Monitoring
Introduction
Je pars du principe que vous utilisez Portainer, que vous savez vous servir d’un éditeur de texte et que vous connaissez vos machines.
Quelques notions
Je vous invite à parcourir mes autres articles :
Ceci afin de vous familiariser avec quelques notions importantes et le style de mes docker-compose et autres fichiers de configurations.
Prérequis
Vous allez avoir besoin de temps pour lire cet article et bien comprendre comment il est articulé.
Je vous laisse aussi adapter les URL présentent dans les différents fichiers de configuration en fonction de votre cas.
J’utilise un conteneur Ntfy pour le système de notification. Si ce n’est pas votre cas il vous faudra soit le mettre en place, soit adapter en fonction du système que vous utilisez ou bien tout simplement commenter les parties en rapport.
Fichiers requis
docker-compose.yml
[Fichier]
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
version: "3.0"
#
# updated: 2023-05-27
# stack: monitoring
#
x-logging: &x-logging
logging:
driver: loki
options:
loki-url: "http://loki:3100/loki/api/v1/push"
loki-retries: "5"
loki-batch-size: "400"
x-common: &x-common
<<: *x-logging
restart: "no"
stop_grace_period: 5s
stdin_open: true
tty: true
privileged: false
security_opt:
- no-new-privileges=true
cap_drop:
- ALL
cap_add:
- KILL
dns:
- 1.1.1.1
- 8.8.8.8
- 1.0.0.1
- 8.8.4.4
ipc: "shareable"
extra_hosts:
- "template.home:192.168.0.0"
environment:
TZ: "Europe/Paris"
PUID: 1000
PGID: 1000
user: 1000:1000
labels:
com.centurylinklabs.watchtower.enable: true
logging: "promtail"
com.stack.name: "common"
com.stack.service.name: "common"
devices:
- /dev/kmsg:/dev/kmsg
deploy:
resources:
limits:
cpus: "0.50"
memory: 256M
ulimits:
nproc: 65535
nofile:
soft: 20000
hard: 40000
tmpfs:
- /tmp:rw,noexec,nosuid,size=64k
sysctls:
net.core.somaxconn: 1024
net.ipv4.tcp_syncookies: 0
x-volume-timezone: &x-volume-timezone "/etc/timezone:/etc/timezone:ro"
x-volume-localtime: &x-volume-localtime "/etc/localtime:/etc/localtime:ro"
x-volume-docker-socket: &x-volume-docker-socket "/var/run/docker.sock:/var/run/docker.sock:rw"
x-volume-cgroups: &x-volume-cgroups "/proc/cgroups:/cgroup:rw"
x-volume-ssl: &x-volume-ssl "/opt/docker/ssl:/ssl:ro"
services:
notifier:
<<: *x-common
container_name: notifier
hostname: notifier
image: academo/grafana-ntfy:latest
restart: always
ports:
- "8088:8080"
expose:
- "8080"
labels:
com.stack.name: "monitoring"
com.stack.service.name: "notifier"
command:
- "-ntfy-url=http://ntfy:8050/grafana"
volumes:
- *x-volume-timezone
- *x-volume-localtime
cadvisor:
<<: *x-common
user: 0:0
container_name: cadvisor
hostname: cadvisor
image: gcr.io/cadvisor/cadvisor:v0.47.1
restart: always
privileged: true
cap_add:
- SYS_PTRACE
ports:
- "8080:8080"
expose:
- "8080"
command:
- "--storage_duration=1m0s"
- "--allow_dynamic_housekeeping=true"
- "--housekeeping_interval=30s"
- "--global_housekeeping_interval=30s"
- "--event_storage_age_limit=default=0"
- "--event_storage_event_limit=default=0"
labels:
com.stack.name: "monitoring"
com.stack.service.name: "cadvisor"
volumes:
- *x-volume-timezone
- *x-volume-localtime
- *x-volume-docker-socket
- *x-volume-cgroups
- /var/lib/docker/:/var/lib/docker:ro
- /etc/machine-id:/etc/machine-id:ro
- /:/rootfs:ro
- /sys:/sys:ro
- /dev/disk/:/dev/disk:ro
- /var/run:/var/run:ro
node-exporter:
<<: *x-common
user: 0:0
container_name: node-exporter
hostname: node-exporter
image: prom/node-exporter:latest
restart: always
privileged: true
cap_add:
- SYS_ADMIN
ports:
- "9100:9100"
expose:
- "9100"
healthcheck:
test: wget --no-verbose --tries=1 --spider http://localhost:9100/ || exit 1
command:
- "--collector.arp"
- "--collector.bcache"
- "--collector.bonding"
- "--collector.btrfs"
- "--collector.conntrack"
- "--collector.cpu"
- "--collector.cpufreq"
- "--collector.diskstats"
- "--collector.dmi"
- "--collector.edac"
- "--collector.entropy"
- "--collector.fibrechannel"
- "--collector.filefd"
- "--collector.filesystem"
- "--collector.hwmon"
- "--collector.infiniband"
- "--collector.ipvs"
- "--collector.loadavg"
- "--collector.mdadm"
- "--collector.meminfo"
- "--collector.netclass"
- "--collector.netdev"
- "--collector.netstat"
- "--collector.nfs"
- "--collector.nfsd"
- "--collector.nvme"
- "--collector.os"
- "--collector.powersupplyclass"
- "--collector.pressure"
- "--collector.rapl"
- "--collector.schedstat"
- "--collector.selinux"
- "--collector.sockstat"
- "--collector.softnet"
- "--collector.stat"
- "--collector.tapestats"
- "--collector.textfile"
- "--collector.thermal_zone"
- "--collector.time"
- "--collector.timex"
- "--collector.udp_queues"
- "--collector.uname"
- "--collector.vmstat"
- "--collector.xfs"
- "--collector.zfs"
- "--collector.buddyinfo"
- "--collector.cgroups"
- "--collector.drbd"
- "--collector.ethtool"
- "--collector.interrupts"
- "--collector.ksmd"
- "--collector.lnstat"
- "--collector.logind"
- "--collector.meminfo_numa"
- "--collector.mountstats"
- "--collector.network_route"
- "--collector.ntp"
- "--collector.perf"
- "--collector.processes"
- "--collector.qdisc"
- "--collector.runit"
#- "--collector.slabinfo"
- "--collector.supervisord"
- "--collector.sysctl"
- "--collector.systemd"
- "--collector.tcpstat"
- "--collector.wifi"
- "--collector.zoneinfo"
- "--path.rootfs=/host"
- "--path.procfs=/host/proc"
- "--path.sysfs=/host/sys"
- "--collector.filesystem.ignored-mount-points='^(/rootfs|/host|)/(sys|proc|dev|host|etc)($$|/)'"
- "--collector.filesystem.ignored-fs-types='^(sys|proc|auto|cgroup|devpts|ns|au|fuse\\.lxc|mqueue)(fs|)$$'"
- "--collector.netdev.device-exclude='^(lo|veth.*)$'"
- "--collector.ethtool.device-exclude='^(lo|br-.*|docker0|flannel.*|veth.*)$'"
labels:
com.stack.name: "monitoring"
com.stack.service.name: "node-exporter"
deploy:
resources:
limits:
memory: 512M
volumes:
- *x-volume-timezone
- *x-volume-localtime
- *x-volume-docker-socket
- *x-volume-cgroups
- /etc/service:/etc/service:ro
- /:/host:ro,rslave
- /sys:/host/sys:ro
- /proc:/host/proc:ro
- /run/udev/data:/run/udev/data:ro
- /var/run/dbus/system_bus_socket:/var/run/dbus/system_bus_socket:ro
ntfy-alertmanager:
<<: *x-common
user: 0:0
cap_add:
- DAC_OVERRIDE
container_name: ntfy-alertmanager
hostname: ntfy-alertmanager
image: xenrox/ntfy-alertmanager:latest
restart: always
ports:
- "6080:8080"
expose:
- "8080"
environment:
NTFY_TOPIC: "alertmanager"
labels:
com.stack.name: "monitoring"
com.stack.service.name: "ntfy"
deploy:
resources:
limits:
memory: 512M
volumes:
- *x-volume-timezone
- *x-volume-localtime
- /opt/docker/monitoring/conf/ntfy-alertmanager.cfg:/etc/ntfy-alertmanager/config
alertmanager:
<<: *x-common
cap_add:
- DAC_OVERRIDE
container_name: alertmanager
hostname: alertmanager
image: prom/alertmanager:latest
restart: always
ports:
- "9093:9093"
expose:
- "9093"
command:
- "--config.file=/etc/alertmanager/alertmanager.yml"
healthcheck:
test: wget --no-verbose --tries=1 --spider http://localhost:9093/ || exit 1
labels:
com.stack.name: "monitoring"
com.stack.service.name: "alertmanager"
deploy:
resources:
limits:
memory: 512M
volumes:
- *x-volume-timezone
- *x-volume-localtime
- /opt/docker/monitoring/conf/alertmanager.yml:/etc/alertmanager/alertmanager.yml
- /opt/docker/monitoring/datas/alertmanager:/alertmanager
mimir:
<<: *x-common
stop_grace_period: 60s
user: 0:0
cap_add:
- DAC_OVERRIDE
- SETUID
- SETGID
- CHOWN
- SYS_ADMIN
container_name: mimir
hostname: mimir
image: grafana/mimir:latest
restart: always
ports:
- "9009:9009"
- "9095:9095"
expose:
- "9009"
- "9095"
command:
- "--config.file=/etc/mimir/mimir.yaml"
healthcheck:
test: wget --no-verbose --tries=1 --spider http://localhost:9009/ || exit 1
labels:
com.stack.name: "monitoring"
com.stack.service.name: "mimir"
deploy:
resources:
limits:
memory: 4G
volumes:
- *x-volume-timezone
- *x-volume-localtime
- /opt/docker/monitoring/conf/mimir.yml:/etc/mimir/mimir.yaml
- /opt/docker/monitoring/datas/mimir:/mimir
prometheus:
<<: *x-common
stop_grace_period: 60s
cap_add:
- DAC_OVERRIDE
container_name: prometheus
hostname: prometheus
image: prom/prometheus:latest
restart: always
depends_on:
- mimir
- alertmanager
- cadvisor
- node-exporter
links:
- mimir
- alertmanager
- cadvisor
- node-exporter
ports:
- "9090:9090"
expose:
- "9090"
healthcheck:
test: wget --no-verbose --tries=1 --spider http://localhost:9090/ || exit 1
command:
- "--storage.tsdb.retention.time=365d"
- "--config.file=/etc/prometheus/prometheus.yml"
labels:
com.stack.name: "monitoring"
com.stack.service.name: "prometheus"
deploy:
resources:
limits:
memory: 2G
volumes:
- *x-volume-timezone
- *x-volume-localtime
- /opt/docker/monitoring/conf/prometheus.yml:/etc/prometheus/prometheus.yml:ro
- /opt/docker/monitoring/conf/alertmanager/rules.yml:/alertmanager/rules.yml:ro
- /opt/docker/monitoring/datas/prometheus:/prometheus
grafana:
<<: *x-common
logging:
driver: json-file
options:
max-size: 32m
max-file: "7"
compress: "true"
user: 0:0
cap_add:
- DAC_OVERRIDE
- SETUID
- SETGID
- CHOWN
- SYS_ADMIN
container_name: grafana
hostname: grafana
image: grafana/grafana:latest
restart: always
ports:
- "3000:3000"
expose:
- "3000"
healthcheck:
test: wget --no-verbose --tries=1 --spider http://localhost:3000/api/health || exit 1
depends_on:
- notifier
- prometheus
links:
- notifier
- prometheus
environment:
GF_USERS_ALLOW_SIGN_UP: false
GF_SERVER_SERVE_FROM_SUB_PATH: true
GF_INSTALL_PLUGINS: "grafana-clock-panel,grafana-piechart-panel,grafana-simple-json-datasource,grafana-worldmap-panel,camptocamp-prometheus-alertmanager-datasource"
GF_SECURITY_ADMIN_USER: "[admin username]"
GF_SECURITY_ADMIN_PASSWORD: "[admin password]"
labels:
com.stack.name: "monitoring"
com.stack.service.name: "grafana"
tmpfs:
- /tmp:rw,noexec,nosuid,size=5120k
deploy:
resources:
limits:
cpus: "4.0"
memory: 1G
volumes:
- *x-volume-timezone
- *x-volume-localtime
- /opt/docker/monitoring/conf/grafana.ini:/etc/grafana/grafana.ini
- /opt/docker/monitoring/conf/provisioning:/etc/grafana/provisioning
- /opt/docker/monitoring/conf/provisioning/provisioned:/etc/grafana/dashboards/provisioned
- /opt/docker/monitoring/datas/grafana/dashboards:/etc/grafana/dashboards
- /opt/docker/monitoring/datas/grafana/datas:/var/lib/grafana
conf/mimir.yml
[Fichier]
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
# 2023-05-25
usage_stats:
enabled: false
multitenancy_enabled: true
blocks_storage:
backend: filesystem
bucket_store:
sync_dir: /mimir/tsdb-sync
filesystem:
dir: /mimir/data/tsdb
tsdb:
dir: /mimir/tsdb
compactor:
data_dir: /mimir/compactor
sharding_ring:
kvstore:
store: memberlist
distributor:
ring:
instance_addr: 127.0.0.1
kvstore:
store: memberlist
ingester:
ring:
instance_addr: 127.0.0.1
kvstore:
store: memberlist
replication_factor: 1
ruler_storage:
backend: filesystem
filesystem:
dir: /tmp/mimir/rules
server:
http_listen_port: 9009
grpc_listen_port: 9095
log_level: error
store_gateway:
sharding_ring:
replication_factor: 1
limits:
max_label_names_per_series: 128
out_of_order_time_window: 90d
conf/alertmanager.yml
[Fichier]
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
# 2023-05-24
global:
resolve_timeout: 5m
route:
group_by: ["..."]
group_wait: 10s
group_interval: 10s
repeat_interval: 1h
receiver: "ntfy"
routes:
- matchers: ['{severity=~"info|warning|critical"}']
receivers:
- name: "ntfy"
webhook_configs:
- url: "http://ntfy-alertmanager:6080"
conf/ntfy-alertmanager.cfg
[Fichier]
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
# 2023-05-24
# Public facing base URL of the service
# This setting is required for the "Silence" feature.
base-url https://ntfyforwarder.domain.com
# http listen address
http-address :6080
# Log level (either debug, info, warning, error)
log-level warning
# When multiple alerts are grouped together by Alertmanager, they can either be sent
# each on their own (single mode) or be kept together (multi mode) (either single or multi; default is single)
alert-mode single
labels {
order "severity,instance"
severity "critical" {
priority 5
tags "rotating_light"
}
severity "info" {
priority 1
}
}
# Settings for resolved alerts
resolved {
tags "resolved,partying_face"
}
ntfy {
# URL of the ntfy topic - required
topic http://ntfy:8050/alerts
}
alertmanager {
# If set, the ntfy message will contain a "Silence" button, which can be used
# to create a silence via the Alertmanager API. Because of limitations in ntfy,
# the request will be proxied through ntfy-alertmanager. Therefore ntfy-alertmanager
# needs to be exposed to external network requests and base-url has to be set.
#
# When alert-mode is set to "single" all alert labels will be used to create the silence.
# When it is "multi" common labels between all the alerts will be used. WARNING: This
# could silence unwanted alerts.
#silence-duration 24h
# By default the Alertmanager URL gets parsed from the webhook. In case that
# Alertmanger is not reachable under that URL, it can be overwritten here.
}
# When the alert-mode is set to single, ntfy-alertmanager will cache each single alert
# to avoid sending recurrences.
cache {
# The type of cache that will be used (either memory or redis; default is memory).
type memory
# How long messages stay in the cache for
duration 24h
# Memory cache settings
# Interval in which the cache is cleaned up
cleanup-interval 1h
# Redis cache settings
# URL to connect to redis (default: redis://localhost:6379)
redis-url redis://redis:6789
}
conf/prometheus.yml
[Fichier]
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
# 2023-05-25
global:
scrape_interval: 15s
scrape_timeout: 10s
evaluation_interval: 15s
external_labels:
cluster: org
namespace: org
remote_write:
- url: http://mimir:9009/api/v1/push
headers:
X-Scope-OrgID: org
alerting:
alertmanagers:
- static_configs:
- targets: [ "template.home:9093" ]
scheme: http
timeout: 10s
rule_files:
- /alertmanager/rules.yml
scrape_configs:
- job_name: "template"
honor_timestamps: true
honor_labels: true
scrape_interval: 15s
scrape_timeout: 10s
metrics_path: /metrics
scheme: http
static_configs:
- targets: ["prometheus:9090", "cadvisor:8080", "node-exporter:9100"]
labels:
alias: Template
ip: 192.168.0.0
conf/grafana.ini
[Fichier]
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
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
# 2023-05-21
##################### Grafana Configuration Defaults #####################
#
# Do not modify this file in grafana installs
#
# possible values : production, development
app_mode = production
# instance name, defaults to HOSTNAME environment variable value or hostname if HOSTNAME var is empty
instance_name = ${HOSTNAME}
# force migration will run migrations that might cause dataloss
force_migration = false
#################################### Paths ###############################
[paths]
# Path to where grafana can store temp files, sessions, and the sqlite3 db (if that is used)
data = data
# Temporary files in `data` directory older than given duration will be removed
temp_data_lifetime = 24h
# Directory where grafana can store logs
logs = data/log
# Directory where grafana will automatically scan and look for plugins
plugins = data/plugins
# folder that contains provisioning config files that grafana will apply on startup and while running.
provisioning = conf/provisioning
#################################### Server ##############################
[server]
# Protocol (http, https, h2, socket)
protocol = http
# Minimum TLS version allowed. By default, this value is empty. Accepted values are: TLS1.2, TLS1.3. If nothing is set TLS1.2 would be taken
min_tls_version = ""
# The ip address to bind to, empty will bind to all interfaces
http_addr =
# The http port to use
http_port = 3000
# The public facing domain name used to access grafana from a browser
domain = localhost
# Redirect to correct domain if host header does not match domain
# Prevents DNS rebinding attacks
enforce_domain = false
# The full public facing url
#root_url = %(protocol)s://%(domain)s:%(http_port)s/
root_url = %(protocol)s://%(domain)s:%(http_port)s/
# Serve Grafana from subpath specified in `root_url` setting. By default it is set to `false` for compatibility reasons.
serve_from_sub_path = false
# Log web requests
router_logging = false
# the path relative working path
static_root_path = public
# enable gzip
#enable_gzip = false
enable_gzip = true
# https certs & key file
cert_file =
cert_key =
# Unix socket gid
# Changing the gid of a file without privileges requires that the target group is in the group of the process and that the process is the file owner
# It is recommended to set the gid as http server user gid
# Not set when the value is -1
socket_gid = -1
# Unix socket mode
socket_mode = 0660
# Unix socket path
socket = /tmp/grafana.sock
# CDN Url
cdn_url =
# Sets the maximum time in minutes before timing out read of an incoming request and closing idle connections.
# `0` means there is no timeout for reading the request.
read_timeout = 0
# This setting enables you to specify additional headers that the server adds to HTTP(S) responses.
[server.custom_response_headers]
#exampleHeader1 = exampleValue1
#exampleHeader2 = exampleValue2
#################################### GRPC Server #########################
[grpc_server]
network = "tcp"
address = "127.0.0.1:10000"
use_tls = false
cert_file =
key_file =
#################################### Database ############################
[database]
# You can configure the database connection by specifying type, host, name, user and password
# as separate properties or as on string using the url property.
# Either "mysql", "postgres" or "sqlite3", it's your choice
type = sqlite3
host = 127.0.0.1:3306
name = grafana
user = root
# If the password contains # or ; you have to wrap it with triple quotes. Ex """#password;"""
password =
# Use either URL or the previous fields to configure the database
# Example: mysql://user:secret@host:port/database
url =
# Max idle conn setting default is 2
max_idle_conn = 2
# Max conn setting default is 0 (mean not set)
max_open_conn =
# Connection Max Lifetime default is 14400 (means 14400 seconds or 4 hours)
conn_max_lifetime = 14400
# Set to true to log the sql calls and execution times.
log_queries =
# For "postgres", use either "disable", "require" or "verify-full"
# For "mysql", use either "true", "false", or "skip-verify".
ssl_mode = disable
# Database drivers may support different transaction isolation levels.
# Currently, only "mysql" driver supports isolation levels.
# If the value is empty - driver's default isolation level is applied.
# For "mysql" use "READ-UNCOMMITTED", "READ-COMMITTED", "REPEATABLE-READ" or "SERIALIZABLE".
isolation_level =
ca_cert_path =
client_key_path =
client_cert_path =
server_cert_name =
# For "sqlite3" only, path relative to data_path setting
path = grafana.db
# For "sqlite3" only. cache mode setting used for connecting to the database
cache_mode = private
# For "sqlite3" only. Enable/disable Write-Ahead Logging, https://sqlite.org/wal.html. Default is false.
wal = false
# For "mysql" only if migrationLocking feature toggle is set. How many seconds to wait before failing to lock the database for the migrations, default is 0.
