Bug 30310

Summary: top does not show CPU usage
Product: Base System Reporter: andrey <andrey>
Component: binAssignee: Gabor Kovesdan <gabor>
Status: Closed FIXED    
Severity: Affects Only Me    
Priority: Normal    
Version: Unspecified   
Hardware: Any   
OS: Any   
Attachments:
Description Flags
smime.p7s
none
boston_1_dia_cpuid__now.png
none
boston_1_dia_cpuid__now.png none

Description andrey 2001-09-04 14:10:01 UTC
top utility allways show 0.00 in CPU states, both in summary and in per process stats:

CPU states:  0.0% user,  0.0% nice,  0.0% system,  0.0% interrupt,  0.0% idle

The system is dual processor enabled
Comment 1 blaze 2001-09-04 14:17:14 UTC
Good daytime.

I dont have problem with TOP

CPU states: 27.9% user,  3.1% nice, 10.5% system,  0.4% interrupt, 58.1%
idle

16:16 [root#frux:p9][/] uname -a
FreeBSD frux.iptelecom.net.ua 4.4-RC FreeBSD 4.4-RC #1: Thu Aug 30
21:38:27 EEST 2001
root@frux.iptelecom.net.ua:/usr/src/sys/compile/FRUX  i386


On Tue, 4 Sep 2001, Andrey Novikov wrote:

AN>
AN>>Number:         30310
AN>>Category:       bin
AN>>Synopsis:       top does not show CPU usage
AN>>Confidential:   no
AN>>Severity:       serious
AN>>Priority:       high
AN>>Responsible:    freebsd-bugs
AN>>State:          open
AN>>Quarter:
AN>>Keywords:
AN>>Date-Required:
AN>>Class:          sw-bug
AN>>Submitter-Id:   current-users
AN>>Arrival-Date:   Tue Sep 04 06:10:01 PDT 2001
AN>>Closed-Date:
AN>>Last-Modified:
AN>>Originator:     Andrey Novikov
AN>>Release:        FreeBSD 4.4-RC
AN>>Organization:
AN>>Environment:
AN>FreeBSD spide.webclub.ru 4.4-RC FreeBSD 4.4-RC #2: Tue Sep  4 16:53:28 MSD 2001     novikov@spide.webclub.ru:/usr/src/sys/compile/SPIDE  i386
AN>
AN>>Description:
AN>top utility allways show 0.00 in CPU states, both in summary and in per process stats:
AN>
AN>CPU states:  0.0% user,  0.0% nice,  0.0% system,  0.0% interrupt,  0.0% idle
AN>
AN>The system is dual processor enabled
AN>>How-To-Repeat:
AN>
AN>>Fix:
AN>
AN>>Release-Note:
AN>>Audit-Trail:
AN>>Unformatted:
AN>
AN>To Unsubscribe: send mail to majordomo@FreeBSD.org
AN>with "unsubscribe freebsd-bugs" in the body of the message
AN>

-- 
[BLAZE-UANIC]
[FRUX-RIPE]
Comment 2 rf 2001-09-04 14:24:50 UTC
>  -----Original Message-----
>  From: owner-freebsd-bugs@FreeBSD.ORG
>  [mailto:owner-freebsd-bugs@FreeBSD.ORG]On Behalf Of Andrey Novikov
>  Sent: 04 September 2001 14:03
>  To: freebsd-gnats-submit@FreeBSD.ORG
>  Subject: bin/30310: top does not show CPU usage
>
>
>
>  >Number:         30310
>  >Category:       bin
>  >Synopsis:       top does not show CPU usage
>  >Confidential:   no
>  >Severity:       serious
>  >Priority:       high
>  >Responsible:    freebsd-bugs
>  >State:          open
>  >Quarter:
>  >Keywords:
>  >Date-Required:
>  >Class:          sw-bug
>  >Submitter-Id:   current-users
>  >Arrival-Date:   Tue Sep 04 06:10:01 PDT 2001
>  >Closed-Date:
>  >Last-Modified:
>  >Originator:     Andrey Novikov
>  >Release:        FreeBSD 4.4-RC
>  >Organization:
>  >Environment:
>  FreeBSD spide.webclub.ru 4.4-RC FreeBSD 4.4-RC #2: Tue Sep  4
>  16:53:28 MSD 2001
>  novikov@spide.webclub.ru:/usr/src/sys/compile/SPIDE  i386
>
>  >Description:
>  top utility allways show 0.00 in CPU states, both in summary and
>  in per process stats:
>
>  CPU states:  0.0% user,  0.0% nice,  0.0% system,  0.0%
>  interrupt,  0.0% idle
>
>  The system is dual processor enabled

I'm running a dual Celeron box and top is showing usage. Run a heavy job
(such as a kernel compile) What does "uptime" show?

