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
| apiVersion: project.openshift.io/v1
kind: Project
metadata:
labels:
app: collectorforopenshift
name: collectorforopenshift
annotations:
openshift.io/node-selector: ''
openshift.io/description: 'Monitoring OpenShift in Splunk, built by Outcold Solutions'
openshift.io/display-name: 'Collectord for OpenShift'
---
apiVersion: apiextensions.k8s.io/v1
kind: CustomResourceDefinition
metadata:
name: configurations.collectord.io
spec:
group: collectord.io
versions:
- name: v1
served: true
storage: true
schema:
openAPIV3Schema:
type: object
properties:
spec:
type: object
additionalProperties: true
force:
type: boolean
scope: Cluster
names:
listKind: ConfigurationList
plural: configurations
singular: configuration
kind: Configuration
---
apiVersion: apiextensions.k8s.io/v1
kind: CustomResourceDefinition
metadata:
name: splunkoutputs.collectord.io
spec:
group: collectord.io
versions:
- name: v1
served: true
storage: true
schema:
openAPIV3Schema:
type: object
properties:
spec:
type: object
properties:
url:
type: string
format: uri
token:
type: string
insecure:
type: boolean
scope: Namespaced
names:
listKind: SplunkOutputList
plural: splunkoutputs
singular: splunkoutput
kind: SplunkOutput
---
apiVersion: scheduling.k8s.io/v1
kind: PriorityClass
metadata:
name: collectorforopenshift-critical
value: 1000000000
---
kind: SecurityContextConstraints
apiVersion: security.openshift.io/v1
metadata:
name: collectorforopenshift
allowHostDirVolumePlugin: true
allowHostIPC: true
allowHostNetwork: true
allowHostPID: true
allowHostPorts: true
allowPrivilegeEscalation: true
allowPrivilegedContainer: true
readOnlyRootFilesystem: false
allowedCapabilities:
- '*'
allowedUnsafeSysctls:
- '*'
fsGroup:
type: RunAsAny
runAsUser:
type: RunAsAny
seLinuxContext:
type: RunAsAny
supplementalGroups:
type: RunAsAny
seccompProfiles:
- '*'
users:
- system:serviceaccount:collectorforopenshift:collectorforopenshift
volumes:
- '*'
---
apiVersion: v1
kind: ServiceAccount
metadata:
labels:
app: collectorforopenshift
name: collectorforopenshift
namespace: collectorforopenshift
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
labels:
app: collectorforopenshift
name: collectorforopenshift
rules:
- apiGroups:
- ""
- apps
- batch
- extensions
- collectord.io
- apps.openshift.io
- build.openshift.io
- authorization.openshift.io
- template.openshift.io
- quota.openshift.io
resources:
- splunkoutputs
- alertmanagers
- cronjobs
- daemonsets
- deployments
- endpoints
- events
- jobs
- namespaces
- nodes
- nodes/metrics
- nodes/proxy
- pods
- replicasets
- replicationcontrollers
- scheduledjobs
- services
- statefulsets
- persistentvolumeclaims
- configurations
- resourcequotas
- deploymentconfigs
- clusterroles
- clusterresourcequotas
verbs:
- get
- list
- watch
- nonResourceURLs:
- /metrics
verbs:
- get
apiGroups: []
resources: []
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
labels:
app: collectorforopenshift
name: collectorforopenshift
roleRef:
kind: ClusterRole
name: collectorforopenshift
apiGroup: rbac.authorization.k8s.io
subjects:
- kind: ServiceAccount
name: collectorforopenshift
namespace: collectorforopenshift
---
apiVersion: v1
kind: ConfigMap
metadata:
name: collectorforopenshift
namespace: collectorforopenshift
labels:
app: collectorforopenshift
data:
001-general.conf: |
# The general configuration is used for all deployments
#
# Run collectord with the flag `-conf` and specify location of the configuration files.
#
# You can override all the values using environment variables with the format like
# COLLECTOR__<ANYNAME>=<section>__<key>=<value>
# As an example you can set `dataPath` in the `[general]` section as
# COLLECTOR__DATAPATH=general__dataPath=C:\\some\\path\\data.db
# This parameter can be configured using -env-override, set it to empty string to disable this feature
[general]
