Files
puppet-prod/hieradata/roles/infra/k8s.yaml
T
unkinben 2d125487c3
ci/woodpecker/pr/ruby-validate Pipeline was successful
ci/woodpecker/pr/erb-validate Pipeline was successful
ci/woodpecker/pr/puppet-lint Pipeline was successful
ci/woodpecker/pr/bolt-validate Pipeline was successful
ci/woodpecker/pr/yamllint Pipeline was successful
ci/woodpecker/pr/epp-validate Pipeline was successful
ci/woodpecker/pr/ruby-check Pipeline was successful
ci/woodpecker/pr/puppet-validate Pipeline was successful
ceph: manage /etc/ceph/ceph.conf on osd and mon/mgr/mds hosts
Bring the hand-maintained /etc/ceph/ceph.conf under Puppet on the
prodnxsr ceph cluster (fsid de96a98f). The file is identified per host
by role: k8s roles include profiles::ceph::osd only and get a [global]
section; the incus node role also includes profiles::ceph::mds and
additionally gets the [mds] + [mds.*] sections.

- Add cluster topology as a single source of truth in common.yaml:
  cluster_public_ips (all 13 ceph host /32s), mon_initial_members, and
  the mds_instances map (two mds daemons per mon/mgr/mds host).
- Render /etc/ceph/ceph.conf from that topology in the reworked
  client.conf.erb, preserving the live two-space indent and key order.
- Gate the [mds] sections on render_mds_config, set true only in the
  incus node role hiera (the role that includes profiles::ceph::mds).
- Drop the hard Package[ceph-common] dependency when the class does not
  manage the package (cephadm/profiles::packages deliver it on the k8s
  and incus hosts).
- Enable manage_ceph_conf on the k8s and incus node roles.

public_network is normalized to all 13 ceph host /32s on every host;
this rewrites it on the mon/mgr/mds hosts (adding .1-.8) as the one
intended content change. RGW hosts keep their profiles::ceph::conf
variant and are untouched.

Claude-Session: https://claude.ai/code/session_01JUoARVdmhxKQHyyyp1pxeT
2026-08-08 19:56:49 +10:00

