,0 +1,290 @@
apiVersion: v1
kind: Namespace
metadata:
labels:
app.kubernetes.io/instance: kubelet-serving-cert-approver
app.kubernetes.io/name: kubelet-serving-cert-approver
name: kubelet-serving-cert-approver
---
apiVersion: v1
kind: ServiceAccount
metadata:
labels:
app.kubernetes.io/instance: kubelet-serving-cert-approver
app.kubernetes.io/name: kubelet-serving-cert-approver
name: kubelet-serving-cert-approver
namespace: kubelet-serving-cert-approver
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
labels:
app.kubernetes.io/instance: kubelet-serving-cert-approver
app.kubernetes.io/name: kubelet-serving-cert-approver
name: certificates:kubelet-serving-cert-approver
rules:
- apiGroups:
- certificates.k8s.io
resources:
- certificatesigningrequests
verbs:
- get
- list
- watch
- apiGroups:
- certificates.k8s.io
resources:
- certificatesigningrequests/approval
verbs:
- update
- apiGroups:
- authorization.k8s.io
resources:
- subjectaccessreviews
verbs:
- create
- apiGroups:
- certificates.k8s.io
resourceNames:
- kubernetes.io/kubelet-serving
resources:
- signers
verbs:
- approve
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
labels:
app.kubernetes.io/instance: kubelet-serving-cert-approver
app.kubernetes.io/name: kubelet-serving-cert-approver
name: events:kubelet-serving-cert-approver
rules:
- apiGroups:
- ""
resources:
- events
verbs:
- create
- patch
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
labels:
app.kubernetes.io/instance: kubelet-serving-cert-approver
app.kubernetes.io/name: kubelet-serving-cert-approver
name: psp:kubelet-serving-cert-approver
rules:
- apiGroups:
- policy
resourceNames:
- kubelet-serving-cert-approver
resources:
- podsecuritypolicies
verbs:
- use
---
apiVersion: rbac.authorization.k8s.io/v1
kind: RoleBinding
metadata:
labels:
app.kubernetes.io/instance: kubelet-serving-cert-approver
app.kubernetes.io/name: kubelet-serving-cert-approver
name: events:kubelet-serving-cert-approver
namespace: default
roleRef:
apiGroup: rbac.authorization.k8s.io
kind: ClusterRole
name: events:kubelet-serving-cert-approver
subjects:
- kind: ServiceAccount
name: kubelet-serving-cert-approver
namespace: kubelet-serving-cert-approver
---
apiVersion: rbac.authorization.k8s.io/v1
kind: RoleBinding
metadata:
labels:
app.kubernetes.io/instance: kubelet-serving-cert-approver
app.kubernetes.io/name: kubelet-serving-cert-approver
name: psp:kubelet-serving-cert-approver
namespace: kubelet-serving-cert-approver
roleRef:
apiGroup: rbac.authorization.k8s.io
kind: ClusterRole
name: psp:kubelet-serving-cert-approver
subjects:
- kind: ServiceAccount
name: kubelet-serving-cert-approver
namespace: kubelet-serving-cert-approver
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
labels:
app.kubernetes.io/instance: kubelet-serving-cert-approver
app.kubernetes.io/name: kubelet-serving-cert-approver
name: kubelet-serving-cert-approver
roleRef:
apiGroup: rbac.authorization.k8s.io
kind: ClusterRole
name: certificates:kubelet-serving-cert-approver
subjects:
- kind: ServiceAccount
name: kubelet-serving-cert-approver
namespace: kubelet-serving-cert-approver
---
apiVersion: v1
kind: Service
metadata:
labels:
app.kubernetes.io/instance: kubelet-serving-cert-approver
app.kubernetes.io/name: kubelet-serving-cert-approver
name: kubelet-serving-cert-approver
namespace: kubelet-serving-cert-approver
spec:
ports:
- name: metrics
port: 9090
protocol: TCP
targetPort: metrics
selector:
app.kubernetes.io/instance: kubelet-serving-cert-approver
app.kubernetes.io/name: kubelet-serving-cert-approver
---
apiVersion: apps/v1
kind: Deployment
metadata:
labels:
app.kubernetes.io/instance: kubelet-serving-cert-approver
app.kubernetes.io/name: kubelet-serving-cert-approver
name: kubelet-serving-cert-approver
namespace: kubelet-serving-cert-approver
spec:
replicas: 1
selector:
matchLabels:
app.kubernetes.io/instance: kubelet-serving-cert-approver
app.kubernetes.io/name: kubelet-serving-cert-approver
template:
metadata:
labels:
app.kubernetes.io/instance: kubelet-serving-cert-approver
app.kubernetes.io/name: kubelet-serving-cert-approver
spec:
tolerations:
- key: "node.cloudprovider.kubernetes.io/uninitialized"
value: "true"
effect: "NoSchedule"
- key: "CriticalAddonsOnly"
operator: "Exists"
- key: "node-role.kubernetes.io/master"
effect: NoSchedule
affinity:
nodeAffinity:
preferredDuringSchedulingIgnoredDuringExecution:
- preference:
matchExpressions:
- key: node-role.kubernetes.io/master
operator: DoesNotExist
- key: node-role.kubernetes.io/control-plane
operator: DoesNotExist
weight: 100
containers:
- args:
- serve
env:
- name: NAMESPACE
valueFrom:
fieldRef:
fieldPath: metadata.namespace
image: ghcr.io/alex1989hu/kubelet-serving-cert-approver:main
imagePullPolicy: Always
livenessProbe:
httpGet:
path: /healthz
port: health
initialDelaySeconds: 6
name: cert-approver
ports:
- containerPort: 8080
name: health
- containerPort: 9090
name: metrics
readinessProbe:
httpGet:
path: /readyz
port: health
initialDelaySeconds: 3
resources:
limits:
cpu: 250m
memory: 32Mi
requests:
cpu: 10m
memory: 12Mi
securityContext:
allowPrivilegeEscalation: false
capabilities:
drop:
- ALL
privileged: false
readOnlyRootFilesystem: true
runAsNonRoot: true
priorityClassName: system-cluster-critical
securityContext:
fsGroup: 65534
runAsGroup: 65534
runAsUser: 65534
serviceAccountName: kubelet-serving-cert-approver
tolerations:
- effect: NoSchedule
key: node-role.kubernetes.io/master
operator: Exists
- effect: NoSchedule
key: node-role.kubernetes.io/control-plane
operator: Exists
---
apiVersion: policy/v1beta1
kind: PodSecurityPolicy
metadata:
annotations:
seccomp.security.alpha.kubernetes.io/allowedProfileNames: runtime/default
seccomp.security.alpha.kubernetes.io/defaultProfileName: runtime/default
labels:
app.kubernetes.io/instance: kubelet-serving-cert-approver
app.kubernetes.io/name: kubelet-serving-cert-approver
name: kubelet-serving-cert-approver
namespace: kubelet-serving-cert-approver
spec:
allowPrivilegeEscalation: false
forbiddenSysctls:
- '*'
fsGroup:
ranges:
- max: 65534
min: 65534
rule: MustRunAs
hostIPC: false
hostNetwork: false
hostPID: false
privileged: false
readOnlyRootFilesystem: true
requiredDropCapabilities:
- ALL
runAsUser:
ranges:
- max: 65534
min: 65534
rule: MustRunAs
seLinux:
rule: RunAsAny
supplementalGroups:
ranges:
- max: 65534
min: 65534
rule: MustRunAs
volumes:
- downwardAPI
- secret

