feat(transport): Use a shorter ECN probe threshold initially #1964

mxinden · 2024-07-06T12:47:29Z

This commit adds a test where a client connects to a server over a connection dropping all ECN marked datagrams (ECN blackhole) in both directions, asserting 43 RTT to detect ECN blackhole, disable ECN and eventually establish connection. Test assumes 20 RTT for client to detect blackhole, 20 RTT for server to detect blackhole and 3 RTT for handshake to be confirmed.

Test for #1925.

How likely are ECN blackholes on today's Internet? Should this block ECN roll-out on Firefox? //CC @larseggert

Bauer et. alia. in "Measuring the State of ECN Readiness in Servers, Clients, and Routers" suggests that ECN blackholes are rare.

Test output

[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = Init
Processing Client at 0ms
0s  0ms DEBUG ECN probing: sent 1 probes
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = Init
Processing Server at 50ms
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = WaitInitial
Processing Client at 100ms
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = Init
Processing Server at 150ms
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = WaitInitial
Processing Client at 200ms
0s  0ms DEBUG ECN probing: sent 2 probes
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = Init
Processing Server at 250ms
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = WaitInitial
Processing Client at 300ms
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = Init
Processing Server at 350ms
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = WaitInitial
Processing Client at 400ms
0s  0ms DEBUG ECN probing: sent 3 probes
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = Init
Processing Server at 450ms
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = WaitInitial
Processing Client at 500ms
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = Init
Processing Server at 550ms
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = WaitInitial
Processing Client at 600ms
0s  1ms DEBUG ECN probing: sent 4 probes
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = Init
Processing Server at 650ms
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = WaitInitial
Processing Client at 700ms
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = Init
Processing Server at 750ms
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = WaitInitial
Processing Client at 800ms
0s  1ms DEBUG ECN probing: sent 5 probes
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = Init
Processing Server at 850ms
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = WaitInitial
Processing Client at 900ms
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = Init
Processing Server at 950ms
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = WaitInitial
Processing Client at 1000ms
0s  1ms DEBUG ECN probing: sent 6 probes
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = Init
Processing Server at 1050ms
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = WaitInitial
Processing Client at 1100ms
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = Init
Processing Server at 1150ms
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = WaitInitial
Processing Client at 1200ms
0s  2ms DEBUG ECN probing: sent 7 probes
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = Init
Processing Server at 1250ms
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = WaitInitial
Processing Client at 1300ms
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = Init
Processing Server at 1350ms
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = WaitInitial
Processing Client at 1400ms
0s  2ms DEBUG ECN probing: sent 8 probes
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = Init
Processing Server at 1450ms
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = WaitInitial
Processing Client at 1500ms
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = Init
Processing Server at 1550ms
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = WaitInitial
Processing Client at 1600ms
0s  3ms DEBUG ECN probing: sent 9 probes
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = Init
Processing Server at 1650ms
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = WaitInitial
Processing Client at 1700ms
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = Init
Processing Server at 1750ms
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = WaitInitial
Processing Client at 1800ms
0s  3ms DEBUG ECN probing: sent 10 probes
0s  3ms DEBUG ECN probing concluded with 10 probes sent
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = Init
Processing Server at 1850ms
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = WaitInitial
Processing Client at 1900ms
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = Init
Processing Server at 1950ms
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = WaitInitial
Processing Client at 2000ms
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = Init
Processing Server at 2050ms
0s  5ms DEBUG ECN probing: sent 1 probes
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = WaitInitial
Processing Client at 2100ms
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = Handshaking
Processing Server at 2150ms
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = WaitInitial
Processing Client at 2200ms
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = Handshaking
Processing Server at 2250ms
0s  6ms DEBUG ECN probing: sent 2 probes
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = WaitInitial
Processing Client at 2300ms
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = Handshaking
Processing Server at 2350ms
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = WaitInitial
Processing Client at 2400ms
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = Handshaking
Processing Server at 2450ms
0s  8ms DEBUG ECN probing: sent 3 probes
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = WaitInitial
Processing Client at 2500ms
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = Handshaking
Processing Server at 2550ms
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = WaitInitial
Processing Client at 2600ms
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = Handshaking
Processing Server at 2650ms
0s  9ms DEBUG ECN probing: sent 4 probes
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = WaitInitial
Processing Client at 2700ms
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = Handshaking
Processing Server at 2750ms
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = WaitInitial
Processing Client at 2800ms
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = Handshaking
Processing Server at 2850ms
0s 10ms DEBUG ECN probing: sent 5 probes
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = WaitInitial
Processing Client at 2900ms
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = Handshaking
Processing Server at 2950ms
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = WaitInitial
Processing Client at 3000ms
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = Handshaking
Processing Server at 3050ms
0s 12ms DEBUG ECN probing: sent 6 probes
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = WaitInitial
Processing Client at 3100ms
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = Handshaking
Processing Server at 3150ms
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = WaitInitial
Processing Client at 3200ms
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = Handshaking
Processing Server at 3250ms
0s 13ms DEBUG ECN probing: sent 7 probes
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = WaitInitial
Processing Client at 3300ms
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = Handshaking
Processing Server at 3350ms
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = WaitInitial
Processing Client at 3400ms
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = Handshaking
Processing Server at 3450ms
0s 14ms DEBUG ECN probing: sent 8 probes
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = WaitInitial
Processing Client at 3500ms
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = Handshaking
Processing Server at 3550ms
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = WaitInitial
Processing Client at 3600ms
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = Handshaking
Processing Server at 3650ms
0s 15ms DEBUG ECN probing: sent 9 probes
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = WaitInitial
Processing Client at 3700ms
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = Handshaking
Processing Server at 3750ms
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = WaitInitial
Processing Client at 3800ms
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = Handshaking
Processing Server at 3850ms
0s 17ms DEBUG ECN probing: sent 10 probes
0s 17ms DEBUG ECN probing concluded with 10 probes sent
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = WaitInitial
Processing Client at 3900ms
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = Handshaking
Processing Server at 3950ms
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = WaitInitial
Processing Client at 4000ms
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = Handshaking
Processing Server at 4050ms
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = WaitInitial
Processing Client at 4100ms
0s 18ms TRACE RTT latest=100ms -> estimate=100ms~50ms
0s 18ms WARN ECN validation failed, no ECN counts in ACK frame
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = Handshaking
Processing Server at 4150ms
0s 19ms TRACE RTT latest=500ms -> estimate=500ms~250ms
0s 19ms TRACE RTT latest=100ms -> estimate=450ms~287.5ms
0s 20ms WARN ECN validation failed, no ECN counts in ACK frame
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = Handshaking
Processing Client at 4200ms
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = Handshaking
Processing Server at 4250ms
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = Connected
Processing Client at 4300ms
0s 21ms TRACE RTT latest=100ms -> estimate=100ms~37.5ms
0s 21ms TRACE RTT latest=100ms -> estimate=100ms~28.125ms
[neqo-transport/src/connection/tests/mod.rs:190:13] c.state() = Confirmed
0s 22ms TRACE RTT latest=100ms -> estimate=406.25ms~303.125ms
test connection::tests::ecn::handshake_delay_with_ecn_blackhole ... ok

