load >1 while 99% idle. The problem went away, and now it's back!

[dochawk]

[some of this is solved; see most recent post]

I'm seeing a couple of bizarre behaviors on this machine, which my paranoia makes me think are related.

When I click on another open application on the bottom bar, my current application collapses--if I click on an xterm, firefox collapses, then I click on firefox, and the xterms collapse, and so forth.

Meanwhile, both xload and top report a load over one, while at the same time top reports 98% idle. There does seem to be some load coming from *somewhere*; I can't edit in audacity as it makes burbly sounds as it grasps for cycles.

The whack-a-mole has been for a few days; I first notice the load today when trying to make a ringtone louder.

hawk

[GreyGeek]

Re: whack-a-mole windows and load >1 while 99% idle

What does powertop show?

[dochawk]

Re: whack-a-mole windows and load >1 while 99% idle

I'd never heard of powertop before this. It says a lot

PowerTOP version 1.11 (C) 2007 Intel Corporation

Cn Avg residency P-states (frequencies)
C0 (cpu running) ( 6.3%) 2.00 Ghz 0.0%
polling 0.0ms ( 0.0%) 1.60 Ghz 0.0%
C1 mwait 0.1ms ( 0.0%) 1200 Mhz 100.0%
C4 mwait 1.9ms (93.7%)


Wakeups-from-idle per second : 491.7 interval: 5.0s
Power usage (ACPI estimate): 17.1W (1.9 hours)

Top causes for wakeups:
27.7% (135.8) <interrupt> : PS/2 keyboard/mouse/touchpad
20.1% ( 98.6) <interrupt> : HDA Intel
17.2% ( 84.4) <kernel IPI> : Rescheduling interrupts
9.1% ( 44.8) <interrupt> : extra timer interrupt
7.1% ( 34.6) firefox : futex_wait (hrtimer_wakeup)
2.3% ( 11.4) Xorg : schedule_hrtimeout_range (hrtimer_wakeup)

Suggestion: Enable USB autosuspend by pressing the U key or adding
usbcore.autosuspend=1 to the kernel command line in the grub config



Is this what is needed?

I fixed the bizarre window behavior simply by rm -r .kde*, but xload still insists that my load is 1 and above.

I'm not having this problem on the other Toshiba (same model, but uniprocessor and less memory).

hawk

[GreyGeek]

Re: whack-a-mole windows and load &gt;1 while 99% idle

My powertop refreshes only every 15 seconds. Your every 5. Yours is doing a lot more interrupts than mine, which will make the interrupt count higher. Your count is 4 to 5 times greater than mine, which hoovers around 100 to 110 interrupts per second when idling with FireFox open.

I wouldn't try anything powertop suggests until you visit their forum and read all about the issues:
http://www.lesswatts.org/projects/powertop/known.php

[dochawk]

Re: whack-a-mole windows and load &gt;1 while 99% idle

But this isn't a power *trimming* issue--it's that something that doesn't show up in the process tables is loading the daylights out of the system. This is new; the system didn't originally do this. Whatever this is is pretty much *exactly* a 1.0 load all by itself, stealing cycles that top reports as idle.

I'm about ready to rip everything out and reinstall . . .

hawk

[dochawk]

load &gt;1 while 99% idle, and no sound gone, too.

I've tried doing a fresh install of the KDE3 remix, and also a plain KDE4 jaunty install on my spare partition.

Both exhibit this same behavior--load reported above 1.0 by top & xload, while top also reports 90-99% idle. The stolen cycles are apparently real, as audacity is strangled when trying to play.

This is a dual core Toshiba.

On top of this, sound disappeared on Thursday or so. I had thought that it was simply turned down all the way (typical for me), but the sound controls "work" to set the sound level, but no sound at any level and the speaker icon in the bottom bar keeps its slash through it even at full volume.

hawk

[dibl]

Re: whack-a-mole windows and load &gt;1 while 99% idle

Audacity makes a HUGE file in your user's home directory, if you don't reset the default location for it. I ran myself out of filesystem space that way the first time I used it.

du -h | more

should reveal the culprit if that is what is going on.

[claydoh]

Re: whack-a-mole windows and load &gt;1 while 99% idle

I'm seeing a couple of bizarre behaviors on this machine, which my paranoia makes me think are related.

