-- Get all tables with row counts and insert/update patterns
WITH table_stats AS (
    SELECT
        schemaname, tablename,
        n_tup_ins as total_inserts,
        n_tup_upd as total_updates,
        n_tup_del as total_deletes,
        n_live_tup as live_rows,
        n_dead_tup as dead_rows
    FROM pg_stat_user_tables
),
table_sizes AS (
    SELECT
        schemaname, tablename,
        pg_size_pretty(pg_total_relation_size(schemaname||'.'||tablename)) as total_size,
        pg_total_relation_size(schemaname||'.'||tablename) as total_size_bytes
    FROM pg_tables
    WHERE schemaname NOT IN ('information_schema', 'pg_catalog')
)
SELECT
    ts.schemaname, ts.tablename, ts.live_rows,
    tsize.total_size, tsize.total_size_bytes,
    ts.total_inserts, ts.total_updates, ts.total_deletes,
    ROUND(CASE WHEN ts.live_rows > 0
          THEN (ts.total_inserts::float / ts.live_rows) * 100
          ELSE 0 END, 2) as insert_ratio_pct
FROM table_stats ts
JOIN table_sizes tsize ON ts.schemaname = tsize.schemaname AND ts.tablename = tsize.tablename
ORDER BY tsize.total_size_bytes DESC;

-- Identify common query dimensions
SELECT schemaname, tablename, indexname, indexdef
FROM pg_indexes
WHERE schemaname NOT IN ('information_schema', 'pg_catalog')
ORDER BY tablename, indexname;

-- Check availability
SELECT EXISTS (SELECT 1 FROM pg_extension WHERE extname = 'pg_stat_statements');

-- Analyze expensive queries for candidate tables
SELECT query, calls, mean_exec_time, total_exec_time
FROM pg_stat_statements
WHERE query ILIKE '%your_table_name%'
ORDER BY total_exec_time DESC LIMIT 20;

-- Check migration compatibility
SELECT conname, contype, pg_get_constraintdef(oid) as definition
FROM pg_constraint
WHERE conrelid = 'your_table_name'::regclass;

# Append-only logging
INSERT INTO events (user_id, event_time, data) VALUES (...);
# Time-series collection
INSERT INTO metrics (device_id, timestamp, value) VALUES (...);
# Time-based queries
SELECT * FROM metrics WHERE timestamp >= NOW() - INTERVAL '24 hours';
# Time aggregations
SELECT DATE_TRUNC('day', timestamp), COUNT(*) GROUP BY 1;

# Frequent updates to historical records
UPDATE users SET email = ..., updated_at = NOW() WHERE id = ...;
# Non-time lookups
SELECT * FROM users WHERE email = ...;
# Small reference tables
SELECT * FROM countries ORDER BY name;

CREATE TABLE orders (
    id BIGSERIAL PRIMARY KEY,           -- Can partition by ID
    user_id BIGINT,
    created_at TIMESTAMPTZ DEFAULT NOW() -- For sparse indexes
);

CREATE TABLE user_events (
    id BIGSERIAL PRIMARY KEY,
    user_id BIGINT,
    event_type TEXT,
    event_time TIMESTAMPTZ DEFAULT NOW(),
    metadata JSONB
);
-- Partition by id, segment by user_id, enable minmax sparse_index on event_time

CREATE TABLE sensor_readings (
    device_id TEXT,
    timestamp TIMESTAMPTZ,
    temperature DOUBLE PRECISION,
    humidity DOUBLE PRECISION
);
-- Partition by timestamp, segment by device_id, minmax sparse indexes on temperature and humidity

CREATE TABLE stock_prices (
    symbol VARCHAR(10),
    price_time TIMESTAMPTZ,
    open_price DECIMAL,
    close_price DECIMAL,
    volume BIGINT
);
-- Partition by price_time, segment by symbol, minmax sparse indexes on open_price and close_price and volume

CREATE TABLE system_metrics (
    hostname TEXT,
    metric_time TIMESTAMPTZ,
    cpu_usage DOUBLE PRECISION,
    memory_usage BIGINT
);
-- Partition by metric_time, segment by hostname, minmax sparse indexes on cpu_usage and memory_usage

CREATE TABLE countries (
    id SERIAL PRIMARY KEY,
    name VARCHAR(100),
    code CHAR(2)
);
-- Static data, no time component

CREATE TABLE users (
    id BIGSERIAL PRIMARY KEY,
    email VARCHAR(255),
    created_at TIMESTAMPTZ,
    updated_at TIMESTAMPTZ
);
-- Accessed by ID, frequently updated, has timestamp but it's not the primary query dimension (the primary query dimension is id or email)

CREATE TABLE user_settings (
    user_id BIGINT PRIMARY KEY,
    theme VARCHAR(20),       -- Changes: light -> dark -> auto
    language VARCHAR(10),    -- Changes: en -> es -> fr
    notifications JSONB,     -- Frequent preference updates
    updated_at TIMESTAMPTZ
);
-- Accessed by user_id, frequently updated, has timestamp but it's not the primary query dimension (the primary query dimension is user_id)