This commit adds a test where a client connects to a server over a connection dropping all ECN marked datagrams (ECN blackhole) in both directions, asserting 43 RTT to detect ECN blackhole, disable ECN and eventually establish connection.

github-actions · 2024-07-06T13:05:03Z

Failed Interop Tests

QUIC Interop Runner, client vs. server

neqo-latest as client

neqo-latest vs. aioquic: Z C1 V2
neqo-latest vs. kwik: Z C2
neqo-latest vs. lsquic: Z E
neqo-latest vs. msquic: Z A C1
neqo-latest vs. mvfst: H DC B U A L1 L2 C1 C2
neqo-latest vs. neqo: Z A
neqo-latest vs. neqo-latest: A
neqo-latest vs. nginx: C1
neqo-latest vs. ngtcp2: Z
neqo-latest vs. picoquic: L1 C1
neqo-latest vs. quic-go: Z
neqo-latest vs. quiche: C1
neqo-latest vs. quinn: H Z
neqo-latest vs. s2n-quic: R
neqo-latest vs. xquic: Z A L1 C1

neqo-latest as server

aioquic vs. neqo-latest: run cancelled after 20 min
chrome vs. neqo-latest: 3
go-x-net vs. neqo-latest: A
kwik vs. neqo-latest: A
lsquic vs. neqo-latest: A
msquic vs. neqo-latest: A
mvfst vs. neqo-latest: Z 3 A L1 C1
neqo vs. neqo-latest: A
ngtcp2 vs. neqo-latest: A
picoquic vs. neqo-latest: A
quic-go vs. neqo-latest: run cancelled after 20 min
quiche vs. neqo-latest: DC 3 A
quinn vs. neqo-latest: A V2
s2n-quic vs. neqo-latest: A
xquic vs. neqo-latest: M A

