Show the versions, 1% low and 0.1% low in the full performance overlay (#587, #588)

The panel opens with the port version and the game update, so a screenshot in a bug report carries both. Under RAM,
after a gap, two rows on the same grid: FPS with the 1% and 0.1% lows, and the frame times. perfmon.c keeps a
histogram of frame times in 0.25 ms bins, one slice per second over the last ten seconds, and reads the lows from it
twice a second.

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

runtime/ov_probe.c

@@ -910,10 +910,12 @@ static void probe_menu_text(void) {
         CHECK(has[0] && has[1] && has[2], "game language list lacks en-GB, fr-CA or es-419");
     }
     // the overlay formats keep their conversions
-    CHECK(strstr(ui_text_in("ru", UI_MENU_OV_GAME_PCT), "%.0f%%") && strstr(ui_text_in("ru", UI_MENU_OV_MAX_MS), "%.1f"),
+    CHECK(strstr(ui_text_in("ru", UI_MENU_OV_GAME_PCT), "%.0f%%") && strstr(ui_text_in("ru", UI_MENU_OV_MAX_MS), "%.1f") &&
+          strstr(ui_text_in("ru", UI_MENU_OV_LOW1), "%.0f") && strstr(ui_text_in("ru", UI_MENU_OV_LOW01), "%.0f"),
           "overlay format lost its conversion");
     CHECK(strstr(ui_text_in("pt-BR", UI_MENU_OV_GAME_PCT), "%.0f%%") &&
-          strstr(ui_text_in("pt-BR", UI_MENU_OV_MAX_MS), "%.1f"), "pt-BR overlay format lost its conversion");
+          strstr(ui_text_in("pt-BR", UI_MENU_OV_MAX_MS), "%.1f") &&
+          strstr(ui_text_in("pt-BR", UI_MENU_OV_LOW1), "%.0f") && strstr(ui_text_in("zh-Hans", UI_MENU_OV_LOW01), "%.0f"), "pt-BR overlay format lost its conversion");
     // a Brazilian game language gets the Brazilian keyboard row, Portugal's Portuguese keeps its own
     CHECK(!strcmp(ui_text_lang("pt-BR"), "pt-BR") && !strcmp(ui_text_lang("pt"), "pt") &&
           strcmp(ui_text_in("pt-BR", UI_SWKBD_PROMPT), ui_text_in("pt", UI_SWKBD_PROMPT)), "pt-BR keyboard row not used");

runtime/perfmon.c

@@ -32,6 +32,14 @@ static float g_ring[PERF_HISTORY];
 static uint64_t g_ring_at[PERF_HISTORY];   // when each frame ended
 static int g_ring_n, g_ring_pos;
 
+// The lows: a histogram of the frame times (perf.c's 0.25 ms bins) over the last LOW_SLICES seconds, kept as one slice
+// per second so the oldest second drops out whole. Per frame: one increment. The percentiles are read twice a second.
+#define LOW_BINS 1024
+#define LOW_SLICES 10
+static uint16_t g_low_hist[LOW_SLICES][LOW_BINS];
+static int g_low_cur;
+static uint64_t g_low_t0;
+
 // The per-frame counters, summed since t0 (the overlay's lines are averages over half a second).
 static struct {
     uint64_t t0, frames, gpu0;
@@ -47,6 +55,14 @@ void perfmon_frame(uint64_t now, uint64_t interval_ns, const uint64_t *wait_ns,
         g_ring_at[g_ring_pos] = now;
         g_ring_pos = (g_ring_pos + 1) % PERF_HISTORY;
         if (g_ring_n < PERF_HISTORY) g_ring_n++;
+        if (now - g_low_t0 >= 1000000000ull) {   // the next second: its slice starts empty
+            g_low_cur = (g_low_cur + 1) % LOW_SLICES;
+            memset(g_low_hist[g_low_cur], 0, sizeof g_low_hist[0]);
+            g_low_t0 = now;
+        }
+        uint64_t bin = interval_ns / 250000ull;
+        uint16_t *h = &g_low_hist[g_low_cur][bin < LOW_BINS ? bin : LOW_BINS - 1];
+        if (*h < 65535) (*h)++;
     }
     g_win.frames++;
     g_win.replay += replay_ns / 1e6;
@@ -76,9 +92,27 @@ static void frames_summary(PerfStats *s, uint64_t now) {   // (lock held)
     }
 }
 
