Collectord configuration (Kubernetes version 1.24.x)
Download
link
collectorforkubernetes-opensearch.yaml
curl
$ curl -O https://www.outcoldsolutions.com/docs/elasticsearch-kubernetes/v5/configuration/opensearch/collectorforkubernetes-elasticsearch.yaml
wget
$ wget https://www.outcoldsolutions.com/docs/elasticsearch-kubernetes/v5/configuration/opensearch/collectorforkubernetes-elasticsearch.yaml
collectorforkubernetes-elasticsearch.yaml
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 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 | apiVersion: v1 kind: Namespace metadata: labels: app: collectorforkubernetes name: collectorforkubernetes --- 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: plural: configurations singular: configuration kind: Configuration --- apiVersion: v1 kind: ServiceAccount metadata: labels: app: collectorforkubernetes name: collectorforkubernetes namespace: collectorforkubernetes --- apiVersion: scheduling.k8s.io/v1 kind: PriorityClass metadata: name: collectorforkubernetes-critical value: 1000000000 --- apiVersion: rbac.authorization.k8s.io/v1 kind: ClusterRole metadata: labels: app: collectorforkubernetes name: collectorforkubernetes rules: - apiGroups: ['extensions'] resources: ['podsecuritypolicies'] verbs: ['use'] resourceNames: - privileged - apiGroups: - "" - apps - batch - extensions - rbac.authorization.k8s.io - collectord.io resources: - alertmanagers - cronjobs - daemonsets - deployments - endpoints - events - jobs - namespaces - nodes - nodes/metrics - nodes/proxy - pods - replicasets - replicationcontrollers - scheduledjobs - services - statefulsets - persistentvolumeclaims - configurations - resourcequotas - clusterroles - secrets - configmaps verbs: - get - list - watch - nonResourceURLs: - /metrics verbs: - get apiGroups: [] resources: [] --- apiVersion: rbac.authorization.k8s.io/v1 kind: ClusterRoleBinding metadata: labels: app: collectorforkubernetes name: collectorforkubernetes namespace: collectorforkubernetes roleRef: apiGroup: rbac.authorization.k8s.io kind: ClusterRole name: collectorforkubernetes subjects: - kind: ServiceAccount name: collectorforkubernetes namespace: collectorforkubernetes --- apiVersion: v1 kind: ConfigMap metadata: name: collectorforkubernetes-elasticsearch namespace: collectorforkubernetes labels: app: collectorforkubernetes-elasticsearch data: 001-general.conf: | # The general configuration is used for all deployments # # Run collector 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 [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 # Collector 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 = # 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 licenseServerProxyUrl = # authentication with basic authorization (user:password) licenseServerProxyBasicAuth = # license key license = # Environment variable $KUBERNETES_NODENAME is used by default to setup hostname # Use value below to override specific name # hostname = ${KUBERNETES_NODENAME}.second # Default output for events, logs and metrics # valid values: elasticsearch and devnull # Use devnull by default if you don't want to redirect data defaultOutput = elasticsearch # Default buffer size for file input fileInputBufferSize = 256b # Maximum size of one line the file reader can read fileInputLineMaxSize = 1mb # Include custom fields to attach to every event, in example below every event sent to elasticsearch will have # indexed field my_environment=dev. Fields names should match to ^[a-z][_a-z0-9\.]*$ # Better way to configure that is to specify labels for Kubernetes Nodes. # ; fields.my_environment = dev # Identify the cluster if you are planning to monitor multiple clusters # For ElasticSearch look at the ECS (Elastic Common Schema) documentation https://www.elastic.co/guide/en/ecs/current/ecs-field-reference.html fields.ecs.version = 8.0.0 fields.orchestrator.cluster.name = - fields.orchestrator.type = kubernetes fields.agent.type = collectord fields.agent.version = ${COLLECTORD_VERSION} fields.agent.ephemeral_id = ${COLLECTORD_INSTANCE_RUNTIME_ID} fields.agent.id = ${COLLECTORD_INSTANCE_ID} fields.agent.name = ${KUBERNETES_NODENAME} fields.host.name = ${KUBERNETES_NODENAME} fields.host.hostname = ${KUBERNETES_NODENAME} fields.host.architecture = ${COLLECTORD_ARCH} # 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.cloud.instance.id = /latest/meta-data/instance-id # ec2Metadata.cloud.machine.type = /latest/meta-data/instance-type # subdomain for the annotations added to the pods, workloads, namespaces or containers, like elasticsearch.collectord.io/.. annotationsSubdomain = elasticsearch # 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 = ; thruputPerSecond = 512Kb # 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 = [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 = # 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 collector discovers new pods) metadataTTL = 30s # 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.