All results

Succeeded Interop Tests

QUIC Interop Runner, client vs. server

neqo-latest as client

neqo-latest vs. aioquic: H DC LR C20 M S R 3 B U A L1 L2 C2 6
neqo-latest vs. go-x-net: H DC LR M B U A L2 C2 6
neqo-latest vs. haproxy: H DC LR C20 M S R Z 3 B U A L1 L2 C1 C2 6 V2
neqo-latest vs. kwik: H DC LR C20 M S R 3 B U A L1 L2 C1 6 V2
neqo-latest vs. lsquic: H DC LR C20 M S R 3 B U A L1 L2 C1 C2 6 V2
neqo-latest vs. msquic: H DC LR C20 M S R B U L1 L2 C2 6 V2
neqo-latest vs. mvfst: LR M R Z 3 6
neqo-latest vs. neqo: H DC LR C20 M S R 3 B U E L1 L2 C1 C2 6 V2
neqo-latest vs. neqo-latest: H DC LR C20 M S R Z 3 B U E L1 L2 C1 C2 6 V2
neqo-latest vs. nginx: H DC LR C20 M S R Z 3 B U A L1 L2 C2 6
neqo-latest vs. ngtcp2: H DC LR C20 M S R 3 B U E A L1 L2 C1 C2 6 V2
neqo-latest vs. picoquic: H DC LR C20 M S R Z 3 B U E A L2 C2 6 V2
neqo-latest vs. quic-go: H DC LR C20 M S R 3 B U A L1 L2 C1 C2 6
neqo-latest vs. quiche: H DC LR C20 M S R Z 3 B U A L1 L2 C2 6
neqo-latest vs. quinn: DC LR C20 M S R 3 B U E A L1 L2 C1 C2 6
neqo-latest vs. s2n-quic: H DC LR C20 M S 3 B U E A L1 L2 C1 C2 6
neqo-latest vs. xquic: H DC LR C20 M R 3 B U L2 C2 6

neqo-latest as server

go-x-net vs. neqo-latest: H DC LR M B U L2 C2 6
kwik vs. neqo-latest: H DC LR C20 M S R Z 3 B U L1 L2 C1 C2 6 V2
lsquic vs. neqo-latest: H DC LR M S R 3 B E L1 L2 C1 C2 6 V2
msquic vs. neqo-latest: H DC LR C20 M S R Z B U L1 L2 C1 C2 6 V2
mvfst vs. neqo-latest: H DC LR M B L2 C2 6
neqo vs. neqo-latest: H DC LR C20 M S R Z 3 B U E L1 L2 C1 C2 6 V2
ngtcp2 vs. neqo-latest: H DC LR C20 M S R Z 3 B U E L1 L2 C1 C2 6 V2
picoquic vs. neqo-latest: H DC LR C20 M S R Z 3 B U E L1 L2 C1 C2 6 V2
quiche vs. neqo-latest: H LR M S R Z B L1 L2 C1 C2 6
quinn vs. neqo-latest: H DC LR C20 M S R Z 3 B U E L1 L2 C1 C2 6
s2n-quic vs. neqo-latest: H DC LR M S R 3 B E L1 L2 C1 C2 6
xquic vs. neqo-latest: H DC LR C20 S R Z 3 B U L1 L2 C1 C2 6

Unsupported Interop Tests

QUIC Interop Runner, client vs. server

neqo-latest as client

neqo-latest vs. aioquic: E
neqo-latest vs. go-x-net: C20 S R Z 3 E L1 C1 V2
neqo-latest vs. haproxy: E
neqo-latest vs. kwik: E
neqo-latest vs. msquic: 3 E
neqo-latest vs. mvfst: C20 S E V2
neqo-latest vs. nginx: E V2
neqo-latest vs. quic-go: E V2
neqo-latest vs. quiche: E V2
neqo-latest vs. quinn: V2
neqo-latest vs. s2n-quic: Z V2
neqo-latest vs. xquic: S E V2

neqo-latest as server

chrome vs. neqo-latest: H DC LR C20 M S R Z B U E A L1 L2 C1 C2 6 V2
go-x-net vs. neqo-latest: C20 S R Z 3 E L1 C1 V2
kwik vs. neqo-latest: E
lsquic vs. neqo-latest: C20 Z U
msquic vs. neqo-latest: 3 E
mvfst vs. neqo-latest: C20 S R U E V2
quiche vs. neqo-latest: C20 U E V2
s2n-quic vs. neqo-latest: C20 Z U V2
xquic vs. neqo-latest: E V2

github-actions · 2024-07-06T13:50:27Z

Firefox builds for this PR

The following builds are available for testing. Crossed-out builds did not succeed.

