Keep the shadow log of players without sync_ahead as it was, sort the new setting names, and fix the sync_ahead frame-time sentence

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

runtime/cfg.c

@@ -56,11 +56,11 @@ static const char *const known[] = {
     "RENDER_SCALE", "REPLAY_ASYNC", "REPLAY_CHUNKS", "REPLAY_CHUNK_DRAWS", "REPLAY_SKEW_US", "REPLAY_STATE_CHECK", "REPLAY_WORKERS",
     "REPLAY_CHECK", "RESOLVE_CHECK", "RESTART_WAIT", "ROMFS", "ROMFS_INDEX", "ROMFS_MMAP", "ROMFS_MODS", "ROMFS_PATCHES",
     "ROMFS_PROOF_DIR", "ROMFS_VERIFY", "RSTICK_DEADZONE", "RUMBLE", "RUMBLE_CURVE", "RUMBLE_STRENGTH", "RUMBLE_TRIGGERS", "SHADER_CACHE",
-    "SHADER_MEMO", "SHADOW_RANGE", "SHADOW_RES", "SHADOW_SCALE", "SHADOW_SNAP", "SHARED_FONTS", "SHARPNESS", "SHOTS", "SHOTS_DIR",
+    "SHADER_MEMO", "SHADOW_DEFER", "SHADOW_RANGE", "SHADOW_RES", "SHADOW_SCALE", "SHADOW_SNAP", "SHARED_FONTS", "SHARPNESS", "SHOTS", "SHOTS_DIR",
     "SHOTS_FULL", "SPEED_PROBE", "SPIN", "SPIN_HANDOFF_US", "SPLIT_DRAWS", "SPLIT_US", "STICK_DEADZONE", "STICK_SENS",
-    "SWKBD_ANSWER",
+    "SWKBD_ANSWER", "SYNC_AHEAD",
     "SWKBD_TEST", "TEST_OOM", "TEST_PAD", "TEST_PREPARE_SHADERS", "TEX_ALIAS", "TEX_BLOCK_MIB", "TEX_HEAP_EXTRA_MB", "TEX_MEMO", "TEX_RELEASED_MIB", "TEX_VRAM_PRESSURE", "TIMER_1MS", "TRACE", "TXD_TRANSPOSE", "UBO_SNAPSHOT", "UB_OVERLAY", "UB_OVERLAY_OUT", "UPSCALER", "VB_USED", "VK_DYN_A2C", "VK_DYN_VERTEX", "VK_NO_FLOAT64",
-    "VK_PRESENT", "VK_RECORDER", "VK_SSBO_ALIGN", "VK_SUBGROUP", "VK_SUBGROUP_PIN", "VK_VALIDATION", "VMA_BLOCK_MIB", "VOLUME", "VRAM_HEADROOM", "VRAM_LIMIT_MIB", "VS_OUTS", "SHADOW_DEFER", "SYNC_AHEAD",
+    "VK_PRESENT", "VK_RECORDER", "VK_SSBO_ALIGN", "VK_SUBGROUP", "VK_SUBGROUP_PIN", "VK_VALIDATION", "VMA_BLOCK_MIB", "VOLUME", "VRAM_HEADROOM", "VRAM_LIMIT_MIB", "VS_OUTS",
     "WALK_KEY", "WALK_SCALE", "WB_EXACT", "WB_FENCE_LIMIT", "WB_MERGE", "WINDOW_SIZE", "XLATE", "XLATE_ID", "XLATE_KEEP", "XLATE_PROCS",
     "ZSTD_CHECK", "ZSTD_NATIVE",
 };

runtime/vk_memory.c

@@ -1271,12 +1271,14 @@ static void shadow_log(uint64_t frame) {
     if (!shadow_on) return;
     plat_mutex_lock(&shadow_lock);
     rt_log("mem: shadow at frame %llu: %lld pools %.1f MiB; since the last: %llu pool syncs, %llu queries, %.1f MiB "
-           "copied in (%llu untracked), %.1f MiB written back, %.2f ms, %d GPU writes pending; deferred (%s): %llu pools, "
-           "%.1f MiB in %llu copies; replay waited for a reader %llu times, %.2f ms",
+           "copied in (%llu untracked), %.1f MiB written back, %.2f ms, %d GPU writes pending",
            (unsigned long long)frame, (long long)s_live_n, s_live_bytes / 1048576.0, (unsigned long long)s_syncs,
            (unsigned long long)s_queries, s_copied / 1048576.0, (unsigned long long)s_untracked, s_wb_bytes / 1048576.0,
-           qpc_ms(s_ticks), nspend, defer_on ? "on" : "off", (unsigned long long)s_defer_pools,
-           s_defer_bytes / 1048576.0, (unsigned long long)s_defer_copies, (unsigned long long)s_waits, qpc_ms(s_wait_ticks));
+           qpc_ms(s_ticks), nspend);
+    if (defer_on || s_waits)   // only with TOTK_SYNC_AHEAD: the shadow log of everyone else stays as it was
+        rt_log("mem: shadow deferred (%s): %llu pools, %.1f MiB in %llu copies; replay waited for a reader %llu times, "
+               "%.2f ms", defer_on ? "on" : "off", (unsigned long long)s_defer_pools, s_defer_bytes / 1048576.0,
+               (unsigned long long)s_defer_copies, (unsigned long long)s_waits, qpc_ms(s_wait_ticks));
     s_syncs = s_queries = s_copied = s_untracked = s_wb_bytes = s_ticks = 0;
     s_defer_pools = s_defer_bytes = s_defer_copies = s_wait_ticks = s_waits = 0;
     plat_mutex_unlock(&shadow_lock);

totk.ini.example

@@ -54,8 +54,7 @@
 # Let the game build the next frame while the GPU still draws the previous one, 0 or 1. Default: off. Each frame the
 # game waits once for the GPU to finish the frame it presented last; with 1 that wait covers the frame before it
 # instead. On Great Sky Island (Linux, RX 9070 XT) with shadow_defer = 1 this took about 73 to 100 fps. Costs one more
-# frame of input delay. The frame rate swings less from frame to frame when uncapped than before, but more than
-# without it. GPU results the game reads back after that wait, for example occlusion queries, can be a frame old.
+# frame of input delay, and frame times vary more from frame to frame than with 0. GPU results the game reads back after that wait, for example occlusion queries, can be a frame old.
 # Works on 1.2.1 and 1.4.3; 1.1.0 ignores it. Needs shadow storage, which is on by default on Linux and Wine and needs
 # the environment variable TOTK_SHADOW=1 on native Windows; without it the setting is ignored and the log says so.
 # sync_ahead = 0