re: confirmed — the probe was causing the guest stalls
The control needed no new decoding: hunting pilot, keep-out 1400, 300 s, and no memory probe at all, judged only from the pilot's own log. It ran healthy the whole way -- 211, 257, 250, 241 and 200 distinct speed values in successive 60 s windows, with no decline in the last one -- against probed runs that stalled at roughly 27, 83 and 255 s and ended with a single distinct speed across 400 lines. So the instrument was degrading the thing it measured. AGENT.md warned that a full scan competes with the emulator for every core under lavapipe, and the probes grew heavier each iteration until wave6 was reading the entire 32 MB entity heap plus about 300 extra preads every 12 seconds while the game rendered. The control is n=1. The contrast is stark and the mechanism was predicted in advance, so this is recorded as confirmed enough to act on rather than proven; a second clean control would settle it. What it costs is worth stating plainly. Every "no arrival" result so far was collected while the probe was running, under conditions the game was struggling with and in some runs after it had frozen. That does not make them wrong -- the elimination test at t=163 s sits in a window the witness later showed was live -- but none of them is as strong as written, and the arrival question deserves re-running with cheap sampling before silence is read as evidence. wave7_probe.py is the fix: one full enumeration, then polling only the hull word at each known craft base, about 1.2 KB per sample instead of 32 MB, with a full rescan every 90 s to catch anything genuinely new. Three or four heavy scans per run instead of twenty-five. Implemented but not yet run, so the claim that it stops the stalling is untested and the next run must report the witness first.
This commit is contained in:
Sylpheed RE agent
18
tools/re-capture/control_session.sh
Executable file
18
tools/re-capture/control_session.sh
Executable file
@@ -0,0 +1,18 @@
|
||||
#!/usr/bin/env bash
|
||||
# CONTROL: hunting pilot, NO memory probe at all. The only question is whether
|
||||
# the guest still stalls when nothing is scanning /dev/shm alongside it.
|
||||
set -u
|
||||
export HOME=/sylph-home/re SDL_AUDIODRIVER=dummy DISPLAY=:98
|
||||
export PYTHONPATH=/sylph-home/.local/lib/python3.12/site-packages
|
||||
SD="$(cd "$(dirname "$0")" && pwd)"
|
||||
SECS="${1:-300}"
|
||||
CFG=/tmp/nav-ctl.json
|
||||
"$SD/launch_mission.sh" fly || { echo "BOOT FAILED"; exit 1; }
|
||||
if python3 "$SD/entities2.py" self 0x130 "$CFG" >/dev/null 2>&1; then
|
||||
SYLPH_HUNT=1 SYLPH_KILL_TURRETS=1 SYLPH_KEEPOUT=1400 \
|
||||
nohup python3 "$SD/pilot.py" "$CFG" "$SECS" </dev/null >/tmp/ctl-pilot.log 2>&1 &
|
||||
PILOT=$!; echo "--- pilot only, no probe"
|
||||
else echo "BIND FAILED"; exit 1; fi
|
||||
python3 -c "import time,sys; time.sleep(int(sys.argv[1]))" "$SECS"
|
||||
kill "$PILOT" 2>/dev/null
|
||||
echo "CONTROL DONE"
|
||||
115
tools/re-capture/wave7_probe.py
Executable file
115
tools/re-capture/wave7_probe.py
Executable file
@@ -0,0 +1,115 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Cheap per-record watch: the heavy rescan was stalling the guest.
|
||||
|
||||
A no-probe control ran 300 s clean while probed runs stalled at 27-255 s
|
||||
(guest-stalls.md), so the 32 MB rescan every 12 s has to go. After one full
|
||||
enumeration the craft bases and their roster links are known, and a sample only
|
||||
needs the hull word at each base -- about 1.2 KB instead of 32 MB. A full rescan
|
||||
runs only every RESCAN seconds to catch anything genuinely new.
