PD_DISAGG_RESULTS §6.3: producer hot-pinning figure

Browse Source

Direct per-producer KV-pool evidence for the session-affinity backfire.
At the same 4P+4D ratio:
- round-robin: 4 producers within 1pp of each other (spread 0pp, CV 0.01)
- session-affinity: spread 49pp (one producer ~93%, another 45%; CV 0.25)

A 25x jump in producer load imbalance — heavy multi-turn sessions
concentrate onto single producers, the same hot-pinning pathology as
sticky routing in the colocated §3.3 study.

plot_producer_hotspot.py: reduce (numpy, per-producer KV timeline from
snapshots, runs on the serving host) + plot (matplotlib, 2-panel rr vs
session comparison) — same two-stage pattern as aggregate_mb5.py.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

...

This commit is contained in:

Gahow Wang

2026-05-29 00:38:20 +08:00

parent 6243b78bba

commit a2f2645fda

5 changed files with 149 additions and 0 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/mb5/mb5_producer_hotspot.png Normal file

Binary file not shown.

Side by Side After Width:  |  Height:  |  Size: 271 KiB