View File

@@ -0,0 +1,163 @@
apiVersion: v1
kind: Namespace
metadata:
name: local-path-storage
---
apiVersion: v1
kind: ServiceAccount
metadata:
name: local-path-provisioner-service-account
namespace: local-path-storage
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
name: local-path-provisioner-role
rules:
- apiGroups: [ "" ]
resources: [ "nodes", "persistentvolumeclaims", "configmaps" ]
verbs: [ "get", "list", "watch" ]
- apiGroups: [ "" ]
resources: [ "endpoints", "persistentvolumes", "pods" ]
verbs: [ "*" ]
- apiGroups: [ "" ]
resources: [ "events" ]
verbs: [ "create", "patch" ]
- apiGroups: [ "storage.k8s.io" ]
resources: [ "storageclasses" ]
verbs: [ "get", "list", "watch" ]
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
name: local-path-provisioner-bind
roleRef:
apiGroup: rbac.authorization.k8s.io
kind: ClusterRole
name: local-path-provisioner-role
subjects:
- kind: ServiceAccount
name: local-path-provisioner-service-account
namespace: local-path-storage
---
apiVersion: apps/v1
kind: Deployment
metadata:
name: local-path-provisioner
namespace: local-path-storage
spec:
replicas: 1
selector:
matchLabels:
app: local-path-provisioner
template:
metadata:
labels:
app: local-path-provisioner
spec:
tolerations:
- key: "CriticalAddonsOnly"
operator: "Exists"
- key: "node-role.kubernetes.io/master"
effect: NoSchedule
serviceAccountName: local-path-provisioner-service-account
containers:
- name: local-path-provisioner
image: rancher/local-path-provisioner:v0.0.19
imagePullPolicy: IfNotPresent
command:
- local-path-provisioner
- --debug
- start
- --config
- /etc/config/config.json
volumeMounts:
- name: config-volume
mountPath: /etc/config/
env:
- name: POD_NAMESPACE
valueFrom:
fieldRef:
fieldPath: metadata.namespace
volumes:
- name: config-volume
configMap:
name: local-path-config
---
apiVersion: storage.k8s.io/v1
kind: StorageClass
metadata:
name: local-path
annotations:
storageclass.kubernetes.io/is-default-class: "true"
provisioner: rancher.io/local-path
volumeBindingMode: WaitForFirstConsumer
reclaimPolicy: Delete
---
kind: ConfigMap
apiVersion: v1
metadata:
name: local-path-config
namespace: local-path-storage
data:
config.json: |-
{
"nodePathMap":[
{
"node":"DEFAULT_PATH_FOR_NON_LISTED_NODES",
"paths":["/var/local-path-provisioner"]
}
]
}
setup: |-
#!/bin/sh
while getopts "m:s:p:" opt
do
case $opt in
p)
absolutePath=$OPTARG
;;
s)
sizeInBytes=$OPTARG
;;
m)
volMode=$OPTARG
;;
esac
done
mkdir -m 0777 -p ${absolutePath}
teardown: |-
#!/bin/sh
while getopts "m:s:p:" opt
do
case $opt in
p)
absolutePath=$OPTARG
;;
s)
sizeInBytes=$OPTARG
;;
m)
volMode=$OPTARG
;;
esac
done
rm -rf ${absolutePath}
helperPod.yaml: |-
apiVersion: v1
kind: Pod
metadata:
name: helper-pod
spec:
containers:
- name: helper-pod
image: busybox
imagePullPolicy: IfNotPresent

