Re: [PATCH net-next 0/8] tcp: default RACK loss recovery

[David Miller <davem@davemloft.net>]

From: Yuchung Cheng <ycheng@google.com>
Date: Wed, 16 May 2018 16:40:09 -0700

> This patch set implements the features correspond to the
> draft-ietf-tcpm-rack-03 version of the RACK draft.
> https://datatracker.ietf.org/meeting/101/materials/slides-101-tcpm-update-on-tcp-rack-00
> 
> 1. SACK: implement equivalent DUPACK threshold heuristic in RACK to
>    replace existing RFC6675 recovery (tcp_mark_head_lost).
> 
> 2. Non-SACK: simplify RFC6582 NewReno implementation
> 
> 3. RTO: apply RACK's time-based approach to avoid spuriouly
>    marking very recently sent packets lost.
> 
> 4. with (1)(2)(3), make RACK the exclusive fast recovery mechanism to
>    mark losses based on time on S/ACK. Tail loss probe and F-RTO remain
>    enabled by default as complementary mechanisms to send probes in
>    CA_Open and CA_Loss states. The probes would solicit S/ACKs to trigger
>    RACK time-based loss detection.
> 
> All Google web and internal servers have been running RACK-only mode
> (4) for a while now. a/b experiments indicate RACK/TLP on average
> reduces recovery latency by 10% compared to RFC6675. RFC6675
> is default-off now but can be enabled by disabling RACK (sysctl
> net.ipv4.tcp_recovery=0) for unseen issues.

Series applied.

These patches, the design of the ordering of changes in the patch series,
and the commit messages themselves were more than a pleasure to read.

Really, this patch series is a great model for others who want to
improve the quality and reviewability of their submissions.

Thank you.