a0206d9626
Currently, if a multi-node cluster is shut down unexpectedly, RabbitMQ is not able to boot and sync with the other nodes. The purpose of this change is to add the possibility to use the rabbitmqctl force_boot command to recover RabbitMQ cluster from an unexpected shut down. Test plan: PASS: Shutdown and start a multi-node RabbitMQ cluster Regression: PASS: OpenStack can be applied successfully PASS: RabbitMQ nodes can join the RabbitMQ cluster Story: 2009784 Task: 44290 Ref: [0] https://www.rabbitmq.com/rabbitmqctl.8.html#force_boot Signed-off-by: Maik Catrinque <maik.wandercatrinqueandrade@windriver.com> Co-authored-by: Andrew Martins Carletti <Andrew.MartinsCarletti@windriver.com> Change-Id: I56e966ea64e8881ba436213f0c9e1cbe547098e3
407 lines
10 KiB
YAML
407 lines
10 KiB
YAML
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
|
|
# Default values for rabbitmq.
|
|
# This is a YAML-formatted file.
|
|
# Declare name/value pairs to be passed into your templates.
|
|
# name: value
|
|
|
|
---
|
|
labels:
|
|
server:
|
|
node_selector_key: openstack-control-plane
|
|
node_selector_value: enabled
|
|
prometheus_rabbitmq_exporter:
|
|
node_selector_key: openstack-control-plane
|
|
node_selector_value: enabled
|
|
test:
|
|
node_selector_key: openstack-control-plane
|
|
node_selector_value: enabled
|
|
jobs:
|
|
node_selector_key: openstack-control-plane
|
|
node_selector_value: enabled
|
|
|
|
images:
|
|
tags:
|
|
prometheus_rabbitmq_exporter: docker.io/kbudde/rabbitmq-exporter:v1.0.0-RC7.1
|
|
prometheus_rabbitmq_exporter_helm_tests: docker.io/openstackhelm/heat:stein-ubuntu_bionic
|
|
rabbitmq_init: docker.io/openstackhelm/heat:stein-ubuntu_bionic
|
|
rabbitmq: docker.io/library/rabbitmq:3.7.26
|
|
dep_check: quay.io/airshipit/kubernetes-entrypoint:v1.0.0
|
|
scripted_test: docker.io/library/rabbitmq:3.7.26-management
|
|
image_repo_sync: docker.io/library/docker:17.07.0
|
|
pull_policy: "IfNotPresent"
|
|
local_registry:
|
|
active: false
|
|
exclude:
|
|
- dep_check
|
|
- image_repo_sync
|
|
|
|
# forceBoot: executes 'rabbitmqctl force_boot' to force boot on
|
|
# cluster shut down unexpectedly in an unknown order.
|
|
# ref: https://www.rabbitmq.com/rabbitmqctl.8.html#force_boot
|
|
forceBoot:
|
|
enabled: false
|
|
|
|
pod:
|
|
probes:
|
|
prometheus_rabbitmq_exporter:
|
|
rabbitmq_exporter:
|
|
readiness:
|
|
enabled: true
|
|
params:
|
|
initialDelaySeconds: 30
|
|
periodSeconds: 30
|
|
timeoutSeconds: 5
|
|
liveness:
|
|
enabled: true
|
|
params:
|
|
initialDelaySeconds: 120
|
|
periodSeconds: 90
|
|
timeoutSeconds: 5
|
|
security_context:
|
|
exporter:
|
|
pod:
|
|
runAsUser: 65534
|
|
container:
|
|
rabbitmq_exporter:
|
|
readOnlyRootFilesystem: true
|
|
allowPrivilegeEscalation: false
|
|
server:
|
|
pod:
|
|
runAsUser: 999
|
|
container:
|
|
rabbitmq_password:
|
|
runAsUser: 0
|
|
readOnlyRootFilesystem: true
|
|
rabbitmq_cookie:
|
|
runAsUser: 0
|
|
readOnlyRootFilesystem: true
|
|
rabbitmq_perms:
|
|
runAsUser: 0
|
|
readOnlyRootFilesystem: true
|
|
rabbitmq:
|
|
allowPrivilegeEscalation: false
|
|
runAsUser: 999
|
|
readOnlyRootFilesystem: false
|
|
cluster_wait:
|
|
pod:
|
|
runAsUser: 999
|
|
