Files
infrastructure/clusters/cl01tl/manifests/cilium/DaemonSet-cilium.yml

495 lines
18 KiB
YAML

---
# Source: cilium/charts/cilium/templates/cilium-agent/daemonset.yaml
apiVersion: apps/v1
kind: DaemonSet
metadata:
name: cilium
namespace: kube-system
labels:
k8s-app: cilium
app.kubernetes.io/part-of: cilium
app.kubernetes.io/name: cilium-agent
spec:
selector:
matchLabels:
k8s-app: cilium
updateStrategy:
rollingUpdate:
maxUnavailable: 2
type: RollingUpdate
template:
metadata:
annotations:
# ensure pods roll when configmap updates
cilium.io/cilium-configmap-checksum: "31ad7748e0aefe75b6436d96c8c85754e0b44e68e6012fa188bc5bcd66085828"
kubectl.kubernetes.io/default-container: cilium-agent
labels:
k8s-app: cilium
app.kubernetes.io/name: cilium-agent
app.kubernetes.io/part-of: cilium
spec:
securityContext:
appArmorProfile:
type: Unconfined
seccompProfile:
type: Unconfined
containers:
- name: cilium-agent
image: "quay.io/cilium/cilium:v1.18.4@sha256:49d87af187eeeb9e9e3ec2bc6bd372261a0b5cb2d845659463ba7cc10fe9e45f"
imagePullPolicy: IfNotPresent
command:
- cilium-agent
args:
- --config-dir=/tmp/cilium/config-map
startupProbe:
httpGet:
host: "127.0.0.1"
path: /healthz
port: 9879
scheme: HTTP
httpHeaders:
- name: "brief"
value: "true"
failureThreshold: 300
periodSeconds: 2
successThreshold: 1
initialDelaySeconds: 5
livenessProbe:
httpGet:
host: "127.0.0.1"
path: /healthz
port: 9879
scheme: HTTP
httpHeaders:
- name: "brief"
value: "true"
- name: "require-k8s-connectivity"
value: "false"
periodSeconds: 30
successThreshold: 1
failureThreshold: 10
timeoutSeconds: 5
readinessProbe:
httpGet:
host: "127.0.0.1"
path: /healthz
port: 9879
scheme: HTTP
httpHeaders:
- name: "brief"
value: "true"
periodSeconds: 30
successThreshold: 1
failureThreshold: 3
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: GOMEMLIMIT
valueFrom:
resourceFieldRef:
resource: limits.memory
divisor: '1'
- name: KUBERNETES_SERVICE_HOST
value: "localhost"
- name: KUBERNETES_SERVICE_PORT
value: "7445"
- name: KUBE_CLIENT_BACKOFF_BASE
value: "1"
- name: KUBE_CLIENT_BACKOFF_DURATION
value: "120"
lifecycle:
postStart:
exec:
command:
- "bash"
- "-c"
- |
set -o errexit
set -o pipefail
set -o nounset
# When running in AWS ENI mode, it's likely that 'aws-node' has
# had a chance to install SNAT iptables rules. These can result
# in dropped traffic, so we should attempt to remove them.
# We do it using a 'postStart' hook since this may need to run
# for nodes which might have already been init'ed but may still
# have dangling rules. This is safe because there are no
# dependencies on anything that is part of the startup script
# itself, and can be safely run multiple times per node (e.g. in
# case of a restart).
if [[ "$(iptables-save | grep -E -c 'AWS-SNAT-CHAIN|AWS-CONNMARK-CHAIN')" != "0" ]];
then
echo 'Deleting iptables rules created by the AWS CNI VPC plugin'
iptables-save | grep -E -v 'AWS-SNAT-CHAIN|AWS-CONNMARK-CHAIN' | iptables-restore
fi
echo 'Done!'
preStop:
exec:
command:
- /cni-uninstall.sh
ports:
- name: peer-service
containerPort: 4244
hostPort: 4244
protocol: TCP
- name: prometheus
containerPort: 9962
hostPort: 9962
protocol: TCP
securityContext:
seLinuxOptions:
level: s0
type: spc_t
capabilities:
add:
- CHOWN
- KILL
- NET_ADMIN
- NET_RAW
- IPC_LOCK
- SYS_ADMIN
- SYS_RESOURCE
- DAC_OVERRIDE
- FOWNER
- SETGID
- SETUID
- PERFMON
- BPF
drop:
- ALL
terminationMessagePolicy: FallbackToLogsOnError
volumeMounts:
