Kevin J. Cummings wrote:
On 07/25/2009 09:58 AM, Aaron Konstam wrote:
Wwll two things, one positive and one negative. The r column tells us
there are not many processes waiting for run time which we normally
associate with a low load average, However your number of interrupts per
second (in) are rather high. Some kernel action seems to be really
beating your machine over the head so to speak. How you find out what
processes these are that are that are interrupting is not clear to me,
however. Is your primary process doing a lot of I/O?
No, astropulse should be CPU bound, not IO bound. It reads in some
data, performs *lots* of calculations on it (hours worth) and then
writes the results out to a file which it then sends back to SETI, and
downloads another work unit.
I'm very much intrested in how I can figure out where the interrupts are
coming from....
so I ran 2 copies of "cat /proc/interurupts" 10 seconds apart, and here
are the delta interrupts in that time....
CPU0
0: 0 IO-APIC-edge timer
1: 0 IO-APIC-edge i8042
4: 0 IO-APIC-edge
6: 0 IO-APIC-edge floppy
7: 0 IO-APIC-edge parport0
8: 0 IO-APIC-edge rtc0
9: 0 IO-APIC-fasteoi acpi
12: 0 IO-APIC-edge i8042
14: 0 IO-APIC-edge pata_amd
15: 209 IO-APIC-edge pata_amd
16: 2790 IO-APIC-fasteoi ivtv0
18: 9 IO-APIC-fasteoi aic7xxx, cx88[0], cx88[0],
cx88[0], eth0
20: 60 IO-APIC-fasteoi ohci_hcd:usb2, NVidia CK8
21: 114 IO-APIC-fasteoi ehci_hcd:usb1, ohci_hcd:usb3
22: 21 IO-APIC-fasteoi sata_nv
NMI: 0 Non-maskable interrupts
LOC: 246 Local timer interrupts
RES: 0 Rescheduling interrupts
CAL: 0 function call interrupts
TLB: 0 TLB shootdowns
TRM: 0 Thermal event interrupts
SPU: 0 Spurious interrupts
ERR: 0
MIS: 0
Could it be my ivtv0 (PVR-350) board? Its not supposed to be doing
anything at the moment! There's nothing plugged into it, and its not
configured under MythTV right now (cable went all digital)....
I'll try removing the driver module and see if that helps. At worst,
I'll remove the board entirely.
Looking at the original 'top' output, all the CPU was going to nice processing,
presumable SETI. When you kill that you note the load average is still high,
could we see the top few lines again to see the distribution? I note that hi/si
are low, and load average indicates runable process (my first guess was the seti
went threaded). So 'top' with the 'i' visual option (only show runnable tasks)
should show what's running.
--
Bill Davidsen <davidsen@xxxxxxx>
"We have more to fear from the bungling of the incompetent than from
the machinations of the wicked." - from Slashdot
--
fedora-list mailing list
fedora-list@xxxxxxxxxx
To unsubscribe: https://www.redhat.com/mailman/listinfo/fedora-list
Guidelines: http://fedoraproject.org/wiki/Communicate/MailingListGuidelines
