Re:Web Framework Benchmarks Round 4
by diroussel on Friday May 03, 2013 @03:42AM
(#5649267)
Indeed. Often latency measurements are clumpy.
You might have one clump of fast responses when no GC occurs, another when some GC occurs, and a smaller clump where a stop-the-world full GC has occurred.
You might have one clump of fast responses when no GC occurs, another when some GC occurs, and a smaller clump where a stop-the-world full GC has occurred.
In such a case average is not meaningful.