# Please review license https://www.outcoldsolutions.com/docs/license-agreement/
# and accept license by changing the value to *true*
acceptLicense = false
# Location for the database
# Collectord stores positions of the files and internal state
dataPath = ./data/
# log level (accepted values are trace, debug, info, warn, error, fatal)
logLevel = info
# http server gives access to two endpoints
# /healthz
# /metrics/json
# /metrics/prometheus
# httpServerBinding = 0.0.0.0:11888
httpServerBinding =
# log requests to the http server
httpServerLog = false
# telemetry report endpoint, set it to empty string to disable telemetry
telemetryEndpoint = https://license.outcold.solutions/telemetry/
# license check endpoint
licenseEndpoint = https://license.outcold.solutions/license/
# license server through proxy
# This configuration is used only for the Outcold Solutions License Server
# For license server running on-premises, use configuration under [license.client]
licenseServerProxyUrl =
# authentication with basic authorization (user:password)
# This configuration is used only for the Outcold Solutions License Server
# For license server running on-premises, use configuration under [license.client]
licenseServerProxyBasicAuth =
# license key
license =
# Environment variable $KUBERNETES_NODENAME is used by default to setup hostname
# Use value below to override specific name
hostname =
# Default output for events, logs and metrics
# valid values: splunk and devnull
# Use devnull by default if you don't want to redirect data
defaultOutput = splunk
# Default buffer size for file input
fileInputBufferSize = 256b
# Maximum size of one line the file reader can read
fileInputLineMaxSize = 1mb
# Include custom fields to attach to every event, in example below every event sent to Splunk will hav
# indexed field my_environment=dev. Fields names should match to ^[a-z][_a-z0-9]*$
# Better way to configure that is to specify labels for OpenShift Nodes.
# ; fields.my_environment = dev
# Identify the cluster if you are planning to monitor multiple clusters
fields.openshift_cluster = -
# Include EC2 Metadata (see list of possible fields https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/ec2-instance-metadata.html)
# Should be in format ec2Metadata.{desired_field_name} = {url path to read the value}
# ec2Metadata.ec2_instance_id = /latest/meta-data/instance-id
# ec2Metadata.ec2_instance_type = /latest/meta-data/instance-type
# subdomain for the annotations added to the pods, workloads, namespaces or containers, like splunk.collectord.io/..
annotationsSubdomain =
# configure global thruput per second for forwarded logs (metrics are not included)
# for example if you set `thruputPerSecond = 512Kb`, that will limit amount of logs forwarded
# from the single Collectord instance to 512Kb per second.
# You can configure thruput individually for the logs (including specific for container logs) below
thruputPerSecond =
# Configure events that are too old to be forwarded, for example 168h (7 days) - that will drop all events
# older than 7 days
tooOldEvents =
# Configure events that are too new to be forwarded, for example 1h - that will drop all events that are 1h in future
tooNewEvents =
# For input.files::X and application logs, when glob or match are configured, Collectord can automatically
# detect gzipped files and skip them (based on the extensions or magic numbers)
autoSkipGzipFiles = true
[license.client]
# point to the license located on the HTTP web server, or a hosted by the Collectord running as license server
url =
# basic authentication for the HTTP server
basicAuth =
# if SSL, ignore the certificate verification
insecure = false
# CA Path for the Server certificate
capath =
# CA Name fot the Server certificate
caname =
# license server through proxy
proxyUrl =
# authentication with basic authorization (user:password)
proxyBasicAuth =
# forward internal collectord metrics
[input.collectord_metrics]
# disable collectord internal metrics
disabled = false
# override type
type = openshift_prometheus
# how often to collect internal metrics
interval = 1m
# set output (splunk or devnull, default is [general]defaultOutput)
output =
# specify Splunk index
index =
# whitelist or blacklist the metrics
whitelist.1 = ^file_input_open$
whitelist.2 = ^file_input_read_bytes$
whitelist.3 = ^openshift_handlers$
whitelist.4 = ^pipe$
whitelist.5 = ^pipelines_num$
whitelist.6 = ^splunk_post_bytes_sum.*$
whitelist.7 = ^splunk_post_events_count_sum.*$
whitelist.8 = ^splunk_post_failed_requests$
whitelist.9 = ^splunk_post_message_max_lag_seconds_bucket.*$
whitelist.10 = ^splunk_post_requests_seconds_sum.*$
whitelist.11 = ^splunk_post_retries_required_sum.*$
# connection to kubernetes api
[general.kubernetes]
# Override service URL for Kubernetes (default is ${KUBERNETES_SERVICE_HOST}:${KUBERNETES_SERVICE_PORT})
serviceURL =
# Environment variable $KUBERNETES_NODENAME is used by default to setup nodeName
# Use it only when you need to override it
nodeName =
# Configuration to access the API server,
# see https://kubernetes.io/docs/tasks/access-application-cluster/access-cluster/#accessing-the-api-from-a-pod
# for details
tokenPath = /var/run/secrets/kubernetes.io/serviceaccount/token
certPath = /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
# Default timeout for http responses. The streaming/watch requests depend on this timeout.
timeout = 30m
# How long to keep the cache for the recent calls to API server (to limit number of calls when collectord discovers new pods)
metadataTTL = 30s
# regex to find pods
podsCgroupFilter = ^/([^/\s]+/)*kubepods(\.slice)?/((kubepods-)?(burstable|besteffort)(\.slice)?/)?([^/]*)pod([0-9a-f]{32}|[0-9a-f\-_]{36})(\.slice)?$
# regex to find containers in the pods
containersCgroupFilter = ^/([^/\s]+/)*kubepods(\.slice)?/((kubepods-)?(burstable|besteffort)(\.slice)?/)?([^/]*)pod([0-9a-f]{32}|[0-9a-f\-_]{36})(\.slice)?/(docker-|crio-|cri-\w+-)?[0-9a-f]{64}(\.scope)?(\/.+)?$