* # watch for changes (annotations) in the objects watch.namespaces = v1/namespace watch.deployments = apps/v1/deployment 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 = collectorforkubernetes # 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 # ElasticSearch output [output.elasticsearch] # Default data stream name dataStream = logs-collectord-{{agent.version}} dataStreamFailedEvents = logs-collectord-failed-{{agent.version}} # ElasticSearch Scheme Host and Port host = # You can specify muiltiple hosts with # # hosts.0 = https://es0:9200 # hosts.1 = https://es1:9200 # hosts.2 = https://es2:9200 # Specify how Hosts should be picked up (in case if multiple is used) # * 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) hostSelection = random-with-round-robin # Configuration for basic authorization authorizationBasicUsername = authorizationBasicPassword = # additional headers headers.Content-Type = application/json headers.Accept = application/json # Allow invalid SSL server certificate insecure = false # Path to CA certificate caPath = # CA Name to verify caName = # path for client certificate (if required) clientCertPath = # path for a client key (if required) clientKeyPath = # Events are batched with the maximum size set by batchSize and staying in a 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 # elasticsearch through proxy proxyUrl = # authentication with basic authorization (user:password) proxyBasicAuth = # Timeout specifies a time limit for requests made by collectord. # The timeout includes connection time, any # redirects, and reading the response body. timeout = 30s # gzip compression level (nocompression, default, 1...9) compressionLevel = default # number of dedicated elasticsearch 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 = roundrobin # Submit objects to elasticsearch #submit._ilm/policy/logs-collectord = /config/es-default-index-lifecycle-management-policy.json put._index_template/logs-collectord-${COLLECTORD_VERSION} = /config/es-default-index-template.json put._index_template/logs-collectord-failed-${COLLECTORD_VERSION} = /config/es-failed-index-template.json # 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 # Configure multiple outputs # [output.elasticsearch::app1] # host = http://esapp1:9200 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 [general.containerd] runtimePath = /rootfs/var/run/containerd namespace = k8s.io # 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 (including Containerd) files # logs are expected in Kubernetes format, like {podID}/{containerName}/0.log crioPath = /rootfs/var/log/pods/ # 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 # override type type = container # override datastream elasticsearch.datastream = # docker splits events when they are larger than 10-100k (depends on the docker version) # we join them together by default and forward to elasticsearch 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 (elasticsearch 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 = # by default every new event should start from not space symbol eventPattern = ^[^\s] # 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 = container.file # override datastream elasticsearch.datastream = # 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 (elasticsearch 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 # Host logs. Input syslog(.\d+)? files [input.files::syslog] # disable host level logs disabled = false # root location of docker files path = /rootfs/var/log/ # regex matching pattern match = ^(syslog|messages)(.\d+)?$ # limit search only on one level recursive = false # 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 = file # override datastream elasticsearch.datastream = # field extraction extraction = ^(?P<timestamp>[A-Za-z]+\s+\d+\s\d+:\d+:\d+)\s(?P<log__syslog__hostname>[^\s]+)\s(?P<log__syslog__appname>[^:\[]+)(\[(?P<log__syslog__procid>\d+)\])?: (.