209 lines
5.6 KiB
YAML

---
hiera_include:
- profiles::selinux::setenforce
- profiles::ceph::node
- profiles::ceph::osd
- profiles::ceph::client
- exporters::frr_exporter
- frrouting
- rke2
# manage rke2
rke2::bootstrap_node: prodnxsr0001.main.unkin.net
rke2::join_url: https://join-k8s.service.consul:9345
# pull the airgap image bundle via artifactapi (host-reachable pre-CNI), not github directly
rke2::container_archive_source: 'https://artifactapi.k8s.syd1.au.unkin.net/api/v1/remote/github/rancher/rke2/releases/download'
rke2::manage_registries: true
rke2::registries:
docker.io:
endpoint:
- "https://artifactapi.k8s.syd1.au.unkin.net"
rewrite:
"^(.*)$": "dockerhub/$1"
disable-default-registry-endpoint: true
ghcr.io:
endpoint:
- "https://artifactapi.k8s.syd1.au.unkin.net"
rewrite:
"^(.*)$": "ghcr/$1"
disable-default-registry-endpoint: true
quay.io:
endpoint:
- "https://artifactapi.k8s.syd1.au.unkin.net"
rewrite:
"^(.*)$": "quay/$1"
disable-default-registry-endpoint: true
registry.k8s.io:
endpoint:
- "https://artifactapi.k8s.syd1.au.unkin.net"
rewrite:
"^(.*)$": "k8s-registry/$1"
disable-default-registry-endpoint: true
registry.gitlab.com:
endpoint:
- "https://artifactapi.k8s.syd1.au.unkin.net"
rewrite:
"^(.*)$": "gitlab/$1"
disable-default-registry-endpoint: true
docker.elastic.co:
endpoint:
- "https://artifactapi.k8s.syd1.au.unkin.net"
rewrite:
"^(.*)$": "elastic/$1"
disable-default-registry-endpoint: true
gcr.io:
endpoint:
- "https://artifactapi.k8s.syd1.au.unkin.net"
rewrite:
"^(.*)$": "gcr/$1"
disable-default-registry-endpoint: true
docker.litellm.ai:
endpoint:
- "https://artifactapi.k8s.syd1.au.unkin.net"
rewrite:
"^(.*)$": "litellm/$1"
disable-default-registry-endpoint: true
public.ecr.aws:
endpoint:
- "https://artifactapi.k8s.syd1.au.unkin.net"
rewrite:
"^(.*)$": "ecr-public/$1"
disable-default-registry-endpoint: true
rke2::config_hash:
bind-address: "%{hiera('networking_loopback0_ip')}"
node-ip: "%{hiera('networking_loopback0_ip')}"
node-external-ip: "%{hiera('networking_loopback0_ip')}"
write-kubeconfig-mode: 644
kubelet-arg:
- '--node-status-update-frequency=4s'
- '--max-pods=100'
node-label:
- "region=%{facts.region}"
- "country=%{facts.country}"
- "asset=%{facts.dmi.product.serial_number}"
- "zone=%{zone}"
# FIXME: puppet-python wants to try manage python-dev, which is required by the ceph package
python::manage_dev_package: false
profiles::packages::include:
bridge-utils: {}
cephadm: {}
profiles::selinux::setenforce::mode: disabled
profiles::ceph::client::manage_ceph_conf: true
profiles::ceph::client::manage_ceph_package: false
profiles::ceph::client::manage_ceph_paths: false
profiles::ceph::client::fsid: 'de96a98f-3d23-465a-a899-86d3d67edab8'
profiles::ceph::client::mons:
- 198.18.23.9
- 198.18.23.10
- 198.18.23.11
- 198.18.23.12
- 198.18.23.13
# additional repos
profiles::yum::global::repos:
ceph:
ensure: present
ceph-noarch:
ensure: present
frr-extras:
ensure: present
frr-stable:
ensure: present
rancher-rke2-common-latest:
ensure: present
rancher-rke2-1-33-latest:
ensure: present
# dns
profiles::dns::base::primary_interface: loopback0
# networking
systemd::manage_networkd: true
systemd::manage_all_network_files: true
networking::interfaces:
"%{hiera('networking_1000_iface')}":
type: physical
ipaddress: "%{hiera('networking_1000_ip')}"
gateway: 198.18.15.254
txqueuelen: 10000
forwarding: true
"%{hiera('networking_2500_iface')}":
type: physical
ipaddress: "%{hiera('networking_2500_ip')}"
mtu: 1500
txqueuelen: 10000
forwarding: true
loopback0:
type: dummy
ipaddress: "%{hiera('networking_loopback0_ip')}"
netmask: 255.255.255.255
mtu: 1500
loopback1:
type: dummy
ipaddress: "%{hiera('networking_loopback1_ip')}"
netmask: 255.255.255.255
mtu: 1500
loopback2:
type: dummy
ipaddress: "%{hiera('networking_loopback2_ip')}"
netmask: 255.255.255.255
mtu: 1500
# configure consul service
profiles::consul::client::host_addr: "%{hiera('networking_loopback0_ip')}"
profiles::consul::client::node_rules:
- resource: service
segment: frr_exporter
disposition: write
# frrouting
exporters::frr_exporter::enable: true
frrouting::ospfd_router_id: "%{hiera('networking_loopback0_ip')}"
frrouting::ospf_preferred_source_enable: true
frrouting::ospf_preferred_source: "%{hiera('networking_loopback0_ip')}"
frrouting::ospfd_redistribute:
- connected
frrouting::ospfd_interfaces:
"%{hiera('networking_1000_iface')}":
area: 0.0.0.0
"%{hiera('networking_2500_iface')}":
area: 0.0.0.0
loopback0:
area: 0.0.0.0
loopback1:
area: 0.0.0.0
loopback2:
area: 0.0.0.0
frrouting::daemons:
ospfd: true
frrouting::ospf_exclude_k8s_enable: true
frrouting::k8s_cluster_cidr: '10.42.0.0/16' # RKE2 cluster-cidr (pods)
frrouting::k8s_service_cidr: '10.43.0.0/16' # RKE2 service-cidr
# sysctl recommendations
sysctl::base::values:
net.ipv4.conf.default.rp_filter:
value: '0'
net.ipv4.conf.all.rp_filter:
value: '0'
fs.inotify.max_user_watches:
value: '524288'
fs.inotify.max_user_instances:
value: '512'
# add loopback interfaces to ssh list
ssh::server::options:
ListenAddress:
- "%{hiera('networking_loopback0_ip')}"
- "%{hiera('networking_1000_ip')}"
- "%{hiera('networking_2500_ip')}"
profiles::ssh::sign::principals:
- "%{hiera('networking_loopback0_ip')}"
- "%{hiera('networking_1000_ip')}"
- "%{hiera('networking_2500_ip')}"