Hangout 07 Feb 2019
Old Business
- IPv6 Fragment reviews which need testing:
IPv6 modernization project: Wiki Page
Julius proposed importing OpenBSD fragmentation regression test cases (see D17376). tjh@ will work on in next two weeks.
- IP6 IDs (and IP IDs, maybe?): may use an insecure algorithm. Ideally, switch to some sort of per-host-pair hash?
- Open PR by jtl@
Auto-window scaling: tuexen@ opened review: D18375
Congestion window collapse: D17614 (review by lstewart@)
- jtl@ to send patch to Richard for burst mitigation in the default stack
D18811: standardize on snd_recover (vs. sack_newdata). Reviewer: tuexen@, lstewart@.
- TCP reassembly code
tuexen@ will MFC. Review available in D18960.
- bz@ found an issue with enabled debug code and doing logging. tuexen@ will talk to rrs@ about a fix for head and stable/12.
@tuexen RTO.Initial from 3 seconds to 1 seconds: D18941. Before that gets committed, the SYN specific backoff factors will be removed. Without doing so, the SYN-cache lifetimes will be too short. This is done in D18974
CUBIC: Only invoking NewReno after_idle, not resetting ssthreash, not resetting epoch time. Upcoming patch from Richard/Cheng. kbowling@ mentions that there were other issues in the past. Fixes: D18982 and D18954, which will be splitted.
Richard will brought up a PRR patch (based on Lars work). D18892.
Sending on IPv4 raw sockets need more input validation: D18834.
New Business
D19000 deal with a bug that the 1 byte occupied in the sequence number space by SYN segments results in a cwnd increase when acked. This bug exists only on the server side. tuexen@ and Richard are working on it.
Richard is working on burst mitigation. An initial version (WIP) is available as D19047.
Heads up: Hackathon on Aberdeen.