When I click on another open application on the bottom bar, my current application collapses--if I click on an xterm, firefox collapses, then I click on firefox, and the xterms collapse, and so forth.

I had this happen to me a couple days ago. it took me a couple minutes to figure out, but I somehow had gotten one of my apps on a different desktop. I don't usually use multiple desktops, so it was disconcerting until I found the cause. If it is still happening, right-click on each windows title bar and select 'to desktop' - desktop1 or whichever. Not sure if it is a bug or not seeing as 2 of us have the same thing pretty close together :/

[dochawk]

Re: whack-a-mole windows and load &gt;1 while 99% idle

There don't seem to be any big unexplained files around (although pausing for files could cause the same type of strangling/gurgling sound).

I believe that I just had sound back momentarily--it made that little whistling sound as a window closed. Also, the load is now showing below 1 on xload and in , but sound is slashed out again.

I rarely use sound, but how am I supposed to play Wesnoth without it?

hawk

[dochawk]

Sound and windows fixed, but load still &gt;1 while 99% idle

Sound came back, in a round-a-bout manner.

The right-click menu of the sound icon stopped being grayed out, and I could finally unmute the thing.

Why it went or what update (I presume) fixed it is beyond me.

I had, however, been convinced that this was related to the full load, but I was wrong.

I have had a few days where load was either normal or dropped to normal after the computer was left alone for a couple of hours.

Right now, the machine has been on with me logged in for almost two hours, with load above 1 the whole time according to the load number in top and xload, but with about 90% idle reported by top.