View File

@@ -0,0 +1,197 @@
apiVersion: v1
kind: ServiceAccount
metadata:
labels:
k8s-app: metrics-server
name: metrics-server
namespace: kube-system
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
labels:
k8s-app: metrics-server
rbac.authorization.k8s.io/aggregate-to-admin: "true"
rbac.authorization.k8s.io/aggregate-to-edit: "true"
rbac.authorization.k8s.io/aggregate-to-view: "true"
name: system:aggregated-metrics-reader
rules:
- apiGroups:
- metrics.k8s.io
resources:
- pods
- nodes
verbs:
- get
- list
- watch
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
labels:
k8s-app: metrics-server
name: system:metrics-server
rules:
- apiGroups:
- ""
resources:
- pods
- nodes
- nodes/stats
- namespaces
- configmaps
verbs:
- get
- list
- watch
---
apiVersion: rbac.authorization.k8s.io/v1
kind: RoleBinding
metadata:
labels:
k8s-app: metrics-server
name: metrics-server-auth-reader
namespace: kube-system
roleRef:
apiGroup: rbac.authorization.k8s.io
kind: Role
name: extension-apiserver-authentication-reader
subjects:
- kind: ServiceAccount
name: metrics-server
namespace: kube-system
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
labels:
k8s-app: metrics-server
name: metrics-server:system:auth-delegator
roleRef:
apiGroup: rbac.authorization.k8s.io
kind: ClusterRole
name: system:auth-delegator
subjects:
- kind: ServiceAccount
name: metrics-server
namespace: kube-system
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
labels:
k8s-app: metrics-server
name: system:metrics-server
roleRef:
apiGroup: rbac.authorization.k8s.io
kind: ClusterRole
name: system:metrics-server
subjects:
- kind: ServiceAccount
name: metrics-server
namespace: kube-system
---
apiVersion: v1
kind: Service
metadata:
labels:
k8s-app: metrics-server
name: metrics-server
namespace: kube-system
spec:
ports:
- name: https
port: 443
protocol: TCP
targetPort: https
selector:
k8s-app: metrics-server
---
apiVersion: apps/v1
kind: Deployment
metadata:
labels:
k8s-app: metrics-server
name: metrics-server
namespace: kube-system
spec:
selector:
matchLabels:
k8s-app: metrics-server
strategy:
rollingUpdate:
maxUnavailable: 0
template:
metadata:
labels:
k8s-app: metrics-server
spec:
tolerations:
- key: "CriticalAddonsOnly"
operator: "Exists"
- key: "node-role.kubernetes.io/master"
effect: NoSchedule
containers:
- args:
- --cert-dir=/tmp
- --secure-port=443
- --kubelet-preferred-address-types=InternalIP,ExternalIP,Hostname
- --kubelet-use-node-status-port
- --metric-resolution=15s
image: k8s.gcr.io/metrics-server/metrics-server:v0.5.0
imagePullPolicy: IfNotPresent
livenessProbe:
failureThreshold: 3
httpGet:
path: /livez
port: https
scheme: HTTPS
periodSeconds: 10
name: metrics-server
ports:
- containerPort: 443
name: https
protocol: TCP
readinessProbe:
failureThreshold: 3
httpGet:
path: /readyz
port: https
scheme: HTTPS
initialDelaySeconds: 20
periodSeconds: 10
resources:
requests:
cpu: 100m
memory: 200Mi
securityContext:
readOnlyRootFilesystem: true
runAsNonRoot: true
runAsUser: 1000
volumeMounts:
- mountPath: /tmp
name: tmp-dir
nodeSelector:
kubernetes.io/os: linux
priorityClassName: system-cluster-critical
serviceAccountName: metrics-server
volumes:
- emptyDir: {}
name: tmp-dir
---
apiVersion: apiregistration.k8s.io/v1
kind: APIService
metadata:
labels:
k8s-app: metrics-server
name: v1beta1.metrics.k8s.io
spec:
group: metrics.k8s.io
groupPriorityMinimum: 100
insecureSkipTLSVerify: true
service:
name: metrics-server
namespace: kube-system
version: v1beta1
versionPriority: 100

