openstack/openstack-helm-infra
Code Issues Proposed changes
openstack-helm-infra/nagios/values.yaml
Steve Wilkerson 99befc2484 Nagios Chart 
This adds the nagios chart to osh-infra to provide additional
monitoring functionality. It uses helper functions to consume
yaml definitions for services, commands, hosts and hostgroups
to generate the required configurations for those entities in
nagios's configuration

Change-Id: I6238bb8cb1e5c8dc48594ddea50693f3e7b0a176
2018-03-23 13:45:40 +00:00

283 lines
8.4 KiB
YAML
Raw Blame History

# Copyright 2017 The Openstack-Helm Authors.
#
# 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 nagios.
# This is a YAML-formatted file.
# Declare variables to be passed into your templates.
images:
tags:
nagios: docker.io/srwilkers/prometheus-nagios:v0.1.0
dep_check: quay.io/stackanetes/kubernetes-entrypoint:v0.2.1
image_repo_sync: docker.io/docker:17.07.0
pull_policy: IfNotPresent
local_registry:
active: false
exclude:
- dep_check
- image_repo_sync
labels:
node_selector_key: openstack-control-plane
node_selector_value: enabled
dependencies:
dynamic:
common:
jobs:
- nagios-image-repo-sync
services:
- service: local_image_registry
endpoint: node
static:
image_repo_sync:
services:
- service: local_image_registry
endpoint: internal
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
hosts:
default: prom-metrics
public: prometheus
host_fqdn_override:
default: null
path:
default: null
scheme:
default: http
port:
api:
default: 9090
public: 80
nagios:
name: nagios
namespace: null
hosts:
default: nagios-metrics
public: nagios
host_fqdn_override:
default: null
path:
default: null
scheme:
default: http
port:
nagios:
default: 25
network:
nagios:
ingress:
public: true
proxy_body_size: 1024M
node_port:
enabled: false
port: 30925
port: 25
pod:
lifecycle:
upgrades:
revision_history: 3
pod_replacement_strategy: RollingUpdate
rolling_update:
max_unavailable: 1
max_surge: 3
termination_grace_period:
nagios:
timeout: 30
replicas:
nagios: 3
resources:
enabled: false
nagios:
limits:
memory: "1024Mi"
cpu: "2000m"
requests:
memory: "128Mi"
cpu: "100m"
jobs:
image_repo_sync:
limits:
memory: "1024Mi"
cpu: "2000m"
requests:
memory: "128Mi"
cpu: "100m"
manifests:
configmap_bin: true
configmap_etc: true
deployment: true
job_image_repo_sync: true
service: true
conf:
nagios:
hosts:
- prometheus:
use: linux-server
host_name: prometheus
alias: "Prometheus Monitoring"
address: $PROMETHEUS_SERVICE
hostgroups: monitoring
host_groups:
- monitoring:
hostgroup_name: monitoring
alias: "Monitoring Instances"
members: prometheus
commands:
- check_prometheus:
command_name: check_prometheus
command_line: "$USER1$/check_prometheus_metric.sh -H $HOSTADDRESS$ -q '$ARG1$' -w $ARG2$ -c $ARG3$ -n $ARG4$ -m $ARG5$"
- check_prometheus_nan_ok:
command_name: check_prometheus_nan_ok
command_line: "$USER1$/check_prometheus_metric.sh -H $HOSTADDRESS$ -q '$ARG1$' -w $ARG2$ -c $ARG3$ -n $ARG4$ -m $ARG5$ -O"
- check_prometheus_extra_info:
command_name: check_prometheus_extra_info
command_line: "$USER1$/check_prometheus_metric.sh -H $HOSTADDRESS$ -q '$ARG1$' -w $ARG2$ -c $ARG3$ -n $ARG4$ -m $ARG5$ -i -t vector"
services:
- check_prometheus_replicas:
use: generic-service
host_name: prometheus
service_description: "Check Prometheus replicas"
check_command: check_prometheus_extra_info!kube_statefulset_status_replicas{namespace="openstack",statefulset="prometheus"}!3!2!prometheus_replicas!lt
check_interval: 1