Linux: Debug Release
macOS: Debug Release
Windows: Debug Release

codecov · 2024-07-08T06:27:36Z

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 94.97%. Comparing base (e05cc70) to head (0242b31).
Report is 4 commits behind head on main.

Additional details and impacted files

@@           Coverage Diff           @@
##             main    #1964   +/-   ##
=======================================
  Coverage   94.96%   94.97%           
=======================================
  Files         112      112           
  Lines       36504    36525   +21     
=======================================
+ Hits        34667    34689   +22     
+ Misses       1837     1836    -1

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

github-actions · 2024-07-08T06:48:16Z

Benchmark results

Performance differences relative to b22512c.

coalesce_acked_from_zero 1+1 entries: Change within noise threshold.

       time:   [192.25 ns 192.69 ns 193.17 ns]
       change: [+0.1683% +0.4838% +0.8057%] (p = 0.00 < 0.05)
Found 10 outliers among 100 measurements (10.00%)

7 (7.00%) high mild

3 (3.00%) high severe

coalesce_acked_from_zero 3+1 entries: No change in performance detected.

       time:   [235.83 ns 236.39 ns 236.98 ns]
       change: [-0.6289% -0.1046% +0.3952%] (p = 0.70 > 0.05)
Found 13 outliers among 100 measurements (13.00%)

10 (10.00%) high mild

3 (3.00%) high severe

coalesce_acked_from_zero 10+1 entries: No change in performance detected.

       time:   [236.56 ns 237.15 ns 237.88 ns]
       change: [-0.9678% -0.3987% +0.1516%] (p = 0.17 > 0.05)
Found 5 outliers among 100 measurements (5.00%)

5 (5.00%) high severe

coalesce_acked_from_zero 1000+1 entries: No change in performance detected.

       time:   [213.75 ns 213.96 ns 214.18 ns]
       change: [-1.1868% -0.5490% +0.0930%] (p = 0.10 > 0.05)
Found 12 outliers among 100 measurements (12.00%)

5 (5.00%) high mild

7 (7.00%) high severe

RxStreamOrderer::inbound_frame(): No change in performance detected.

       time:   [118.61 ms 118.72 ms 118.84 ms]
       change: [-0.3036% -0.0863% +0.0809%] (p = 0.43 > 0.05)

transfer/pacing-false/varying-seeds: No change in performance detected.

       time:   [40.458 ms 42.593 ms 44.736 ms]
       change: [-6.8707% +0.0713% +7.2035%] (p = 0.99 > 0.05)
Found 1 outliers among 100 measurements (1.00%)

1 (1.00%) high mild

transfer/pacing-true/varying-seeds: No change in performance detected.

       time:   [52.546 ms 55.536 ms 58.573 ms]
       change: [-8.1822% -0.8443% +6.8292%] (p = 0.84 > 0.05)

transfer/pacing-false/same-seed: No change in performance detected.

       time:   [47.073 ms 48.737 ms 50.340 ms]
       change: [-3.5406% +1.2385% +6.2402%] (p = 0.61 > 0.05)

transfer/pacing-true/same-seed: No change in performance detected.

       time:   [72.021 ms 78.496 ms 84.917 ms]
       change: [-3.6631% +8.5992% +22.400%] (p = 0.18 > 0.05)

1-conn/1-100mb-resp (aka. Download)/client: No change in performance detected.

       time:   [252.28 ms 262.67 ms 272.67 ms]
       thrpt:  [366.74 MiB/s 380.71 MiB/s 396.39 MiB/s]
change:
       time:   [-11.590% -4.0943% +2.7527%] (p = 0.28 > 0.05)
       thrpt:  [-2.6790% +4.2691% +13.109%]
Found 22 outliers among 100 measurements (22.00%)

22 (22.00%) low mild

1-conn/10_000-parallel-1b-resp (aka. RPS)/client: No change in performance detected.

