feat(server): persist server self-metrics into ClickHouse

Snapshot the full Micrometer registry (cameleer business metrics, alerting
metrics, and Spring Boot Actuator defaults) every 60s into a new
server_metrics table so server health survives restarts without an external
Prometheus. Includes a dashboard-builder reference for the SaaS team.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
hsiegeln
2026-04-23 23:20:45 +02:00
parent 0bbe5d6623
commit 48ce75bf38
14 changed files with 913 additions and 1 deletions

View File

@@ -401,6 +401,29 @@ CREATE TABLE IF NOT EXISTS route_catalog (
ENGINE = ReplacingMergeTree(last_seen)
ORDER BY (tenant_id, environment, application_id, route_id);
-- ── Server Self-Metrics ────────────────────────────────────────────────
-- Periodic snapshot of the server's own Micrometer registry (written by
-- ServerMetricsSnapshotScheduler). No `environment` column — the server
-- straddles environments. `statistic` distinguishes Timer/DistributionSummary
-- sub-measurements (count, total_time, max, mean) from plain counter/gauge values.
CREATE TABLE IF NOT EXISTS server_metrics (
tenant_id LowCardinality(String) DEFAULT 'default',
collected_at DateTime64(3),
server_instance_id LowCardinality(String),
metric_name LowCardinality(String),
metric_type LowCardinality(String),
statistic LowCardinality(String) DEFAULT 'value',
metric_value Float64,
tags Map(String, String) DEFAULT map(),
server_received_at DateTime64(3) DEFAULT now64(3)
)
ENGINE = MergeTree()
PARTITION BY (tenant_id, toYYYYMM(collected_at))
ORDER BY (tenant_id, collected_at, server_instance_id, metric_name, statistic)
TTL toDateTime(collected_at) + INTERVAL 90 DAY DELETE
SETTINGS index_granularity = 8192;
-- insert_id tiebreak for keyset pagination (fixes same-millisecond cursor collision).
-- IF NOT EXISTS on ADD COLUMN is idempotent. MATERIALIZE COLUMN is a background mutation,
-- effectively a no-op once all parts are already materialized.