DEVX-155: fix: kill dockerd by PID when pkill fails, use /dev/shm for alive daemon

Add pgrep diagnostics before/after pkill to identify lingering dockerd
processes. If pkill fails and pgrep still finds dockerd, kill by PID
directly via os.kill. When inner dockerd can't be killed (still alive),
use /dev/shm as data root since the overlay is still full.

Generated with [Devin](https://devin.ai)

Co-Authored-By: Devin <158243242+devin-ai-integration[bot]@users.noreply.github.com>

src/devx/molecule/start_docker.py

@@ -224,8 +224,18 @@ def start_docker_daemon(timeout: int = DEFAULT_TIMEOUT) -> bool:
     # overlay (38G, often 100% full).  Killing it frees up the
     # socket and any space used by its containers/volumes.
     # Use SIGKILL (-9) since the inner dockerd may not respond to SIGTERM.
-    # Try multiple patterns to match different dockerd invocations.
-    for pattern in ["dockerd", "dockerd-entrypoint.sh"]:
+    # Try multiple approaches to ensure the inner dockerd is killed.
+    with contextlib.suppress(Exception):
+        result = subprocess.run(  # nosec B603 B607
+            ["pgrep", "-af", "dockerd"],
+            capture_output=True,
+            text=True,
+            timeout=5,
+        )
+        if result.stdout.strip():
+            click.echo(f"  dockerd processes before kill: {result.stdout.strip()}")
+
+    for pattern in ["dockerd", "dockerd-entrypoint.sh", "containerd"]:
         with contextlib.suppress(Exception):
             subprocess.run(  # nosec B603 B607
                 ["pkill", "-9", "-f", pattern],
@@ -234,6 +244,24 @@ def start_docker_daemon(timeout: int = DEFAULT_TIMEOUT) -> bool:
             )
     time.sleep(3)
 
+    # Check if dockerd processes are still alive
+    with contextlib.suppress(Exception):
+        result = subprocess.run(  # nosec B603 B607
+            ["pgrep", "-af", "dockerd"],
+            capture_output=True,
+            text=True,
+            timeout=5,
+        )
+        if result.stdout.strip():
+            click.echo(f"  dockerd processes after kill: {result.stdout.strip()}")
+            # Try killing by PID directly
+            for pid_str in result.stdout.split("\n"):
+                pid = pid_str.split()[0] if pid_str.strip() else ""
+                if pid:
+                    with contextlib.suppress(Exception):
+                        os.kill(int(pid), 9)
+            time.sleep(2)
+
     # Verify the inner dockerd is actually dead.  If we can still
     # connect to /var/run/docker.sock, the old daemon is still running
     # and we need to use a different socket path.
@@ -265,10 +293,11 @@ def start_docker_daemon(timeout: int = DEFAULT_TIMEOUT) -> bool:
             timeout=30,
         )
 
-    # Use a fresh data root on the container's overlay.
-    # /dev/shm is a small tmpfs (16G) — too small for images.
-    # The container's overlay (38G) has more space after cleanup.
-    docker_data_root = "/tmp/docker-data"  # nosec B108
+    # Use a fresh data root.  If the inner dockerd is dead, use the
+    # container's overlay (38G, with freed space).  If the inner
+    # dockerd is still alive, use /dev/shm (16G tmpfs) — the overlay
+    # is still full because the inner dockerd's data can't be cleaned.
+    docker_data_root = "/dev/shm/docker" if old_daemon_alive else "/tmp/docker-data"  # nosec B108
 
     # Remove stale socket if present
     with contextlib.suppress(OSError):