locking_attempt_timeout_sec = 0
# For "sqlite" only. How many times to retry query in case of database is locked failures. Default is 0 (disabled).
query_retries = 0
# For "sqlite" only. How many times to retry transaction in case of database is locked failures. Default is 5.
transaction_retries = 5
# Set to true to add metrics and tracing for database queries.
instrument_queries = false
#################################### Cache server #############################
[remote_cache]
# Either "redis", "memcached" or "database" default is "database"
#type = database
type = redis
# cache connectionstring options
# database: will use Grafana primary database.
# redis: config like redis server e.g. `addr=127.0.0.1:6379,pool_size=100,db=0,ssl=false`. Only addr is required. ssl may be 'true', 'false', or 'insecure'.
# memcache: 127.0.0.1:11211
#connstr =
connstr = addr=redis:6379,pool_size=100,db=0,ssl=false
# prefix prepended to all the keys in the remote cache
prefix =
# This enables encryption of values stored in the remote cache
encryption =
#################################### Data proxy ###########################
[dataproxy]
# This enables data proxy logging, default is false
logging = false
# How long the data proxy waits to read the headers of the response before timing out, default is 30 seconds.
# This setting also applies to core backend HTTP data sources where query requests use an HTTP client with timeout set.
timeout = 30
# How long the data proxy waits to establish a TCP connection before timing out, default is 10 seconds.
dialTimeout = 10
# How many seconds the data proxy waits before sending a keepalive request.
keep_alive_seconds = 30
# How many seconds the data proxy waits for a successful TLS Handshake before timing out.
tls_handshake_timeout_seconds = 10
# How many seconds the data proxy will wait for a server's first response headers after
# fully writing the request headers if the request has an "Expect: 100-continue"
# header. A value of 0 will result in the body being sent immediately, without
# waiting for the server to approve.
expect_continue_timeout_seconds = 1
# Optionally limits the total number of connections per host, including connections in the dialing,
# active, and idle states. On limit violation, dials will block.
# A value of zero (0) means no limit.
max_conns_per_host = 0
# The maximum number of idle connections that Grafana will keep alive.
max_idle_connections = 100
# How many seconds the data proxy keeps an idle connection open before timing out.
idle_conn_timeout_seconds = 90
# If enabled and user is not anonymous, data proxy will add X-Grafana-User header with username into the request.
send_user_header = false
# Limit the amount of bytes that will be read/accepted from responses of outgoing HTTP requests.
response_limit = 0
# Limits the number of rows that Grafana will process from SQL data sources.
row_limit = 1000000
# Sets a custom value for the `User-Agent` header for outgoing data proxy requests. If empty, the default value is `Grafana/<BuildVersion>` (for example `Grafana/9.0.0`).
user_agent =
#################################### Analytics ###########################
[analytics]
# Server reporting, sends usage counters to stats.grafana.org every 24 hours.
# No ip addresses are being tracked, only simple counters to track
# running instances, dashboard and error counts. It is very helpful to us.
# Change this option to false to disable reporting.
#reporting_enabled = true
reporting_enabled = false
# The name of the distributor of the Grafana instance. Ex hosted-grafana, grafana-labs
reporting_distributor = grafana-labs
# Set to false to disable all checks to https://grafana.com
# for new versions of grafana. The check is used
# in some UI views to notify that a grafana update exists.
# This option does not cause any auto updates, nor send any information
# only a GET request to https://raw.githubusercontent.com/grafana/grafana/main/latest.json to get the latest version.
check_for_updates = true
# Set to false to disable all checks to https://grafana.com
# for new versions of plugins. The check is used
# in some UI views to notify that a plugin update exists.
# This option does not cause any auto updates, nor send any information
# only a GET request to https://grafana.com to get the latest versions.
check_for_plugin_updates = true
# Google Analytics universal tracking code, only enabled if you specify an id here
google_analytics_ua_id =
# Google Analytics 4 tracking code, only enabled if you specify an id here
google_analytics_4_id =
# When Google Analytics 4 Enhanced event measurement is enabled, we will try to avoid sending duplicate events and let Google Analytics 4 detect navigation changes, etc.
google_analytics_4_send_manual_page_views = false
# Google Tag Manager ID, only enabled if you specify an id here
google_tag_manager_id =
# Rudderstack write key, enabled only if rudderstack_data_plane_url is also set
rudderstack_write_key =
# Rudderstack data plane url, enabled only if rudderstack_write_key is also set
rudderstack_data_plane_url =
# Rudderstack SDK url, optional, only valid if rudderstack_write_key and rudderstack_data_plane_url is also set
rudderstack_sdk_url =
# Rudderstack Config url, optional, used by Rudderstack SDK to fetch source config
rudderstack_config_url =
# Intercom secret, optional, used to hash user_id before passing to Intercom via Rudderstack
intercom_secret =
# Application Insights connection string. Specify an URL string to enable this feature.
application_insights_connection_string =
# Optional. Specifies an Application Insights endpoint URL where the endpoint string is wrapped in backticks ``.
application_insights_endpoint_url =
# Controls if the UI contains any links to user feedback forms
feedback_links_enabled = true
#################################### Security ############################
[security]
# disable creation of admin user on first start of grafana
disable_initial_admin_creation = false
# default admin user, created on startup
admin_user = admin
# default admin password, can be changed before first start of grafana, or in profile settings
admin_password = admin
# default admin email, created on startup
admin_email = admin@localhost
# used for signing
secret_key =
# current key provider used for envelope encryption, default to static value specified by secret_key
encryption_provider = secretKey.v1
# list of configured key providers, space separated (Enterprise only): e.g., awskms.v1 azurekv.v1
available_encryption_providers =
# disable gravatar profile images
disable_gravatar = false
# data source proxy whitelist (ip_or_domain:port separated by spaces)
data_source_proxy_whitelist =
# disable protection against brute force login attempts
disable_brute_force_login_protection = false
# set to true if you host Grafana behind HTTPS. default is false.
cookie_secure = false
# set cookie SameSite attribute. defaults to `lax`. can be set to "lax", "strict", "none" and "disabled"
cookie_samesite = lax
# set to true if you want to allow browsers to render Grafana in a <frame>, <iframe>, <embed> or <object>. default is false.
allow_embedding = false
# Set to true if you want to enable http strict transport security (HSTS) response header.
# HSTS tells browsers that the site should only be accessed using HTTPS.
strict_transport_security = false
# Sets how long a browser should cache HSTS. Only applied if strict_transport_security is enabled.
strict_transport_security_max_age_seconds = 86400
# Set to true if to enable HSTS preloading option. Only applied if strict_transport_security is enabled.
strict_transport_security_preload = false
# Set to true if to enable the HSTS includeSubDomains option. Only applied if strict_transport_security is enabled.
strict_transport_security_subdomains = false
# Set to true to enable the X-Content-Type-Options response header.
# The X-Content-Type-Options response HTTP header is a marker used by the server to indicate that the MIME types advertised
# in the Content-Type headers should not be changed and be followed.
x_content_type_options = true
# Set to true to enable the X-XSS-Protection header, which tells browsers to stop pages from loading
# when they detect reflected cross-site scripting (XSS) attacks.
x_xss_protection = true
# Enable adding the Content-Security-Policy header to your requests.
# CSP allows to control resources the user agent is allowed to load and helps prevent XSS attacks.
content_security_policy = false
# Set Content Security Policy template used when adding the Content-Security-Policy header to your requests.
# $NONCE in the template includes a random nonce.
# $ROOT_PATH is server.root_url without the protocol.
content_security_policy_template = """script-src 'self' 'unsafe-eval' 'unsafe-inline' 'strict-dynamic' $NONCE;object-src 'none';font-src 'self';style-src 'self' 'unsafe-inline' blob:;img-src * data:;base-uri 'self';connect-src 'self' grafana.com ws://$ROOT_PATH wss://$ROOT_PATH;manifest-src 'self';media-src 'none';form-action 'self';"""
# Enable adding the Content-Security-Policy-Report-Only header to your requests.
# Allows you to monitor the effects of a policy without enforcing it.
content_security_policy_report_only = false
# Set Content Security Policy Report Only template used when adding the Content-Security-Policy-Report-Only header to your requests.
# $NONCE in the template includes a random nonce.
# $ROOT_PATH is server.root_url without the protocol.
content_security_policy_report_only_template = """script-src 'self' 'unsafe-eval' 'unsafe-inline' 'strict-dynamic' $NONCE;object-src 'none';font-src 'self';style-src 'self' 'unsafe-inline' blob:;img-src * data:;base-uri 'self';connect-src 'self' grafana.com ws://$ROOT_PATH wss://$ROOT_PATH;manifest-src 'self';media-src 'none';form-action 'self';"""
# Controls if old angular plugins are supported or not. This will be disabled by default in future release
angular_support_enabled = true
# The CSRF check will be executed even if the request has no login cookie.
csrf_always_check = false
[security.encryption]
# Defines the time-to-live (TTL) for decrypted data encryption keys stored in memory (cache).
# Please note that small values may cause performance issues due to a high frequency decryption operations.
data_keys_cache_ttl = 15m
# Defines the frequency of data encryption keys cache cleanup interval.
# On every interval, decrypted data encryption keys that reached the TTL are removed from the cache.
data_keys_cache_cleanup_interval = 1m
#################################### Snapshots ###########################
[snapshots]
# set to false to remove snapshot functionality
enabled = true
# snapshot sharing options
external_enabled = true
external_snapshot_url = https://snapshots.raintank.io
external_snapshot_name = Publish to snapshots.raintank.io
# Set to true to enable this Grafana instance act as an external snapshot server and allow unauthenticated requests for
# creating and deleting snapshots.
public_mode = false
# remove expired snapshot
snapshot_remove_expired = true
#################################### Dashboards ##################
[dashboards]
# Number dashboard versions to keep (per dashboard). Default: 20, Minimum: 1
versions_to_keep = 20
# Minimum dashboard refresh interval. When set, this will restrict users to set the refresh interval of a dashboard lower than given interval. Per default this is 5 seconds.
# The interval string is a possibly signed sequence of decimal numbers, followed by a unit suffix (ms, s, m, h, d), e.g. 30s or 1m.
min_refresh_interval = 5s
# Path to the default home dashboard. If this value is empty, then Grafana uses StaticRootPath + "dashboards/home.json"
default_home_dashboard_path =
################################### Data sources #########################
[datasources]
# Upper limit of data sources that Grafana will return. This limit is a temporary configuration and it will be deprecated when pagination will be introduced on the list data sources API.
datasource_limit = 5000
################################### SQL Data Sources #####################
[sql_datasources]
# Default maximum number of open connections maintained in the connection pool
# when connecting to SQL based data sources
max_open_conns_default = 100
# Default maximum number of idle connections maintained in the connection pool
# when connecting to SQL based data sources
max_idle_conns_default = 100
# Default maximum connection lifetime used when connecting
# to SQL based data sources.
max_conn_lifetime_default = 14400
#################################### Users ###############################
[users]
# disable user signup / registration
allow_sign_up = false
# Allow non admin users to create organizations
allow_org_create = false
# Set to true to automatically assign new users to the default organization (id 1)
auto_assign_org = true
# Set this value to automatically add new users to the provided organization (if auto_assign_org above is set to true)
auto_assign_org_id = 1
# Default role new users will be automatically assigned (if auto_assign_org above is set to true)
auto_assign_org_role = Viewer
# Require email validation before sign up completes
verify_email_enabled = false
# Background text for the user field on the login page
login_hint = email or username
password_hint = password
# Default UI theme ("dark" or "light" or "system")
default_theme = dark
# Default UI language (supported IETF language tag, such as en-US)
default_language = en-US
# Path to a custom home page. Users are only redirected to this if the default home dashboard is used. It should match a frontend route and contain a leading slash.
home_page =
# External user management
external_manage_link_url =
external_manage_link_name =
external_manage_info =
# Viewers can edit/inspect dashboard settings in the browser. But not save the dashboard.
viewers_can_edit = false
# Editors can administrate dashboard, folders and teams they create
editors_can_admin = false
# The duration in time a user invitation remains valid before expiring. This setting should be expressed as a duration. Examples: 6h (hours), 2d (days), 1w (week). Default is 24h (24 hours). The minimum supported duration is 15m (15 minutes).
user_invite_max_lifetime_duration = 24h
# Enter a comma-separated list of usernames to hide them in the Grafana UI. These users are shown to Grafana admins and to themselves.
hidden_users =
[secretscan]
# Enable secretscan feature
enabled = false
# Interval to check for token leaks
interval = 5m
# base URL of the grafana token leak check service
base_url = https://secret-scanning.grafana.net
# URL to send outgoing webhooks to in case of detection
oncall_url =
# Whether to revoke the token if a leak is detected or just send a notification
revoke = true
[service_accounts]
# When set, Grafana will not allow the creation of tokens with expiry greater than this setting.
token_expiration_day_limit =
[auth]
# Login cookie name
login_cookie_name = grafana_session
# Disable usage of Grafana build-in login solution.
disable_login = false
# The maximum lifetime (duration) an authenticated user can be inactive before being required to login at next visit. Default is 7 days (7d). This setting should be expressed as a duration, e.g. 5m (minutes), 6h (hours), 10d (days), 2w (weeks), 1M (month). The lifetime resets at each successful token rotation (token_rotation_interval_minutes).
login_maximum_inactive_lifetime_duration =
# The maximum lifetime (duration) an authenticated user can be logged in since login time before being required to login. Default is 30 days (30d). This setting should be expressed as a duration, e.g. 5m (minutes), 6h (hours), 10d (days), 2w (weeks), 1M (month).
login_maximum_lifetime_duration =
# How often should auth tokens be rotated for authenticated users when being active. The default is each 10 minutes.
token_rotation_interval_minutes = 10
# Set to true to disable (hide) the login form, useful if you use OAuth
disable_login_form = false
# Set to true to disable the sign out link in the side menu. Useful if you use auth.proxy or auth.jwt.
disable_signout_menu = false
# URL to redirect the user to after sign out
signout_redirect_url =
# Set to true to attempt login with OAuth automatically, skipping the login screen.
# This setting is ignored if multiple OAuth providers are configured.
# Deprecated, use auto_login option for specific provider instead.
oauth_auto_login = false
# OAuth state max age cookie duration in seconds. Defaults to 600 seconds.
oauth_state_cookie_max_age = 600
# Skip forced assignment of OrgID 1 or 'auto_assign_org_id' for social logins
# Deprecated, use skip_org_role_sync option for specific provider instead.
oauth_skip_org_role_update_sync = false
# limit of api_key seconds to live before expiration
api_key_max_seconds_to_live = -1
# Set to true to enable SigV4 authentication option for HTTP-based datasources
sigv4_auth_enabled = false
# Set to true to enable verbose logging of SigV4 request signing
sigv4_verbose_logging = false
# Set to true to enable Azure authentication option for HTTP-based datasources
azure_auth_enabled = false
#################################### Anonymous Auth ######################
[auth.anonymous]
# enable anonymous access
enabled = false
# specify organization name that should be used for unauthenticated users
org_name = Main Org.