+// The fps of the slowest 1% and 0.1% of the frames in the window (the bin's upper edge, as perf.c's summary does); -1
+// when the window holds too few frames. (lock held)
+static void lows_summary(PerfStats *s) {
+    uint32_t total = 0;
+    for (int k = 0; k < LOW_SLICES; k++)
+        for (int b = 0; b < LOW_BINS; b++) total += g_low_hist[k][b];
+    s->low1_fps = s->low01_fps = -1;
+    if (total < 100) return;
+    uint32_t cut1 = (total + 99) / 100, cut01 = (total + 999) / 1000, acc = 0;
+    for (int b = LOW_BINS - 1; b >= 0 && s->low1_fps < 0; b--) {
+        for (int k = 0; k < LOW_SLICES; k++) acc += g_low_hist[k][b];
+        float fps = 1000.0f / ((b + 1) * 0.25f);
+        if (s->low01_fps < 0 && acc >= cut01) s->low01_fps = fps;
+        if (acc >= cut1) s->low1_fps = fps;
+    }
+}
+
 // Every half second: the window's sums as per-frame averages into g_stats, and a new window. (lock held)
 static void counters_summary(uint64_t now) {
     if (now - g_win.t0 < 500000000ull) return;
+    lows_summary(&g_stats);
     uint64_t gpu = perf_gpu_busy_total();
     if (g_win.t0 && g_win.frames) {
         double n = (double)g_win.frames;
@@ -342,6 +376,8 @@ void perfmon_mode(int mode) {
     }
     if (!mode) {   // the next start begins a new graph and a new counter window
         g_ring_n = g_ring_pos = 0;
+        memset(g_low_hist, 0, sizeof g_low_hist);
+        g_low_t0 = 0;
         memset(&g_win, 0, sizeof g_win);
     }
     plat_mutex_unlock(&g_lock);

runtime/perfmon.h

@@ -17,6 +17,8 @@ extern "C" {
 typedef struct {
     // the game's frames (presents), over the last second
     float fps, frame_ms_avg, frame_ms_max;
+    // fps of the slowest 1% and 0.1% of the frames over the last ten seconds (-1: too few frames yet)
+    float low1_fps, low01_fps;
     float frame_ms[PERF_HISTORY];   // oldest first
     // CPU: the whole machine and this process, percent of all logical processors
     char cpu_name[64];

