-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathotel-coll-daemonset.yml
336 lines (317 loc) · 14.3 KB
/
otel-coll-daemonset.yml
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
mode: daemonset
presets:
logsCollection:
enabled: true
includeCollectorLogs: true
kubernetesAttributes:
enabled: true
resources:
limits:
cpu: 3000m
memory: 3Gi
extraEnvs:
- name: MIMIR_USER
valueFrom:
secretKeyRef:
name: grafana-cloud
key: mimirUser
- name: MIMIR_PASS
valueFrom:
secretKeyRef:
name: grafana-cloud
key: mimirPass
- name: LOKI_USER
valueFrom:
secretKeyRef:
name: grafana-cloud
key: lokiUser
- name: LOKI_PASS
valueFrom:
secretKeyRef:
name: grafana-cloud
key: lokiPass
- name: KUBE_NODE_NAME
valueFrom:
fieldRef:
fieldPath: spec.nodeName
clusterRole:
rules:
- apiGroups:
- ''
resources:
- 'services'
- 'events'
- 'namespaces'
- 'namespaces/status'
- 'nodes'
- 'nodes/spec'
- 'pods'
- 'pods/status'
- 'replicationcontrollers'
- 'replicationcontrollers/status'
- 'resourcequotas'
- 'nodes/proxy'
- 'endpoints'
verbs:
- 'get'
- 'list'
- 'watch'
- apiGroups:
- apps
resources:
- 'daemonsets'
- 'deployments'
- 'replicasets'
- 'statefulsets'
verbs:
- 'get'
- 'list'
- 'watch'
- apiGroups:
- extensions
resources:
- daemonsets
- deployments
- replicasets
verbs:
- get
- list
- watch
- apiGroups:
- batch
resources:
- jobs
- cronjobs
verbs:
- get
- list
- watch
- apiGroups:
- autoscaling
resources:
- horizontalpodautoscalers
verbs:
- get
- list
- watch
- apiGroups:
- 'events.k8s.io'
resources:
- events
verbs:
- watch
- nonResourceURLs:
- /metrics
verbs:
- get
config:
receivers:
filelog:
include:
- /var/log/pods/*/*/*.log
start_at: beginning
include_file_path: true
include_file_name: false
operators:
# Find out which format is used by kubernetes
- type: router
id: get-format
routes:
- output: parser-docker
expr: 'body matches "^\\{"'
- output: parser-crio
expr: 'body matches "^[^ Z]+ "'
- output: parser-containerd
expr: 'body matches "^[^ Z]+Z"'
# Parse CRI-O format
- type: regex_parser
id: parser-crio
regex: '^(?P<time>[^ Z]+) (?P<stream>stdout|stderr) (?P<logtag>[^ ]*) ?(?P<log>.*)$'
output: extract_metadata_from_filepath
timestamp:
parse_from: attributes.time
layout_type: gotime
layout: '2006-01-02T15:04:05.999999999Z07:00'
# Parse CRI-Containerd format
- type: regex_parser
id: parser-containerd
regex: '^(?P<time>[^ ^Z]+Z) (?P<stream>stdout|stderr) (?P<logtag>[^ ]*) ?(?P<log>.*)$'
output: extract_metadata_from_filepath
timestamp:
parse_from: attributes.time
layout: '%Y-%m-%dT%H:%M:%S.%LZ'
# Parse Docker format
- type: json_parser
id: parser-docker
output: extract_metadata_from_filepath
timestamp:
parse_from: attributes.time
layout: '%Y-%m-%dT%H:%M:%S.%LZ'
- type: move
from: attributes.log
to: body
# Extract metadata from file path
- type: regex_parser
id: extract_metadata_from_filepath
regex: '^.*\/(?P<namespace>[^_]+)_(?P<pod_name>[^_]+)_(?P<uid>[a-f0-9\-]{36})\/(?P<container_name>[^\._]+)\/(?P<restart_count>\d+)\.log$'
parse_from: attributes["log.file.path"]
cache:
size: 128 # default maximum amount of Pods per Node is 110
# Rename attributes
- type: move
from: attributes["log.file.path"]
to: resource["filename"]
- type: move
from: attributes.container_name
to: resource["container"]
- type: move
from: attributes.namespace
to: resource["namespace"]
- type: move
from: attributes.pod_name
to: resource["pod"]
- type: add
field: resource["cluster"]
value: "bdrck-sbx-cluster" # Set your cluster name here
prometheus:
config:
scrape_configs:
- job_name: opentelemetry-collector
scrape_interval: 15s
static_configs:
- targets:
- ${MY_POD_IP}:8888
- job_name: integrations/node_exporter
kubernetes_sd_configs:
- namespaces:
names:
- observability
role: pod
selectors:
- role: pod
# only scrape data from pods running on the same node as collector
field: "spec.nodeName=$KUBE_NODE_NAME"
relabel_configs:
- action: keep
regex: prometheus-node-exporter.*
source_labels:
- __meta_kubernetes_pod_label_app_kubernetes_io_name
- action: replace
source_labels:
- __meta_kubernetes_pod_node_name