# specify role for unauthenticated users
org_role = Viewer
# mask the Grafana version number for unauthenticated users
hide_version = false
#################################### GitHub Auth #########################
[auth.github]
name = GitHub
icon = github
enabled = false
allow_sign_up = true
auto_login = false
client_id = some_id
client_secret =
scopes = user:email,read:org
auth_url = https://github.com/login/oauth/authorize
token_url = https://github.com/login/oauth/access_token
api_url = https://api.github.com/user
allowed_domains =
team_ids =
allowed_organizations =
role_attribute_path =
role_attribute_strict = false
allow_assign_grafana_admin = false
tls_skip_verify_insecure = false
#################################### GitLab Auth #########################
[auth.gitlab]
name = GitLab
icon = gitlab
enabled = false
allow_sign_up = true
auto_login = false
client_id = some_id
client_secret =
scopes = api
auth_url = https://gitlab.com/oauth/authorize
token_url = https://gitlab.com/oauth/token
api_url = https://gitlab.com/api/v4
allowed_domains =
allowed_groups =
role_attribute_path =
role_attribute_strict = false
allow_assign_grafana_admin = false
skip_org_role_sync = false
tls_skip_verify_insecure = false
use_pkce = true
#################################### Google Auth #########################
[auth.google]
name = Google
icon = google
enabled = false
allow_sign_up = true
auto_login = false
client_id = some_client_id
client_secret =
scopes = https://www.googleapis.com/auth/userinfo.profile https://www.googleapis.com/auth/userinfo.email
auth_url = https://accounts.google.com/o/oauth2/auth
token_url = https://accounts.google.com/o/oauth2/token
api_url = https://www.googleapis.com/oauth2/v1/userinfo
allowed_domains =
hosted_domain =
skip_org_role_sync = false
tls_skip_verify_insecure = false
use_pkce = true
#################################### Grafana.com Auth ####################
# legacy key names (so they work in env variables)
[auth.grafananet]
enabled = false
allow_sign_up = true
client_id = some_id
client_secret =
scopes = user:email
allowed_organizations =
[auth.grafana_com]
name = Grafana.com
icon = grafana
enabled = false
allow_sign_up = true
auto_login = false
client_id = some_id
client_secret =
scopes = user:email
allowed_organizations =
skip_org_role_sync = false
#################################### Azure AD OAuth #######################
[auth.azuread]
name = Microsoft
icon = microsoft
enabled = false
allow_sign_up = true
auto_login = false
client_id = some_client_id
client_secret =
scopes = openid email profile
auth_url = https://login.microsoftonline.com/<tenant-id>/oauth2/v2.0/authorize
token_url = https://login.microsoftonline.com/<tenant-id>/oauth2/v2.0/token
allowed_domains =
allowed_groups =
role_attribute_strict = false
allow_assign_grafana_admin = false
force_use_graph_api = false
tls_skip_verify_insecure = false
use_pkce = true
#################################### Okta OAuth #######################
[auth.okta]
name = Okta
icon = okta
enabled = false
allow_sign_up = true
auto_login = false
client_id = some_id
client_secret =
scopes = openid profile email groups
auth_url = https://<tenant-id>.okta.com/oauth2/v1/authorize
token_url = https://<tenant-id>.okta.com/oauth2/v1/token
api_url = https://<tenant-id>.okta.com/oauth2/v1/userinfo
allowed_domains =
allowed_groups =
role_attribute_path =
role_attribute_strict = false
allow_assign_grafana_admin = false
skip_org_role_sync = false
tls_skip_verify_insecure = false
use_pkce = true
#################################### Generic OAuth #######################
[auth.generic_oauth]
name = OAuth
icon = signin
enabled = false
allow_sign_up = true
auto_login = false
client_id = some_id
client_secret =
scopes = user:email
empty_scopes = false
email_attribute_name = email:primary
email_attribute_path =
login_attribute_path =
name_attribute_path =
role_attribute_path =
role_attribute_strict = false
groups_attribute_path =
id_token_attribute_name =
team_ids_attribute_path =
auth_url =
token_url =
api_url =
teams_url =
allowed_domains =
team_ids =
allowed_organizations =
tls_skip_verify_insecure = false
tls_client_cert =
tls_client_key =
tls_client_ca =
use_pkce = false
auth_style =
allow_assign_grafana_admin = false
skip_org_role_sync = false
#################################### Basic Auth ##########################
[auth.basic]
enabled = true
#################################### Auth Proxy ##########################
[auth.proxy]
enabled = false
header_name = X-WEBAUTH-USER
header_property = username
auto_sign_up = true
sync_ttl = 60
whitelist =
headers =
headers_encoded = false
enable_login_token = false
#################################### Auth JWT ##########################
[auth.jwt]
enabled = false
enable_login_token = false
header_name =
email_claim =
username_claim =
jwk_set_url =
jwk_set_file =
cache_ttl = 60m
expect_claims = {}
key_file =
role_attribute_path =
role_attribute_strict = false
auto_sign_up = false
url_login = false
allow_assign_grafana_admin = false
skip_org_role_sync = false
#################################### Auth LDAP ###########################
[auth.ldap]
enabled = false
config_file = /etc/grafana/ldap.toml
allow_sign_up = true
skip_org_role_sync = false
# LDAP background sync (Enterprise only)
# At 1 am every day
sync_cron = "0 1 * * *"
active_sync_enabled = true
#################################### AWS ###########################
[aws]
# Enter a comma-separated list of allowed AWS authentication providers.
# Options are: default (AWS SDK Default), keys (Access && secret key), credentials (Credentials field), ec2_iam_role (EC2 IAM Role)
allowed_auth_providers = default,keys,credentials
# Allow AWS users to assume a role using temporary security credentials.
# If true, assume role will be enabled for all AWS authentication providers that are specified in aws_auth_providers
assume_role_enabled = true
# Specify max no of pages to be returned by the ListMetricPages API
list_metrics_page_limit = 500
#################################### Azure ###############################
[azure]
# Azure cloud environment where Grafana is hosted
# Possible values are AzureCloud, AzureChinaCloud, AzureUSGovernment and AzureGermanCloud
# Default value is AzureCloud (i.e. public cloud)
cloud = AzureCloud
# Specifies whether Grafana hosted in Azure service with Managed Identity configured (e.g. Azure Virtual Machines instance)
# If enabled, the managed identity can be used for authentication of Grafana in Azure services
# Disabled by default, needs to be explicitly enabled
managed_identity_enabled = false
# Client ID to use for user-assigned managed identity
# Should be set for user-assigned identity and should be empty for system-assigned identity
managed_identity_client_id =
# Specifies whether user identity authentication (on behalf of currently signed-in user) should be enabled in datasources
# that support it (requires AAD authentication)
# Disabled by default, needs to be explicitly enabled
user_identity_enabled = false
# Override token URL for Azure Active Directory
# By default is the same as token URL configured for AAD authentication settings
user_identity_token_url =
# Override ADD application ID which would be used to exchange users token to an access token for the datasource
# By default is the same as used in AAD authentication or can be set to another application (for OBO flow)
user_identity_client_id =
# Override the AAD application client secret
# By default is the same as used in AAD authentication or can be set to another application (for OBO flow)
user_identity_client_secret =
#################################### Role-based Access Control ###########
[rbac]
# If enabled, cache permissions in a in memory cache
permission_cache = true
# Reset basic roles permissions on boot
# Warning left to true, basic roles permissions will be reset on every boot
reset_basic_roles = false
#################################### SMTP / Emailing #####################
[smtp]
enabled = false
host = localhost:25
user =
# If the password contains # or ; you have to wrap it with triple quotes. Ex """#password;"""
password =
cert_file =
key_file =
skip_verify = false
from_address = admin@grafana.localhost
from_name = Grafana
ehlo_identity =
startTLS_policy =
[emails]
welcome_email_on_sign_up = false
templates_pattern = emails/*.html, emails/*.txt
content_types = text/html
#################################### Logging ##########################
[log]
# Either "console", "file", "syslog". Default is console and file
# Use space to separate multiple modes, e.g. "console file"
mode = console file
# Either "debug", "info", "warn", "error", "critical", default is "info"
#level = info
level = warn
# optional settings to set different levels for specific loggers. Ex filters = sqlstore:debug
filters =
# For "console" mode only
[log.console]
level =
# log line format, valid options are text, console and json
format = console
# For "file" mode only
[log.file]
level =
# log line format, valid options are text, console and json
format = text
# This enables automated log rotate(switch of following options), default is true
log_rotate = true
# Max line number of single file, default is 1000000
max_lines = 1000000
# Max size shift of single file, default is 28 means 1 << 28, 256MB
max_size_shift = 28
# Segment log daily, default is true
daily_rotate = true
# Expired days of log file(delete after max days), default is 7
max_days = 7
[log.syslog]
level =
# log line format, valid options are text, console and json
format = text
# Syslog network type and address. This can be udp, tcp, or unix. If left blank, the default unix endpoints will be used.
network =
address =
# Syslog facility. user, daemon and local0 through local7 are valid.
facility =
# Syslog tag. By default, the process' argv[0] is used.
tag =
[log.frontend]
# Should Faro javascript agent be initialized
enabled = false
# Custom HTTP endpoint to send events to. Default will log the events to stdout.
custom_endpoint =
# Requests per second limit enforced per an extended period, for Grafana backend log ingestion endpoint (/log).
log_endpoint_requests_per_second_limit = 3
# Max requests accepted per short interval of time for Grafana backend log ingestion endpoint (/log)
log_endpoint_burst_limit = 15
# Should error instrumentation be enabled, only affects Grafana Javascript Agent
instrumentations_errors_enabled = true
# Should console instrumentation be enabled, only affects Grafana Javascript Agent
instrumentations_console_enabled = false
# Should webvitals instrumentation be enabled, only affects Grafana Javascript Agent
instrumentations_webvitals_enabled = false
# Api Key, only applies to Grafana Javascript Agent provider
api_key =
#################################### Usage Quotas ########################
[quota]
enabled = false
#### set quotas to -1 to make unlimited. ####
# limit number of users per Org.
org_user = 10
# limit number of dashboards per Org.
org_dashboard = 100
# limit number of data_sources per Org.
org_data_source = 10
# limit number of api_keys per Org.
org_api_key = 10
# limit number of alerts per Org.
org_alert_rule = 100
# limit number of orgs a user can create.
user_org = 10
# Global limit of users.
global_user = -1
# global limit of orgs.
global_org = -1
# global limit of dashboards
global_dashboard = -1
# global limit of api_keys
global_api_key = -1
# global limit on number of logged in users.
global_session = -1
# global limit of alerts
global_alert_rule = -1
# global limit of files uploaded to the SQL DB
global_file = 1000
# global limit of correlations
global_correlations = -1
#################################### Unified Alerting ####################
[unified_alerting]
# Enable the Unified Alerting sub-system and interface. When enabled we'll migrate all of your alert rules and notification channels to the new system. New alert rules will be created and your notification channels will be converted into an Alertmanager configuration. Previous data is preserved to enable backwards compatibility but new data is removed when switching. When this configuration section and flag are not defined, the state is defined at runtime. See the documentation for more details.
enabled =
# Comma-separated list of organization IDs for which to disable unified alerting. Only supported if unified alerting is enabled.
disabled_orgs =
# Specify the frequency of polling for admin config changes.
# The interval string is a possibly signed sequence of decimal numbers, followed by a unit suffix (ms, s, m, h, d), e.g. 30s or 1m.
admin_config_poll_interval = 60s
# Specify the frequency of polling for Alertmanager config changes.
# The interval string is a possibly signed sequence of decimal numbers, followed by a unit suffix (ms, s, m, h, d), e.g. 30s or 1m.
alertmanager_config_poll_interval = 60s
# The redis server address that should be connected to.
ha_redis_address =
# The username that should be used to authenticate with the redis server.
ha_redis_username =
# The password that should be used to authenticate with the redis server.
ha_redis_password =
# The redis database, by default it's 0.
ha_redis_db =
# A prefix that is used for every key or channel that is created on the redis server
# as part of HA for alerting.
ha_redis_prefix =
# The name of the cluster peer that will be used as identifier. If none is
# provided, a random one will be generated.
ha_redis_peer_name =
# Listen address/hostname and port to receive unified alerting messages for other Grafana instances. The port is used for both TCP and UDP. It is assumed other Grafana instances are also running on the same port.
ha_listen_address = "0.0.0.0:9094"
# Explicit address/hostname and port to advertise other Grafana instances. The port is used for both TCP and UDP.
ha_advertise_address = ""
# Comma-separated list of initial instances (in a format of host:port) that will form the HA cluster. Configuring this setting will enable High Availability mode for alerting.
ha_peers = ""
# Time to wait for an instance to send a notification via the Alertmanager. In HA, each Grafana instance will
# be assigned a position (e.g. 0, 1). We then multiply this position with the timeout to indicate how long should
# each instance wait before sending the notification to take into account replication lag.
# The interval string is a possibly signed sequence of decimal numbers, followed by a unit suffix (ms, s, m, h, d), e.g. 30s or 1m.
ha_peer_timeout = 15s
# The label is an optional string to include on each packet and stream.
# It uniquely identifies the cluster and prevents cross-communication
# issues when sending gossip messages in an enviromenet with multiple clusters.
ha_label =
# The interval between sending gossip messages. By lowering this value (more frequent) gossip messages are propagated
# across cluster more quickly at the expense of increased bandwidth usage.
# The interval string is a possibly signed sequence of decimal numbers, followed by a unit suffix (ms, s, m, h, d), e.g. 30s or 1m.
ha_gossip_interval = 200ms
# The interval between gossip full state syncs. Setting this interval lower (more frequent) will increase convergence speeds
# across larger clusters at the expense of increased bandwidth usage.
# The interval string is a possibly signed sequence of decimal numbers, followed by a unit suffix (ms, s, m, h, d), e.g. 30s or 1m.
ha_push_pull_interval = 60s
# Enable or disable alerting rule execution. The alerting UI remains visible. This option has a legacy version in the `[alerting]` section that takes precedence.
execute_alerts = true
# Alert evaluation timeout when fetching data from the datasource. This option has a legacy version in the `[alerting]` section that takes precedence.
# The timeout string is a possibly signed sequence of decimal numbers, followed by a unit suffix (ms, s, m, h, d), e.g. 30s or 1m.
evaluation_timeout = 30s
# Number of times we'll attempt to evaluate an alert rule before giving up on that evaluation. This option has a legacy version in the `[alerting]` section that takes precedence.
max_attempts = 3
# Minimum interval to enforce between rule evaluations. Rules will be adjusted if they are less than this value or if they are not multiple of the scheduler interval (10s). Higher values can help with resource management as we'll schedule fewer evaluations over time. This option has a legacy version in the `[alerting]` section that takes precedence.
# The interval string is a possibly signed sequence of decimal numbers, followed by a unit suffix (ms, s, m, h, d), e.g. 30s or 1m.
min_interval = 10s
[unified_alerting.screenshots]
# Enable screenshots in notifications. You must have either installed the Grafana image rendering
# plugin, or set up Grafana to use a remote rendering service.
# For more information on configuration options, refer to [rendering].
capture = false
# The timeout for capturing screenshots. If a screenshot cannot be captured within the timeout then
# the notification is sent without a screenshot. The maximum duration is 30 seconds. This timeout
# should be less than the minimum Interval of all Evaluation Groups to avoid back pressure on alert
# rule evaluation.
capture_timeout = 10s
# The maximum number of screenshots that can be taken at the same time. This option is different from
# concurrent_render_request_limit as max_concurrent_screenshots sets the number of concurrent screenshots
# that can be taken at the same time for all firing alerts where as concurrent_render_request_limit sets
# the total number of concurrent screenshots across all Grafana services.
max_concurrent_screenshots = 5
# Uploads screenshots to the local Grafana server or remote storage such as Azure, S3 and GCS. Please
# see [external_image_storage] for further configuration options. If this option is false then
# screenshots will be persisted to disk for up to temp_data_lifetime.
upload_external_image_storage = false
[unified_alerting.reserved_labels]
# Comma-separated list of reserved labels added by the Grafana Alerting engine that should be disabled.
# For example: `disabled_labels=grafana_folder`
disabled_labels =
[unified_alerting.state_history]
# Enable the state history functionality in Unified Alerting. The previous states of alert rules will be visible in panels and in the UI.
enabled = true
# Select which pluggable state history backend to use. Either "annotations", "loki", or "multiple"
# "loki" writes state history to an external Loki instance. "multiple" allows history to be written to multiple backends at once.
# Defaults to "annotations".
backend =
# For "multiple" only.
# Indicates the main backend used to serve state history queries.
# Either "annotations" or "loki"
primary =
# For "multiple" only.
# Comma-separated list of additional backends to write state history data to.
secondaries =
# For "loki" only.
# URL of the external Loki instance.
# Either "loki_remote_url", or both of "loki_remote_read_url" and "loki_remote_write_url" is required for the "loki" backend.
loki_remote_url =
# For "loki" only.
# URL of the external Loki's read path. To be used in configurations where Loki has separated read and write URLs.
# Either "loki_remote_url", or both of "loki_remote_read_url" and "loki_remote_write_url" is required for the "loki" backend.
loki_remote_read_url =
# For "loki" only.
# URL of the external Loki's write path. To be used in configurations where Loki has separated read and write URLs.
# Either "loki_remote_url", or both of "loki_remote_read_url" and "loki_remote_write_url" is required for the "loki" backend.
loki_remote_write_url =
# For "loki" only.
# Optional tenant ID to attach to requests sent to Loki.
loki_tenant_id =
# For "loki" only.
# Optional username for basic authentication on requests sent to Loki. Can be left blank to disable basic auth.
loki_basic_auth_username =
# For "loki" only.
# Optional password for basic authentication on requests sent to Loki. Can be left blank.
loki_basic_auth_password =
[unified_alerting.state_history.external_labels]
# Optional extra labels to attach to outbound state history records or log streams.
# Any number of label key-value-pairs can be provided.
#
# ex.
# mylabelkey = mylabelvalue
#################################### Alerting ############################
[alerting]
# Enable the legacy alerting sub-system and interface. If Unified Alerting is already enabled and you try to go back to legacy alerting, all data that is part of Unified Alerting will be deleted. When this configuration section and flag are not defined, the state is defined at runtime. See the documentation for more details.
enabled =
# Makes it possible to turn off alert execution but alerting UI is visible
execute_alerts = true
# Default setting for new alert rules. Defaults to categorize error and timeouts as alerting. (alerting, keep_state)
error_or_timeout = alerting
# Default setting for how Grafana handles nodata or null values in alerting. (alerting, no_data, keep_state, ok)
nodata_or_nullvalues = no_data
# Alert notifications can include images, but rendering many images at the same time can overload the server
# This limit will protect the server from render overloading and make sure notifications are sent out quickly
concurrent_render_limit = 5
# Default setting for alert calculation timeout. Default value is 30
evaluation_timeout_seconds = 30
# Default setting for alert notification timeout. Default value is 30
notification_timeout_seconds = 30
# Default setting for max attempts to sending alert notifications. Default value is 3
max_attempts = 3
# Makes it possible to enforce a minimal interval between evaluations, to reduce load on the backend
min_interval_seconds = 1
# Configures for how long alert annotations are stored. Default is 0, which keeps them forever.
# This setting should be expressed as an duration. Ex 6h (hours), 10d (days), 2w (weeks), 1M (month).
max_annotation_age =
# Configures max number of alert annotations that Grafana stores. Default value is 0, which keeps all alert annotations.
max_annotations_to_keep =
#################################### Annotations #########################
[annotations]
# Configures the batch size for the annotation clean-up job. This setting is used for dashboard, API, and alert annotations.
cleanupjob_batchsize = 100
# Enforces the maximum allowed length of the tags for any newly introduced annotations. It can be between 500 and 4096 inclusive (which is the respective's column length). Default value is 500.
# Setting it to a higher value would impact performance therefore is not recommended.
tags_length = 500
[annotations.dashboard]
# Dashboard annotations means that annotations are associated with the dashboard they are created on.
# Configures how long dashboard annotations are stored. Default is 0, which keeps them forever.
# This setting should be expressed as a duration. Examples: 6h (hours), 10d (days), 2w (weeks), 1M (month).
max_age =
# Configures max number of dashboard annotations that Grafana stores. Default value is 0, which keeps all dashboard annotations.
max_annotations_to_keep =
[annotations.api]
# API annotations means that the annotations have been created using the API without any
# association with a dashboard.
# Configures how long Grafana stores API annotations. Default is 0, which keeps them forever.
# This setting should be expressed as a duration. Examples: 6h (hours), 10d (days), 2w (weeks), 1M (month).
max_age =
# Configures max number of API annotations that Grafana keeps. Default value is 0, which keeps all API annotations.
max_annotations_to_keep =
#################################### Explore #############################
[explore]
# Enable the Explore section
enabled = true
#################################### Help #############################
[help]
# Enable the Help section
enabled = true
#################################### Profile #############################
[profile]
# Enable the Profile section
enabled = true
#################################### Query History #############################
[query_history]
# Enable the Query history
enabled = true
#################################### Internal Grafana Metrics ############
# Metrics available at HTTP URL /metrics and /metrics/plugins/:pluginId
[metrics]
enabled = true
interval_seconds = 10
# Disable total stats (stat_totals_*) metrics to be generated
disable_total_stats = false
#If both are set, basic auth will be required for the metrics endpoints.
basic_auth_username =
basic_auth_password =
# Metrics environment info adds dimensions to the `grafana_environment_info` metric, which
# can expose more information about the Grafana instance.
[metrics.environment_info]
#exampleLabel1 = exampleValue1
#exampleLabel2 = exampleValue2
# Send internal Grafana metrics to graphite
[metrics.graphite]
# Enable by setting the address setting (ex localhost:2003)
address =
prefix = prod.grafana.%(instance_name)s.