container:
|
|
rabbitmq_cluster_wait:
|
|
allowPrivilegeEscalation: false
|
|
readOnlyRootFilesystem: true
|
|
rabbitmq_cookie:
|
|
allowPrivilegeEscalation: false
|
|
readOnlyRootFilesystem: true
|
|
test:
|
|
pod:
|
|
runAsUser: 999
|
|
container:
|
|
rabbitmq_test:
|
|
allowPrivilegeEscalation: false
|
|
readOnlyRootFilesystem: true
|
|
affinity:
|
|
anti:
|
|
type:
|
|
default: preferredDuringSchedulingIgnoredDuringExecution
|
|
topologyKey:
|
|
default: kubernetes.io/hostname
|
|
weight:
|
|
default: 10
|
|
replicas:
|
|
server: 2
|
|
prometheus_rabbitmq_exporter: 1
|
|
lifecycle:
|
|
upgrades:
|
|
deployments:
|
|
revision_history: 3
|
|
pod_replacement_strategy: RollingUpdate
|
|
rolling_update:
|
|
max_unavailable: 1
|
|
max_surge: 3
|
|
termination_grace_period:
|
|
prometheus_rabbitmq_exporter:
|
|
timeout: 30
|
|
disruption_budget:
|
|
mariadb:
|
|
min_available: 0
|
|
resources:
|
|
enabled: false
|
|
prometheus_rabbitmq_exporter:
|
|
limits:
|
|
memory: "1024Mi"
|
|
cpu: "2000m"
|
|
requests:
|
|
memory: "128Mi"
|
|
cpu: "500m"
|
|
server:
|
|
limits:
|
|
memory: "128Mi"
|
|
cpu: "500m"
|
|
requests:
|
|
memory: "128Mi"
|
|
cpu: "500m"
|
|
jobs:
|
|
tests:
|
|
limits:
|
|
memory: "1024Mi"
|
|
cpu: "2000m"
|
|
requests:
|
|
memory: "128Mi"
|
|
cpu: "100m"
|
|
image_repo_sync:
|
|
requests:
|
|
memory: "128Mi"
|
|
cpu: "100m"
|
|
limits:
|
|
memory: "1024Mi"
|
|
cpu: "2000m"
|
|
|
|
conf:
|
|
enabled_plugins:
|
|
- rabbitmq_management
|
|
- rabbitmq_peer_discovery_k8s
|
|
prometheus_exporter:
|
|
capabilities:
|
|
- no_sort
|
|
log_level: info
|
|
skipverify: 1
|
|
skip_queues: "^$"
|
|
include_queues: ".*"
|
|
rabbit_exporters: "overview,exchange,node,queue"
|
|
rabbitmq:
|
|
listeners:
|
|
tcp:
|
|
# NOTE(portdirect): This is always defined via the endpoints section.
|
|
1: null
|
|
cluster_formation:
|
|
peer_discovery_backend: rabbit_peer_discovery_k8s
|
|
k8s:
|
|
address_type: hostname
|
|
node_cleanup:
|
|
interval: "10"
|
|
only_log_warning: "true"
|
|
cluster_partition_handling: autoheal
|
|
queue_master_locator: min-masters
|
|
loopback_users.guest: "false"
|
|
management.load_definitions: "/var/lib/rabbitmq/definitions.json"
|
|
rabbit_additonal_conf:
|
|
# This confinguration is used for non TLS deployments
|
|
management.listener.ip: "::"
|
|
management.listener.port: null
|
|
rabbitmq_exporter:
|
|
rabbit_timeout: 30
|
|
# Feature Flags is introduced in RabbitMQ 3.8.0
|
|
# To deploy with standard list of feature, leave as default
|
|
# To deploy with specific feature, separate each feature with comma
|
|
# To deploy with all features disabled, leave blank or empty
|
|
feature_flags: default
|
|
dependencies:
|
|
dynamic:
|
|
common:
|
|
local_image_registry:
|
|
jobs:
|
|
- rabbitmq-image-repo-sync
|
|
services:
|
|
- endpoint: node
|
|
service: local_image_registry
|
|
static:
|
|
prometheus_rabbitmq_exporter:
|
|
services:
|
|
- endpoint: internal
|
|
service: oslo_messaging
|
|
prometheus_rabbitmq_exporter_tests:
|
|
services:
|
|
- endpoint: internal
|
|
service: prometheus_rabbitmq_exporter
|
|
- endpoint: internal
|
|
service: monitoring
|
|
rabbitmq:
|
|
jobs: null
|
|
tests:
|
|
services:
