Generational ZGC vs G1 on JDK 25: benchmarks, internals and captured results

Complete companion suite for the ankurm.com guide. Everything was compiled and
executed on java 25.0.3+9-LTS-195 (AMD Ryzen 5 5600U, Windows 11); every file
under results/ is unedited program output.

Code
  latency/    open-loop latency harness that measures from intended arrival, so
              coordinated omission is accounted for rather than hidden. Reports
              response time and service time side by side; the gap reached 2910x
              on G1.
  jmh/        four microbenchmarks isolating one mechanism each: TLAB allocation,
              the ZGC load barrier (with a primitive-load control), the write
              barrier (with null / old-to-old / primitive controls), and promotion
              pressure.
  tuning/     provokes ZGC allocation stalls and reads its own JFR recording back,
              grouped by page class. jdk.ZAllocationStall is enabled without a
              threshold, because the 10 ms default hides most stalls.
  internals/  ZGC page classes vs G1 humongous, read from the live VM via
              HotSpotDiagnosticMXBean and jdk.ZPageAllocation events.
  analysis/   unified GC log parser that keeps stop-the-world pauses and
              concurrent phases in separate buckets.
  env/        environment capture; proves generational mode from JMX bean names.

Docs
  Eight chapters covering the JEP 439/474/490 timeline, colored pointers and both
  barriers, allocation stalls, a full flag reference, logging and JFR, benchmark
  methodology, corner cases, and a decision procedure.

Headline result (60 s, 20k req/s, 2 GB heap, ~585 MB live)
  p50               ZGC 0.006 ms   G1 0.005 ms
  p99.9             ZGC 1.437 ms   G1 95.169 ms
  total STW time    ZGC 1.503 ms   G1 1,139.624 ms

results/04-stalls-zgc-softmax.txt

@@ -0,0 +1,41 @@
+max heap        : 512 MB
+target live set : 281 MB (55% of heap)
+threads         : 12, duration: 20 s
+
+filling live set ...
+live set filled: 4,505 chunks x 64 KB
+now allocating hard for 20 s -- expect stalls
+
+allocation phase done
+
+========================================================================
+JFR summary  (C:\Users\Ankur\allocation-stalls.jfr)
+========================================================================
+young collections : 1,778
+old collections   : 217
+page allocations  : 39,685
+ALLOCATION STALLS : 31,967
+
+total time threads spent stalled : 138,521 ms
+mean stall                       : 4.33 ms
+longest stall                    : 51.41 ms
+
+stalls by ZGC page type
+  Small    count=31,967   total=138,521 ms   mean=4.33 ms
+
+ten longest stalls
+  duration    page     size       thread
+     51.41 ms Small    2097152    allocator-10
+     50.18 ms Small    2097152    allocator-0
+     48.12 ms Small    2097152    allocator-5
+     47.93 ms Small    2097152    allocator-1
+     46.90 ms Small    2097152    allocator-1
+     46.14 ms Small    2097152    allocator-11
+     46.14 ms Small    2097152    allocator-11
+     46.08 ms Small    2097152    allocator-6
+     46.02 ms Small    2097152    allocator-4
+     45.68 ms Small    2097152    allocator-9
+
+Compare against your pause-time chart: none of the above is a pause.
+Inspect the raw events, including the stack that was stalled, with:
+  jfr print --events ZAllocationStall allocation-stalls.jfr