+)$ # extractionMessageField = # timestamp field timestampField = timestamp # 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 = Jan 2 15:04:05 # Adjust date, if month/day aren't set in format timestampSetMonth = false timestampSetDay = false # timestamp location (if not defined by format) timestampLocation = Local # 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 (elasticsearch 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] # Blacklisting and whitelisting the logs # whitelist.0 = ^regexp$ # blacklist.0 = ^regexp$ # Host logs. Input all *.log(.\d+)? files [input.files::logs] # disable host level logs disabled = false # root location of log files path = /rootfs/var/log/ # regex matching pattern match = ^(([\w\-.]+\.log(.[\d\-]+)?)|(docker))$ # 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 = file # override datastream elasticsearch.datastream = # field extraction extraction = # 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 = # 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 (elasticsearch 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] # Blacklisting and whitelisting the logs # whitelist.0 = ^regexp$ # blacklist.0 = ^regexp$ [input.journald] # disable host level logs disabled = false # root location of log files path.persistent = /rootfs/var/log/journal/ 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 = journald # override datastream elasticsearch.datastream = # 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 (elasticsearch or devnull, default is [general]defaultOutput) output = # configure default thruput per second for journald # for example if you set `thruputPerSecond = 128Kb`, that will limit amount of logs forwarded # from the journald 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] # Blacklisting and whitelisting the logs # whitelist.0 = ^regexp$ # blacklist.0 = ^regexp$ # 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] # 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 = $1******** 004-addon.conf: | [ general ] # addons can be run in parallel with agents addon = true [input.kubernetes_events] # disable events disabled = false # override type type = events # override datastream elasticsearch.datastream = # set output (elasticsearch or devnull, default is [general]defaultOutput) output = # exclude managed fields from the metadata excludeManagedFields = true [input.kubernetes_watch::pods] # disable events disabled = false # Set the timeout for how often watch request should refresh the whole list refresh = 10m apiVersion = v1 kind = pod namespace = excludeManagedFields = true # override type type = objects # override datastream elasticsearch.datastream = # set output (elasticsearch or devnull, default is [general]defaultOutput) output = # you can remove or hash some values in the events (after modifyValues you can define path in the JSON object, # and the value can be hash:{hashFunction}, or remove to remove the object ) ; modifyValues.object.data.* = hash:sha256 ; modifyValues.object.metadata.annotations.* = remove # You can exclude events by namespace with blacklist or whitelist only required namespaces # blacklist.kubernetes_namespace = ^namespace0$ # whitelist.kubernetes_namespace = ^((namespace1)|(namespace2))$ [input.kubernetes_watch::deployments] # disable events disabled = false # Set the timeout for how often watch request should refresh the whole list refresh = 10m apiVersion = apps/v1 kind = deployment namespace = excludeManagedFields = true # override type type = objects # override datastream elasticsearch.datastream = # set output (elasticsearch or devnull, default is [general]defaultOutput) output = es-default-index-lifecycle-management-policy.json: | { "policy": { "_meta": { "description": "Default policy for Collectord indexes", "version": 1 }, "phases": { "hot": { "min_age": "0ms", "actions": { "rollover": { "max_primary_shard_size": "50gb", "max_age": "30d" } } } } } } es-default-index-template.json: | { "version": 1, "data_stream": {}, "_meta": { "description": "Default template for Collectord indexes" }, "priority": 500, "template": { "settings": { "index": { "refresh_interval": "5s", "mapping": { "total_fields": { "limit": "10000" } }, "max_docvalue_fields_search": "200" }, "query": { "default_field": [ "message", "container.name", "container.image.name", "host.name", "orchestrator.namespace", "orchestrator.cluster.name", "container.name", "kubernetes.pod.name", "kubernetes.pod.id", "kubernetes.pod.ip", "kubernetes.namespace.name", "kubernetes.node.name", "kubernetes.cluster.name", "kubernetes.replicaset.name", "kubernetes.deployment.name", "kubernetes.statefulset.name", "kubernetes.daemonset.name", "kubernetes.job.name", "kubernetes.cronjob.name" ] } }, "mappings": { "dynamic_templates": [ { "kubernetes.pod.labels.