SUSE Linux Enterprise Desktop 文档 › System Analysis and Tuning Guide
ContentsContents
System Analysis and Tuning Guide
  1. About This Guide
  2. I Basics
    1. 1 General Notes on System Tuning
  3. II System Monitoring
    1. 2 System Monitoring Utilities
    2. 3 Analyzing and Managing System Log Files
  4. III Kernel Monitoring
    1. 4 SystemTap—Filtering and Analyzing System Data
    2. 5 Kernel Probes
    3. 6 Hardware-Based Performance Monitoring with Perf
    4. 7 OProfile—System-Wide Profiler
  5. IV Resource Management
    1. 8 General System Resource Management
    2. 9 Kernel Control Groups
    3. 10 Automatic Non-Uniform Memory Access (NUMA) Balancing
    4. 11 Power Management
  6. V Kernel Tuning
    1. 12 Tuning I/O Performance
    2. 13 Tuning the Task Scheduler
    3. 14 Tuning the Memory Management Subsystem
    4. 15 Tuning the Network
  7. VI Handling System Dumps
    1. 16 Tracing Tools
    2. 17 Kexec and Kdump
  8. VII Synchronized Clocks with Precision Time Protocol
    1. 18 Precision Time Protocol
  9. A Documentation Updates
  10. B GNU 许可证
Navigation←→
SUSE Linux Enterprise Desktop 文档 › System Analysis and Tuning Guide
Top
←→
SUSE Linux Enterprise Desktop 12 SP2

System Analysis and Tuning Guide

An administrator's guide for problem detection, resolution and optimization. Find how to inspect and optimize your system by means of monitoring tools and how to efficiently manage resources. Also contains an overview of common problems and solutions and of additional help and documentation resources.

