Database Sharding

-- Original single database (scaling problem)
CREATE TABLE users (
  user_id INT PRIMARY KEY,
  name VARCHAR(100),
  email VARCHAR(100),
  country VARCHAR(50)
);
-- Problem: 100 million users, én server kan ikke håndtere load

-----------------------------------------------------

-- Sharding Strategy 1: Range-based
-- Shard 1: user_id 1 - 25,000,000
-- Shard 2: user_id 25,000,001 - 50,000,000  
-- Shard 3: user_id 50,000,001 - 75,000,000
-- Shard 4: user_id 75,000,001 - 100,000,000

-- Query routing logic
function getShardForUser(user_id) {
  if (user_id <= 25000000) return 'shard1';
  if (user_id <= 50000000) return 'shard2';
  if (user_id <= 75000000) return 'shard3';
  return 'shard4';
}

-- Problem med range: Uneven distribution hvis
-- user_id ikke er uniformt fordelt

-----------------------------------------------------

-- Sharding Strategy 2: Hash-based
-- Shard = hash(user_id) % num_shards

function getShardForUser(user_id) {
  const shardNum = hashFunction(user_id) % 4;
  return `shard${shardNum + 1}`;
}
-- Fordel: Jævn distribution
-- Ulempe: Range queries spans alle shards

-----------------------------------------------------

-- Sharding Strategy 3: Geography-based
-- Shard 1: country = 'DK', 'SE', 'NO' (Nordic)
-- Shard 2: country = 'DE', 'FR', 'UK' (Central EU)
-- Shard 3: country = 'US', 'CA' (North America)
-- Shard 4: country = 'JP', 'CN', 'IN' (Asia)

function getShardForUser(country) {
  const regionMap = {
    'DK': 'shard1', 'SE': 'shard1', 'NO': 'shard1',
    'DE': 'shard2', 'FR': 'shard2', 'UK': 'shard2',
    'US': 'shard3', 'CA': 'shard3',
    'JP': 'shard4', 'CN': 'shard4', 'IN': 'shard4'
  };
  return regionMap[country] || 'shard1';
}
-- Fordel: Data locality, GDPR compliance
-- Ulempe: Kan være unbalanced