asmhatre/spring-async-demo
1
0
Fork 0
Code Activity

Add virtual-threads-benchmark-webflux: the WebFlux leg of the three-way benchmark

Browse Source 
Fixes two bugs found during self-correction before publishing:
- /stream used Flux.interval(), which ticks on its own wall-clock schedule
  independent of downstream demand and threw OverflowException under a slow
  subscriber; switched to Flux.range(), which has no independent production
  schedule and can never outrun demand.
- The event-loop-starvation test's first cut used only 8 concurrent /cpu
  requests as background load, which drained through the 4 event-loop
  threads well inside the /io measurement window and produced an
  inconsistent, sometimes-inverted result across runs; raised to 60
  concurrent requests (matching the CPU-bound benchmark's own concurrency)
  so the load actually occupies the event loop for the full window.

Also adds StreamBackpressureTest, a StepVerifier proof that the /stream
endpoint never emits ahead of its subscriber's outstanding requests.
This commit is contained in:
Claude
2026-09-19 08:48:58 +00:00
parent f506b01389
commit b331db6638
19 changed files with 863 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
virtual-threads-benchmark-webflux/docs/output/01-io-bound-webflux.txt
+8
View File
@@ -0,0 +1,8 @@
I/O-bound endpoint (/io, Mono.delay(300ms)), concurrency=600, 2 vCPU sandbox, Spring Boot 4.1.1 / JDK 25.0.4.1
==============================================================================================================
webflux (netty) : total=600 success=600 wall=852ms p50=591ms p99=738ms
Mono.delay() never parks a thread -- the event loop schedules a timer callback and
goes back to the selector loop immediately. Wall time for 600 concurrent requests
stays close to a single 300ms round, same shape as virtual threads' /io result in
../virtual-threads-benchmark/docs/output/01-io-bound-benchmark.txt.