       time:   [417.52 ms 420.98 ms 424.42 ms]
       thrpt:  [23.562 Kelem/s 23.754 Kelem/s 23.951 Kelem/s]
change:
       time:   [-0.4052% +0.7829% +1.9536%] (p = 0.20 > 0.05)
       thrpt:  [-1.9162% -0.7769% +0.4069%]
Found 2 outliers among 100 measurements (2.00%)

1 (1.00%) low mild

1 (1.00%) high mild

1-conn/1-1b-resp (aka. HPS)/client: No change in performance detected.

       time:   [66.929 ms 67.265 ms 67.642 ms]
       thrpt:  [14.784  elem/s 14.867  elem/s 14.941  elem/s]
change:
       time:   [-0.5603% +0.1853% +0.9915%] (p = 0.64 > 0.05)
       thrpt:  [-0.9818% -0.1850% +0.5635%]
Found 6 outliers among 100 measurements (6.00%)

1 (1.00%) low mild

5 (5.00%) high severe

Client/server transfer results

Transfer of 33554432 bytes over loopback.

Client	Server	CC	Pacing	Mean [ms]	Min [ms]	Max [ms]	Relative
msquic	msquic			194.0 ± 93.3	106.6	386.3	1.00
neqo	msquic	reno	on	264.5 ± 8.5	252.5	281.8	1.00
neqo	msquic	reno		323.9 ± 95.3	258.8	500.7	1.00
neqo	msquic	cubic	on	280.8 ± 39.8	260.0	391.3	1.00
neqo	msquic	cubic		360.3 ± 121.7	253.5	574.4	1.00
msquic	neqo	reno	on	213.9 ± 80.5	154.1	395.5	1.00
msquic	neqo	reno		209.0 ± 88.8	119.1	397.7	1.00
msquic	neqo	cubic	on	212.7 ± 87.1	148.4	364.7	1.00
msquic	neqo	cubic		220.8 ± 81.5	120.6	427.2	1.00
neqo	neqo	reno	on	254.2 ± 78.5	179.1	402.4	1.00
neqo	neqo	reno		166.4 ± 14.6	150.4	203.3	1.00
neqo	neqo	cubic	on	207.8 ± 86.8	161.1	463.3	1.00
neqo	neqo	cubic		178.5 ± 10.6	163.3	207.1	1.00

⬇️ Download logs

mxinden · 2024-07-15T06:59:32Z

Friendly ping @larseggert.

larseggert · 2024-07-15T07:14:37Z

Thanks. I'll add a fix so that we stop trying ECN earlier in this case.

neqo-transport/src/connection/tests/mod.rs

larseggert · 2024-07-15T11:17:51Z

@mxinden WDYT?

mxinden

Implementation looks good to me. Thank you!

Intuitively 6 RTT to detect an ECN black-hole on the client seems fine under the assumption that ECN black-holes are very rare.

I can clean-up the tests later today or tomorrow unless you want to.

neqo-transport/src/ecn.rs

Co-authored-by: Max Inden <[email protected]> Signed-off-by: Lars Eggert <[email protected]>

mxinden

@larseggert I cleaned-up the tests. Mind taking another look?

neqo-transport/src/connection/tests/mod.rs

larseggert · 2024-07-17T09:26:10Z

@KershawChang or @martinthomson, could you take a look? This would let us enable ECN in Gecko w/@mxinden's patch.

larseggert · 2024-07-25T15:11:38Z

Would be nice to get this reviewed and merged.

KershawChang

Looks good. Thanks!

larseggert reviewed Jul 15, 2024

View reviewed changes

neqo-transport/src/connection/tests/mod.rs Outdated Show resolved Hide resolved

larseggert added 2 commits July 15, 2024 10:34

Merge branch 'main' into ecn-blackhole

6d98899

Bail out of ECN validation after three failed Initials

b42ee42

larseggert marked this pull request as ready for review July 15, 2024 11:16

larseggert requested review from KershawChang and martinthomson as code owners July 15, 2024 11:16

larseggert changed the title ~~test(transport): handshake delay with ecn blackhole~~ feat(transport): Use a shorter ECN probe threshold initially Jul 15, 2024

mxinden commented Jul 15, 2024

View reviewed changes

larseggert and others added 7 commits July 15, 2024 15:02

Update neqo-transport/src/ecn.rs

69a6fe7

Co-authored-by: Max Inden <[email protected]> Signed-off-by: Lars Eggert <[email protected]>

