forked from openstack/openstack-helm-infra
-
Notifications
You must be signed in to change notification settings - Fork 0
/
values.yaml
1170 lines (1055 loc) · 45.3 KB
/
values.yaml
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
# 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:https://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:
apache_proxy: docker.io/httpd:2.4
nagios: docker.io/openstackhelm/nagios:ubuntu_xenial-20191113
dep_check: quay.io/stackanetes/kubernetes-entrypoint:v0.2.1
selenium_tests: docker.io/openstackhelm/osh-selenium:ubuntu_bionic-20191017
image_repo_sync: docker.io/docker:17.07.0
pull_policy: IfNotPresent
local_registry:
active: false
exclude:
- dep_check
- image_repo_sync
labels:
nagios:
node_selector_key: openstack-control-plane
node_selector_value: enabled
job:
node_selector_key: openstack-control-plane
node_selector_value: enabled
test:
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
nagios:
services: null
tests:
services:
- service: nagios
endpoint: internal
secrets:
nagios:
admin: nagios-admin-creds
tls:
nagios:
nagios:
public: nagios-tls-public
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
auth:
admin:
username: admin
password: changeme
hosts:
default: prom-metrics
public: prometheus
host_fqdn_override:
default: null
path:
default: null
scheme:
default: http
port:
http:
default: 80
nagios:
name: nagios
namespace: null
auth:
admin:
username: nagiosadmin
password: password
hosts:
default: nagios-metrics
public: nagios
host_fqdn_override:
default: null
# NOTE(srwilkers): this chart supports TLS for fqdn over-ridden public
# endpoints using the following format:
# public:
# host: null
# tls:
# crt: null
# key: null
path:
default: null
scheme:
default: http
port:
nagios:
default: 8000
http:
default: 80
ldap:
hosts:
default: ldap
auth:
admin:
bind: "cn=admin,dc=cluster,dc=local"
password: password
host_fqdn_override:
default: null
path:
default: "/ou=People,dc=cluster,dc=local"
scheme:
default: ldap
port:
ldap:
default: 389
elasticsearch:
name: elasticsearch
namespace: null
auth:
admin:
username: admin
password: changeme
hosts:
default: elasticsearch-logging
host_fqdn_override:
default: null
path:
default: /
scheme:
default: http
port:
http:
default: 80
ceph_mgr:
namespace: null
hosts:
default: ceph-mgr
host_fqdn_override:
default: null
port:
mgr:
default: 7000
metrics:
default: 9283
scheme:
default: http
network:
nagios:
ingress:
public: true
classes:
namespace: "nginx"
cluster: "nginx-cluster"
annotations:
nginx.ingress.kubernetes.io/rewrite-target: /
nginx.ingress.kubernetes.io/affinity: cookie
nginx.ingress.kubernetes.io/session-cookie-name: kube-ingress-session-nagios
nginx.ingress.kubernetes.io/session-cookie-hash: sha1
nginx.ingress.kubernetes.io/session-cookie-expires: "600"
nginx.ingress.kubernetes.io/session-cookie-max-age: "600"
nginx.ingress.kubernetes.io/configuration-snippet: |
more_set_headers "X-Content-Type-Options: 'nosniff'";
more_set_headers "X-Frame-Options: SAMEORIGIN";
more_set_headers "Content-Security-Policy: script-src 'self'";
more_set_headers "X-XSS-Protection: 1; mode=block";
node_port:
enabled: false
port: 30925
network_policy:
nagios:
ingress:
- {}
egress:
- {}
pod:
security_context:
monitoring:
pod:
runAsUser: 0
container:
apache_proxy:
readOnlyRootFilesystem: false
nagios:
readOnlyRootFilesystem: false
helm_tests:
readOnlyRootFilesystem: false
affinity:
anti:
type:
default: preferredDuringSchedulingIgnoredDuringExecution
topologyKey:
default: kubernetes.io/hostname
weight:
default: 10
lifecycle:
upgrades:
deployments:
revision_history: 3
pod_replacement_strategy: RollingUpdate
rolling_update:
max_unavailable: 1
max_surge: 3
termination_grace_period:
