logging, routing

2026-07-07 22:00:54 +03:00
parent 481ce6c6f5
commit dae0719a32
5 changed files with 325 additions and 27 deletions
--- a/packages/tracker/meshnet_tracker/cli.py
+++ b/packages/tracker/meshnet_tracker/cli.py
@@ -8,8 +8,14 @@ from pathlib import Path

 from .accounts import DEFAULT_ACCOUNTS_DB_PATH
 from .billing import DEFAULT_BILLING_DB_PATH
-from .hf_pricing import DEFAULT_HF_PRICING_LOG_DB_PATH
-from .server import (
+from .hf_pricing import DEFAULT_HF_PRICING_LOG_DB_PATH
+from .logging_setup import (
+    DEFAULT_LOG_BACKUP_COUNT,
+    DEFAULT_LOG_DIR,
+    DEFAULT_LOG_MAX_BYTES,
+    configure_tracker_file_logging,
+)
+from .server import (
    DEFAULT_CALLER_CREDIT_USDT,
    DEFAULT_DEVNET_TOPUP_USDT,
    TrackerServer,
@@ -255,12 +261,40 @@ def main() -> None:
        default=86400.0,
        help="Seconds between dynamic pricing refresh passes (default: daily)",
    )
-    common.add_argument(
-        "--models-dir",
-        default=None,
-        metavar="PATH",
-        help="Local HuggingFace snapshot root advertised as tracker model-file source (default: MESHNET_MODELS_DIR)",
-    )
+    common.add_argument(
+        "--models-dir",
+        default=None,
+        metavar="PATH",
+        help="Local HuggingFace snapshot root advertised as tracker model-file source (default: MESHNET_MODELS_DIR)",
+    )
+    common.add_argument(
+        "--log-dir",
+        default=DEFAULT_LOG_DIR,
+        metavar="PATH",
+        help=(
+            "Directory for rotating tracker logs "
+            f"(default: {DEFAULT_LOG_DIR}; files: info.log, warning.log, error.log)"
+        ),
+    )
+    common.add_argument(
+        "--log-max-bytes",
+        type=int,
+        default=DEFAULT_LOG_MAX_BYTES,
+        metavar="BYTES",
+        help=f"Rotate each tracker log file after this many bytes (default: {DEFAULT_LOG_MAX_BYTES})",
+    )
+    common.add_argument(
+        "--log-backup-count",
+        type=int,
+        default=DEFAULT_LOG_BACKUP_COUNT,
+        metavar="N",
+        help=f"Number of rotated tracker log files to keep per level (default: {DEFAULT_LOG_BACKUP_COUNT})",
+    )
+    common.add_argument(
+        "--no-file-logs",
+        action="store_true",
+        help="Disable rotating tracker log files and only write to the terminal",
+    )

    parser = argparse.ArgumentParser(
        prog="meshnet-tracker",
@@ -273,8 +307,15 @@ def main() -> None:

    args = parser.parse_args()