View File

@@ -0,0 +1,113 @@
resource "google_compute_address" "controlplane" {
count = lookup(var.controlplane, "count", 0)
project = var.project_id
region = var.region
name = "${var.cluster_name}-master-${count.index + 1}"
description = "Local ${var.cluster_name}-master-${count.index + 1} ip"
address_type = "INTERNAL"
address = cidrhost(cidrsubnet(var.network_cidr, 8, 0), 231 + count.index)
subnetwork = "core"
purpose = "GCE_ENDPOINT"
}
resource "google_compute_instance_from_template" "controlplane" {
count = lookup(var.controlplane, "count", 0)
name = "master-${count.index + 1}"
project = var.project_id
zone = element(var.zones, count.index)
network_interface {
network = var.network
network_ip = google_compute_address.controlplane[count.index].address
subnetwork = "core"
access_config {
network_tier = "STANDARD"
}
}
source_instance_template = google_compute_instance_template.controlplane.id
depends_on = [
google_compute_instance_template.controlplane
]
}
resource "google_compute_instance_template" "controlplane" {
name_prefix = "${var.cluster_name}-master-"
project = var.project_id
region = var.region
machine_type = lookup(var.controlplane, "type", "e2-standard-2")
# min_cpu_platform = ""
tags = concat(var.tags, ["${var.cluster_name}-infra", "${var.cluster_name}-master", "${var.cluster_name}-web"])
labels = {
label = "controlplane"
}
# metadata = {
# ssh-keys = "debian:${file("~/.ssh/terraform.pub")}"
# }
# metadata_startup_script = "apt-get install -y nginx"
disk {
boot = true
auto_delete = true
disk_size_gb = 16
disk_type = "pd-ssd"
resource_policies = []
source_image = data.google_compute_image.talos.self_link
labels = { label = "controlplane" }
}
network_interface {
network = var.network
subnetwork = "core"
access_config {
network_tier = "STANDARD"
}
}
scheduling {
automatic_restart = true
on_host_maintenance = "MIGRATE"
}
shielded_instance_config {
enable_integrity_monitoring = true
enable_secure_boot = false
enable_vtpm = true
}
lifecycle {
create_before_destroy = "true"
}
}
resource "local_file" "controlplane" {
count = lookup(var.controlplane, "count", 0)
content = templatefile("${path.module}/templates/controlplane.yaml",
merge(var.kubernetes, {
name = "master-${count.index + 1}"
type = count.index == 0 ? "init" : "controlplane"
ipv4_local = cidrhost(cidrsubnet(var.network_cidr, 8, 0), 231 + count.index)
ipv4 = google_compute_instance_from_template.controlplane[count.index].network_interface[0].access_config[0].nat_ip
lbv4_local = cidrhost(cidrsubnet(var.network_cidr, 8, 0), 230)
lbv4 = google_compute_address.api.address
})
)
filename = "_cfgs/controlplane-${count.index + 1}.yaml"
file_permission = "0640"
depends_on = [google_compute_instance_from_template.controlplane]
}
resource "null_resource" "controlplane" {
count = lookup(var.controlplane, "count", 0)
provisioner "local-exec" {
command = "sleep 60 && talosctl apply-config --insecure --nodes ${google_compute_instance_from_template.controlplane[count.index].network_interface[0].access_config[0].nat_ip} --file _cfgs/controlplane-${count.index + 1}.yaml"
}
depends_on = [google_compute_address.api, local_file.controlplane]
}