# path to the kubelet root location (use it to discover application logs for emptyDir)
# the expected format is `pods/{pod-id}/volumes/kubernetes.io~empty-dir/{volume-name}/_data/`
volumesRootDir = /rootfs/var/lib/kubelet/
# You can attach annotations as a metadata, using the format
# includeAnnotations.{key} = {regexp}
# For example if you want to include all annotations that starts with `prometheus.io` or `example.com` you can include
# the following format:
# includeAnnotations.1 = ^prometheus\.io.*
# includeAnnotations.2 = ^example\.com.*
# You can exclude labels from metadata, using the format
# excludeLabels.{key} = {regexp}
# For example if you want to exclude all labels that starts with `prometheus.io` or `example.com` you can include
# the following format:
# excludeLabels.1 = ^prometheus\.io.*
# excludeLabels.2 = ^example\.com.*
# watch for changes (annotations) in the objects
watch.namespaces = v1/namespace
watch.deploymentconfigs = apps.openshift.io/v1/deploymentconfig
watch.configurations = collectord.io/v1/configuration
# Collectord can review the assigned ClusterRole and traverse metadata for the Pods only for the Owner objects
# that are defined in the ClusterRole, ignoring anything else, it does not have access to.
# This way Collectord does not generate 403 requests on API Server
clusterRole = collectorforopenshift
# Alternative of telling Collectord about the ClusterRole is to manually list the objects.
# You can define which objects Collectord should traverse when it sees Owners.
; traverseOwnership.namespaces = v1/namespace
# Implementation of the watch protocol.
# 0 - use the default implementation (2)
# 1 - use the watch implementation that is optimized for the small number of objects (just issue one watch for all objects)
# 2 - use the watch implementation that is optimized for the large number of objects (paginate through the list of objects and issue watch for the last resource version)
watchImplementation = 2
# watch for pods annotations, setup prometheus collection
# for these pods
# Addon listens on Pod Network
# DaemonSets listen on Host Network
[input.prometheus_auto]
# disable prometheus auto discovery for pods
disabled = false
# override type
type = openshift_prometheus
# specify Splunk index
index =
# how often to collect prometheus metrics
interval = 60s
# request timeout
timeout = 60s
# include metrics help with the events
includeHelp = true
# http client timeout
timeout = 30s
# set output (splunk or devnull, default is [general]defaultOutput)
output =
# Include an Authorization header for the prometheus scrapper
# When configuring scrapping with collectord using annotations use prometheus.1-AuthorizationKey=key1
# authorization.key1 = Bearer FOO
# Splunk output
[output.splunk]
