Database scaling & optimization
Indexing, connection pooling, read replicas, query tuning, and throughput-aware SQL.
Build a Partial Index Mock in Python for Database Filtering
Simulate a partial database index by filtering keys with a predicate, then return a limited mock lookup dictionary.
data = [
"alpha", "beta", "gamma", "delta", "epsilon",
"zeta", "eta", "theta", "iota", "kappa"
]
filtered_keys = [item for item in data if len(item) >= 5]
def mock_partial_index(keys, filter_func, limit=3):
result = {}
for key in keys:
if not filter_func(key):
continue
res…Database indexing and query timing optimization in Python
Create SQLite indexes and time query performance to measure speedup for large table lookups in Python.
import sqlite3
import time
def time_query(db_path, query, params=()):
conn = sqlite3.connect(db_path)
conn.execute("PRAGMA journal_mode = WAL")
start = time.perf_counter()
result = conn.execute(query, params).fetchall()
elapsed = time.perf_counter() - start
conn.close()
return result, ela…Geo shard by region in Python
Maps users to database shards based on geographic region with a deterministic hash fallback.
import json
from collections import defaultdict
REGION_SHARD_MAP = {
"na": ["shard-01", "shard-02"],
"eu": ["shard-03", "shard-04", "shard-05"],
"ap": ["shard-06"],
"sa": ["shard-07", "shard-08"],
}
# user_id -> region (mock lookup)
USER_REGIONS = {
"u_1001": "na",
"u_1002": "eu",
"u_1003…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 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 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 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 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 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 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 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…How to Replicate Data Across All Shards in Python
Mocks a global table that replicates a key-value pair to every shard, ensuring reads return the same value from any shard.
from dataclasses import dataclass
from typing import Dict, List
@dataclass
class Shard:
id: str
data: Dict[str, int]
class GlobalTable:
def __init__(self, shards: List[Shard]):
self._shards = {s.id: s for s in shards}
def set_value(self, key: str, value: int) -> None:
"""Replicate …How to Validate Data Before Scaling in Python
A reusable Python helper that validates required fields and constraint checks on data rows before entering a database pipeline, improving data quality and throughput.
def validate_data(data, required_fields, constraints=None):
"""
Basic validation helper demonstrating data-quality workflows
before scaling (catches bad rows early, improves throughput).
"""
constraints = constraints or {}
errors = []
for field in required_fields:
if field not in d…How to mock directory-based sharding in Python
Simulates distributing files into logical shards using a deterministic hash of each filename, mocking how a database might shard rows across nodes.
import os
import hashlib
from collections import defaultdict
from pathlib import Path
def get_shard_for_key(key: str, num_shards: int) -> int:
"""Return a deterministic shard index (0..num_shards-1) for a key."""
digest = hashlib.md5(key.encode('utf-8')).hexdigest()
return int(digest, 16) % num_shards
…Monitor Database Index Bloat in Python
Simulates index bloat checks for database tables using random ratio thresholds and reports alerts per index.
import random
import time
class IndexBloatMonitor:
def __init__(self, thresholds=(0.5, 0.8, 0.9)):
self.thresholds = thresholds
self.indices = {
"users_pk": 48.2,
"orders_created_idx": 124.7,
"products_name_idx": 15.3,
"payments_user_idx": 203.9,
…Rebalance Shard Ranges Across Nodes in Python
A mock rebalancing function that shuffles shard ranges and distributes them evenly across nodes using round-robin assignment.
import random
from dataclasses import dataclass
@dataclass
class Shard:
id: int
start: int
end: int
def rebalance_shards(shards: list[Shard], node_count: int) -> dict[int, list[Shard]]:
"""Mock rebalancing of shard ranges across nodes."""
all_ranges = [(s.start, s.end) for s in shards]
random…Route SELECT Queries to Read Replicas in Python
A mock round-robin router that forwards SELECT queries to read replicas and sends writes to the primary.
import random
class ReadReplicaRouter:
"""Round-robin router that sends SELECT queries to read replicas."""
def __init__(self, replicas):
self.replicas = replicas
self.counter = 0
def route(self, sql):
if sql.strip().upper().startswith("SELECT"):
replica = sel…Simulate PostgreSQL Vacuum to Reclaim Space in Python
A Python class that safely rewrites a data file to remove deleted rows and reclaim physical space, mimicking PostgreSQL's VACUUM operation.
import shutil
import os
class VacuumCleaner:
"""Simulates PostgreSQL-style vacuum reclaiming dead space in a file."""
def __init__(self, filepath, fill_ratio=0.7, dead_marker="[DELETED]"):
self.filepath = filepath
self.fill_ratio = fill_ratio
self.dead_marker = dead_marker
…UUID vs sequential primary key in Python
Simulate and compare UUID vs sequential primary key generation in Python to understand trade-offs in ordering and uniqueness.
import uuid
import time
def create_record_with_uuid(name):
record_id = uuid.uuid4()
return {"id": record_id, "name": name}
def create_record_with_sequential_id(name, counter):
counter += 1
return {"id": counter, "name": name}
if __name__ == "__main__":
# Simulate users inserting records
sequ…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.