Observability & SRE
Structured logging, metrics, tracing, health checks, and SLO-friendly instrumentation.
Check if a Timestamp Falls in a Daily Maintenance Window in Python
A small Python function that returns True when a datetime falls inside a daily maintenance window, and a demo printing yes/no for sample timestamps.
from datetime import datetime, timedelta
from zoneinfo import ZoneInfo
def in_maintenance_window(now: datetime, start_hour: int = 2, duration_hours: int = 4) -> bool:
"""Return True if 'now' falls inside the daily maintenance window."""
day_start = now.replace(hour=start_hour, minute=0, second=0, microsecond…Generate Synthetic CPU Utilization Metrics in Python
Creates realistic time-series CPU utilization samples with timestamps, noise, and output as structured JSON for observability demos and testing.
from datetime import datetime, timedelta
import random
import json
def generate_metric_samples(base_value, noise, count=60, interval_minutes=1):
"""Generate realistic CPU utilization samples for a given time window."""
timestamps = []
values = []
now = datetime.utcnow()
start_time = now - timede…How to Build a Consumer Lag Gauge in Python
Simulate Kafka consumer lag with a Python class that tracks lag over time and reports health and averages.
import time
import random
from collections import deque
class ConsumerLagGauge:
"""Mock consumer lag gauge measuring how far behind a consumer is."""
def __init__(self, producer_rate=10, consumer_rate=7, initial_lag=0):
self.producer_rate = producer_rate
self.consumer_rate = consumer_rate
…How to Calculate SLO Error Budget in Python
Simulate an SLO error budget by computing allowed downtime from a target availability percentage and mocking monthly incidents.
```python
import random
def calculate_error_budget(total_seconds: int, target_availability: float) -> float:
return (1.0 - target_availability) * total_seconds
def simulate_monthly_availability(seconds_in_month: int, budget_seconds: float) -> float:
# Mock: randomly consume a fraction of the error budget i…How to Compute SRE Metrics Like Error Rate and Availability in Python
Tracks log events in a sliding time window and calculates error rate per second and availability percentage using an easy-to-follow class.
from collections import deque
from datetime import datetime, timedelta
from typing import Dict, Deque
class LogMetrics:
"""Simple observability helper to track log events and calculate SRE metrics."""
def __init__(self, window_seconds: int = 60):
self.window_seconds = window_seconds
self.eve…How to Create a Deep Health Check Database in Python
Setup a SQLite-backed health check database, insert mock data with response times and statuses, and generate a report ordered by most recent check.
import sqlite3
from datetime import datetime, timedelta
from pathlib import Path
DB_PATH = Path("deep_health_check.db")
def setup_database():
conn = sqlite3.connect(DB_PATH)
cursor = conn.cursor()
cursor.execute("""
CREATE TABLE IF NOT EXISTS health_checks (
id INTEGER PRIMARY KEY AU…How to Do Structured JSON Line Logging in Python
Create a simple JSON-lines logger that writes one JSON object per line to stdout with timestamp, level, message, and custom context fields.
import json
import sys
from datetime import datetime
class JsonLineLogger:
def __init__(self, stream=sys.stdout):
self.stream = stream
def log(self, level, message, **context):
record = {
"timestamp": datetime.utcnow().isoformat() + "Z",
"level": level,
"me…How to Do Structured JSON Logging in Python
Create a custom logging formatter that outputs each log entry as a single JSON line with timestamp, level, logger name, and message.
import json
import logging
from datetime import datetime
class JsonFormatter(logging.Formatter):
def format(self, record):
log_entry = {
"timestamp": datetime.utcnow().isoformat() + "Z",
"level": record.levelname,
"logger": record.name,
"message": record.ge…How to Mock HTTP Client Latency in Python
Simulate outbound HTTP request latency with configurable ranges to test timeouts, retries, and SLO monitoring without external services.
import time
import random
def mock_latency(host: str, min_ms: int = 100, max_ms: int = 500) -> dict:
"""Simulate an outbound HTTP request with mock latency."""
latency_ms = random.randint(min_ms, max_ms)
start = time.perf_counter()
time.sleep(latency_ms / 1000)
elapsed_ms = (time.perf_counter() - …How to Model Span Events in Python
Define a Span class with timestamped milestone events and a completion marker to track operation lifecycle.
import time
from dataclasses import dataclass, field
from enum import Enum
from typing import List
class SpanStatus(Enum):
STARTED = "started"
COMPLETED = "completed"
@dataclass
class SpanEvent:
name: str
timestamp: float = field(default_factory=time.time)
attributes: dict = field(default_facto…How to Parse Log Lines with Regex in Python
Extracts timestamp, log level, service name, and message from a log line using compiled regex named groups.
import re
LOG_PATTERN = re.compile(
r'^(?P<timestamp>\d{4}-\d{2}-\d{2} \d{2}:\d{2}:\d{2}) '
r'\[(?P<level>\w+)\] '
r'\((?P<service>[^)]+)\) '
r'(?P<message>.*)$'
)
def parse_log_line(line: str) -> dict:
match = LOG_PATTERN.match(line)
if not match:
return {"error": "invalid log format…How to Simulate a Queue Depth Gauge in Python
Simulate a queue depth over time using a random enqueue/dequeue process, returning depth values that can be used for monitoring or testing dashboards.
import collections
import random
import time
def simulate_queue_depth(max_depth=10, steps=20):
queue = collections.deque()
depth_history = []
for _ in range(steps):
# Randomly enqueue or dequeue
if random.random() < 0.6 and len(queue) < max_depth:
queue.append("task")
…Mock Health Endpoint Liveness Check in Python
Simulate a liveness endpoint that reports service health with a configurable failure rate and uptime.
import time
import random
def liveness_check(service_name: str, failure_rate: float = 0.1) -> dict:
"""Mock health check that returns liveness status with a configurable failure rate."""
healthy = random.random() > failure_rate
response = {
"service": service_name,
"status": "alive" if he…Browse by section
Each section groups closely related Python snippets.
Observability & SRE — Python code examples
What you will find here
This page collects observability & sre 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.