# Splunk HTTP Event Collector url
url =
# You can specify muiltiple splunk URls with
#
# urls.0 = https://server1:8088/services/collector/event/1.0
# urls.1 = https://server1:8088/services/collector/event/1.0
# urls.2 = https://server1:8088/services/collector/event/1.0
#
# Limitations:
# * The urls cannot have different path.
# Specify how URL should be picked up (in case if multiple is used)
# urlSelection = random|round-robin|random-with-round-robin
# where:
# * random - choose random url on first selection and after each failure (connection or HTTP status code >= 500)
# * round-robin - choose url starting from first one and bump on each failure (connection or HTTP status code >= 500)
# * random-with-round-robin - choose random url on first selection and after that in round-robin on each
# failure (connection or HTTP status code >= 500)
urlSelection = random-with-round-robin
# Splunk HTTP Event Collector Token
token =
# Allow invalid SSL server certificate
insecure = false
# minTLSVersion = TLSv1.2
# maxTLSVersion = TLSv1.3
# Path to CA cerificate
caPath =
# CA Name to verify
caName =
# path for client certificate (if required)
clientCertPath =
# path for client key (if required)
clientKeyPath =
# Events are batched with the maximum size set by batchSize and staying in pipeline for not longer
# than set by frequency
frequency = 5s
batchSize = 768K
# limit by the number of events (0 value has no limit on the number of events)
events = 50
# Splunk through proxy
proxyUrl =
# authentication with basic authorization (user:password)
proxyBasicAuth =
# Splunk acknowledgement url (.../services/collector/ack)
ackUrl =
# You can specify muiltiple splunk URls for ackUrl
#
# ackUrls.0 = https://server1:8088/services/collector/ack
# ackUrls.1 = https://server1:8088/services/collector/ack
# ackUrls.2 = https://server1:8088/services/collector/ack
#
# Make sure that they in the same order as urls for url, to make sure that this Splunk instance will be
# able to acknowledge the payload.
#
# Limitations:
# * The urls cannot have different path.
# Enable index acknowledgment
ackEnabled = false
# Index acknowledgment timeout
ackTimeout = 3m
# Timeout specifies a time limit for requests made by collectord.
# The timeout includes connection time, any
# redirects, and reading the response body.
timeout = 30s
# in case when pipeline can post to multiple indexes, we want to avoid posibility of blocking
# all pipelines, because just some events have incorrect index
dedicatedClientPerIndex = true
# possible values: RedirectToDefault, Drop, Retry
incorrectIndexBehavior = RedirectToDefault
# gzip compression level (nocompression, default, 1...9)
compressionLevel = default
# number of dedicated splunk output threads (to increase throughput above 4k events per second)
threads = 2
# Default algorithm between threads is roundrobin, but you can change it to weighted
; threadsAlgorithm = weighted
# if you want to exclude some preindexed fields from events
# excludeFields.openshift_pod_ip = true
# By default if there are no indexes defined on the message, Collectord sends the event without the index, and
# Splunk HTTP Event Collector going to use the default index for the Token. You can change that, and tell Collectord
# to ignore all events that don't have index defined explicitly
; requireExplicitIndex = true
# You can define if you want to truncate messages that are larger than 1M in length (or define your own size, like 256K)
; maximumMessageLength = 1M
# For messages generated from logs, include unique `event_id` in the event
; includeEventID = false
# Dedicated queue size for the output, default is 1024, larger queue sizes will require more memory,
# but will allow to handle more events in case of network issues
queueSize = 1024
# How many digits after the decimal point to keep for timestamps (0-9)
# Defaults to 3 (milliseconds)
# Change to 6 for microseconds
# Change to 9 for nanoseconds
; timestampPrecision = 3
002-daemonset.conf: |
# DaemonSet configuration is used for Nodes and Masters.
# connection to CRIO
[general.cri-o]
# url for CRIO API, only unix socket is supported
url = unix:///rootfs/var/run/crio/crio.sock
# Timeout for http responses to docker client. The streaming requests depend on this timeout.
timeout = 1m
# cgroup input
[input.system_stats]
# disable system level stats
disabled.host = false
disabled.cgroup = false
# cgroups fs location
pathCgroups = /rootfs/sys/fs/cgroup
# proc location
pathProc = /rootfs/proc
# how often to collect cgroup stats
statsInterval = 30s
# override type
type.host = openshift_stats_v2_host
type.cgroup = openshift_stats_v2_cgroup
# specify Splunk index
index.host =
index.cgroup =
# set output (splunk or devnull, default is [general]defaultOutput)
output.host =
output.cgroup =
# proc input
[input.proc_stats]
# disable proc level stats
disabled = false
# proc location
pathProc = /rootfs/proc
# how often to collect proc stats
statsInterval = 60s
# override type
type = openshift_proc_stats_v2
# specify Splunk index
index.host =
index.cgroup =
# proc filesystem includes by default system threads (there can be over 100 of them)
# these stats do not help with the observability
# excluding them can reduce the size of the index, performance of the searches and usage of the collector
includeSystemThreads = false
# set output (splunk or devnull, default is [general]defaultOutput)
output.host =
output.cgroup =
# Hide arguments for the processes, replacing with HIDDEN_ARGS(NUMBER)
hideArgs = false
# network stats
[input.net_stats]
# disable net stats
disabled = false
# proc path location
pathProc = /rootfs/proc
# how often to collect net stats
statsInterval = 30s
# override type
type = openshift_net_stats_v2
# specify Splunk index
index.host =
index.cgroup =
# set output (splunk or devnull, default is [general]defaultOutput)
output.host =
output.cgroup =
# network socket table
[input.net_socket_table]
# disable net stats
disabled = false
# proc path location
pathProc = /rootfs/proc
# how often to collect net stats
statsInterval = 30s
# override type
type = openshift_net_socket_table
# specify Splunk index
index.host =
index.cgroup =
# set output (splunk or devnull, default is [general]defaultOutput)
output.host =
output.cgroup =
# group connections by tcp_state, localAddr, remoteAddr (if localPort is not the port it is listening on)
# that can significally reduces the amount of events
group = true
# Collectord can watch for services, node, and pod IP addresses, and lookup the names
# for the IP addresses. Keeping this enabled can add a significant load on the API Server, with large number of pods.
disableLookup = false
# mount input (collects mount stats where kubelet runtime is stored)
[input.mount_stats]
# disable system level stats
disabled = false
# how often to collect mount stats
statsInterval = 30s
# override type
type = openshift_mount_stats
# specify Splunk index
index =
# set output (splunk or devnull, default is [general]defaultOutput)
output =
# diskstats input (collects /proc/diskstats)
[input.disk_stats]
# disable system level stats
disabled = false
# how often to collect mount stats
statsInterval = 30s
# override type
type = openshift_disk_stats
# specify Splunk index
index =
# set output (splunk or devnull, default is [general]defaultOutput)
output =
# Container Log files
[input.files]
# disable container logs monitoring
disabled = false
# root location of docker log files
# logs are expected in standard docker format like {containerID}/{containerID}-json.log
# rotated files
path = /rootfs/var/lib/docker/containers/
# root location of CRI-O files
# logs are expected in Kubernetes format, like {podID}/{containerName}/0.log
crioPath = /rootfs/var/log/pods/
# (obsolete) glob matching pattern for log files
# glob = */*-json.log*
# files are read using polling schema, when reach the EOF how often to check if files got updated
pollingInterval = 250ms
# how often to look for the new files under logs path
walkingInterval = 5s
# include verbose fields in events (file offset)
verboseFields = false
# override type
type = openshift_logs
# specify Splunk index
index =
# docker splits events when they are larger than 10-100k (depends on the docker version)
# we join them together by default and forward to Splunk as one event
joinPartialEvents = true
# In case if your containers report messages with terminal colors or other escape sequences
# you can enable strip for all the containers in one place.
# Better is to enable it only for required container with the label collectord.io/strip-terminal-escape-sequences=true
stripTerminalEscapeSequences = false
# Regexp used for stripping terminal colors, it does not stip all the escape sequences
# Read http://man7.org/linux/man-pages/man4/console_codes.4.html for more information
stripTerminalEscapeSequencesRegex = (\x1b\[\d{1,3}(;\d{1,3})*m)|(\x07)|(\x1b]\d+(\s\d)?;[^\x07]+\x07)|(.*\x1b\[K)
# sample output (-1 does not sample, 20 - only 20% of the logs should be forwarded)
samplingPercent = -1
# sampling key for hash based sampling (should be regexp with the named match pattern `key`)
samplingKey =
# set output (splunk or devnull, default is [general]defaultOutput)
output =
# configure default thruput per second for for each container log
# for example if you set `thruputPerSecond = 128Kb`, that will limit amount of logs forwarded
# from the single container to 128Kb per second.
thruputPerSecond =
# Configure events that are too old to be forwarded, for example 168h (7 days) - that will drop all events
# older than 7 days
tooOldEvents =
# Configure events that are too new to be forwarded, for example 1h - that will drop all events that are 1h in future
tooNewEvents =
# Application Logs
[input.app_logs]
# disable container application logs monitoring
disabled = false
# root location of mounts (applies to hostPath mounts only), if the hostPath differs inside container from the path on host
root = /rootfs/
# how often to review list of available volumes
syncInterval = 5s
# glob matching pattern for log files
glob = *.log*
# files are read using polling schema, when reach the EOF how often to check if files got updated
pollingInterval = 250ms
# how often to look for the new files under logs path
walkingInterval = 5s
# include verbose fields in events (file offset)
verboseFields = false
# override type
type = openshift_logs
# specify Splunk index
index =
# we split files using new line character, with this configuration you can specify what defines the new event
# after new line
eventPatternRegex = ^[^\s]
# Maximum interval of messages in pipeline
eventPatternMaxInterval = 100ms
# Maximum time to wait for the messages in pipeline
eventPatternMaxWait = 1s
# Maximum message size
eventPatternMaxSize = 1MB
# sample output (-1 does not sample, 20 - only 20% of the logs should be forwarded)
samplingPercent = -1
# sampling key for hash based sampling (should be regexp with the named match pattern `key`)
samplingKey =
# set output (splunk or devnull, default is [general]defaultOutput)
output =
# configure default thruput per second for for each container log
# for example if you set `thruputPerSecond = 128Kb`, that will limit amount of logs forwarded
# from the single container to 128Kb per second.
thruputPerSecond =
# Configure events that are too old to be forwarded, for example 168h (7 days) - that will drop all events
# older than 7 days
tooOldEvents =
# Configure events that are too new to be forwarded, for example 1h - that will drop all events that are 1h in future
tooNewEvents =
# Configure how long Collectord should keep the file descriptors open for files, that has not been forwarded yet
# When using PVC, and if pipeline is lagging behind, Collectord holding open fd for files, can cause long termination
# of pods, as kubelet cannot unmount the PVC volume from the system
maxHoldAfterClose = 1800s
[input.journald]
# disable host level logs
disabled = false
# root location of log files
path.persistent = /rootfs/var/log/journal/
# only if required
# path.volatile = /rootfs/run/log/journal/
# when reach end of journald, how often to pull
pollingInterval = 250ms
# if you don't want to forward journald from the beginning,
# set the oldest event in relative value, like -14h or -30m or -30s (h/m/s supported)
startFromRel =
# override type
type = openshift_host_logs
# specify Splunk index
index =
# sample output (-1 does not sample, 20 - only 20% of the logs should be forwarded)
samplingPercent = -1
# sampling key (should be regexp with the named match pattern `key`)
samplingKey =
# how often to reopen the journald to free old files
reopenInterval = 1h
# set output (splunk or devnull, default is [general]defaultOutput)
output =
# configure default thruput per second for this files group
# for example if you set `thruputPerSecond = 128Kb`, that will limit amount of logs forwarded
# from the files in this group to 128Kb per second.
thruputPerSecond =
# Configure events that are too old to be forwarded, for example 168h (7 days) - that will drop all events
# older than 7 days
tooOldEvents =
# Configure events that are too new to be forwarded, for example 1h - that will drop all events that are 1h in future
tooNewEvents =
# by default every new event should start from not space symbol
eventPattern = ^[^\s]
# By default ignoring verbose hyperkube logs (all INFO messages)
blacklist.0 = ^I\d+.*$
# whitelist.0 = ^regexp$
# blacklist.1 = ^regexp$
# Move Journald logs reader to a separate process, to prevent process from crashing in case of corrupted log files
spawnExternalProcess = false
# Pipe to join events (container logs only)
[pipe.join]
# disable joining event
disabled = false
# Maximum interval of messages in pipeline
maxInterval = 100ms
# Maximum time to wait for the messages in pipeline
maxWait = 1s
# Maximum message size
maxSize = 1MB
# Default pattern to indicate new message (should start not from space)
patternRegex = ^[^\s]
# (depricated, use annotations for settings up join rules)
# Define special event join patterns for matched events
# Section consist of [pipe.join::<name>]
# [pipe.join::my_app]
## Set match pattern for the fields
#; matchRegex.docker_container_image = my_app
#; matchRegex.stream = stdout
## All events start from '[<digits>'
#; patternRegex = ^\[\d+
# You can configure global replace rules for the events, which can help to remove sensitive data
# from logs before they are sent to Splunk. Those rules will be applied to all pipelines for container logs, host logs,
# application logs and events.
# In the following example we replace password=TEST with password=********
; [pipe.replace::name]
; patternRegex = (password=)([^\s]+)
; replace = $1********
[input.prometheus::kubelet]
# disable prometheus kubelet metrics
disabled = false
# override type
type = openshift_prometheus
# specify Splunk index
index =
# Override host (environment variables are supported)
host = ${KUBERNETES_NODENAME}
# Override source
source = kubelet
# how often to collect prometheus metrics
interval = 60s
# request timeout
timeout = 60s
# prometheus endpoint
endpoint = https://127.0.0.1:10250/metrics
# token for "Authorization: Bearer $(cat tokenPath)"
tokenPath = /var/run/secrets/kubernetes.io/serviceaccount/token
# server certificate for certificate validation
certPath = /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
# client certificate for authentication
clientCertPath =
# Allow invalid SSL server certificate
insecure = true
# include metrics help with the events
# can be useful to explore prometheus metrics
includeHelp = false
# set output (splunk or devnull, default is [general]defaultOutput)
output =
# filter only metrics used by dashboards
whitelist.1 = ^(kubernetes|openshift)_build_info$
whitelist.2 = ^kubelet_runtime_operations_duration_seconds_sum$
whitelist.3 = ^kubelet_docker_operations_duration_seconds_sum$
whitelist.4 = ^kubelet_network_plugin_operations_duration_seconds_sum$
whitelist.5 = ^kubelet_cgroup_manager_duration_seconds_sum$
whitelist.6 = ^storage_operation_duration_seconds_sum$
whitelist.7 = ^kubelet_docker_operations_errors_total$
whitelist.8 = ^kubelet_runtime_operations_errors_total$
whitelist.9 = ^rest_client_requests_total$
whitelist.10 = ^process_cpu_seconds_total$
whitelist.11 = ^process_resident_memory_bytes$
whitelist.12 = ^process_virtual_memory_bytes$
whitelist.13 = ^kubelet_volume_stats_.+$
; # Collectord reports if entropy is low (uncomment to use it)
; [diagnostics::node-entropy]
