Files
k3s-ansible/roles/k3s_server_post/tasks/metallb.yml
T
Timothy Stewart 21f7317ab8 fix(metallb): retry the webhook endpoint check on transient kube API errors
- retry the webhook-service endpoint get until it succeeds
- extend the regression test to cover the webhook task too
2026-08-07 01:30:53 -05:00

155 lines
5.8 KiB
YAML

---
- name: Create manifests directory for temp configuration
ansible.builtin.file:
path: /tmp/k3s
state: directory
owner: "{{ ansible_user_id }}"
mode: "0755"
with_items: "{{ groups[group_name_master | default('master')] }}"
run_once: true
- name: Delete outdated metallb replicas
ansible.builtin.shell: |-
set -o pipefail
REPLICAS=$({{ k3s_kubectl_binary | default('k3s kubectl') }} --namespace='metallb-system' get replicasets \
-l 'component=controller,app=metallb' \
-o jsonpath='{.items[0].spec.template.spec.containers[0].image}, {.items[0].metadata.name}' 2>/dev/null || true)
REPLICAS_SETS=$(echo ${REPLICAS} | grep -v '{{ metal_lb_controller_tag_version }}' | sed -e "s/^.*\s//g")
if [ -n "${REPLICAS_SETS}" ] ; then
for REPLICAS in "${REPLICAS_SETS}"
do
{{ k3s_kubectl_binary | default('k3s kubectl') }} --namespace='metallb-system' \
delete rs "${REPLICAS}"
done
fi
args:
executable: /bin/bash
changed_when: false
run_once: true
with_items: "{{ groups[group_name_master | default('master')] }}"
- name: Copy metallb CRs manifest to first master
ansible.builtin.template:
src: metallb.crs.j2
dest: /tmp/k3s/metallb-crs.yaml
owner: "{{ ansible_user_id }}"
mode: "0755"
with_items: "{{ groups[group_name_master | default('master')] }}"
run_once: true
- name: Test metallb-system namespace
ansible.builtin.command: >-
{{ k3s_kubectl_binary | default('k3s kubectl') }} get namespace metallb-system
changed_when: false
# The kube API can briefly return ServiceUnavailable while MetalLB converges,
# which would otherwise abort the whole converge play on a transient error.
register: metallb_namespace_result
until: metallb_namespace_result.rc == 0
retries: "{{ download_retries }}"
delay: "{{ download_delay }}"
with_items: "{{ groups[group_name_master | default('master')] }}"
run_once: true
- name: Wait for MetalLB resources
ansible.builtin.command: >-
{{ k3s_kubectl_binary | default('k3s kubectl') }} wait {{ item.resource }}
--namespace='metallb-system'
{% if item.name | default(False) -%}{{ item.name }}{%- endif %}
{% if item.selector | default(False) -%}--selector='{{ item.selector }}'{%- endif %}
{% if item.condition | default(False) -%}{{ item.condition }}{%- endif %}
--timeout='{{ metal_lb_available_timeout }}'
changed_when: false
# The kube API can briefly return ServiceUnavailable while MetalLB converges,
# which would otherwise abort the whole converge play on a transient error.
register: metallb_wait_result
until: metallb_wait_result.rc == 0
retries: "{{ download_retries }}"
delay: "{{ download_delay }}"
run_once: true
with_items:
- description: controller
resource: deployment
name: controller
condition: --for condition=Available=True
- description: webhook service
resource: pod
selector: component=controller
condition: --for=jsonpath='{.status.phase}'=Running
- description: pods in replica sets
resource: pod
selector: component=controller,app=metallb
condition: --for condition=Ready
- description: ready replicas of controller
resource: replicaset
selector: component=controller,app=metallb
condition: --for=jsonpath='{.status.readyReplicas}'=1
- description: fully labeled replicas of controller
resource: replicaset
selector: component=controller,app=metallb
condition: --for=jsonpath='{.status.fullyLabeledReplicas}'=1
- description: available replicas of controller
resource: replicaset
selector: component=controller,app=metallb
condition: --for=jsonpath='{.status.availableReplicas}'=1
loop_control:
label: "{{ item.description }}"
- name: Set metallb webhook service name
ansible.builtin.set_fact:
# Inspected the v0.16.0 manifest: the newer webhook Service name is used
# by every supported MetalLB release, so the old pre-0.14.4 branch is gone.
metallb_webhook_service_name: metallb-webhook-service
- name: Test metallb-system webhook-service endpoint
ansible.builtin.command: >-
{{ k3s_kubectl_binary | default('k3s kubectl') }} -n metallb-system get endpoints {{ metallb_webhook_service_name }}
changed_when: false
# The kube API can briefly return ServiceUnavailable while MetalLB converges,
# which would otherwise abort the whole converge play on a transient error.
register: metallb_webhook_result
until: metallb_webhook_result.rc == 0
retries: "{{ download_retries }}"
delay: "{{ download_delay }}"
with_items: "{{ groups[group_name_master | default('master')] }}"
run_once: true
- name: Apply metallb CRs
ansible.builtin.command: >-
{{ k3s_kubectl_binary | default('k3s kubectl') }} apply -f /tmp/k3s/metallb-crs.yaml
--timeout='{{ metal_lb_available_timeout }}'
register: this
changed_when: false
run_once: true
until: this.rc == 0
retries: 5
- name: Test metallb-system resources for Layer 2 configuration
ansible.builtin.command: >-
{{ k3s_kubectl_binary | default('k3s kubectl') }} -n metallb-system get {{ item }}
changed_when: false
run_once: true
when: metal_lb_mode == "layer2"
register: metallb_l2_test_result
until: metallb_l2_test_result.rc == 0
retries: "{{ download_retries }}"
delay: "{{ download_delay }}"
with_items:
- IPAddressPool
- L2Advertisement
- name: Test metallb-system resources for BGP configuration
ansible.builtin.command: >-
{{ k3s_kubectl_binary | default('k3s kubectl') }} -n metallb-system get {{ item }}
changed_when: false
run_once: true
when: metal_lb_mode == "bgp"
register: metallb_bgp_test_result
until: metallb_bgp_test_result.rc == 0
retries: "{{ download_retries }}"
delay: "{{ download_delay }}"
with_items:
- IPAddressPool
- BGPPeer
- BGPAdvertisement