From 80ac882346b474bb7ea4e8c8afd4694bd13dd9dd Mon Sep 17 00:00:00 2001 From: Christophe Besson Date: Wed, 14 Oct 2026 10:17:49 +0200 Subject: feat(node): skip a file the disk stops answering for, then pause its root A Windows tester's scan stuck for good on one directory of a large disk: one read that never returned held the indexer's only thread, and with it every root behind that one. - A disk call is timed by its silence, not its length: each directory entry listed and each megabyte read counts as an answer. After 60 s of silence the call is abandoned on its daemon thread, the file is noted unread and the scan goes on. - Three silent files in a row pause the root (not persisted). Resume skips the files already known to give no answer; a restart, a replug or a change to the file retries them. - The walk is per directory with os.scandir: a subdirectory that cannot be listed costs itself, and a listing that stops answering pauses the root at once. A scan no longer stats anything from the event loop. - The log names the file after 10 s of silence, the indexing band shows it, and Group settings shows the paused root, where it stuck and the unread files with their reason, on the node's machine only. - generate_http_api.py writes LF on Windows too. Verified with real kernel-blocked opens (an unacknowledged oplock) in the installed frozen app. Co-Authored-By: Claude Opus 5.5 --- packages/meshbay-node/src/meshbay_node/ops/roots.py | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'packages/meshbay-node/src/meshbay_node/ops/roots.py') diff --git a/packages/meshbay-node/src/meshbay_node/ops/roots.py b/packages/meshbay-node/src/meshbay_node/ops/roots.py index 187e134..0cd2daa 100644 --- a/packages/meshbay-node/src/meshbay_node/ops/roots.py +++ b/packages/meshbay-node/src/meshbay_node/ops/roots.py @@ -361,13 +361,16 @@ async def pause_root(state: dict, group_id: str, root_name: str) -> dict: async def resume_root(state: dict, group_id: str, root_name: str) -> dict: """Index a paused root again; the walk runs in the background.""" roots, root = _live_root(state, group_id, root_name) - if not root.paused: + indexer = state.get("indexers", {}).get(group_id) + # A root the node paused by itself, its disk having stopped answering, is + # paused on the indexer's own set and nowhere in the roster. + own = indexer.roots.by_name(root.name) if indexer else None + if not root.paused and not (own is not None and own.paused): return {"status": "already_resumed", "name": root.name, "group_id": group_id, "roots": roots.describe()} await _roster(state).set_root_paused( group_id, root.name, False, set_by=state.get("node_user_id", "")) - indexer = state.get("indexers", {}).get(group_id) if indexer: await indexer.resume_root(root.name) root.paused = False -- cgit v1.2.3