nagios:
timeout: 30
replicas:
nagios: 1
resources:
enabled: false
nagios:
limits:
memory: "1024Mi"
cpu: "2000m"
requests:
memory: "128Mi"
cpu: "100m"
apache_proxy:
limits:
memory: "1024Mi"
cpu: "2000m"
requests:
memory: "128Mi"
cpu: "100m"
jobs:
image_repo_sync:
limits:
memory: "1024Mi"
cpu: "2000m"
requests:
memory: "128Mi"
cpu: "100m"
tests:
limits:
memory: "1024Mi"
cpu: "2000m"
requests:
memory: "128Mi"
cpu: "100m"
manifests:
configmap_bin: true
configmap_etc: true
deployment: true
ingress: true
job_image_repo_sync: true
network_policy: false
pod_helm_test: true
secret_nagios: true
secret_ingress_tls: true
service: true
service_ingress: true
conf:
httpd: |
ServerRoot "/usr/local/apache2"
Listen 80
LoadModule mpm_event_module modules/mod_mpm_event.so
LoadModule authn_file_module modules/mod_authn_file.so
LoadModule authn_core_module modules/mod_authn_core.so
LoadModule authz_host_module modules/mod_authz_host.so
LoadModule authz_groupfile_module modules/mod_authz_groupfile.so
LoadModule authz_user_module modules/mod_authz_user.so
LoadModule authz_core_module modules/mod_authz_core.so
LoadModule access_compat_module modules/mod_access_compat.so
LoadModule auth_basic_module modules/mod_auth_basic.so
LoadModule ldap_module modules/mod_ldap.so
LoadModule authnz_ldap_module modules/mod_authnz_ldap.so
LoadModule reqtimeout_module modules/mod_reqtimeout.so
LoadModule filter_module modules/mod_filter.so
LoadModule proxy_html_module modules/mod_proxy_html.so
LoadModule log_config_module modules/mod_log_config.so
LoadModule env_module modules/mod_env.so
LoadModule headers_module modules/mod_headers.so
LoadModule setenvif_module modules/mod_setenvif.so
LoadModule version_module modules/mod_version.so
LoadModule proxy_module modules/mod_proxy.so
LoadModule proxy_connect_module modules/mod_proxy_connect.so
LoadModule proxy_http_module modules/mod_proxy_http.so
LoadModule proxy_balancer_module modules/mod_proxy_balancer.so
LoadModule slotmem_shm_module modules/mod_slotmem_shm.so
LoadModule slotmem_plain_module modules/mod_slotmem_plain.so
LoadModule unixd_module modules/mod_unixd.so
LoadModule status_module modules/mod_status.so
LoadModule autoindex_module modules/mod_autoindex.so
<IfModule unixd_module>
User daemon
Group daemon
</IfModule>
<Directory />
AllowOverride none
Require all denied
</Directory>
<Files ".ht*">
Require all denied
</Files>
ErrorLog /dev/stderr
LogLevel warn
<IfModule log_config_module>
LogFormat "%a %l %u %t \"%r\" %>s %b \"%{Referer}i\" \"%{User-Agent}i\"" combined
LogFormat "%{X-Forwarded-For}i %l %u %t \"%r\" %>s %b \"%{Referer}i\" \"%{User-Agent}i\"" proxy
LogFormat "%h %l %u %t \"%r\" %>s %b" common
<IfModule logio_module>
LogFormat "%a %l %u %t \"%r\" %>s %b \"%{Referer}i\" \"%{User-Agent}i\" %I %O" combinedio
</IfModule>
SetEnvIf X-Forwarded-For "^.*\..*\..*\..*" forwarded
CustomLog /dev/stdout common
CustomLog /dev/stdout combined
CustomLog /dev/stdout proxy env=forwarded
</IfModule>
<Directory "/usr/local/apache2/cgi-bin">
AllowOverride None
Options None
Require all granted
</Directory>
<IfModule headers_module>
RequestHeader unset Proxy early
</IfModule>
<IfModule proxy_html_module>
Include conf/extra/proxy-html.conf
</IfModule>
<VirtualHost *:80>
<Location />
ProxyPass http:https://localhost:{{ tuple "nagios" "internal" "nagios" . | include "helm-toolkit.endpoints.endpoint_port_lookup" }}/
ProxyPassReverse http:https://localhost:{{ tuple "nagios" "internal" "nagios" . | include "helm-toolkit.endpoints.endpoint_port_lookup" }}/
</Location>
<Proxy *>
AuthName "Nagios"
AuthType Basic
AuthBasicProvider file ldap
AuthUserFile /usr/local/apache2/conf/.htpasswd
AuthLDAPBindDN {{ .Values.endpoints.ldap.auth.admin.bind }}