Rus
Comment 3 .@babolo.ru 2001-09-04 22:51:52 UTC
Andrey Novikov writes:
> 
> >Number:         30310
> >Category:       bin
> >Synopsis:       top does not show CPU usage
> >Confidential:   no
> >Severity:       serious
> >Priority:       high
> >Responsible:    freebsd-bugs
> >State:          open
> >Quarter:        
> >Keywords:       
> >Date-Required:
> >Class:          sw-bug
> >Submitter-Id:   current-users
> >Arrival-Date:   Tue Sep 04 06:10:01 PDT 2001
> >Closed-Date:
> >Last-Modified:
> >Originator:     Andrey Novikov
> >Release:        FreeBSD 4.4-RC
> >Organization:
> >Environment:
> FreeBSD spide.webclub.ru 4.4-RC FreeBSD 4.4-RC #2: Tue Sep  4 16:53:28 MSD 2001     novikov@spide.webclub.ru:/usr/src/sys/compile/SPIDE  i386
> 
> >Description:
> top utility allways show 0.00 in CPU states, both in summary and in per process stats:
> 
> CPU states:  0.0% user,  0.0% nice,  0.0% system,  0.0% interrupt,  0.0% idle
This is not a top utility problem.
I saw sometime in in multiprocessor systems
(possibly with one installed processor
and free socket(s))
that timer 100 Hz (or may be my memory
leak and it is 128Hz timer) stops.
strange nulls on top is not the worst with this
hardware.
Usually timer throw interrupts some
time (hours or days) after reboot then stops.

-- 
@BABOLO      http://links.ru/
Comment 4 Kris Kennaway 2001-09-05 01:09:30 UTC
On Tue, Sep 04, 2001 at 06:02:51AM -0700, Andrey Novikov wrote:

> top utility allways show 0.00 in CPU states, both in summary and in per process stats:
> 
> CPU states:  0.0% user,  0.0% nice,  0.0% system,  0.0% interrupt,  0.0% idle
> 
> The system is dual processor enabled

Is your userland in sync with your kernel?  libkvm mismatch can
sometimes cause this kind of thing.

Kris
Comment 5 larse 2001-09-20 05:04:43 UTC
I see the same symtoms on a non-SMP laptop with 4.4-RELEASE.
-- 
Lars Eggert <larse@isi.edu>               Information Sciences Institute
http://www.isi.edu/larse/              University of Southern California
Comment 6 colin.percival 2003-02-07 00:35:15 UTC
   Can anyone reproduce this problem any more?  A new version of top has 
been imported, so it's quite likely that this problem has been fixed.

Colin Percivl
Comment 7 rafael.umann 2004-04-04 06:16:38 UTC
	Hi,

	I reproduce that error. I have 15 computers (smp quad-processors) for
a chat system with freebsd 4.8 and  4.9. Sometimes this error appears
and only after reboot or much time the error disappears.

	See the graph in annex.

top:

CPU states:  0.0% user,  0.0% nice,  0.0% system,  0.0% interrupt,  0.0% idle

But "iostat" and "vmstat" its OK:

01:50:23 root@boston /root # iostat 
      tty             da0             acd0              fd0             cpu
 tin tout  KB/t tps  MB/s   KB/t tps  MB/s   KB/t tps  MB/s  us ni sy in id
   0    0  0.00   0  0.00   0.00   0  0.00   0.00   0  0.00   4  0  8  1 88
01:50:34 root@boston /root # vmstat 
 procs      memory      page                    disks     faults      cpu
 r b w     avm    fre  flt  re  pi  po  fr  sr da0 md0   in   sy  cs us sy id
237 8 0 1324660 1369916 1466   0   0   0 230   0   0   0  718   87 3224  4  8 88
01:50:36 root@boston /root # 


	Any sugestion or patch for "top"?


	[]s,

-- 
Rafael Umann <rafael.umann@corp.terralycos.com>
Comment 8 rafael.umann 2004-04-11 17:35:48 UTC
	Hi,

	I reproduce that error. I have 15 computers (smp quad-processors) for
a chat system with freebsd 4.8 and  4.9. Sometimes this error appears
and only after reboot or much time the error disappears.

	See the graph in annex.

top:

CPU states:  0.0% user,  0.0% nice,  0.0% system,  0.0% interrupt,  0.0% idle

But "iostat" and "vmstat" its OK:

01:50:23 root@boston /root # iostat 
      tty             da0             acd0              fd0             cpu
 tin tout  KB/t tps  MB/s   KB/t tps  MB/s   KB/t tps  MB/s  us ni sy in id
   0    0  0.00   0  0.00   0.00   0  0.00   0.00   0  0.00   4  0  8  1 88
01:50:34 root@boston /root # vmstat 
 procs      memory      page                    disks     faults      cpu
 r b w     avm    fre  flt  re  pi  po  fr  sr da0 md0   in   sy  cs us sy id
237 8 0 1324660 1369916 1466   0   0   0 230   0   0   0  718   87 3224  4  8 88
01:50:36 root@boston /root # 


	Any sugestion or patch for "top"?


