Files
ProductionDataBaseSync_Data…/src/sync/logging_setup.py
Misaka_Company 2ce03d21d9 Refine incremental sync audit observability
- Add per-cycle correlation ID ([cyc:xxxxxxxx]) threaded through Python
  logs and SQL audit tables for end-to-end traceability of any divergence.
- New ProductionDataBaseSync.SyncApplyRunLog table + @CycleID on usp_SyncApply
  for per-table apply auditing (pending/merged/deleted/applied, dead/error
  counts, duration). Audit write isolated in its own TRY/CATCH outside txn.
- Capture/cleanup phases now emit full detail: Insert->Delete downgrade
  warning with record_id/log_id, dedup_skipped as apply-stall signal,
  per-file summary, and access log-id ranges on cleanup.
- Queue health check surfaces error/dead rows with recent samples instead of
  silent accumulation (previously the top cause of data divergence).
- sql_writer uses INSERT...SELECT...WHERE NOT EXISTS for observable dedup;
  idle cycles lowered to DEBUG with periodic heartbeat.
- Backward compatible: old proc callers still work (CycleID nullable; legacy
  coarse-grained logging with one-time notice).

Excluded from this commit: CODE.md, build_code_doc.py (doc generation).
2026-07-31 17:10:23 +08:00

172 lines
6.6 KiB
Python

"""Logging configuration for the sync service.
Configures the root logger with a RotatingFileHandler (10 MB x 5, UTF-8) plus
a console StreamHandler. The level and log path come from ``cfg.logging``.
Every record written to the log file carries a cycle correlation id
(``[cyc:xxxxxxxx]``): ``sync.service.cycle`` allocates one per pass via
``set_cycle_id`` and ``_CycleIdFilter`` injects it into each record, so every
capture/apply/cleanup line of one pass -- and the matching
``SyncApplyRunLog.CycleID`` rows on SQL Server -- can be correlated with a
single grep. Outside a cycle (fullsync, compare, startup) the field is ``-``.
Log files are managed per-day: at startup any previously produced log
(including the project's own ``sync.log`` and NSSM's ``nssm_*.log`` captures)
is relocated into an ``Archive/`` subfolder next to the active log. Where a log
lacks a timestamp, a ``-YYYY-MM-DD`` suffix is added (derived from its first
log line, falling back to mtime) so historical files carry a date. The log
root therefore only ever shows the current day's ``sync.log``.
"""
import contextvars
import datetime
import logging
import logging.handlers
import os
import re
import shutil
_LOG_DATE_RE = re.compile(r"^(\d{4}-\d{2}-\d{2})")
# Current cycle correlation id ("-" when not inside a service cycle).
_cycle_id: contextvars.ContextVar[str] = contextvars.ContextVar(
"sync_cycle_id", default="-"
)
def set_cycle_id(cycle_id: str | None) -> None:
"""Set (or clear, with ``None``) the id stamped on every log record.
Called by ``sync.service.cycle`` at the start/end of each pass. The same
id is passed to ``usp_SyncApply`` so SQL-side ``SyncApplyRunLog`` rows can
be joined back to the exact log lines of the cycle that produced them.
"""
_cycle_id.set(cycle_id or "-")
class _CycleIdFilter(logging.Filter):
"""Inject the current cycle id into every record as ``record.cycle``.
Attached to the handlers (not the logger) so records emitted through any
module logger -- capture, cleanup, access_reader, ... -- are covered.
"""
def filter(self, record: logging.LogRecord) -> bool: # noqa: A003
record.cycle = _cycle_id.get()
return True
def _first_line_date(path: str) -> str | None:
"""Best-effort extraction of the first log line's YYYY-MM-DD date."""
try:
with open(path, "r", encoding="utf-8", errors="replace") as f:
for line in f:
m = _LOG_DATE_RE.match(line)
if m:
return m.group(1)
except OSError:
pass
return None
def _archive_completed_logs(log_dir: str, active_name: str):
"""Move already-produced logs out of *log_dir* into *log_dir*/Archive.
The active log (*active_name*) is left in place only when it belongs to the
current day; an older ``sync.log`` is archived (with a ``-YYYY-MM-DD``
suffix) so a fresh one can be opened. NSSM's own ``nssm_*.log`` captures are
timestamped already and are moved as-is. Moves are best-effort: files locked
by another process (e.g. NSSM's live handles) are skipped.
"""
archive_dir = os.path.join(log_dir, "Archive")
os.makedirs(archive_dir, exist_ok=True)
today = datetime.date.today()
for name in os.listdir(log_dir):
src = os.path.join(log_dir, name)
if not os.path.isfile(src):
continue
if name == "Archive":
continue
if not (name.endswith(".log") or ".log." in name):
continue
# Keep NSSM's live, currently-open handles in place.
if name in ("nssm_stderr.log", "nssm_stdout.log"):
continue
if name == active_name:
# Only archive the active log if it is from a previous day.
log_date = _first_line_date(src)
log_date = (
datetime.date.fromisoformat(log_date)
if log_date
else datetime.date.fromtimestamp(os.path.getmtime(src))
)
if log_date >= today:
continue # today's log: keep appending
new_name = f"sync-{log_date.strftime('%Y-%m-%d')}.log"
else:
new_name = name
dst = os.path.join(archive_dir, new_name)
if os.path.exists(dst):
stem, ext = os.path.splitext(new_name)
i = 2
while os.path.exists(os.path.join(archive_dir, f"{stem}({i}){ext}")):
i += 1
dst = os.path.join(archive_dir, f"{stem}({i}){ext}")
try:
shutil.move(src, dst)
except OSError:
# Locked by another process (e.g. NSSM holding the file open).
pass
def setup_logging(cfg_dict: dict | None):
"""Configure root logging from the ``cfg.logging`` dict.
``cfg_dict`` is ``SyncConfig.logging`` (a dict or None). ``level`` is a
logging-level name string (default ``"INFO"``); ``path`` is the log file
path (default ``"sync.log"``). The parent directory is created if missing,
and any previously produced logs are archived before the new handler opens.
"""
level = getattr(logging, (cfg_dict or {}).get("level", "INFO")) if cfg_dict else logging.INFO
path = (cfg_dict or {}).get("path", "sync.log")
log_dir = os.path.dirname(path) or "."
os.makedirs(log_dir, exist_ok=True)
# Archive everything from prior runs so the root only shows today's log.
_archive_completed_logs(log_dir, os.path.basename(path))
# Idempotent: drop any handlers already attached to the root logger before
# re-adding. setup_logging can be called from more than one entry point
# (e.g. main.py and service.run), and the old code unconditionally
# addHandler'd each time, stacking duplicate handlers so every log line was
# written twice. Clearing first means repeated calls always yield exactly
# one file handler + one console handler, regardless of caller.
root = logging.getLogger()
for old in list(root.handlers):
root.removeHandler(old)
try:
old.close()
except Exception:
pass
root.setLevel(level)
cycle_filter = _CycleIdFilter()
h = logging.handlers.RotatingFileHandler(
path, maxBytes=10 * 1024 * 1024, backupCount=5, encoding="utf-8"
)
h.addFilter(cycle_filter)
h.setFormatter(logging.Formatter(
"%(asctime)s %(levelname)s [%(name)s] [cyc:%(cycle)s] %(message)s"
))
root.addHandler(h)
sh = logging.StreamHandler()
sh.addFilter(cycle_filter)
# Console keeps the short format (fullsync/compare are interactive there).
sh.setFormatter(logging.Formatter("%(levelname)s %(message)s"))
root.addHandler(sh)