[tulip-bug] transmit timed out + too much work during an inte rrupt problems

[Gehrken Klaus]

This message is in MIME format. Since your mail reader does not understand
this format, some or all of this message may not be legible.

------_=_NextPart_000_01C243A8.4C17F380
Content-Type: text/plain;
	charset="iso-8859-1"

Dear Donald,

thanks for help!
Here is some additional infomration: output of cat /dev/proc/net  and output
of tulip-diag -af on the living interfaces (the last three days we did not
had the "hangup situation").
A real strange thing is, the catalyst ports (all fixed at 100MB-FD) report
no errors at all ?!
  

> You can increase the max_interrupt_work parameter, but this likely the
driver protecting the system from interrupt thrashing.  During the
no-interrupt periods the NIC runs short of receive buffers.

Hm, its on the default of 25 (what is an event? carrier transition, rx
packet ?)
What are the risks increasing it? 
How can i find/recognize "the limits"?


>   What kind of workload do you have?

We have heavy network traffic, no other CPU load. 
This is a firewall system without software encryption. Since the
firewall-module runs in kernel mode, it is hard to find out, what load it
causes.
Anyway the load in mpstat is between usr:0-1% sys:0-1% (1500-6200 intr/s)!
Half of the 256M memory is still free.
There seems to be no CPU/RAM overload.
 
>   How important is handling network traffic vs. doing other work?

Network is most important!

regards and many thanks for your comments,
Klaus Gehrken


------_=_NextPart_000_01C243A8.4C17F380
Content-Type: text/plain;
	name="tudiag_af.txt"
Content-Disposition: attachment;
	filename="tudiag_af.txt"

tulip-diag.c:v2.03 7/31/2000 Donald Becker (becker@scyld.com)
 http://www.scyld.com/diag/index.html
Index #1: Found a Digital DS21143 Tulip adapter at 0xc800.
Digital DS21143 Tulip chip registers at 0xc800:
  f8a08000 ffffffff ffffffff 0ffdc000 0ffdc200 f0660000 b38ea202 fbfffbff
  e0000000 ffffcbf8 ffffffff 8b240000 000000c4 ffff0001 fffbff7f 8fff0008
 Port selection is 100mbps-SYM/PCS 100baseTx scrambler, full-duplex.
 Transmit started, Receive started, full-duplex.
  The Rx process state is 'Waiting for packets'.
  The Tx process state is 'Idle'.
  The transmit threshold is 512.
  The NWay status register is 000000c4.
  Internal autonegotiation state is 'Autonegotiation disabled'.
Index #2: Found a Digital DS21143 Tulip adapter at 0xc400.
Digital DS21143 Tulip chip registers at 0xc400:
  f8a08000 ffffffff ffffffff 0e447000 0e447200 f0660000 b38ee202 fbfffbff
  e0000000 ffffcbf8 ffffffff 8b240000 000000c5 ffff0001 fffbff7f 8fff0008
 Port selection is 100mbps-SYM/PCS 100baseTx scrambler, full-duplex.
 Transmit started, Receive started, full-duplex.
  The Rx process state is 'Waiting for packets'.
  The Tx process state is 'Idle'.
  The transmit threshold is 1024.
  The NWay status register is 000000c5.
  Internal autonegotiation state is 'Autonegotiation disabled'.
Index #3: Found a Digital DS21143 Tulip adapter at 0xc000.
Digital DS21143 Tulip chip registers at 0xc000:
  f8a08000 ffffffff ffffffff 0e446000 0e446200 f0660000 b38ee202 fbfffbff
  e0000000 ffffcbf8 ffffffff 8b240000 000000c4 ffff0001 fffbff7f 8fffc008
 Port selection is 100mbps-SYM/PCS 100baseTx scrambler, full-duplex.
 Transmit started, Receive started, full-duplex.
  The Rx process state is 'Waiting for packets'.
  The Tx process state is 'Idle'.
  The transmit threshold is 1024.
  The NWay status register is 000000c4.
  Internal autonegotiation state is 'Autonegotiation disabled'.
Index #4: Found a Digital DS21143 Tulip adapter at 0xb800.
Digital DS21143 Tulip chip registers at 0xb800:
  f8000000 ffffffff ffffffff 7787d7fb ca975f9d f0000010 b2420200 f3fe0000
  e0000000 ffffcbf8 ffffffff 00000000 000022ce ffff0001 fffbffff 8ff5c008
 Port selection is 10mpbs-serial, full-duplex.
 Transmit stopped, Receive stopped, full-duplex.
  The Rx process state is 'Stopped'.
  The Tx process state is 'Stopped'.
  The transmit threshold is 72.
  The NWay status register is 000022ce.
  Internal autonegotiation state is 'Ability detect'.

------_=_NextPart_000_01C243A8.4C17F380
Content-Type: text/plain;
	name="proc_net.txt"
Content-Disposition: attachment;
	filename="proc_net.txt"

Inter-|   Receive                                                |  Transmit
 face |bytes    packets errs drop fifo frame compressed multicast|bytes    packets errs drop fifo colls carrier compressed
    lo:   54504     524    0    0    0     0          0         0    54504     524    0    0    0     0       0          0
  eth0:2840129094 2442199066  227    0    0     0          0         0 2531858554 3337282284    0    0    5     0       0          0
  eth1:2423737106 431118998  129    0    0     0          0         0 3320434852 508792981    0    0    5     0       0          0
  eth2:4110241397 3909253922    0 3726    0     0          0         0 2781859933 2894046797  145    0    5     0       4          0
  eth3:3007384615 701619792    0  468    0     0          0         0 803089869 632777123  266    0    3     0     260          0
  eth4:2458871273 1137927167    0 2254    0     0          0         0 2895040569 1220797357  550    0    6     0     415          0
  eth5:       0       0    0    0    0     0          0         0        0       0    0    0    0     0       0          0

------_=_NextPart_000_01C243A8.4C17F380--