jan/rrt
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Record save-invariant peer-site payload stride

Browse source
This commit is contained in:
Jan Petykiewicz 2026-04-18 20:12:01 -07:00
commit c843b55d10
1 changed files with 6 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

11
docs/rehost-queue.md
View file

@ -91,7 +91,8 @@ Working rule:
- the periodic-company trace now also surfaces the save-side `0x5dc1` payload/status summaries - the periodic-company trace now also surfaces the save-side `0x5dc1` payload/status summaries
already parsed from the `0x36b1` triplet seam; on grounded `p.gms` the payload dword lane is already parsed from the `0x36b1` triplet seam; on grounded `p.gms` the payload dword lane is
almost entirely unique while the status kind stays `unset`, and the dominant adjacent payload almost entirely unique while the status kind stays `unset`, and the dominant adjacent payload
delta is `0x00000780` across `1908` steps delta is `0x00000780` across `1908` steps; grounded `q.gms` shows the same dominant adjacent
delta `0x00000780` across `1868` steps
So the next owner question is no longer “what does the acquisition branch do?” or “which post- So the next owner question is no longer “what does the acquisition branch do?” or “which post-
load owner replays linked-site refresh?” but “which concrete `0x00455b70` caller family applies load owner replays linked-site refresh?” but “which concrete `0x00455b70` caller family applies
to the live site rows, and which persisted lane becomes the selector bundle that ultimately to the live site rows, and which persisted lane becomes the selector bundle that ultimately
@ -118,10 +119,10 @@ Working rule:
`0x0040ceab -> 0x0045c150` / `0x0040d1a1 -> 0x0045c310` / `0x0040ceab -> 0x0045c150` / `0x0040d1a1 -> 0x0045c310` /
`0x0040cd70 seeds [site+0x3cc/+0x3d0] from 0x62b2fc / 0x62b268` `0x0040cd70 seeds [site+0x3cc/+0x3d0] from 0x62b2fc / 0x62b268`
- use the new `0x5dc1` payload/status summary in the same trace as negative evidence too: - use the new `0x5dc1` payload/status summary in the same trace as negative evidence too:
the current `profile_payload_dword` lane behaves like a monotone ladder (`dominant adjacent the current `profile_payload_dword` lane behaves like a save-invariant monotone ladder
delta 0x780`) rather than a compact selector family, so the next peer-site slice should treat (`dominant adjacent delta 0x780` on both `p.gms` and `q.gms`) rather than a compact selector
that raw dword as a likely allocator/offset lane until a stronger selector interpretation family, so the next peer-site slice should treat that raw dword as a likely allocator/offset
appears lane until a stronger selector interpretation appears
- treat the peer-site selector seam itself as grounded enough for planning purposes - treat the peer-site selector seam itself as grounded enough for planning purposes
- use the new structured restore/runtime field split in the same trace: - use the new structured restore/runtime field split in the same trace:
restore subset restore subset