|
|
- endpoint: internal
|
|
service: oslo_messaging
|
|
# NOTE (portdirect): this key is somewhat special, if set to the string
|
|
# `cluster_wait` then the job dep will be populated with a single value
|
|
# containing the generated name for the `cluster_wait` job name.
|
|
jobs: cluster_wait
|
|
cluster_wait:
|
|
services:
|
|
- endpoint: internal
|
|
service: oslo_messaging
|
|
image_repo_sync:
|
|
services:
|
|
- endpoint: internal
|
|
service: local_image_registry
|
|
|
|
monitoring:
|
|
prometheus:
|
|
enabled: false
|
|
rabbitmq_exporter:
|
|
scrape: true
|
|
|
|
network:
|
|
management:
|
|
ingress:
|
|
public: true
|
|
classes:
|
|
namespace: "nginx"
|
|
cluster: "nginx-cluster"
|
|
annotations:
|
|
nginx.ingress.kubernetes.io/rewrite-target: /
|
|
|
|
secrets:
|
|
tls:
|
|
oslo_messaging:
|
|
server:
|
|
internal: rabbitmq-tls-direct
|
|
|
|
# typically overridden by environmental
|
|
# values, but should include all endpoints
|
|
# required by this chart
|
|
endpoints:
|
|
cluster_domain_suffix: cluster.local
|
|
local_image_registry:
|
|
name: docker-registry
|
|
namespace: docker-registry
|
|
hosts:
|
|
default: localhost
|
|
internal: docker-registry
|
|
node: localhost
|
|
host_fqdn_override:
|
|
default: null
|
|
port:
|
|
registry:
|
|
node: 5000
|
|
monitoring:
|
|
name: prometheus
|
|
namespace: null
|
|
hosts:
|
|
default: prom-metrics
|
|
public: prometheus
|
|
host_fqdn_override:
|
|
default: null
|
|
path:
|
|
default: null
|
|
scheme:
|
|
default: 'http'
|
|
port:
|
|
api:
|
|
default: 9090
|
|
public: 80
|
|
oslo_messaging:
|
|
auth:
|
|
erlang_cookie: openstack-cookie
|
|
user:
|
|
username: rabbitmq
|
|
password: password
|
|
hosts:
|
|
default: rabbitmq
|
|
# NOTE(portdirect): the public host is only used to the management WUI
|
|
# If left empty, the release name sha suffixed with mgr, will be used to
|
|
# produce an unique hostname.
|
|
public: null
|
|
host_fqdn_override:
|
|
default: null
|
|
path: /
|
|
scheme: rabbit
|
|
port:
|
|
clustering:
|
|
# NOTE(portdirect): the value for this port is driven by amqp+20000
|
|
# it should not be set manually.
|
|
default: null
|
|
amqp:
|
|
default: 5672
|
|
http:
|
|
default: 15672
|
|
public: 80
|
|
prometheus_rabbitmq_exporter:
|
|
namespace: null
|
|
hosts:
|
|
default: rabbitmq-exporter
|
|
host_fqdn_override:
|
|
default: null
|
|
path:
|
|
default: /metrics
|
|
scheme:
|
|
default: 'http'
|
|
port:
|
|
metrics:
|
|
default: 9095
|
|
kube_dns:
|
|
namespace: kube-system
|
|
name: kubernetes-dns
|
|
hosts:
|
|
default: kube-dns
|
|
host_fqdn_override:
|
|
default: null
|
|
path:
|
|
default: null
|
|
scheme: http
|
|
port:
|
|
dns_tcp:
|
|
default: 53
|
|
dns:
|
|
default: 53
|
|
protocol: UDP
|
|
|
|
network_policy:
|
|
prometheus_rabbitmq_exporter:
|
|
ingress:
|
|
- {}
|
|
egress:
|
|
- {}
|
|
rabbitmq:
|
|
ingress:
|
|
- {}
|
|
egress:
|
|
- {}
|
|
|
|
volume:
|
|
use_local_path:
|
|
enabled: false
|
|
host_path: /var/lib/rabbitmq
|
|
chown_on_start: true
|
|
enabled: true
|
|
class_name: general
|
|
size: 256Mi
|
|
|
|
# Hook break for helm2.
|
|
# Set helm3_hook to false while using helm2
|
|
helm3_hook: true
|
|
|
|
manifests:
|
|
certificates: false
|
|
configmap_bin: true
|
|
configmap_etc: true
|
|
config_ipv6: false
|
|
ingress_management: true
|
|
job_cluster_wait: true
|
|
job_image_repo_sync: true
|
|
monitoring:
|
|
prometheus:
|
|
configmap_bin: true
|
|
deployment_exporter: true
|
|
service_exporter: true
|
|
network_policy_exporter: false
|
|
network_policy: false
|
|
pod_test: true
|
|
secret_admin_user: true
|
|
secret_erlang_cookie: true
|
|
service_discovery: true
|
|
service_ingress_management: true
|
|
service: true
|
|
statefulset: true
|
|
...
|