Tulip tx and rx stopage
Marko Engelmann
ema@tesis.de
Tue Nov 24 12:41:32 1998
On Mon, 23 Nov 1998, Jim Bauer wrote:
>
>I can easily recreate the problem by running...
>
> find /usr -type f -exec wc {} \;
>
>while ping flooding the system. I have not tried this on kernel
>version earlier then 2.1.127..
>
Yes, i have the same problems, but with 2.0.3[56], tulip 0.89
I have 5 different machines with "dlink dfe500" and some intel eepro100.
I could reproduce this with FreeBSD and Solaris(intel,7.0).
May this be some trouble between the busmaster network-devices and my
busmaster-capable ncr-53c810-scsi-controllers ?
also tested with 100MBit (cross-over-cable) and connections via an
10Mbit-hub
Same result: slow traffic make no problems, ping flooding or
ftp-transmission of big files leads to this "transmit-timeouts" after a
few seconds, mostly in combination with "scsi-command-timeouts"...
I dont think, this is a (single) hardware-problem:
* different mashines: P90,P100,K5, 2*K6, different Boards, different
OS's, different NIC's ( 5 dlink's, 2 eepro100, 1 eepro10)
>Boot messages, tulip driver is *not* a module.
>
>eth0: 21041 transmit timed out, status fc660000, CSR12 000001c8, CSR13 ffffef05, CSR14 ffffff3f, resetting...
>eth0: 21041 transmit timed out, status fc660010, CSR12 000052c8, CSR13 ffffef09, CSR14 fffff7fd, resetting...
me too ;-(
>ifconfig eth0 down; ifconfig eth0 up
>fixes the problem.
mhh. don't tried this yet.
>System is a UP 200MHz K6, all SCSI, Kingston KNE40T tulip based
>ethernet card.
>
no IDE-systems here ;-)...
Yours
Marko
PS: short list of tested combinations:
linux(tulip) - linux(eepro10)
linux(tulip) - linux(tulip)
linux(epro10) - sol7.0(tulip)
bsd(eepro100) - bsd(eepro100) [100FD]
linux(eepro100) - linux(eepro100) [100FD+10HD]
linux(tulip) - bsd(tulip)
linux(tulip) - bsd(eepro100)
------------------------------------
Marko Engelmann \
email: ema@tesis.de | Never trust a |
phone: +049/089 747377-0 | short-haired guru |
SysAdmin - TESIS GmbH Munic,Germany /
------------------------------------