123
gcp-zonal/instances-web.tf Normal file
View File

@@ -0,0 +1,123 @@
resource "google_compute_region_instance_group_manager" "web" {
name = "${var.cluster_name}-web-mig"
project = var.project_id
region = var.region
distribution_policy_zones = var.zones
base_instance_name = "${var.cluster_name}-web"
version {
instance_template = google_compute_instance_template.web["all"].id
}
target_pools = [google_compute_target_pool.web.self_link]
target_size = lookup(var.instances["all"], "web_count", 0)
wait_for_instances = false
lifecycle {
create_before_destroy = true
}
}
resource "google_compute_instance_group_manager" "web" {
for_each = { for k, v in var.instances : k => v if contains(var.zones, "${var.region}-${k}") }
name = "${var.cluster_name}-web-${each.key}-mig"
project = var.project_id
zone = "${var.region}-${each.key}"
base_instance_name = "${var.cluster_name}-web-${each.key}"
version {
instance_template = google_compute_instance_template.web[each.key].id
}
named_port {
name = "http"
port = 80
}
named_port {
name = "https"
port = 443
}
target_pools = [google_compute_target_pool.web.self_link]
target_size = lookup(each.value, "web_count", 0)
wait_for_instances = false
lifecycle {
create_before_destroy = true
}
}
resource "google_compute_instance_template" "web" {
for_each = var.instances
name_prefix = "${var.cluster_name}-web-${each.key}-"
project = var.project_id
region = var.region
machine_type = lookup(each.value, "web_instance_type", "e2-standard-2")
# min_cpu_platform = ""
tags = concat(var.tags, ["${var.cluster_name}-infra", "${var.cluster_name}-master", "${var.cluster_name}-web"])
labels = {
label = "web"
}
metadata = {
ssh-keys = "debian:${file("~/.ssh/terraform.pub")}"
}
metadata_startup_script = "apt-get install -y nginx"
disk {
boot = true
auto_delete = true
disk_size_gb = 16
disk_type = "pd-balanced" // pd-ssd
source_image = "debian-cloud/debian-10"
labels = { label = "web" }
}
network_interface {
network = var.network
subnetwork = "core"
access_config {
network_tier = "STANDARD"
}
}
scheduling {
automatic_restart = true
on_host_maintenance = "MIGRATE"
}
shielded_instance_config {
enable_integrity_monitoring = true
enable_secure_boot = false
enable_vtpm = true
}
lifecycle {
create_before_destroy = "true"
}
}
# module "web" {
# source = "./modules/web"
# for_each = var.instances
# location = each.key
# labels = merge(var.tags, { label = "web" })
# network = hcloud_network.main.id
# subnet = hcloud_network_subnet.core.ip_range
# vm_name = "web-${each.key}-"
# vm_items = lookup(each.value, "web_count", 0)
# vm_type = lookup(each.value, "web_instance_type", "cx11")
# vm_image = data.hcloud_image.talos.id
# vm_ip_start = (3 + index(var.regions, each.key)) * 10
# vm_security_group = [hcloud_firewall.web.id]
# vm_params = merge(var.kubernetes, {
# lbv4 = hcloud_load_balancer_network.api.ip
# })
# }

View File

@@ -0,0 +1,89 @@
resource "google_compute_region_instance_group_manager" "worker" {
name = "${var.cluster_name}-worker-mig"
project = var.project_id
region = var.region
distribution_policy_zones = var.zones
base_instance_name = "${var.cluster_name}-worker"
version {
instance_template = google_compute_instance_template.worker["all"].id
}
target_pools = []
target_size = lookup(var.instances["all"], "worker_count", 0)
wait_for_instances = false
lifecycle {
create_before_destroy = true
}
}
resource "google_compute_instance_group_manager" "worker" {
for_each = { for k, v in var.instances : k => v if contains(var.zones, "${var.region}-${k}") }
name = "${var.cluster_name}-worker-${each.key}-mig"
project = var.project_id
zone = "${var.region}-${each.key}"
base_instance_name = "${var.cluster_name}-worker-${each.key}"
version {
instance_template = google_compute_instance_template.worker[each.key].id
}
target_pools = []
target_size = lookup(each.value, "worker_count", 0)
wait_for_instances = false
lifecycle {
create_before_destroy = true
}
}
resource "google_compute_instance_template" "worker" {
for_each = var.instances
name_prefix = "${var.cluster_name}-worker-${each.key}-"
project = var.project_id
region = var.region
machine_type = lookup(each.value, "worker_instance_type", "e2-standard-2")
# min_cpu_platform = ""
tags = concat(var.tags, ["${var.cluster_name}-infra", "${var.cluster_name}-master", "${var.cluster_name}-worker"])
labels = {
label = "worker"
}
metadata = {
ssh-keys = "debian:${file("~/.ssh/terraform.pub")}"
}
metadata_startup_script = "apt-get install -y nginx"
disk {
boot = true
auto_delete = true
disk_size_gb = 16
disk_type = "pd-balanced" // pd-ssd
source_image = "debian-cloud/debian-10"
labels = { label = "worker" }
}
network_interface {
network = var.network
subnetwork = "core"
}
scheduling {
automatic_restart = true
on_host_maintenance = "MIGRATE"
}
shielded_instance_config {
enable_integrity_monitoring = true
enable_secure_boot = false
enable_vtpm = true
}
lifecycle {
create_before_destroy = "true"
}
}

