AIX Training : IBM AIX Systems Administration (PERFORMANCE CONCEPTS AND ANALYSIS)

IBM AIX Systems Administration (PERFORMANCE CONCEPTS AND ANALYSIS)

AIX Training Overview

This course is designed to teach performance concepts relating to Unix systems (IBM AIX pSeries and RS/6000 hardware platforms), and to use these concepts to develop a tuning methodology to monitor, interpret, and adjust mechanisms that affect performance. The course will Develop the skills to measure, analyze, and tune AIX subsystems for optimum performance. The course will also show how to use standard AIX performance tools (sar, iostat, vmstat, and trace), along with advanced AIX performance tools (tprof, svmon,filemon, monitor, and nmon).

AIX Training Prerequisites

It is assumed that the student has experience with interactive Unix systems with user-level commands, basic shell or PERL scripting techniques, and essential systems administrator functions.

AIX Training Course duration

This course requires four (4) days, approximately 70 % lecture, and 30 % lab time.

AIX Training Course Objectives

Upon completion of this course, a system performance analyst will be able to : understand fundamental performance concepts for memory management, CPU management, and I/O management in AIX systems; use supplied monitoring tools to interpret performance statistics.

AIX Training Course outline

Performance Basics

Factors affecting system performance
Performance metrics
Virtual system caching
Effects of Computer Architecture

Memory Management

Memory usage by the kernel
Process creation
Buffer Cache (and allocation control)
Shared Memory / Page Caching
Paging and Swapping
Monitoring Tools

CPU Management

Software priorities concepts
Impact of the nice parameters
Priority boosting
Differences in hardware implementations
Monitoring tools

I/O Management

Breakdown of disk I/O
Measuring Disk and terminal I/O
File system structure concepts
File system caching
Name Lookup Caching
Tuning the Usage of Non-Computational Memory
Monitoring tools

Network Management

TCP/IP Layers
Socket controls
Controlling network services
Setting network buffer values
Monitoring tools

NFS Performance

RPC Performance Considerations
Impact of NFS Blocking and Caching Sizes
Optimizing NFS Servers and Clients
Monitoring tools

X-window basics and implementation

Client-server communications
Optimizing a system with X
Reducing xterm memory usage
Monitoring tools

Modification of Performance Parameters

using smit to change basic parameters
dynamic changes with vmtune, schedtune, schedo, iotune

Summaries

Memory management
CPU management
I/O management
Network management
User program management