udpscope

0 Fork 0

Files

T

Martino FerrariandClaude Opus 4.6 210d124814 docs: the five reseq probe cases as this build measures them, plus the overflow counter's reading

Re-measured all four recorded cases and added a fifth for the re-plan path,
which needs 100 kS/s: at 10 kS/s the ring already covers 838 s, so no window
the control can reach moves time_stride and the window probe re-plans nothing.
Also notes that `stale` is 0 by construction while resequencing is on, and that
the reservation cap is counted in packets, so its sample cost scales with the
batch.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

2026-10-09 06:52:31 +02:00

architecture.md

docs: CLAUDE.md is a goal and a table of contents, so a context pays for what it reads

2026-10-07 01:49:28 +02:00

build-and-run.md

fix: a full reorder ring keeps the arriving packet and counts the overflow, instead of dropping it silently

2026-10-09 06:50:43 +02:00

invariants-data-path.md

docs: the five reseq probe cases as this build measures them, plus the overflow counter's reading

2026-10-09 06:52:31 +02:00

invariants-gtk-and-chrome.md

docs: CLAUDE.md is a goal and a table of contents, so a context pays for what it reads