Publication Date: October 19, 2016
About This Guide
可用文档
反馈
文档约定
I Basics
1 General Notes on System Tuning
1.1 Be Sure What Problem to Solve
1.2 Rule Out Common Problems
1.3 Finding the Bottleneck
1.4 Step-by-step Tuning
II System Monitoring
2 System Monitoring Utilities
2.1 Multi-Purpose Tools
2.2 System Information
2.3 Processes
2.4 Memory
2.5 Networking
2.6 The /proc File System
2.7 Hardware Information
2.8 Files and File Systems
2.9 User Information
2.10 Time and Date
2.11 Graph Your Data: RRDtool
3 Analyzing and Managing System Log Files
3.1 System Log Files in /var/log/
3.2 Viewing and Parsing Log Files
3.3 Managing Log Files with logrotate
3.4 Monitoring Log Files with logwatch
3.5 Using logger to Make System Log Entries
III Kernel Monitoring
4 SystemTap—Filtering and Analyzing System Data
4.1 Conceptual Overview
4.2 Installation and Setup
4.3 Script Syntax
4.4 Example Script
4.5 User Space Probing
4.6 For More Information
5 Kernel Probes
5.1 Supported Architectures
5.2 Types of Kernel Probes
5.3 Kprobes API
5.4 debugfs Interface
5.5 For More Information
6 Hardware-Based Performance Monitoring with Perf
6.1 Hardware-Based Monitoring
6.2 Sampling and Counting
6.3 Installing Perf
6.4 Perf Subcommands
6.5 Counting Particular Types of Event
6.6 Recording Events Specific to Particular Commands
6.7 For More Information
7 OProfile—System-Wide Profiler
7.1 Conceptual Overview
7.2 Installation and Requirements
7.3 Available OProfile Utilities
7.4 Using OProfile
7.5 Using OProfile's GUI
7.6 Generating Reports
7.7 For More Information
IV Resource Management
8 General System Resource Management
8.1 Planning the Installation
8.2 Disabling Unnecessary Services
8.3 File Systems and Disk Access
9 Kernel Control Groups
9.1 Technical Overview and Definitions
9.2 Scenario
9.3 Control Group Subsystems
9.4 Using Controller Groups
9.5 For More Information
10 Automatic Non-Uniform Memory Access (NUMA) Balancing
10.1 Implementation
10.2 Configuration
10.3 Monitoring
10.4 Impact
11 Power Management
11.1 Power Management at CPU Level
11.2 In-Kernel Governors
11.3 The cpupower Tools
11.4 Monitoring Power Consumption with powerTOP
11.5 Special Tuning Options
11.6 Troubleshooting
11.7 For More Information
V Kernel Tuning
12 Tuning I/O Performance
12.1 Switching I/O Scheduling
12.2 Available I/O Elevators
12.3 I/O Barrier Tuning
13 Tuning the Task Scheduler
13.1 Introduction
13.2 Process Classification
13.3 Completely Fair Scheduler
13.4 For More Information
14 Tuning the Memory Management Subsystem
14.1 Memory Usage
14.2 Reducing Memory Usage
14.3 Virtual Memory Manager (VM) Tunable Parameters
14.4 Monitoring VM Behavior
15 Tuning the Network
15.1 Configurable Kernel Socket Buffers
15.2 Detecting Network Bottlenecks and Analyzing Network Traffic
15.3 Netfilter
15.4 Improving the Network Performance with Receive Packet Steering (RPS)
15.5 For More Information
VI Handling System Dumps
16 Tracing Tools
16.1 Tracing System Calls with strace
16.2 Tracing Library Calls with ltrace
16.3 Debugging and Profiling with Valgrind
16.4 For More Information
17 Kexec and Kdump
17.1 Introduction
17.2 Required Packages
17.3 Kexec Internals
17.4 Calculating crashkernel Allocation Size
17.5 Basic Kexec Usage
17.6 How to Configure Kexec for Routine Reboots
17.7 Basic Kdump Configuration
17.8 Analyzing the Crash Dump
17.9 Advanced Kdump Configuration
17.10 For More Information
VII Synchronized Clocks with Precision Time Protocol
18 Precision Time Protocol
18.1 Introduction to PTP
18.2 Using PTP
18.3 Synchronizing the Clocks with phc2sys
18.4 Examples of Configurations
18.5 PTP and NTP
A Documentation Updates
A.1 October 2016 (Initial Release of SUSE Linux Enterprise Desktop 12 SP2)
A.2 March 2016 (Maintenance Release of SUSE Linux Enterprise Desktop 12 SP1)
A.3 December 2015 (Initial Release of SUSE Linux Enterprise Desktop 12 SP1)
A.4 February 2015 (Documentation Maintenance Update)
A.5 October 2014 (Initial Release of SUSE Linux Enterprise Desktop 12)
B GNU 许可证
B.1 GNU Free Documentation License
List of Figures
2.1 Example Graph Created with RRDtool
7.1 GUI for OProfile
9.1 Resource Planning
17.1 YaST Kdump Module: Start-Up Page
List of Tables
2.1 List of Query Options of ethtool
11.1 C-States
List of Examples
2.1 vmstat Output on a Lightly Used Machine
2.2 vmstat Output on a Heavily Used Machine (CPU bound)
3.1 Example for /etc/logrotate.conf
4.1 Simple SystemTap Script
4.2 Probe with Timer Event
4.3 printf Function with Format Specifiers
4.4 Using Global Variables
4.5 Monitoring Incoming TCP Connections with tcp_connections.stp
11.1 Example Output of cpupower frequency-info
11.2 Example Output of cpupower idle-info
11.3 Example cpupower monitor Output
11.4 Example powerTOP Output
12.1 Increasing individual thread throughput using CFQ
18.1 Slave clock using software time stamping
18.2 Slave clock using hardware time stamping
18.3 Master clock using hardware time stamping
18.4 Master clock using software time stamping (not generally recommended)

版权所有 © 2006– 2016 SUSE LLC 和贡献者。保留所有权利。

根据 GNU 自由文档许可证 (GNU Free Documentation License) 版本 1.2 或（根据您的选择）版本 1.3 中的条款，在此授予您复制、分发和/或修改本文档的许可权限；本版权声明和许可证附带不可变部分。许可证版本 1.2 的副本包含在题为“GNU 自由文档许可证”的部分。

有关 SUSE 商标，请参见 http://www.suse.com/company/legal/。所有其它第三方商标是其各自拥有者的财产。商标符号（®、™ 等）代表 SUSE 及其附属公司的商标。星号 (*) 代表第三方商标。

本指南力求涵盖所有细节。但这并不确保本指南准确无误。SUSE LLC 及其附属公司、作者和译者对于可能出现的错误或由此造成的后果皆不承担责任。

→About This Guide
Print this page

© 2016 SUSE