Database scaling & optimization
Indexing, connection pooling, read replicas, query tuning, and throughput-aware SQL.
How to Avoid SELECT * and Mock SQL Column Queries in Python
Mock a SQLite cursor to verify that queries specify explicit columns instead of using SELECT *.
import sqlite3
from unittest.mock import Mock, patch
def get_user_emails(connection):
"""Fetch only the required columns instead of SELECT *."""
cursor = connection.cursor()
cursor.execute("SELECT email FROM users")
return [row[0] for row in cursor.fetchall()]
def test_get_user_emails_specific_colu…How to Batch Load JSON Data in Python for Database Optimization
This code parses JSON data into records and loads them in batches to simulate efficient database insertion, reducing load and improving performance.
import json
import time
def parse_and_load(data, batch_size=100):
"""
Parse JSON data and batch-load into a list of dicts.
Demonstrates batching for database efficiency.
"""
records = json.loads(data)
batches = []
for i in range(0, len(records), batch_size):
batch = records[i:i + …How to Build a Connection Pool Reuse Mock in Python
Build a mock connection pool with context manager to track connection reuse, acquires, and releases in Python.
import time
from contextlib import contextmanager
class Connection:
def __init__(self, name):
self.name = name
self.in_use = False
self.busy_since = None
def fetch(self):
return f"data from {self.name}"
class ConnectionPool:
def __init__(self, size=3):
self.conn…How to Build a Shard Map Mock Dict in Python
Implement a dictionary-like class that distributes keys across multiple shards using Python's hash() for realistic data partitioning.
class ShardMap:
def __init__(self, shard_count):
self.shards = {i: {} for i in range(shard_count)}
self.shard_count = shard_count
def _shard_for(self, key):
return hash(key) % self.shard_count
def __getitem__(self, key):
return self.shards[self._shard_for(key)][key]
d…How to Convert Data with Scaling for Database Optimization in Python
A beginner-friendly helper that normalizes and scales numeric fields in a list of dicts, reducing storage footprint for database efficiency.
import json
from datetime import datetime
def convert_data(data: list[dict], scale_factor: int = 1) -> list[dict]:
"""Convert a list of dicts to a scaled, normalized format for database efficiency."""
converted = []
for row in data:
normalized = {}
for key, value in row.items():
…How to Count Star vs Estimate Matches in Python
Count how many times 'star' and 'estimate' annotations match their actual labels in a list of mock comparison results.
def count_star_vs_estimate(mock_scores):
"""
Count the number of times 'star' wins and 'estimate' wins
from a list of mock comparison results.
Args:
mock_scores: list of tuples, each (annotation, actual)
where annotation is 'star' or 'estimate'
Returns:
dict w…How to Create a Covering Index with INCLUDE Columns in Python
Create a covering index with INCLUDE columns in SQLite from Python and inspect the query plan to confirm the index covers the query.
import sqlite3
def create_covering_index_mock():
conn = sqlite3.connect(":memory:")
cursor = conn.cursor()
cursor.execute("""
CREATE TABLE employees (
id INTEGER PRIMARY KEY,
name TEXT,
department TEXT,
salary INTEGER
)
""")
employe…How to Create a Data Helper Class in Python for JSON Files
Build a beginner-friendly Python helper class to read, write, filter, and summarize JSON data files with clean, reusable methods.
import json
from pathlib import Path
class DataHelper:
"""Simple beginner-friendly helper for reading and writing JSON data files."""
@staticmethod
def read_json(filename):
file_path = Path(filename)
if file_path.exists():
with file_path.open("r", encoding="utf-8") as f:
…How to Create a Database Helper Class for Beginners in Python
Build a beginner-friendly SQLite helper class with indexing and batch inserts to optimize database queries in Python.
import sqlite3
class DatabaseHelper:
def __init__(self, db_path):
self.connection = sqlite3.connect(db_path)
self.cursor = self.connection.cursor()
def create_table_with_index(self, table_name, columns, indexed_column):
columns_sql = ", ".join(f"{name} {dtype}" for name, dtype in col…How to Eager Load with JOIN to Reduce N+1 Queries in Python
Demonstrates eager loading with a SQL JOIN to reduce N+1 query patterns down to a single database call when fetching related data.
import sqlite3
def eager_load_join_reduce(mock_db_path=":memory:"):
"""Demonstrate eager loading where joins reduce query count from N+1 to 1."""
conn = sqlite3.connect(mock_db_path)
cursor = conn.cursor()
cursor.executescript(
"""
CREATE TABLE authors (id INTEGER PRIMARY KEY, name TE…How to Explain SQLite Query Plans in Python
Build a Python function that runs EXPLAIN QUERY PLAN on SQLite in-memory tables and prints the optimizer's execution plan for any SELECT statement.
import sqlite3
def explain_query(sql: str) -> str:
"""Return the SQLite query plan for the given SQL statement."""
conn = sqlite3.connect(":memory:")
cursor = conn.cursor()
# Create sample data for a realistic plan
cursor.execute("CREATE TABLE users (id INTEGER PRIMARY KEY, name TEXT)")
c…How to Implement Consistent Hashing in Python
Build a consistent hash ring in Python that distributes keys across nodes and minimizes remapping when nodes are added or removed.
import hashlib
from bisect import bisect_right
class ConsistentHashRing:
def __init__(self, nodes, replicas=3):
self.replicas = replicas
self.ring = {}
self.sorted_keys = []
for node in nodes:
self.add_node(node)
def _hash(self, key):
return int(hashlib.md…How to Implement Keyset Pagination in Python (Seek Method)
Implement keyset (seek) pagination in Python with a mock paginator that efficiently fetches pages based on the last row rather than OFFSET.