- check_alertmanager_replicas:
use: generic-service
host_name: prometheus
service_description: "Check Alertmanager replicas"
check_command: check_prometheus_extra_info!kube_statefulset_status_replicas{namespace="openstack",statefulset="alertmanager"}!3!2!alertmanager_replicas!lt
check_interval: 1
config:
log_file: /opt/nagios/var/nagios.log
cfg_file:
- /opt/nagios/etc/nagios_objects.cfg
- /opt/nagios/etc/objects/commands.cfg
- /opt/nagios/etc/objects/contacts.cfg
- /opt/nagios/etc/objects/timeperiods.cfg
- /opt/nagios/etc/objects/templates.cfg
object_cache_file: /opt/nagios/var/objects.cache
precached_object_file: /opt/nagios/var/objects.precache
resource_file: /opt/nagios/etc/resource.cfg
status_file: /opt/nagios/var/status.dat
status_update_interval: 10
nagios_user: nagios
nagios_group: nagios
check_external_commands: 1
command_file: /opt/nagios/var/rw/nagios.cmd
lock_file: /opt/nagios/var/nagios.lock
temp_file: /opt/nagios/var/nagios.tmp
temp_path: /tmp
event_broker_options: -1
log_rotation_method: d
log_archive_path: /opt/nagios/var/archives
use_syslog: 1
log_service_retries: 1
log_host_retries: 1
log_event_handlers: 1
log_initial_states: 0
log_current_states: 1
log_external_commands: 1
log_passive_checks: 1
service_inter_check_delay_method: s
max_service_check_spread: 30
service_interleave_factor: s
host_inter_check_delay_method: s
max_host_check_spread: 30
max_concurrent_checks: 0
check_result_reaper_frequency: 10
max_check_result_reaper_time: 30
check_result_path: /opt/nagios/var/spool/checkresults
max_check_result_file_age: 3600
cached_host_check_horizon: 15
cached_service_check_horizon: 15
enable_predictive_host_dependency_checks: 1
enable_predictive_service_dependency_checks: 1
soft_state_dependencies: 0
auto_reschedule_checks: 0
auto_rescheduling_interval: 30
auto_rescheduling_window: 180
service_check_timeout: 60
host_check_timeout: 30
event_handler_timeout: 30
notification_timeout: 30
ocsp_timeout: 5
perfdata_timeout: 5
retain_state_information: 1
state_retention_file: /opt/nagios/var/retention.dat
retention_update_interval: 60
use_retained_program_state: 1
use_retained_scheduling_info: 1
retained_host_attribute_mask: 0
retained_service_attribute_mask: 0
retained_process_host_attribute_mask: 0
retained_process_service_attribute_mask: 0
retained_contact_host_attribute_mask: 0
retained_contact_service_attribute_mask: 0
interval_length: 60
check_for_updates: 1
bare_update_check: 0
use_aggressive_host_checking: 0
execute_service_checks: 1
accept_passive_service_checks: 1
execute_host_checks: 1
accept_passive_host_checks: 1
enable_notifications: 1
enable_event_handlers: 1
process_performance_data: 0
obsess_over_services: 0
obsess_over_hosts: 0
translate_passive_host_checks: 0
passive_host_checks_are_soft: 0
check_for_orphaned_services: 1
check_for_orphaned_hosts: 1
check_service_freshness: 1
service_freshness_check_interval: 60
check_host_freshness: 0
host_freshness_check_interval: 60
additional_freshness_latency: 15
enable_flap_detection: 1
low_service_flap_threshold: 5.0
high_service_flap_threshold: 20.0
low_host_flap_threshold: 5.0
high_host_flap_threshold: 20.0
date_format: us
use_regexp_matching: 0
use_true_regexp_matching: 0
daemon_dumps_core: 0
use_large_installation_tweaks: 0
enable_environment_macros: 0
debug_level: 0
debug_verbosity: 1
debug_file: /opt/nagios/var/nagios.debug
max_debug_file_size: 1000000
allow_empty_hostgroup_assignment: 0
View Git Blame Copy Permalink