Hey Lothar,

I've just done some testing:

First the beta12 binary:
./src/tcpreplay -i en0 -tl 50000 test/test.pcap
Actual: 5000000 packets (531450000 bytes) sent in 28.66 seconds
Rated: 18540696.0 bps, 141.45 Mbps/sec, 174435.02 pps

Then using a hacked version which doesn't print the notices (they're
commented out):
Actual: 5000000 packets (531450000 bytes) sent in 28.90 seconds
Rated: 18384908.0 bps, 140.27 Mbps/sec, 172969.33 pps

This is on a Apple Powerbook G4 1.67Ghz, 2GB of RAM.  The
test/test.pcap in the source tarball is  100 packets.

You'll notice that they're basically the same (actually the version
which printed the notices was .24 seconds faster).  I also tried the
latest 2.3.5 binary with the equivalent options:

 ../branches/stable/tcpreplay -i en0 -l 50000 -R test/test.pcap
 5000000 packets (531450000 bytes) sent in 35.85 seconds
 14824134.0 bytes/sec 113.10 megabits/sec 139468 packets/sec

This is what I would expect based on how much more optimized the code
in 3.0.beta12 is vs. 2.x.

Anyways, since my results are very different from yours, I was hoping
you could send me the exact command lines you were using for beta12 &
2.3.5 as well as the pcap involved.

Thanks,
Aaron

On 2/23/07, Lothar Braun <[EMAIL PROTECTED]> wrote:
> Hi,
>
> i replayed a small dump file (about 30 packets) using -l 10000 at different
> speeds (2000, 4000, 8000 and 15000 pkts/s) using tcpreplay 2.x and tcpreplay
> 3.0.betax
> Both, tcpreplay 2 and 3, displayed the message
>
> processing file: /home/lothar/net/localhost.dump
>
> on stdout.
>
> Tcpreplay 2 writes this message once, while tcpreplay 3.0 writes the message
> each time the dumpfile is processed. This behavior results in an huge amount
> of messages printed to the screen with tcpreplay.
> The more packets per second you replay, the more busy tcpreplay gets printing
> these messages.
>
> Whereas tcpreplay 2 had no problem to send out all packets at 15000 pkts/s,
> tcpreplay 3 already got problems at 4000 pkts/s because it was so busy
> printing its messages.
>
> I think it would be a good idea to get the tcpreplay-2 behavior back. Is that
> possible for the next beta or the final release?
>
> Best regards,
>   Lothar
>
> --
> Blog: http://const-cast.blogspot.com
>
> -------------------------------------------------------------------------
> Take Surveys. Earn Cash. Influence the Future of IT
> Join SourceForge.net's Techsay panel and you'll get the chance to share your
> opinions on IT & business topics through brief surveys-and earn cash
> http://www.techsay.com/default.php?page=join.php&p=sourceforge&CID=DEVDEV
> _______________________________________________
> Tcpreplay-users mailing list
> [email protected]
> https://lists.sourceforge.net/lists/listinfo/tcpreplay-users
>
>
>


-- 
Aaron Turner
http://synfin.net/
http://tcpreplay.synfin.net/ - Pcap editing & replay tools for Unix

-------------------------------------------------------------------------
Take Surveys. Earn Cash. Influence the Future of IT
Join SourceForge.net's Techsay panel and you'll get the chance to share your
opinions on IT & business topics through brief surveys-and earn cash
http://www.techsay.com/default.php?page=join.php&p=sourceforge&CID=DEVDEV
_______________________________________________
Tcpreplay-users mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/tcpreplay-users

Reply via email to