target_label: instance
- action: replace
source_labels:
- __meta_kubernetes_namespace
target_label: namespace
metric_relabel_configs:
- source_labels: [__name__]
action: keep
regex: 'kubelet_running_containers|go_goroutines|kubelet_runtime_operations_errors_total|cluster:namespace:pod_cpu:active:kube_pod_container_resource_limits|namespace_memory:kube_pod_container_resource_limits:sum|kubelet_volume_stats_inodes_used|kubelet_certificate_manager_server_ttl_seconds|namespace_workload_pod:kube_pod_owner:relabel|kubelet_node_config_error|kube_daemonset_status_number_misscheduled|kube_pod_container_resource_requests|namespace_cpu:kube_pod_container_resource_limits:sum|container_memory_working_set_bytes|container_fs_reads_bytes_total|kube_node_status_condition|namespace_cpu:kube_pod_container_resource_requests:sum|kubelet_server_expiration_renew_errors|container_fs_writes_total|kube_horizontalpodautoscaler_status_desired_replicas|node_filesystem_avail_bytes|kube_pod_status_reason|node_filesystem_size_bytes|kube_deployment_spec_replicas|kube_statefulset_metadata_generation|namespace_workload_pod|storage_operation_duration_seconds_count|kubelet_certificate_manager_client_expiration_renew_errors|kube_pod_container_resource_limits|kube_statefulset_status_replicas_updated|node_namespace_pod_container:container_memory_rss|kube_statefulset_status_observed_generation|node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate|kubelet_pleg_relist_interval_seconds_bucket|kube_job_status_start_time|kube_deployment_status_observed_generation|kubelet_pod_worker_duration_seconds_bucket|container_memory_cache|kube_resourcequota|kube_horizontalpodautoscaler_spec_min_replicas|namespace_memory:kube_pod_container_resource_requests:sum|kube_persistentvolumeclaim_resource_requests_storage_bytes|kube_daemonset_status_number_available|kube_job_failed|storage_operation_errors_total|cluster:namespace:pod_memory:active:kube_pod_container_resource_limits|container_fs_writes_bytes_total|kube_statefulset_replicas|kube_replicaset_owner|container_network_receive_bytes_total|volume_manager_total_volumes|kube_horizontalpodautoscaler_spec_max_replicas|kube_daemonset_status_desired_number_scheduled|kube_pod_container_status_waiting_reason|process_cpu_seconds_total|kube_node_status_allocatable|kube_deployment_status_replicas_available|kube_daemonset_status_updated_number_scheduled|container_network_receive_packets_total|container_memory_rss|container_cpu_usage_seconds_total|kube_namespace_status_phase|cluster:namespace:pod_memory:active:kube_pod_container_resource_requests|kubelet_volume_stats_available_bytes|kube_deployment_status_replicas_updated|kubelet_running_container_count|kube_node_info|container_network_transmit_packets_dropped_total|kubelet_certificate_manager_client_ttl_seconds|kube_pod_owner|kubelet_volume_stats_inodes|kubelet_runtime_operations_total|container_cpu_cfs_throttled_periods_total|kubelet_cgroup_manager_duration_seconds_bucket|kubelet_running_pod_count|container_network_transmit_packets_total|kubelet_node_name|kube_daemonset_status_current_number_scheduled|kube_statefulset_status_replicas_ready|cluster:namespace:pod_cpu:active:kube_pod_container_resource_requests|kubelet_volume_stats_capacity_bytes|kube_horizontalpodautoscaler_status_current_replicas|node_quantile:kubelet_pleg_relist_duration_seconds:histogram_quantile|kube_node_spec_taint|kubelet_pleg_relist_duration_seconds_bucket|kube_pod_status_phase|container_cpu_cfs_periods_total|kube_deployment_metadata_generation|node_namespace_pod_container:container_memory_cache|kube_statefulset_status_current_revision|kubelet_pleg_relist_duration_seconds_count|container_fs_reads_total|kube_statefulset_status_update_revision|container_network_receive_packets_dropped_total|kube_pod_info|kubelet_running_pods|process_resident_memory_bytes|kubelet_pod_worker_duration_seconds_count|kubelet_pod_start_duration_seconds_count|kubelet_cgroup_manager_duration_seconds_count|kube_node_status_capacity|container_network_transmit_bytes_total|rest_client_requests_total|kubernetes_build_info|machine_memory_bytes|kube_statefulset_status_replicas|container_memory_swap|kube_job_status_active|kubelet_pod_start_duration_seconds_bucket|node_namespace_pod_container:container_memory_working_set_bytes|node_namespace_pod_container:container_memory_swap|kube_namespace_status_phase|container_cpu_usage_seconds_total|kube_pod_status_phase|kube_pod_start_time|kube_pod_container_status_restarts_total|kube_pod_container_info|kube_pod_container_status_waiting_reason|kube_daemonset.