Attendees: rgrimes@, rrs@, rscheff@, thj@, tuexen@
Discussion
- tuexen discussed how to mitigate blackhole detection problems
tuexen@ has a review to ensure we don't do blackhole detection once we are at the minimum value D24308; committed
- Discussion on what should trigger blackhole detection -- full size? Or, even smaller messages which are above our min MTU? For at least IPv6, min MTU makes sense.
- Otherwise, tuexen@'s plan remains unchanged.
- BBR and RACK needs some modifcation
Discussion of D24237: rscheff@ changed both the in-order and out-of-order data path so we call sorwakeup_locked() [when necessary] after the SACK blocks are updated. Still ongoing. rrs@ will review.
PR241958: Not sure what happens there. tuexen will try to reproduce it on stable/12 in VBox. thj@ has reproduced this on bhyve.
D18624: Approved by kbowling@.
- Can the TCP_STATS framework be turned on and sample no connections? Yes. thj@ will do.
D18892: Upcoming: PRR
D18985: Upcoming: Rescue retransmission
D21117: Upcoming: Reduce counter space
D22438: Upcoming: Performance improvement for after idle
D25746: Cubic fix. Waiting for NetAPP testing.
D25976: Another Cubic fix. Waiting for NetAPP testing.
- Cubic: When to increase the congestion window? Once per tick instead of once per send window or when an ACK comes in? Once per ACK is suggested. rscheff@ will provide a patch?
D6611, D6612, D6656: Get gallatin@ involved. What needs to be done to also support IPv6?
D8253: rscheff@ will look into it.
D10894: possibly use hystart++ instead. rrs@ will look into this later this year.
- Anyone using NICs with P4 support?
Next meeting: 27 August @ 1400 UTC