Slackware This Forum is for the discussion of Slackware Linux.
Notices
Welcome to
LinuxQuestions.org , a friendly and active Linux Community.
You are currently viewing LQ as a guest. By joining our community you will have the ability to post topics, receive our newsletter, use the advanced search, subscribe to threads and access many other special features. Registration is quick, simple and absolutely free.
Join our community today!
Note that registered members see fewer ads, and ContentLink is completely disabled once you log in.
Are you new to LinuxQuestions.org? Visit the following links:
Site Howto |
Site FAQ |
Sitemap |
Register Now
If you have any problems with the registration process or your account login, please
contact us . If you need to reset your password,
click here .
Having a problem logging in? Please visit this page to clear all LQ-related cookies.
Get a
virtual cloud desktop with the Linux distro that you want in less than five minutes with Shells! With over 10 pre-installed distros to choose from, the worry-free installation life is here! Whether you are a digital nomad or just looking for flexibility, Shells can put your Linux machine on the device that you want to use.
Exclusive for LQ members, get up to 45% off per month.
Click here for more info.
09-02-2007, 11:15 AM
#1
Senior Member
Registered: Oct 2006
Distribution: Slackware 12 Kernel 2.6.24 - probably upgraded by now
Posts: 1,054
Rep:
Interrupts being processed by only 1 cpu
I am running Intel P4 with SMP support and P4 clock mod support (self compiled very thin kernel)
I was reading stuff and found that cat /proc/interrupts gives information about interrupts processed etc.
I did the same and found the following ..
Quote:
CPU0 CPU1
0: 257 0 IO-APIC-edge timer
1: 1726 0 IO-APIC-edge i8042
8: 1 0 IO-APIC-edge rtc
9: 0 0 IO-APIC-fasteoi acpi
12: 102 0 IO-APIC-edge i8042
14: 16742 0 IO-APIC-edge ide0
16: 90501 0 IO-APIC-fasteoi uhci_hcd:usb5, HDA Intel, i915@pci:0000:00:02.0
18: 0 0 IO-APIC-fasteoi uhci_hcd:usb4
19: 370 0 IO-APIC-fasteoi libata, uhci_hcd:usb3
20: 22263 0 IO-APIC-fasteoi ehci_hcd:usb1, uhci_hcd:usb2
223: 15250 0 PCI-MSI-edge eth0
NMI: 0 0
LOC: 264692 237553
ERR: 0
MIS: 0
Why is it that all my interrupts are being processed by only 1 cpu? This is more like asymmetric multi processing rather than SMP. Is this correct /default or have I done something wrong?
I am on Slack 12, so I posted here. .. does this belong in Linux-Kernel?
09-02-2007, 11:41 AM
#2
Member
Registered: Apr 2002
Distribution: Slackware
Posts: 266
Rep:
It is likely, you are running hyperthreading, not a real dual CPU.
Below is my system with hyperthreading:
Code:
$> cat /proc/interrupts
CPU0 CPU1
0: 69 0 IO-APIC-edge timer
1: 2 0 IO-APIC-edge i8042
8: 0 0 IO-APIC-edge rtc0
9: 0 0 IO-APIC-fasteoi acpi
12: 4 0 IO-APIC-edge i8042
14: 87 0 IO-APIC-edge libata
15: 0 0 IO-APIC-edge libata
17: 2164620 0 IO-APIC-fasteoi eth0
18: 5777763 0 IO-APIC-fasteoi libata
19: 2 0 IO-APIC-fasteoi uhci_hcd:usb1, ehci_hcd:usb5
20: 171 0 IO-APIC-fasteoi uhci_hcd:usb2
21: 8998692 0 IO-APIC-fasteoi uhci_hcd:usb3, eth1
22: 0 0 IO-APIC-fasteoi uhci_hcd:usb4
NMI: 0 0
LOC: 41835688 54137944
ERR: 0
MIS: 0
Dual-Core CPU:
Code:
$> cat /proc/interrupts
CPU0 CPU1
0: 58 0 IO-APIC-edge timer
1: 0 0 IO-APIC-edge i8042
9: 0 0 IO-APIC-fasteoi acpi
14: 26659002 246421 IO-APIC-edge ide0
17: 861 0 IO-APIC-fasteoi uhci_hcd:usb4
18: 18270792 14447081 IO-APIC-fasteoi uhci_hcd:usb3, eth1
19: 91815155 92895086 IO-APIC-fasteoi libata, uhci_hcd:usb2
20: 2 0 IO-APIC-fasteoi uhci_hcd:usb1, ehci_hcd:usb5
220: 22402963 27465773 PCI-MSI-edge eth0
NMI: 0 0
LOC: 294942007 294960800
ERR: 0
MIS: 0
Two real CPU:
Code:
$> cat /proc/interrupts
CPU0 CPU1
0: 1117517110 1116826299 IO-APIC-edge timer
1: 0 9 IO-APIC-edge i8042
6: 23 32 IO-APIC-edge floppy
8: 526534 375594 IO-APIC-edge rtc
9: 0 1 IO-APIC-level acpi
12: 0 190 IO-APIC-edge i8042
15: 40241530 40201519 IO-APIC-edge ide1
169: 0 0 IO-APIC-level ohci_hcd:usb1, ohci_hcd:usb2
177: 18521287 18171304 IO-APIC-level ioc0
185: 1399170 30 IO-APIC-level eth0
193: 0 18142613 IO-APIC-level eth1
NMI: 0 0
LOC: 2234672828 2234672827
ERR: 0
MIS: 0
I think, this should be expected expected. For SMP, real CPUs > Dual-Core > Hyperthreading.