Update neqo-transport/src/ecn.rs

96d243b

Co-authored-by: Max Inden <[email protected]> Signed-off-by: Lars Eggert <[email protected]>

Update neqo-transport/src/ecn.rs

b60fdec

Co-authored-by: Max Inden <[email protected]> Signed-off-by: Lars Eggert <[email protected]>

Update neqo-transport/src/ecn.rs

52c662f

Co-authored-by: Max Inden <[email protected]> Signed-off-by: Lars Eggert <[email protected]>

Update neqo-transport/src/ecn.rs

1572c12

Co-authored-by: Max Inden <[email protected]> Signed-off-by: Lars Eggert <[email protected]>

Fixes

0710e27

clean-up tests

75e1668

mxinden commented Jul 15, 2024

View reviewed changes

neqo-transport/src/connection/tests/mod.rs Show resolved Hide resolved

neqo-transport/src/connection/tests/mod.rs Show resolved Hide resolved

larseggert enabled auto-merge July 16, 2024 05:55

larseggert added 2 commits July 16, 2024 11:54

Merge branch 'main' into ecn-blackhole

7d287c1

Merge branch 'main' into ecn-blackhole

0242b31

mxinden mentioned this pull request Jul 17, 2024

Release neqo v0.8.1 #1989

Closed

larseggert added the needs-review Needs a review by a CODEOWNER. label Jul 17, 2024

larseggert linked an issue Jul 17, 2024 that may be closed by this pull request

Test ECN on a path dropping all marked packets #1925

Closed

Merge branch 'main' into ecn-blackhole

044c11f

KershawChang approved these changes Jul 31, 2024

View reviewed changes

larseggert added this pull request to the merge queue Jul 31, 2024

Merged via the queue into mozilla:main with commit b033d95 Jul 31, 2024
55 of 57 checks passed

larseggert removed the needs-review Needs a review by a CODEOWNER. label Jul 31, 2024

mxinden mentioned this pull request Aug 5, 2024

Release neqo v0.8.2 #2040

Closed

mxinden mentioned this pull request Sep 2, 2024

fix: Handle migrating to a path that is an ECN blackhole #2081

Merged

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

feat(transport): Use a shorter ECN probe threshold initially #1964

feat(transport): Use a shorter ECN probe threshold initially #1964

mxinden commented Jul 6, 2024 •

edited

Loading

github-actions bot commented Jul 6, 2024 •

edited

Loading

Succeeded Interop Tests

neqo-latest as client

neqo-latest as server

Unsupported Interop Tests

neqo-latest as client

neqo-latest as server

github-actions bot commented Jul 6, 2024 •

edited

Loading

codecov bot commented Jul 8, 2024 •

edited

Loading

github-actions bot commented Jul 8, 2024 •

edited

Loading

mxinden commented Jul 15, 2024

larseggert commented Jul 15, 2024

larseggert commented Jul 15, 2024

mxinden left a comment

mxinden left a comment

larseggert commented Jul 17, 2024

larseggert commented Jul 25, 2024

KershawChang left a comment

feat(transport): Use a shorter ECN probe threshold initially #1964

feat(transport): Use a shorter ECN probe threshold initially #1964

Conversation

mxinden commented Jul 6, 2024 • edited Loading

github-actions bot commented Jul 6, 2024 • edited Loading

Failed Interop Tests

neqo-latest as client

neqo-latest as server

Succeeded Interop Tests

neqo-latest as client

neqo-latest as server

Unsupported Interop Tests

neqo-latest as client

neqo-latest as server

github-actions bot commented Jul 6, 2024 • edited Loading

Firefox builds for this PR

codecov bot commented Jul 8, 2024 • edited Loading

Codecov Report

github-actions bot commented Jul 8, 2024 • edited Loading

Benchmark results

Client/server transfer results

mxinden commented Jul 15, 2024

larseggert commented Jul 15, 2024

larseggert commented Jul 15, 2024

mxinden left a comment

Choose a reason for hiding this comment

mxinden left a comment

Choose a reason for hiding this comment

larseggert commented Jul 17, 2024

larseggert commented Jul 25, 2024

KershawChang left a comment

Choose a reason for hiding this comment

mxinden commented Jul 6, 2024 •

edited

Loading

github-actions bot commented Jul 6, 2024 •

edited

Loading

github-actions bot commented Jul 6, 2024 •

edited

Loading

codecov bot commented Jul 8, 2024 •

edited

Loading

github-actions bot commented Jul 8, 2024 •

edited

Loading