| 1 |
Ok, I've fixed the problem. I've plugged both systems into my router |
| 2 |
(which is a switch) and they are working fine now. There is obviously a |
| 3 |
bug in the 8139too driver. I'll have to live with the long cables going |
| 4 |
to the switch for the time being though!! |
| 5 |
|
| 6 |
Cheers for everyones help. |
| 7 |
Dave. |
| 8 |
|
| 9 |
James wrote: |
| 10 |
|
| 11 |
>Dave Oxley <dave <at> daveoxley.co.uk> writes: |
| 12 |
> |
| 13 |
> |
| 14 |
> |
| 15 |
> |
| 16 |
>>Yeah, its a hub. I'll stop trying to set it to full duplex now. |
| 17 |
>> |
| 18 |
>> |
| 19 |
> |
| 20 |
> |
| 21 |
> |
| 22 |
>>It is 40 times quicker in one direction than the other. Can you |
| 23 |
>>give me a hint where to go from here. |
| 24 |
>> |
| 25 |
>> |
| 26 |
> |
| 27 |
>Try connecting the 2 systems with only a 'cross-over cable' run the applications |
| 28 |
>and make measurements. If this results in an increase in the bandwidth |
| 29 |
>in either direction, you may want to put systems back on the hub, and |
| 30 |
>have a third system run ethereal. Look at your data traffic and see |
| 31 |
>if anythingelse is using the bandwidth from either of these 2 system |
| 32 |
>or what else is plug into the hub/switch. |
| 33 |
> |
| 34 |
>Is the hub a 10Mbps only hub/switch, check that. On 10 Mbps ethernet |
| 35 |
>hubs,you can never reach the full 10 Mbps, in fact with many systems |
| 36 |
>chattering,the practical throughput is marginally around 33%. |
| 37 |
> |
| 38 |
>If when you are on the cross over cable and you get similar poor |
| 39 |
>results,then the problem may be in the ethernet driver code, |
| 40 |
>kernel, irq settings or |
| 41 |
>some other low level part of the kernel/modules, especially if |
| 42 |
>you get the same skewed results with several different |
| 43 |
>applications moving data between the systems. But, if when |
| 44 |
> you move data between these 2 isolated system, and |
| 45 |
>get different bandwidth performance semantics, then the problem |
| 46 |
>is most likely between the applications or a bottleneck in the |
| 47 |
>application code (poor data structure for example). |
| 48 |
> |
| 49 |
>Make sure you computers are not resource limited, thus blocking |
| 50 |
>the processthat you are running to move the data. Top and ntop |
| 51 |
>are just a few toolsto help track down these sort of issues. |
| 52 |
> |
| 53 |
>Sadly, you may have a complex mix of part or all of these |
| 54 |
>aforementioned issues... |
| 55 |
> |
| 56 |
>hth, |
| 57 |
>James |
| 58 |
> |
| 59 |
> |
| 60 |
> |
| 61 |
-- |
| 62 |
gentoo-user@g.o mailing list |
Archives