Replace vector-archiver with logarchiver (#308)
## Why The Vector archiver leg wrote gzip NDJSON to S3 with no index or encryption. logarchiver replaces it with a Go service that seals raw logs to S3 as zstd + OpenPGP objects and indexes each object in ClickHouse (`logs.archive_index`), acking JetStream only after the object is stored and indexed. ## Changes - Add logarchiver Deployment (`git.unkin.net/unkin/logarchiver:v0.1.0`), ConfigMap, and dedicated ServiceAccount, reusing the archiver's NATS (`log-consumer` / durable `archiver` / `ARCHIVE_SUBJECTS=logs.k8s.vault.>`), S3 (`logs-archive-s3`), ClickHouse (`clickhouse-credentials`) and `vault-ca` wiring. - Encrypts to the `logarchive` gpg public key, fetched from the gpg engine via k8s auth (role `logging_logarchiver`, projected vault-audience token). `ack_wait` (5m) > batch `max_age` (2m) so messages aren't redelivered mid-batch. - Add `logs.archive_index` DDL to the clickhouse-schema bootstrap Job (no TTL — outlives `logs.raw`). - Remove the vector-archiver Helm release, values and pipeline ConfigMap. Cross-repo: apply **terraform-vault #106** (gpg key + role/policy) before this syncs, or the pod can't fetch the public key. Sequencing: apply after #306 (already merged). https://claude.ai/code/session_015ur3i7D2azsMAWTSVABApv --------- Co-authored-by: benvin <neotheo@gmail.com> Reviewed-on: #308 Co-authored-by: Ben Vincent <ben@unkin.net> Co-committed-by: Ben Vincent <ben@unkin.net>
This commit was merged in pull request #308.
This commit is contained in:
@@ -36,10 +36,4 @@ helmCharts:
|
||||
releaseName: vector-aggregator
|
||||
namespace: logging
|
||||
valuesFile: values-vector-aggregator.yaml
|
||||
# Archiver (Deployment): independent JetStream consumer -> raw logs to S3.
|
||||
- name: vector
|
||||
repo: https://helm.vector.dev
|
||||
version: "0.57.0"
|
||||
releaseName: vector-archiver
|
||||
namespace: logging
|
||||
valuesFile: values-vector-archiver.yaml
|
||||
# Archiver: replaced by the logarchiver Deployment (apps/base/logging).
|
||||
|
||||
@@ -1,59 +0,0 @@
|
||||
# Vector ARCHIVER tier (Deployment) — independent JetStream consumer writing raw
|
||||
# logs to S3 (Ceph RGW). Isolated from the ClickHouse path (own durable
|
||||
# consumer). Pipeline: apps/base/logging/vector/archiver.yaml.
|
||||
role: Stateless-Aggregator
|
||||
fullnameOverride: vector-archiver
|
||||
replicas: 1
|
||||
|
||||
image:
|
||||
repository: artifactapi.k8s.syd1.au.unkin.net/dockerhub/timberio/vector
|
||||
tag: 0.57.0-distroless-libc
|
||||
|
||||
workloadResourceAnnotations:
|
||||
reloader.stakater.com/auto: "true"
|
||||
|
||||
podLabels:
|
||||
vector.dev/exclude: "true"
|
||||
|
||||
dataDir: /vector-data-dir
|
||||
existingConfigMaps:
|
||||
- vector-archiver-config
|
||||
|
||||
env:
|
||||
# Vector 0.57 disables ${VAR} config interpolation by default; auth needs it.
|
||||
- name: VECTOR_DANGEROUSLY_ALLOW_ENV_VAR_INTERPOLATION
|
||||
value: "true"
|
||||
- name: NATS_CONSUMER_PASSWORD
|
||||
valueFrom:
|
||||
secretKeyRef:
|
||||
name: nats-auth
|
||||
key: consumer_password
|
||||
|
||||
# S3 creds (AWS_ACCESS_KEY_ID / AWS_SECRET_ACCESS_KEY) from the cephrgw-operator
|
||||
# BucketAccess Secret.
|
||||
envFrom:
|
||||
- secretRef:
|
||||
name: logs-archive-s3
|
||||
|
||||
# Trust the internal unkin.net Vault-PKI CA to verify s3.ceph.unkin.net.
|
||||
# vault-ca-cert is reflected into every namespace from the certificates ns.
|
||||
extraVolumes:
|
||||
- name: vault-ca-cert
|
||||
secret:
|
||||
secretName: vault-ca-cert
|
||||
extraVolumeMounts:
|
||||
- name: vault-ca-cert
|
||||
mountPath: /etc/vault-ca/ca.crt
|
||||
subPath: ca.crt
|
||||
readOnly: true
|
||||
|
||||
service:
|
||||
enabled: false
|
||||
|
||||
resources:
|
||||
requests:
|
||||
cpu: 100m
|
||||
memory: 256Mi
|
||||
limits:
|
||||
cpu: "1"
|
||||
memory: 1Gi
|
||||
Reference in New Issue
Block a user