64
gcp-zonal/network-lb.tf Normal file
View File

@@ -0,0 +1,64 @@
resource "google_compute_address" "api" {
project = var.project_id
region = var.region
name = "${var.cluster_name}-controlplane"
description = "External ${var.cluster_name}-controlplane lb ip"
address_type = "EXTERNAL"
network_tier = "STANDARD"
}
# resource "google_compute_forwarding_rule" "controlplane" {
# project = var.project_id
# name = "${var.cluster_name}-controlplane"
# region = var.region
# target = google_compute_target_pool.controlplane.self_link
# load_balancing_scheme = "EXTERNAL"
# # ip_address
# port_range = "80-443"
# ip_protocol = "TCP"
# network_tier = "STANDARD"
# }
# resource "google_compute_target_pool" "controlplane" {
# project = var.project_id
# name = "${var.cluster_name}-controlplane-pool"
# region = var.region
# instances = google_compute_instance.controlplane[*].self_link
# health_checks = [google_compute_http_health_check.controlplane.id]
# }
# resource "google_compute_http_health_check" "controlplane" {
# name = "${var.cluster_name}-controlplane-pool"
# check_interval_sec = 15
# timeout_sec = 1
# request_path = "/"
# }
# resource "google_compute_forwarding_rule" "web" {
# project = var.project_id
# name = "${var.cluster_name}-web"
# region = var.region
# target = google_compute_target_pool.web.self_link
# load_balancing_scheme = "EXTERNAL"
# # ip_address
# port_range = "80-443"
# ip_protocol = "TCP"
# network_tier = "STANDARD"
# }
resource "google_compute_target_pool" "web" {
project = var.project_id
name = "${var.cluster_name}-web-pool"
region = var.region
health_checks = [google_compute_http_health_check.web.id]
}
resource "google_compute_http_health_check" "web" {
name = "${var.cluster_name}-web-pool"
check_interval_sec = 15
timeout_sec = 1
request_path = "/"
}

31
gcp-zonal/network-nat.tf Normal file
View File

@@ -0,0 +1,31 @@
resource "google_compute_address" "nat" {
project = var.project_id
region = var.region
name = "${var.cluster_name}-nat"
description = "External ${var.cluster_name}-nat ip"
address_type = "EXTERNAL"
network_tier = "PREMIUM"
}
resource "google_compute_router" "core" {
name = "${var.cluster_name}-route"
region = var.region
network = var.network
}
resource "google_compute_router_nat" "core" {
name = "${var.cluster_name}-nat"
project = var.project_id
region = var.region
router = google_compute_router.core.name
nat_ip_allocate_option = "MANUAL_ONLY"
nat_ips = [google_compute_address.nat.self_link]
source_subnetwork_ip_ranges_to_nat = "LIST_OF_SUBNETWORKS"
subnetwork {
name = "core"
source_ip_ranges_to_nat = ["PRIMARY_IP_RANGE"]
}
}

View File

@@ -0,0 +1,80 @@
resource "google_compute_firewall" "controlplane" {
project = var.project_id
name = "${var.cluster_name}-controlplane"
network = var.network
description = "Managed by terraform: Allow k8s/talos service"
priority = 1000
direction = "INGRESS"
source_ranges = [var.network_cidr]
target_tags = ["${var.cluster_name}-master"]
allow {
protocol = "tcp"
ports = ["6443", "50000", "50001"]
}
}
resource "google_compute_firewall" "controlplane_admin" {
project = var.project_id
name = "${var.cluster_name}-controlplane-admin"
network = var.network
description = "Managed by terraform: Allow admin console"
priority = 1001
direction = "INGRESS"
source_ranges = var.whitelist_admin
target_tags = ["${var.cluster_name}-master"]
allow {
protocol = "tcp"
ports = ["22", "6443", "50000"]
}
}
resource "google_compute_firewall" "controlplane_health_check" {
project = var.project_id
name = "${var.cluster_name}-controlplane-health"
network = var.network
description = "Managed by terraform: Allow health check"
priority = 1002
direction = "INGRESS"
source_ranges = ["169.254.169.254"]
target_tags = ["${var.cluster_name}-master"]
allow {
protocol = "tcp"
ports = ["6443"]
}
}
resource "google_compute_firewall" "web" {
project = var.project_id
name = "${var.cluster_name}-web"
network = var.network
description = "Managed by terraform: Allow web"
priority = 1000
direction = "INGRESS"
source_ranges = var.whitelist_web
target_tags = ["${var.cluster_name}-web"]
allow {
protocol = "tcp"
ports = ["80", "443"]
}
}
resource "google_compute_firewall" "web_health_check" {
project = var.project_id
name = "${var.cluster_name}-web-health"
network = var.network
description = "Managed by terraform: Allow web health check"
priority = 1001
direction = "INGRESS"
source_ranges = ["169.254.169.254"]
target_tags = ["${var.cluster_name}-web"]
allow {
protocol = "tcp"
ports = ["80"]
}
}