Last edited by ghostdancer; 09-02-2007 at 11:54 AM .
09-02-2007, 01:31 PM
#3
Senior Member
Registered: Oct 2006
Distribution: Slackware 12 Kernel 2.6.24 - probably upgraded by now
Posts: 1,054
Original Poster
Rep:
yeah, but then wats the point of having HT and abstracting it as 2 cpus ?
09-02-2007, 01:33 PM
#4
Senior Member
Registered: Oct 2006
Distribution: Slackware 12 Kernel 2.6.24 - probably upgraded by now
Posts: 1,054
Original Poster
Rep:
and damn!! where are you??? You have access to
1. A PC with HT
2. A dual core PC
3. A PC with actual 2 processors
damn!
09-02-2007, 01:36 PM
#5
Member
Registered: Apr 2002
Distribution: Slackware
Posts: 266
Rep:
Quote:
Originally Posted by
duryodhan
yeah, but then wats the point of having HT and abstracting it as 2 cpus ?
LOL... Very interesting question.
I will need to ask an Intel representative for that.
Quote:
Originally Posted by
duryodhan
and damn!! where are you??? You have access to
1. A PC with HT
2. A dual core PC
3. A PC with actual 2 processors
damn!
I have a few systems (in my office and home).
09-02-2007, 01:45 PM
#6
LQ Veteran
Registered: Aug 2003
Location: Australia
Distribution: Lots ...
Posts: 21,126
My thoughts as well.
On multi CPU hyperthreaded, you actually want the interrupts handled by the real CPU instances (0,2,4,6) , not the SMT instance.
09-03-2007, 08:02 AM
#7
Member
Registered: Apr 2002
Distribution: Slackware
Posts: 266
Rep:
I forgot something, for your kernel configuration, make sure "kernel irq balancing" is enabled in the "Processor type and features". It maybe the reason why your system behave this way.
09-03-2007, 08:16 AM
#8
Senior Member
Registered: Oct 2006
Location: Cp6uja
Distribution: Slackware on x86 and arm
Posts: 2,471
@ghostdancer
What is then better by means of cost/gain?
a. A Dual-cored CPU
b. Two CPUs on a single MoBo
c. A Single-cored CPU fr the same money?
I've seen nothing but disappointment since i swithced from 2500+Athlon (Barton) to a 3600+Athlon (the one @65nm process) regarding the SMP 'ability'.
Neither the 2.6.22.1 kernel nor the CPU seems worth the cost compared to a Sempron.
The BOX is an all around Desktop...
09-04-2007, 01:19 AM
#9
Member
Registered: Apr 2002
Distribution: Slackware
Posts: 266
Rep:
From my experience, even with hyperthreading, my desktop behave much better than using single CPU. However, I don't have any real benchmark or statistical records to prove it.
09-04-2007, 08:00 AM
#10
Senior Member
Registered: Oct 2006
Distribution: Slackware 12 Kernel 2.6.24 - probably upgraded by now
Posts: 1,054
Original Poster
Rep:
kernel irq balancing didn't change much for me!
09-04-2007, 11:02 PM
#11
Member
Registered: Apr 2002
Distribution: Slackware
Posts: 266
Rep:
Quote:
Originally Posted by
duryodhan
kernel irq balancing didn't change much for me!
I see. Anyway, just share with you something interesting (or at least I find it interesting).
I have a few boxes of dual-core system. Pentium D, Centrino Duo T5x and T7x series and Xeon dual core.
