Re: top output: 8 cpus busy in user-mode activities, 6 processes running
- From: Troy Knabe <knabe@xxxxxxxxxxx>
- Date: Tue, 31 Oct 2006 11:30:55 -0800
My understanding is that "top" refreshes every 5 seconds by default. So at the instant of the refresh, it is reporting what processes are actually on the cpu(s) at that time. Not what processes are or were on the process during the 5 seconds between refreshes.
-Troy
----- Original Message -----
From: Susie White <swhite@xxxxxxxxxxxx>
Date: Tuesday, October 31, 2006 9:31 am
Subject: top output: 8 cpus busy in user-mode activities, 6 processes running
To: redhat-list@xxxxxxxxxx
Can you give me some insights about how we can have a case of
more busy cpus than users on the run queue or waiting for the
run queue. Below is a point in time snap shot using
'top'. We have 8 cpus, all with user-mode activity.
And yet we have 6 processes in an R or S state. All the
rest are in SW state. Any speculation is welcome.
We are running this version of linux: 2.4.21-32.0.1.ELsmp
#1 SMP Tue May 17 17:52:23 EDT 2005 i686 i686 i386 GNU/Linux
Thanks!
05:10:01 up 24 days, 5:58, 3
users, load average: 3.50, 2.24, 1.33
1061 processes: 1060 sleeping, 1 running, 0 zombie, 0 stopped
CPU states: cpu user
nice system irq softirq
iowait idle
total 21.6% 0.0%
43.2% 0.0%
0.8% 9.6% 724.0%
cpu00 0.9%
0.0% 3.6%
0.0% 0.0%
0.0% 95.4%
cpu01 2.7%
0.0% 7.2%
0.0% 0.0%
0.0% 90.0%
cpu02 7.2%
0.0% 0.9%
0.0% 0.0%
5.4% 86.4%
cpu03 3.6%
0.0% 4.5%
0.0% 0.0%
4.5% 87.3%
cpu04 1.8%
0.0% 3.6%
0.0% 0.9%
0.0% 93.6%
cpu05 1.8%
0.0% 8.1%
0.0% 0.0%
0.0% 90.0%
cpu06 1.8%
0.0% 6.3%
0.0% 0.0%
0.0% 91.8%
cpu07 1.8%
0.0% 9.0%
0.0% 0.0%
0.0% 89.0%
Mem: 15887700k av, 14688888k used, 1198812k
free, 0k shrd,
75228k buff
10974816k actv, 2098712k in_d, 244572k in_c
Swap: 12582712k av, 128796k used, 12453916k
free 12403560k cached
PID USER PRI NI
SIZE RSS SHARE STAT %CPU %MEM TIME CPU COMMAND
9477 oracle 25 0 1944
1944 788 R 9.9
0.0 0:00 7 top
1937 root 16
0 1204 1076 692 S
7.2 0.0 328:13 2 hpasmd
9531 oracle 25 0 14208
13M 12596 S 4.5 0.0
0:00 3 oracle
25749 oracle 15 0 14200
13M 8584 S 2.7
0.0 0:06 6 oracle
1 root
25 0 520 520 460
S 0.9 0.0 190:19 0 init
25741 oracle 15 0 25132 24M
21952 S 0.9 0.1
4:38 3 oracle
2 root
RT 0 0
0 0 SW 0.0
0.0 0:00 0 migration/0
3 root
RT 0 0
0 0 SW 0.0
0.0 0:00 1 migration/1
4 root
RT 0 0
0 0 SW 0.0
0.0 0:00 2 migration/2
5 root
RT 0 0
0 0 SW 0.0
0.0 0:00 3 migration/3
6 root
RT 0 0
0 0 SW 0.0
0.0 0:00 4 migration/4
7 root
RT 0 0
0 0 SW 0.0
0.0 0:00 5 migration/5
8 root
RT 0 0
0 0 SW 0.0
0.0 0:00 6 migration/6
9 root
RT 0 0
0 0 SW 0.0
0.0 0:00 7 migration/7
--
redhat-list mailing list
unsubscribe mailto:redhat-list-request@xxxxxxxxxx?subject=unsubscribe
https://www.redhat.com/mailman/listinfo/redhat-list
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Troy Knabe
Senior Systems Administrator
Computing and Information Services
4J School District
knabe@xxxxxxxxxxx
Ph: 541.687.3587
Cell: 541.968.0780
--
redhat-list mailing list
unsubscribe mailto:redhat-list-request@xxxxxxxxxx?subject=unsubscribe
https://www.redhat.com/mailman/listinfo/redhat-list
- Follow-Ups:
- Re: top output: 8 cpus busy in user-mode activities, 6 processes running
- From: Susie White
- Re: top output: 8 cpus busy in user-mode activities, 6 processes running
- References:
- top output: 8 cpus busy in user-mode activities, 6 processes running
- From: Susie White
- top output: 8 cpus busy in user-mode activities, 6 processes running
- Prev by Date: RE: Using flat-screen monitor with RedHat 9
- Next by Date: Re: top output: 8 cpus busy in user-mode activities, 6 processes running
- Previous by thread: top output: 8 cpus busy in user-mode activities, 6 processes running
- Next by thread: Re: top output: 8 cpus busy in user-mode activities, 6 processes running
- Index(es):
Relevant Pages
- Re: Multiple CPU and Load Average
... On Saturday 20 May 2006 08:01, Dave Vandervies stood up and spoke the ... Suppose
further that there are two processes running, ... The load average is the average
over the last N seconds of the ... (So if loadavg < #CPUs, you have CPU cycles that
aren't getting used, ... (comp.os.linux.misc) - Re: Multiple CPU and Load Average
... Suppose further that there are two processes running, ... calculation loop,
each working 100% hard. ... The load average is the average over the last N seconds of
the ... (So if loadavg < #CPUs, you have CPU cycles that aren't getting used, ...
(comp.os.linux.misc) - Re: GCC on multiprocessor platform?
... Make sure that there are enough processes running to require all available ...
cpus. ... Different disk/disk controllers/memory bandwidth/etc will make your ...
(comp.unix.bsd.openbsd.misc) - Re: Multiple CPU and Load Average
... Suppose further that there are two processes running, ... calculation loop (no
swapping, I/O or network), each working 100% hard. ... The load average is
the average number of processes that are either running or ready to be run. ... If both CPUs
are 100% busy, there must always be at least two processes ready to run, at all times, one for each CPU.
... (comp.os.linux.misc) - Summary: Sizing Hardware
... Oracle treats one UIV as actually being two CPUs, ... Will the V1280 cope as
a database and web server? ... CPUs are at 1 or 1.2 GHz. ... (SunManagers)