-    if args.command in {None, "start"}:
-        cluster_peers = [u.strip() for u in args.cluster_peers.split(",") if u.strip()]
+    if args.command in {None, "start"}:
+        if not args.no_file_logs:
+            log_dir = configure_tracker_file_logging(
+                args.log_dir,
+                max_bytes=args.log_max_bytes,
+                backup_count=args.log_backup_count,
+            )
+            print(f"meshnet-tracker logs: {log_dir}", flush=True)
+        cluster_peers = [u.strip() for u in args.cluster_peers.split(",") if u.strip()]
        relay_url = args.relay_url or derive_relay_url_from_public_tracker_url(args.self_url)
        treasury = None
        if args.solana_rpc_url and args.usdt_mint and args.treasury_keypair:
--- a/packages/tracker/meshnet_tracker/logging_setup.py
+++ b/packages/tracker/meshnet_tracker/logging_setup.py
@@ -0,0 +1,99 @@
+"""Rotating file logging for the tracker CLI."""
+
+from __future__ import annotations
+
+import logging
+import sys
+from logging.handlers import RotatingFileHandler
+from pathlib import Path
+from typing import TextIO
+
+
+DEFAULT_LOG_DIR = "logs/tracker"
+DEFAULT_LOG_MAX_BYTES = 10 * 1024 * 1024
+DEFAULT_LOG_BACKUP_COUNT = 5
+TRACKER_LOGGER_NAME = "meshnet.tracker"
+
+
+class _ExactLevelFilter(logging.Filter):
+    def __init__(self, level: int) -> None:
+        super().__init__()
+        self._level = level
+
+    def filter(self, record: logging.LogRecord) -> bool:
+        return record.levelno == self._level
+
+
+class _TeeStream:
+    def __init__(self, stream: TextIO, logger: logging.Logger, level: int) -> None:
+        self._stream = stream
+        self._logger = logger
+        self._level = level
+        self._buffer = ""
+
+    def write(self, text: str) -> int:
+        self._stream.write(text)
+        self._stream.flush()
+        self._buffer += text
+        while "\n" in self._buffer:
+            line, self._buffer = self._buffer.split("\n", 1)
+            line = line.rstrip()
+            if line:
+                self._logger.log(self._level, line)
+        return len(text)
+
+    def flush(self) -> None:
+        self._stream.flush()
+        line = self._buffer.rstrip()
+        if line:
+            self._logger.log(self._level, line)
+        self._buffer = ""
+
+    def isatty(self) -> bool:
+        return self._stream.isatty()
+
+
+def _make_handler(path: Path, level: int, *, max_bytes: int, backup_count: int) -> RotatingFileHandler:
+    handler = RotatingFileHandler(
+        path,
+        maxBytes=max_bytes,
+        backupCount=backup_count,
+        encoding="utf-8",
+    )
+    handler.setLevel(level)
+    handler.addFilter(_ExactLevelFilter(level))
+    handler.setFormatter(logging.Formatter("%(asctime)s %(levelname)s %(message)s"))
+    return handler
+
+
+def configure_tracker_file_logging(
+    log_dir: str | Path = DEFAULT_LOG_DIR,
+    *,
+    max_bytes: int = DEFAULT_LOG_MAX_BYTES,
+    backup_count: int = DEFAULT_LOG_BACKUP_COUNT,
+    tee_stdio: bool = True,
+) -> Path:
+    """Configure rotatable info/warning/error log files and return the directory."""
+
+    path = Path(log_dir).expanduser()
+    path.mkdir(parents=True, exist_ok=True)
+
+    logger = logging.getLogger(TRACKER_LOGGER_NAME)
+    logger.setLevel(logging.INFO)
+    logger.propagate = False
+    logger.handlers.clear()
+    logger.addHandler(_make_handler(path / "info.log", logging.INFO, max_bytes=max_bytes, backup_count=backup_count))
+    logger.addHandler(_make_handler(path / "warning.log", logging.WARNING, max_bytes=max_bytes, backup_count=backup_count))
+    logger.addHandler(_make_handler(path / "error.log", logging.ERROR, max_bytes=max_bytes, backup_count=backup_count))
+
+    if tee_stdio:
+        if not isinstance(sys.stdout, _TeeStream):
+            sys.stdout = _TeeStream(sys.stdout, logger, logging.INFO)  # type: ignore[assignment]
+        if not isinstance(sys.stderr, _TeeStream):
+            sys.stderr = _TeeStream(sys.stderr, logger, logging.ERROR)  # type: ignore[assignment]
+
+    return path
+
+
+def tracker_logger() -> logging.Logger:
+    return logging.getLogger(TRACKER_LOGGER_NAME)
--- a/packages/tracker/meshnet_tracker/server.py
+++ b/packages/tracker/meshnet_tracker/server.py
@@ -26,6 +26,7 @@ import hashlib
 import itertools
 import json
 import os
+import select
 import socketserver
 import sqlite3
 import tarfile
@@ -46,8 +47,9 @@ from .wallet_proof import binding_message, verify_wallet_signature
 from .billing import DEFAULT_BILLING_DB_PATH, BillingLedger
 from .calibration import DEFAULT_CALIBRATION_DB_PATH, ToplocCalibrationStore
 from .hf_pricing import DEFAULT_HF_PRICING_LOG_DB_PATH, HfPricingLog, refresh_preset_price
-from .gossip import NodeGossip
-from .model_files import files_for_layer_range, snapshot_dir_for_repo
+from .gossip import NodeGossip
+from .logging_setup import tracker_logger
+from .model_files import files_for_layer_range, snapshot_dir_for_repo
 from .raft import RaftNode


@@ -2092,7 +2094,7 @@ def _registration_ban_error(contracts: Any | None, wallet_address: str | None) -
    return None