AuthLDAPBindPassword {{ .Values.endpoints.ldap.auth.admin.password }}
AuthLDAPURL {{ tuple "ldap" "default" "ldap" . | include "helm-toolkit.endpoints.keystone_endpoint_uri_lookup" | quote }}
Require valid-user
</Proxy>
</VirtualHost>
nagios:
notification:
snmp:
primary_target: 127.0.0.1:15162
secondary_target: 127.0.0.1:15162
http:
primary_target: 127.0.0.1:3904/events
secondary_target: 127.0.0.1:3904/events
objects:
base:
template: |
define host {
address 127.0.0.1
alias Prometheus Monitoring
check_command check-prometheus-host-alive
host_name {{ tuple "monitoring" "public" . | include "helm-toolkit.endpoints.hostname_short_endpoint_lookup" }}
hostgroups prometheus-hosts
use linux-server
}
define contact {
alias notifying contact
contact_name notifying_contact
host_notification_options d,u,r,f,s
host_notification_period 24x7
name notifying_contact
register 0
service_notification_options w,u,c,r,f,s
service_notification_period 24x7
}
define contact {
alias snmp contact
contact_name snmp_notifying_contact
host_notification_commands send_host_snmp_trap
name snmp_notifying_contact
service_notification_commands send_service_snmp_trap
use notifying_contact
}
define contact {
alias HTTP contact
contact_name http_notifying_contact
host_notification_commands send_host_http_post
name http_notifying_contact
service_notification_commands send_service_http_post
use notifying_contact
}
define contactgroup {
alias SNMP and HTTP notifying group
contactgroup_name snmp_and_http_notifying_contact_group
members snmp_notifying_contact,http_notifying_contact
}
define hostgroup {
alias Prometheus Virtual Host
hostgroup_name prometheus-hosts
}
define hostgroup {
alias all
hostgroup_name all
}
define hostgroup {
alias base-os
hostgroup_name base-os
}
define command {
command_line $USER1$/send_service_trap.sh '$USER8$' '$HOSTNAME$' '$SERVICEDESC$' $SERVICESTATEID$ '$SERVICEOUTPUT$' '$USER4$' '$USER5$'
command_name send_service_snmp_trap
}
define command {
command_line $USER1$/send_host_trap.sh '$USER8$' '$HOSTNAME$' $HOSTSTATEID$ '$HOSTOUTPUT$' '$USER4$' '$USER5$'
command_name send_host_snmp_trap
}
define command {
command_line $USER1$/send_http_post_event.py --type service --hostname '$HOSTNAME$' --servicedesc '$SERVICEDESC$' --state_id $SERVICESTATEID$ --output '$SERVICEOUTPUT$' --monitoring_hostname '$HOSTNAME$' --primary_url '$USER6$' --secondary_url '$USER7$'
command_name send_service_http_post
}
define command {
command_line $USER1$/send_http_post_event.py --type host --hostname '$HOSTNAME$' --state_id $HOSTSTATEID$ --output '$HOSTOUTPUT$' --monitoring_hostname '$HOSTNAME$' --primary_url '$USER6$' --secondary_url '$USER7$'
command_name send_host_http_post
}
define command {
command_line $USER1$/check_rest_get_api.py --url $USER2$ --warning_response_seconds 5 --critical_response_seconds 10
command_name check-prometheus-host-alive
}
define command {
command_line $USER1$/query_prometheus_alerts.py --prometheus_api $USER2$ --alertname '$ARG1$' --labels_csv '$ARG2$' --msg_format '$ARG3$' --ok_message '$ARG4$'
command_name check_prom_alert_with_labels
}
define command {
command_line $USER1$/query_prometheus_alerts.py --prometheus_api $USER2$ --alertname '$ARG1$' --msg_format '$ARG2$' --ok_message '$ARG3$'
command_name check_prom_alert
}
define service {
check_interval 60
contact_groups snmp_and_http_notifying_contact_group
flap_detection_enabled 0
name notifying_service
notification_interval 120
process_perf_data 0
register 0
retry_interval 30
use generic-service
}
kubernetes:
template: |
define service {
check_command check_prom_alert!prom_exporter_calico_unavailable!CRITICAL- Calico exporter is not collecting metrics for alerting!OK- Calico exporter metrics are available.
hostgroup_name prometheus-hosts
service_description Prometheus-exporter_Calico
use generic-service
}
define service {
check_command check_prom_alert!prom_exporter_kube_state_metrics_unavailable!CRITICAL- kube-state-metrics exporter is not collecting metrics for alerting!OK- kube-state-metrics exporter metrics are available.
hostgroup_name prometheus-hosts
service_description Prometheus-exporter_Kube-state-metrics
use generic-service
}
define service {
check_command check_prom_alert!K8SNodesNotReady!CRITICAL- One or more nodes are not ready.
check_interval 60
hostgroup_name prometheus-hosts
service_description Nodes_health
use generic-service
}
define service {
check_command check_prom_alert_with_labels!kube_statefulset_replicas_unavailable!statefulset="prometheus"!statefulset {statefulset} has lesser than configured replicas
check_interval 60
hostgroup_name prometheus-hosts
service_description Prometheus_replica-count
use notifying_service
}
define service {
check_command check_prom_alert_with_labels!kube_statefulset_replicas_unavailable!statefulset="alertmanager"!statefulset {statefulset} has lesser than configured replicas
check_interval 60
hostgroup_name prometheus-hosts
service_description PrometheusAlertmanager_replica-count
use notifying_service
}
define service {
check_command check_prom_alert!kube_statefulset_replicas_unavailable!CRITICAL- statefulset {statefulset} has lesser than configured replicas!OK- All statefulsets have configured amount of replicas
check_interval 60
hostgroup_name prometheus-hosts
service_description Statefulset_replica-count
use notifying_service
}
define service {
check_command check_prom_alert!daemonsets_misscheduled!CRITICAL- Daemonset {daemonset} is incorrectly scheudled!OK- No daemonset misscheduling detected
check_interval 60
hostgroup_name prometheus-hosts
service_description Daemonset_misscheduled
use notifying_service
}
define service {
check_command check_prom_alert!daemonsets_not_scheduled!CRITICAL- Daemonset {daemonset} is missing to be scheduled in some nodes!OK- All daemonset scheduling is as desired
check_interval 60
hostgroup_name prometheus-hosts
service_description Daemonset_not-scheduled
use notifying_service
}
define service {
check_command check_prom_alert!daemonset_pods_unavailable!CRITICAL- Daemonset {daemonset} has pods unavailable!OK- All daemonset pods available
check_interval 60
hostgroup_name prometheus-hosts
service_description Daemonset_pods-unavailable
use notifying_service
}
define service {
check_command check_prom_alert!deployment_replicas_unavailable!CRITICAL- Deployment {deployment} has less than desired replicas!OK- All deployments have desired replicas
check_interval 60
hostgroup_name prometheus-hosts
service_description Deployment_replicas-unavailable
use notifying_service
}
define service {
check_command check_prom_alert!volume_claim_capacity_high_utilization!CRITICAL- Volume claim {persistentvolumeclaim} has exceed 80% utilization!OK- All volume claims less than 80% utilization
check_interval 60
hostgroup_name prometheus-hosts
service_description Volume_claim_high_utilization
use notifying_service
}
define service {
check_command check_prom_alert!rollingupdate_deployment_replica_less_than_spec_max_unavailable!CRITICAL- Deployment {deployment} has less than desired replicas during a rolling update!OK- All deployments have desired replicas
check_interval 60
hostgroup_name prometheus-hosts
service_description RollingUpdate_Deployment-replicas-unavailable
use notifying_service
}
define service {
check_command check_prom_alert!job_status_failed!CRITICAL- Job {exported_job} has failed!OK- No Job failures
check_interval 60
hostgroup_name prometheus-hosts
service_description Job_status-failed
use notifying_service
}
define service {
check_command check_prom_alert!pod_status_pending!CRITICAL- Pod {pod} in namespace {namespace} has been in pending status for more than 10 minutes!OK- No pods in pending status
check_interval 60
hostgroup_name prometheus-hosts
service_description Pod_status-pending
use notifying_service
}
define service {
check_command check_prom_alert!pod_status_error_image_pull!CRITICAL- Pod {pod} in namespace {namespace} has been in errpr status of ErrImagePull for more than 10 minutes!OK- No pods in error status
check_interval 60
hostgroup_name prometheus-hosts
service_description Pod_status-error-image-pull
use notifying_service
}
define service {