#################################### Grafana.com integration ##########################
[grafana_net]
url = https://grafana.com
[grafana_com]
url = https://grafana.com
api_url = https://grafana.com/api
#################################### Distributed tracing ############
# Opentracing is deprecated use opentelemetry instead
[tracing.jaeger]
# jaeger destination (ex localhost:6831)
address =
# tag that will always be included in when creating new spans. ex (tag1:value1,tag2:value2)
always_included_tag =
# Type specifies the type of the sampler: const, probabilistic, rateLimiting, or remote
sampler_type = const
# jaeger samplerconfig param
# for "const" sampler, 0 or 1 for always false/true respectively
# for "probabilistic" sampler, a probability between 0 and 1
# for "rateLimiting" sampler, the number of spans per second
# for "remote" sampler, param is the same as for "probabilistic"
# and indicates the initial sampling rate before the actual one
# is received from the mothership
sampler_param = 1
# sampling_server_url is the URL of a sampling manager providing a sampling strategy.
sampling_server_url =
# Whether or not to use Zipkin span propagation (x-b3- HTTP headers).
zipkin_propagation = false
# Setting this to true disables shared RPC spans.
# Not disabling is the most common setting when using Zipkin elsewhere in your infrastructure.
disable_shared_zipkin_spans = false
[tracing.opentelemetry]
# attributes that will always be included in when creating new spans. ex (key1:value1,key2:value2)
custom_attributes =
[tracing.opentelemetry.jaeger]
# jaeger destination (ex http://localhost:14268/api/traces)
address =
# Propagation specifies the text map propagation format: w3c, jaeger
propagation =
# This is a configuration for OTLP exporter with GRPC protocol
[tracing.opentelemetry.otlp]
# otlp destination (ex localhost:4317)
address =
# Propagation specifies the text map propagation format: w3c, jaeger
propagation =
#################################### External Image Storage ##############
[external_image_storage]
# Used for uploading images to public servers so they can be included in slack/email messages.
# You can choose between (s3, webdav, gcs, azure_blob, local)
provider =
[external_image_storage.s3]
endpoint =
path_style_access =
bucket_url =
bucket =
region =
path =
access_key =
secret_key =
[external_image_storage.webdav]
url =
username =
password =
public_url =
[external_image_storage.gcs]
key_file =
bucket =
path =
enable_signed_urls = false
signed_url_expiration =
[external_image_storage.azure_blob]
account_name =
account_key =
container_name =
sas_token_expiration_days =
[external_image_storage.local]
# does not require any configuration
[rendering]
# Options to configure a remote HTTP image rendering service, e.g. using https://github.com/grafana/grafana-image-renderer.
# URL to a remote HTTP image renderer service, e.g. http://localhost:8081/render, will enable Grafana to render panels and dashboards to PNG-images using HTTP requests to an external service.
server_url =
# If the remote HTTP image renderer service runs on a different server than the Grafana server you may have to configure this to a URL where Grafana is reachable, e.g. http://grafana.domain/.
callback_url =
# An auth token that will be sent to and verified by the renderer. The renderer will deny any request without an auth token matching the one configured on the renderer side.
renderer_token = -
# Concurrent render request limit affects when the /render HTTP endpoint is used. Rendering many images at the same time can overload the server,
# which this setting can help protect against by only allowing a certain amount of concurrent requests.
concurrent_render_request_limit = 30
# Determines the lifetime of the render key used by the image renderer to access and render Grafana.
# This setting should be expressed as a duration. Examples: 10s (seconds), 5m (minutes), 2h (hours).
# Default is 5m. This should be more than enough for most deployments.
# Change the value only if image rendering is failing and you see `Failed to get the render key from cache` in Grafana logs.
render_key_lifetime = 5m
[panels]
# here for to support old env variables, can remove after a few months
enable_alpha = false
disable_sanitize_html = false
[plugins]
enable_alpha = false
app_tls_skip_verify_insecure = false
# Enter a comma-separated list of plugin identifiers to identify plugins to load even if they are unsigned. Plugins with modified signatures are never loaded.
allow_loading_unsigned_plugins =
# Enable or disable installing / uninstalling / updating plugins directly from within Grafana.
plugin_admin_enabled = true
plugin_admin_external_manage_enabled = false
plugin_catalog_url = https://grafana.com/grafana/plugins/
# Enter a comma-separated list of plugin identifiers to hide in the plugin catalog.
plugin_catalog_hidden_plugins =
# Log all backend requests for core and external plugins.
log_backend_requests = false
# Force download of public key for verifying plugin signature on startup.
enforce_public_key_download = false
#################################### Grafana Live ##########################################
[live]
# max_connections to Grafana Live WebSocket endpoint per Grafana server instance. See Grafana Live docs
# if you are planning to make it higher than default 100 since this can require some OS and infrastructure
# tuning. 0 disables Live, -1 means unlimited connections.
max_connections = 100
# allowed_origins is a comma-separated list of origins that can establish connection with Grafana Live.
# If not set then origin will be matched over root_url. Supports wildcard symbol "*".
allowed_origins =
# engine defines an HA (high availability) engine to use for Grafana Live. By default no engine used - in
# this case Live features work only on a single Grafana server.
# Available options: "redis".
# Setting ha_engine is an EXPERIMENTAL feature.
ha_engine =
# ha_engine_address sets a connection address for Live HA engine. Depending on engine type address format can differ.
# For now we only support Redis connection address in "host:port" format.
# This option is EXPERIMENTAL.
ha_engine_address = "127.0.0.1:6379"
#################################### Grafana Image Renderer Plugin ##########################
[plugin.grafana-image-renderer]
# Instruct headless browser instance to use a default timezone when not provided by Grafana, e.g. when rendering panel image of alert.
# See ICU’s metaZones.txt (https://cs.chromium.org/chromium/src/third_party/icu/source/data/misc/metaZones.txt) for a list of supported
# timezone IDs. Fallbacks to TZ environment variable if not set.
rendering_timezone =
# Instruct headless browser instance to use a default language when not provided by Grafana, e.g. when rendering panel image of alert.
# Please refer to the HTTP header Accept-Language to understand how to format this value, e.g. 'fr-CH, fr;q=0.9, en;q=0.8, de;q=0.7, *;q=0.5'.
rendering_language =
# Instruct headless browser instance to use a default device scale factor when not provided by Grafana, e.g. when rendering panel image of alert.
# Default is 1. Using a higher value will produce more detailed images (higher DPI), but will require more disk space to store an image.
rendering_viewport_device_scale_factor =
# Instruct headless browser instance whether to ignore HTTPS errors during navigation. Per default HTTPS errors are not ignored. Due to
# the security risk it's not recommended to ignore HTTPS errors.
rendering_ignore_https_errors =
# Instruct headless browser instance whether to capture and log verbose information when rendering an image. Default is false and will
# only capture and log error messages. When enabled, debug messages are captured and logged as well.
# For the verbose information to be included in the Grafana server log you have to adjust the rendering log level to debug, configure
# [log].filter = rendering:debug.
rendering_verbose_logging =
# Instruct headless browser instance whether to output its debug and error messages into running process of remote rendering service.
# Default is false. This can be useful to enable (true) when troubleshooting.
rendering_dumpio =
# Additional arguments to pass to the headless browser instance. Default is --no-sandbox. The list of Chromium flags can be found
# here (https://peter.sh/experiments/chromium-command-line-switches/). Multiple arguments is separated with comma-character.
rendering_args =
# You can configure the plugin to use a different browser binary instead of the pre-packaged version of Chromium.
# Please note that this is not recommended, since you may encounter problems if the installed version of Chrome/Chromium is not
# compatible with the plugin.
rendering_chrome_bin =
# Instruct how headless browser instances are created. Default is 'default' and will create a new browser instance on each request.
# Mode 'clustered' will make sure that only a maximum of browsers/incognito pages can execute concurrently.
# Mode 'reusable' will have one browser instance and will create a new incognito page on each request.
rendering_mode =
# When rendering_mode = clustered, you can instruct how many browsers or incognito pages can execute concurrently. Default is 'browser'
# and will cluster using browser instances.
# Mode 'context' will cluster using incognito pages.
rendering_clustering_mode =
# When rendering_mode = clustered, you can define the maximum number of browser instances/incognito pages that can execute concurrently. Default is '5'.
rendering_clustering_max_concurrency =
# When rendering_mode = clustered, you can specify the duration a rendering request can take before it will time out. Default is `30` seconds.
rendering_clustering_timeout =
# Limit the maximum viewport width, height and device scale factor that can be requested.
rendering_viewport_max_width =
rendering_viewport_max_height =
rendering_viewport_max_device_scale_factor =
# Change the listening host and port of the gRPC server. Default host is 127.0.0.1 and default port is 0 and will automatically assign
# a port not in use.
grpc_host =
grpc_port =
[enterprise]
license_path =
[feature_toggles]
# there are currently two ways to enable feature toggles in the `grafana.ini`.
# you can either pass an array of feature you want to enable to the `enable` field or
# configure each toggle by setting the name of the toggle to true/false. Toggles set to true/false
# will take precedence over toggles in the `enable` list.
# enable = feature1,feature2
enable =
# Some features are enabled by default, see:
# https://grafana.com/docs/grafana/next/setup-grafana/configure-grafana/feature-toggles/
# To enable features by default, set `Expression: "true"` in:
# https://github.com/grafana/grafana/blob/main/pkg/services/featuremgmt/registry.go
# feature1 = true
# feature2 = false
[date_formats]
# For information on what formatting patterns that are supported https://momentjs.com/docs/#/displaying/
# Default system date format used in time range picker and other places where full time is displayed
full_date = YYYY-MM-DD HH:mm:ss
# Used by graph and other places where we only show small intervals
interval_second = HH:mm:ss
interval_minute = HH:mm
interval_hour = MM/DD HH:mm
interval_day = MM/DD
interval_month = YYYY-MM
interval_year = YYYY
# Experimental feature
use_browser_locale = false
# Default timezone for user preferences. Options are 'browser' for the browser local timezone or a timezone name from IANA Time Zone database, e.g. 'UTC' or 'Europe/Amsterdam' etc.
default_timezone = browser
[expressions]
# Enable or disable the expressions functionality.
enabled = true
[geomap]
# Set the JSON configuration for the default basemap
default_baselayer_config =
# Enable or disable loading other base map layers
enable_custom_baselayers = true
#################################### Support Bundles #####################################
[support_bundles]
# Enable support bundle creation (default: true)
enabled = true
# Only server admins can generate and view support bundles (default: true)
server_admin_only = true
# If set, bundles will be encrypted with the provided public keys separated by whitespace
public_keys = ""
#################################### Storage ################################################
[storage]
# Allow uploading SVG files without sanitization.
allow_unsanitized_svg_upload = false
#################################### Search ################################################
[search]
# Defines the number of dashboards loaded at once in a batch during a full reindex.
# This is a temporary settings that might be removed in the future.
dashboard_loading_batch_size = 200
# Defines the frequency of a full search reindex.
# This is a temporary settings that might be removed in the future.
full_reindex_interval = 5m
# Defines the frequency of partial index updates based on recent changes such as dashboard updates.
# This is a temporary settings that might be removed in the future.
index_update_interval = 10s
# Move an app plugin referenced by its id (including all its pages) to a specific navigation section
# Format: <Plugin ID> = <Section ID> <Sort Weight>
[navigation.app_sections]
# Move a specific app plugin page (referenced by its `path` field) to a specific navigation section
# Format: <Page URL> = <Section ID> <Sort Weight>
[navigation.app_standalone_pages]
#################################### Secure Socks5 Datasource Proxy #####################################
[secure_socks_datasource_proxy]
enabled = false
root_ca_cert =
client_key =
client_cert =
server_name =
# The address of the socks5 proxy datasources should connect to
proxy_address =
conf/alertmanager/rules.yml
[Fichier]
Vous n’aurez peut-être pas besoin de l’ensemble de ces alertes mais elle constituent une bonne base de suivi.
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
# 2023-05-28
groups:
- name: Alerts
rules:
# Host out of memory
- alert: HostOutOfMemory
expr: (node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes * 100 < 10) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
for: 2m
labels:
severity: warning
annotations:
summary: Host out of memory (instance {{ $labels.instance }})
description: "Node memory is filling up (< 10% left)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# Host memory under memory pressure
- alert: HostMemoryUnderMemoryPressure
expr: (rate(node_vmstat_pgmajfault[1m]) > 1000) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
for: 2m
labels:
severity: warning
annotations:
summary: Host memory under memory pressure (instance {{ $labels.instance }})
description: "The node is under heavy memory pressure. High rate of major page faults\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# Host Memory is under utilized
# You may want to increase the alert manager 'repeat_interval' for this type of alert to daily or weekly
- alert: HostMemoryIsUnderUtilized
expr: (100 - (rate(node_memory_MemAvailable_bytes[30m]) / node_memory_MemTotal_bytes * 100) < 20) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
for: 1w
labels:
severity: info
annotations:
summary: Host Memory is under utilized (instance {{ $labels.instance }})
description: "Node memory is < 20% for 1 week. Consider reducing memory space.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# Host unusual network throughput in
- alert: HostUnusualNetworkThroughputIn
expr: (sum by (instance) (rate(node_network_receive_bytes_total[2m])) / 1024 / 1024 > 100) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
for: 5m
labels:
severity: warning
annotations:
summary: Host unusual network throughput in (instance {{ $labels.instance }})
description: "Host network interfaces are probably receiving too much data (> 100 MB/s)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# Host unusual network throughput out
- alert: HostUnusualNetworkThroughputOut
expr: (sum by (instance) (rate(node_network_transmit_bytes_total[2m])) / 1024 / 1024 > 100) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
for: 5m
labels:
severity: warning
annotations:
summary: Host unusual network throughput out (instance {{ $labels.instance }})
description: "Host network interfaces are probably sending too much data (> 100 MB/s)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# Host unusual disk read rate
- alert: HostUnusualDiskReadRate
expr: (sum by (instance) (rate(node_disk_read_bytes_total[2m])) / 1024 / 1024 > 50) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
for: 5m
labels:
severity: warning
annotations:
summary: Host unusual disk read rate (instance {{ $labels.instance }})
description: "Disk is probably reading too much data (> 50 MB/s)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# Host unusual disk write rate
- alert: HostUnusualDiskWriteRate
expr: (sum by (instance) (rate(node_disk_written_bytes_total[2m])) / 1024 / 1024 > 50) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
for: 2m
labels:
severity: warning
annotations:
summary: Host unusual disk write rate (instance {{ $labels.instance }})
description: "Disk is probably writing too much data (> 50 MB/s)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# Host out of disk space
# Please add ignored mountpoints in node_exporter parameters like
# "--collector.filesystem.ignored-mount-points=^/(sys|proc|dev|run)($|/)".
# Same rule using "node_filesystem_free_bytes" will fire when disk fills for non-root users.
- alert: HostOutOfDiskSpace
expr: ((node_filesystem_avail_bytes * 100) / node_filesystem_size_bytes < 10 and ON (instance, device, mountpoint) node_filesystem_readonly == 0) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
for: 2m
labels:
severity: warning
annotations:
summary: Host out of disk space (instance {{ $labels.instance }})
description: "Disk is almost full (< 10% left)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# Host disk will fill in 24 hours
# Please add ignored mountpoints in node_exporter parameters like
# "--collector.filesystem.ignored-mount-points=^/(sys|proc|dev|run)($|/)".
# Same rule using "node_filesystem_free_bytes" will fire when disk fills for non-root users.
- alert: HostDiskWillFillIn24Hours
expr: ((node_filesystem_avail_bytes * 100) / node_filesystem_size_bytes < 10 and ON (instance, device, mountpoint) predict_linear(node_filesystem_avail_bytes{fstype!~"tmpfs"}[1h], 24 * 3600) < 0 and ON (instance, device, mountpoint) node_filesystem_readonly == 0) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
for: 2m
labels:
severity: warning
annotations:
summary: Host disk will fill in 24 hours (instance {{ $labels.instance }})
description: "Filesystem is predicted to run out of space within the next 24 hours at current write rate\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# Host out of inodes
- alert: HostOutOfInodes
expr: (node_filesystem_files_free / node_filesystem_files * 100 < 10 and ON (instance, device, mountpoint) node_filesystem_readonly == 0) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
for: 2m
labels:
severity: warning
annotations:
summary: Host out of inodes (instance {{ $labels.instance }})
description: "Disk is almost running out of available inodes (< 10% left)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# Host inodes will fill in 24 hours
- alert: HostInodesWillFillIn24Hours
expr: (node_filesystem_files_free / node_filesystem_files * 100 < 10 and predict_linear(node_filesystem_files_free[1h], 24 * 3600) < 0 and ON (instance, device, mountpoint) node_filesystem_readonly == 0) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
for: 2m
labels:
severity: warning
annotations:
summary: Host inodes will fill in 24 hours (instance {{ $labels.instance }})
description: "Filesystem is predicted to run out of inodes within the next 24 hours at current write rate\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# Host unusual disk read latency
- alert: HostUnusualDiskReadLatency
expr: (rate(node_disk_read_time_seconds_total[1m]) / rate(node_disk_reads_completed_total[1m]) > 0.1 and rate(node_disk_reads_completed_total[1m]) > 0) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
for: 2m
labels:
severity: warning
annotations:
summary: Host unusual disk read latency (instance {{ $labels.instance }})
description: "Disk latency is growing (read operations > 100ms)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# Host unusual disk write latency
- alert: HostUnusualDiskWriteLatency
expr: (rate(node_disk_write_time_seconds_total[1m]) / rate(node_disk_writes_completed_total[1m]) > 0.1 and rate(node_disk_writes_completed_total[1m]) > 0) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
for: 2m
labels:
severity: warning
annotations:
summary: Host unusual disk write latency (instance {{ $labels.instance }})
description: "Disk latency is growing (write operations > 100ms)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# Host high CPU
- alert: HostHighCpuLoad
expr: (sum by (instance) (avg by (mode, instance) (rate(node_cpu_seconds_total{mode!="idle"}[2m]))) > 0.8) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
for: 0m
labels:
severity: warning
annotations:
summary: Host high CPU load (instance {{ $labels.instance }})
description: "CPU load is > 80%\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# Host CPU is under utilized
# You may want to increase the alert manager 'repeat_interval' for this type of alert to daily or weekly
- alert: HostCpuIsUnderUtilized
expr: (100 - (rate(node_cpu_seconds_total{mode="idle"}[30m]) * 100) < 20) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
for: 1w
labels:
severity: info
annotations:
summary: Host CPU is under utilized (instance {{ $labels.instance }})
description: "CPU load is < 20% for 1 week. Consider reducing the number of CPUs.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# Host CPU steal noisy neighbor
- alert: HostCpuStealNoisyNeighbor
expr: (avg by(instance) (rate(node_cpu_seconds_total{mode="steal"}[5m])) * 100 > 10) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
for: 0m
labels:
severity: warning
annotations:
summary: Host CPU steal noisy neighbor (instance {{ $labels.instance }})
description: "CPU steal is > 10%. A noisy neighbor is killing VM performances or a spot instance may be out of credit.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# Host CPU high iowait
- alert: HostCpuHighIowait
expr: (avg by (instance) (rate(node_cpu_seconds_total{mode="iowait"}[5m])) * 100 > 10) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
for: 0m
labels:
severity: warning
annotations:
summary: Host CPU high iowait (instance {{ $labels.instance }})
description: "CPU iowait > 10%. A high iowait means that you are disk or network bound.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# Host unusual disk IO
- alert: HostUnusualDiskIo
expr: (rate(node_disk_io_time_seconds_total[1m]) > 0.5) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
for: 5m
labels:
severity: warning
annotations:
summary: Host unusual disk IO (instance {{ $labels.instance }})
description: "Time spent in IO is too high on {{ $labels.instance }}. Check storage for issues.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
