[Oisf-users] af_packet and rss queue count

Cooper F. Nelson cnelson at ucsd.edu
Thu Jan 26 19:56:33 UTC 2017

I admit I've had a hard time finding good documentation on this subject.
 For example, to determine the maximum size of merged packets I had to
just record traffic for a while and then look at it in wireshark.

From what I've read GRO supersedes LRO and is a hybrid
(hardware+software) solution.  It also supports TCP and UDP, whereas LRO
only supports TCP.  I've googled a bit more and see other references
suggesting it's a software-only solution, implemented within the


On 1/26/2017 11:32 AM, Michał Purzyński wrote:
> GRO is not hardware. LRO would be.
> GRO kicks in later in the path and results with pretty significant
> savings of the amount of work kernel needs to do per packet, since
> packets are merged.
> Hence the word Generic there ;) it's basically merging packets before
> taking them out of the DMA area. And it is smarter, much smarter,
> about which packets should be merged. LRO merges everything in sight
> - GRO does not.
> LRO is gone from newest cards too.

Cooper Nelson
Network Security Analyst
UCSD ITS Security Team
cnelson at ucsd.edu x41042

-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 488 bytes
Desc: OpenPGP digital signature
URL: <http://lists.openinfosecfoundation.org/pipermail/oisf-users/attachments/20170126/760433ac/attachment-0002.sig>

More information about the Oisf-users mailing list