Keep a fault from releasing a lazily written range unseen while a part is handed over, merge what a part skipped and must write back after all, and leave the lazy write-back off on Linux unless set.

A review found a gap: a part checked what it had skipped at its end, and a fault between that check and the part's
hand-over to the queue fetched without the part's writes while nothing wrote them back afterwards. The replay now
opens a window from the check to the hand-over, per part, and a fault on an armed page waits for it to close (at most
20 ms; the replay thread's own faults and thaws do not wait and are counted). What a part skipped for a range that is
no longer armed goes back through the usual snapshot and merge, taken in that part's prologue, and not as a plain
copy, which would have put the mirror's words over what the CPU had just written there. A part split off earlier
makes the same check before its prologue. wb_lazy_touch is a test that reads armed ranges on purpose.

Dev build, Hyrule Field: 71.1 fps as before; standing, a fight, pause and unpause, and the touch test made 146 to 338
faults each, none inside a window, no fault of its own.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
This commit is contained in:
chrg6
2026-11-10 05:23:43 -05:00
parent 17c13e49ff
commit bd9b48ff04
6 changed files with 93 additions and 25 deletions

View File

@@ -642,7 +642,7 @@
# wb_split = 1
# 1: what the game's shaders write into its memory is copied back from the video card once, and after that only when
# the game's CPU code touches it (most of it never is: 66 MiB a frame in Hyrule Field). 0: copied back at the end of
# every GPU submission, as before.
# every GPU submission, as before. On Linux it is off unless set here.
# wb_lazy = 1
# 1: the game's flushes of mirrored memory are copied into the mirrors even where the write watch already sees every
# page the game wrote; 0 (default) copies only the written pages there, which saved 47-57 MiB of copies a frame in