*": { "path_match": "kubernetes.pod.labels.*", "mapping": { "type": "keyword" }, "match_mapping_type": "*" } }, { "kubernetes.namespace.labels.*": { "path_match": "kubernetes.namespace.labels.*", "mapping": { "type": "keyword" }, "match_mapping_type": "*" } }, { "kubernetes.node.labels.*": { "path_match": "kubernetes.node.labels.*", "mapping": { "type": "keyword" }, "match_mapping_type": "*" } }, { "kubernetes.daemonset.labels.*": { "path_match": "kubernetes.daemonset.labels.*", "mapping": { "type": "keyword" }, "match_mapping_type": "*" } }, { "kubernetes.replicaset.labels.*": { "path_match": "kubernetes.replicaset.labels.*", "mapping": { "type": "keyword" }, "match_mapping_type": "*" } }, { "kubernetes.deployment.labels.*": { "path_match": "kubernetes.deployment.labels.*", "mapping": { "type": "keyword" }, "match_mapping_type": "*" } }, { "kubernetes.statefulset.labels.*": { "path_match": "kubernetes.statefulset.labels.*", "mapping": { "type": "keyword" }, "match_mapping_type": "*" } }, { "kubernetes.job.labels.*": { "path_match": "kubernetes.job.labels.*", "mapping": { "type": "keyword" }, "match_mapping_type": "*" } }, { "kubernetes.cronjob.labels.*": { "path_match": "kubernetes.cronjob.labels.*", "mapping": { "type": "keyword" }, "match_mapping_type": "*" } }, { "strings_as_keyword": { "mapping": { "ignore_above": 1024, "type": "keyword" }, "match_mapping_type": "string" } } ], "properties": { "@timestamp": { "type": "date"}, "message":{"type":"text"}, "collectord_errors": {"type": "keyword","ignore_above": 1024}, "input":{"properties":{"type":{"ignore_above":1024,"type":"keyword"}}}, "container": {"properties": { "name": { "ignore_above": 1024, "type": "keyword"}, "id": { "ignore_above": 1024, "type": "keyword"}, "runtime": {"ignore_above": 1024, "type": "keyword"}, "image": {"properties": { "name": { "ignore_above": 1024, "type": "keyword"} }} } }, "event": {"properties": { "id": {"ignore_above": 1024, "type": "keyword"} }}, "host": {"properties": { "name": {"ignore_above": 1024, "type": "keyword"}, "architecture": {"ignore_above": 1024, "type": "keyword"}, "hostname": {"ignore_above": 1024, "type": "keyword"} }}, "log": { "properties": { "file": { "properties": { "path": {"ignore_above": 1024, "type": "keyword"} }}, "offset": {"type": "long"}, "syslog": {"properties": { "appname": {"ignore_above": 1024, "type": "keyword"}, "facility": {"properties": { "code": {"type": "long"} }}, "priority": {"type": "long"}, "procid": {"type": "long"}, "hostname": {"ignore_above": 1024, "type": "keyword"} }} }}, "orchestrator": {"properties": { "cluster": {"properties": { "name": {"ignore_above": 1024, "type": "keyword"} }}, "namespace": {"properties": { "name":{"path":"kubernetes.namespace.name","type":"alias"} }}, "type": {"ignore_above": 1024, "type": "keyword"} }}, "stream": {"ignore_above": 1024, "type": "keyword"}, "agent":{"properties":{ "hostname":{"path":"agent.name","type":"alias"}, "name":{"ignore_above":1024,"type":"keyword"}, "id":{"ignore_above":1024,"type":"keyword"}, "type":{"ignore_above":1024,"type":"keyword"}, "ephemeral_id":{"ignore_above":1024,"type":"keyword"}, "version":{"ignore_above":1024,"type":"keyword"} }}, "ecs":{"properties":{"version":{"ignore_above":1024,"type":"keyword"}}}, "kubernetes": { "properties": { "container": {"properties": { "imageid": {"ignore_above": 1024, "type": "keyword"} }}, "host": {"properties": { "ip": {"type": "ip"} }}, "namespace": {"properties": { "name": {"ignore_above": 1024, "type": "keyword"} }}, "node": { "properties": { "id": {"ignore_above": 1024, "type": "keyword"}, "name": {"ignore_above": 1024,"type": "keyword"} }}, "pod": {"properties": { "id": {"ignore_above": 1024,"type": "keyword"}, "ip": {"type": "ip"}, "name": {"ignore_above": 1024,"type": "keyword"} }}, "statefulset": { "properties": { "id": {"ignore_above": 1024,"type": "keyword"}, "name": {"ignore_above": 1024,"type": "keyword"} }}, "replicaset": {"properties": { "id": {"ignore_above": 1024,"type": "keyword"}, "name": {"ignore_above": 1024, "type": "keyword"} }}, "deployment": { "properties": { "id": {"ignore_above": 1024,"type": "keyword"}, "name": {"ignore_above": 1024,"type": "keyword" } }}, "cronjob": {"properties": { "id": {"ignore_above": 1024,"type": "keyword"}, "name": {"ignore_above": 