44
gcp-zonal/network.tf Normal file
View File

@@ -0,0 +1,44 @@
resource "google_compute_network" "network" {
name = var.network
description = "Project ${var.cluster_name}"
project = var.project_id
routing_mode = "REGIONAL"
mtu = 1500
auto_create_subnetworks = false
}
resource "google_compute_subnetwork" "core" {
name = "core"
project = var.project_id
region = var.region
description = "Core subnet"
network = google_compute_network.network.id
ip_cidr_range = cidrsubnet(var.network_cidr, 8, 0)
private_ip_google_access = true
}
resource "google_compute_subnetwork" "private" {
name = "private"
project = var.project_id
region = var.region
description = "Private subnet"
network = google_compute_network.network.id
ip_cidr_range = cidrsubnet(var.network_cidr, 8, 1)
private_ip_google_access = true
}
resource "google_compute_global_address" "google" {
name = "google-private-ip-address"
purpose = "VPC_PEERING"
address = cidrhost(cidrsubnet(var.network_cidr, 8, 2), 0)
address_type = "INTERNAL"
prefix_length = 24
network = google_compute_network.network.id
}
resource "google_service_networking_connection" "private_vpc_connection" {
network = google_compute_network.network.id
service = "servicenetworking.googleapis.com"
reserved_peering_ranges = [google_compute_global_address.google.name]
}

11
gcp-zonal/registry.tf Normal file
View File

@@ -0,0 +1,11 @@
resource "google_container_registry" "registry" {
project = var.project_id
location = "EU"
}
resource "google_storage_bucket_iam_member" "viewer" {
bucket = google_container_registry.registry.id
role = "roles/storage.objectViewer"
member = "serviceAccount:${data.google_client_openid_userinfo.terraform.email}"
}

View File

@@ -0,0 +1,69 @@
version: v1alpha1
debug: false
persist: true
machine:
type: ${type}
certSANs:
- "${lbv4}"
- "${lbv4_local}"
- "${ipv4}"
kubelet:
extraArgs:
node-ip: "${ipv4_local}"
rotate-server-certificates: true
network:
hostname: "${name}"
interfaces:
- interface: eth0
dhcp: true
- interface: eth0
cidr: ${lbv4_local}/32
- interface: eth0
cidr: ${lbv4}/32
- interface: dummy0
cidr: "169.254.2.53/32"
- interface: dummy0
cidr: "fd00::169:254:2:53/128"
install:
disk: /dev/sda
bootloader: true
wipe: false
extraKernelArgs:
- elevator=noop
sysctls:
net.core.somaxconn: 65535
net.core.netdev_max_backlog: 4096
systemDiskEncryption:
ephemeral:
provider: luks2
keys:
- nodeID: {}
slot: 0
cluster:
controlPlane:
endpoint: https://${lbv4}:6443
network:
dnsDomain: ${domain}
podSubnets: ${format("[%s]",podSubnets)}
serviceSubnets: ${format("[%s]",serviceSubnets)}
cni:
name: custom
urls:
- https://raw.githubusercontent.com/sergelogvinov/terraform-talos/main/gcp-zonal/deployments/cilium_result.yaml
proxy:
disabled: true
mode: ipvs
apiServer:
certSANs:
- "${lbv4_local}"
- "${lbv4}"
- "${ipv4}"
controllerManager: {}
scheduler: {}
etcd: {}
externalCloudProvider:
enabled: true
manifests:
- https://raw.githubusercontent.com/sergelogvinov/terraform-talos/main/gcp-zonal/deployments/kubelet-serving-cert-approver.yaml
- https://raw.githubusercontent.com/sergelogvinov/terraform-talos/main/gcp-zonal/deployments/metrics-server.yaml
- https://raw.githubusercontent.com/sergelogvinov/terraform-talos/main/gcp-zonal/deployments/local-path-storage.yaml