runtime/ui/menu.cpp

@@ -1381,17 +1381,30 @@ static void perf_full_draw(const MenuTarget *t, float scale) {
     ImGui::SetWindowFontScale(0.72f);
     const ImVec4 gpu_c(0.55f, 0.83f, 0.31f, 1), cpu_c(0.18f, 0.59f, 0.80f, 1), ram_c(0.80f, 0.45f, 0.70f, 1),
         fps_c(0.95f, 0.95f, 0.95f, 1), wait_c(0.93f, 0.76f, 0.33f, 1), pic_c(0.62f, 0.70f, 0.95f, 1);
+    // the port version and the game update first, so a screenshot in a bug report carries both; formatted once per
+    // menu language
+    static char ver[96];
+    static const char *ver_fmt;
+    if (ver_fmt != menu_text(UI_MENU_VERSION)) {
+        ver_fmt = menu_text(UI_MENU_VERSION);
+        char game[16];
+        snprintf(game, sizeof game, "%d.%d.%d", rt_game_version / 100, rt_game_version / 10 % 10, rt_game_version % 10);
+        snprintf(ver, sizeof ver, ver_fmt, rt_port_version, game);
+    }
+    ImGui::TextDisabled("%s", ver);
     if (ImGui::BeginTable("##perft", 4, ImGuiTableFlags_SizingFixedFit)) {
-        static const UiTextId labels[] = {UI_MENU_OV_GPU, UI_MENU_OV_VRAM, UI_MENU_OV_CPU, UI_MENU_OV_RAM};
-        static const PerfCol c0[] = {{UI_MENU_OV_FPS, 888}};
-        static const PerfCol c1[] = {{UI_MENU_OV_FMT_PCT, 100}, {UI_MENU_OV_FMT_GB, 888.8f}, {UI_MENU_OV_FRAME_MS, 888.8f}};
-        static const PerfCol c2[] = {{UI_MENU_OV_FMT_TEMP, 188}, {UI_MENU_OV_FMT_GB_OF, 888.8f}, {UI_MENU_OV_MAX_MS, 8888.8f}};
+        static const UiTextId labels[] = {UI_MENU_OV_GPU, UI_MENU_OV_VRAM, UI_MENU_OV_CPU, UI_MENU_OV_RAM,
+                                          UI_MENU_OV_FPS_LABEL, UI_MENU_OV_FRAME_LABEL};
+        static const PerfCol c1[] = {{UI_MENU_OV_FMT_PCT, 100}, {UI_MENU_OV_FMT_GB, 888.8f}, {UI_MENU_OV_FMT_FPS, 888},
+                                     {UI_MENU_OV_FRAME_MS, 888.8f}};
+        static const PerfCol c2[] = {{UI_MENU_OV_FMT_TEMP, 188}, {UI_MENU_OV_FMT_GB_OF, 888.8f}, {UI_MENU_OV_LOW1, 888},
+                                     {UI_MENU_OV_MAX_MS, 8888.8f}};
         static const PerfCol c3[] = {{UI_MENU_OV_FMT_POWER, 888}, {UI_MENU_OV_FMT_MHZ, 8888}, {UI_MENU_OV_GAME_PCT, 100},
-                                     {UI_MENU_OV_GAME_GB, 888.8f}};
-        perf_column("##c0", c0, 1, labels, 4);
-        perf_column("##c1", c1, 3);
-        perf_column("##c2", c2, 3);
-        perf_column("##c3", c3, 4);
+                                     {UI_MENU_OV_GAME_GB, 888.8f}, {UI_MENU_OV_LOW01, 888}};
+        perf_column("##c0", nullptr, 0, labels, 6);
+        perf_column("##c1", c1, 4);
+        perf_column("##c2", c2, 4);
+        perf_column("##c3", c3, 5);
         perf_label(UI_MENU_OV_GPU, gpu_c);
         perf_cell(UI_MENU_OV_FMT_PCT, s.gpu_pct);
         perf_cell(UI_MENU_OV_FMT_TEMP, s.gpu_temp_c);
@@ -1408,12 +1421,16 @@ static void perf_full_draw(const MenuTarget *t, float scale) {
         perf_cell(UI_MENU_OV_FMT_GB, perf_gb(s.ram_used_mb));
         perf_cell(UI_MENU_OV_FMT_GB_OF, perf_gb(s.ram_total_mb));
         perf_cell(UI_MENU_OV_GAME_GB, perf_gb(s.ram_game_mb));
-        ImGui::TableNextColumn();   // the frame row: no label, the rate in its place
-        char b[64];
-        snprintf(b, sizeof b, menu_text(UI_MENU_OV_FPS), s.fps);
-        ImGui::TextColored(fps_c, "%s", b);
+        ImGui::TableNextRow(ImGuiTableRowFlags_None, 6 * scale);   // a gap between the machine and the frames
+        // the frames: the rate over the last second with the lows over the last ten seconds, then the frame times
+        perf_label(UI_MENU_OV_FPS_LABEL, fps_c);
+        perf_cell(UI_MENU_OV_FMT_FPS, s.fps);
+        perf_cell(UI_MENU_OV_LOW1, s.low1_fps);
+        perf_cell(UI_MENU_OV_LOW01, s.low01_fps);
+        perf_label(UI_MENU_OV_FRAME_LABEL, fps_c);
         perf_cell(UI_MENU_OV_FRAME_MS, s.frame_ms_avg);
         perf_cell(UI_MENU_OV_MAX_MS, s.frame_ms_max);
+        ImGui::TableNextColumn();
         ImGui::EndTable();
     }
     float top = s.frame_ms_max > 50 ? s.frame_ms_max : 50;

runtime/ui_text.c

@@ -408,6 +408,8 @@ static const char *const text_en[UI_TEXT_COUNT] = {
 
     [UI_MENU_OV_FPS] = "%.0f FPS", [UI_MENU_OV_FRAME_MS] = "%.1f ms", [UI_MENU_OV_GAME_PCT] = "game %.0f%%",
     [UI_MENU_OV_MAX_MS] = "max %.1f ms",
+    [UI_MENU_OV_FPS_LABEL] = "FPS", [UI_MENU_OV_FRAME_LABEL] = "Frame", [UI_MENU_OV_FMT_FPS] = "%.0f",
+    [UI_MENU_OV_LOW1] = "1%% low %.0f", [UI_MENU_OV_LOW01] = "0.1%% low %.0f",
     [UI_MENU_OV_GPU] = "GPU", [UI_MENU_OV_CPU] = "CPU", [UI_MENU_OV_RAM] = "RAM", [UI_MENU_OV_VRAM] = "VRAM",
     [UI_MENU_OV_TEMP] = "Temperature", [UI_MENU_OV_POWER] = "Power", [UI_MENU_OV_CLOCK] = "Clock",
     [UI_MENU_OV_NONE] = "-",
@@ -843,6 +845,8 @@ static const char *const text_ru[UI_TEXT_COUNT] = {
 
