Date: Sun, 1 Feb 2004 10:11:33 +1000 (EST) From: Andy Farkas <andyf@speednet.com.au> To: Steve Kargl <sgk@troutmask.apl.washington.edu> Cc: Harald Schmalzbauer <h@schmalzbauer.de> Subject: Re: SCHED_ULE and nice still ignored Message-ID: <20040201100311.A81496@hewey.af.speednet.com.au> In-Reply-To: <20040131212419.GA76513@troutmask.apl.washington.edu> References: <200401312146.32847@harrymail> <20040131212419.GA76513@troutmask.apl.washington.edu>
next in thread | previous in thread | raw e-mail | index | archive | help
Steve Kargl wrote:
> Seems to work for me. You need to describe your problem better.
sched_ule broke about a week ago. The following example shows an idle 4
CPU SMP box running -current from 2 days ago. Note the CPU percentages for
the idle threads:
$ top -Sb
last pid: 67063; load averages: 0.32, 0.38, 0.39 up 1+12:08:26 10:02:38
91 processes: 6 running, 71 sleeping, 14 waiting
Mem: 82M Active, 300M Inact, 76M Wired, 29M Cache, 60M Buf, 11M Free
Swap: 64M Total, 64M Free
PID USERNAME PRI NICE SIZE RES STATE C TIME WCPU CPU COMMAND
10 root -16 0 0K 12K CPU3 3 34.3H 153.91% 153.91% idle: cpu3
11 root -16 0 0K 12K CPU2 2 34.1H 98.44% 98.44% idle: cpu2
13 root -16 0 0K 12K RUN 0 24.8H 92.97% 92.97% idle: cpu0
12 root -16 0 0K 12K CPU1 1 32.6H 32.03% 32.03% idle: cpu1
67 root 20 0 0K 12K syncer 3 34:36 4.69% 4.69% syncer
67063 andyf 84 0 2200K 1328K CPU0 0 0:00 3.12% 3.12% top
Also, this box sits idle alot (like it is in the example above) yet the
load average now does not return to 0.00 like it used to.
WITNESS and INVARIANTS is turned off, ADAPTIVE_MUTEXES turned on.
There is something definately not right anymore.
--
:{ andyf@speednet.com.au
Andy Farkas
System Administrator
Speednet Communications
http://www.speednet.com.au/
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20040201100311.A81496>