Files
MobileGL/docs/Disaggregated/notes/p7/device-window-1/E1-lockstep/README.md
T
swung0x48 4f2d4c4e83 [MG_Remote, docs] (P7): CONTRACT-P7 carries wave 0's numbers, and device window #1a is on record
CONTRACT-P7: the lane counts (magma-split 73 / spawn 52 / tcp 54; full-suite 510 x 3
with one StreamLink x Magma red), the census baseline (79 abort sites over 20 files,
43 family words, 0 unmarked), the ratchet baseline (186 = p7-magma 101 / espryt 14 /
both 60 / core 11; espryt's clearable count is 9) and the @P7 count (15 sites / 4
files) replace the 待填 markers.

Device window #1a (Redmi 2f7cbe2e, APK p7w1-d260f110, reboot-clean): E0a monolith
39/39 deterministic, three below threshold on monolith itself (create-indirect,
1.21.11 main-menu, iris-photon - Adreno refuses its pipelines with VK_ERROR_UNKNOWN);
E0a inproc: OpenRA 0.976494 (run-ahead) / E1 lockstep 0.988998 - both historical
numbers were OpenRA, and its client log shows a TextureResources verb answered from
caps generation 0 (package F1); 26.3 / create-* SIGSEGV in the replayer's memcpy on
BOTH backends and with the persistent-map push off (package X1); iterationt x2 die
by name on Magma:mipmap-shader-format-or-shape (package B); bsl-esc-menu hits
scudo OOM under inproc. Gate 3's denominator is 36; run-ahead and present credit
are off the suspect list.
2026-09-22 14:49:42 -04:00

18 lines
1.5 KiB
Markdown
Executable File
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
# E1 · `MOBILEGL_IPC_RUN_AHEAD=0` 的 lockstep 对照
集合 = E0a 的分歧 / 死亡 case(OpenRA、26.3、create-instancing、bsl-esc-menu-854、iterationt)+ 两个对照(`minecraft-1.21.4-in-world`、`sodium-in-world`),DirectVulkan × inproc × pbuffer × 1 遍。
**臂证明**(`arm-proof.txt`,7/7):每例 `run-ahead ARMED` 计数 **0**,`Config: IPC` 行只有 `run-ahead=0`。这就是 runbook §5 说的「一条在 + 一条不在」;`running lockstep` 这句在 RUN_AHEAD=0 下本来就不打。每例退出码非零是 `--require-inproc` 门要求 `run-ahead=1` 的已知副作用,结果与归档照常可用(`E1.log`)。
| case | ARMED(E0a) | lockstep(E1) | 读法 |
|---|---|---|---|
| OpenRA | 0.976494 | **0.988998** | 仍分歧;幅度变小。= 历史第二个观测值。run-ahead **不是**原因,只影响首个 CapsSnapshot 前丢掉多少发射 |
| 26.3 | SIGSEGV | SIGSEGV | 与 run-ahead 无关 |
| create-instancing | SIGSEGV | SIGSEGV | 同上 |
| bsl-esc-menu-854 | SIGABRT(scudo OOM) | SIGSEGV | 内存上限附近的不同死法 |
| iterationt | `Fatal{UnmigratedVerb,"Magma:mipmap-shader-format-or-shape"}` | 同 | 确定性具名拒绝 |
| 1.21.4-in-world(对照) | 0.9999956 | 0.9999956 | 同 |
| sodium-in-world(对照) | 0.9999938 | 0.9999938 | 同 |
**判别(runbook §5 的那一行):不变 ⇒ run-ahead 整条线出局,原因在 server 的内容路径 / 能力协商。** E2(credit 扫描)据此不跑。