unkinben
5ae14b3a38
Ben: 1.2 TiB is too much. Cut both stores to 3d and resize honestly. - NATS LOGS stream max_age 168h -> 72h in the nats-stream-limits ConfigMap. At the stated ~33 GiB/day compressed (S2), 3d ~= 100 GiB, so max_bytes -> 130 GiB and the file-store PVC -> 180Gi/node. 3 replicas = ~0.5 TiB total (down from 1.2 TiB). - ClickHouse logs.raw TTL 30d -> 3d in the bootstrap DDL. At ~130 GiB/day raw, LZ4/ZSTD (~6x) stores ~20-25 GiB/day => ~60-75 GiB/3d; with merge headroom the CHI PVC -> 150Gi (from 200Gi). logs.raw is the only table. - Long-term retention now lives EXCLUSIVELY in the S3 archive (logarchiver) for the configured subjects; everything else is gone after 3 days — accepted design, documented in the runbook + PR body. - Update all 7d/30d comments and the replay window (now 3d). PVC shrink is a plan-time change: this stack is not deployed yet, so it is clean. Once deployed, PVCs cannot shrink in place (would need recreate). Claude-Session: https://claude.ai/code/session_015ur3i7D2azsMAWTSVABApv
63 lines
1.8 KiB
YAML
63 lines
1.8 KiB
YAML
---
|
|
# Vector ARCHIVER tier — long-term raw-log backup to S3 (Ceph RGW). Independent
|
|
# durable JetStream consumer (`archiver`) so its offsets/lag are fully isolated
|
|
# from the ClickHouse transform path (archive lag can never stall ingest — true
|
|
# fan-out). Writes RAW, pre-transform events (as they sit in JetStream) as
|
|
# gzipped NDJSON, partitioned by subject + date. This is the long-horizon replay
|
|
# source beyond JetStream's 3d retention window.
|
|
data_dir: /vector-data-dir
|
|
|
|
api:
|
|
enabled: true
|
|
address: 0.0.0.0:8686
|
|
|
|
sources:
|
|
js_archive:
|
|
type: nats
|
|
url: nats://nats.logging.svc.cluster.local:4222
|
|
connection_name: vector-archiver
|
|
subject: "logs.>"
|
|
jetstream:
|
|
stream: LOGS
|
|
consumer: archiver
|
|
auth:
|
|
strategy: user_password
|
|
user_password:
|
|
user: log-consumer
|
|
password: ${NATS_CONSUMER_PASSWORD}
|
|
decoding:
|
|
codec: json
|
|
|
|
sinks:
|
|
s3:
|
|
type: aws_s3
|
|
inputs:
|
|
- js_archive
|
|
bucket: logs-archive
|
|
endpoint: https://s3.ceph.unkin.net
|
|
region: us-east-1
|
|
force_path_style: true
|
|
tls:
|
|
ca_file: /etc/vault-ca/ca.crt
|
|
# AWS_ACCESS_KEY_ID / AWS_SECRET_ACCESS_KEY come from the logs-archive-s3
|
|
# Secret (cephrgw-operator) via envFrom on the deployment.
|
|
key_prefix: "raw/{{ subject }}/%Y/%m/%d/"
|
|
compression: gzip
|
|
encoding:
|
|
codec: json
|
|
framing:
|
|
method: newline_delimited
|
|
filename_time_format: "%Y%m%dT%H%M%SZ"
|
|
filename_append_uuid: true
|
|
batch:
|
|
max_bytes: 134217728
|
|
timeout_secs: 300
|
|
buffer:
|
|
type: memory
|
|
max_events: 5000
|
|
when_full: block
|
|
# Disabled so slow BucketAccess credential propagation doesn't crash-loop
|
|
# the pod; RGW reachability is proven by the operator's own health.
|
|
healthcheck:
|
|
enabled: false
|