I've attached the output of psaux following

hawk


redtail pts/0:hawk>cat /tmp/psaux
USER PID %CPU %MEM VSZ RSS TTY STAT START TIME COMMAND
root 1 0.0 0.0 3084 1884 ? Ss 09:21 0:01 /sbin/init
root 2 0.0 0.0 0 0 ? S< 09:21 0:00 [kthreadd]
root 3 0.0 0.0 0 0 ? S< 09:21 0:00 [migration/0]
root 4 0.0 0.0 0 0 ? S< 09:21 0:00 [ksoftirqd/0]
root 5 0.0 0.0 0 0 ? S< 09:21 0:00 [watchdog/0]
root 6 0.0 0.0 0 0 ? S< 09:21 0:00 [migration/1]
root 7 0.0 0.0 0 0 ? S< 09:21 0:00 [ksoftirqd/1]
root 8 0.0 0.0 0 0 ? S< 09:21 0:00 [watchdog/1]
root 9 0.0 0.0 0 0 ? S< 09:21 0:00 [events/0]
root 10 0.0 0.0 0 0 ? S< 09:21 0:00 [events/1]
root 11 0.0 0.0 0 0 ? S< 09:21 0:00 [khelper]
root 12 0.0 0.0 0 0 ? S< 09:21 0:00 [kstop/0]
root 13 0.0 0.0 0 0 ? S< 09:21 0:00 [kstop/1]
root 14 0.0 0.0 0 0 ? S< 09:21 0:00 [kintegrityd/0]
root 15 0.0 0.0 0 0 ? S< 09:21 0:00 [kintegrityd/1]
root 16 0.0 0.0 0 0 ? S< 09:21 0:00 [kblockd/0]
root 17 0.0 0.0 0 0 ? S< 09:21 0:00 [kblockd/1]
root 18 0.0 0.0 0 0 ? S< 09:21 0:00 [kacpid]
root 19 0.0 0.0 0 0 ? S< 09:21 0:00 [kacpi_notify]
root 20 0.0 0.0 0 0 ? S< 09:21 0:00 [cqueue]
root 21 0.0 0.0 0 0 ? S< 09:21 0:00 [ata/0]
root 22 0.0 0.0 0 0 ? S< 09:21 0:00 [ata/1]
root 23 0.0 0.0 0 0 ? S< 09:21 0:00 [ata_aux]
root 24 0.0 0.0 0 0 ? S< 09:21 0:00 [ksuspend_usbd]
root 25 0.0 0.0 0 0 ? S< 09:21 0:00 [khubd]
root 26 0.0 0.0 0 0 ? S< 09:21 0:00 [kseriod]
root 27 0.0 0.0 0 0 ? S< 09:21 0:00 [kmmcd]
root 28 0.0 0.0 0 0 ? S< 09:21 0:00 [btaddconn]
root 29 0.0 0.0 0 0 ? S< 09:21 0:00 [btdelconn]
root 30 0.0 0.0 0 0 ? S 09:21 0:00 [pdflush]
root 31 0.0 0.0 0 0 ? S 09:21 0:00 [pdflush]
root 32 0.0 0.0 0 0 ? S< 09:21 0:00 [kswapd0]
root 33 0.0 0.0 0 0 ? S< 09:21 0:00 [aio/0]
root 34 0.0 0.0 0 0 ? S< 09:21 0:00 [aio/1]
root 35 0.0 0.0 0 0 ? S< 09:21 0:00 [ecryptfs-kthrea]
root 38 0.0 0.0 0 0 ? S< 09:21 0:00 [scsi_eh_0]
root 39 0.0 0.0 0 0 ? S< 09:21 0:00 [scsi_eh_1]
root 40 0.0 0.0 0 0 ? S< 09:21 0:00 [scsi_eh_2]
root 41 0.0 0.0 0 0 ? S< 09:21 0:00 [scsi_eh_3]
root 42 0.0 0.0 0 0 ? S< 09:21 0:00 [scsi_eh_4]
root 43 0.0 0.0 0 0 ? S< 09:21 0:00 [scsi_eh_5]
root 44 0.0 0.0 0 0 ? S< 09:21 0:00 [kstriped]
root 45 0.0 0.0 0 0 ? S< 09:21 0:00 [kmpathd/0]
root 46 0.0 0.0 0 0 ? S< 09:21 0:00 [kmpathd/1]
root 47 0.0 0.0 0 0 ? S< 09:21 0:00 [kmpath_handlerd]
root 48 0.0 0.0 0 0 ? S< 09:21 0:00 [ksnapd]
root 49 0.0 0.0 0 0 ? S< 09:21 0:00 [kondemand/0]
root 50 0.0 0.0 0 0 ? S< 09:21 0:00 [kondemand/1]
root 51 0.0 0.0 0 0 ? S< 09:21 0:00 [krfcommd]
root 209 0.0 0.0 0 0 ? S< 09:21 0:00 [scsi_eh_6]
root 211 0.0 0.0 0 0 ? S< 09:21 0:00 [usb-storage]
root 833 0.0 0.0 0 0 ? S< 09:21 0:00 [kjournald]
root 972 0.0 0.0 2224 580 ? S<s 09:21 0:00 /sbin/udevd --daemon
root 1701 0.0 0.0 0 0 ? S< 09:21 0:00 [kpsmoused]
root 1762 0.0 0.0 0 0 ? S< 09:21 0:00 [iwlagn/0]
root 1763 0.0 0.0 0 0 ? S< 09:21 0:00 [iwlagn/1]
root 1764 0.0 0.0 0 0 ? S< 09:21 0:00 [iwlagn]
root 2176 0.0 0.0 0 0 ? S< 09:21 0:00 [kjournald]