- name: envoy-sockets
mountPath: /var/run/cilium/envoy/sockets
readOnly: false
# Unprivileged containers need to mount /proc/sys/net from the host
# to have write access
- mountPath: /host/proc/sys/net
name: host-proc-sys-net
# Unprivileged containers need to mount /proc/sys/kernel from the host
# to have write access
- mountPath: /host/proc/sys/kernel
name: host-proc-sys-kernel
- name: bpf-maps
mountPath: /sys/fs/bpf
# Unprivileged containers can't set mount propagation to bidirectional
# in this case we will mount the bpf fs from an init container that
# is privileged and set the mount propagation from host to container
# in Cilium.
mountPropagation: HostToContainer
# Check for duplicate mounts before mounting
- name: cilium-cgroup
mountPath: /sys/fs/cgroup
- name: cilium-run
mountPath: /var/run/cilium
- name: cilium-netns
mountPath: /var/run/cilium/netns
mountPropagation: HostToContainer
- name: etc-cni-netd
mountPath: /host/etc/cni/net.d
- name: clustermesh-secrets
mountPath: /var/lib/cilium/clustermesh
readOnly: true
# Needed to be able to load kernel modules
- name: lib-modules
mountPath: /lib/modules
readOnly: true
- name: xtables-lock
mountPath: /run/xtables.lock
- name: hubble-tls
mountPath: /var/lib/cilium/tls/hubble
readOnly: true
- name: tmp
mountPath: /tmp
initContainers:
- name: config
image: "quay.io/cilium/cilium:v1.18.4@sha256:49d87af187eeeb9e9e3ec2bc6bd372261a0b5cb2d845659463ba7cc10fe9e45f"
imagePullPolicy: IfNotPresent
command:
- cilium-dbg
- build-config
env:
- name: K8S_NODE_NAME
valueFrom:
fieldRef:
apiVersion: v1
fieldPath: spec.nodeName
- name: CILIUM_K8S_NAMESPACE
valueFrom:
fieldRef:
apiVersion: v1
fieldPath: metadata.namespace
- name: KUBERNETES_SERVICE_HOST
value: "localhost"
- name: KUBERNETES_SERVICE_PORT
value: "7445"
volumeMounts:
- name: tmp
mountPath: /tmp
terminationMessagePolicy: FallbackToLogsOnError
- name: apply-sysctl-overwrites
image: "quay.io/cilium/cilium:v1.18.4@sha256:49d87af187eeeb9e9e3ec2bc6bd372261a0b5cb2d845659463ba7cc10fe9e45f"
imagePullPolicy: IfNotPresent
env:
- name: BIN_PATH
value: /opt/cni/bin
command:
- sh
- -ec
# The statically linked Go program binary is invoked to avoid any
# dependency on utilities like sh 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-sysctlfix /hostbin/cilium-sysctlfix;
nsenter --mount=/hostproc/1/ns/mnt "${BIN_PATH}/cilium-sysctlfix";
rm /hostbin/cilium-sysctlfix
volumeMounts:
- name: hostproc
mountPath: /hostproc
- name: cni-path
mountPath: /hostbin
terminationMessagePolicy: FallbackToLogsOnError
securityContext:
seLinuxOptions:
level: s0
type: spc_t
capabilities:
add:
- SYS_ADMIN
- SYS_CHROOT
- SYS_PTRACE
drop:
- ALL
# Mount the bpf fs if it is not mounted. We will perform this task
# from a privileged container because the mount propagation bidirectional
# only works from privileged containers.
- name: mount-bpf-fs
image: "quay.io/cilium/cilium:v1.18.4@sha256:49d87af187eeeb9e9e3ec2bc6bd372261a0b5cb2d845659463ba7cc10fe9e45f"
imagePullPolicy: IfNotPresent
args:
- 'mount | grep "/sys/fs/bpf type bpf" || mount -t bpf bpf /sys/fs/bpf'
command:
- /bin/bash
- -c
- --
terminationMessagePolicy: FallbackToLogsOnError
securityContext:
privileged: true
volumeMounts:
- name: bpf-maps
mountPath: /sys/fs/bpf
mountPropagation: Bidirectional
- name: clean-cilium-state
image: "quay.io/cilium/cilium:v1.18.4@sha256:49d87af187eeeb9e9e3ec2bc6bd372261a0b5cb2d845659463ba7cc10fe9e45f"
imagePullPolicy: IfNotPresent
command:
- /init-container.sh
env:
- name: CILIUM_ALL_STATE
valueFrom:
configMapKeyRef:
name: cilium-config
key: clean-cilium-state
optional: true
- name: CILIUM_BPF_STATE
valueFrom:
configMapKeyRef:
name: cilium-config
key: clean-cilium-bpf-state
optional: true
- name: WRITE_CNI_CONF_WHEN_READY
valueFrom:
configMapKeyRef:
name: cilium-config
key: write-cni-conf-when-ready
optional: true
- name: KUBERNETES_SERVICE_HOST
value: "localhost"
- name: KUBERNETES_SERVICE_PORT
value: "7445"
terminationMessagePolicy: FallbackToLogsOnError
securityContext:
seLinuxOptions:
level: s0
type: spc_t
capabilities:
add:
- NET_ADMIN
- SYS_ADMIN
- SYS_RESOURCE
drop:
- ALL
volumeMounts:
- name: bpf-maps
mountPath: /sys/fs/bpf