; settings.path = /rootfs/proc/sys/kernel/random/entropy_avail
; settings.interval = 1h
; settings.threshold = 800
# Collectord can report if node reboot is required (uncomment to use it)
[diagnostics::node-reboot-required]
settings.path = /rootfs/var/run/reboot-required*
settings.interval = 1h
# See https://www.kernel.org/doc/Documentation/admin-guide/hw-vuln/index.rst
# And https://www.kernel.org/doc/Documentation/ABI/testing/sysfs-devices-system-cpu
[diagnostics::cpu-vulnerabilities]
settings.path = /rootfs/sys/devices/system/cpu/vulnerabilities/*
settings.interval = 1h
003-daemonset-master.conf: |
[input.prometheus::kubernetes-api]
# disable prometheus kubernetes-api input
disabled = false
# override type
type = openshift_prometheus
# specify Splunk index
index =
# override host
host = ${KUBERNETES_NODENAME}
# override source
source = kubernetes-api
# how often to collect prometheus metrics
interval = 60s
# request timeout
timeout = 60s
# prometheus endpoint
# at first trying to get it from localhost (that way avoiding load balancer, if multiple)
# as fallback using proxy
endpoint.1localhost = https://127.0.0.1:8443/metrics
endpoint.2kubeapi = https://${KUBERNETES_SERVICE_HOST}:${KUBERNETES_SERVICE_PORT}/metrics
# token for "Authorization: Bearer $(cat tokenPath)"
tokenPath = /var/run/secrets/kubernetes.io/serviceaccount/token
# server certificate for certificate validation
certPath = /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
# client certificate for authentication
clientCertPath =
# Allow invalid SSL server certificate
insecure = true
# include metrics help with the events
includeHelp = false
# set output (splunk or devnull, default is [general]defaultOutput)
output =
# filter only metrics used by dashboards
whitelist.1 = ^(kubernetes|openshift)_build_info$
whitelist.2 = ^authenticated_user_requests$
whitelist.3 = ^apiserver_request_total$
whitelist.4 = ^process_cpu_seconds_total$
whitelist.5 = ^process_resident_memory_bytes$
whitelist.6 = ^process_virtual_memory_bytes$
[input.prometheus::controller]
# disable prometheus controller metrics
disabled = false
# override type
type = openshift_prometheus
# specify Splunk index
index =
# override host
host = ${KUBERNETES_NODENAME}
# override source
source = controller
# how often to collect prometheus metrics
interval = 60s
# request timeout
timeout = 60s
# prometheus endpoint
endpoint.https1 = https://:10257/metrics
endpoint.https2 = https://:8444/metrics
# token for "Authorization: Bearer $(cat tokenPath)"
tokenPath = /var/run/secrets/kubernetes.io/serviceaccount/token
# server certificate for certificate validation
certPath =
# client certificate for authentication
clientCertPath =
clientKeyPath =
# Allow invalid SSL server certificate
insecure = true
# include metrics help with the events
includeHelp = false
# set output (splunk or devnull, default is [general]defaultOutput)
output =
# filter only metrics used by dashboards
whitelist.1 = ^(kubernetes|openshift)_build_info$
whitelist.2 = ^process_cpu_seconds_total$
whitelist.3 = ^process_resident_memory_bytes$
whitelist.4 = ^process_virtual_memory_bytes$
whitelist.5 = ^node_collector_zone_size$
whitelist.6 = ^node_collector_zone_health$
whitelist.7 = ^node_collector_unhealthy_nodes_in_zone$
[input.prometheus::scheduler]
# disable prometheus scheduler metrics
disabled = false
# override type
type = openshift_prometheus
# specify Splunk index
index =
# override host
host = ${KUBERNETES_NODENAME}
# override source
source = scheduler
# how often to collect prometheus metrics
interval = 60s
# request timeout
timeout = 60s
# prometheus endpoint
endpoint.https1 = https://:10259/metrics
endpoint.https2 = https://:8444/metrics
# token for "Authorization: Bearer $(cat tokenPath)"
tokenPath = /var/run/secrets/kubernetes.io/serviceaccount/token
# server certificate for certificate validation
certPath =
# client certificate for authentication
clientCertPath =
clientKeyPath =
# Allow invalid SSL server certificate
insecure = true
# include metrics help with the events
includeHelp = false
# set output (splunk or devnull, default is [general]defaultOutput)
output =
# filter only metrics used by dashboards
whitelist.1 = ^(kubernetes|openshift)_build_info$
whitelist.2 = ^scheduler_e2e_scheduling_duration_seconds_sum$
whitelist.3 = ^scheduler_binding_duration_seconds_sum$
whitelist.4 = ^scheduler_scheduling_algorithm_duration_seconds_sum$
whitelist.5 = ^process_cpu_seconds_total$
whitelist.6 = ^process_resident_memory_bytes$
whitelist.7 = ^process_virtual_memory_bytes$
[input.prometheus::etcd]
# disable prometheus etcd metrics
disabled = false
# override type
type = openshift_prometheus
# specify Splunk index
index =
# override host
host = ${KUBERNETES_NODENAME}
# override source
source = etcd
# how often to collect prometheus metricd
interval = 60s
# prometheus endpoint
endpoint.https1 = https://:9979/metrics
endpoint.https2 = https://:9978/metrics
# token for "Authorization: Bearer $(cat tokenPath)"
tokenPath =
# server certificate for certificate validation
certPath = /rootfs/etc/kubernetes/static-pod-resources/etcd-certs/secrets/etcd-all-certs/etcd-serving-*.crt
# client certificate for authentication
clientCertPath = /rootfs/etc/kubernetes/static-pod-resources/etcd-certs/secrets/etcd-all-certs/etcd-peer-*.crt
clientKeyPath = /rootfs/etc/kubernetes/static-pod-resources/etcd-certs/secrets/etcd-all-certs/etcd-peer-*.key
# Allow invalid SSL server certificate
insecure = true
# include metrics help with the events
includeHelp = false
# set output (splunk or devnull, default is [general]defaultOutput)
output =
whitelist.1 = ^etcd_server_leader_changes_seen_total$
whitelist.2 = ^etcd_server_has_leader$
whitelist.3 = ^etcd_server_proposals_committed_total$
whitelist.4 = ^etcd_server_proposals_applied_total$
whitelist.5 = ^etcd_server_proposals_committed_total$
whitelist.6 = ^etcd_server_proposals_pending$
whitelist.7 = ^etcd_server_proposals_failed_total$
