perf: apply masking key 8 bytes at a time

[mccutchen]

Basically what it says on the tin. Key results from the benchmarks below, indicating ~35% faster read/write frame and and ~55% higher throughput:

                  │ ./baseline/bench-results.txt │       ./head/bench-results.txt       │
                  │            sec/op            │    sec/op     vs base                │
ReadFrame/1KiB-4                     867.5n ± 3%   575.8n ±  4%  -33.63% (p=0.000 n=10)
ReadFrame/1MiB-4                     550.2µ ± 1%   331.0µ ± 18%  -39.84% (p=0.000 n=10)
WriteFrame/1KiB-4                    932.5n ± 0%   675.9n ±  0%  -27.51% (p=0.000 n=10)
WriteFrame/1MiB-4                    588.4µ ± 4%   336.3µ ±  4%  -42.84% (p=0.000 n=10)
geomean                              22.62µ        14.43µ        -36.22%

                  │ ./baseline/bench-results.txt │       ./head/bench-results.txt        │
                  │             B/s              │      B/s       vs base                │
ReadFrame/1KiB-4                    1.109Gi ± 3%   1.671Gi ±  4%  +50.67% (p=0.000 n=10)
ReadFrame/1MiB-4                    1.775Gi ± 1%   2.950Gi ± 15%  +66.22% (p=0.000 n=10)
WriteFrame/1KiB-4                   1.032Gi ± 0%   1.423Gi ±  0%  +37.95% (p=0.000 n=10)
WriteFrame/1MiB-4                   1.660Gi ± 3%   2.904Gi ±  3%  +74.97% (p=0.000 n=10)
geomean                             1.355Gi        2.125Gi        +56.80%

[github-actions]

🔥 Run benchmarks comparing 547619b against main:

gh workflow run bench.yaml -f pr_number=58

Note: this comment will update with each new commit.

[github-actions]

benchstats: d74cdf7...547619b

View full benchmark output on the workflow summary.

goos: linux
goarch: amd64
pkg: github.com/mccutchen/websocket
cpu: AMD EPYC 7763 64-Core Processor                
                  │ ./baseline/bench-results.txt │       ./head/bench-results.txt       │
                  │            sec/op            │    sec/op     vs base                │
ReadFrame/1KiB-4                     867.5n ± 3%   575.8n ±  4%  -33.63% (p=0.000 n=10)
ReadFrame/1MiB-4                     550.2µ ± 1%   331.0µ ± 18%  -39.84% (p=0.000 n=10)
WriteFrame/1KiB-4                    932.5n ± 0%   675.9n ±  0%  -27.51% (p=0.000 n=10)
WriteFrame/1MiB-4                    588.4µ ± 4%   336.3µ ±  4%  -42.84% (p=0.000 n=10)
geomean                              22.62µ        14.43µ        -36.22%

                  │ ./baseline/bench-results.txt │       ./head/bench-results.txt        │
                  │             B/s              │      B/s       vs base                │
ReadFrame/1KiB-4                    1.109Gi ± 3%   1.671Gi ±  4%  +50.67% (p=0.000 n=10)
ReadFrame/1MiB-4                    1.775Gi ± 1%   2.950Gi ± 15%  +66.22% (p=0.000 n=10)
WriteFrame/1KiB-4                   1.032Gi ± 0%   1.423Gi ±  0%  +37.95% (p=0.000 n=10)
WriteFrame/1MiB-4                   1.660Gi ± 3%   2.904Gi ±  3%  +74.97% (p=0.000 n=10)
geomean                             1.355Gi        2.125Gi        +56.80%

                  │ ./baseline/bench-results.txt │       ./head/bench-results.txt        │
                  │             B/op             │     B/op      vs base                 │
ReadFrame/1KiB-4                    1.164Ki ± 0%   1.164Ki ± 0%       ~ (p=1.000 n=10) ¹
ReadFrame/1MiB-4                    1.008Mi ± 0%   1.008Mi ± 0%       ~ (p=0.056 n=10)
WriteFrame/1KiB-4                   1.125Ki ± 0%   1.125Ki ± 0%       ~ (p=1.000 n=10) ¹
WriteFrame/1MiB-4                   1.008Mi ± 0%   1.008Mi ± 0%       ~ (p=0.057 n=10)
geomean                             34.37Ki        34.37Ki       -0.00%
¹ all samples are equal

                  │ ./baseline/bench-results.txt │      ./head/bench-results.txt       │
                  │          allocs/op           │ allocs/op   vs base                 │
ReadFrame/1KiB-4                      5.000 ± 0%   5.000 ± 0%       ~ (p=1.000 n=10) ¹
ReadFrame/1MiB-4                      5.000 ± 0%   5.000 ± 0%       ~ (p=1.000 n=10) ¹
WriteFrame/1KiB-4                     1.000 ± 0%   1.000 ± 0%       ~ (p=1.000 n=10) ¹
WriteFrame/1MiB-4                     1.000 ± 0%   1.000 ± 0%       ~ (p=1.000 n=10) ¹
geomean                               2.236        2.236       +0.00%
¹ all samples are equal

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 92.94%. Comparing base (d74cdf7) to head (547619b).
⚠️ Report is 1 commits behind head on main.

Additional details and impacted files

@@           Coverage Diff           @@
##             main      #58   +/-   ##
=======================================
  Coverage   92.94%   92.94%           
=======================================
  Files           2        2           
  Lines         496      496           
=======================================
  Hits          461      461           
  Misses         28       28           
  Partials        7        7           

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

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.