unkinben
9c10b9096a
## 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>
134 lines
4.2 KiB
YAML
134 lines
4.2 KiB
YAML
---
|
|
# logarchiver — replaces the vector-archiver leg. Independent JetStream durable
|
|
# consumer (archiver) that seals raw logs to S3 as zstd + OpenPGP objects and
|
|
# indexes each object in ClickHouse (logs.archive_index). Acks only after the
|
|
# object is in S3 AND indexed. Reuses the same NATS/S3/CA wiring the Vector
|
|
# archiver used; the OpenPGP public key is delivered as a mounted file.
|
|
apiVersion: apps/v1
|
|
kind: Deployment
|
|
metadata:
|
|
name: logarchiver
|
|
namespace: logging
|
|
annotations:
|
|
reloader.stakater.com/auto: "true"
|
|
labels:
|
|
app.kubernetes.io/name: logarchiver
|
|
app.kubernetes.io/component: archiver
|
|
spec:
|
|
replicas: 1
|
|
strategy:
|
|
type: Recreate
|
|
selector:
|
|
matchLabels:
|
|
app.kubernetes.io/name: logarchiver
|
|
template:
|
|
metadata:
|
|
labels:
|
|
app.kubernetes.io/name: logarchiver
|
|
vector.dev/exclude: "true"
|
|
spec:
|
|
# Dedicated SA whose projected vault-audience token authenticates the
|
|
# k8s-auth login used to fetch the logarchive public key from the gpg engine.
|
|
serviceAccountName: logarchiver
|
|
automountServiceAccountToken: false
|
|
securityContext:
|
|
runAsNonRoot: true
|
|
runAsUser: 65532
|
|
runAsGroup: 65532
|
|
seccompProfile:
|
|
type: RuntimeDefault
|
|
containers:
|
|
- name: logarchiver
|
|
image: git.unkin.net/unkin/logarchiver:v0.1.0
|
|
imagePullPolicy: IfNotPresent
|
|
args: ["run"]
|
|
securityContext:
|
|
allowPrivilegeEscalation: false
|
|
readOnlyRootFilesystem: true
|
|
capabilities:
|
|
drop:
|
|
- ALL
|
|
ports:
|
|
- containerPort: 9090
|
|
name: metrics
|
|
protocol: TCP
|
|
env:
|
|
- name: LOGARCHIVER_CONFIG
|
|
value: /etc/logarchiver/config.yaml
|
|
# Server-side subject filter; must match the archiver consumer's filter.
|
|
- name: ARCHIVE_SUBJECTS
|
|
value: "logs.k8s.vault.>"
|
|
- name: NATS_CONSUMER_PASSWORD
|
|
valueFrom:
|
|
secretKeyRef:
|
|
name: nats-auth
|
|
key: consumer_password
|
|
- name: CLICKHOUSE_USER
|
|
valueFrom:
|
|
secretKeyRef:
|
|
name: clickhouse-credentials
|
|
key: username
|
|
- name: CLICKHOUSE_PASSWORD
|
|
valueFrom:
|
|
secretKeyRef:
|
|
name: clickhouse-credentials
|
|
key: password
|
|
# S3 creds + S3_ENDPOINT + BUCKET_NAME from the cephrgw BucketAccess Secret.
|
|
envFrom:
|
|
- secretRef:
|
|
name: logs-archive-s3
|
|
livenessProbe:
|
|
httpGet:
|
|
path: /healthz
|
|
port: metrics
|
|
initialDelaySeconds: 15
|
|
periodSeconds: 30
|
|
timeoutSeconds: 5
|
|
failureThreshold: 3
|
|
readinessProbe:
|
|
httpGet:
|
|
path: /healthz
|
|
port: metrics
|
|
initialDelaySeconds: 5
|
|
periodSeconds: 10
|
|
timeoutSeconds: 5
|
|
failureThreshold: 3
|
|
resources:
|
|
requests:
|
|
cpu: 100m
|
|
memory: 256Mi
|
|
limits:
|
|
cpu: "1"
|
|
memory: 1Gi
|
|
volumeMounts:
|
|
- name: config
|
|
mountPath: /etc/logarchiver/config.yaml
|
|
subPath: config.yaml
|
|
readOnly: true
|
|
- name: vault-token
|
|
mountPath: /var/run/secrets/vault
|
|
readOnly: true
|
|
- name: vault-ca-cert
|
|
mountPath: /etc/vault-ca/ca.crt
|
|
subPath: ca.crt
|
|
readOnly: true
|
|
- name: tmp
|
|
mountPath: /tmp
|
|
volumes:
|
|
- name: config
|
|
configMap:
|
|
name: logarchiver-config
|
|
# Projected SA token with audience "vault" for the gpg-engine k8s login.
|
|
- name: vault-token
|
|
projected:
|
|
sources:
|
|
- serviceAccountToken:
|
|
path: token
|
|
audience: vault
|
|
expirationSeconds: 600
|
|
- name: vault-ca-cert
|
|
secret:
|
|
secretName: vault-ca-cert
|
|
- name: tmp
|
|
emptyDir: {}
|