root 2180 0.0 0.1 7336 4496 ? Ss 09:21 0:06 /sbin/mount.ntfs /dev/sda1 /dos -o rw,nls=utf8,umask=007,gid=46
root 2181 0.0 0.0 0 0 ? S< 09:21 0:00 [kjournald]
root 2431 0.0 0.0 1808 524 tty4 Ss+ 09:21 0:00 /sbin/getty 38400 tty4
root 2432 0.0 0.0 1808 528 tty5 Ss+ 09:21 0:00 /sbin/getty 38400 tty5
root 2439 0.0 0.0 1808 528 tty2 Ss+ 09:21 0:00 /sbin/getty 38400 tty2
root 2440 0.0 0.0 1808 532 tty3 Ss+ 09:21 0:00 /sbin/getty 38400 tty3
root 2441 0.0 0.0 1808 532 tty6 Ss+ 09:21 0:00 /sbin/getty 38400 tty6
root 2506 0.0 0.0 2204 1084 ? Ss 09:21 0:00 /usr/sbin/acpid -c /etc/acpi/events -s /var/run/acpid.socket
syslog 2581 0.0 0.0 2040 696 ? Ss 09:21 0:00 /sbin/syslogd -u syslog
root 2604 0.0 0.0 1968 536 ? S 09:21 0:00 /bin/dd bs 1 if /proc/kmsg of /var/run/klogd/kmsg
klog 2606 0.0 0.0 3736 2580 ? Ss 09:21 0:00 /sbin/klogd -P /var/run/klogd/kmsg
106 2629 0.1 0.0 2984 1196 ? Ss 09:21 0:08 /bin/dbus-daemon --system
root 2653 0.0 0.0 5436 1044 ? Ss 09:21 0:00 /usr/sbin/sshd
root 2711 0.2 0.2 20104 6312 ? S 09:21 0:15 python /usr/share/wicd/wicd-daemon.py
109 2733 0.0 0.1 6560 4364 ? Ss 09:21 0:00 /usr/sbin/hald
root 2736 0.0 0.0 17448 2612 ? Ssl 09:21 0:00 /usr/sbin/console-kit-daemon
root 2799 0.0 0.0 3328 1152 ? S 09:21 0:00 hald-runner
root 2835 0.0 0.0 5176 1796 ? S 09:21 0:00 hald-addon-input: Listening on /dev/input/event7 /dev/input/event1 /dev/input/event0 /dev/input/event2 /dev/input/event5 /dev/input/event4
root 2853 0.0 0.0 5176 1772 ? S 09:21 0:00 /usr/lib/hal/hald-addon-rfkill-killswitch
root 2863 0.0 0.0 5172 1756 ? S 09:21 0:00 /usr/lib/hal/hald-addon-generic-backlight
root 2892 0.0 0.0 5180 1804 ? S 09:21 0:00 hald-addon-storage: polling /dev/sdb (every 2 sec)
root 2894 0.0 0.0 5188 1780 ? S 09:21 0:00 /usr/lib/hal/hald-addon-cpufreq
109 2896 0.0 0.0 5032 1760 ? S 09:21 0:00 hald-addon-acpi: listening on acpid socket /var/run/acpid.socket
root 2910 0.0 0.0 5180 1804 ? D 09:21 0:00 hald-addon-storage: polling /dev/sr0 (every 2 sec)
root 2936 0.0 0.0 3556 1548 ? Ss 09:21 0:00 /usr/sbin/bluetoothd
root 2970 0.0 0.0 4280 768 ? Ss 09:21 0:00 wpa_supplicant -B -i wlan0 -c /var/lib/wicd/configurations/00226b069332 -D wext
root 2995 0.0 0.2 10960 6476 ? S 09:21 0:04 python /usr/share/wicd/monitor.py
root 2996 0.0 0.0 2200 356 ? Ss 09:21 0:00 /sbin/mdadm --monitor --pid-file /var/run/mdadm/monitor.pid --daemonise --scan --syslog
avahi 3024 0.0 0.0 2944 1488 ? Ss 09:21 0:00 avahi-daemon: registering [redtail.local]
avahi 3025 0.0 0.0 2944 508 ? Ss 09:21 0:00 avahi-daemon: chroot helper
root 3054 0.0 0.0 6220 2720 ? Ss 09:21 0:00 /usr/sbin/cupsd
root 3093 0.0 0.0 3412 748 ? Ss 09:21 0:00 /opt/kde3/bin/kdm -config /var/run/kdm-kde3/kdmrc
root 3097 4.4 1.7 100708 53212 tty7 Ss+ 09:21 4:47 /usr/bin/X -br -nolisten tcp :0 vt7 -auth /var/run/xauth/A:0-l5v7Eu
root 3110 0.0 0.0 4324 1160 ? Ss 09:21 0:00 /usr/bin/system-tools-backends
daemon 3185 0.0 0.0 2096 452 ? Ss 09:21 0:00 /usr/sbin/atd
root 3213 0.0 0.0 3480 1036 ? Ss 09:21 0:00 /usr/sbin/cron