*|kube_replicaset.*|kube_statefulset.*|kube_job.*|kube_node.*|node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate|cluster:namespace:pod_cpu:active:kube_pod_container_resource_requests|namespace_cpu:kube_pod_container_resource_requests:sum|node_cpu.*|node_memory.*|node_filesystem.*'
- job_name: "kubernetes-pods"
kubernetes_sd_configs:
- role: pod
selectors:
- role: pod
# only scrape data from pods running on the same node as collector
field: "spec.nodeName=$KUBE_NODE_NAME"
metric_relabel_configs:
- regex: autonomic_ai_(.+)_access
action: labeldrop
- regex: 'autonomic_ai_(team|app|component_full_name|tracing|managed_by_kapp|business_service|call_.+|allow_.+|hydra_.+)'
action: labeldrop
- regex: pod_template_hash
action: labeldrop
- regex: '(kafka|sidecar_istio_io_inject|kapp_k14s_io_association|app_kubernetes_io_managed_by|app_kubernetes_io_name|app_kubernetes_io_instance|app_kubernetes_io_version|app_kubernetes_io_component|heritage)'
action: labeldrop
- regex: '(beta_|)kubernetes_io_(arch|os)'
action: labeldrop
- regex: '(failure_domain_beta|topology)_kubernetes_io_region'
action: labeldrop
- regex: '(assets|chart|release|component|baseChart|coordinator|created_by|dns|groups|hasDNS|updatedAt|updatedBy)'
action: labeldrop
relabel_configs:
- source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_scrape]
action: keep
regex: true
- source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_path]
action: replace
target_label: __metrics_path__
regex: (.+)
- source_labels: [__address__, __meta_kubernetes_pod_annotation_prometheus_io_port]
action: replace
regex: ([^:]+)(?::\d+)?;(\d+)
replacement: $${1}:$${2}
target_label: __address__
- source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_scheme]
action: replace
target_label: __scheme__
regex: (https?)
- action: labelmap
regex: __meta_kubernetes_pod_annotation_prometheus_io_param_(.+)
replacement: __param_$$1
- action: labelmap
regex: __meta_kubernetes_pod_label_(.+)
- source_labels: [__meta_kubernetes_namespace]
action: replace
target_label: kubernetes_namespace
- source_labels: [__meta_kubernetes_pod_name]
action: replace
target_label: kubernetes_pod_name
extensions:
basicauth/metrics:
client_auth:
username: "${MIMIR_USER}"
password: "${MIMIR_PASS}"
basicauth/logs:
client_auth:
username: "${LOKI_USER}"
password: "${LOKI_PASS}"
zpages:
endpoint: 0.0.0.0:55679
exporters:
prometheusremotewrite:
external_labels:
cluster: 'bdrck-sbx-cluster'
endpoint: "https://prometheus-us-central1.grafana.net/api/prom/push"
auth:
authenticator: basicauth/metrics
resource_to_telemetry_conversion:
enabled: true
target_info:
enabled: true
loki:
endpoint: "https://logs-prod-017.grafana.net/loki/api/v1/push"
auth:
authenticator: basicauth/logs
logging:
verbosity: detailed
processors:
memory_limiter:
check_interval: 1s
limit_percentage: 75
spike_limit_percentage: 50
batch:
send_batch_size: 10000
timeout: 10s
resourcedetection:
detectors: [env, gcp]
resource/logs:
attributes:
- action: insert
key: loki.format
value: raw
- action: insert
key: loki.resource.labels
value: pod, namespace, container, cluster, filename
service:
extensions: [ basicauth/metrics, basicauth/logs, health_check, memory_ballast, zpages ]
pipelines:
metrics:
receivers: [otlp, prometheus]
processors: [memory_limiter, batch, k8sattributes, resourcedetection]
exporters: [prometheusremotewrite]
logs:
receivers: [filelog]
processors: [batch, resource/logs, k8sattributes]
exporters: [loki]