## Host context switching
# # 1000 context switches is an arbitrary number.
# # Alert threshold depends on nature of application.
# # Please read: https://github.com/samber/awesome-prometheus-alerts/issues/58
# - alert: HostContextSwitching
# expr: ((rate(node_context_switches_total[5m])) / (count without(cpu, mode) (node_cpu_seconds_total{mode="idle"})) > 1000) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
# for: 0m
# labels:
# severity: warning
# annotations:
# summary: Host context switching (instance {{ $labels.instance }})
# description: "Context switching is growing on node (> 1000 / s)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# Host swap is filling up
- alert: HostSwapIsFillingUp
expr: ((1 - (node_memory_SwapFree_bytes / node_memory_SwapTotal_bytes)) * 100 > 80) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
for: 2m
labels:
severity: warning
annotations:
summary: Host swap is filling up (instance {{ $labels.instance }})
description: "Swap is filling up (>80%)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# Host systemd service crashed
- alert: HostSystemdServiceCrashed
expr: (node_systemd_unit_state{state="failed"} == 1) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
for: 0m
labels:
severity: warning
annotations:
summary: Host systemd service crashed (instance {{ $labels.instance }})
description: "systemd service crashed\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# Host kernel version deviations
- alert: HostKernelVersionDeviations
expr: (count(sum(label_replace(node_uname_info, "kernel", "$1", "release", "([0-9]+.[0-9]+.[0-9]+).*")) by (kernel)) > 1) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
for: 6h
labels:
severity: warning
annotations:
summary: Host kernel version deviations (instance {{ $labels.instance }})
description: "Different kernel versions are running\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# Host OOM kill detected
- alert: HostOomKillDetected
expr: (increase(node_vmstat_oom_kill[1m]) > 0) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
for: 0m
labels:
severity: warning
annotations:
summary: Host OOM kill detected (instance {{ $labels.instance }})
description: "OOM kill detected\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# Host Network Receive Errors
- alert: HostNetworkReceiveErrors
expr: (rate(node_network_receive_errs_total[2m]) / rate(node_network_receive_packets_total[2m]) > 0.01) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
for: 2m
labels:
severity: warning
annotations:
summary: Host Network Receive Errors (instance {{ $labels.instance }})
description: "Host {{ $labels.instance }} interface {{ $labels.device }} has encountered {{ printf \"%.0f\" $value }} receive errors in the last two minutes.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# Host Network Transmit Errors
- alert: HostNetworkTransmitErrors
expr: (rate(node_network_transmit_errs_total[2m]) / rate(node_network_transmit_packets_total[2m]) > 0.01) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
for: 2m
labels:
severity: warning
annotations:
summary: Host Network Transmit Errors (instance {{ $labels.instance }})
description: "Host {{ $labels.instance }} interface {{ $labels.device }} has encountered {{ printf \"%.0f\" $value }} transmit errors in the last two minutes.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# Host Network Interface Saturated
- alert: HostNetworkInterfaceSaturated
expr: ((rate(node_network_receive_bytes_total{device!~"^tap.*|^vnet.*|^veth.*|^tun.*"}[1m]) + rate(node_network_transmit_bytes_total{device!~"^tap.*|^vnet.*|^veth.*|^tun.*"}[1m])) / node_network_speed_bytes{device!~"^tap.*|^vnet.*|^veth.*|^tun.*"} > 0.8 < 10000) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
for: 1m
labels:
severity: warning
annotations:
summary: Host Network Interface Saturated (instance {{ $labels.instance }})
description: "The network interface \"{{ $labels.device }}\" on \"{{ $labels.instance }}\" is getting overloaded.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# Host Network Bond Degraded
- alert: HostNetworkBondDegraded
expr: ((node_bonding_active - node_bonding_slaves) != 0) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
for: 2m
labels:
severity: warning
annotations:
summary: Host Network Bond Degraded (instance {{ $labels.instance }})
description: "Bond \"{{ $labels.device }}\" degraded on \"{{ $labels.instance }}\".\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# Host conntrack limit
- alert: HostConntrackLimit
expr: (node_nf_conntrack_entries / node_nf_conntrack_entries_limit > 0.8) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
for: 5m
labels:
severity: warning
annotations:
summary: Host conntrack limit (instance {{ $labels.instance }})
description: "The number of conntrack is approaching limit\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# Host clock skew
- alert: HostClockSkew
expr: ((node_timex_offset_seconds > 0.05 and deriv(node_timex_offset_seconds[5m]) >= 0) or (node_timex_offset_seconds < -0.05 and deriv(node_timex_offset_seconds[5m]) <= 0)) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
for: 2m
labels:
severity: warning
annotations:
summary: Host clock skew (instance {{ $labels.instance }})
description: "Clock skew detected. Clock is out of sync. Ensure NTP is configured correctly on this host.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# Host clock not synchronising
- alert: HostClockNotSynchronising
expr: (min_over_time(node_timex_sync_status[1m]) == 0 and node_timex_maxerror_seconds >= 16) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
for: 2m
labels:
severity: warning
annotations:
summary: Host clock not synchronising (instance {{ $labels.instance }})
description: "Clock not synchronising. Ensure NTP is configured on this host.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# Host requires reboot
- alert: HostRequiresReboot
expr: (node_reboot_required > 0) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
for: 4h
labels:
severity: info
annotations:
summary: Host requires reboot (instance {{ $labels.instance }})
description: "{{ $labels.instance }} requires a reboot.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
## Container killed
# # This rule can be very noisy in dynamic infra with legitimate container start/stop/deployment.
# - alert: ContainerKilled
# expr: time() - container_last_seen > 60
# for: 0m
# labels:
# severity: warning
# annotations:
# summary: Container killed (instance {{ $labels.instance }})
# description: "A container has disappeared\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# Container CPU usage
- alert: ContainerCpuUsage
expr: (sum(rate(container_cpu_usage_seconds_total{name!=""}[3m])) BY (instance, name) * 100) > 80
for: 2m
labels:
severity: warning
annotations:
summary: Container CPU usage (instance {{ $labels.instance }})
description: "Container CPU usage is above 80%\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# Container Memory usage
# See https://medium.com/faun/how-much-is-too-much-the-linux-oomkiller-and-used-memory-d32186f29c9d
- alert: ContainerMemoryUsage
expr: (sum(container_memory_working_set_bytes{name!=""}) BY (instance, name) / sum(container_spec_memory_limit_bytes > 0) BY (instance, name) * 100) > 80
for: 2m
labels:
severity: warning
annotations:
summary: Container Memory usage (instance {{ $labels.instance }})
description: "Container Memory usage is above 80%\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# Container Volume usage
- alert: ContainerVolumeUsage
expr: (1 - (sum(container_fs_inodes_free{name!=""}) BY (instance) / sum(container_fs_inodes_total) BY (instance))) * 100 > 80
for: 2m
labels:
severity: warning
annotations:
summary: Container Volume usage (instance {{ $labels.instance }})
description: "Container Volume usage is above 80%\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# Container high throttle rate
- alert: ContainerHighThrottleRate
expr: rate(container_cpu_cfs_throttled_seconds_total[3m]) > 1
for: 2m
labels:
severity: warning
annotations:
summary: Container high throttle rate (instance {{ $labels.instance }})
description: "Container is being throttled\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# Container Low CPU utilization
- alert: ContainerLowCpuUtilization
expr: (sum(rate(container_cpu_usage_seconds_total{name!=""}[3m])) BY (instance, name) * 100) < 20
for: 7d
labels:
severity: info
annotations:
summary: Container Low CPU utilization (instance {{ $labels.instance }})
description: "Container CPU utilization is under 20% for 1 week. Consider reducing the allocated CPU.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# ContainerLowMemoryUsage
- alert: ContainerLowMemoryUsage
expr: (sum(container_memory_working_set_bytes{name!=""}) BY (instance, name) / sum(container_spec_memory_limit_bytes > 0) BY (instance, name) * 100) < 20
for: 7d
labels:
severity: info
annotations:
summary: Container Low Memory usage (instance {{ $labels.instance }})
description: "Container Memory usage is under 20% for 1 week. Consider reducing the allocated memory.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# Traefik service down
- alert: TraefikServiceDown
expr: count(traefik_service_server_up) by (service) == 0
for: 0m
labels:
severity: critical
annotations:
summary: Traefik service down (instance {{ $labels.instance }})
description: "All Traefik services are down\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# Traefik high HTTP 4xx error rate service
- alert: TraefikHighHttp4xxErrorRateService
expr: sum(rate(traefik_service_requests_total{code=~"4.*"}[3m])) by (service) / sum(rate(traefik_service_requests_total[3m])) by (service) * 100 > 10
for: 1m
labels:
severity: critical
annotations:
summary: Traefik high HTTP 4xx error rate service (instance {{ $labels.instance }})
description: "Traefik service 4xx error rate is above 10%\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# Traefik high HTTP 5xx error rate service
- alert: TraefikHighHttp5xxErrorRateService
expr: sum(rate(traefik_service_requests_total{code=~"5.*"}[3m])) by (service) / sum(rate(traefik_service_requests_total[3m])) by (service) * 100 > 10
for: 1m
labels:
severity: critical
annotations:
summary: Traefik high HTTP 5xx error rate service (instance {{ $labels.instance }})
description: "Traefik service 5xx error rate is above 10%\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# MySQL down
- alert: MysqlDown
expr: mysql_up == 0
for: 0m
labels:
severity: critical
annotations:
summary: MySQL down (instance {{ $labels.instance }})
description: "MySQL instance is down on {{ $labels.instance }}\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# MySQL too many connections (> 80%)
- alert: MysqlTooManyConnections(>80%)
expr: max_over_time(mysql_global_status_threads_connected[1m]) / mysql_global_variables_max_connections * 100 > 80
for: 2m
labels:
severity: warning
annotations:
summary: MySQL too many connections (> 80%) (instance {{ $labels.instance }})
description: "More than 80% of MySQL connections are in use on {{ $labels.instance }}\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# MySQL high threads running
- alert: MysqlHighThreadsRunning
expr: max_over_time(mysql_global_status_threads_running[1m]) / mysql_global_variables_max_connections * 100 > 60
for: 2m
labels:
severity: warning
annotations:
summary: MySQL high threads running (instance {{ $labels.instance }})
description: "More than 60% of MySQL connections are in running state on {{ $labels.instance }}\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# MySQL slow queries
- alert: MysqlSlowQueries
expr: increase(mysql_global_status_slow_queries[1m]) > 0
for: 2m
labels:
severity: warning
annotations:
summary: MySQL slow queries (instance {{ $labels.instance }})
description: "MySQL server mysql has some new slow query.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# Postgresql down
- alert: PostgresqlDown
expr: pg_up == 0
for: 0m
labels:
severity: critical
annotations:
summary: Postgresql down (instance {{ $labels.instance }})
description: "Postgresql instance is down\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# Postgresql too many connections
- alert: PostgresqlTooManyConnections
expr: sum by (datname) (pg_stat_activity_count{datname!~"template.*|postgres"}) > pg_settings_max_connections * 0.8
for: 2m
labels:
severity: warning
annotations:
summary: Postgresql too many connections (instance {{ $labels.instance }})
description: "PostgreSQL instance has too many connections (> 80%).\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
## Postgresql not enough connections
# - alert: PostgresqlNotEnoughConnections
# expr: sum by (datname) (pg_stat_activity_count{datname!~"template.*|postgres"}) < 5
# for: 2m
# labels:
# severity: warning
# annotations:
# summary: Postgresql not enough connections (instance {{ $labels.instance }})
# description: "PostgreSQL instance should have more connections (> 5)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# Postgresql dead locks
- alert: PostgresqlDeadLocks
expr: increase(pg_stat_database_deadlocks{datname!~"template.*|postgres"}[1m]) > 5
for: 0m
labels:
severity: warning
annotations:
summary: Postgresql dead locks (instance {{ $labels.instance }})
description: "PostgreSQL has dead-locks\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# Postgresql high rollback rate
- alert: PostgresqlHighRollbackRate
expr: sum by (namespace,datname) ((rate(pg_stat_database_xact_rollback{datname!~"template.*|postgres",datid!="0"}[3m])) / ((rate(pg_stat_database_xact_rollback{datname!~"template.*|postgres",datid!="0"}[3m])) + (rate(pg_stat_database_xact_commit{datname!~"template.*|postgres",datid!="0"}[3m])))) > 0.02
for: 0m
labels:
severity: warning
annotations:
summary: Postgresql high rollback rate (instance {{ $labels.instance }})
description: "Ratio of transactions being aborted compared to committed is > 2 %\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
## Postgresql commit rate low
# - alert: PostgresqlCommitRateLow
# expr: rate(pg_stat_database_xact_commit[1m]) < 10
# for: 2m
# labels:
# severity: critical
# annotations:
# summary: Postgresql commit rate low (instance {{ $labels.instance }})
# description: "Postgresql seems to be processing very few transactions\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# Postgresql high rate statement timeout
- alert: PostgresqlHighRateStatementTimeout
expr: rate(postgresql_errors_total{type="statement_timeout"}[1m]) > 3
for: 0m
labels:
severity: critical
annotations:
summary: Postgresql high rate statement timeout (instance {{ $labels.instance }})
description: "Postgres transactions showing high rate of statement timeouts\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# Postgresql high rate deadlock
- alert: PostgresqlHighRateDeadlock
expr: increase(postgresql_errors_total{type="deadlock_detected"}[1m]) > 1
for: 0m
labels:
severity: critical
annotations:
summary: Postgresql high rate deadlock (instance {{ $labels.instance }})
description: "Postgres detected deadlocks\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# Postgresql too many dead tuples
- alert: PostgresqlTooManyDeadTuples
expr: ((pg_stat_user_tables_n_dead_tup > 10000) / (pg_stat_user_tables_n_live_tup + pg_stat_user_tables_n_dead_tup)) >= 0.1
for: 2m
labels:
severity: warning
annotations:
summary: Postgresql too many dead tuples (instance {{ $labels.instance }})
description: "PostgreSQL dead tuples is too large\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# Postgresql too many locks acquired
- alert: PostgresqlTooManyLocksAcquired
expr: ((sum (pg_locks_count)) / (pg_settings_max_locks_per_transaction * pg_settings_max_connections)) > 0.20
for: 2m
labels:
severity: critical
annotations:
summary: Postgresql too many locks acquired (instance {{ $labels.instance }})
description: "Too many locks acquired on the database. If this alert happens frequently, we may need to increase the postgres setting max_locks_per_transaction.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# Postgresql bloat index high (> 80%)
# See https://github.com/samber/awesome-prometheus-alerts/issues/289#issuecomment-1164842737
- alert: PostgresqlBloatIndexHigh(>80%)
expr: pg_bloat_btree_bloat_pct > 80 and on (idxname) (pg_bloat_btree_real_size > 100000000)
for: 1h
labels:
severity: warning
annotations:
summary: Postgresql bloat index high (> 80%) (instance {{ $labels.instance }})
description: "The index {{ $labels.idxname }} is bloated. You should execute `REINDEX INDEX CONCURRENTLY {{ $labels.idxname }};`\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# Postgresql bloat table high (> 80%)
# See https://github.com/samber/awesome-prometheus-alerts/issues/289#issuecomment-1164842737
- alert: PostgresqlBloatTableHigh(>80%)
expr: pg_bloat_table_bloat_pct > 80 and on (relname) (pg_bloat_table_real_size > 200000000)
for: 1h
labels:
severity: warning
annotations:
summary: Postgresql bloat table high (> 80%) (instance {{ $labels.instance }})
description: "The table {{ $labels.relname }} is bloated. You should execute `VACUUM {{ $labels.relname }};`\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# Redis down
- alert: RedisDown
expr: redis_up == 0
for: 0m
labels:
severity: critical
annotations:
summary: Redis down (instance {{ $labels.instance }})
description: "Redis instance is down\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# Redis out of system memory
# The exporter must be started with --include-system-metrics flag or REDIS_EXPORTER_INCL_SYSTEM_METRICS=true environment variable.