whitelist.8 = ^etcd_disk_wal_fsync_duration_seconds_sum$
whitelist.9 = ^etcd_disk_wal_fsync_duration_seconds_count$
whitelist.10 = ^etcd_disk_backend_commit_duration_seconds_sum$
whitelist.11 = ^etcd_disk_backend_commit_duration_seconds_count$
whitelist.12 = ^etcd_network_client_grpc_.*$
whitelist.13 = ^grpc_server_handled_total$
whitelist.14 = ^etcd_network_peer_round_trip_time_seconds_bucket$
whitelist.15 = ^process_cpu_seconds_total$
whitelist.16 = ^process_resident_memory_bytes$
whitelist.17 = ^process_virtual_memory_bytes$
whitelist.18 = ^process_open_fds$
whitelist.19 = ^process_max_fds$
whitelist.20 = ^etcd_disk_backend_commit_duration_seconds_bucket$
whitelist.21 = ^etcd_disk_wal_fsync_duration_seconds_bucket$
# Audit logs
[input.files::audit-logs]
# disable host level logs
disabled = false
# root location of for audit logs
path = /rootfs/var/log/kube-apiserver/
# glob matching files
glob = audit*.log
# files are read using polling schema, when reach the EOF how often to check if files got updated
pollingInterval = 250ms
# how often o look for the new files under logs path
walkingInterval = 5s
# include verbose fields in events (file offset)
verboseFields = false
# override type
type = openshift_host_logs
# specify Splunk index
index =
# field extraction
extraction =
# extractionMessageField =
# timestamp field
timestampField =
# format for timestamp
# the layout defines the format by showing how the reference time, defined to be `Mon Jan 2 15:04:05 -0700 MST 2006`
timestampFormat =
# timestamp location (if not defined by format)
timestampLocation =
# set output (splunk or devnull, default is [general]defaultOutput)
output =
# configure default thruput per second for this files group
# for example if you set `thruputPerSecond = 128Kb`, that will limit amount of logs forwarded
# from the files in this group to 128Kb per second.
thruputPerSecond =
# Configure events that are too old to be forwarded, for example 168h (7 days) - that will drop all events
# older than 7 days
tooOldEvents =
# Configure events that are too new to be forwarded, for example 1h - that will drop all events that are 1h in future
tooNewEvents =
# Blacklisting and whitelisting the logs
# whitelist.0 = ^regexp$
# blacklist.0 = ^regexp$
004-addon.conf: |
[general]
# addons can be run in parallel with agents
addon = true
[input.kubernetes_events]
# disable collecting kubernetes events
disabled = false
# override type
type = openshift_events
# specify Splunk index
index =
# set output (splunk or devnull, default is [general]defaultOutput)
output =
# exclude managed fields from the metadata
excludeManagedFields = true
[input.kubernetes_watch::pods]
# disable events
disabled = false
# Set the timeout for how often watch request should refresh the whole list
refresh = 10m
apiVersion = v1
kind = Pod
namespace =
# override type
type = openshift_objects
# specify Splunk index
index =
# set output (splunk or devnull, default is [general]defaultOutput)
output =
# exclude managed fields from the metadata
excludeManagedFields = true
# you can remove or hash some values in the events (after modifyValues you can define path in the JSON object,
# and the value can be hash:{hashFunction}, or remove to remove the object )
; modifyValues.object.data.* = hash:sha256
; modifyValues.object.metadata.annotations.* = remove
# You can exclude events by namespace with blacklist or whitelist only required namespaces
# blacklist.kubernetes_namespace = ^namespace0$
# whitelist.kubernetes_namespace = ^((namespace1)|(namespace2))$
[input.kubernetes_watch::resourcequota]
# disable events
disabled = false
# Set the timeout for how often watch request should refresh the whole list
refresh = 10m
apiVersion = v1
kind = ResourceQuota
namespace =
# override type
type = openshift_objects
# specify Splunk index
index =
# set output (splunk or devnull, default is [general]defaultOutput)
output =
# exclude managed fields from the metadata
excludeManagedFields = true
[input.kubernetes_watch::clusterresourcequota]
# disable events
disabled = false
# Set the timeout for how often watch request should refresh the whole list
refresh = 10m
apiVersion = quota.openshift.io/v1
kind = ClusterResourceQuota
namespace =
# override type
type = openshift_objects
# specify Splunk index
index =
# set output (splunk or devnull, default is [general]defaultOutput)
output =
# exclude managed fields from the metadata
excludeManagedFields = true
[input.kubernetes_watch::nodes]
# disable events
disabled = false
# Set the timeout for how often watch request should refresh the whole list
refresh = 10m
apiVersion = v1
kind = Node
namespace =
# override type
type = openshift_objects
# specify Splunk index
index =
# set output (splunk or devnull, default is [general]defaultOutput)
output =
# exclude managed fields from the metadata
excludeManagedFields = true
---
apiVersion: apps/v1
kind: DaemonSet
metadata:
name: collectorforopenshift
namespace: collectorforopenshift
labels:
app: collectorforopenshift
spec:
# Default updateStrategy is OnDelete. For collectord RollingUpdate is suitable
# When you update configuration
updateStrategy:
type: RollingUpdate
selector:
matchLabels:
daemon: collectorforopenshift
template:
metadata:
name: collectorforopenshift
labels:
daemon: collectorforopenshift
spec:
priorityClassName: collectorforopenshift-critical
dnsPolicy: ClusterFirstWithHostNet
hostNetwork: true
serviceAccountName: collectorforopenshift
# We run this DaemonSet only for Non-Masters
affinity:
nodeAffinity:
requiredDuringSchedulingIgnoredDuringExecution:
nodeSelectorTerms:
- matchExpressions:
- key: node-role.kubernetes.io/control-plane
operator: DoesNotExist
tolerations:
- operator: "Exists"
effect: "NoSchedule"
- operator: "Exists"
effect: "NoExecute"
containers:
- name: collectorforopenshift
# Stick to specific version
image: docker.io/outcoldsolutions/collectorforopenshift:5.24.443
securityContext:
