feat: Shuffle the client Initial crypto data #2228
Open
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Look for ranges of `N` or more bytes of graphical ASCII data in `data`. Create at least one split point for each range, multiple ones each `N` bytes if the range is long enough. Create data chunks based on those split points. Shuffle the chunks and return them. CC @martinthomson @dennisjackson
Failed Interop TestsQUIC Interop Runner, client vs. server neqo-latest as client
neqo-latest as server
All resultsSucceeded Interop TestsQUIC Interop Runner, client vs. server neqo-latest as client
neqo-latest as server
Unsupported Interop TestsQUIC Interop Runner, client vs. server neqo-latest as client
neqo-latest as server
|
larseggert
requested review from
KershawChang,
martinthomson and
mxinden
as code owners
Codecov ReportAll modified and coverable lines are covered by tests ✅
Additional details and impacted files@@ Coverage Diff @@
## main #2228 +/- ##
==========================================
+ Coverage 95.37% 95.39% +0.02%
==========================================
Files 112 112
Lines 36563 36726 +163
==========================================
+ Hits 34872 35035 +163
Misses 1691 1691 ☔ View full report in Codecov by Sentry. |
Benchmark resultsPerformance differences relative to 68e19fc. coalesce_acked_from_zero 1+1 entries: 💔 Performance has regressed. time: [105.06 ns 105.39 ns 105.72 ns]
change: [+15.668% +16.427% +17.107%] (p = 0.00 < 0.05)
coalesce_acked_from_zero 3+1 entries: 💔 Performance has regressed. time: [120.90 ns 121.31 ns 121.74 ns]
change: [+17.463% +18.175% +18.907%] (p = 0.00 < 0.05)
coalesce_acked_from_zero 10+1 entries: 💔 Performance has regressed. time: [120.44 ns 120.97 ns 121.69 ns]
change: [+17.793% +18.396% +19.104%] (p = 0.00 < 0.05)
coalesce_acked_from_zero 1000+1 entries: 💔 Performance has regressed. time: [100.77 ns 100.92 ns 101.09 ns]
change: [+24.584% +26.175% +27.680%] (p = 0.00 < 0.05)
RxStreamOrderer::inbound_frame(): Change within noise threshold. time: [111.34 ms 111.47 ms 111.68 ms]
change: [-0.3123% -0.1806% +0.0512%] (p = 0.02 < 0.05)
transfer/pacing-false/varying-seeds: Change within noise threshold. time: [25.878 ms 26.930 ms 27.976 ms]
change: [-10.961% -5.7746% -0.4791%] (p = 0.03 < 0.05)
transfer/pacing-true/varying-seeds: No change in performance detected. time: [33.610 ms 35.178 ms 36.700 ms]
change: [-8.5493% -2.4048% +4.1986%] (p = 0.47 > 0.05)
transfer/pacing-false/same-seed: Change within noise threshold. time: [24.783 ms 25.650 ms 26.539 ms]
change: [-8.8786% -4.6845% -0.5154%] (p = 0.03 < 0.05)
transfer/pacing-true/same-seed: No change in performance detected. time: [40.200 ms 42.409 ms 44.648 ms]
change: [-8.7856% -1.9785% +5.2403%] (p = 0.58 > 0.05)
1-conn/1-100mb-resp/mtu-1504 (aka. Download)/client: No change in performance detected. time: [910.13 ms 918.60 ms 927.14 ms]
thrpt: [107.86 MiB/s 108.86 MiB/s 109.87 MiB/s]
change:
time: [-2.1263% -0.8129% +0.4358%] (p = 0.22 > 0.05)
thrpt: [-0.4339% +0.8195% +2.1725%]
1-conn/10_000-parallel-1b-resp/mtu-1504 (aka. RPS)/client: No change in performance detected. time: [319.90 ms 323.29 ms 326.78 ms]
thrpt: [30.601 Kelem/s 30.932 Kelem/s 31.260 Kelem/s]
change:
time: [-1.8396% -0.3597% +1.0478%] (p = 0.63 > 0.05)
thrpt: [-1.0370% +0.3610% +1.8741%]
1-conn/1-1b-resp/mtu-1504 (aka. HPS)/client: No change in performance detected. time: [34.298 ms 34.456 ms 34.633 ms]
thrpt: [28.874 elem/s 29.022 elem/s 29.156 elem/s]
change:
time: [-0.3577% +0.3962% +1.1376%] (p = 0.30 > 0.05)
thrpt: [-1.1248% -0.3947% +0.3590%]
1-conn/1-100mb-resp/mtu-1504 (aka. Upload)/client: No change in performance detected. time: [1.6906 s 1.7062 s 1.7232 s]
thrpt: [58.033 MiB/s 58.609 MiB/s 59.151 MiB/s]
change:
time: [-0.5759% +0.9413% +2.4603%] (p = 0.22 > 0.05)
thrpt: [-2.4012% -0.9326% +0.5792%]
Client/server transfer resultsTransfer of 33554432 bytes over loopback.
|
larseggert
changed the title
mxinden
reviewed
Nov 16, 2024
| for i in 0..(n - 1) { | ||
| // j ← random integer such that i ≤ j < n | ||
| let j = loop { | ||
| let j = (random::<8>()[0] as usize) % (n - i) + i; |
There was a problem hiding this comment.
Is there a modulo bias here when n - i does not evenly divide 256?
There was a problem hiding this comment.
Maybe? Not sure if it matters in practice, since we just try to get some order out that isn't sequential.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Look for ranges of
Nor more bytes of graphical ASCII data indata. Create at least one split point atN/2into the range for each range, multiple ones eachNbytes afterwards if the range is long enough. Create data chunks based on those split points. Shuffle the chunks and return them. (Nis currently3.)CC @martinthomson @dennisjackson