clickhouse-analytics

# ClickHouse analytics ClickHouse is a multi-user, always-on, replicated columnar server built to ingest continuous high-volume writes and answer aggregation queries over billions of rows in milliseconds. You reach for it when the workload is "append a firehose of events/logs/metrics, then GROUP BY them for dashboards." Target **26.3 LTS** (v26.3.12.3, 2026-05-22) — several defaults below changed in the 26.x line, so version matters. The fork before you write any DDL: files on a laptop, in-process, no server, no concurrent writers → `../duckdb/SKILL.md`; app CRUD, point updates, foreign keys, row locks, RLS, migrations → `../postgresdb/SKILL.md`; `clickhouse-server`, replication, concurrent writers, 100M+ rows/s ingest → this skill. Instrumenting capture (GA4/PostHog) is `../analytics/SKILL.md`; charting the result for humans is `../dashboard/SKILL.md`; deciding which metrics matter is `../kpi-framework/SKILL.md`. ClickHouse is the engine underneath all three. ## Pick the engine first The engine decides dedup and merge behavior, and you cannot change `ORDER BY`/`PARTITION BY` later without a rebuild — so choose before typing `CREATE TABLE`. | Engine | Use it for | Dedup / merge behavior | Gotcha | |---|---|---|---| | `MergeTree` | Append-only events, logs, metrics | No dedup of logical rows; inserts dedup'd by block since 26.2 | The default and 90% of tables | | `ReplacingMergeTree(ver)` | Upserts / keep latest version per key | Collapses duplicate `ORDER BY` keys *even...