privileged: true
runAsUser: 0
# Define your resources if you need. Defaults should be fine for most.
resources:
limits:
cpu: 2000m
memory: 512Mi
requests:
cpu: 500m
memory: 256Mi
env:
- name: KUBERNETES_NODENAME
valueFrom:
fieldRef:
fieldPath: spec.nodeName
- name: POD_NAME
valueFrom:
fieldRef:
fieldPath: metadata.name
volumeMounts:
# We store state in /data folder (file positions)
- name: collectorforopenshift-state
mountPath: /data
# Configuration file deployed with ConfigMap
- name: collectorforopenshift-config
mountPath: /config/
readOnly: true
# Rootfs
- name: rootfs
mountPath: /rootfs/
readOnly: false
mountPropagation: HostToContainer
# correct timezone
- name: localtime
mountPath: /etc/localtime
readOnly: true
volumes:
# We store state directly on host, change this location, if
# your persistent volume is somewhere else
- name: collectorforopenshift-state
hostPath:
path: /var/lib/collectorforopenshift/data/
type: DirectoryOrCreate
# Location of rootfs
- name: rootfs
hostPath:
path: /
# correct timezone
- name: localtime
hostPath:
path: /etc/localtime
# configuration from ConfigMap
- name: collectorforopenshift-config
configMap:
name: collectorforopenshift
items:
- key: 001-general.conf
path: 001-general.conf
- key: 002-daemonset.conf
path: 002-daemonset.conf
---
apiVersion: apps/v1
kind: DaemonSet
metadata:
name: collectorforopenshift-master
namespace: collectorforopenshift
labels:
app: collectorforopenshift
spec:
updateStrategy:
type: RollingUpdate
selector:
matchLabels:
daemon: collectorforopenshift
template:
metadata:
name: collectorforopenshift-master
labels:
daemon: collectorforopenshift
spec:
priorityClassName: collectorforopenshift-critical
dnsPolicy: ClusterFirstWithHostNet
hostNetwork: true
serviceAccountName: collectorforopenshift
# Deploy only on master
affinity:
nodeAffinity:
requiredDuringSchedulingIgnoredDuringExecution:
nodeSelectorTerms:
- matchExpressions:
- key: node-role.kubernetes.io/control-plane
operator: Exists
tolerations:
- operator: "Exists"
effect: "NoSchedule"
- operator: "Exists"
effect: "NoExecute"
containers:
- name: collectorforopenshift
image: docker.io/outcoldsolutions/collectorforopenshift:5.24.443
securityContext:
privileged: true
runAsUser: 0
resources:
limits:
cpu: 2000m
memory: 1024Mi
requests:
cpu: 500m
memory: 256Mi
env:
- name: KUBERNETES_NODENAME
valueFrom:
fieldRef:
fieldPath: spec.nodeName
- name: POD_NAME
valueFrom:
fieldRef:
fieldPath: metadata.name
volumeMounts:
- name: collectorforopenshift-state
mountPath: /data
- name: collectorforopenshift-config
mountPath: /config/
readOnly: true
# Rootfs
- name: rootfs
mountPath: /rootfs/
readOnly: false
mountPropagation: HostToContainer
- name: localtime
mountPath: /etc/localtime
readOnly: true
volumes:
- name: collectorforopenshift-state
hostPath:
path: /var/lib/collectorforopenshift/data/
type: DirectoryOrCreate
- name: rootfs
hostPath:
path: /
- name: localtime
hostPath:
path: /etc/localtime
- name: collectorforopenshift-config
configMap:
name: collectorforopenshift
items:
- key: 001-general.conf
path: 001-general.conf
- key: 002-daemonset.conf
path: 002-daemonset.conf
- key: 003-daemonset-master.conf
path: 003-daemonset-master.conf
---
apiVersion: apps/v1
kind: Deployment
metadata:
name: collectorforopenshift-addon
namespace: collectorforopenshift
labels:
app: collectorforopenshift
spec:
replicas: 1
selector:
matchLabels:
daemon: collectorforopenshift
template:
metadata:
name: collectorforopenshift-addon
labels:
daemon: collectorforopenshift
spec:
priorityClassName: collectorforopenshift-critical
serviceAccountName: collectorforopenshift
containers:
- name: collectorforopenshift
image: docker.io/outcoldsolutions/collectorforopenshift:5.24.443
securityContext:
privileged: true
runAsUser: 0
resources:
limits:
cpu: 1000m
memory: 512Mi
requests:
cpu: 200m
memory: 64Mi
env:
- name: KUBERNETES_NODENAME
valueFrom:
fieldRef:
fieldPath: spec.nodeName
- name: POD_NAME
valueFrom:
fieldRef:
fieldPath: metadata.name
volumeMounts:
- name: collectorforopenshift-state
mountPath: /data
- name: collectorforopenshift-config
mountPath: /config/
readOnly: true
volumes:
- name: collectorforopenshift-state
hostPath:
path: /var/lib/collectorforopenshift/data/
type: Directory
- name: collectorforopenshift-config
configMap:
name: collectorforopenshift
items:
- key: 001-general.conf
path: 001-general.conf
- key: 004-addon.conf
path: 004-addon.conf
|