     [UI_MENU_OV_FPS] = "%.0f FPS", [UI_MENU_OV_FRAME_MS] = "%.1f мс", [UI_MENU_OV_GAME_PCT] = "игра %.0f%%",
     [UI_MENU_OV_MAX_MS] = "макс. %.1f мс",
+    [UI_MENU_OV_FPS_LABEL] = "FPS", [UI_MENU_OV_FRAME_LABEL] = "Кадр", [UI_MENU_OV_FMT_FPS] = "%.0f",
+    [UI_MENU_OV_LOW1] = "1%% худших %.0f", [UI_MENU_OV_LOW01] = "0.1%% худших %.0f",
     [UI_MENU_OV_GPU] = "GPU", [UI_MENU_OV_CPU] = "ЦП", [UI_MENU_OV_RAM] = "ОЗУ", [UI_MENU_OV_VRAM] = "Видеопамять",
     [UI_MENU_OV_TEMP] = "Температура", [UI_MENU_OV_POWER] = "Мощность", [UI_MENU_OV_CLOCK] = "Частота",
     [UI_MENU_OV_NONE] = "-",
@@ -1193,6 +1197,8 @@ static const char *const text_pt_br[UI_TEXT_COUNT] = {
 
     [UI_MENU_OV_FPS] = "%.0f FPS", [UI_MENU_OV_FRAME_MS] = "%.1f ms", [UI_MENU_OV_GAME_PCT] = "jogo %.0f%%",
     [UI_MENU_OV_MAX_MS] = "máx. %.1f ms",
+    [UI_MENU_OV_FPS_LABEL] = "FPS", [UI_MENU_OV_FRAME_LABEL] = "Quadro", [UI_MENU_OV_FMT_FPS] = "%.0f",
+    [UI_MENU_OV_LOW1] = "1%% piores %.0f", [UI_MENU_OV_LOW01] = "0.1%% piores %.0f",
     [UI_MENU_OV_GPU] = "GPU", [UI_MENU_OV_CPU] = "CPU", [UI_MENU_OV_RAM] = "RAM", [UI_MENU_OV_VRAM] = "VRAM",
     [UI_MENU_OV_TEMP] = "Temperatura", [UI_MENU_OV_POWER] = "Consumo", [UI_MENU_OV_CLOCK] = "Frequência",
     [UI_MENU_OV_NONE] = "-",
@@ -1785,6 +1791,8 @@ static const char *const text_zh_hans[UI_TEXT_COUNT] = {
     [UI_MENU_OV_FRAME_MS] = "%.1f ms",
     [UI_MENU_OV_GAME_PCT] = "游戏 %.0f%%",
     [UI_MENU_OV_MAX_MS] = "最长 %.1f ms",
+    [UI_MENU_OV_FPS_LABEL] = "FPS", [UI_MENU_OV_FRAME_LABEL] = "帧时间", [UI_MENU_OV_FMT_FPS] = "%.0f",
+    [UI_MENU_OV_LOW1] = "1%% 低 %.0f", [UI_MENU_OV_LOW01] = "0.1%% 低 %.0f",
     [UI_MENU_OV_GPU] = "GPU",
     [UI_MENU_OV_CPU] = "CPU",
     [UI_MENU_OV_RAM] = "内存",

runtime/ui_text.h

@@ -204,6 +204,8 @@ typedef enum {
 
     // Performance overlay
     UI_MENU_OV_FPS, UI_MENU_OV_FRAME_MS, UI_MENU_OV_GAME_PCT, UI_MENU_OV_MAX_MS,
+    UI_MENU_OV_FPS_LABEL, UI_MENU_OV_FRAME_LABEL, UI_MENU_OV_FMT_FPS,   // the frame rows: their labels, the rate
+    UI_MENU_OV_LOW1, UI_MENU_OV_LOW01,   // printf: the fps of the slowest 1% / 0.1% of the frames, no unit (the overlay column stays narrow)
     UI_MENU_OV_GPU, UI_MENU_OV_CPU, UI_MENU_OV_RAM, UI_MENU_OV_VRAM, UI_MENU_OV_TEMP, UI_MENU_OV_POWER,
     UI_MENU_OV_CLOCK, UI_MENU_OV_NONE,
     UI_MENU_OV_REPLAY, UI_MENU_OV_GPU_TIME, UI_MENU_OV_PIPE_WAIT, UI_MENU_OV_SHADER_WAIT, UI_MENU_OV_TEX_UPLOADS,