- alert: RedisOutOfSystemMemory
expr: redis_memory_used_bytes / redis_total_system_memory_bytes * 100 > 90
for: 2m
labels:
severity: warning
annotations:
summary: Redis out of system memory (instance {{ $labels.instance }})
description: "Redis is running out of system memory (> 90%)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# Redis out of configured maxmemory
- alert: RedisOutOfConfiguredMaxmemory
expr: redis_memory_used_bytes / redis_memory_max_bytes * 100 > 90
for: 2m
labels:
severity: warning
annotations:
summary: Redis out of configured maxmemory (instance {{ $labels.instance }})
description: "Redis is running out of configured maxmemory (> 90%)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# Redis too many connections
- alert: RedisTooManyConnections
expr: redis_connected_clients > 100
for: 2m
labels:
severity: warning
annotations:
summary: Redis too many connections (instance {{ $labels.instance }})
description: "Redis instance has too many connections\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
## Redis not enough connections
# - alert: RedisNotEnoughConnections
# expr: redis_connected_clients < 5
# for: 2m
# labels:
# severity: warning
# annotations:
# summary: Redis not enough connections (instance {{ $labels.instance }})
# description: "Redis instance should have more connections (> 5)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# Redis rejected connections
- alert: RedisRejectedConnections
expr: increase(redis_rejected_connections_total[1m]) > 0
for: 0m
labels:
severity: critical
annotations:
summary: Redis rejected connections (instance {{ $labels.instance }})
description: "Some connections to Redis has been rejected\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# JVM memory filling up
- alert: JvmMemoryFillingUp
expr: (sum by (instance)(jvm_memory_used_bytes{area="heap"}) / sum by (instance)(jvm_memory_max_bytes{area="heap"})) * 100 > 80
for: 2m
labels:
severity: warning
annotations:
summary: JVM memory filling up (instance {{ $labels.instance }})
description: "JVM memory is filling up (> 80%)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# SSL certificate revoked
- alert: SslCertificateRevoked
expr: ssl_ocsp_response_status == 1
for: 0m
labels:
severity: critical
annotations:
summary: SSL certificate revoked (instance {{ $labels.instance }})
description: "SSL certificate revoked {{ $labels.instance }}\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# SSL certificate expiry (< 7 days)
- alert: SslCertificateExpiry(<7Days)
expr: ssl_verified_cert_not_after{chain_no="0"} - time() < 86400 * 7
for: 0m
labels:
severity: warning
annotations:
summary: SSL certificate expiry (< 7 days) (instance {{ $labels.instance }})
description: "{{ $labels.instance }} Certificate is expiring in 7 days\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# Loki process too many restarts
- alert: LokiProcessTooManyRestarts
expr: changes(process_start_time_seconds{job=~"loki"}[15m]) > 2
for: 0m
labels:
severity: warning
annotations:
summary: Loki process too many restarts (instance {{ $labels.instance }})
description: "A loki process had too many restarts (target {{ $labels.instance }})\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# Loki request errors
- alert: LokiRequestErrors
expr: 100 * sum(rate(loki_request_duration_seconds_count{status_code=~"5.."}[1m])) by (namespace, job, route) / sum(rate(loki_request_duration_seconds_count[1m])) by (namespace, job, route) > 10
for: 15m
labels:
severity: critical
annotations:
summary: Loki request errors (instance {{ $labels.instance }})
description: "The {{ $labels.job }} and {{ $labels.route }} are experiencing errors\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# Loki request panic
- alert: LokiRequestPanic
expr: sum(increase(loki_panic_total[10m])) by (namespace, job) > 0
for: 5m
labels:
severity: critical
annotations:
summary: Loki request panic (instance {{ $labels.instance }})
description: "The {{ $labels.job }} is experiencing {{ printf \"%.2f\" $value }}% increase of panics\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# Loki request latency
- alert: LokiRequestLatency
expr: (histogram_quantile(0.99, sum(rate(loki_request_duration_seconds_bucket{route!~"(?i).*tail.*"}[5m])) by (le))) > 1
for: 5m
labels:
severity: critical
annotations:
summary: Loki request latency (instance {{ $labels.instance }})
description: "The {{ $labels.job }} {{ $labels.route }} is experiencing {{ printf \"%.2f\" $value }}s 99th percentile latency\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# Promtail request errors
- alert: PromtailRequestErrors
expr: 100 * sum(rate(promtail_request_duration_seconds_count{status_code=~"5..|failed"}[1m])) by (namespace, job, route, instance) / sum(rate(promtail_request_duration_seconds_count[1m])) by (namespace, job, route, instance) > 10
for: 5m
labels:
severity: critical
annotations:
summary: Promtail request errors (instance {{ $labels.instance }})
description: "The {{ $labels.job }} {{ $labels.route }} is experiencing {{ printf \"%.2f\" $value }}% errors.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# Promtail request latency
- alert: PromtailRequestLatency
expr: histogram_quantile(0.99, sum(rate(promtail_request_duration_seconds_bucket[5m])) by (le)) > 1
for: 5m
labels:
severity: critical
annotations:
summary: Promtail request latency (instance {{ $labels.instance }})
description: "The {{ $labels.job }} {{ $labels.route }} is experiencing {{ printf \"%.2f\" $value }}s 99th percentile latency.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# Cloudflare http 4xx error rate
- alert: CloudflareHttp4xxErrorRate
expr: (sum by(zone) (rate(cloudflare_zone_requests_status{status=~"^4.."}[15m])) / on (zone) sum by (zone) (rate(cloudflare_zone_requests_status[15m]))) * 100 > 5
for: 0m
labels:
severity: warning
annotations:
summary: Cloudflare http 4xx error rate (instance {{ $labels.instance }})
description: "Cloudflare high HTTP 4xx error rate (> 5% for domain {{ $labels.zone }})\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# Cloudflare http 5xx error rate
- alert: CloudflareHttp5xxErrorRate
expr: (sum by (zone) (rate(cloudflare_zone_requests_status{status=~"^5.."}[5m])) / on (zone) sum by (zone) (rate(cloudflare_zone_requests_status[5m]))) * 100 > 5
for: 0m
labels:
severity: critical
annotations:
summary: Cloudflare http 5xx error rate (instance {{ $labels.instance }})
description: "Cloudflare high HTTP 5xx error rate (> 5% for domain {{ $labels.zone }})\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
conf/provisioning/datasources/datasource.yml
[Fichier]
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
# 2023-05-24
apiVersion: 1
datasources:
- name: Prometheus
type: prometheus
isDefault: false
editable: true
url: http://prometheus:9090
access: proxy
- name: Loki
type: loki
editable: true
url: http://loki:3100
access: proxy
- name: Mimir
type: prometheus
isDefault: true
editable: true
url: http://mimir:9009/prometheus
access: proxy
jsonData:
httpHeaderName1: 'X-Scope-OrgID'
secureJsonData:
httpHeaderValue1: 'org'
conf/provisioning/dashboards/dashboard.yml
[Fichier]
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
# 2023-05-24
# config file version
apiVersion: 1
providers:
# <string> an unique provider name
- name: Org
# <int> org id. will default to orgId 1 if not specified
org_id: 1
# <string, required> name of the dashboard folder. Required
folder: "General"
# <string, required> provider type. Required
type: "file"
# <bool> disable dashboard deletion
disableDeletion: false
# <bool> enable dashboard editing
editable: true
# <int> how often Grafana will scan for changed dashboards
updateIntervalSeconds: 5
# <bool> allow updating provisioned dashboards from the UI
allowUiUpdates: true
options:
# <string, required> path to dashboard files on disk. Required
path: /etc/grafana/dashboards/provisioned
#path: /opt/monitor-stack/grafana/dashboards
# <bool> use folder names from filesystem to create folders in Grafana
foldersFromFilesStructure: true
conf/provisioning/provisioned/monitoring.json
[Fichier]
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
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
3239
3240
3241
3242
3243
3244
3245
3246
3247
3248
3249
3250
3251
3252
3253
3254
3255
3256
3257
3258
3259
3260
3261
3262
3263
3264
3265
3266
3267
3268
3269
3270
3271
3272
3273
3274
3275
3276
3277
3278
3279
3280
3281
3282
3283
3284
3285
3286
3287
3288
3289
3290
3291
3292
3293
3294
3295
{
"annotations": {
"list": [
{
"builtIn": 1,
"datasource": {
"type": "grafana",
"uid": "-- Grafana --"
},
"enable": true,
"hide": true,
"iconColor": "rgba(0, 211, 255, 1)",
"name": "Annotations & Alerts",
"target": {
"limit": 100,
"matchAny": false,
"tags": [],
"type": "dashboard"
},
"type": "dashboard"
}
]
},
"description": "System Monitoring",
"editable": true,
"fiscalYearStartMonth": 0,
"graphTooltip": 0,
"id": 8,
"links": [
{
"asDropdown": true,
"icon": "external link",
"includeVars": false,
"keepTime": false,
"tags": [
"Zogg"
],
"targetBlank": false,
"title": "Dashboards",
"tooltip": "",
"type": "dashboards",
"url": ""
}
],
"liveNow": false,
"panels": [
{
"collapsed": false,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 0
},
"id": 36,
"panels": [],
"title": "Global",
"type": "row"
},
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"description": "",
"fieldConfig": {
"defaults": {
"decimals": 1,
"mappings": [
{
"options": {
"match": "null",
"result": {
"text": "N/A"
}
},
"type": "special"
}
],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
}
]
},
"unit": "s"
},
"overrides": []
},
"gridPos": {
"h": 4,
"w": 3,
"x": 0,
"y": 1
},
"id": 38,
"links": [],
"maxDataPoints": 100,
"options": {
"colorMode": "value",
"graphMode": "none",
"justifyMode": "auto",
"orientation": "horizontal",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"text": {},
"textMode": "auto"
},
"pluginVersion": "9.5.2",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"editorMode": "code",
"exemplar": true,
"expr": "time() - node_boot_time_seconds{instance=\"$nodeexporter\"}",
"format": "time_series",
"hide": false,
"interval": "",
"intervalFactor": 1,
"legendFormat": "",
"range": true,
"refId": "A",
"step": 1800
}
],
"title": "Uptime",
"type": "stat"
},
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"description": "",
"fieldConfig": {
"defaults": {
"mappings": [
{
"options": {
"match": "null",
"result": {
"text": "N/A"
}
},
"type": "special"
}
],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
},
"unit": "none"
},
"overrides": []
},
"gridPos": {
"h": 4,
"w": 3,
"x": 3,
"y": 1
},
"id": 40,
"links": [],
"maxDataPoints": 100,
"options": {
"colorMode": "value",
"graphMode": "none",
"justifyMode": "auto",
"orientation": "horizontal",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"text": {},
"textMode": "auto"
},
"pluginVersion": "9.5.2",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"exemplar": true,
"expr": "count(container_last_seen{instance=~\"$cadvisor\",image=~\"(.)+\"})",
"format": "time_series",
"hide": false,
"interval": "",
"intervalFactor": 1,
"legendFormat": "",
"refId": "A",
"step": 1800
}
],
"title": "Containers",
"type": "stat"
},
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"description": "",
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"mappings": [
{
"options": {
"match": "null",
"result": {
"text": "N/A"
}
},
"type": "special"
}
],
"max": 100,
"min": 0,
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "rgba(50, 172, 45, 0.97)",
"value": null
},
{
"color": "rgba(237, 129, 40, 0.89)",
"value": 80
},
{
"color": "rgba(245, 54, 54, 0.9)",
"value": 90
}
]
},
"unit": "percent"
},
"overrides": []
},
"gridPos": {
"h": 4,
"w": 5,
"x": 6,
"y": 1
},
"id": 14,
"links": [],
"options": {
"orientation": "horizontal",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"showThresholdLabels": false,
"showThresholdMarkers": true
},
"pluginVersion": "9.5.2",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "100 - ((node_filesystem_avail_bytes{instance=\"$nodeexporter\",job=\"$vm\",mountpoint=\"/\",fstype!=\"rootfs\"} * 100) / node_filesystem_size_bytes{instance=\"$nodeexporter\",job=\"$vm\",mountpoint=\"/\",fstype!=\"rootfs\"})",
"format": "time_series",
"intervalFactor": 1,
"refId": "A",
"step": 240
}
],
"title": "Root FS Used",
"type": "gauge"
},
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"description": "",
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"mappings": [
{
"options": {
"match": "null",
"result": {
"text": "N/A"
}
},
"type": "special"
}
],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
},
"unit": "short"
},
"overrides": []
},
"gridPos": {
"h": 2,
"w": 3,
"x": 11,
"y": 1
},
"id": 16,
"links": [],
"maxDataPoints": 100,
"options": {
"colorMode": "none",
"graphMode": "none",
"justifyMode": "auto",
"orientation": "horizontal",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"textMode": "auto"
},
"pluginVersion": "9.5.2",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"editorMode": "code",
"expr": "count(count(node_cpu_seconds_total{instance=\"$nodeexporter\",job=\"$vm\"}) by (cpu))",
"interval": "",
"intervalFactor": 1,
"legendFormat": "",
"range": true,
"refId": "A",
"step": 240
}
],
"title": "CPU Cores",
"type": "stat"
},
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"description": "",
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"decimals": 1,
"mappings": [
{
"options": {
"match": "null",
"result": {
"text": "N/A"
}
},
"type": "special"
}
],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
},
"unit": "s"
},
"overrides": []
},
"gridPos": {
"h": 2,
"w": 6,
"x": 14,
"y": 1
},
"hideTimeOverride": true,
"id": 18,
"links": [],
"maxDataPoints": 100,
"options": {
"colorMode": "none",
"graphMode": "none",
"justifyMode": "auto",
"orientation": "horizontal",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"textMode": "auto"
},
"pluginVersion": "9.5.2",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "node_time_seconds{instance=\"$nodeexporter\",job=\"$vm\"} - node_boot_time_seconds{instance=\"$nodeexporter\",job=\"$vm\"}",
"intervalFactor": 1,
"refId": "A",
"step": 240
}
],
"title": "Uptime",
"type": "stat"
},
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"description": "",
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"mappings": [
{
"options": {
"match": "null",
"result": {
"text": "N/A"
}
},
"type": "special"
}
],
"max": 100,
"min": 0,
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "rgba(50, 172, 45, 0.97)",
"value": null
},
{
"color": "rgba(237, 129, 40, 0.89)",
"value": 85
},
{
"color": "rgba(245, 54, 54, 0.9)",
"value": 95
}
]
},
"unit": "percent"
},
"overrides": []
},
"gridPos": {
"h": 4,
"w": 4,
"x": 20,
"y": 1
},
"id": 4,
"links": [],
"options": {
"orientation": "horizontal",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"showThresholdLabels": false,
"showThresholdMarkers": true
},
"pluginVersion": "9.5.2",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "(((count(count(node_cpu_seconds_total{instance=\"$nodeexporter\",job=\"$vm\"}) by (cpu))) - avg(sum by (mode)(rate(node_cpu_seconds_total{mode='idle',instance=\"$nodeexporter\",job=\"$vm\"}[$__rate_interval])))) * 100) / count(count(node_cpu_seconds_total{instance=\"$nodeexporter\",job=\"$vm\"}) by (cpu))",
"hide": false,
"intervalFactor": 1,
"legendFormat": "",
"refId": "A",
"step": 240
}
],
"title": "CPU Busy",
"type": "gauge"
},
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"description": "",
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"decimals": 0,
"mappings": [
{
"options": {
"match": "null",
"result": {
"text": "N/A"
}
},
"type": "special"
}
],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "rgba(50, 172, 45, 0.97)",
"value": null
},
{
"color": "rgba(237, 129, 40, 0.89)",
"value": 70
},
{
"color": "rgba(245, 54, 54, 0.9)",
"value": 90
}
]
},
"unit": "bytes"
},
"overrides": []
},
"gridPos": {
"h": 2,
"w": 3,
"x": 11,
"y": 3
},
"id": 20,
"links": [],
"maxDataPoints": 100,
"options": {
"colorMode": "none",
"graphMode": "none",
"justifyMode": "auto",
"orientation": "horizontal",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"textMode": "auto"
},
"pluginVersion": "9.5.2",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "node_filesystem_size_bytes{instance=\"$nodeexporter\",job=\"$vm\",mountpoint=\"/\",fstype!=\"rootfs\"}",
"format": "time_series",
"hide": false,
"intervalFactor": 1,
"refId": "A",
"step": 240
}
],
"title": "RootFS Total",
"type": "stat"
},
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"description": "",
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"decimals": 0,
"mappings": [
{
"options": {
"match": "null",
"result": {
"text": "N/A"
}
},
"type": "special"
}
],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
},
"unit": "bytes"
},
"overrides": []
},
"gridPos": {
"h": 2,
"w": 3,
"x": 14,
"y": 3
},
"id": 22,
"links": [],
"maxDataPoints": 100,
"options": {
"colorMode": "none",
"graphMode": "none",
"justifyMode": "auto",
"orientation": "horizontal",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"textMode": "auto"
},
"pluginVersion": "9.5.2",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "node_memory_MemTotal_bytes{instance=\"$nodeexporter\",job=\"$vm\"}",
"intervalFactor": 1,
"refId": "A",
"step": 240
}
],
"title": "RAM Total",
"type": "stat"
},
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"description": "",
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"decimals": 0,
"mappings": [
{
"options": {
"match": "null",
"result": {
"text": "N/A"
}
},
"type": "special"
}
],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
},
"unit": "bytes"
},
"overrides": []
},
"gridPos": {
"h": 2,
"w": 3,
"x": 17,
"y": 3
},
"id": 24,
"links": [],
"maxDataPoints": 100,
"options": {
"colorMode": "none",
"graphMode": "none",
"justifyMode": "auto",
"orientation": "horizontal",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"textMode": "auto"
},
"pluginVersion": "9.5.2",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "node_memory_SwapTotal_bytes{instance=\"$nodeexporter\",job=\"$vm\"}",
"intervalFactor": 1,
"refId": "A",
"step": 240
}
],
"title": "SWAP Total",
"type": "stat"
},
{
"collapsed": false,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 5
},
"id": 64,
"panels": [],
"title": "Usages",
"type": "row"
},
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 100,
"gradientMode": "opacity",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "never",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "normal"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
},
"unit": "percent"
},
"overrides": [
{
"matcher": {
"id": "byName",
"options": "{id=\"/\",instance=\"cadvisor:8080\",job=\"prometheus\"}"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "#BA43A9",
"mode": "fixed"