from dataclasses import dataclass
from typing import List, Optional
@dataclass
class Row:
id: int
name: str
def __lt__(self, other: "Row") -> bool:
return (self.id, self.name) < (other.id, other.name)
class MockKeysetPaginator:
"""Pagination using keyset (seek) method instead of OFFSET."""…How to Implement Read-After-Write Consistency Mock in Python
Simulate strong versus eventual read-after-write consistency with a primary and replica store, demonstrating the difference in data visibility over time.
import time
class MockStorage:
def __init__(self, write_delay=0.1):
self.store = {}
self.replica = {}
self.write_delay = write_delay
def write(self, key, value):
# Write to primary storage immediately
self.store[key] = value
# Simulate async replication delay
…How to Insert a Mock Route Record Using SQLite in Python
This code creates an in-memory SQLite table for routes and inserts a mock route record, returning the inserted row for verification.
import sqlite3
from datetime import datetime
def insert_mock_record(db_path=":memory:"):
conn = sqlite3.connect(db_path)
cursor = conn.cursor()
cursor.execute("""
CREATE TABLE IF NOT EXISTS routes (
id INTEGER PRIMARY KEY AUTOINCREMENT,
origin TEXT NOT NULL,
des…How to Limit a Result Set to Top N Rows in Python
Sort a list of dictionaries by a numeric key and return only the top N results, formatted as a readable ranked list.
import random
def top_n_mock(limit: int = 5):
"""Return a formatted top-N result set as a mock example."""
# Simulated data source
scores = [
{"name": "Alice", "score": 87},
{"name": "Bob", "score": 92},
{"name": "Charlie", "score": 78},
{"name": "Diana", "score": 95},
…How to Mock Date Sharding by Range in Python
Split a date interval into fixed-size contiguous shards, returning each window as an ISO date string pair.
from datetime import date, timedelta
def shard_ranges(start_date, end_date, shard_days=7):
if start_date > end_date:
raise ValueError("start_date cannot be after end_date")
shards = []
current = start_date
while current <= end_date:
shard_end = min(current + timedelta(days=shard_days …How to Mock Replica Lag Monitoring in Python
Simulates database replica lag with a mock monitor class that generates realistic lag metrics and health statuses.
import time
import random
from datetime import datetime, timedelta
class MockReplicaLagMonitor:
def __init__(self, replicas=3, base_lag=0.5, jitter=0.2):
self.replicas = [f"replica-{i}" for i in range(replicas)]
self.base_lag = base_lag
self.jitter = jitter
self.last_write = dateti…How to Mock SQLite executemany When Batch Inserting in Python
Batch insert many rows into SQLite with executemany and mock the cursor for isolated tests.
import sqlite3
from unittest.mock import Mock, patch
def insert_users(conn, users):
"""Insert multiple user records using executemany."""
cursor = conn.cursor()
cursor.executemany(
"INSERT INTO users (name, age) VALUES (?, ?)",
users
)
conn.commit()
return cursor.rowcount
if _…How to Mock Sticky Session Read-Your-Writes in Python
Simulates a sticky session store that routes reads for a session to the node where the last write occurred, demonstrating read-your-writes consistency.
class StickySessionStore:
def __init__(self):
self.data = {}
self.session_nodes = {}
def write(self, session_id, key, value):
self.data[key] = value
self.session_nodes[session_id] = key
return f"Wrote {key}={value} for session {session_id}"
def read(self, session_i…How to Mock a Cross-Shard Saga in Python
Simulate a distributed saga with compensating transactions across multiple database shards using a lightweight Python class that tracks executed steps and rolls them back in reverse on failure.
import json
class SagaState:
def __init__(self, saga_id):
self.saga_id = saga_id
self.executed_steps = []
self.compensations = []
def execute_step(self, shard, step_name, operation):
self.executed_steps.append((shard, step_name))
print(f"[Saga {self.saga_id}] Executin…How to Mock a Function Call in Python with unittest.mock
Use unittest.mock.Mock to wrap a function and spy on its call count and arguments in Python.
import random
from unittest.mock import Mock, patch
def select_n_plus_one(numbers: list[int]) -> int:
"""Return the first number that appears more than once, if any."""
seen = set()
for num in numbers:
if num in seen:
return num
seen.add(num)
return -1
def detect_mock(se…How to Mock a Hot Shard Split in Python
Simulate a database hot shard splitting into two shards by key ranges when it exceeds a threshold, with a mock class for testing.
import random
from collections import defaultdict
class HotShardMock:
"""Mock implementation of a hot shard split in a distributed database."""
def __init__(self, shard_id="shard_1", max_entries=5):
self.shard_id = shard_id
self.max_entries = max_entries
self.entries = {}
def ad…How to Optimize SQLite Database Performance in Python
A Python helper that creates an index, enables WAL mode, and tunes synchronous settings to optimize SQLite database performance.
import sqlite3
DATABASE_PATH = "beginners.db"
UNOPTIMIZED_TABLE_SCHEMA = """
CREATE TABLE IF NOT EXISTS users (
id INTEGER PRIMARY KEY,
name TEXT NOT NULL,
email TEXT NOT NULL
)
"""
def optimize_database(db_path: str = DATABASE_PATH) -> dict:
with sqlite3.connect(db_path) as connection:
curs…Browse by section
Each section groups closely related Python snippets.
Database scaling & optimization — Python code examples
What you will find here
This page collects database scaling & optimization snippets — short, copy-ready Python you can paste into our free online IDE and run without installing anything. Each sample includes a plain-English explanation and the full source code.
Samples vs tutorials and challenges
Samples are quick reference — one concept per page. For step-by-step teaching, use our Python tutorials. To test yourself, try quizzes or coding challenges. Clean up style with the Python formatter.