[Ns-developers] For Review: Redo ASCII and pcap Tracing
craigdo at ee.washington.edu
Fri Jan 29 10:05:11 PST 2010
> > I haven't done performance measurements yet to quantify the impact of
> > the header before writing the pcap traces out, but if it becomes a
> > like the old joke, I just won't do that.
> It seems like we need to test this now since this issue of adding
> was the main concern raised during last month's review. Is there a
> forward if we find that it does impact performance?
Yes. I'm doing these tests now, but the ultimate answer don't seem to block
a code review since an alternate plan that doesn't do the copy could be
quite easily implemented. BTW, the same add-the-header approach was already
taken elsewhere in existing trace code.
More information about the Ns-developers