check_command check_prom_alert! pod_status_error_image_pull_backoff!CRITICAL- Pod {pod} in namespace {namespace} has been in errpr status of ImagePullBackOff for more than 10 minutes!OK- No pods in error status
check_interval 60
hostgroup_name prometheus-hosts
service_description Pod_status-error-image-pull
use notifying_service
}
define service {
check_command check_prom_alert! pod_error_config_error!CRITICAL- Pod {pod} in namespace {namespace} has been in errpr status of CreateContainerConfigError for more than 10 minutes!OK- No pods in error status
check_interval 60
hostgroup_name prometheus-hosts
service_description Pod_status-error-image-pull
use notifying_service
}
define service {
check_command check_prom_alert!pod_error_crash_loop_back_off!CRITICAL- Pod {pod} in namespace {namespace} has been in error status of CrashLoopBackOff for more than 10 minutes!OK- No pods in crashLoopBackOff status
check_interval 60
hostgroup_name prometheus-hosts
service_description Pod_status-crashLoopBackOff
use notifying_service
}
define service {
check_command check_prom_alert!replicaset_missing_replicas!CRITICAL- Replicaset {replicaset} is missing replicas!OK- No replicas missing from replicaset
check_interval 60
hostgroup_name prometheus-hosts
service_description Replicaset_missing-replicas
use notifying_service
}
define service {
check_command check_prom_alert!pod_container_terminated!CRITICAL- pod {pod} in namespace {namespace} has a container in terminated state!OK- pod container status looks good
check_interval 60
hostgroup_name prometheus-hosts
service_description Pod_status-container-terminated
use notifying_service
}
define service {
check_command check_prom_alert_with_labels!etcd_HighNumberOfFailedHTTPRequests!method="DELETE"!CRITICAL- ETCD {instance} has a high HTTP DELETE operations failure!OK- ETCD at {instance} has low or no failures for HTTP DELETE
check_interval 60
hostgroup_name prometheus-hosts
service_description ETCD_high-http-delete-failures
use notifying_service
}
define service {
check_command check_prom_alert_with_labels!etcd_HighNumberOfFailedHTTPRequests!method=~"GET|QGET"!CRITICAL- ETCD {instance} has a high HTTP GET operations failure!OK- ETCD at {instance} has low or no failures for HTTP GET
check_interval 60
hostgroup_name prometheus-hosts
service_description ETCD_high-http-get-failures
use notifying_service
}
define service {
check_command check_prom_alert_with_labels!etcd_HighNumberOfFailedHTTPRequests!method="PUT"!CRITICAL- ETCD {instance} has a high HTTP PUT operations failure!OK- ETCD at {instance} has low or no failures for HTTP PUT
check_interval 60
hostgroup_name prometheus-hosts
service_description ETCD_high-http-update-failures
use notifying_service
}
define service {
check_command check_prom_alert!calico_iptable_save_errors_high_1h!CRITICAL- Felix instance {instance} has seen high iptable save errors within the last hour!OK- iptables save errors are none or low
hostgroup_name prometheus-hosts
service_description Calico_iptables-save-errors
use notifying_service
}
define service {
check_command check_prom_alert!calico_ipset_errors_high_1h!CRITICAL- Felix instance {instance} has seen high ipset errors within the last hour!OK- ipset errors are none or low
hostgroup_name prometheus-hosts
service_description Calico_ipset-errors
use notifying_service
}
define service {
check_command check_prom_alert!calico_datapane_iface_msg_batch_size_high_5m!CRITICAL- Felix instance {instance} has seen a high value of dataplane interface message batch size!OK- dataplane interface message batch size are low
hostgroup_name prometheus-hosts
service_description Calico_interface-message-batch-size
use notifying_service
}
define service {
check_command check_prom_alert!calico_datapane_address_msg_batch_size_high_5m!CRITICAL- Felix instance {instance} has seen a high value of dataplane address message batch size!OK- dataplane address message batch size are low
hostgroup_name prometheus-hosts
service_description Calico_address-message-batch-size
use notifying_service
}
define service {
check_command check_prom_alert!calico_datapane_failures_high_1h!CRITICAL- Felix instance {instance} has seen high dataplane failures within the last hour!OK- datapane failures are none or low
hostgroup_name prometheus-hosts
service_description Calico_datapane_failures_high
use notifying_service
}
node:
template: |
define service {
check_command check_prom_alert!prom_exporter_node_unavailable!CRITICAL- Node exporter is not collecting metrics for alerting!OK- Node exporter metrics are available.