|
||||
"""
|
||||
import os, sys, time, struct, collections, importlib.util
|
||||
SD = __file__.rsplit('/', 1)[0]
|
||||
sys.path.insert(0, SD)
|
||||
import gmem, gworld, entities2
|
||||
_w3 = importlib.util.spec_from_file_location('w3', SD + '/wave3_probe.py')
|
||||
wave3 = importlib.util.module_from_spec(_w3); _w3.loader.exec_module(wave3)
|
||||
|
||||
ROSTER_VT = struct.pack('>I', 0x820AF030)
|
||||
DELTA, WIN, LINK, HULL = 0x130, 0x400, 0x08, 0x154
|
||||
BASELINE, RESCAN = 116, 90
|
||||
|
||||
def scan_vt(fd, size, vt):
|
||||
out = []
|
||||
for a, b in gmem.extents(fd, size):
|
||||
pos = a
|
||||
while pos < b:
|
||||
m = min(1 << 24, b - pos)
|
||||
blob = os.pread(fd, m, pos)
|
||||
i = blob.find(vt)
|
||||
while i != -1:
|
||||
if (pos + i) % 4 == 0: out.append(pos + i)
|
||||
i = blob.find(vt, i + 1)
|
||||
pos += m
|
||||
return sorted(out)
|
||||
|
||||
def enumerate_craft(fd, defs, want):
|
||||
"""Heavy: full heap scan. Returns [(base, unit, roster_off)]."""
|
||||
lo, hi = gmem.va_to_off(entities2.ENT_VA_LO), gmem.va_to_off(entities2.ENT_VA_HI)
|
||||
out, pos = [], lo
|
||||
while pos < hi:
|
||||
m = min(1 << 24, hi - pos)
|
||||
blob = os.pread(fd, m, pos)
|
||||
for k in range(0, len(blob) - 3, 4):
|
||||
nm = defs.get(blob[k:k+4])
|
||||
if not nm: continue
|
||||
base = pos + k - DELTA
|
||||
head = os.pread(fd, WIN, base)
|
||||
own = None
|
||||
for j in range(0, len(head) - 3, 4):
|
||||
(p,) = struct.unpack_from('>I', head, j)
|
||||
if p in want: own = want[p]; break
|
||||
out.append((base, nm, own))
|
||||
pos += m
|
||||
return out
|
||||
|
||||
def alive(fd, base):
|
||||
try: return struct.unpack('>f', os.pread(fd, 4, base + HULL))[0] > 0
|
||||
except Exception: return False
|
||||
|
||||
def main():
|
||||
secs = int(sys.argv[1]) if len(sys.argv) > 1 else 300
|
||||
every = int(sys.argv[2]) if len(sys.argv) > 2 else 15
|
||||
w = gworld.World(); fd = w.fd
|
||||
defs = entities2.definitions(w)
|
||||
if not defs: print('NOT IN A MISSION'); return 2
|
||||
roster = scan_vt(fd, w.size, ROSTER_VT)
|
||||
print('roster records: %d (baseline %d)' % (len(roster), BASELINE))
|
||||
if len(roster) != BASELINE:
|
||||
print('DISCARD: not the reproduced baseline'); return 3
|
||||
f = os.fdopen(os.dup(fd), 'rb')
|
||||
label, want = {}, {}
|
||||
for o in roster:
|
||||
va = gmem.primary_va(o)
|
||||
if va is None: continue
|
||||
label[o] = wave3.resolve_id(f, w.size, o)[0] or '?'