View File

@@ -0,0 +1,14 @@
data:
hosts: |
# static hosts
169.254.2.53 dns.local
fd00::169:254:2:53 dns.local
# terraform
%{ for node in masters ~}
${format("%-24s",node.ipv4_address)} ${node.name}
${format("%-24s",node.ipv6_address)} ${node.name}
%{ endfor ~}
%{ for node in web ~}
${format("%-24s",node.ipv4_address)} ${node.name}
${format("%-24s",node.ipv6_address)} ${node.name}
%{ endfor ~}

118
gcp-zonal/variables.tf Normal file
View File

@@ -0,0 +1,118 @@
variable "project_id" {
description = "The project ID to host the cluster in"
}
variable "cluster_name" {
description = "A default cluster name"
default = "talos"
}
variable "region" {
description = "The region to host the cluster in"
}
variable "zones" {
type = list(string)
description = "The zone to host the cluster in (required if is a zonal cluster)"
}
variable "kubernetes" {
type = map(string)
default = {
podSubnets = "10.32.0.0/12"
serviceSubnets = "10.200.0.0/22"
domain = "cluster.local"
cluster_name = "talos-k8s-hezner"
tokenmachine = ""
token = ""
ca = ""
}
sensitive = true
}
variable "network" {
description = "The VPC network created to host the cluster in"
default = "production"
}
variable "network_cidr" {
description = "Local subnet rfc1918"
default = "172.16.0.0/16"
}
variable "whitelist_web" {
description = "Cloudflare subnets"
default = [
"173.245.48.0/20",
"103.21.244.0/22",
"103.22.200.0/22",
"103.31.4.0/22",
"141.101.64.0/18",
"108.162.192.0/18",
"190.93.240.0/20",
"188.114.96.0/20",
"197.234.240.0/22",
"198.41.128.0/17",
"162.158.0.0/15",
"172.64.0.0/13",
"131.0.72.0/22",
"104.16.0.0/13",
"104.24.0.0/14",
]
}
variable "whitelist_admin" {
description = "Cloudflare subnets"
default = [
"0.0.0.0/0",
]
}
variable "tags" {
description = "Tags of resources"
type = list(string)
default = [
"develop"
]
}
variable "controlplane" {
description = "Count of controlplanes"
type = map(any)
default = {
count = 0,
type = "e2-small"
}
}
variable "instances" {
description = "Map of region's properties"
type = map(any)
default = {
"a" = {
web_count = 0,
web_instance_type = "e2-small",
worker_count = 0,
worker_instance_type = "e2-small",
},
"b" = {
web_count = 0,
web_instance_type = "e2-small",
worker_count = 0,
worker_instance_type = "e2-small",
}
"c" = {
web_count = 0,
web_instance_type = "e2-small",
worker_count = 0,
worker_instance_type = "e2-small",
}
"all" = {
web_count = 0,
web_instance_type = "e2-small",
worker_count = 0,
worker_instance_type = "e2-small",
}
}
}

9
gcp-zonal/versions.tf Normal file
View File

@@ -0,0 +1,9 @@
terraform {
required_providers {
google = {
source = "hashicorp/google"
version = "~> 3.76.0"
}
}
required_version = ">= 1.0"
}

56
system_os/gcp/gcp.pkr.hcl Normal file
View File

@@ -0,0 +1,56 @@
packer {
required_plugins {
googlecompute = {
version = ">= 1.0.0"
source = "github.com/hashicorp/googlecompute"
}
}
}
variable "google_account" {
type = string
default = ""
sensitive = true
}
variable "google_project" {
type = string
default = ""
sensitive = true
}
variable "talos_version" {
type = string
default = "v0.11.3"
}
source "googlecompute" "talos" {
account_file = "${var.google_account}"
project_id = "${var.google_project}"
zone = "europe-west4-a"
subnetwork = "default"
source_image_family = "debian-10"
ssh_username = "debian"
machine_type = "e2-small"
disk_size = 10
disk_type = "pd-standard"
image_name = "talos"
image_description = "talos system disk"
image_family = "talos"
image_licenses = ["projects/vm-options/global/licenses/enable-vmx"]
image_storage_locations = ["europe-west4"]
}
build {
sources = ["source.googlecompute.talos"]
provisioner "shell" {
inline = [
"sudo apt-get install -y wget",
"wget -O /tmp/talos.tar.gz https://github.com/talos-systems/talos/releases/download/${var.talos_version}/gcp-amd64.tar.gz",
"tar xOzf /tmp/talos.tar.gz | sudo dd of=/dev/sda",
]
}
}