(another) Network Response Slowdown

From: John J. LeMay Jr. (jlemay@njmc.com)
Date: Mon Jun 05 2000 - 18:00:07 EST

I have had this before, but I don't think it was ever determined what the
problem may have been.

When under a significant network load (even though only connected at 10Mbit/s
HDX), my Mandrake 6.1 machine with an Intel PRO 100+ adapter grinds to almost no
activity leaving the waiting machine (my mail client on my desktop, for example)
awaiting more data. The only fix has been to ssh over to the box (which is
obviously also excrutiatingly slow, and necessary since I run this headless
unless I need to connect a monitor and keyboard) and execute
"/etc/rc.d/init.d/network restart". ifconfig verifies that the nic is still up
(also obvious), but shows 8 error packets have been received. (See below) How
can I determine (or can I) what these packets were? Is there other info
somewhere in /proc/net that I haven't stumbled upon?

Dump of ifconfig (one more bad packet was rec'd since I restarted the network

[root@gambit jlemay]# ifconfig
eth0 Link encap:Ethernet HWaddr 00:D0:B7:1D:24:82
          inet addr: Bcast: Mask:
          UP BROADCAST RUNNING MTU:1500 Metric:1
          RX packets:4631045 errors:9 dropped:0 overruns:0 frame:3
          TX packets:3438102 errors:0 dropped:0 overruns:0 carrier:0
          collisions:13350 txqueuelen:100
          Interrupt:11 Base address:0x1000

lo Link encap:Local Loopback
          inet addr: Mask:
          UP LOOPBACK RUNNING MTU:3924 Metric:1
          RX packets:233122 errors:0 dropped:0 overruns:0 frame:0
          TX packets:233122 errors:0 dropped:0 overruns:0 carrier:0
          collisions:0 txqueuelen:0

John LeMay Jr.
Senior Enterprise Consultant

The rules have changed... Get paid to surf the web!!!
To unsubscribe from this list: send the line "unsubscribe linux-net" in
the body of a message to majordomo@vger.rutgers.edu

This archive was generated by hypermail 2b29 : Wed Jun 07 2000 - 21:00:33 EST