/clickhouse-io

name: clickhouse-io
description: ClickHouse database patterns, query optimization, analytics, and data engineering best practices for high-performance analytical workloads. Use when writing ClickHouse schemas or queries, or when an analytical query is too slow.
metadata:
  origin: ECC

ClickHouse Analytics Patterns

ClickHouse-specific patterns for high-performance analytics and data engineering.

When to Activate

• Designing ClickHouse table schemas (MergeTree engine selection)
• Writing analytical queries (aggregations, window functions, joins)
• Optimizing query performance (partition pruning, projections, materialized views)
• Ingesting large volumes of data (batch inserts, Kafka integration)
• Migrating from PostgreSQL/MySQL to ClickHouse for analytics
• Implementing real-time dashboards or time-series analytics

Overview

ClickHouse is a column-oriented database management system (DBMS) for online analytical processing (OLAP). It's optimized for fast analytical queries on large datasets.

**Key Features:**

• Column-oriented storage
• Data compression
• Parallel query execution
• Distributed queries
• Real-time analytics

Table Design Patterns

MergeTree Engine (Most Common)

CREATE TABLE markets_analytics (
    date Date,
    market_id String,
    market_name String,
    volume UInt64,
    trades UInt32,
    unique_traders UInt32,
    avg_trade_size Float64,
    created_at DateTime
) ENGINE = MergeTree()
PARTITION BY toYYYYMM(date)
ORDER BY (date, market_id)
SETTINGS index_granularity = 8192;

ReplacingMergeTree (Deduplication)

-- For data that may have duplicates (e.g., from multiple sources)
CREATE TABLE user_events (
    event_id String,
    user_id String,
    event_type String,
    timestamp DateTime,
    properties String
) ENGINE = ReplacingMergeTree()
PARTITION BY toYYYYMM(timestamp)
ORDER BY (user_id, event_id, timestamp)
PRIMARY KEY (user_id, event_id);

AggregatingMergeTree (Pre-aggregation)

-- For maintaining aggregated metrics
CREATE TABLE market_stats_hourly (
    hour DateTime,
    market_id String,
    total_volume AggregateFunction(sum, UInt64),
    total_trades AggregateFunction(count, UInt32),
    unique_users AggregateFunction(uniq, String)
) ENGINE = AggregatingMergeTree()
PARTITION BY toYYYYMM(hour)
ORDER BY (hour, market_id);

-- Query aggregated data
SELECT
    hour,
    market_id,
    sumMerge(total_volume) AS volume,
    countMerge(total_trades) AS trades,
    uniqMerge(unique_users) AS users
FROM market_stats_hourly
WHERE hour >= toStartOfHour(now() - INTERVAL 24 HOUR)
GROUP BY hour, market_id
ORDER BY hour DESC;

Query Optimization Patterns

Efficient Filtering

-- PASS: GOOD: Use indexed columns first
SELECT *
FROM markets_analytics
WHERE date >= '2025-01-01'
  AND market_id = 'market-123'
  AND volume > 1000
ORDER BY date DESC
LIMIT 100;

-- FAIL: BAD: Filter on non-indexed columns first
SELECT *
FROM markets_analytics
WHERE volume > 1000
  AND market_name LIKE '%election%'
  AND date >= '2025-01-01';

Aggregations

-- PASS: GOOD: Use ClickHouse-specific aggregation functions
SELECT
    toStartOfDay(created_at) AS day,
    market_id,
    sum(volume) AS total_volume,
    count() AS total_trades,
    uniq(trader_id) AS unique_traders,
    avg(trade_size) AS avg_size
FROM trades
WHERE created_at >= today() - INTERVAL 7 DAY
GROUP BY day, market_id
ORDER BY day DESC, total_volume DESC;

-- PASS: Use quantile for percentiles (more efficient than percentile)
SELECT
    quantile(0.50)(trade_size) AS median,
    quantile(0.95)(trade_size) AS p95,
    quantile(0.99)(trade_size) AS p99
FROM trades
WHERE created_at >= now() - INTERVAL 1 HOUR;

Window Functions

-- Calculate running totals
SELECT
    date,
    market_id,
    volume,
    sum(volume) OVER (
        PARTITION BY market_id
        ORDER BY date
        ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW
    ) AS cumulative_volume
FROM markets_analytics
WHERE date >= today() - INTERVAL 30 DAY
ORDER BY market_id, date;

Data Insertion Patterns

Bulk Insert (Recommended)

import { createClient } from '@clickhouse/client'

const clickhouse = createClient({
  url: process.env.CLICKHOUSE_URL ?? 'http://localhost:8123',
  username: process.env.CLICKHOUSE_USER,
  password: process.env.CLICKHOUSE_PASSWORD
})

// PASS: Batch insert (efficient)
async function bulkInsertTrades(trades: Trade[]) {
  await clickhouse.insert({
    table: 'trades',
    values: trades.map(trade => ({
      id: trade.id,
      market_id: trade.market_id,
      user_id: trade.user_id,
      amount: trade.amount,
      timestamp: trade.timestamp.toISOString()
    })),
    format: 'JSONEachRow'
  })
}

// FAIL: Individual inserts (slow)
async function insertTrade(trade: Trade) {
  // Don't do this in a loop!
  await clickhouse.insert({
    table: 'trades',
    values: [{
      id: trade.id,
      market_id: trade.market_id,
      user_id: trade.user_id,
      amount: trade.amount,
      timestamp: trade.timestamp.toISOString()
    }],
    format: 'JSONEachRow'
  })
}

Streaming Insert

// For continuous data ingestion
import { Readable } from 'node:stream'

async function streamInserts(dataSource: AsyncIterable<Record<string, unknown>>) {
  await clickhouse.insert({
    table: 'trades',
    values: Readable.from(dataSource, { objectMode: true }),
    format: 'JSONEachRow'
  })
}

Materialized Views

Real-time Aggregations

-- Create materialized view for hourly stats
CREATE MATERIALIZED VIEW market_stats_hourly_mv
TO market_stats_hourly
AS SELECT
    toStartOfHour(timestamp) AS hour,
    market_id,
    sumState(amount) AS total_volume,
    countState() AS total_trades,
    uniqState(user_id) AS unique_users
FROM trades
GROUP BY hour, market_id;

-- Query the materialized view
SELECT
    hour,
    market_id,
    sumMerge(total_volume) AS volume,
    countMerge(total_trade