Handle two-frame Ego4D bbox tails and preserve worker errors

extract_ego4d_local_multigpu.py

@@ -107,11 +107,17 @@ def worker_environment(gpu, cpu_threads):
     return env
 
 
-def log_tail(path):
+def log_tail(path, *, failure=False):
+    """Compact progress, but retain traceback/long diagnostic lines on failure."""
     try:
         with path.open("rb") as handle:
-            handle.seek(max(0, path.stat().st_size - 4096))
+            handle.seek(max(0, path.stat().st_size - (65536 if failure else 4096)))
             lines = handle.read().decode("utf-8", errors="replace").replace("\r", "\n").splitlines()
+        if failure:
+            for index in range(len(lines) - 1, -1, -1):
+                if lines[index].startswith("Traceback (most recent call last):"):
+                    return "\n".join(lines[index:])
+            return "\n".join(lines[-40:]) or "no worker output"
         return next((line.strip() for line in reversed(lines) if line.strip()), "starting")[-300:]
     except FileNotFoundError:
         return "starting"
@@ -166,14 +172,16 @@ def run_workers(plans, args, log_dir):
                 time.sleep(args.startup_delay)
             for started, child, child_log in running:
                 if child.poll() not in (None, 0):
-                    raise RuntimeError(f"GPU {started['gpu']} failed (exit={child.returncode}); see {child_log}")
+                    raise RuntimeError(f"GPU {started['gpu']} failed (exit={child.returncode}); see {child_log}\n"
+                                       f"{log_tail(child_log, failure=True)}")
         next_status, last_status = 0., {}
         while True:
             completed = 0
             for plan, process, log in running:
                 code = process.poll()
                 if code not in (None, 0):
-                    raise RuntimeError(f"GPU {plan['gpu']} failed (exit={code}); see {log}\n{log_tail(log)}")
+                    raise RuntimeError(f"GPU {plan['gpu']} failed (exit={code}); see {log}\n"
+                                       f"{log_tail(log, failure=True)}")
                 completed += code == 0
             if time.monotonic() >= next_status or completed == len(running):
                 for plan, process, log in running: