performance improvement

sam-tool-tauri/src-tauri/src/decoder.rs

@@ -2,7 +2,7 @@ use crate::video::VideoInfo;
 use std::collections::{HashMap, VecDeque};
 use std::io::{BufRead, BufReader};
 use std::path::PathBuf;
-use std::process::{Child, ChildStdout, Command, Stdio};
+use std::process::{Child, ChildStderr, ChildStdout, Command, Stdio};
 use std::sync::{Arc, Condvar, Mutex};
 use std::thread::{self, JoinHandle};
 use std::time::{Duration, Instant};
@@ -14,6 +14,10 @@ const READ_BUF_BYTES: usize = 256 * 1024;
 /// If the requested frame is this far ahead of the worker, kill + reseek.
 const SEEK_AHEAD_THRESHOLD: u64 = 60;
 const DECODE_TIMEOUT: Duration = Duration::from_secs(15);
+/// Keep the last N stderr lines from ffmpeg so error messages can include
+/// the real reason (e.g. "vaapi: failed to load driver") instead of just
+/// "pipe closed before frame completed".
+const STDERR_TAIL_LINES: usize = 32;
 
 struct FrameCache {
     map: HashMap<u64, Vec<u8>>,
@@ -89,20 +93,32 @@ struct SharedState {
 struct Shared {
     state: Mutex<SharedState>,
     cond: Condvar,
+    /// Ring buffer of recent ffmpeg stderr lines, filled by a sibling drain
+    /// thread. Cleared at each new seek.
+    stderr_tail: Mutex<VecDeque<String>>,
 }
 
 pub struct DecoderSession {
     path: PathBuf,
     info: VideoInfo,
+    /// ffmpeg `-hwaccel` argument. None / empty = software decode. Cleared
+    /// on any decode failure so the next attempt uses software — we'd
+    /// rather degrade than keep retrying a flaky GPU path.
+    hwaccel: Option<String>,
     shared: Arc<Shared>,
     worker: Option<JoinHandle<()>>,
+    /// Sibling thread draining ffmpeg's stderr into `shared.stderr_tail`.
+    /// Joined in `stop_worker` so the tail doesn't get clobbered by a
+    /// straggling drain across seeks.
+    stderr_drain: Option<JoinHandle<()>>,
 }
 
 impl DecoderSession {
-    pub fn open(path: PathBuf, info: VideoInfo) -> Self {
+    pub fn open(path: PathBuf, info: VideoInfo, hwaccel: Option<String>) -> Self {
         Self {
             path,
             info,
+            hwaccel: hwaccel.filter(|s| !s.is_empty()),
             shared: Arc::new(Shared {
                 state: Mutex::new(SharedState {
                     child: None,
@@ -115,8 +131,10 @@ impl DecoderSession {
                     shutdown: false,
                 }),
                 cond: Condvar::new(),
+                stderr_tail: Mutex::new(VecDeque::new()),
             }),
             worker: None,
+            stderr_drain: None,
         }
     }
 
@@ -132,6 +150,28 @@ impl DecoderSession {
     }
 
     pub fn decode_at(&mut self, idx: u64) -> Result<Vec<u8>, String> {
+        match self.decode_at_inner(idx) {
+            Ok(bytes) => Ok(bytes),
+            Err(e) => {
+                // Auto-fallback: any decode failure while hwaccel is on
+                // retries once with software. Covers both first-frame init
+                // failures and later seek/codec-edge failures (e.g. a GPU
+                // path that worked on h264 but chokes on an HEVC segment).
+                // Once cleared, subsequent failures propagate.
+                if let Some(prev) = self.hwaccel.take() {
+                    eprintln!(
+                        "[decoder] hwaccel '{prev}' failed ({e}); falling back to software"
+                    );
+                    self.stop_worker();
+                    self.decode_at_inner(idx)
+                } else {
+                    Err(e)
+                }
+            }
+        }
+    }
+
+    fn decode_at_inner(&mut self, idx: u64) -> Result<Vec<u8>, String> {
         if idx >= self.info.total_frames {
             return Err(format!(
                 "frame {} out of range (total {})",
@@ -194,7 +234,8 @@ impl DecoderSession {
     fn seek_and_start_worker(&mut self, idx: u64) -> Result<(), String> {
         self.stop_worker();
 
