Unix & Linux Stack Exchange is a question and answer site for users of Linux, FreeBSD and other Un*x-like operating systems. It's 100% free, no registration required.

Sign up
Here's how it works:
  1. Anybody can ask a question
  2. Anybody can answer
  3. The best answers are voted up and rise to the top

This question already has an answer here:

What does it mean when I have a non-trivial load and when I run top, there are no processes using non-trivial amounts of cpu time?

For example, I have a server with this top line:

top - 10:10:59 up 128 days, 23:44, 10 users,  load average: 4.00, 4.00, 4.00
Tasks: 254 total,   1 running, 252 sleeping,   0 stopped,   1 zombie
Cpu(s):  0.1%us,  0.1%sy,  0.0%ni, 99.8%id,  0.0%wa,  0.0%hi,  0.0%si,  0.0%st
Mem:  65912492k total, 20628812k used, 45283680k free,   573908k buffers
Swap: 33431544k total,    30376k used, 33401168k free, 12085808k cached

 2584 sgeadmin  20   0  416m 2536 1572 S  1.3  0.0   1265:45 sge_execd
    4 root      20   0     0    0    0 S  1.0  0.0   4681:42 ksoftirqd/0


share|improve this question

marked as duplicate by Stéphane Chazelas, Anthon, slm, Stéphane Gimenez, jasonwryan Nov 15 '13 at 18:27

This question has been asked before and already has an answer. If those answers do not fully address your question, please ask a new question.

4 processes in uninterruptible state. (D in the "S" column in top). In top, x, b then < and R (to reverse sort on the S column) would show those processes at the top – Stéphane Chazelas Nov 15 '13 at 15:15
OK, is there a way to determine why they are in the uninteruptable state and what I should do about them? – David Mackintosh Nov 15 '13 at 15:19
@DavidMackintosh typically, D means waiting on I/O. iostat -kx 10 would be the first thing to check (are your disks pegged?). – derobert Nov 15 '13 at 15:22
Have not checked, but I would presume in that case that the [%wa] (ie, wait-on-io) parameter would be non-trivial at that point? – David Mackintosh Nov 15 '13 at 15:24
The results of iostat -kx 10 show that the disks are not busy. It does appear that these processes are blocked on nfs somehow. @StephaneChazelas, if you write your comment as an answer I'll accept it. – David Mackintosh Nov 15 '13 at 15:28

The load can be high if multiple processes are waiting for I/O (disk or network).

share|improve this answer
I would presume the [%wa] field would be high in that case? – David Mackintosh Nov 15 '13 at 15:23

Not the answer you're looking for? Browse other questions tagged or ask your own question.