root 3364 0.0 0.0 1808 532 tty1 Ss+ 09:21 0:00 /sbin/getty 38400 tty1
root 3386 0.0 0.0 2276 412 ? Ss 09:21 0:00 /sbin/dhclient wlan0
root 3398 0.0 0.0 4864 2036 ? S 09:21 0:00 -:0
hawk 3442 0.0 0.0 1872 552 ? Ss 09:22 0:00 /bin/sh /opt/kde3/bin/startkde
hawk 3562 0.0 0.0 4784 600 ? Ss 09:22 0:00 /usr/bin/ssh-agent /usr/bin/dbus-launch --exit-with-session /opt/kde3/bin/startkde
hawk 3565 0.0 0.0 3144 704 ? S 09:22 0:00 /usr/bin/dbus-launch --exit-with-session /opt/kde3/bin/startkde
hawk 3566 0.0 0.0 2672 768 ? Ss 09:22 0:00 //bin/dbus-daemon --fork --print-pid 5 --print-address 7 --session
root 3608 0.0 0.0 1656 160 ? S 09:22 0:00 start_kdeinit --new-startup +kcminit_startup
hawk 3609 0.0 0.1 24168 3864 ? Ss 09:22 0:00 kdeinit Running...
hawk 3612 0.0 0.0 24272 2616 ? S 09:22 0:00 dcopserver [kdeinit] --nosid
hawk 3615 0.0 0.2 25468 5960 ? S 09:22 0:00 klauncher [kdeinit] --new-startup
hawk 3617 0.8 0.5 33412 14912 ? S 09:22 0:51 kded [kdeinit] --new-startup
hawk 3622 0.0 0.0 1792 376 ? S 09:22 0:00 kwrapper ksmserver
hawk 3624 0.0 0.2 26292 8012 ? S 09:22 0:00 ksmserver [kdeinit]
hawk 3625 0.0 0.3 28836 11236 ? S 09:22 0:02 kwin [kdeinit] -session 10d3ced074000124577899200000035560000_1
hawk 3627 0.0 0.3 32256 9472 ? S 09:22 0:00 knotify [kdeinit]
hawk 3630 0.1 0.2 46960 7860 ? S 09:22 0:08 /opt/kde3/bin/artsd -F 10 -S 4096 -a oss -s 60 -m artsmessage -c drkonqi -l 3 -f
hawk 3632 0.0 0.4 30252 13112 ? S 09:22 0:01 kdesktop [kdeinit]
hawk 3637 0.3 0.5 34116 17084 ? S 09:22 0:21 kicker [kdeinit]
hawk 3638 0.0 0.1 24248 4744 ? S 09:22 0:00 kio_file [kdeinit] file /tmp/ksocket-hawk/klauncher7hVX7b.slave
hawk 3643 0.0 0.3 28500 11244 ? S 09:22 0:00 kio_uiserver [kdeinit]
hawk 3669 0.0 0.2 25168 6916 ? S 09:22 0:00 kaccess [kdeinit]
hawk 3676 0.0 0.3 29752 11516 ? S 09:22 0:00 kmix [kdeinit] -session 10d8cecf96000111065458100000063760027_1
hawk 3677 0.0 0.5 28752 15604 ? S 09:22 0:00 katapult -session 10d9d39668000112680660600000081280032_1247804942_3 76870
hawk 3682 0.0 0.1 6768 3856 ? S 09:22 0:00 xterm -xtsessionID 10d3ced074000124578294700000034790023
hawk 3683 0.0 0.5 36508 17024 ? S 09:22 0:00 konqueror [kdeinit] --preload
hawk 3685 0.0 0.0 4224 2032 ? S 09:22 0:00 xload -bg lightblue -hi lightblue -geometry 100x100-0-0
hawk 3686 0.0 0.5 27340 15096 ? S 09:22 0:03 python /usr/share/wicd/wicd-client.py
hawk 3688 0.0 0.0 4320 2628 pts/0 Ss 09:22 0:00 -csh
hawk 3693 0.0 0.2 26392 8672 ? S 09:22 0:00 klipper [kdeinit]
hawk 3699 0.0 0.0 6828 1884 ? S 09:22 0:00 aspell -a -S -C -Tutf8 --encoding=utf-8
hawk 3700 0.0 0.5 34368 15948 ? S 09:22 0:05 adept_notifier
hawk 3709 0.0 0.5 36508 17024 ? S 09:22 0:00 konqueror [kdeinit] --preload
hawk 3747 0.0 0.0 4512 2464 ? S 09:23 0:00 /usr/lib/libgconf2-4/gconfd-2
hawk 4859 10.6 5.5 334060 165016 pts/0 Sl 09:35 9:55 /usr/lib/firefox-3.0.11/firefox -no-about-splash -dont-force-window-stacking -geometry +850+10
hawk 11934 0.0 0.0 2488 948 pts/0 R+ 11:09 0:00 ps aux
redtail pts/0:hawk>

