Subject: Re: negative value from ps
To: None <current-users@netbsd.org>
From: Derek God3 <derek0godfrey@netscape.net>
List: current-users
Date: 12/04/2003 09:01:05
I notice in many platforms the case of nested
time ticks incorrectly sets the time base to
the current instead of leaving it along as that can
cause microtime to go backwards.

dieter.NetBSD@pandora.be wrote:
> On Wed, 3 Dec 2003, Martti Kuparinen wrote:
> 
> 
>>>Apparently microtime(9) stepped backward (which should never happen). Does
>>>your CPU have the TSC feature (see dmesg)? Is this with a multiprocessor
>>
>>This a 3 year old Dell PowerEdge 2400.
>>
>>NetBSD 1.6ZF (P3) #0: Wed Dec  3 11:59:24 EET 2003
>>         root@p3:/usr/src/sys/arch/i386/compile/P3
> 
> 
> FYI, I see this also on NetBSD 1.6.2_RC2 i386 :
> 
>   PID TT  STAT        TIME COMMAND
>     0 ??  DKs      0:-34.36 [swapper]
>   257 ??  Ss      -1:-17.23 /usr/libexec/postfix/master
>   284 ??  Ss      -2:-6.41 /usr/sbin/cron
>   295 ??  Ss      -1:-17.93 fetchmail
>   297 E0- S        0:-33.59 postmaster: stats collector process (postgres)
> 
> Some days seem to be worse than others. (I can tell by running for
> instance "time echo -n" a few times. There are times where this gives
> ludicrous results almost every time.)
> 
> NetBSD 1.6.2_RC2 (GAOSU) #4: Tue Nov 18 14:34:50 UTC 2003
>     root@gaosu.rave.org:/usr/src/sys/arch/i386/compile/GAOSU
> cpu0: AMD Athlon Model 2 (686-class), 651.19 MHz
> cpu0: I-cache 64 KB 64b/line 2-way, D-cache 64 KB 64b/line 2-way
> cpu0: L2 cache 512 KB 64b/line 2-way
> cpu0: features 183f9ff<FPU,VME,DE,PSE,TSC,MSR,PAE,MCE,CX8,SEP,MTRR>
> cpu0: features 183f9ff<PGE,MCA,CMOV,FGPAT,PSE36,MMX>
> cpu0: features 183f9ff<FXSR>
> 
> 
> kind regards,
> dieter
>