Analyzing Linux's top command's result

UNIX for Advanced & Expert Users
1

RHEL 5.4

What are the first things you would look for when analyzing Linux's top command output?

Below is a top output from one of our Linux machines; Do you see anything wrong?

top - 15:56:01 up 133 days,  5:55,  5 users,  load average: 2.94, 2.93, 6.58
Tasks: 178 total,   2 running, 176 sleeping,   0 stopped,   0 zombie
Cpu(s):  1.2% us, 15.3% sy,  0.0% ni, 48.0% id, 35.4% wa,  0.2% hi,  0.0% si
Mem:  15985240k total, 15960560k used,    24680k free,     6808k buffers
Swap: 16711672k total,    56112k used, 16655560k free, 14737900k cached

  PID USER      PR  NI  VIRT  RES  SHR S %CPU %MEM    TIME+  COMMAND
17902 oracle    18   0  4376  600  524 D 46.4  0.0   6:51.29 mv
18160 root      17   0  1800  496  428 R  8.6  0.0   0:00.26 hwclock
 1444 root      16   0     0    0    0 D  3.3  0.0   0:31.51 kjournald
   41 root      15   0     0    0    0 S  3.0  0.0  21:46.45 kswapd0
25099 root      15   0     0    0    0 D  1.3  0.0   5:46.88 pdflush
18150 root      15   0     0    0    0 D  1.0  0.0   0:00.16 pdflush
18155 root      16   0  3220  992  740 R  1.0  0.0   0:00.09 top
 2300 root      17   0  7096 4116 1604 S  0.3  0.0 127:02.78 hald
22023 oracle    16   0 1406m  17m  13m D  0.3  0.1   0:00.10 oracle
18158 root      15   0  3864  844  732 S  0.3  0.0   0:00.01 ntpdate
    1 root      16   0  2032  556  480 S  0.0  0.0  45:09.59 init
    2 root      RT   0     0    0    0 S  0.0  0.0   1:33.27 migration/0
    3 root      34  19     0    0    0 S  0.0  0.0   0:07.26 ksoftirqd/0
    4 root      RT   0     0    0    0 S  0.0  0.0   0:35.20 migration/1
    5 root      34  19     0    0    0 S  0.0  0.0   0:14.62 ksoftirqd/1
    6 root      RT   0     0    0    0 S  0.0  0.0   0:35.66 migration/2
    7 root      34  19     0    0    0 S  0.0  0.0   0:14.94 ksoftirqd/2
    8 root      RT   0     0    0    0 S  0.0  0.0   0:35.20 migration/3
    9 root      34  19     0    0    0 S  0.0  0.0   0:15.60 ksoftirqd/3
   10 root       5 -10     0    0    0 S  0.0  0.0   0:02.95 events/0
2

Finding performance problems based on the output of a single "look" at top is not usually very productive.

To answer your question: no. You are using a lot of memory - because of oracle shared memory usage, I assume.

You are running oracle. A database box looks, acts, smells, tastes, and in all other ways can appear different from a multiprocessing user box.

What problems are you having? If you want help with your problems, please post
the output of

uname -a

and then we can give you other things to pursue.

1 Like
3

Hi Jim,
Here is what you've asked for

$ uname -a
Linux TUEX_D_DB01 2.6.9-34.ELhugemem #1 SMP Fri Feb 24 17:04:34 EST 2006 i686 i686 i386 GNU/Linux
$
$
$
$ cat /etc/redhat-release
Red Hat Enterprise Linux AS release 3 (Taroon)