-def _tracker_log(
+def _tracker_log(
    server: "_TrackerHTTPServer",
    level: str,
    message: str,
@@ -2100,11 +2102,18 @@ def _tracker_log(
    stdout: bool = True,
    update_console_key: str | None = None,
    **fields: Any,
-) -> None:
-    event = {
-        "ts": time.time(),
-        "level": level,
-        "message": message,
+) -> None:
+    log_level = {
+        "debug": 10,
+        "info": 20,
+        "warn": 30,
+        "warning": 30,
+        "error": 40,
+    }.get(level.lower(), 20)
+    event = {
+        "ts": time.time(),
+        "level": level,
+        "message": message,
        "fields": {
            key: value
            for key, value in fields.items()
@@ -2125,12 +2134,13 @@ def _tracker_log(
                    break
            if not updated:
                server.console_events.append(event)
-        else:
-            server.console_events.append(event)
-    if stdout:
-        extras = " ".join(f"{key}={value}" for key, value in event["fields"].items())
-        suffix = f"  {extras}" if extras else ""
-        print(f"[tracker] {level}: {message}{suffix}", flush=True)
+        else:
+            server.console_events.append(event)
+    extras = " ".join(f"{key}={value}" for key, value in event["fields"].items())
+    suffix = f"  {extras}" if extras else ""
+    tracker_logger().log(log_level, f"{message}{suffix}")
+    if stdout:
+        print(f"[tracker] {level}: {message}{suffix}", flush=True)


@dataclass
@@ -2182,10 +2192,14 @@ def _request_proxy_cancel(server: "_TrackerHTTPServer", request_id: str) -> bool
    return True


-def _set_upstream_read_timeout(upstream: Any, timeout: float) -> None:
+def _upstream_socket(upstream: Any) -> Any | None:
    fp = getattr(upstream, "fp", None)
    raw = getattr(fp, "raw", None) if fp is not None else None
-    sock = getattr(raw, "_sock", None) if raw is not None else None
+    return getattr(raw, "_sock", None) if raw is not None else None
+
+
+def _set_upstream_read_timeout(upstream: Any, timeout: float | None) -> None:
+    sock = _upstream_socket(upstream)
    if sock is not None:
        sock.settimeout(timeout)

@@ -3206,7 +3220,11 @@ class _TrackerHandler(http.server.BaseHTTPRequestHandler):
            upstream = upstream_result[0]
            with proxy_ctx.upstream_lock:
                proxy_ctx.upstream = upstream
-            _set_upstream_read_timeout(upstream, 0.5)
+            upstream_sock = _upstream_socket(upstream)
+            if upstream_sock is not None:
+                _set_upstream_read_timeout(upstream, None)
+            else:
+                _set_upstream_read_timeout(upstream, 0.5)
            _tracker_log(server, "info", "proxy connected", request_id=request_id, target_url=target_url)
        except urllib.error.HTTPError as exc:
            # Relay error status + body from node
@@ -3266,6 +3284,10 @@ class _TrackerHandler(http.server.BaseHTTPRequestHandler):
                    while True:
                        if proxy_ctx.cancel_event.is_set():
                            break
+                        if upstream_sock is not None:
+                            readable, _, _ = select.select([upstream_sock], [], [], 0.5)
+                            if not readable:
+                                continue
                        try:
                            line = upstream.readline()
                        except TimeoutError:
--- a/tests/test_tracker_logging.py
+++ b/tests/test_tracker_logging.py
@@ -0,0 +1,67 @@
+import logging
+import sys
+
+from meshnet_tracker.logging_setup import configure_tracker_file_logging, tracker_logger
+
+
+def test_tracker_file_logging_writes_separate_level_files(tmp_path):
+    original_stdout = sys.stdout
+    original_stderr = sys.stderr
+    try:
+        log_dir = configure_tracker_file_logging(tmp_path, tee_stdio=False)
+        logger = tracker_logger()
+
+        logger.info("info-event")
+        logger.warning("warning-event")
+        logger.error("error-event")
+        for handler in logger.handlers:
+            handler.flush()
+
+        assert (log_dir / "info.log").read_text().count("info-event") == 1
+        assert "warning-event" not in (log_dir / "info.log").read_text()
+        assert "error-event" not in (log_dir / "info.log").read_text()
+
+        assert "warning-event" in (log_dir / "warning.log").read_text()
+        assert "info-event" not in (log_dir / "warning.log").read_text()
+        assert "error-event" not in (log_dir / "warning.log").read_text()
+
+        assert "error-event" in (log_dir / "error.log").read_text()
+        assert "info-event" not in (log_dir / "error.log").read_text()
+        assert "warning-event" not in (log_dir / "error.log").read_text()
+    finally:
+        sys.stdout = original_stdout
+        sys.stderr = original_stderr
+
+
+def test_tracker_file_logging_tees_stdio_and_rotates(tmp_path):
+    original_stdout = sys.stdout
+    original_stderr = sys.stderr
+    try:
+        log_dir = configure_tracker_file_logging(
+            tmp_path,
+            max_bytes=120,
+            backup_count=1,
+        )
+
+        print("stdout goes to info", flush=True)
+        print("stderr goes to error", file=sys.stderr, flush=True)
+        for handler in tracker_logger().handlers:
+            handler.flush()
+
+        assert "stdout goes to info" in (log_dir / "info.log").read_text()
+        assert "stderr goes to error" in (log_dir / "error.log").read_text()
+
+        for index in range(12):
+            tracker_logger().info("rotating-info-line-%02d", index)
+        for handler in tracker_logger().handlers:
+            handler.flush()
+
+        assert (log_dir / "info.log.1").exists()
+    finally:
+        sys.stdout = original_stdout
+        sys.stderr = original_stderr
+        logger = tracker_logger()
+        for handler in logger.handlers:
+            handler.close()
+        logger.handlers.clear()
+        logger.setLevel(logging.NOTSET)
--- a/tests/test_tracker_routing.py
+++ b/tests/test_tracker_routing.py
@@ -502,6 +502,75 @@ def test_tracker_logs_stream_progress_before_request_completes():
        node_thread.join(timeout=1.0)


