Skip site navigation (1)Skip section navigation (2)
Date:      Tue, 4 Oct 2011 20:52:11 +0530
From:      Gautam Mani <execve@gmail.com>
To:        questions@freebsd.org
Subject:   nan/inf in WCPU of ps / top
Message-ID:  <CAD9pFYD3Lk5rPHbEwnj3DbvwLXXawsQNcyTaFQ5Fw4W=TZJy7A@mail.gmail.com>

Next in thread | Raw E-Mail | Index | Archive | Help
Hi,

On one virtual machine (qemu on cygwin) running RELENG_8 (csupped around
12.Sep.11) -- I noticed:

$ ps aux
USER     PID %CPU %MEM   VSZ   RSS  TT  STAT STARTED      TIME COMMAND
root       0  nan  0.1     0    64  ??  DLs   8:39PM   0:00.66 [kernel]
root      10  nan  0.0     0     8  ??  DL    8:39PM   0:00.00 [audit]
root       1  nan  0.4  2912   472  ??  ILs   8:39PM   0:00.15 /sbin/init --
root      11  inf  0.0     0    16  ??  RL    8:39PM  10:26.08 [idle]
root      12  nan  0.1     0   120  ??  WL    8:39PM   0:07.22 [intr]
root       2  nan  0.0     0     8  ??  DL    8:39PM   0:00.13 [g_event]
root       3  nan  0.0     0     8  ??  DL    8:39PM   0:01.45 [g_up]
root       4  nan  0.0     0     8  ??  DL    8:39PM   0:13.08 [g_down]
root      13  nan  0.0     0     8  ??  DL    8:39PM   0:00.26 [yarrow]
root       5  nan  0.0     0     8  ??  DL    8:39PM   0:00.00
[sctp_iterator]
root       6  nan  0.0     0     8  ??  DL    8:39PM   0:00.00 [xpt_thrd]
root       7  nan  0.0     0     8  ??  DL    8:39PM   0:00.03 [pagedaemon]
root       8  nan  0.0     0     8  ??  DL    8:39PM   0:00.00 [vmdaemon]
root       9  nan  0.0     0     8  ??  DL    8:39PM   0:00.00 [pagezero]
root      14  nan  0.0     0     8  ??  DL    8:39PM   0:00.02 [bufdaemon]
root      15  nan  0.0     0     8  ??  DL    8:39PM   0:00.02 [vnlru]
root      16  nan  0.0     0     8  ??  DL    8:39PM   0:00.29 [syncer]
root      17  nan  0.0     0     8  ??  DL    8:39PM   0:00.06
[softdepflush]
root     104  nan  0.7  1540   836  ??  Is    8:39PM   0:00.05 adjkerntz -i
root     130  nan  0.0     0     8  ??  DL    8:39PM   0:00.03 [md0]
<snip/>

even top has this problem:
last pid:  1111;  load averages:  0.00,  0.08,
0.07                                                                  up
0+00:08:50  20:48:15
23 processes:  1 running, 22 sleeping
CPU:  2.0% user,  0.0% nice,  1.1% system,  0.0% interrupt, 96.9% idle
Mem: 11M Active, 7300K Inact, 17M Wired, 8K Cache, 12M Buf, 78M Free
Swap: 94M Total, 94M Free

  PID USERNAME    THR PRI NICE   SIZE    RES STATE   C   TIME   WCPU COMMAND
  104 root          1  76    0  1540K   836K pause   1   0:00   nan%
adjkerntz
  491 root          1  76    0  3288K  1276K select  0   0:00   nan%
dhclient
  507 _dhcp         1  50    0  3288K  1404K select  1   0:00   nan%
dhclient
  523 root          1  44    0  3936K  2292K select  0   0:00   nan% devd
  646 root          1  44    0  3348K  1180K select  0   0:00   nan% syslogd
  767 nobody        1  44    0  3388K  1604K kqread  0   0:00   nan% thttpd
  920 root          1  44    0  6088K  3200K select  1   0:00   nan%
sendmail
<snip/>

I thought this might have something to do with my experimentation with the
CPUTYPE in /etc/make.conf.
I then rebuilt world and kernel with GENERIC and removed all the changes I
had made in /etc/make.conf -- but this also didnt help.

I run qemu without the -cpu flag and dmesg shows:

CPU: QEMU Virtual CPU version 0.15.0 (2216.03-MHz 686-class CPU)
  Origin = "GenuineIntel"  Id = 0x633  Family = 6  Model = 3  Stepping = 3

Features=0x781abf9<FPU,PSE,TSC,MSR,PAE,MCE,CX8,APIC,SEP,PGE,CMOV,PAT,MMX,FXSR,SSE,SSE2>
  Features2=0x80800001<SSE3,POPCNT,HV>


Any pointers how I can get my WCPU values back -- its a little difficult if
I cannot sort by WCPU in top.

Thanks,
Gautam



Want to link to this message? Use this URL: <http://docs.FreeBSD.org/cgi/mid.cgi?CAD9pFYD3Lk5rPHbEwnj3DbvwLXXawsQNcyTaFQ5Fw4W=TZJy7A>