IBM REDP-4285-00 Manual De Usuario
4285ch02.fm
Draft Document for Review May 4, 2007 11:35 am
40
Linux Performance and Tuning Guidelines
2.1 Introduction
The Enterprise Linux distributions are shipped with many monitoring tools. Some of them deal
with many metrics in a single tool and give us well formatted output for easy understanding of
system activities. Some of them are specific to certain performance metrics (i.e. Disk I/O) and
give us detailed information.
with many metrics in a single tool and give us well formatted output for easy understanding of
system activities. Some of them are specific to certain performance metrics (i.e. Disk I/O) and
give us detailed information.
Being familiar with these tools will help to enhance your understand of what’s going on in the
system and to find the possible causes of a performance problem.
system and to find the possible causes of a performance problem.
2.2 Overview of tool function
Table 2-1 lists the function of the monitoring tools covered in this chapter.
Table 2-1 Linux performance monitoring tools
Table 2-2 lists the function of the benchmark tools covered in this chapter.
Table 2-2 Benchmark tools
Tool
Most useful tool function
top
Process activity
vmstat
System activity Hardware and system information
uptime, w
Average system load
ps, pstree
Displays the processes
free
Memory usage
iostat
Average CPU load, disk activity
sar
Collect and report system activity
mpstat
Multiprocessor usage
numastat
NUMA-related statistics
pmap
Process memory usage
netstat
Network statistics
iptraf
Real-time network statistics
tcpdump, ethereal
Detailed network traffic analysis
nmon
Collect and report system activity
strace
System calls
Proc file system
Various kernel statistics
KDE system guard
Real-time systems reporting and graphing
Gnome System Monitor
Real-time systems reporting and graphing
Tool
Most useful tool function
lmbench
Microbenchmark for operating system functions
iozone
File system benchmark