On Tue, Apr 7, 2015 at 6:19 AM, Matthieu Boutier <bout...@pps.univ-paris-diderot.fr> wrote: >> If you work with atomic route replacement even putting ALL of them >> into a netlink message (or as many as you can fit in) works. > > What I understand is that we can't (in general) work with atomic > *next-hop* replacement (interface index and metric may change). > > I proposed a workaround where instead of using two distinct messages > for "del(r)" and "add(r)" we use one message with "del(r); add(r)". > Even if it's not necessarily atomic (is it?), it should be faster > (only one system call, since it was what frightened Dave).
No "fright" here. Doing an atomic_replace(old_route,new_route) seems *desirable* at high forwarding rates, and measuring the impact on tcp flows when a route switch is staged (*with* reordering, *without* loss) is interesting in the context of evaluating aqm and fq algorithms. Route flaps do nasty things to networks in general. It can wait til after babel-1.6 in particular. I'll have a testbed setup this summer that will pair up an 8 port edgerouter pro (weak cpu) with an 8 port rangeley (much less weak cpu) to fiddle with as a fault tolerant configuration, that I will regularly be driving to saturating loads. ship 1.6 soon please so it lands in edgerouter os 1.7. :) Sorry for the distractions. > Matthieu > -- Dave Täht We CAN make better hardware, ourselves, beat bufferbloat, and take back control of the edge of the internet! If we work together, on making it: https://www.kickstarter.com/projects/onetswitch/onetswitch-open-source-hardware-for-networking _______________________________________________ Babel-users mailing list Babel-users@lists.alioth.debian.org http://lists.alioth.debian.org/cgi-bin/mailman/listinfo/babel-users