Introduction to Linux Performance Tuning

Course Summary

The Introduction to Linux Performance Tuning training course is designed to demonstrate how to tune a production system running Linux.

The course begins with an overview of performance methodologies, terminologies, and concepts. Next, it examines system levels and components like processes, threads, memory, disk I/o, and file systems. The course concludes with an exploration of OS specific tuning tools, like prstat on Solaris and strace on Linux.

Prerequisites: A fundamental background in Linux is expected, this builds off those foundations.

Purpose	Learn how to get the most out of a production Linux server.
Audience	System administrators responsible for the care-and-feeding of production Linux systems.
Role	System Administrator
Skill Level	Intermediate
Style	Hack-a-thon - Learning Spikes - Workshops
Duration	3 Days
Related Technologies	Linux

Productivity Objectives

Describe 4 key performance tuning terms
Define a performance tuning strategy for an organization
Devise a baseline
Measure tuning increases/decreases against the baseline

What You'll Learn:

In the Introduction to Linux Performance Tuning training course, you'll learn:

Performance Methodology
- Terms for performance analysis
- Isolate and mitigate bottlenecks
- Identify outcomes for tuning
- Set up regular monitoring
Observing the System
- Common performance tools
- Interpret sar, vmstat, and iostat output
- Third-party analysis tools
- Infer trouble from system reports
CPU Performance Measurement
- Calculate the impact of caches and busses
- Observe caching performance
- Utilize CPI to measure utilization
- Tune the process scheduler
Managing Processes & Threads
- Measure process utilization
- Physical and virtual process size
- Trace a process
- Trace a Virtual Machine
Memory Management
- How virtual memory works
- Swap vs page behavior
- Large/huge page size support
Tuning Disk to I/O Demand
- Utilization, Saturation and Throughput
- Sequential and random demand
- Plot disk activity
Observing File System Latency
- The STREAMS model for I/O
- Match Workload to I/O Services
- SAN/NAS File Systems
- What Distributed File Systems do
Tuning for the Network
- Observe network latency
- Calculate distance in Hops
Solaris-specific Tools
- prstat
- truss
- p-tools
- DTrace
Linux-specific tools
- top
- strace
- valgrind
- SystemTap
JVM-specific tools
- jps
- jstat
- jhat
- VisualVM
- JMX telemetry

Real-World Content

Project-focused demos and labs using your tool stack and environment, not some canned "training room" lab.

Expert Practitioners

Industry experts that bring their battle scars into the classroom.

Experiential Learning

More coding than lecture, coupled with architectural and design discussions.

Tailored Outlines

One-size-fits-all doesn't apply to training teams. That's where we come in!

“I appreciated the instructor's technique of writing live code examples rather than using fixed slide decks to present the material.”

VMware

Dive in and learn more

When transforming your workforce, it's important to have expert advice and tailored solutions. We can help. Tell us your unique needs and we'll explore ways to address them.

Let's chat

First name*

Last name*

Business email*

Company*

Job title*

Phone*

Country*

Tell us about what you’re looking to accomplish:

By clicking submit, you agree to our Privacy Policy and Terms of Use.