Pentium D - Self built no-brand desktop
Code:
$> uname -a
Linux orion 2.6.22.6 #1 SMP Fri Aug 31 23:41:25 SGT 2007 i686 Intel(R) Pentium(R) D CPU 2.66GHz GenuineIntel GNU/Linux
$> cat /proc/interrupts
CPU0 CPU1
0: 252 0 IO-APIC-edge timer
1: 23064 9 IO-APIC-edge i8042
7: 0 0 IO-APIC-edge parport0
9: 0 0 IO-APIC-fasteoi acpi
12: 1318210 7 IO-APIC-edge i8042
14: 476911 9 IO-APIC-edge ide0
15: 3670636 14 IO-APIC-edge ide1
16: 2417398 9 IO-APIC-fasteoi sata_via
17: 172498 1 IO-APIC-fasteoi ehci_hcd:usb1, uhci_hcd:usb2, uhci_hcd:usb3, uhci_hcd:usb4, uhci_hcd:usb5, eth1
18: 259979 1 IO-APIC-fasteoi VIA8237
19: 9866374 51320789 IO-APIC-fasteoi eth0, nvidia
NMI: 0 0
LOC: 130385130 125966143
ERR: 0
MIS: 0
Xeon - HP Proliant ML110
Code:
$> uname -a
Linux vm2 2.6.22.6 #1 SMP Tue Sep 4 22:13:28 SGT 2007 i686 Intel(R) Xeon(R) CPU 3040 @ 1.86GHz GenuineIntel GNU/Linux
$> cat /proc/interrupts
CPU0 CPU1
0: 58 0 IO-APIC-edge timer
1: 0 0 IO-APIC-edge i8042
9: 0 0 IO-APIC-fasteoi acpi
14: 432541 0 IO-APIC-edge ide0
17: 55 0 IO-APIC-fasteoi uhci_hcd:usb4
18: 65080 86682 IO-APIC-fasteoi uhci_hcd:usb3, eth1
19: 0 0 IO-APIC-fasteoi uhci_hcd:usb2
20: 2 0 IO-APIC-fasteoi uhci_hcd:usb1, ehci_hcd:usb5
219: 444652 418839 PCI-MSI-edge eth0
220: 1249107 1218435 PCI-MSI-edge ahci
NMI: 0 0
LOC: 4805058 4804723
ERR: 0
MIS: 0
Centrino Duo T5300 - Dell Inspiron 640m
Code:
$> uname -a
Linux linux-dell1 2.6.22.6 #1 SMP Mon Sep 3 21:02:04 SGT 2007 i686 Intel(R) Core(TM)2 CPU T5300 @ 1.73GHz GenuineIntel GNU/Linux
$> cat /proc/interrupts
CPU0 CPU1
0: 3870397 0 IO-APIC-edge timer
1: 6483 0 IO-APIC-edge i8042
9: 5 0 IO-APIC-fasteoi acpi
12: 166 0 IO-APIC-edge i8042
14: 26101 0 IO-APIC-edge libata
15: 71180 0 IO-APIC-edge libata
16: 1138941 0 IO-APIC-fasteoi i915@pci:0000:00:02.0
17: 36714 0 IO-APIC-fasteoi eth0
18: 2 0 IO-APIC-fasteoi ohci1394
19: 3 0 IO-APIC-fasteoi uhci_hcd:usb1, ehci_hcd:usb5
20: 1388726 0 IO-APIC-fasteoi uhci_hcd:usb2, HDA Intel
21: 120064 0 IO-APIC-fasteoi uhci_hcd:usb3
22: 0 0 IO-APIC-fasteoi uhci_hcd:usb4
23: 0 0 IO-APIC-fasteoi sdhci:slot0
NMI: 0 0
LOC: 1232656 2603578
ERR: 0
MIS: 0
Centrino Duo T7100 - Dell Vostro 1400
Code:
$> uname -a
Linux virgo 2.6.22.6 #3 SMP Tue Sep 4 02:00:11 SGT 2007 i686 Intel(R) Core(TM)2 Duo CPU T7100 @ 1.80GHz GenuineIntel GNU/Linux
$> cat /proc/interrupts
CPU0 CPU1
0: 290861 438 IO-APIC-edge timer
1: 2245 13 IO-APIC-edge i8042
9: 22 23 IO-APIC-fasteoi acpi
12: 2 1 IO-APIC-edge i8042
14: 7361 23 IO-APIC-edge libata
15: 0 0 IO-APIC-edge libata
16: 72411 143 IO-APIC-fasteoi i915@pci:0000:00:02.0
17: 70455 94 IO-APIC-fasteoi ipw3945
18: 15 1 IO-APIC-fasteoi firewire_ohci
19: 0 0 IO-APIC-fasteoi sdhci:slot0
20: 97226 247 IO-APIC-fasteoi uhci_hcd:usb1, uhci_hcd:usb4, ehci_hcd:usb7
21: 11742 27 IO-APIC-fasteoi uhci_hcd:usb2, uhci_hcd:usb5, HDA Intel
22: 1 1 IO-APIC-fasteoi ehci_hcd:usb3, uhci_hcd:usb6
218: 2080 2659 PCI-MSI-edge eth0
219: 18012 20 PCI-MSI-edge ahci
NMI: 0 0
LOC: 141221 242488
ERR: 0
MIS: 0
None looks well balance in terms of interrupts, and, Dell Impersion 640m seems to be the worst (perform similarly like my hyperthreaded P4).