[GreyGeek]

Re: windows &amp; sound solved, but load still &gt;1 while 99% idle

chroot?
system-tools?

What do you have those loaded for?

[dochawk]

some sound, but no /dev/dsp, and load still &gt;1 while 99% idle

They seem to be started by avahi, which is required by kde3-desktop.

I've also found that /dev/dsp is available in consoles, but not kde. That is, if I go to a console and type mplayer humble.wav it works and plays, while the same command in an xterm starts the program, but with silence.

I do get sound-effect sounds in X/kde.

In a console, I get


redtail pts/0:hawk>mplayer humble.wav^M
MPlayer 1.0rc2-4.3.3 (C) 2000-2007 MPlayer Team
CPU: Intel(R) Core(TM)2 Duo CPU T6400 @ 2.00GHz (Family: 6, Model: 23, Stepping: 10)
CPUflags: MMX: 1 MMX2: 1 3DNow: 0 3DNow2: 0 SSE: 1 SSE2: 1
Compiled with runtime CPU detection.
mplayer: could not connect to socket
mplayer: No such file or directory
Failed to open LIRC support. You will not be able to use your remote control.

Playing humble.wav.
Audio file file format detected.
================================================== ========================
Forced audio codec: mad
Opening audio decoder: [pcm] Uncompressed PCM audio decoder
AUDIO: 44100 Hz, 2 ch, s16le, 1411.2 kbit/100.00% (ratio: 176400->176400)
Selected audio codec: [pcm] afm: pcm (Uncompressed PCM)
================================================== ========================
E: context.c: ESC[1;31mwaitpid(): No child processesESC[0m
AO: [pulse] Failed to connect to server: Internal error
AO: [alsa] 48000Hz 2ch s16le (2 bytes per sample)
Video: no video
Starting playback...


That is, it fails to use pulse and succeeds with alsa.

After killing avahi, I can now use sound in kde intermittently--somtimes it plays, others it doesn't. Once I try in kde, I seem to lose it in the console.

In wesnoth (OK, I'll admit it--the only use I have for sound ), the sound checkboxes in preferences are disabled; attempting to click one produces a message to the effect

ALSA lib pcm_dmix.c:1008snd_pcm_dmix_open) unable to open slave
20090717 15:22:52 error audio: Could not initialize audio: No available audio device


The load remains over 1.0, with nothing running (but still 90%+ idle . . .)

Hmm, editing this yet again: I've found that with all the alsa and artsd stuff killed, wesnoth gets sound back, and I can play music with mplayer and run wesnoth at the same time (not that it's a pleasant combination

But load remains over 1.0 with no apparent cause.

Now I'm baffled . . .

hawk

[dibl]

Re: sound works but not /dev/dsp, and load still &gt;1 while 99% idle

It might be worthwhile to boot a Live CD of the same version that you're running, just to see if the system ends up performing similarly, in terms of idle resource usage. Another Linux Live CD would be good to compare, too. Maybe sidux -- it's pretty good with hardware detection.

BTW, I don't know that a top load average of 1 is anything to get excited about. That's what top is showing me at this moment -- well, then it runs down to 0.20 when I sit and stare at it. With flash plugin loaded (npviewer) the browser seems to be the biggest CPU user, VMware in second (in my current session), compiz.real third, and xorg fourth, conky fifth or sixth. I have a dual core Intel X6800, overclocked. Looks like 164 processes running.

[dochawk]

Re: sound works but not /dev/dsp, and load still &gt;1 while 99% idle

This was initially installed off of the release candidate kde3 remix, and the last one I had is damaged. But it didn't start with this behavior.

I just tried off of the release cd, and it does not show this behavior.

As for the 1.0 being a problem--this isn't that it's *initially* at 1.0, but that it only drops to this value, even after hours.

This results in both excess heat from this thing on my lap, and slowing the machine down (although it's finally running audacity without garbling the sound again).

ADDED:

Hmm, and now, after being up for about fifty minutes, the load plunged down to where it should be. It does this sometimes, but not most of the time.

hawk

[dochawk]

Re: sound works but not /dev/dsp, and load still &gt;1 while 99% idle

OK, I give up.

It no longer does it.

Consistently for a month, then 90% of the time for another, and now it's stopped.

I'd sure like to know what was hogging those cycles, though . . .

hawk