unkinben
c39af2f9c3
Rework the logging pipeline around a durable message bus so logs survive a ClickHouse outage, can be replayed after a bad transform, and fan out to multiple independent consumers. Add long-term raw-log backup to S3. Topology becomes edge -> JetStream -> consumers -> sinks: - Dedicated JetStream NATS cluster (3 replicas, file storage) in the logging namespace. Deliberately separate from app messaging (streamstack) for blast-radius isolation. Stream LOGS (subjects logs.>, retention=limits, 40GiB / 72h) is the outage buffer; durable consumers give independent offsets. - Edge publishers (thin): the k8s DaemonSet and a new VM-ingest Deployment (HTTP NDJSON front door behind the logs-ingest Gateway) publish into JetStream (logs.k8s.<ns>.<container> / logs.vm.<host>). No parsing on the edge. - Transform tier (StatefulSet): pulls the whole stream via the durable `transform` consumer, routes by subject, shapes, and remains the sole ClickHouse writer. Its disk buffer shrinks (JetStream is the outage buffer). - Archiver (Deployment): its OWN durable `archiver` consumer (independent offsets — archive lag never affects the ClickHouse path) writes RAW, pre-transform events to a Ceph RGW S3 bucket (cephrgw-operator ObjectStoreUser + Bucket + BucketAccess) as gzipped NDJSON keyed by raw/<subject>/YYYY/MM/DD/. Default subject filter is Vault audit (logs.k8s.vault.>), configurable. Auth: distinct NATS users (producer publish-only, consumer pull+ack, admin for the stream/consumer bootstrap Job) with passwords from Vault (nats-auth Secret); S3 creds from the BucketAccess Secret. Streams/consumers are provisioned by an idempotent PostSync bootstrap Job. Add local kubeconform schemas for the ceph.unkin.net CRDs (datreeio lacks them) and extend the vector-test CI to cover the agent, VM-ingest and archiver configs. Verified end-to-end locally: NATS ACLs, vector JetStream publish, and durable-consumer pull+ack (at-least-once) all work. Claude-Session: https://claude.ai/code/session_015ur3i7D2azsMAWTSVABApv
133 lines
3.1 KiB
JSON
133 lines
3.1 KiB
JSON
{
|
|
"$schema": "http://json-schema.org/draft-07/schema#",
|
|
"properties": {
|
|
"apiVersion": {
|
|
"type": "string"
|
|
},
|
|
"kind": {
|
|
"type": "string"
|
|
},
|
|
"metadata": {
|
|
"type": "object"
|
|
},
|
|
"spec": {
|
|
"properties": {
|
|
"displayName": {
|
|
"type": "string"
|
|
},
|
|
"email": {
|
|
"type": "string"
|
|
},
|
|
"maxBuckets": {
|
|
"default": 1000,
|
|
"format": "int32",
|
|
"type": "integer"
|
|
},
|
|
"quota": {
|
|
"properties": {
|
|
"enabled": {
|
|
"default": true,
|
|
"type": "boolean"
|
|
},
|
|
"maxObjects": {
|
|
"format": "int64",
|
|
"type": "integer"
|
|
},
|
|
"maxSizeBytes": {
|
|
"format": "int64",
|
|
"type": "integer"
|
|
}
|
|
},
|
|
"type": "object"
|
|
},
|
|
"retainOnDelete": {
|
|
"type": "boolean"
|
|
},
|
|
"secretName": {
|
|
"type": "string"
|
|
},
|
|
"suspended": {
|
|
"type": "boolean"
|
|
},
|
|
"uid": {
|
|
"type": "string"
|
|
}
|
|
},
|
|
"type": "object"
|
|
},
|
|
"status": {
|
|
"properties": {
|
|
"adopted": {
|
|
"type": "boolean"
|
|
},
|
|
"conditions": {
|
|
"items": {
|
|
"properties": {
|
|
"lastTransitionTime": {
|
|
"format": "date-time",
|
|
"type": "string"
|
|
},
|
|
"message": {
|
|
"maxLength": 32768,
|
|
"type": "string"
|
|
},
|
|
"observedGeneration": {
|
|
"format": "int64",
|
|
"minimum": 0,
|
|
"type": "integer"
|
|
},
|
|
"reason": {
|
|
"maxLength": 1024,
|
|
"minLength": 1,
|
|
"pattern": "^[A-Za-z]([A-Za-z0-9_,:]*[A-Za-z0-9_])?$",
|
|
"type": "string"
|
|
},
|
|
"status": {
|
|
"enum": [
|
|
"True",
|
|
"False",
|
|
"Unknown"
|
|
],
|
|
"type": "string"
|
|
},
|
|
"type": {
|
|
"maxLength": 316,
|
|
"pattern": "^([a-z0-9]([-a-z0-9]*[a-z0-9])?(\\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)*/)?(([A-Za-z0-9][-A-Za-z0-9_.]*)?[A-Za-z0-9])$",
|
|
"type": "string"
|
|
}
|
|
},
|
|
"required": [
|
|
"lastTransitionTime",
|
|
"message",
|
|
"reason",
|
|
"status",
|
|
"type"
|
|
],
|
|
"type": "object"
|
|
},
|
|
"type": "array",
|
|
"x-kubernetes-list-map-keys": [
|
|
"type"
|
|
],
|
|
"x-kubernetes-list-type": "map"
|
|
},
|
|
"observedGeneration": {
|
|
"format": "int64",
|
|
"type": "integer"
|
|
},
|
|
"phase": {
|
|
"type": "string"
|
|
},
|
|
"secretName": {
|
|
"type": "string"
|
|
},
|
|
"uid": {
|
|
"type": "string"
|
|
}
|
|
},
|
|
"type": "object"
|
|
}
|
|
},
|
|
"type": "object"
|
|
}
|