diff options
Diffstat (limited to 'packages/meshbay-node/src/meshbay_node/daemon.py')
| -rw-r--r-- | packages/meshbay-node/src/meshbay_node/daemon.py | 173 |
1 files changed, 172 insertions, 1 deletions
diff --git a/packages/meshbay-node/src/meshbay_node/daemon.py b/packages/meshbay-node/src/meshbay_node/daemon.py index e270b6c..371c2f0 100644 --- a/packages/meshbay-node/src/meshbay_node/daemon.py +++ b/packages/meshbay-node/src/meshbay_node/daemon.py @@ -32,6 +32,7 @@ import logging import os import signal import sys +import time from pathlib import Path import uvicorn @@ -51,6 +52,7 @@ from meshbay_node.indexer.enrich_audio import AudioEnricher from meshbay_node.indexer.enrich_photo import PhotoEnricher from meshbay_node.media_cache import MediaCache from meshbay_node.tmdb import TmdbClient +from meshbay_node import uploads as uploads_mod from meshbay_node.musicbrainz import MusicBrainzClient from meshbay_node.keystore import create_keystore, load_keystore, load_or_create_keystore from meshbay_node.platform import chmod_private, config_dir, data_dir, state_dir @@ -249,6 +251,8 @@ class NodeDaemon: self._tasks.append(asyncio.create_task(ui_server.serve())) log.info("Control API on 127.0.0.1:%d", self._config.node.ui_port) + self._tasks.append(asyncio.create_task(self._reap_partial_uploads())) + # 3. Hub connection (Ed25519 auth — retries until node key is linked) hub_cfg = HubConfig( hub_url=self._config.hub.url, @@ -406,6 +410,12 @@ class NodeDaemon: # which the RootSet above already carries.) "enabled_apps": await self._roster.enabled_apps( group_cfg.id) if self._roster else list(Roster.DEFAULT_APPS), + # How many transfers one member may run at once here. Empty + # means the operator has not said, and the node's default + # applies — never "unlimited" (transfers.member_cap). + "transfer_limits": ( + await self._roster.transfer_limits(group_cfg.id) + if self._roster else {}), # Which folder(s) inside the shared roots each app works # over. One shape for every app (roster.py's # app_directories) — an empty list means nothing has been @@ -511,6 +521,8 @@ class NodeDaemon: groups=groups_ctx, denylist=denylist, max_concurrent_streams=self._config.node.max_concurrent_streams, + max_concurrent_downloads=self._config.node.max_concurrent_downloads, + max_concurrent_uploads=self._config.node.max_concurrent_uploads, transcode_incompatible_video=self._config.node.transcode_incompatible_video, stun_servers=self._config.node.stun_servers or None, ) @@ -874,6 +886,9 @@ class NodeDaemon: "enabled_apps": ( await self._roster.enabled_apps(group_cfg.id) if self._roster else list(Roster.DEFAULT_APPS)), + "transfer_limits": ( + await self._roster.transfer_limits(group_cfg.id) + if self._roster else {}), **(await self._app_directories_ctx(group_cfg.id)), "chat_link_preview": ( await self._roster.chat_link_preview(group_cfg.id) @@ -1046,6 +1061,60 @@ class NodeDaemon: group_id[:8], e) return 0 + async def _reap_partial_uploads(self, interval: float = 3600.0, + first_delay: float = 60.0) -> None: + """ + Delete `.part` files that no upload will ever finish. + + An upload interrupted for good leaves its partial file behind, and + nothing else ever looks at it: `.part` is not an index entry, so it is + invisible to every group member and to the operator's own file list. One + abandoned film is a gigabyte of their disk, kept for ever. + + Two conditions, both required, and `uploads.orphaned_parts` is where + they are stated and tested. What this adds is the walk and the deletion, + and one rule of its own: it runs a minute after start rather than at + once, so a client reconnecting to finish an upload that outlived a node + restart is not raced by the janitor that would have deleted it — the age + threshold makes that impossible in practice, and doing it anyway costs a + minute. + + `interval` and `first_delay` are parameters so a test can drive this + without waiting an hour. + """ + await asyncio.sleep(first_delay) + while True: + try: + self._reap_once() + except Exception as exc: # never let the janitor kill the node + log.warning("Reaping partial uploads failed: %s", exc) + await asyncio.sleep(interval) + + def _reap_once(self, now: float | None = None) -> int: + """One pass over every group. Returns how many files were deleted.""" + groups = (self._webrtc._ctx.get("groups") or {}) if self._webrtc else {} + when = time.time() if now is None else now + deleted = 0 + for gid, ctx in groups.items(): + roots = ctx.get("roots") + if roots is None: + continue + store = ctx.get("partial_uploads") + live = store.live_paths() if store is not None else set() + for path in uploads_mod.orphaned_parts( + uploads_mod.find_parts(roots.roots), live, when): + try: + size = path.stat().st_size + path.unlink() + except OSError as exc: + log.warning("Could not remove abandoned upload %s: %s", + path.name, exc) + continue + deleted += 1 + log.info("Removed abandoned upload %s (%d bytes, group %s)", + path.name, size, gid[:8]) + return deleted + async def _progress_pusher(self, indexer: DirectoryIndexer, interval: float = 2.0) -> None: """ @@ -1799,6 +1868,7 @@ def main() -> None: choices=["init", "reset", "status", "gek-init", "gek", "operator", "member", "group", "root", "file", "video", "chat", "denylist", "stun", + "transfers", "reload", "restart-daemon", "autostart", "service", "calibrate-argon2"], @@ -1814,6 +1884,9 @@ def main() -> None: "| chat status|rotate|encrypt-history|prune " "| denylist show|clear " "| stun list|add|remove|reset " + "| transfers show|set|per-member: live transfer " + "slots, the node-wide caps, and how many one " + "member may run at once in a group " "| reload: re-read node.toml (hot; systemd or the " "loopback API) | restart-daemon: restart the node " "(systemd unit, the Windows autostart launcher, or the " @@ -1831,12 +1904,16 @@ def main() -> None: "init|rotate for gek; " "list|rm for file; rematch for video; show|clear for " "denylist; list|add|remove|reset for stun; " + "show|set|per-member for transfers; " "install|remove|start|stop|status for autostart and " "for service") parser.add_argument("target", nargs="?", help="username for member invite|revoke|unpin; group name " "for group add; file id for file rm; identifier for " - "denylist clear") + "denylist clear; download cap for transfers set") + parser.add_argument("value", nargs="?", + help="the second value where a verb takes two: the " + "upload cap for transfers set") parser.add_argument("--hub-url", default=None, help="hub URL, for init (e.g. https://meshbay.org)") parser.add_argument("--username", default=None, @@ -2560,6 +2637,100 @@ def main() -> None: print("usage: meshbay-node stun list|add|remove|reset [url]") sys.exit(1) + if args.command == "transfers": + cfg = load_config(args.config or DEFAULT_CONFIG_PATH) + sub = args.subcommand or "show" + + if sub == "show": + out = _daemon_api(cfg, "/api/transfers") + for kind, pool in out.get("pools", {}).items(): + print(f" {kind:<9} {pool['in_use']}/{pool['cap']} in use, " + f"{pool['queued']} queued (node-wide)") + # Per group, because that is the cap that decides how many one + # person runs at once — and it is not the node-wide number. An + # operator raising `transfers set 8 8` and still seeing two at a + # time is looking at this line, which used to print the node's + # default and say nothing about where it came from. + groups = out.get("groups") or [] + if groups: + print("\n per member, per group " + "(meshbay-node transfers per-member <dl> <ul> --group X):") + for g in groups: + how = "set" if g["set"] else "default" + print(f" {g['name']:<20} {g['download']} download(s), " + f"{g['upload']} upload(s) [{how}]") + leases = out.get("leases", []) + if not leases: + print("\n nothing transferring") + return + print(f"\n {'transfer':<14}{'kind':<10}{'state':<9}" + f"{'user':<12}{'bytes':>12}") + for x in leases: + where = f" (#{x['ahead'] + 1} in queue)" if x["state"] == "queued" else "" + print(f" {x['tr']:<14}{x['kind']:<10}{x['state']:<9}" + f"{x['user_id'][:10]:<12}{x['bytes']:>12}{where}") + return + + if sub == "set": + # `transfers set 4 2` — downloads, then uploads. Node-wide; the + # per-member cap is a group's setting and is signed, so it is not + # settable from here (see `ops.set_transfer_limits`). + values = [v for v in (args.target, args.value) if v] + if len(values) != 2: + print("usage: meshbay-node transfers set <downloads> <uploads>") + sys.exit(1) + try: + downloads, uploads = int(values[0]), int(values[1]) + except ValueError: + print("error: both values must be whole numbers") + sys.exit(1) + if downloads < 1 or uploads < 1: + print("error: a cap below 1 is not 'unlimited'; it would stop " + "every transfer. Revoke the member instead.") + sys.exit(1) + out = _daemon_api(cfg, "/api/node-settings", method="PUT", + body={"max_concurrent_downloads": downloads, + "max_concurrent_uploads": uploads}) + print(f"downloads: {downloads}, uploads: {uploads} " + f"(applied now, and kept in node.toml)") + return + + if sub == "per-member": + # How many transfers ONE member may run at once in this group. Not + # the same knob as `set`, which is the machine's total — and the + # reason "I set 8 8 and still only get two" is the commonest + # confusion here: per-member is checked first, by design. + values = [v for v in (args.target, args.value) if v] + if len(values) != 2: + print("usage: meshbay-node transfers per-member <downloads> " + "<uploads> [--group NAME]") + sys.exit(1) + try: + downloads, uploads = int(values[0]), int(values[1]) + except ValueError: + print("error: both values must be whole numbers") + sys.exit(1) + if downloads < 1 or uploads < 1: + print("error: a cap below 1 is not 'unlimited'; it would stop " + "every transfer for that member. Revoke them instead.") + sys.exit(1) + group_id = _resolve_group(cfg, args.group) + out = _daemon_api(cfg, f"/api/groups/{group_id}/transfer-limits", + method="PUT", + body={"downloads": downloads, "uploads": uploads}) + got = out.get("limits", {}) + started = out.get("started") or [] + print(f"each member of this group may now run " + f"{got.get('download')} download(s) and " + f"{got.get('upload')} upload(s) at once") + if started: + print(f"{len(started)} waiting transfer(s) started at once") + return + + print("usage: meshbay-node transfers show|set <downloads> <uploads>|" + "per-member <downloads> <uploads> [--group NAME]") + sys.exit(1) + if args.command == "file": cfg = load_config(args.config or DEFAULT_CONFIG_PATH) sub = args.subcommand or "list" |