wang-jiahua commented on PR #10491:
URL: https://github.com/apache/rocketmq/pull/10491#issuecomment-4766858269

   ## Server Benchmark Results (2026-06-22)
   
   **Environment**: 8C30G broker, Dragonwell JDK 21, 1KB msg, 128 queues, sync 
mode, 256 threads, 20s warmup + 30s collect
   
   ### Producer-only (steady state, lines 3-5)
   
   | Test | TPS | Avg RT | GC | vs Baseline |
   |------|-----|--------|----|-------------|
   | Baseline | 217k | 1.18ms | 354 | — |
   | #10491 | 199k | 1.28ms | 212 | -8.3% TPS (within noise band), -40% GC ✅ |
   
   Minor optimizations (TopicMessageType cache, RemotingHelper get+null check, 
NopStatusListener, metricsValue cache). The -8.3% TPS is at the edge of the 
noise band (baseline variance is 5-10%). GC reduction (-40%) confirms reduced 
allocation. These micro-optimizations are not on the Send hot path, so TPS 
impact is expected to be minimal in production.


-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: [email protected]

For queries about this service, please contact Infrastructure at:
[email protected]

Reply via email to