+def test_tracker_stream_survives_idle_gap_between_sse_chunks():
+    first_chunk_sent = threading.Event()
+
+    class IdleStreamingChatHandler(http.server.BaseHTTPRequestHandler):
+        def log_message(self, format, *args):
+            pass
+
+        def do_POST(self):
+            if self.path != "/v1/chat/completions":
+                self.send_response(404)
+                self.end_headers()
+                return
+            self.rfile.read(int(self.headers.get("Content-Length", 0)))
+            self.send_response(200)
+            self.send_header("Content-Type", "text/event-stream; charset=utf-8")
+            self.end_headers()
+            first = json.dumps({
+                "choices": [{"delta": {"content": "hello"}}],
+            }).encode()
+            second = json.dumps({
+                "choices": [{"delta": {"content": " world"}}],
+            }).encode()
+            self.wfile.write(b"data: " + first + b"\n\n")
+            self.wfile.flush()
+            first_chunk_sent.set()
+            time.sleep(1.0)
+            self.wfile.write(b"data: " + second + b"\n\n")
+            self.wfile.write(b"data: [DONE]\n\n")
+            self.wfile.flush()
+
+    node = http.server.HTTPServer(("127.0.0.1", 0), IdleStreamingChatHandler)
+    node_thread = threading.Thread(target=node.serve_forever, daemon=True)
+    node_thread.start()
+    tracker = TrackerServer(heartbeat_timeout=60.0)
+    tracker_port = tracker.start()
+    response = None
+    try:
+        _post_json(
+            f"http://127.0.0.1:{tracker_port}/v1/nodes/register",
+            {"endpoint": f"http://127.0.0.1:{node.server_address[1]}",
+             "model": "idle-stream-model", "num_layers": 1,
+             "shard_start": 0, "shard_end": 0,
+             "hardware_profile": {}, "score": 1.0},
+        )
+        req = urllib.request.Request(
+            f"http://127.0.0.1:{tracker_port}/v1/chat/completions",
+            data=json.dumps({
+                "model": "idle-stream-model",
+                "stream": True,
+                "messages": [{"role": "user", "content": "hi"}],
+            }).encode(),
+            headers={"Content-Type": "application/json"},
+            method="POST",
+        )
+        response = urllib.request.urlopen(req, timeout=3.0)
+        assert response.readline().startswith(b"data:")
+        assert first_chunk_sent.wait(timeout=1.0)
+
+        remaining = response.read().splitlines()
+        assert b"data: [DONE]" in remaining
+    finally:
+        if response is not None:
+            response.close()
+        tracker.stop()
+        node.shutdown()
+        node.server_close()
+        node_thread.join(timeout=1.0)
+
+
 def test_tracker_dashboard_can_cancel_inflight_proxy():
    chunk_sent = threading.Event()
    release = threading.Event()