|
||||
want[va + LINK] = o
|
||||
|
||||
tick = None
|
||||
lo = gmem.va_to_off(0xBC000000)
|
||||
a = os.pread(fd, 1 << 20, lo); time.sleep(2.0); b = os.pread(fd, 1 << 20, lo)
|
||||
for k in range(0, len(a) - 3, 4):
|
||||
va, vb = struct.unpack_from('>I', a, k)[0], struct.unpack_from('>I', b, k)[0]
|
||||
if va < vb and 5 < (vb - va) / 2.0 < 1 << 18: tick = lo + k; break
|
||||
print('tick witness: %s' % (('%#x' % tick) if tick else 'NONE'))
|
||||
last_tick = struct.unpack('>I', os.pread(fd, 4, tick))[0] if tick else 0
|
||||
|
||||
craft = enumerate_craft(fd, defs, want)
|
||||
print('craft %d, linked %d' % (len(craft), sum(1 for c in craft if c[2])))
|
||||
prev = collections.Counter(c[2] for c in craft if c[2] and alive(fd, c[0]))
|
||||
print('t= 0s deployed=%d strengths %s'
|
||||
% (len(prev), sorted(collections.Counter(prev.values()).items())), flush=True)
|
||||
t0 = time.time(); last_rescan = t0; arr = los = 0; stalls = 0
|
||||
while time.time() - t0 < secs:
|
||||
time.sleep(every)
|
||||
el = round(time.time() - t0)
|
||||
if time.time() - last_rescan > RESCAN:
|
||||
craft = enumerate_craft(fd, defs, want); last_rescan = time.time()
|
||||
cur = collections.Counter(c[2] for c in craft if c[2] and alive(fd, c[0]))
|
||||
st = ''
|
||||
if tick:
|
||||
now = struct.unpack('>I', os.pread(fd, 4, tick))[0]
|
||||
if now <= last_tick: st = ' *** GUEST STALLED ***'; stalls += 1
|
||||
last_tick = now
|
||||
a_ = [(o, cur[o]) for o in cur if prev.get(o, 0) == 0 < cur[o]]
|
||||
l_ = [(o, prev[o], cur.get(o, 0)) for o in prev if cur.get(o, 0) < prev[o]]
|
||||
arr += len(a_); los += len(l_)
|
||||
print('t=%4ds deployed=%d ARRIVALS=%d losses=%d (cum %d/%d)%s'
|
||||
% (el, len(cur), len(a_), len(l_), arr, los, st), flush=True)
|
||||
for o, c in a_: print(' ARRIVAL %-30s 0 -> %d' % (label.get(o, '?'), c), flush=True)
|
||||
for o, x, y in l_: print(' loss %-30s %d -> %d' % (label.get(o, '?'), x, y), flush=True)
|
||||
prev = cur
|
||||
print('\nTOTAL arrivals=%d losses=%d stalled samples=%d' % (arr, los, stalls))
|
||||
return 0
|
||||
|
||||
if __name__ == '__main__':
|
||||
sys.exit(main())
|
||||
16
tools/re-capture/wave7_session.sh
Executable file
16
tools/re-capture/wave7_session.sh
Executable file
@@ -0,0 +1,16 @@
|
||||
#!/usr/bin/env bash
|
||||
set -u
|
||||
export HOME=/sylph-home/re SDL_AUDIODRIVER=dummy DISPLAY=:98
|
||||
export PYTHONPATH=/sylph-home/.local/lib/python3.12/site-packages
|
||||
SD="$(cd "$(dirname "$0")" && pwd)"
|
||||
SECS="${1:-180}"; EVERY="${2:-10}"; HUNT="${3:-1}"
|
||||
CFG=/tmp/nav-live.json
|
||||
"$SD/launch_mission.sh" fly || { echo "BOOT FAILED"; exit 1; }
|
||||
if python3 "$SD/entities2.py" self 0x130 "$CFG" >/dev/null 2>&1; then
|
||||
SYLPH_HUNT="$HUNT" SYLPH_KILL_TURRETS=1 SYLPH_KEEPOUT="${SYLPH_KEEPOUT:-1400}" nohup python3 "$SD/pilot.py" "$CFG" "$SECS" \
|
||||
</dev/null >/tmp/live-pilot.log 2>&1 &
|
||||
PILOT=$!; echo "--- pilot (SYLPH_HUNT=$HUNT)"
|
||||
else PILOT=""; echo "--- BIND FAILED, no pilot"; fi
|
||||
python3 "$SD/wave7_probe.py" "$SECS" "$EVERY"; rc=$?
|
||||
[ -n "$PILOT" ] && kill "$PILOT" 2>/dev/null
|
||||
echo "LIVENESS DONE rc=$rc"
|
||||
Reference in New Issue
Block a user