Skip to contentSkip to conversation

2.5.65-mm1: eth0: Transmit error, Tx status register 90

DISCUSSION Felipe Alfaro Solana 2 participants 2 messages Mar 19, 2003

lore
Share & tools
lore
#0 lore raw

----- Original Message -----
From: Andrew Morton <[email protected]>
Date: Tue, 18 Mar 2003 19:18:33 -0800
To: "Felipe Alfaro Solana" <[email protected]>
Subject: Re: 2.5.65-mm1: eth0: Transmit error, Tx status register 90

Quoted 9 lines
Quoted 6 lines · Felipe Alfaro Solana

I've been benchmarking file copy operations between 2.5.65-mm1 and 2.4.20-2.51 since I have noticed that transferring files from my 2.4.20 machine to 2.5.65-mm1 gives an steady 10MBps throughput but doing the opposite (from 2.5.65-mm1 to 2.4.20) gives me a mere 3MBps throughput.

Is it slow with both scp and NFS? Or just NFS?

Well, it seems the network transport is slow. I have benchmarked using NFS, FTP and SCP and *all* of them are 4 orders of magnitude slower when sending data (from 2.5 to 2.4), but behave normally when receiving data (from 2.4 to 2.5).

Quoted 2 lines

If just NFS then yes, I see this too. Transferring files 2.5->2.4 over NFS is several times slower than 2.4->2.4 or 2.5->2.5. Quite repeatable.

The problem is that FTP is also four times slower. Here are my timings against 2.5.64 vanilla:

Test case: 128MB file (dd if=/dev/zero of=test bs=1024k count=128)

NFS
---
time cp 2.4 -> 2.5: 0m11.759s
time cp 2.5 -> 2.4: 0m39.541s

FTP
---
time get 2.4 -> 2.5: 11.5s
time put 2.5 -> 2.4: 43.3s

So it seems a problem with the network transport. This doesn't happen with 2.4 on the same hardware: NEC Chrom@ laptop, TI CardBus bridge, 3Com Corporation 3CCFE575CT Cyclone CardBus (rev 10) NIC.

Attached is my .config file. It's worth a look since I needed to build CardBus into the kernel (my RedHat distro doesn't work with CardBus built as a module).

Quoted 4 lines

That's a transmit underrun. The PCI/memory system was not able to feed data into the NIC fast enough.
Please determine when this started. 2.5.64 would be a good kernel to test because it doesn't have the PCI changes.

During benchmarks with 2.5.64 I've also seen this errors, although they were quite few (only two).

Now, what else? I'm lost...
Thanks!

Felipe

Signature · 5 lines
______________________________________________
http://www.linuxmail.org/
Now with e-mail forwarding for only US$5.95/yr

Powered by Outblaze
#1 lore raw
Quoted 2 lines · Felipe Alfaro Solana

So it seems a problem with the network transport.

yes, it's a network problem.

Quoted 4 lines

This doesn't
happen with 2.4 on the same hardware: NEC Chrom@ laptop, TI CardBus bridge, 3Com Corporation 3CCFE575CT Cyclone CardBus (rev 10) NIC.

Ah. You're using cardbus. Please send lspci output.

Quoted 1 line

Now, what else? I'm lost...

The NIC driver is basically unchanged from 2.4. It will be a cardbus/PCI/northbrige/southbridge setup problem.

Look for suspicious dmesg output. Compare the `lspci -vvxx' output for 2.5 and 2.4, see if any of the registers look different. This will be hard.