Performance on Samuel Matildes - Knowledge Base

How to Troubleshoot Linux Performance — Field Playbook

Tue, 19 May 2026 00:00:00 +0000

A field-ready reference for Linux performance investigations — keep it open in a second terminal.

How to use this playbook

Linux performance problems split cleanly into two very different investigations, and picking the wrong one wastes hours:

Situation	Track	What you do
The problem is happening right now (or you can reproduce it on demand)	Track A — Live Triage	Interactive tools, sample at 1s intervals, follow the bottleneck
The problem is intermittent / random (happens overnight, once a week, only under load you can’t reproduce)	Track B — Background Collection	Arm continuous loggers before the next occurrence, then mine the logs afterwards

Rule of thumb

If you can’t reproduce it, do not keep staring at top. Stop, deploy collectors, walk away, and analyse later. Otherwise you’ll miss the event every single time.

Before You Scale: Why Software Optimization Beats Hardware Every Time

Mon, 02 Feb 2026 00:00:00 +0000

Before You Scale: Why Software Optimization Beats Hardware Every Time

Summary

When your application crashes with an Out-of-Memory (OOM) error, the instinctive response is often: “Let’s add more RAM.” In the age of cloud computing where resources are just a slider away, this approach has become the default. But what if I told you that a 30-minute code investigation could reduce your memory usage by 95%—turning a 3GB memory spike into 150MB?

Understanding IO Delays in Linux - Performance Testing with io-delayer

Wed, 07 Jan 2026 00:00:00 +0000

GitHub • Linux Kernel Module

Simulate and analyze IO performance degradation at multiple kernel layers to understand system bottlenecks.

Why IO Delays Matter in System Performance

Input/Output operations form the backbone of system performance, yet they represent one of the most complex and often misunderstood aspects of Linux performance engineering. When applications experience slowdowns, the root cause frequently traces back to IO delays introduced at various kernel layers.

How to Benchmark Linux with Tux Toaster

Fri, 17 Oct 2025 00:00:00 +0000

GitHub • PyPI

Benchmark smarter, not harder — with Tux Toaster.

What is Tux Toaster?

Tux Toaster is an all-in-one performance toolkit for Linux. It triggers various load tests (“toasters”) to help you evaluate the performance and stability of your system across CPU, memory, disk, and network. It offers an interactive terminal menu with multi-select support and clear, stoppable workloads.

Understanding CPU Statistics in Linux (/proc/stat)

Tue, 14 Jan 2025 00:00:00 +0000

Kernel-Level CPU Time Accounting

Summary

The Linux kernel maintains precise, per-CPU time accounting across ten distinct execution contexts. These statistics, exposed via /proc/stat, represent cumulative jiffy counters (typically 1/100th or 1/1000th of a second) since system boot. Understanding these counters is essential for performance analysis, capacity planning, and diagnosing CPU contention, I/O bottlenecks, interrupt storms, and virtualization overhead.

The /proc/stat Interface

/proc/stat is a virtual file provided by the kernel’s proc filesystem. It contains system-wide statistics aggregated across all CPUs and individual per-CPU lines. The format is non-blocking and updated atomically by the kernel scheduler’s tick handler.