[eepro100] Too many interrupts

infos chez fdrconseil infos at fdrconseil.fr
Sat Apr 2 07:58:22 PST 2005


Hi,

I am using an Intel eepro 100 dual port adapter and I have a problem.
I want to use only one port (eth0) and no cable is connected on the second  
one.
The board is using IRQ 6; Apparently, there is no IRQ sharing.
The network is running well.
The problem is that the network board is raising a huge amount of  
interrupts and the CPUs
(bi pentium III motherboard) are busy processing these interrupts (about  
10%).

Here are some screen shots :

vmstat 1       when the machine is idle (see the "in" column) :

procs -----------memory---------- ---swap-- -----io---- --system--  
----cpu----
  r  b   swpd   free   buff  cache   si   so    bi    bo   in    cs us sy  
id wa
  0  0      0 638512  22620 179392    0    0     0     0 148920    26  0  9  
91  0
  0  0      0 638512  22620 179392    0    0     0     0 148903    30  0 11  
89  0
  0  0      0 638512  22624 179392    0    0     0   104 148758    32  0 16  
84  0
  0  0      0 638512  22624 179392    0    0     0     0 148900    31  0 12  
88  0
  0  0      0 638512  22624 179392    0    0     0     0 148934    24  0 13  
87  0
  0  0      0 638512  22624 179392    0    0     0     0 148911    30  0 12  
88  0
  0  0      0 638512  22636 179392    0    0     0   168 148691    39  0 13  
87  0
  0  1      0 638512  22636 179392    0    0     0     0 149128    29  0 11  
88  0
  0  0      0 638512  22640 179392    0    0     4     0 148932    26  0 11  
88  0
  0  0      0 638512  22640 179392    0    0     0     0 148652    66  4  8  
88  0
  0  0      0 638512  22640 179392    0    0     0     0 148909    26  0  9  
91  0
  0  0      0 638512  22656 179392    0    0     0   132 148731    43  0 13  
87  0
  0  0      0 638512  22656 179392    0    0     0     0 149125    24  0 10  
90  0


Contents of /proc/interrupts :

            CPU0       CPU1
   0:     345727     344918    IO-APIC-edge  timer
   1:          4          1    IO-APIC-edge  keyboard
   2:          0          0          XT-PIC  cascade
   6:  501331320  501309654   IO-APIC-level  eth0
   8:          0          1    IO-APIC-edge  rtc
  10:       4529       4453   IO-APIC-level  dlgnpci
  14:       9785       8091    IO-APIC-edge  ide0
  15:       8969       7710    IO-APIC-edge  ide1
NMI:          0          0
LOC:     690547     690524
ERR:          0
MIS:          0

The same file, few seconds later :

            CPU0       CPU1
   0:     346414     345604    IO-APIC-edge  timer
   1:          4          1    IO-APIC-edge  keyboard
   2:          0          0          XT-PIC  cascade
   6:  502333959  502312308   IO-APIC-level  eth0
   8:          0          1    IO-APIC-edge  rtc
  10:       4531       4453   IO-APIC-level  dlgnpci
  14:       9788       8097    IO-APIC-edge  ide0
  15:       8975       7714    IO-APIC-edge  ide1
NMI:          0          0
LOC:     691920     691897
ERR:          0
MIS:          0

Here is the dmesg messages when starting the system :

Apr  2 15:52:47 localhost kernel: EXT3-fs: mounted filesystem with ordered  
data mode.
Apr  2 15:52:47 localhost kernel: eepro100.c:v1.09j-t 9/29/99 Donald  
Becker http://www.scyld.com/network/eepro100.html
Apr  2 15:52:47 localhost kernel: eepro100.c: $Revision: 1.36 $ 2000/11/17  
Modified by Andrey V. Savochkin <saw at saw.sw.com.sg> and others
Apr  2 15:52:47 localhost kernel: eth0: Intel Corp. 82557/8/9 [Ethernet  
Pro 100], 00:02:B3:B6:2B:39, IRQ 6.
Apr  2 15:52:47 localhost kernel:   Board assembly a56831-002, Physical  
connectors present: RJ45
Apr  2 15:52:47 localhost kernel:   Primary interface chip i82555 PHY #1.
Apr  2 15:52:47 localhost kernel:     Secondary interface chip i82555.
Apr  2 15:52:47 localhost kernel:   General self-test: passed.
Apr  2 15:52:47 localhost kernel:   Serial sub-system self-test: passed.
Apr  2 15:52:47 localhost kernel:   Internal registers self-test: passed.
Apr  2 15:52:47 localhost kernel:   ROM checksum self-test: passed  
(0xb874c1d3).
Apr  2 15:52:47 localhost kernel: eth1: Intel Corp. 82557/8/9 [Ethernet  
Pro 100] (#2), 00:02:B3:B6:2B:3A, IRQ 11.
Apr  2 15:52:47 localhost kernel:   Board assembly a56831-002, Physical  
connectors present: RJ45
Apr  2 15:52:47 localhost kernel:   Primary interface chip i82555 PHY #1.
Apr  2 15:52:47 localhost kernel:     Secondary interface chip i82555.
Apr  2 15:52:47 localhost kernel:   General self-test: passed.
Apr  2 15:52:47 localhost kernel:   Serial sub-system self-test: passed.
Apr  2 15:52:47 localhost kernel:   Internal registers self-test: passed.
Apr  2 15:52:47 localhost kernel:   ROM checksum self-test: passed  
(0xb874c1d3).


# lsmod | grep eepro100

eepro100               21780   1  (autoclean)
mii                     3996   0  (autoclean) [eepro100]


# grep eepro100 /etc/modules.conf

alias eth0 eepro100


The questions are :
- Am i wrong saying the problem comes from the network card ?
- What can I do ? (CPU power is wasted and CPU temperature increases)

Thank you for your answers,

FdR





More information about the eepro100 mailing list