hostgroup_name prometheus-hosts
service_description Prometheus-exporter_Node
use generic-service
}
define command {
command_line $USER1$/query_prometheus_alerts.py --prometheus_api $USER2$ --alertname 'node_filesystem_full_in_4h' --labels_csv 'instance=~"$HOSTADDRESS$.*"' --msg_format 'CRITICAL- Mountpoint {mountpoint} will be full in four hours' --ok_message 'OK- All mountpoints usage rate is normal'
command_name check_filespace_mounts-usage-rate-fullin4hrs
}
define command {
command_line $USER1$/query_prometheus_alerts.py --prometheus_api $USER2$ --alertname 'node_filesystem_full_80percent' --labels_csv 'instance=~"$HOSTADDRESS$.*"' --msg_format 'CRITICAL- Mountpoint {mountpoint} is more than 80 pecent full' --ok_message 'OK- All mountpoints usage is normal'
command_name check_filespace_mounts-usage
}
define command {
command_line $USER1$/query_prometheus_alerts.py --prometheus_api $USER2$ --alertname 'node_load1_90percent' --labels_csv 'instance=~"$HOSTADDRESS$.*"' --msg_format 'CRITICAL- Node load average has been more than 90% for the pash hour' --ok_message 'OK- Node load average is normal'
command_name check_node_loadavg
}
define command {
command_line $USER1$/query_prometheus_alerts.py --prometheus_api $USER2$ --alertname 'node_cpu_util_90percent' --labels_csv 'instance=~"$HOSTADDRESS$.*"' --msg_format 'CRITICAL- Node CPU utilization has been more than 90% for the pash hour' --ok_message 'OK- Node cpu utilization is normal'
command_name check_node_cpu_util
}
define command {
command_line $USER1$/query_prometheus_alerts.py --prometheus_api $USER2$ --alertname 'node_network_conntrack_usage_80percent' --labels_csv 'instance=~"$HOSTADDRESS$.*"' --msg_format 'CRITICAL- Node network connections are more than 90% in use' --ok_message 'OK- Network connection utilization is normal'
command_name check_network_connections
}
define command {
command_line $USER1$/query_prometheus_alerts.py --prometheus_api $USER2$ --alertname 'node_high_memory_load' --labels_csv 'instance=~"$HOSTADDRESS$.*"' --msg_format 'CRITICAL- Node memory usage is more than 85%' --ok_message 'OK- Node memory usage is less than 85%'
command_name check_memory_usage
}
define command {
command_line $USER1$/query_prometheus_alerts.py --prometheus_api $USER2$ --alertname 'node_disk_write_latency' --labels_csv 'instance=~"$HOSTADDRESS$.*"' --msg_format 'CRITICAL- Disk write latency is high' --ok_message 'OK- Node disk write latency is normal'
command_name check_disk_write_latency
}
define command {
command_line $USER1$/query_prometheus_alerts.py --prometheus_api $USER2$ --alertname 'node_disk_read_latency' --labels_csv 'instance=~"$HOSTADDRESS$.*"' --msg_format 'CRITICAL- Disk read latency is high' --ok_message 'OK- Node disk read latency is normal'
command_name check_disk_read_latency
}
define command {
command_line $USER1$/query_prometheus_alerts.py --prometheus_api $USER2$ --alertname 'node_entropy_available_low' --labels_csv 'instance=~"$HOSTADDRESS$.*"' --msg_format 'CRITICAL- System has low entropy availability' --ok_message 'OK- System entropy availability is sufficient'
command_name check_entropy_availability
}
define command {
command_line $USER1$/query_prometheus_alerts.py --prometheus_api $USER2$ --alertname 'node_filedescriptors_full_in_3h' --labels_csv 'instance=~"$HOSTADDRESS$.*"' --msg_format 'CRITICAL- at current consumption rate no free file descriptors will be available in 3hrs.' --ok_message 'OK- System file descriptor consumption is ok.'
