Hi Bill (again),
I've got some non-cached numbers for you:

Using a single file containing 100000, 440 byte packets:
tcpreplay-3.3.2 -i eth1 -q -t -l 50 single.pcap
Actual: 5000000 packets (2200000000 bytes) sent in 22.93 seconds
Rated: 99575688.0 bps, 759.70 Mbps/sec, 226308.39 pps

Single file containing 100000, 1500 byte packets:
tcpreplay-3.3.2 -i eth1 -q -t -l 50 single.pcap
Actual: 5000000 packets (7500000000 bytes) sent in 63.56 seconds
Rated: 117995800.0 bps, 900.24 Mbps/sec, 78663.87 pps

On the basis of these numbers the only factor that I can see that might 
give you some issues is if you're after highly accurate timing. (note 
that the figures above are using the "-t", top speed, option)
The figure you gave earlier of approximately 100k packets/second should 
not be a huge problem to achieve.

> Hi Bill,
> I went back yesterday to collect some numbers for you. These are taken 
> using the cache option so we can see best case scenario.
>
> Replaying a single 440 byte packet:
> tcpreplay-3.3.2 -i eth1 -q -t -l 10000000 -K single.pcap
> Actual: 10000000 packets (4400000000 bytes) sent in 43.52 seconds
> Rated: 101081024.0 bps, 771.19 Mbps/sec, 229729.61 pps
> CPU was pretty well flat out.
>
> Replaying a single 1500 byte packet:
> tcpreplay-3.3.2 -i eth1 -q -t -l 1000000 -K single.pcap
> Actual: 1000000 packets (1500000000 bytes) sent in 12.27 seconds
> Rated: 122217080.0 bps, 932.44 Mbps/sec, 81478.05 pps
> CPU usage was about between 40 and 50%
>
> The hardware that I'm running this on is nothing particularly special. 
> It's about a 2Ghz P4 with about 1gig of ram. It does have a pci-express 
> x4 gigabit ethernet card though. (Syskonnect, from memory)
>
> I'll try and get back to you with some figures when not using the cache 
> option.
>
> cheers,
> Andrew Edgecombe
>
> William Cobau wrote:
>   
>> Andrew,
>>
>> Average packet size is about 450 bytes with a packet rate or 100k  
>> packets/second.
>>
>> So what type of box do you use? How much disk? How long can you  
>> saturate a link with 1k sized packets?
>>
>> Bill Cobau
>>
>> On May 26, 2008, at 6:29 PM, Andrew Edgecombe wrote:
>>
>>   
>>     
>>> William Cobau wrote:
>>>     
>>>       
>>>> Tcpreplay community,
>>>>
>>>> I am already successfully using tcpreplay for my testing activities.
>>>> Our setup is rather simple with a Linux server (typically Redhat EL5)
>>>> connected directly via 1000 B/T to the system under test. The linux
>>>> server uses tcpreplay (presently v3.2.5, but we could/will upgrade to
>>>> v3.3.x) to send previous captured data streams to the system under
>>>> test. There is no need for tcprewrite or the other tools in the
>>>> tcpreplay suite as the tcpreplay box is simulating a mirror port  
>>>> or a tap.
>>>>
>>>> We are trying to enhance our testing by increasing amount of data and
>>>> the data rate. The data was captured at roughly 350 Mbps over 3 hours
>>>> for 450 Gbytes/1e9 packets.
>>>>
>>>> Has anyone built or bought a box that handles this data rate and
>>>> volume? Any suggestions or comments would be welcome.
>>>>
>>>> Bill Cobau
>>>>       
>>>>         
>>> Hi William,
>>> What sort of traffic are you trying to replay? In particular, what  
>>> sort
>>> of packet sizes are you using?
>>> I've found in testing that the packet rate that I'm able to achieve is
>>> more or less consistent regardless of the packet size. Meaning that if
>>> I'm replaying large packets (eg. 1k) I can saturate a gigabit link  
>>> (even
>>> without the cache option), but if I'm replaying small packets (eg.
>>> 58bytes) I'll see figures more like 80mb/s.
>>>
>>> I second Peter Van Epp's comments about pci-express. If possible  
>>> I'd go
>>> for a pci-express x4, or better, card.
>>>
>>> Andrew Edgecombe
>>>
>>>     
>>>       


-------------------------------------------------------------------------
This SF.net email is sponsored by: Microsoft
Defy all challenges. Microsoft(R) Visual Studio 2008.
http://clk.atdmt.com/MRT/go/vse0120000070mrt/direct/01/
_______________________________________________
Tcpreplay-users mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/tcpreplay-users
Support Information: http://tcpreplay.synfin.net/trac/wiki/Support

Reply via email to