09-05-2007, 11:20 AM
#12
Member
Registered: Sep 2003
Location: USA & Canada
Distribution: Slackware 12.0
Posts: 978
Rep:
Thanks!
Quote:
Originally Posted by
ghostdancer
I forgot something, for your kernel configuration, make sure "kernel irq balancing" is enabled in the "Processor type and features". It maybe the reason why your system behave this way.
This is what I got at the moment:
AMD Athlon 64, VIA K8T800 K8T Neo 64-bit processor based
Code:
perry@slackware:~$ uname -a
Linux slackware 2.6.21.5-smp #2 SMP Thu Aug 30 09:35:20 PDT 2007 i686 AMD Athlon(tm) 64 Processor 3000+ AuthenticAMD GNU/Linux
perry@slackware:~$ cat /proc/interrupts
CPU0
0: 62 IO-APIC-edge timer
1: 12994 IO-APIC-edge i8042
6: 5 IO-APIC-edge floppy
7: 0 IO-APIC-edge parport0
8: 1 IO-APIC-edge rtc
9: 0 IO-APIC-fasteoi acpi
12: 47320 IO-APIC-edge i8042
14: 28872 IO-APIC-edge ide0
15: 55311 IO-APIC-edge ide1
17: 3 IO-APIC-fasteoi fglrx
18: 67284 IO-APIC-fasteoi VIA8237
19: 133625 IO-APIC-fasteoi uhci_hcd:usb1, uhci_hcd:usb2, uhci_hcd:usb3, uhci_hcd:usb4, ehci_hcd:usb5
NMI: 0
LOC: 762478
ERR: 0
MIS: 0
perry@slackware:~$
Thanks to you I noticed that my
kernel irq balancing is not turned on. If I really do have hyperthreading then I'd like for it to be turned on.
I'll be sure to let you know how it turns out if things *blow up*
- Perry
ps.
make all... ...looks like a *huge* compile option just took effect...!
Last edited by perry; 09-05-2007 at 11:26 AM .
09-05-2007, 12:21 PM
#13
Member
Registered: Sep 2003
Location: USA & Canada
Distribution: Slackware 12.0
Posts: 978
Rep:
SMP enabled
Code:
perry@slackware:~$ cat /proc/interrupts
CPU0
0: 62 IO-APIC-edge timer
1: 119 IO-APIC-edge i8042
6: 5 IO-APIC-edge floppy
7: 0 IO-APIC-edge parport0
8: 1 IO-APIC-edge rtc
9: 0 IO-APIC-fasteoi acpi
12: 5648 IO-APIC-edge i8042
14: 25694 IO-APIC-edge ide0
15: 2734 IO-APIC-edge ide1
17: 6338 IO-APIC-fasteoi uhci_hcd:usb1, uhci_hcd:usb2, uhci_hcd:usb3, uhci_hcd:usb4, ehci_hcd:usb5
19: 3777 IO-APIC-fasteoi VIA8237
NMI: 0
LOC: 142458
ERR: 0
MIS: 0
perry@slackware:~$ cat /proc/cpuinfo
processor : 0
vendor_id : AuthenticAMD
cpu family : 15
model : 12
model name : AMD Athlon(tm) 64 Processor 3000+
stepping : 0
cpu MHz : 1000.000
cache size : 512 KB
fdiv_bug : no
hlt_bug : no
f00f_bug : no
coma_bug : no
fpu : yes
fpu_exception : yes
cpuid level : 1
wp : yes
flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 syscall nx mmxext lm 3dnowext 3dnow up ts fid vid ttp
bogomips : 2001.97
clflush size : 64
New kernel compiled with
kernel irq enabled and it seems to be working better than ever. however there is nothing to indicate that i have hyperthreading enabled other than I know i have smp enabled.
This just might be a fundamental difference between Intel and AMD so I'll not worry about the reports.
- Perry
09-05-2007, 02:46 PM
#14
Member
Registered: Apr 2002
Distribution: Slackware
Posts: 266
Rep:
AFAIK, Hyperthreading is Intel only...
09-05-2007, 04:31 PM
#15
LQ Veteran
Registered: Aug 2003
Location: Australia
Distribution: Lots ...
Posts: 21,126
Quote:
Originally Posted by
perry
however there is nothing to indicate that i have hyperthreading enabled other than I know i have smp enabled.
According to your output, you only have a single engine - seems right for what I remember of that chip. Turning SMP on won't do anything for you - shouldn't do any harm either though.
Maybe you're confusing Hypertransport with hyperthreading.
All times are GMT -5. The time now is 03:14 PM .
LinuxQuestions.org is looking for people interested in writing
Editorials, Articles, Reviews, and more. If you'd like to contribute
content, let us know .
Latest Threads
LQ News