command_name check_filedescriptor_usage_rate
}
define command {
command_line $USER1$/query_prometheus_alerts.py --prometheus_api $USER2$ --alertname 'node_hwmon_high_cpu_temp' --labels_csv 'instance=~"$HOSTADDRESS$.*"' --msg_format 'CRITICAL- CPU temperature is 90 percent of critical temperature.' --ok_message 'OK- CPU temperatures are normal.'
command_name check_hwmon_high_cpu_temp
}
define command {
command_line $USER1$/query_prometheus_alerts.py --prometheus_api $USER2$ --alertname 'node_high_network_drop_rcv' --labels_csv 'instance=~"$HOSTADDRESS$.*"' --msg_format 'CRITICAL- Host system has an unusally high drop in network reception.' --ok_message 'OK- network packet receive drops not high.'
command_name check_network_receive_drop_high
}
define command {
command_line $USER1$/query_prometheus_alerts.py --prometheus_api $USER2$ --alertname 'node_high_network_drop_send' --labels_csv 'instance=~"$HOSTADDRESS$.*"' --msg_format 'CRITICAL- Host system has an unusally high drop in network transmission.' --ok_message 'OK- network packet tramsmit drops not high.'
command_name check_network_transmit_drop_high
}
define command {
command_line $USER1$/query_prometheus_alerts.py --prometheus_api $USER2$ --alertname 'node_high_network_errs_rcv' --labels_csv 'instance=~"$HOSTADDRESS$.*"' --msg_format 'CRITICAL- Host system has an unusally high error rate in network reception.' --ok_message 'OK- network reception errors not high.'
command_name check_network_receive_errors_high
}
define command {
command_line $USER1$/query_prometheus_alerts.py --prometheus_api $USER2$ --alertname 'node_high_network_errs_send' --labels_csv 'instance=~"$HOSTADDRESS$.*"' --msg_format 'CRITICAL- Host system has an unusally high error rate in network transmission.' --ok_message 'OK- network transmission errors not high.'
command_name check_network_transmit_errors_high
}
define command {
command_line $USER1$/query_prometheus_alerts.py --prometheus_api $USER2$ --alertname 'node_vmstat_paging_rate_high' --labels_csv 'instance=~"$HOSTADDRESS$.*"' --msg_format 'CRITICAL- Memory paging rate over 5 minutes is high.' --ok_message 'OK- Memory paging rate over 5 minutes is ok.'
command_name check_vmstat_paging_rate
}
define command {
command_line $USER1$/query_prometheus_alerts.py --prometheus_api $USER2$ --alertname 'node_xfs_block_allocation_high' --labels_csv 'instance=~"$HOSTADDRESS$.*"' --msg_format 'CRITICAL- XFS block allocation is more than 80 percent of available.' --ok_message 'OK- XFS block allocation is less than 80 percent of available.'
command_name check_xfs_block_allocation
}
define command {
command_line $USER1$/query_prometheus_alerts.py --prometheus_api $USER2$ --alertname 'node_network_bond_slaves_down' --labels_csv 'instance=~"$HOSTADDRESS$.*"' --msg_format 'CRITICAL- {master} is missing slave interfaces.' --ok_message 'OK- Network bonds have slave interfaces functional.'
command_name check_network_bond_status
}
define command {
command_line $USER1$/query_prometheus_alerts.py --prometheus_api $USER2$ --alertname 'node_numa_memory_used' --labels_csv 'instance=~"$HOSTADDRESS$.*"' --msg_format 'CRITICAL- NUMA memory usage is more than 80 percent of available.' --ok_message 'OK- NUMA memory usage is normal.'