	[]s,

-- 
Rafael Umann <rafael.umann@corp.terralycos.com>
Comment 9 Julien Gabel 2004-04-18 18:54:20 UTC
Hello,

I can reproduce the problem here:

 - FreeBSD 5.2.1-RELEASE-p4 #0: Wed Apr 14 22:06:33 CEST 2004 i386;

 - Single processor, Hyperthreading *enable*;

 - dmesg:
   Preloaded elf kernel "/boot/kernel/kernel" at 0xc0aa6000.
   Preloaded elf module "/boot/kernel/acpi.ko" at 0xc0aa626c.
   ACPI APIC Table: <PTLTD          APIC  >
   Timecounter "i8254" frequency 1193182 Hz quality 0
   CPU: Intel(R) Pentium(R) 4 CPU 3.00GHz (3000.12-MHz 686-class CPU)
     Origin = "GenuineIntel"  Id = 0xf29  Stepping = 9
     Features=0xbfebfbff<FPU,VME,DE,PSE,TSC,MSR,PAE,MCE,CX8,APIC,SEP,
      MTRR,PGE,MCA,CMOV,PAT,PSE36,CLFLUSH,DTS,ACPI,MMX,FXSR,SSE,SSE2,SS,
      HTT,TM,PBE>
     Hyperthreading: 2 logical CPUs
   real memory  = 1071579136 (1021 MB)
   avail memory = 1031471104 (983 MB)
   FreeBSD/SMP: Multiprocessor System Detected: 2 CPUs
    cpu0 (BSP): APIC ID:  0
    cpu1 (AP): APIC ID:  1
   ioapic0 <Version 1.1> irqs 0-23 on motherboard
   Pentium Pro MTRR support enabled
   npx0: [FAST]
   npx0: <math processor> on motherboard
   npx0: INT 16 interface
   acpi0: <PTLTD    RSDT  > on motherboard
   pcibios: BIOS version 2.10
   Using $PIR table, 6 entries at 0xc00fdf60
   acpi0: Power Button (fixed)
   Timecounter "ACPI-fast" frequency 3579545 Hz quality 1000

 - vmstat/iostat/top all fail to report CPU usage;

 - This seems to be an SMP specific problem since I have an other machine
   with an identical level release, but which a single processor *without*
   Hyperthreading.

Note: I think this problem may be related to Problem Report bin/60385.
-- 
-jpeg.
Comment 10 jbehl 2004-11-15 07:24:09 UTC
i'm encountering the same problem with a dual proc amd64 system on a ibm 
e series server.  this machine has been cvsup multiple times from 5.2.1 
to the current 5.3-RELEASE.  the problem started occurring on the 
5.3-BETA release.  i'm doing the usual make 
buildworld/buildkernel/installkernel/installworld procedure, with 
appropriate reboots as specified in the updating doc.

this is a pretty serious problem as we're in the middle of testing this 
system vs. redhat AES on the same hardware.  i'd really like to use bsd 
as i think redhat aes server sucks, but it's a tough sell when you can't 
get performance benchmarks (snmpd is reporting the same cpu stats, so 
this obviously isn't a top issue).

thx
Comment 11 Gabor Kovesdan freebsd_committer freebsd_triage 2006-12-25 21:44:32 UTC
State Changed
From-To: open->feedback

Could you please test if this issue still exists on a recent FreeBSD 
release? I haven't seen it on a recent 7-CURRENT/SMP. Thanks for the effort 
on investigating this issue from all of you! 

Regards, 
Gabor Kovesdan 


Comment 12 Gabor Kovesdan freebsd_committer freebsd_triage 2006-12-25 21:44:32 UTC
Responsible Changed
From-To: freebsd-bugs->gabor

Could you please test if this issue still exists on a recent FreeBSD 
release? I haven't seen it on a recent 7-CURRENT/SMP. Thanks for the effort 
on investigating this issue from all of you! 

Regards, 
Gabor Kovesdan
Comment 13 Gabor Kovesdan freebsd_committer freebsd_triage 2007-01-09 13:10:45 UTC
State Changed
From-To: feedback->closed

Fedback timeout. If this problem shows up again, please feel 
free to submit a follow-up to this PR ticket, so that we can re-open it 
and find a solution for the problem. 

Regards, 
Gabor Kovesdan