v2: linear (default cache-aware) baseline + 2x wall-cap on first600s

Browse Source

Follow-up to the LMetric sweep: rerun with --policy linear (cache-aware
load + sticky session affinity, the cache_aware_proxy default) and cap
each PD-disagg arm at 2x the colo bench wall (SIGTERM bench.sh once cap
is exceeded; the cleanup trap clears vLLM and proxy; capped runs lack
metrics.summary.json so the analysis script computes from raw
metrics.jsonl).

Headline: the success-rate ceiling is policy-invariant.

  arm        linear (capped at 2x)    lmetric (uncapped)
  colo       807/807 = 100%, 964s     807/807 = 100%, 1021s
  pd6 (6:2)  472/807 =  58%, 2280s ⊗  474/807 =  59%, 3325s
  pd4 (4:4)  349/807 =  43%, 2281s ⊗  348/807 =  43%, 6850s
  pd2 (2:6)  176/807 =  22%, 2280s ⊗  180/807 =  22%, 19275s

Routing affects only how much wall is wasted timing out unreachable
requests at 600s each. Linear hits the same ceiling in 2280s as
LMetric does in 3300-19000s. This *strengthens* the §5 D-pool
capacity-ceiling thesis -- the cap is structural, not a routing
artifact.

Artifacts:
  analysis/v2/fig4r_linear.json          -- 4-arm linear summary
  analysis/v2/PD_DISAGG_LMETRIC.md       -- extended with wall-cap section
  figs/v2/fig4_linear_vs_lmetric.png     -- 3-panel side-by-side comparison
  microbench/fresh_setup/plot_fig4_linear_vs_lmetric.py

...

This commit is contained in:

Gahow Wang

2026-06-01 00:55:40 +08:00

parent 7529284cee

commit 32f7f55990

4 changed files with 163 additions and 1 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

BIN

figs/v2/fig4_linear_vs_lmetric.png Normal file

Binary file not shown.

Side by Side After Width:  |  Height:  |  Size: 109 KiB