Optimization #1014
closed
app layer reassembly fast-path
Added by Victor Julien about 11 years ago.
Updated over 9 years ago.
Description
In many cases the applayer reassembly will just send one payload to the applayer. Currently, we copy this one segment into a buffer and push that. Should be faster to directly invoke applayer on the segment.
Another fast-path possibility: we often walk the entire segment list only to find out all segments have already been processed and are just in the list while the smsg is still in flight. We could also as a fast-path first only check the seg_list_tail flags.
- Priority changed from Normal to Low
- Target version changed from 2.0rc2 to 3.0RC2
- Priority changed from Low to Normal
- Target version changed from 3.0RC2 to 2.1beta4
- Status changed from Assigned to Closed
- % Done changed from 0 to 100
Also available in: Atom
PDF