}
}
]
},
{
"matcher": {
"id": "byType",
"options": "time"
},
"properties": [
{
"id": "custom.axisPlacement",
"value": "hidden"
}
]
}
]
},
"gridPos": {
"h": 6,
"w": 6,
"x": 0,
"y": 6
},
"id": 62,
"links": [],
"options": {
"legend": {
"calcs": [],
"displayMode": "list",
"placement": "bottom",
"showLegend": false
},
"tooltip": {
"mode": "multi",
"sort": "none"
}
},
"pluginVersion": "9.5.1",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"editorMode": "code",
"expr": "sum(rate(container_cpu_system_seconds_total{instance=\"$cadvisor\"}[1m]))",
"hide": true,
"intervalFactor": 2,
"legendFormat": "a",
"range": true,
"refId": "B",
"step": 120
},
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"editorMode": "code",
"expr": "sum(rate(container_cpu_system_seconds_total{instance=\"$cadvisor\", name=~\".+\"}[1m]))",
"hide": true,
"interval": "",
"intervalFactor": 2,
"legendFormat": "nur container",
"range": true,
"refId": "F",
"step": 10
},
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"editorMode": "code",
"expr": "sum(rate(container_cpu_system_seconds_total{instance=\"$cadvisor\", id=\"/\"}[1m]))",
"hide": true,
"interval": "",
"intervalFactor": 2,
"legendFormat": "nur docker host",
"metric": "",
"range": true,
"refId": "A",
"step": 20
},
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"editorMode": "code",
"expr": "sum(rate(process_cpu_seconds_total{instance=\"$cadvisor\"}[$interval])) * 100",
"hide": false,
"interval": "",
"intervalFactor": 2,
"legendFormat": "host",
"metric": "",
"range": true,
"refId": "C",
"step": 600
},
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"editorMode": "code",
"expr": "sum(rate(container_cpu_system_seconds_total{instance=\"$cadvisor\", name=~\".+\"}[1m])) + sum(rate(container_cpu_system_seconds_total{instance=\"$cadvisor\", id=\"/\"}[1m])) + sum(rate(process_cpu_seconds_total[1m]))",
"hide": true,
"intervalFactor": 2,
"legendFormat": "",
"range": true,
"refId": "D",
"step": 120
}
],
"title": "CPU Usage",
"type": "timeseries"
},
{
"alert": {
"conditions": [
{
"evaluator": {
"params": [
1.25
],
"type": "gt"
},
"query": {
"params": [
"A",
"5m",
"now"
]
},
"reducer": {
"params": [],
"type": "avg"
},
"type": "query"
}
],
"executionErrorState": "alerting",
"frequency": "60s",
"handler": 1,
"name": "Panel Title alert",
"noDataState": "keep_state",
"notifications": [
{
"id": 1
}
]
},
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 100,
"gradientMode": "opacity",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "never",
"spanNulls": true,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "line+area"
}
},
"mappings": [],
"max": 1.5,
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "transparent",
"value": null
},
{
"color": "red",
"value": 1.25
}
]
},
"unit": "percentunit"
},
"overrides": [
{
"matcher": {
"id": "byType",
"options": "time"
},
"properties": [
{
"id": "custom.axisPlacement",
"value": "hidden"
}
]
}
]
},
"gridPos": {
"h": 6,
"w": 6,
"x": 6,
"y": 6
},
"id": 66,
"links": [],
"options": {
"legend": {
"calcs": [
"mean",
"lastNotNull"
],
"displayMode": "list",
"placement": "bottom",
"showLegend": false
},
"tooltip": {
"mode": "multi",
"sort": "none"
}
},
"pluginVersion": "9.5.1",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"editorMode": "code",
"expr": "scalar(node_load1{ip=~\"$ip\"}) / scalar(count by(job, instance)(count by(job, instance, cpu)(node_cpu_seconds_total{ip=~\"$ip\"})))",
"intervalFactor": 2,
"range": true,
"refId": "A",
"step": 600
}
],
"title": "Load",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 80,
"gradientMode": "opacity",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "never",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
},
"unit": "Bps"
},
"overrides": [
{
"matcher": {
"id": "byName",
"options": "IN on /sda"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "#7EB26D",
"mode": "fixed"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "OUT on /sda"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "#890F02",
"mode": "fixed"
}
}
]
},
{
"matcher": {
"id": "byType",
"options": "time"
},
"properties": [
{
"id": "custom.axisPlacement",
"value": "hidden"
}
]
}
]
},
"gridPos": {
"h": 6,
"w": 6,
"x": 12,
"y": 6
},
"id": 68,
"links": [],
"options": {
"legend": {
"calcs": [],
"displayMode": "list",
"placement": "bottom",
"showLegend": false
},
"tooltip": {
"mode": "multi",
"sort": "none"
}
},
"pluginVersion": "9.5.1",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"editorMode": "code",
"expr": "-sum(rate(node_disk_read_bytes_total{instance=\"$nodeexporter\"}[$interval])) by (device)",
"hide": false,
"intervalFactor": 2,
"legendFormat": "OUT on /{{device}}",
"metric": "node_disk_bytes_read",
"range": true,
"refId": "A",
"step": 600
},
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"editorMode": "code",
"expr": "sum(rate(node_disk_written_bytes_total{instance=\"$nodeexporter\"}[$interval])) by (device)",
"intervalFactor": 2,
"legendFormat": "IN on /",
"metric": "",
"range": true,
"refId": "B",
"step": 600
}
],
"title": "Disk I/O",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 80,
"gradientMode": "opacity",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "auto",
"spanNulls": true,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
},
"unit": "bytes"
},
"overrides": [
{
"matcher": {
"id": "byName",
"options": "SENT"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "#BF1B00",
"mode": "fixed"
}
}
]
},
{
"matcher": {
"id": "byType",
"options": "time"
},
"properties": [
{
"id": "custom.axisPlacement",
"value": "hidden"
}
]
}
]
},
"gridPos": {
"h": 6,
"w": 6,
"x": 18,
"y": 6
},
"id": 70,
"links": [],
"options": {
"legend": {
"calcs": [],
"displayMode": "list",
"placement": "bottom",
"showLegend": false
},
"tooltip": {
"mode": "multi",
"sort": "none"
}
},
"pluginVersion": "9.5.1",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"editorMode": "code",
"expr": "sum(rate(container_network_receive_bytes_total{instance=\"$cadvisor\", id=\"/\"}[$interval])) by (id)",
"intervalFactor": 2,
"legendFormat": "RECEIVED",
"range": true,
"refId": "A",
"step": 600
},
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"editorMode": "code",
"expr": "- sum(rate(container_network_transmit_bytes_total{instance=\"$cadvisor\", id=\"/\"}[$interval])) by (id)",
"hide": false,
"intervalFactor": 2,
"legendFormat": "SENT",
"range": true,
"refId": "B",
"step": 600
}
],
"title": "Network Traffic",
"type": "timeseries"
},
{
"collapsed": false,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 12
},
"id": 2,
"panels": [],
"title": "CPU / Mem / Disk",
"type": "row"
},
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"description": "",
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"mappings": [
{
"options": {
"match": "null",
"result": {
"text": "N/A"
}
},
"type": "special"
}
],
"max": 100,
"min": 0,
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "rgba(50, 172, 45, 0.97)",
"value": null
},
{
"color": "rgba(237, 129, 40, 0.89)",
"value": 85
},
{
"color": "rgba(245, 54, 54, 0.9)",
"value": 95
}
]
},
"unit": "percent"
},
"overrides": []
},
"gridPos": {
"h": 4,
"w": 5,
"x": 0,
"y": 13
},
"id": 50,
"links": [],
"options": {
"orientation": "horizontal",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"showThresholdLabels": false,
"showThresholdMarkers": true,
"text": {}
},
"pluginVersion": "9.5.2",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"editorMode": "code",
"exemplar": true,
"expr": "avg(node_load1) / count(count(node_cpu_seconds_total{instance=\"$nodeexporter\"}) by (cpu)) * 100",
"format": "time_series",
"hide": false,
"interval": "",
"intervalFactor": 1,
"legendFormat": "",
"range": true,
"refId": "A",
"step": 240
}
],
"title": "Sys Load (1m avg)",
"type": "gauge"
},
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"description": "",
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"mappings": [
{
"options": {
"match": "null",
"result": {
"text": "N/A"
}
},
"type": "special"
}
],
"max": 100,
"min": 0,
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "rgba(50, 172, 45, 0.97)",
"value": null
},
{
"color": "rgba(237, 129, 40, 0.89)",
"value": 85
},
{
"color": "rgba(245, 54, 54, 0.9)",
"value": 95
}
]
},
"unit": "percent"
},
"overrides": []
},
"gridPos": {
"h": 4,
"w": 5,
"x": 5,
"y": 13
},
"id": 6,
"links": [],
"options": {
"orientation": "horizontal",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"showThresholdLabels": false,
"showThresholdMarkers": true
},
"pluginVersion": "9.5.2",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"editorMode": "code",
"expr": "avg(node_load5{instance=\"$nodeexporter\",job=\"$vm\"}) / count(count(node_cpu_seconds_total{instance=\"$nodeexporter\",job=\"$vm\"}) by (cpu)) * 100",
"format": "time_series",
"hide": false,
"intervalFactor": 1,
"range": true,
"refId": "A",
"step": 240
}
],
"title": "Sys Load (5m avg)",
"type": "gauge"
},
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"description": "",
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"mappings": [
{
"options": {
"match": "null",
"result": {
"text": "N/A"
}
},
"type": "special"
}
],
"max": 100,
"min": 0,
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "rgba(50, 172, 45, 0.97)",
"value": null
},
{
"color": "rgba(237, 129, 40, 0.89)",
"value": 85
},
{
"color": "rgba(245, 54, 54, 0.9)",
"value": 95
}
]
},
"unit": "percent"
},
"overrides": []
},
"gridPos": {
"h": 4,
"w": 5,
"x": 10,
"y": 13
},
"id": 8,
"links": [],
"options": {
"orientation": "horizontal",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"showThresholdLabels": false,
"showThresholdMarkers": true
},
"pluginVersion": "9.5.2",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "avg(node_load15{instance=\"$nodeexporter\",job=\"$vm\"}) / count(count(node_cpu_seconds_total{instance=\"$nodeexporter\",job=\"$vm\"}) by (cpu)) * 100",
"hide": false,
"intervalFactor": 1,
"refId": "A",
"step": 240
}
],
"title": "Sys Load (15m avg)",
"type": "gauge"
},
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"description": "",
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"decimals": 0,
"mappings": [],
"max": 100,
"min": 0,
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "rgba(50, 172, 45, 0.97)",
"value": null
},
{
"color": "rgba(237, 129, 40, 0.89)",
"value": 80
},
{
"color": "rgba(245, 54, 54, 0.9)",
"value": 90
}
]
},
"unit": "percent"
},
"overrides": []
},
"gridPos": {
"h": 4,
"w": 5,
"x": 15,
"y": 13
},
"hideTimeOverride": false,
"id": 10,
"links": [],
"options": {
"orientation": "horizontal",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"showThresholdLabels": false,
"showThresholdMarkers": true
},
"pluginVersion": "9.5.2",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "((node_memory_MemTotal_bytes{instance=\"$nodeexporter\",job=\"$vm\"} - node_memory_MemFree_bytes{instance=\"$nodeexporter\",job=\"$vm\"}) / (node_memory_MemTotal_bytes{instance=\"$nodeexporter\",job=\"$vm\"} )) * 100",
"format": "time_series",
"hide": true,
"intervalFactor": 1,
"refId": "A",
"step": 240
},
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "100 - ((node_memory_MemAvailable_bytes{instance=\"$nodeexporter\",job=\"$vm\"} * 100) / node_memory_MemTotal_bytes{instance=\"$nodeexporter\",job=\"$vm\"})",
"format": "time_series",
"hide": false,
"intervalFactor": 1,
"refId": "B",
"step": 240
}
],
"title": "RAM Used",
"type": "gauge"
},
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"description": "",
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"mappings": [
{
"options": {
"match": "null",
"result": {
"text": "N/A"
}
},
"type": "special"
}
],
"max": 100,
"min": 0,
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "rgba(50, 172, 45, 0.97)",
"value": null
},
{
"color": "rgba(237, 129, 40, 0.89)",
"value": 10
},
{
"color": "rgba(245, 54, 54, 0.9)",
"value": 25
}
]
},
"unit": "percent"
},
"overrides": []
},
"gridPos": {
"h": 4,
"w": 4,
"x": 20,
"y": 13
},
"id": 12,
"links": [],
"options": {
"orientation": "horizontal",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"showThresholdLabels": false,
"showThresholdMarkers": true
},
"pluginVersion": "9.5.2",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "((node_memory_SwapTotal_bytes{instance=\"$nodeexporter\",job=\"$vm\"} - node_memory_SwapFree_bytes{instance=\"$nodeexporter\",job=\"$vm\"}) / (node_memory_SwapTotal_bytes{instance=\"$nodeexporter\",job=\"$vm\"} )) * 100",
"intervalFactor": 1,
"refId": "A",
"step": 240
}
],
"title": "SWAP Used",
"type": "gauge"
},
{
"collapsed": false,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 17
},
"id": 26,
"panels": [],
"title": "System",
"type": "row"
},
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "counter",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 20,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "never",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"links": [],
"mappings": [],
"min": 0,
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
},
"unit": "short"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 24,
"x": 0,
"y": 18
},
"id": 28,
"links": [],
"options": {
"legend": {
"calcs": [
"mean",
"lastNotNull",
"max",
"min"
],
"displayMode": "table",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "multi",
"sort": "none"
}
},
"pluginVersion": "9.5.1",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "node_load1{instance=\"$nodeexporter\",job=\"$vm\"}",
"format": "time_series",
"intervalFactor": 4,
"legendFormat": "Load 1m",
"refId": "A",
"step": 240
},
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "node_load5{instance=\"$nodeexporter\",job=\"$vm\"}",
"format": "time_series",
"intervalFactor": 4,
"legendFormat": "Load 5m",
"refId": "B",
"step": 240
},
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "node_load15{instance=\"$nodeexporter\",job=\"$vm\"}",
"format": "time_series",
"intervalFactor": 4,
"legendFormat": "Load 15m",
"refId": "C",
"step": 240
}
],
"title": "System Load",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 50,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "never",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "normal"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
},
"unit": "percent"
},
"overrides": []
},
"gridPos": {
"h": 6,
"w": 24,
"x": 0,
"y": 26
},
"id": 52,
"links": [],
"options": {
"legend": {
"calcs": [],
"displayMode": "table",
"placement": "right",
"showLegend": true
},
"tooltip": {
"mode": "multi",
"sort": "none"
}
},
"pluginVersion": "9.0.5",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"editorMode": "code",
"expr": "sum(rate(container_cpu_usage_seconds_total{instance=~\"$cadvisor\", name=~\".+\"}[$interval])) by (name) * 100",
"hide": false,
"interval": "",
"intervalFactor": 2,
"legendFormat": "",
"metric": "",
"range": true,
"refId": "F",
"step": 240
}
],
"title": "CPU Usage per Container",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 30,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"lineInterpolation": "linear",
"lineStyle": {
"fill": "solid"
},
"lineWidth": 2,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "auto",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "normal"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
},
"unit": "decbytes"
},
"overrides": []
},
"gridPos": {
"h": 10,
"w": 24,
"x": 0,
"y": 32
},
"id": 75,
"links": [],
"options": {
"legend": {
"calcs": [],
"displayMode": "list",
"placement": "right",
"showLegend": true
},
"tooltip": {
"mode": "multi",
"sort": "none"
}
},
"pluginVersion": "9.5.1",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"editorMode": "code",
"expr": "sum(container_memory_rss{instance=~\"$cadvisor\", name=~\".+\"}) by (name)",
"hide": false,
"intervalFactor": 2,
"legendFormat": "",
"range": true,
"refId": "A",
"step": 2
},
{
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"editorMode": "code",
"expr": "container_memory_usage_bytes{instance=~\"$cadvisor\", name=~\".+\"}",
"hide": true,
"intervalFactor": 2,
"legendFormat": "",
"range": true,
"refId": "B",
"step": 240
}
],
"title": "Memory Usage per Container",
"type": "timeseries"
},
{
"collapsed": false,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 42
},
"id": 56,
"panels": [],
"title": "Network",
"type": "row"
},
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 10,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"lineInterpolation": "linear",
"lineWidth": 2,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "auto",
"spanNulls": true,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
},
"unit": "Bps"
},
"overrides": []
},
"gridPos": {
"h": 7,
"w": 24,
"x": 0,
"y": 43
},
"id": 58,
"links": [],
"options": {
"legend": {
"calcs": [],
"displayMode": "table",
"placement": "right",
"showLegend": true
},
"tooltip": {
"mode": "multi",
"sort": "none"
}
},
"pluginVersion": "9.5.1",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"editorMode": "code",
"expr": "sum(rate(container_network_receive_bytes_total{instance=~\"$cadvisor\", name=~\".+\"}[$interval])) by (name)",
"intervalFactor": 2,
"legendFormat": "",
"range": true,
"refId": "A",
"step": 240
},
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"editorMode": "code",
"expr": "- rate(container_network_transmit_bytes_total{instance=~\"$cadvisor\", name=~\".+\"}[$interval])",
"hide": true,
"intervalFactor": 2,
"legendFormat": "",
"range": true,
"refId": "B",
"step": 10
}
],
"title": "Received Network Traffic per Container",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 10,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"lineInterpolation": "linear",
"lineWidth": 2,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "auto",
"spanNulls": true,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
},
"unit": "Bps"
},
"overrides": []
},
"gridPos": {
"h": 7,
"w": 24,
"x": 0,
"y": 50
},
"id": 60,
"links": [],
"options": {
"legend": {
"calcs": [],
"displayMode": "table",
"placement": "right",
"showLegend": true
},
"tooltip": {
"mode": "multi",
"sort": "none"
}
},
"pluginVersion": "9.5.1",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"editorMode": "code",
"expr": "sum(rate(container_network_transmit_bytes_total{instance=~\"$cadvisor\", name=~\".+\"}[$interval])) by (name)",
"intervalFactor": 2,
"legendFormat": "",
"range": true,
"refId": "A",
"step": 240
},
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"editorMode": "code",
"expr": "rate(container_network_transmit_bytes_total{instance=~\"$cadvisor\", id=\"/\"}[$interval])",
"hide": true,
"intervalFactor": 2,
"legendFormat": "",
"range": true,
"refId": "B",
"step": 10
}
],
"title": "Sent Network Traffic per Container",
"type": "timeseries"
},
{
"collapsed": false,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 57
},
"id": 32,
"panels": [],
"title": "Storage",
"type": "row"
},
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"description": "",