# Required to mount cgroup filesystem from the host to cilium agent pod
- name: cilium-cgroup
mountPath: /sys/fs/cgroup
mountPropagation: HostToContainer
- name: cilium-run
mountPath: /var/run/cilium # wait-for-kube-proxy
# Install the CNI binaries in an InitContainer so we don't have a writable host mount in the agent
- name: install-cni-binaries
image: "quay.io/cilium/cilium:v1.18.4@sha256:49d87af187eeeb9e9e3ec2bc6bd372261a0b5cb2d845659463ba7cc10fe9e45f"
imagePullPolicy: IfNotPresent
command:
- "/install-plugin.sh"
resources:
requests:
cpu: 100m
memory: 10Mi
securityContext:
seLinuxOptions:
level: s0
type: spc_t
capabilities:
drop:
- ALL
terminationMessagePolicy: FallbackToLogsOnError
volumeMounts:
- name: cni-path
mountPath: /host/opt/cni/bin # .Values.cni.install
restartPolicy: Always
priorityClassName: system-node-critical
serviceAccountName: "cilium"
automountServiceAccountToken: true
terminationGracePeriodSeconds: 1
hostNetwork: true
affinity:
podAntiAffinity:
requiredDuringSchedulingIgnoredDuringExecution:
- labelSelector:
matchLabels:
k8s-app: cilium
topologyKey: kubernetes.io/hostname
nodeSelector:
kubernetes.io/os: linux
tolerations:
- operator: Exists
volumes:
# For sharing configuration between the "config" initContainer and the agent
- name: tmp
emptyDir: {}
# To keep state between restarts / upgrades
- name: cilium-run
hostPath:
path: /var/run/cilium
type: DirectoryOrCreate
# To exec into pod network namespaces
- name: cilium-netns
hostPath:
path: /var/run/netns
type: DirectoryOrCreate
# To keep state between restarts / upgrades for bpf maps
- name: bpf-maps
hostPath:
path: /sys/fs/bpf
type: DirectoryOrCreate
# To mount cgroup2 filesystem on the host or apply sysctlfix
- name: hostproc
hostPath:
path: /proc
type: Directory
# To keep state between restarts / upgrades for cgroup2 filesystem
- name: cilium-cgroup
hostPath:
path: /sys/fs/cgroup
type: DirectoryOrCreate
# To install cilium cni plugin in the host
- name: cni-path
hostPath:
path: /opt/cni/bin
type: DirectoryOrCreate
# To install cilium cni configuration in the host
- name: etc-cni-netd
hostPath:
path: /etc/cni/net.d
type: DirectoryOrCreate
# To be able to load kernel modules
- name: lib-modules
hostPath:
path: /lib/modules
# To access iptables concurrently with other processes (e.g. kube-proxy)
- name: xtables-lock
hostPath:
path: /run/xtables.lock
type: FileOrCreate
# Sharing socket with Cilium Envoy on the same node by using a host path
- name: envoy-sockets
hostPath:
path: "/var/run/cilium/envoy/sockets"
type: DirectoryOrCreate
# To read the clustermesh configuration
- name: clustermesh-secrets
projected:
# note: the leading zero means this number is in octal representation: do not remove it
defaultMode: 0400
sources:
- secret:
name: cilium-clustermesh
optional: true
# note: items are not explicitly listed here, since the entries of this secret
# depend on the peers configured, and that would cause a restart of all agents
# at every addition/removal. Leaving the field empty makes each secret entry
# to be automatically projected into the volume as a file whose name is the key.
- secret:
name: clustermesh-apiserver-remote-cert
optional: true
items:
- key: tls.key
path: common-etcd-client.key
- key: tls.crt
path: common-etcd-client.crt
- key: ca.crt
path: common-etcd-client-ca.crt
# note: we configure the volume for the kvstoremesh-specific certificate
# regardless of whether KVStoreMesh is enabled or not, so that it can be
# automatically mounted in case KVStoreMesh gets subsequently enabled,
# without requiring an agent restart.
- secret:
name: clustermesh-apiserver-local-cert
optional: true
items:
- key: tls.key
path: local-etcd-client.key
- key: tls.crt
path: local-etcd-client.crt
- key: ca.crt
path: local-etcd-client-ca.crt
- name: host-proc-sys-net
hostPath:
path: /proc/sys/net
type: Directory
- name: host-proc-sys-kernel
hostPath:
path: /proc/sys/kernel
type: Directory
- name: hubble-tls
projected:
# note: the leading zero means this number is in octal representation: do not remove it
defaultMode: 0400
sources:
- secret:
name: hubble-server-certs
optional: true
items:
- key: tls.crt
path: server.crt
- key: tls.key
path: server.key
- key: ca.crt
path: client-ca.crt