Red Hat ENTERPRISE LINUX 3 - INTRODUCTION TO SYSTEM ADMINISTRATION Administration Manual page 53

Chapter 3. Bandwidth and Processing Power
To gain more detailed knowledge regarding CPU utilization, we must change tools. If we examine
output from
vmstat
procs
r b w swpd
1 0 0 0 233276 146636 469808
0 0 0 0 233276 146636 469808
0 0 0 0 233276 146636 469808
0 0 0 0 233276 146636 469808
0 0 0 0 233276 146636 469808
0 0 0 0 233276 146636 469808
0 0 0 0 233276 146636 469808
0 0 0 0 233276 146636 469808
0 0 0 0 233276 146636 469808
0 0 0 0 233276 146636 469808
Here we have used the command
first, the CPU-related statistics (the
maybe even appear a bit less detailed. However, unlike
the CPU is being used.
If we examine at the
system
on average and is switching between processes anywhere from 80 to nearly 400 times a second. If you
think this seems like a lot of activity, think again, because the user-level processing (the
only averaging 2%, while system-level processing (the
idle system.
Reviewing the tools Sysstat offers, we find that
tion over what we have already experienced with
of reports that can come in handy when monitoring CPU utilization.
The first report is obtained by the command
number of processes, and the load averages for the past one and five minutes. Here is a sample:
Linux 2.4.21-1.1931.2.349.2.2.entsmp (falcon.example.com)
12:00:01 AM runq-sz
12:10:00 AM
12:20:01 AM
...
09:50:00 AM
Average:
In this example, the system is always busy (given that more than one process is runnable at any given
time), but is not overly loaded (due to the fact that this particular system has more than one processor).
The next CPU-related
Linux 2.4.21-1.1931.2.349.2.2.entsmp (falcon.example.com)
12:00:01 AM
12:10:00 AM
12:20:01 AM
...
10:00:00 AM
Average:
, we obtain a slightly different understanding of our example system:
memory
free buff cache
vmstat 1 10
,
us sy
fields, we notice that the CPU is handling about 500 interrupts per second
plist-sz
3 122
5 123
5 124
4 123
report is produced by the command
sar
CPU %user
all 3.69
all 1.73
all 35.17
all 7.47
swap
si so bi
0 0 7
0 0 0
0 0 0
0 0 0
0 0 0
0 0 0
0 0 0
0 0 0
0 0 0
0 0 0
to sample the system every second for ten times. At
, and fields) seem similar to what
id
, we can also gain a bit of insight into how
top
field) is usually under 1%. Again, this is an
sy
and
iostat mpstat
and
top vmstat
, which displays the run queue length, total
sar -q
ldavg-1 ldavg-5
0.07 0.28
0.00 0.03
0.67 0.65
0.26 0.26
%nice %system
20.10 1.06
0.22 0.80
0.83 1.06
4.85 3.87
io system
bo in cs us
7 14 27 10
0 523 138
0 557 385
0 544 343
0 517 89
32 518 102
0 516 91
0 516 72
0 516 88
0 516 81
top
provide little additional informa-
. However, produces a number
sar
07/21/2003
:
sar -u
07/21/2003
%idle
75.15
97.25
62.93
83.81
41
cpu
sy id
3 87
3 0 96
2 1 97
2 0 97
2 0 98
2 0 98
2 1 98
2 0 98
2 0 97
2 0 97
displayed, and
field) is
us