perf(diag): per-frame history export + checkpoint LOH/cache counters + soak capped mode (2026-07-24 audit review)
An adversarial performance review found our own instruments cannot measure the project's own performance gates: - FrameProfiler aggregated CPU/GPU/alloc/stage samples into ~5-second windows and reset the ring buffers after each report, so route-wide p50/p95/p99 distributions across a whole soak could not be reconstructed after the fact. ACDREAM_FRAME_HISTORY=<path> now opts into a separate per-frame history (one record per frame, ~72 bytes/record, accumulated in memory with zero frame-thread I/O) that a shutdown-only Dispose() writes as CSV. The aggregated [frame-prof] report format and its existing metrics are unchanged. - The canonical checkpoint JSON tracked cache residency (entry/byte counts) but never LOH size/fragmentation, process-wide allocated bytes, or cache hit/miss/eviction traffic — a committed audit JSON showed 65% LOH fragmentation that no tracked instrument recorded, and "does a revisit portal hit or miss the caches" was unanswerable from an artifact alone. WorldLifecycleResourceSnapshot now carries loh_size_bytes/loh_fragmentation_bytes (GCMemoryInfo.GenerationInfo index 3), process_total_allocated_bytes (GC.GetTotalAllocatedBytes), and Interlocked hit/miss/eviction counters for the CPU mesh cache, decoded-texture cache, and the four bounded DAT-object caches (portal/cell/highRes/language, aggregated). - run-connected-r6-soak.ps1 unconditionally forced ACDREAM_UNCAPPED_RENDER=1 with no capped mode, while its sibling lifecycle-gate script correctly gated it behind a switch. Added -Uncapped (default capped, matching the sibling script's pattern), fixed the stationary dwell (12s -> 26s, past the 25s LiveEntityLivenessController deadline the adjacent comment already cited), and now write an env-disclosure.json into the automation artifact directory before every launch listing every ACDREAM_* var the script sets plus -Uncapped, since the prior audit could only see ACDREAM_DUMP_MOVE_TRUTH and nothing else was ever recorded anywhere. Cache counters are wired via the existing composition path (ObjectMeshManager already owns the CPU mesh cache and the mesh extractor directly; content.Dats is threaded into WorldLifecycleResourceSnapshotSource the same way every other composition consumer receives it). The DAT-object cache lives behind IDatReaderWriter, a third-party interface from the DatReaderWriter package that cannot be extended; RuntimeDatCollection (the one production implementation) exposes the aggregate stats directly and a pattern match reads them, degrading to zero for any test double — no new static registry was introduced (GpuMemoryTracker remains the one precedented process-wide static). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> (cherry picked from commit 1da2c33c875b41fa383dd79694ee2765f0e21896)
This commit is contained in:
parent
bfc5e47365
commit
7b456b49d6
20 changed files with 477 additions and 9 deletions
|
|
@ -271,6 +271,21 @@ internal sealed class CpuMeshUploadCache
|
|||
private readonly long _byteCapacity;
|
||||
private long _residentBytes;
|
||||
|
||||
// Hit/miss/eviction traffic counters (2026-07-24 measurement-tooling
|
||||
// review). Read via Stats from the diagnostics/checkpoint thread
|
||||
// without taking _data's lock, so plain fields with Interlocked
|
||||
// increments — the 4 concurrent preparation workers all consult
|
||||
// TryGetAndStage.
|
||||
private long _hits;
|
||||
private long _misses;
|
||||
private long _evictions;
|
||||
|
||||
/// <summary>Cumulative hit/miss/eviction counts since construction.</summary>
|
||||
internal CacheStats Stats => new(
|
||||
Interlocked.Read(ref _hits),
|
||||
Interlocked.Read(ref _misses),
|
||||
Interlocked.Read(ref _evictions));
|
||||
|
||||
public CpuMeshUploadCache(int capacity, long byteCapacity = 128L * 1024 * 1024)
|
||||
{
|
||||
if (capacity <= 0)
|
||||
|
|
@ -292,9 +307,11 @@ internal sealed class CpuMeshUploadCache
|
|||
lock (_data)
|
||||
{
|
||||
if (!_data.TryGetValue(id, out data)) {
|
||||
Interlocked.Increment(ref _misses);
|
||||
stageResult = default;
|
||||
return false;
|
||||
}
|
||||
Interlocked.Increment(ref _hits);
|
||||
_lru.Remove(id);
|
||||
_lru.AddLast(id);
|
||||
stageResult = staging.TryStage(data);
|
||||
|
|
@ -325,6 +342,7 @@ internal sealed class CpuMeshUploadCache
|
|||
_data.Remove(oldest);
|
||||
if (_bytesById.Remove(oldest, out long oldestBytes))
|
||||
_residentBytes -= oldestBytes;
|
||||
Interlocked.Increment(ref _evictions);
|
||||
}
|
||||
|
||||
_data[data.ObjectId] = data;
|
||||
|
|
|
|||
|
|
@ -276,6 +276,12 @@ namespace AcDream.App.Rendering.Wb
|
|||
internal (int Count, long Bytes) CpuCacheDiagnostics =>
|
||||
(_cpuMeshCache.Count, _cpuMeshCache.ResidentBytes);
|
||||
|
||||
/// <summary>CPU prepared-mesh cache hit/miss/eviction counts (2026-07-24 measurement-tooling review).</summary>
|
||||
internal CacheStats CpuMeshCacheStats => _cpuMeshCache.Stats;
|
||||
|
||||
/// <summary>Decoded-texture cache hit/miss/eviction counts (2026-07-24 measurement-tooling review).</summary>
|
||||
internal CacheStats DecodedTextureCacheStats => _extractor.DecodedTextureCacheStats;
|
||||
|
||||
private sealed class PreparationRequest(
|
||||
ulong id,
|
||||
bool isSetup,
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue