On 10/17/2012 10:19 AM, Ajith Adapa wrote:
But does NAPI comes into picture in case of packet transmission ??
it does not
Yeah I have observed that PF_RING has an advantage of 10-15% but both
the application hardly can generate at half the rate.
I know, standard PF_RING focuses on RX
Luca
But seems PF_RING uses more processing power sometimes around 20-30%
more than a PACKET_MMAP application.
Regards,
Ajith
On Wed, Oct 17, 2012 at 1:28 PM, Luca Deri <[email protected]
<mailto:[email protected]>> wrote:
Ajith,
PF_RING is 5-10% faster so they are basically alike as with NAPI
the performance penalty is there
Luca
On 10/17/2012 08:33 AM, Ajith Adapa wrote:
Hi,
I am trying to understand the basic performance differences
between linux kernel supported PACKET_MMAP and PF_RING (without
any DNA and modified drivers).
Have you got any numbers regarding transmission performance with
basic PF_RING and PACKET_MMAP ??
Regards,
Ajith
_______________________________________________
Ntop-misc mailing list
[email protected] <mailto:[email protected]>
http://listgateway.unipi.it/mailman/listinfo/ntop-misc
_______________________________________________
Ntop-misc mailing list
[email protected] <mailto:[email protected]>
http://listgateway.unipi.it/mailman/listinfo/ntop-misc
_______________________________________________
Ntop-misc mailing list
[email protected]
http://listgateway.unipi.it/mailman/listinfo/ntop-misc
_______________________________________________
Ntop-misc mailing list
[email protected]
http://listgateway.unipi.it/mailman/listinfo/ntop-misc