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "bytes",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 20,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "never",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"links": [],
"mappings": [],
"min": 0,
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
},
"unit": "bytes"
},
"overrides": []
},
"gridPos": {
"h": 10,
"w": 24,
"x": 0,
"y": 58
},
"id": 34,
"links": [],
"options": {
"legend": {
"calcs": [
"mean",
"lastNotNull",
"max",
"min"
],
"displayMode": "table",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "multi",
"sort": "none"
}
},
"pluginVersion": "9.5.1",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "node_filesystem_avail_bytes{instance=\"$nodeexporter\",job=\"$vm\",device!~'rootfs'}",
"format": "time_series",
"hide": false,
"intervalFactor": 1,
"legendFormat": " - Available",
"metric": "",
"refId": "A",
"step": 240
},
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "node_filesystem_free_bytes{instance=\"$nodeexporter\",job=\"$vm\",device!~'rootfs'}",
"format": "time_series",
"hide": true,
"intervalFactor": 1,
"legendFormat": " - Free",
"refId": "B",
"step": 240
},
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "node_filesystem_size_bytes{instance=\"$nodeexporter\",job=\"$vm\",device!~'rootfs'}",
"format": "time_series",
"hide": true,
"intervalFactor": 1,
"legendFormat": " - Size",
"refId": "C",
"step": 240
}
],
"title": "Filesystem space available",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"description": "",
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "%util",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 40,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "never",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"links": [],
"mappings": [],
"min": 0,
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
},
"unit": "percentunit"
},
"overrides": [
{
"matcher": {
"id": "byName",
"options": "io time"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "#890F02",
"mode": "fixed"
}
}
]
},
{
"matcher": {
"id": "byType",
"options": "time"
},
"properties": [
{
"id": "custom.axisPlacement",
"value": "hidden"
}
]
}
]
},
"gridPos": {
"h": 9,
"w": 24,
"x": 0,
"y": 68
},
"id": 74,
"links": [],
"options": {
"legend": {
"calcs": [
"mean",
"lastNotNull",
"max",
"min"
],
"displayMode": "table",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "multi",
"sort": "none"
}
},
"pluginVersion": "9.5.1",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "rate(node_disk_io_time_seconds_total{instance=\"$nodeexporter\",job=\"$vm\",device=~\"$diskdevices\"} [$__rate_interval])",
"format": "time_series",
"hide": false,
"interval": "",
"intervalFactor": 1,
"legendFormat": "",
"refId": "A",
"step": 240
}
],
"title": "I/O Utilization",
"type": "timeseries"
},
{
"collapsed": false,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 77
},
"id": 44,
"panels": [],
"title": "Informations",
"type": "row"
},
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"description": "",
"fieldConfig": {
"defaults": {
"color": {
"mode": "fixed"
},
"custom": {
"align": "auto",
"cellOptions": {
"type": "auto"
},
"filterable": false,
"inspect": false
},
"decimals": 0,
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
}
]
},
"unit": "none"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 78
},
"hideTimeOverride": false,
"id": 46,
"links": [],
"options": {
"cellHeight": "sm",
"footer": {
"countRows": false,
"enablePagination": false,
"fields": "",
"reducer": [
"sum"
],
"show": false
},
"showHeader": false
},
"pluginVersion": "9.5.2",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"editorMode": "code",
"exemplar": true,
"expr": "cadvisor_version_info{instance=~\"$nodeexporter\",job=\"$vm\"}",
"format": "time_series",
"instant": false,
"interval": "",
"intervalFactor": 1,
"legendFormat": "cAdvisor Version: ",
"refId": "A",
"step": 2
},
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"editorMode": "code",
"exemplar": true,
"expr": "prometheus_build_info{instance=~\"$nodeexporter\",job=\"$vm\"}",
"interval": "",
"intervalFactor": 1,
"legendFormat": "Prometheus Version: ",
"range": true,
"refId": "B",
"step": 2
},
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"editorMode": "code",
"exemplar": true,
"expr": "node_exporter_build_info{instance=~\"$nodeexporter\",job=\"$vm\"}",
"interval": "",
"intervalFactor": 1,
"legendFormat": "Node-Exporter Version: ",
"range": true,
"refId": "C",
"step": 2
},
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"editorMode": "code",
"exemplar": true,
"expr": "cadvisor_version_info{instance=~\"$cadvisor\",job=\"$vm\"}",
"hide": false,
"interval": "",
"intervalFactor": 1,
"legendFormat": "Docker Version: ",
"range": true,
"refId": "D",
"step": 2
},
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"editorMode": "code",
"exemplar": true,
"expr": "cadvisor_version_info{instance=~\"$cadvisor\",job=\"$vm\"}",
"interval": "",
"intervalFactor": 1,
"legendFormat": "Host OS Version: ",
"range": true,
"refId": "E",
"step": 2
},
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"editorMode": "code",
"exemplar": true,
"expr": "cadvisor_version_info{instance=~\"$cadvisor\",job=\"$vm\"}",
"interval": "",
"intervalFactor": 1,
"legendFormat": "Host Kernel Version: ",
"range": true,
"refId": "F",
"step": 2
}
],
"title": "Stack Info",
"transformations": [
{
"id": "reduce",
"options": {
"includeTimeField": false,
"labelsToFields": false,
"reducers": [
"mean"
]
}
},
{
"id": "organize",
"options": {
"excludeByName": {
"Mean": true
},
"indexByName": {},
"renameByName": {
"Field": "Stack Info",
"Mean": ""
}
}
}
],
"type": "table"
},
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"decimals": 2,
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "yellow",
"value": 102400
},
{
"color": "orange",
"value": 512000
},
{
"color": "dark-orange",
"value": 1048576
},
{
"color": "semi-dark-red",
"value": 5242880
}
]
},
"unit": "deckbytes"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 78
},
"id": 72,
"links": [],
"options": {
"displayMode": "basic",
"minVizHeight": 10,
"minVizWidth": 0,
"orientation": "horizontal",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"showUnfilled": true,
"text": {
"valueSize": 10
},
"valueMode": "color"
},
"pluginVersion": "9.5.2",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"editorMode": "builder",
"exemplar": false,
"expr": "container_memory_usage_bytes{instance=~\"$cadvisor\", name=~\".+\"} / 1024",
"format": "time_series",
"hide": false,
"instant": false,
"intervalFactor": 2,
"legendFormat": "",
"range": true,
"refId": "A",
"step": 240
}
],
"title": "Usage memory",
"type": "bargauge"
}
],
"refresh": "5m",
"schemaVersion": 38,
"style": "dark",
"tags": [
"Zogg",
"Prometheus",
"Linux",
"cAdvisor",
"NodeExporter",
"Grafana"
],
"templating": {
"list": [
{
"current": {
"selected": false,
"text": "Mimir",
"value": "Mimir"
},
"hide": 2,
"includeAll": false,
"label": "datasource",
"multi": false,
"name": "DS_PROMETHEUS",
"options": [],
"query": "prometheus",
"queryValue": "",
"refresh": 1,
"regex": "",
"skipUrlSync": false,
"type": "datasource"
},
{
"auto": true,
"auto_count": 50,
"auto_min": "50s",
"current": {
"selected": false,
"text": "auto",
"value": "$__auto_interval_interval"
},
"hide": 0,
"label": "Interval",
"name": "interval",
"options": [
{
"selected": true,
"text": "auto",
"value": "$__auto_interval_interval"
},
{
"selected": false,
"text": "30s",
"value": "30s"
},
{
"selected": false,
"text": "1m",
"value": "1m"
},
{
"selected": false,
"text": "2m",
"value": "2m"
},
{
"selected": false,
"text": "3m",
"value": "3m"
},
{
"selected": false,
"text": "5m",
"value": "5m"
},
{
"selected": false,
"text": "7m",
"value": "7m"
},
{
"selected": false,
"text": "10m",
"value": "10m"
},
{
"selected": false,
"text": "30m",
"value": "30m"
},
{
"selected": false,
"text": "1h",
"value": "1h"
},
{
"selected": false,
"text": "6h",
"value": "6h"
},
{
"selected": false,
"text": "12h",
"value": "12h"
},
{
"selected": false,
"text": "1d",
"value": "1d"
},
{
"selected": false,
"text": "7d",
"value": "7d"
},
{
"selected": false,
"text": "14d",
"value": "14d"
},
{
"selected": false,
"text": "30d",
"value": "30d"
}
],
"query": "30s,1m,2m,3m,5m,7m,10m,30m,1h,6h,12h,1d,7d,14d,30d",
"queryValue": "",
"refresh": 2,
"skipUrlSync": false,
"type": "interval"
},
{
"current": {
"selected": false,
"text": "services",
"value": "services"
},
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"definition": "label_values(node_uname_info, job)",
"hide": 0,
"includeAll": false,
"label": "VM",
"multi": false,
"name": "vm",
"options": [],
"query": {
"query": "label_values(node_uname_info, job)",
"refId": "StandardVariableQuery"
},
"refresh": 1,
"regex": "",
"skipUrlSync": false,
"sort": 1,
"type": "query"
},
{
"current": {
"selected": false,
"text": "template.home:9100",
"value": "template.home:9100"
},
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"definition": "label_values(node_uname_info{job=\"$vm\"},instance)",
"hide": 2,
"includeAll": false,
"label": "Exporter",
"multi": false,
"name": "nodeexporter",
"options": [],
"query": {
"query": "label_values(node_uname_info{job=\"$vm\"},instance)",
"refId": "PrometheusVariableQueryEditor-VariableQuery"
},
"refresh": 1,
"regex": "",
"skipUrlSync": false,
"sort": 1,
"type": "query"
},
{
"current": {
"selected": false,
"text": "[a-z]+|nvme[0-9]+n[0-9]+|mmcblk[0-9]+",
"value": "[a-z]+|nvme[0-9]+n[0-9]+|mmcblk[0-9]+"
},
"hide": 2,
"includeAll": false,
"multi": false,
"name": "diskdevices",
"options": [
{
"selected": true,
"text": "[a-z]+|nvme[0-9]+n[0-9]+|mmcblk[0-9]+",
"value": "[a-z]+|nvme[0-9]+n[0-9]+|mmcblk[0-9]+"
}
],
"query": "[a-z]+|nvme[0-9]+n[0-9]+|mmcblk[0-9]+",
"skipUrlSync": false,
"type": "custom"
},
{
"current": {
"selected": false,
"text": "template.home:8080",
"value": "template.home:8080"
},
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"definition": "label_values(container_cpu_user_seconds_total{job=~\"$vm\"},instance)",
"hide": 2,
"includeAll": false,
"label": "Advisor",
"multi": false,
"name": "cadvisor",
"options": [],
"query": {
"query": "label_values(container_cpu_user_seconds_total{job=~\"$vm\"},instance)",
"refId": "PrometheusVariableQueryEditor-VariableQuery"
},
"refresh": 1,
"regex": "",
"skipUrlSync": false,
"sort": 1,
"type": "query"
},
{
"current": {
"selected": false,
"text": "192.168.50.102",
"value": "192.168.50.102"
},
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"definition": "label_values(node_boot_time_seconds{job=\"$vm\"},ip)",
"hide": 2,
"includeAll": false,
"label": "IP",
"multi": false,
"name": "ip",
"options": [],
"query": {
"query": "label_values(node_boot_time_seconds{job=\"$vm\"},ip)",
"refId": "PrometheusVariableQueryEditor-VariableQuery"
},
"refresh": 1,
"regex": "",
"skipUrlSync": false,
"sort": 0,
"type": "query"
}
]
},
"time": {
"from": "now-1h",
"to": "now"
},
"timepicker": {},
"timezone": "",
"title": "Monitoring",
"uid": "ZOGG0001",
"version": 3,
"weekStart": ""
}
Répertoires requis
Hormis les répertoires spécifié par les fichiers de configuration, il faudra créer les répertoires suivant :
- datas/alertmanager
- datas/mimir
- datas/prometheus
- datas/grafana/dashboards
- datas/grafana/datas
Mise en place
Je partirai du principe que vous utilisez Portainer pour gérer vos stack Docker.
Dans l’ordre, il vous faut créer les répertoires requis sous le dossier /opt/docker/monitoring.
Si vous choisissez de placer l’ensemble des fichiers ailleurs, il sera donc nécessaire de mettre à jour les chemins dans le docker-compose entre autre.
Ces informations doivent refléter votre propre besoin ou organisation sur votre disque.
Par défaut, pour des raisons de sécurité, l’ensemble des répertoires que j’utilise est positionné avec les droits utilisateur 1000:1000. Ce sera donc à ajuster au besoin selon votre cas.
Lorsque c’est fait, vous créez une nouvelle stack sous Portainer et copier/coller le contenu du fichier docker-compose.yml dans l’éditeur et vous lancez sa création.
Précisions
Il s’agit ici d’une configuration complète de monitoring.
Sur vos autres machines, il vous suffit de jouer le stack suivant sous Portainer :
[Fichier]
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
version: "3.0"
#
# updated: 2023-05-28
# stack: monitoring (light only to export VMs)
#
x-logging: &x-logging
logging:
driver: loki
options:
loki-url: "http://loki:3100/loki/api/v1/push"
loki-retries: "5"
loki-batch-size: "400"
x-common: &x-common
<<: *x-logging
restart: "no"
stop_grace_period: 5s
stdin_open: true
tty: true
privileged: false
security_opt:
- no-new-privileges=true
cap_drop:
- ALL
cap_add:
- KILL
dns:
- 1.1.1.1
- 8.8.8.8
- 1.0.0.1
- 8.8.4.4
ipc: "shareable"
extra_hosts:
- "template.home:192.168.0.0"
environment:
TZ: "Europe/Paris"
PUID: 1000
PGID: 1000
user: 1000:1000
labels:
com.centurylinklabs.watchtower.enable: true
logging: "promtail"
com.stack.name: "common"
com.stack.service.name: "common"
devices:
- /dev/kmsg:/dev/kmsg
deploy:
resources:
limits:
cpus: "0.50"
memory: 256M
ulimits:
nproc: 65535
nofile:
soft: 20000
hard: 40000
tmpfs:
- /tmp:rw,noexec,nosuid,size=64k
sysctls:
net.core.somaxconn: 1024
net.ipv4.tcp_syncookies: 0
x-volume-timezone: &x-volume-timezone "/etc/timezone:/etc/timezone:ro"
x-volume-localtime: &x-volume-localtime "/etc/localtime:/etc/localtime:ro"
x-volume-docker-socket: &x-volume-docker-socket "/var/run/docker.sock:/var/run/docker.sock:rw"
x-volume-cgroups: &x-volume-cgroups "/proc/cgroups:/cgroup:rw"
x-volume-ssl: &x-volume-ssl "/opt/docker/ssl:/ssl:ro"
services:
cadvisor:
<<: *x-common
user: 0:0
container_name: cadvisor
hostname: cadvisor
image: gcr.io/cadvisor/cadvisor:v0.47.1
restart: always
privileged: true
cap_add:
- SYS_PTRACE
ports:
- "8080:8080"
expose:
- "8080"
command:
- "--storage_duration=1m0s"
- "--allow_dynamic_housekeeping=true"
- "--housekeeping_interval=30s"
- "--global_housekeeping_interval=30s"
- "--event_storage_age_limit=default=0"
- "--event_storage_event_limit=default=0"
labels:
com.stack.name: "monitoring"
com.stack.service.name: "cadvisor"
volumes:
- *x-volume-timezone
- *x-volume-localtime
- *x-volume-docker-socket
- *x-volume-cgroups
- /var/lib/docker/:/var/lib/docker:ro
- /etc/machine-id:/etc/machine-id:ro
- /:/rootfs:ro
- /sys:/sys:ro
- /dev/disk/:/dev/disk:ro
- /var/run:/var/run:ro
node-exporter:
<<: *x-common
user: 0:0
container_name: node-exporter
hostname: node-exporter
image: prom/node-exporter:latest
restart: always
privileged: true
cap_add:
- SYS_ADMIN
ports:
- "9100:9100"
expose:
- "9100"
healthcheck:
test: wget --no-verbose --tries=1 --spider http://localhost:9100/ || exit 1
command:
- "--collector.arp"
- "--collector.bcache"
- "--collector.bonding"
- "--collector.btrfs"
- "--collector.conntrack"
- "--collector.cpu"
- "--collector.cpufreq"
- "--collector.diskstats"
- "--collector.dmi"
- "--collector.edac"
- "--collector.entropy"
- "--collector.fibrechannel"
- "--collector.filefd"
- "--collector.filesystem"
- "--collector.hwmon"
- "--collector.infiniband"
- "--collector.ipvs"
- "--collector.loadavg"
- "--collector.mdadm"
- "--collector.meminfo"
- "--collector.netclass"
- "--collector.netdev"
- "--collector.netstat"
- "--collector.nfs"
- "--collector.nfsd"
- "--collector.nvme"
- "--collector.os"
- "--collector.powersupplyclass"
- "--collector.pressure"
- "--collector.rapl"
- "--collector.schedstat"
- "--collector.selinux"
- "--collector.sockstat"
- "--collector.softnet"
- "--collector.stat"
- "--collector.tapestats"
- "--collector.textfile"
- "--collector.thermal_zone"
- "--collector.time"
- "--collector.timex"
- "--collector.udp_queues"
- "--collector.uname"
- "--collector.vmstat"
- "--collector.xfs"
- "--collector.zfs"
- "--collector.buddyinfo"
- "--collector.cgroups"
- "--collector.drbd"
- "--collector.ethtool"
- "--collector.interrupts"
- "--collector.ksmd"
- "--collector.lnstat"
- "--collector.logind"
- "--collector.meminfo_numa"
- "--collector.mountstats"
- "--collector.network_route"
- "--collector.ntp"
- "--collector.perf"
- "--collector.processes"
- "--collector.qdisc"
- "--collector.runit"
#- "--collector.slabinfo"
- "--collector.supervisord"
- "--collector.sysctl"
- "--collector.systemd"
- "--collector.tcpstat"
- "--collector.wifi"
- "--collector.zoneinfo"
- "--path.rootfs=/host"
- "--path.procfs=/host/proc"
- "--path.sysfs=/host/sys"
- "--collector.filesystem.ignored-mount-points='^(/rootfs|/host|)/(sys|proc|dev|host|etc)($$|/)'"
- "--collector.filesystem.ignored-fs-types='^(sys|proc|auto|cgroup|devpts|ns|au|fuse\\.lxc|mqueue)(fs|)$$'"
- "--collector.netdev.device-exclude='^(lo|veth.*)$'"
- "--collector.ethtool.device-exclude='^(lo|br-.*|docker0|flannel.*|veth.*)$'"
labels:
com.stack.name: "monitoring"
com.stack.service.name: "node-exporter"
volumes:
- *x-volume-timezone
- *x-volume-localtime
- *x-volume-docker-socket
- *x-volume-cgroups
- /etc/service:/etc/service:ro
- /:/host:ro,rslave
- /sys:/host/sys:ro
- /proc:/host/proc:ro
- /run/udev/data:/run/udev/data:ro
- /var/run/dbus/system_bus_socket:/var/run/dbus/system_bus_socket:ro
prometheus:
<<: *x-common
user: 0:0
cap_add:
- DAC_OVERRIDE
stop_grace_period: 60s
container_name: prometheus
hostname: prometheus
image: prom/prometheus:latest
restart: always
privileged: true
depends_on:
- cadvisor
- node-exporter
links:
- cadvisor
- node-exporter
ports:
- "9090:9090"
expose:
- "9090"
healthcheck:
test: wget --no-verbose --tries=1 --spider http://localhost:9090/ || exit 1
command:
- "--storage.tsdb.retention.time=30d"
- "--config.file=/etc/prometheus/prometheus.yml"
labels:
com.stack.name: "monitoring"
com.stack.service.name: "prometheus"
deploy:
resources:
limits:
memory: 1G
volumes:
- *x-volume-timezone
- *x-volume-localtime
- /opt/docker/monitoring/conf/prometheus.yml:/etc/prometheus/prometheus.yml:ro
- /opt/docker/monitoring/datas:/prometheus
Exploitation
Lorsque le stack complet est lancé et que l’ensemble des conteneurs à bien démarré, vous pouvez vous rendre sur :
1
http://grafana:3000
Les information d’identification sont ici celles par défaut : admin / admin
Dashboard
Conclusion
Vous disposer maintenant des bases vous permettant de mettre en place un système de surveillance complet d’une ou plusieurs machines.
Vous avez aussi la possibilité d’effectuer une surveillance active grâce aux alertes prises en comptes par Alertmanager mais vous pouvez aussi en définir au sein de Grafana.
Si vous souhaiter tester des requêtes en PromQL (le language de requêtes de Prometheus utilisé aussi par Grafana), il suffit de vous rendre sur:
1
http://prometheus:9090
Le suivi de Mimi se fait ici :
1
http://mimir:9009
Et le suivi des alertes levées par Alertmanager se fait ici :
1
http://alertmanager:9093
Bon monitoring :)
Petit bonus
Vive les alertes automatisées pour suivre simplement l’état de vos machines :
Cet article est sous licence CC BY 4.0 par l'auteur.