command_name check_numa_memory_usage
}
define command {
command_line $USER1$/query_prometheus_alerts.py --prometheus_api $USER2$ --alertname 'node_ntp_clock_skew_high' --labels_csv 'instance=~"$HOSTADDRESS$.*"' --msg_format 'CRITICAL- NTP clock skew is more than 2 seconds.' --ok_message 'OK- NTP clock skew is less than 2 seconds.'
command_name check_ntp_sync
}
define service {
check_command check_filespace_mounts-usage-rate-fullin4hrs
check_interval 60
hostgroup_name base-os
service_description Filespace_mounts-usage-rate-fullin4hrs
use notifying_service
}
define service {
check_command check_filespace_mounts-usage
check_interval 60
hostgroup_name base-os
service_description Filespace_mounts-usage
use notifying_service
}
define service {
check_command check_node_loadavg
hostgroup_name base-os
service_description CPU_Load-average
use notifying_service
}
define service {
check_command check_node_cpu_util
hostgroup_name base-os
service_description CPU_utilization
use notifying_service
}
define service {
check_command check_network_connections
hostgroup_name base-os
service_description Network_connections
use notifying_service
}
define service {
check_command check_memory_usage
hostgroup_name base-os
service_description Memory_usage
use notifying_service
}
define service {
check_command check_disk_write_latency
hostgroup_name base-os
service_description Disk_write-latency
use notifying_service
}
define service {
check_command check_disk_read_latency
hostgroup_name base-os
service_description Disk_read-latency
use notifying_service
}
define service {
check_command check_entropy_availability
hostgroup_name base-os
service_description Entropy_availability
use notifying_service
}
define service {
check_command check_filedescriptor_usage_rate
hostgroup_name base-os
service_description FileDescriptors_usage-rate-high
use notifying_service
}
define service {
check_command check_hwmon_high_cpu_temp
hostgroup_name base-os
service_description HW_cpu-temp-high
use notifying_service
}
define service {
check_command check_network_receive_drop_high
hostgroup_name base-os
service_description Network_receive-drop-high
use notifying_service
}
define service {
check_command check_network_transmit_drop_high
hostgroup_name base-os
service_description Network_transmit-drop-high
use notifying_service
}
define service {
check_command check_network_receive_errors_high
hostgroup_name base-os
service_description Network_receive-errors-high
use notifying_service
}
define service {
check_command check_network_transmit_errors_high
hostgroup_name base-os
service_description Network_transmit-errors-high
use notifying_service
}
define service {
check_command check_vmstat_paging_rate
hostgroup_name base-os
service_description Memory_vmstat-paging-rate
use notifying_service
}
define service {
check_command check_xfs_block_allocation
hostgroup_name base-os
service_description XFS_block-allocation
use notifying_service
}
define service {
check_command check_network_bond_status
hostgroup_name base-os
service_description Network_bondstatus
use notifying_service
}
define service {
check_command check_numa_memory_usage
hostgroup_name base-os
service_description Memory_NUMA-usage
use notifying_service
}
define service {
check_command check_ntp_sync
hostgroup_name base-os
service_description NTP_sync
use notifying_service
}
ceph:
template: |
define service {
check_command check_prom_alert!prom_exporter_ceph_unavailable!CRITICAL- CEPH exporter is not collecting metrics for alerting!OK- CEPH exporter metrics are available.
hostgroup_name prometheus-hosts
service_description Prometheus-exporter_CEPH
use generic-service
}
define command {
command_line $USER1$/check_exporter_health_metric.py --exporter_api $USER10$ --health_metric ceph_health_status --critical 2 --warning 1
command_name check_ceph_health
}
define service {
check_command check_ceph_health
check_interval 300
hostgroup_name base-os
service_description CEPH_health
use notifying_service
}
define service {
check_command check_prom_alert!ceph_mon_quorum_low!CRITICAL- ceph monitor quorum does not exist!OK- ceph monitor quorum exists
check_interval 60
hostgroup_name prometheus-hosts
service_description CEPH_quorum
use notifying_service
}
define service {