03f58d2f54
Two harness problems, one fixed and verified, one diagnosed. Bind: three consecutive attempts failed and the session aborted rather than flying an unattended craft, which is last iteration's guard working as intended. The cause is that entities2 self finds the player by motion between two samples, so a craft sitting still at mission start is invisible. The session now holds the throttle for three seconds before each attempt. Verified: the next run bound immediately and produced 11 losses with zero confirmed arrivals, making fourteen runs without one. One increase, 10 to 11, was surfaced and correctly not counted. Witness: the frame-rate-band selection is still unreliable. It found only five candidates in band and reported 0 of 5 moved in samples where craft were being destroyed, and a counter genuinely running at 24/s cannot fail to advance across a 15 s sample -- it would gain about 360. They are bursty counters that moved during the 3 s calibration and then stopped. The cause is mine. When the witness was bolted into wave7_probe the candidate search was narrowed to a 4 MB window, while timer_probe searched the whole 32 MB region and found 286 candidates with a clean cluster near 17/s. The narrowing was never justified, it was just cheaper to write. Now searches the full region once at startup, which is a one-off cost rather than per sample, and warns explicitly when fewer than eight witnesses are available so a weak vote is visible instead of silently trusted. Not yet run. Worth recording: this is the third attempt at this witness, and all three failures share one pattern -- a shortcut in selecting the witness rather than in the voting logic. Each was caught only because the flagged samples contradicted the loss events in the same output. That internal contradiction is the real check and should survive into any future version.
177 lines
8.5 KiB
Python
Executable File
177 lines
8.5 KiB
Python
Executable File
#!/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
|
|
|
|
# A 1 MB window was too narrow and found nothing, yet the summary still
|
|
# printed "stalled samples=0" -- a witness that does not exist cannot report
|
|
# zero stalls, and that is false reassurance, not a clean run. Search wider,
|
|
# and if there is still no witness say the run is UNVALIDATED.
|
|
# Taking the FIRST word that advances was wrong: it flagged 13 samples as
|
|
# stalled in a run that was recording losses in those same samples, which a
|
|
# frozen guest cannot do. Some counters simply advance intermittently. Use
|
|
# timer_probe's approach instead -- collect every candidate, keep the modal
|
|
# rate cluster, and call a stall only when a MAJORITY of that cluster fails
|
|
# to advance.
|
|
# 4 MB was too narrow: it yielded 5 candidates at a nominal 24/s that then
|
|
# failed to advance in 15 s windows where craft were being destroyed, i.e.
|
|
# they are bursty, not frame counters. timer_probe searched the WHOLE 32 MB
|
|
# region and found 286 with a clean cluster at ~17/s. Pay the one-off cost.
|
|
lo, hiw = gmem.va_to_off(0xBC000000), gmem.va_to_off(0xBE000000)
|
|
span = hiw - lo
|
|
def grab():
|
|
out, pos = bytearray(), lo
|
|
while pos < hiw:
|
|
n = min(1 << 24, hiw - pos); out += os.pread(fd, n, pos); pos += n
|
|
return bytes(out)
|
|
a = grab(); time.sleep(3.0); b = grab()
|
|
cands = []
|
|
for k in range(0, min(len(a), len(b)) - 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) / 3.0 < 200:
|
|
cands.append((lo + k, round((vb - va) / 3.0)))
|
|
# The MODAL cluster is not the frame counter. One run picked a modal rate of
|
|
# 93/s, and only 11 of 31 of those advanced during active combat -- they are
|
|
# subsystem counters that tick in bursts. timer_probe measured the frame-rate
|
|
# cluster at ~17/s, matching Canary's 14-19 fps on this box, so prefer a
|
|
# cluster in that band and fall back to modal only if none exists.
|
|
rates = collections.Counter(r for _, r in cands)
|
|
band = [r for r in rates if 8 <= r <= 40]
|
|
pick = max(band, key=lambda r: rates[r]) if band else (
|
|
rates.most_common(1)[0][0] if rates else None)
|
|
ticks = [o for o, r in cands if r == pick][:32]
|
|
if len(ticks) < 8:
|
|
print('WARNING: only %d witnesses; stall detection is weak' % len(ticks))
|
|
print('tick witnesses: %d candidates, using %d at %s/s (frame-rate band)'
|
|
% (len(cands), len(ticks), pick)
|
|
if ticks else 'tick witnesses: NONE -- RUN UNVALIDATED')
|
|
last_ticks = [struct.unpack('>I', os.pread(fd, 4, o))[0] for o in ticks]
|
|
|
|
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
|
|
pending, confirmed = {}, 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 ticks:
|
|
now = [struct.unpack('>I', os.pread(fd, 4, o))[0] for o in ticks]
|
|
moved = sum(1 for x, y in zip(last_ticks, now) if y > x)
|
|
# "Fewer than half" was too strict: 11 of 31 advanced while craft
|
|
# were being destroyed. The unambiguous signal in that run was
|
|
# 0 of 31, which coincided exactly with losses stopping.
|
|
if moved == 0:
|
|
st = ' *** GUEST STALLED (%d/%d witnesses moved) ***' % (moved, len(ticks))
|
|
stalls += 1
|
|
last_ticks = now
|
|
# Report EVERY increase, not just 0 -> n. The first run logged a record
|
|
# reading 13 then 14 with no event printed, which is how flicker in the
|
|
# hull-based liveness read hides: only decreases were being surfaced, so
|
|
# a spurious 0 -> 2 looked like an arrival while 13 -> 14 looked like
|
|
# nothing. An arrival must also PERSIST to count.
|
|
a_ = [(o, prev.get(o, 0), cur[o]) for o in cur if cur[o] > prev.get(o, 0)]
|
|
l_ = [(o, prev[o], cur.get(o, 0)) for o in prev if cur.get(o, 0) < prev[o]]
|
|
for o, x, y in a_:
|
|
if x == 0: pending[o] = pending.get(o, 0) + 1
|
|
for o in list(pending):
|
|
if cur.get(o, 0) == 0: pending.pop(o, None) # vanished: flicker
|
|
elif pending[o] == 2:
|
|
confirmed += 1
|
|
print(' *** CONFIRMED ARRIVAL %-26s now %d (persisted 2 samples)'
|
|
% (label.get(o, '?'), cur[o]), flush=True)
|
|
pending[o] = 3
|
|
arr += sum(1 for x in a_ if x[1] == 0); los += len(l_)
|
|
print('t=%4ds deployed=%d up=%d down=%d (cum up %d / down %d, confirmed %d)%s'
|
|
% (el, len(cur), len(a_), len(l_), arr, los, confirmed, st), flush=True)
|
|
for o, x, y in a_:
|
|
print(' up %-30s %d -> %d%s' % (label.get(o, '?'), x, y,
|
|
' <- candidate arrival' if x == 0 else ''), flush=True)
|
|
for o, x, y in l_: print(' loss %-30s %d -> %d' % (label.get(o, '?'), x, y), flush=True)
|
|
prev = cur
|
|
if not ticks:
|
|
print('\nRUN UNVALIDATED: no tick witness, so flat samples prove nothing.')
|
|
print('\nTOTAL candidate-up=%d down=%d CONFIRMED arrivals=%d stalled samples=%s'
|
|
% (arr, los, confirmed, stalls if ticks else 'UNKNOWN'))
|
|
return 0
|
|
|
|
if __name__ == '__main__':
|
|
sys.exit(main())
|