Subject: Followup to Odd top behavior with current, smp sparc 20
To: None <port-sparc@netbsd.org>
From: Bruce O'Neel <edoneel@sdf.lonestar.org>
List: port-sparc
Date: 11/10/2005 08:20:50
Hi,

This is a snip of top running.  All four ecl commands started at the same
time, plus or minus a second or so.  All have been getting 95+% of 
the cpu time.

load averages:  3.57,  1.64,  1.26                  up 0 days, 11:59   08:11:46
43 processes:  1 runnable, 38 sleeping, 4 on processor
CPU0 states: 96.2% user,  0.0% nice,  2.8% system,  0.9% interrupt,  0.0% idle
CPU1 states:  100% user,  0.0% nice,  0.0% system,  0.0% interrupt,  0.0% idle
CPU2 states: 99.1% user,  0.0% nice,  0.5% system,  0.5% interrupt,  0.0% idle
CPU3 states: 99.5% user,  0.0% nice,  0.0% system,  0.5% interrupt,  0.0% idle
Memory: 141M Act, 2780K Inact, 3832K Wired, 7052K Exec, 104M File, 74M Free
Swap: 200M Total, 200M Free

  PID USERNAME PRI NICE   SIZE   RES STATE      TIME   WCPU    CPU COMMAND
11728 edoneel    2    0  6648K 8176K CPU/3      0:08 99.48% 98.88% ecl
11469 edoneel   -1    0  6648K 8176K CPU/1      0:11 99.38% 98.78% ecl
 9328 edoneel   61    0  6648K 8176K CPU/2      1:39 97.07% 96.48% ecl
11961 edoneel   62    0  6648K 8176K RUN/0      1:39 96.24% 95.65% ecl

Eventually pids 11728 and 11469 will both show the correct cpu time. 

And here is the output from the time command.

      125.22 real       118.25 user         2.84 sys
      157.03 real       141.88 user         2.78 sys
      157.56 real       143.10 user         2.82 sys
      178.99 real       165.02 user         2.15 sys

This is on a system with a 3.99.11 kernel built from current from
5 November.

cheers

bruce

-- 
edoneel@sdf.lonestar.org
SDF Public Access UNIX System - http://sdf.lonestar.org