-        let (child, stdout) = spawn_ffmpeg(&self.path, &self.info, idx)?;
+        let (child, stdout, stderr) =
+            spawn_ffmpeg(&self.path, &self.info, idx, self.hwaccel.as_deref())?;
 
         {
             let mut st = self.shared.state.lock().unwrap();
@@ -205,8 +246,24 @@ impl DecoderSession {
             st.error = None;
             st.shutdown = false;
         }
+        self.shared.stderr_tail.lock().unwrap().clear();
         self.shared.cond.notify_all();
 
+        // Drain ffmpeg's stderr into a ring buffer so error messages can
+        // include the real reason. We must drain even on success — leaving
+        // stderr unread would let the pipe buffer fill and stall ffmpeg.
+        let drain_shared = self.shared.clone();
+        self.stderr_drain = Some(thread::spawn(move || {
+            let reader = BufReader::new(stderr);
+            for line in reader.lines().map_while(Result::ok) {
+                let mut tail = drain_shared.stderr_tail.lock().unwrap();
+                if tail.len() >= STDERR_TAIL_LINES {
+                    tail.pop_front();
+                }
+                tail.push_back(line);
+            }
+        }));
+
         let shared = self.shared.clone();
         let handle = thread::spawn(move || {
             worker_loop(stdout, shared);
@@ -232,6 +289,12 @@ impl DecoderSession {
         if let Some(handle) = self.worker.take() {
             let _ = handle.join();
         }
+        // Killing the child closed stderr, so the drain thread sees EOF and
+        // exits — joining it here prevents a straggling write into the new
+        // session's stderr_tail after the next seek clears it.
+        if let Some(handle) = self.stderr_drain.take() {
+            let _ = handle.join();
+        }
 
         let mut st = self.shared.state.lock().unwrap();
         st.shutdown = false;
@@ -246,15 +309,55 @@ impl Drop for DecoderSession {
     }
 }
 
+/// Pick a VAAPI render node. `SAM_TOOL_VAAPI_DEVICE` overrides; otherwise we
+/// probe `/dev/dri/renderD128..199` for the first that exists. Multi-GPU
+/// systems can end up with the integrated card on D128 and a discrete card
+/// on D129+ — the env var is the escape hatch when the auto pick is wrong.
+fn vaapi_device() -> String {
+    if let Ok(p) = std::env::var("SAM_TOOL_VAAPI_DEVICE") {
+        if !p.is_empty() {
+            return p;
+        }
+    }
+    for n in 128..200u32 {
+        let p = format!("/dev/dri/renderD{n}");
+        if std::path::Path::new(&p).exists() {
+            return p;
+        }
+    }
+    "/dev/dri/renderD128".to_string()
+}
+
 fn spawn_ffmpeg(
     path: &PathBuf,
     info: &VideoInfo,
     idx: u64,
-) -> Result<(Child, BufReader<ChildStdout>), String> {
+    hwaccel: Option<&str>,
+) -> Result<(Child, BufReader<ChildStdout>, ChildStderr), String> {
     let path_str = path.to_str().ok_or_else(|| "non-utf8 path".to_string())?;
     let t = idx as f64 / info.fps;
     let mut cmd = Command::new("ffmpeg");
     cmd.args(["-v", "error", "-threads", "0"]);
+    // -hwaccel must come BEFORE -i. Output goes to CPU memory by default
+    // (no -hwaccel_output_format), so the downstream mjpeg encoder works
+    // unchanged. If the GPU init fails, ffmpeg will exit nonzero and the
+    // worker thread surfaces the error via shared.error.
+    match hwaccel {
+        Some("auto") => {
+            cmd.args(["-hwaccel", "auto"]);
+        }
+        Some("vaapi") => {
+            let dev = vaapi_device();
+            cmd.args(["-hwaccel", "vaapi", "-vaapi_device", &dev]);
+        }
+        Some("cuda") => {
+            cmd.args(["-hwaccel", "cuda"]);
+        }
+        Some("vdpau") => {
+            cmd.args(["-hwaccel", "vdpau"]);
+        }
+        _ => {}
+    }
     if t > 1.0 {
         cmd.args(["-ss", &format!("{:.3}", t - 1.0)]);
         cmd.args(["-i", path_str]);
@@ -273,13 +376,21 @@ fn spawn_ffmpeg(
         "mjpeg",
         "pipe:1",
     ]);
-    cmd.stdout(Stdio::piped()).stderr(Stdio::null());
+    cmd.stdout(Stdio::piped()).stderr(Stdio::piped());
     let mut child = cmd.spawn().map_err(|e| format!("ffmpeg spawn: {e}"))?;
     let stdout = child
         .stdout
         .take()
         .ok_or_else(|| "ffmpeg stdout unavailable".to_string())?;
-    Ok((child, BufReader::with_capacity(READ_BUF_BYTES, stdout)))
+    let stderr = child
+        .stderr
+        .take()
+        .ok_or_else(|| "ffmpeg stderr unavailable".to_string())?;
+    Ok((
+        child,
+        BufReader::with_capacity(READ_BUF_BYTES, stdout),
+        stderr,
+    ))
 }
 
 fn worker_loop(mut stdout: BufReader<ChildStdout>, shared: Arc<Shared>) {
@@ -315,8 +426,19 @@ fn worker_loop(mut stdout: BufReader<ChildStdout>, shared: Arc<Shared>) {
                 shared.cond.notify_all();
             }
             Err(e) => {
+                // ffmpeg closes stderr right alongside stdout; on real
+                // failures the drain thread may not have flushed yet, so
+                // we wait briefly. On a clean exit there's nothing to
+                // flush — collect_stderr_tail short-circuits via the
+                // child's exit code so end-of-stream EOF isn't penalised.
+                let tail = collect_stderr_tail(&shared, Duration::from_millis(150));
                 let mut st = shared.state.lock().unwrap();
-                if e.contains("pipe closed") || e.contains("EOF") {
+                if !tail.is_empty() {
+                    // With `-v error`, anything on stderr means ffmpeg
+                    // actually failed (vs a clean exit) — surface it as a
+                    // real error so decode_at can fall back / report.
+                    st.error = Some(format!("{e}: ffmpeg: {tail}"));
+                } else if e.contains("pipe closed") || e.contains("EOF") {
                     st.eof = true;
                 } else {
                     st.error = Some(e);
@@ -328,6 +450,50 @@ fn worker_loop(mut stdout: BufReader<ChildStdout>, shared: Arc<Shared>) {
     }
 }
 
+fn read_tail_now(shared: &Arc<Shared>) -> Option<String> {
+    let tail = shared.stderr_tail.lock().unwrap();
+    if tail.is_empty() {
+        None
+    } else {
+        Some(tail.iter().cloned().collect::<Vec<_>>().join(" | "))
+    }
+}
+
+fn collect_stderr_tail(shared: &Arc<Shared>, max_wait: Duration) -> String {
+    // Fast path: drain already flushed — common when ffmpeg writes its
+    // error before exiting and stdout EOF arrives after the drain.
+    if let Some(tail) = read_tail_now(shared) {
+        return tail;
+    }
+    // Skip the poll on clean ffmpeg exit (exit code 0): natural end-of-
+    // stream has nothing on stderr (we run with `-v error`), and 150ms ×
+    // every EOF seek near the final frames adds up.
+    let exited_cleanly = {
+        let mut st = shared.state.lock().unwrap();
+        st.child
+            .as_mut()
+            .and_then(|c| c.try_wait().ok().flatten())
+            .map(|status| status.success())
+            .unwrap_or(false)
+    };
+    if exited_cleanly {
+        return String::new();
+    }
+    // Slow path: ffmpeg exited non-zero (or hasn't exited yet) and the
+    // drain thread hasn't flushed. Poll briefly so the error message
+    // carries the real reason.
+    let deadline = Instant::now() + max_wait;
+    loop {
+        if let Some(tail) = read_tail_now(shared) {
+            return tail;
+        }
+        if Instant::now() >= deadline {
+            return String::new();
+        }
+        thread::sleep(Duration::from_millis(10));
+    }
+}
+
 fn read_jpeg_bytes(reader: &mut BufReader<ChildStdout>) -> Result<Vec<u8>, String> {
     let mut out = Vec::with_capacity(64 * 1024);
     let mut last = 0u8;

sam-tool-tauri/src-tauri/src/lib.rs

@@ -33,9 +33,14 @@ fn open_video(
         return Err(format!("file not found: {}", p.display()));
     }
     let info = video::probe(&p)?;
-    let decoder = DecoderSession::open(p, info.clone());
-    if let Ok(settings) = settings::load(&app) {
-        decoder.set_cache_capacity(settings.cache_capacity);
+    let settings = settings::load(&app).ok();
+    let hwaccel = settings
+        .as_ref()
+        .map(|s| s.hwaccel.clone())
+        .filter(|s| !s.is_empty());
+    let decoder = DecoderSession::open(p, info.clone(), hwaccel);
+    if let Some(s) = settings.as_ref() {
+        decoder.set_cache_capacity(s.cache_capacity);
     }
     let mut guard = state.decoder.lock().map_err(|e| format!("lock: {e}"))?;
     *guard = Some(decoder);
@@ -117,23 +122,27 @@ fn bulk_extract(
     out_dir: String,
     shapes_by_frame: HashMap<String, Vec<coco::Shape>>,
     author: String,
+    frame_skip: Option<u64>,
 ) -> Result<u64, String> {
     if end < start {
         return Err("end must be >= start".into());
     }
+    let step = frame_skip.unwrap_or(1).max(1);
     let mut guard = state.decoder.lock().map_err(|e| format!("lock: {e}"))?;
     let decoder = guard.as_mut().ok_or("no video loaded")?;
     let dir = PathBuf::from(&out_dir);
-    let total = end - start + 1;
+    let total = ((end - start) / step) + 1;
     let empty: Vec<coco::Shape> = Vec::new();
     let mut done: u64 = 0;
-    for idx in start..=end {
+    let mut idx = start;
+    while idx <= end {
         let shapes = shapes_by_frame.get(&idx.to_string()).unwrap_or(&empty);
         extract::extract_one(decoder, idx, &dir, shapes, &author)?;
         done += 1;
         if done == 1 || done % 5 == 0 || done == total {
             let _ = app.emit("bulk-extract-progress", BulkProgress { done, total });
         }
+        idx += step;
     }
     Ok(done)
 }

sam-tool-tauri/src-tauri/src/settings.rs

@@ -15,6 +15,15 @@ pub struct Settings {
     pub sam_model: Option<String>,
     #[serde(default = "default_cache_capacity")]
     pub cache_capacity: usize,
+    /// ffmpeg `-hwaccel` argument. Empty string = software decode (default).
+    /// Recognized: "auto", "vaapi", "cuda", "vdpau". Applied on next
+    /// `open_video` or worker respawn.
+    #[serde(default)]
+    pub hwaccel: String,
+    /// Decimation factor used by playback (advance by N frames per tick) and
+    /// bulk extract (take every Nth frame in range). 1 = no decimation.
+    #[serde(default = "default_frame_skip")]
+    pub frame_skip: u64,
 }
 
 fn default_sam_url() -> String {
@@ -25,11 +34,18 @@ fn default_cache_capacity() -> usize {
     crate::decoder::DEFAULT_CACHE_CAPACITY
 }
 
+fn default_frame_skip() -> u64 {
+    1
+}
+
 fn normalize(mut s: Settings) -> Settings {
     s.cache_capacity = s.cache_capacity.clamp(
         crate::decoder::MIN_CACHE_CAPACITY,
         crate::decoder::MAX_CACHE_CAPACITY,
     );
+    if s.frame_skip < 1 {
+        s.frame_skip = 1;
+    }
     s
 }
 
@@ -40,6 +56,8 @@ impl Default for Settings {
             sam_enabled: false,
             sam_model: None,
             cache_capacity: default_cache_capacity(),
+            hwaccel: String::new(),
+            frame_skip: default_frame_skip(),
         }
     }
 }