Files
SQLmem/src/sqlmem/stats.py
T

100 lines
3.6 KiB
Python

import sqlite3
import threading
from dataclasses import dataclass
class TableState:
"""Live processing state of a cached table (value of ``TableStats.state``)."""
LOADING = "loading" # a full load is in progress
REFRESHING = "refreshing" # an incremental (delta) refresh is in progress
READY = "ready" # cached and idle
STALE = "stale" # TTL expired / schedule slot passed — reloads on next access
ERROR = "error" # the last load failed
@dataclass(frozen=True)
class TableStats:
rows: int
columns: list[str]
# Persisted wall-clock of the last actual data write (full load / delta with rows).
# Survives restarts. Answers "when did the data last change?".
last_upsert: str | None
# In-memory (this process) wall-clock of the last time a refresh cycle ran for the
# table — bumped even when the cycle wrote nothing. Liveness signal; ``None`` until
# the first cycle runs after start. Answers "is the refresh loop alive?".
last_refresh: str | None = None
state: str = TableState.READY
tracking: str = "static" # "delta" | "ttl" | "schedule" | "static"
# Most recent load/refresh failure for this table, if any. ``consecutive_failures``
# resets to 0 on the next success, so > 0 means the table is currently failing.
last_error: str | None = None
last_error_at: str | None = None
consecutive_failures: int = 0
@dataclass(frozen=True)
class Stats:
hits: int
misses: int
refetches: int
tables: dict[str, TableStats]
errors: int = 0 # total load/refresh failures since start
db_size_bytes: int = 0 # on-disk cache file size (0 in memory mode)
class StatsCollector:
def __init__(self) -> None:
self._lock = threading.Lock()
self.hits = 0
self.misses = 0
self.refetches = 0
def record_hit(self) -> None:
with self._lock:
self.hits += 1
def record_miss(self) -> None:
with self._lock:
self.misses += 1
def record_refetch(self) -> None:
with self._lock:
self.refetches += 1
def snapshot(
self, conn: sqlite3.Connection, states: dict[str, str] | None = None
) -> Stats:
states = states or {}
with self._lock:
hits, misses, refetches = self.hits, self.misses, self.refetches
tables: dict[str, TableStats] = {}
cached: set[str] = set()
for table_name, row_count, last_upsert in conn.execute(
"SELECT table_name, row_count, last_refresh_at FROM _sqlmem_tables"
).fetchall():
cached.add(table_name)
columns = [
r[0]
for r in conn.execute(
"SELECT column_name FROM _sqlmem_columns WHERE table_name = ? ORDER BY column_name",
(table_name,),
).fetchall()
]
# last_refresh (run/liveness) is filled in by the engine from the
# in-memory last-run map; only the persisted write time is read here.
tables[table_name] = TableStats(
rows=row_count or 0,
columns=columns,
last_upsert=last_upsert,
state=states.get(table_name, TableState.READY),
)
# Surface tables that are mid-first-load (not yet in _sqlmem_tables) or failed.
for name, state in states.items():
if name not in cached and state in (TableState.LOADING, TableState.ERROR):
tables[name] = TableStats(rows=0, columns=[], last_upsert=None, state=state)
return Stats(hits=hits, misses=misses, refetches=refetches, tables=tables)