1024, "type": "keyword"} }}, "job": {"properties": { "id": {"ignore_above": 1024,"type": "keyword"}, "name": {"ignore_above": 1024, "type": "keyword"} }} }}, "volume": {"properties": { "name": {"ignore_above": 1024,"type": "keyword"} }} } } }, "index_patterns": ["logs-collectord-${COLLECTORD_VERSION}"] } es-failed-index-template.json: | { "version": 1, "data_stream": {}, "_meta": { "description": "Default template for Collectord indexes for events that failed to be ingested" }, "priority": 1000, "template": { "settings": { "index": { "refresh_interval": "5s", "mapping": { "total_fields": { "limit": "10000" } }, "max_docvalue_fields_search": "200" }, "query": { "default_field": [ "message" ] } }, "mappings": { "properties": { "@timestamp": { "type": "date"}, "message": { "type": "text"} } } }, "index_patterns": [ "logs-collectord-failed-${COLLECTORD_VERSION}"] } --- apiVersion: apps/v1 kind: DaemonSet metadata: name: collectorforkubernetes-elasticsearch namespace: collectorforkubernetes labels: app: collectorforkubernetes-elasticsearch spec: updateStrategy: type: RollingUpdate selector: matchLabels: daemon: collectorforkubernetes-elasticsearch template: metadata: name: collectorforkubernetes-elasticsearch labels: daemon: collectorforkubernetes-elasticsearch spec: priorityClassName: collectorforkubernetes-critical dnsPolicy: ClusterFirstWithHostNet hostNetwork: true serviceAccountName: collectorforkubernetes tolerations: - operator: "Exists" effect: "NoSchedule" - operator: "Exists" effect: "NoExecute" containers: - name: collectorforkubernetes image: docker.io/outcoldsolutions/collectorforkubernetes:5.23.431 imagePullPolicy: Always securityContext: runAsUser: 0 privileged: true # Define your resources if you need. Defaults should be fine for most. # You can lower or increase based on your hosts. resources: limits: cpu: 2000m memory: 512Mi requests: cpu: 200m memory: 192Mi 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: collectorforkubernetes-state mountPath: /data # Configuration file deployed with ConfigMap - name: collectorforkubernetes-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: collectorforkubernetes-state hostPath: path: /var/lib/collectorforkubernetes-elasticsearch/data/ type: DirectoryOrCreate # Location of docker root (for container logs and metadata) - name: rootfs hostPath: path: / # correct timezone - name: localtime hostPath: path: /etc/localtime # configuration from ConfigMap - name: collectorforkubernetes-config configMap: name: collectorforkubernetes-elasticsearch items: - key: 001-general.conf path: 001-general.conf - key: 002-daemonset.conf path: 002-daemonset.conf - key: es-default-index-template.json path: es-default-index-template.json - key: es-default-index-lifecycle-management-policy.json path: es-default-index-lifecycle-management-policy.json - key: es-failed-index-template.json path: es-failed-index-template.json --- apiVersion: apps/v1 kind: Deployment metadata: name: collectorforkubernetes-elasticsearch-addon namespace: collectorforkubernetes labels: app: collectorforkubernetes-elasticsearch spec: replicas: 1 selector: matchLabels: daemon: collectorforkubernetes-elasticsearch template: metadata: name: collectorforkubernetes-elasticsearch-addon labels: daemon: collectorforkubernetes-elasticsearch spec: priorityClassName: collectorforkubernetes-critical serviceAccountName: collectorforkubernetes containers: - name: collectorforkubernetes image: docker.io/outcoldsolutions/collectorforkubernetes:5.23.431 imagePullPolicy: Always securityContext: runAsUser: 0 privileged: true resources: limits: cpu: 500m memory: 256Mi requests: cpu: 50m memory: 64Mi env: - name: KUBERNETES_NODENAME valueFrom: fieldRef: fieldPath: spec.nodeName - name: POD_NAME valueFrom: fieldRef: fieldPath: metadata.name volumeMounts: - name: collectorforkubernetes-state mountPath: /data - name: collectorforkubernetes-config mountPath: /config/ readOnly: true volumes: - name: collectorforkubernetes-state hostPath: path: /var/lib/collectorforkubernetes-elasticsearch/data/ type: Directory - name: collectorforkubernetes-config configMap: name: collectorforkubernetes-elasticsearch items: - key: 001-general.conf path: 001-general.conf - key: 004-addon.conf path: 004-addon.conf - key: es-default-index-template.json path: es-default-index-template.json - key: es-default-index-lifecycle-management-policy.json path: es-default-index-lifecycle-management-policy.json - key: es-failed-index-template.json path: es-failed-index-template.json |