TASK-032: Implement geo_cache retention policy and cleanup
Add automatic cleanup of stale geolocation cache entries to prevent unbounded database growth. Resolves the issue where unique IP addresses accumulated indefinitely in the geo_cache table, degrading query performance. ## Changes ### Database Schema (Migration 3) - Add 'last_seen' column to geo_cache table tracking last reference time - Existing entries default to current timestamp ### Repository Layer (geo_cache_repo.py) - Update upsert_entry() to set/refresh last_seen on insert/update - Update upsert_neg_entry() to set/refresh last_seen on negative cache hits - Update bulk_upsert_entries() to set/refresh last_seen in batch operations - Add delete_stale_entries(db, cutoff_iso) -> int for purging old entries ### Background Task (geo_cache_cleanup.py) - New APScheduler task that runs nightly (24-hour interval) - Calculates cutoff as 90 days ago from current time (UTC) - Deletes all entries with last_seen older than cutoff - Logs operation results (info when deleted > 0, debug when 0 deleted) - Configurable retention period via GEO_CACHE_RETENTION_DAYS constant ### Application Startup (startup.py) - Register geo_cache_cleanup task in scheduler during app startup - Placed after geo_cache_flush in task registration order ### Tests - Add delete_stale_entries test cases covering: * Removal of old entries beyond cutoff * No deletion when all entries are recent * Empty table edge case - Update existing test fixtures to include last_seen column - Add full test suite for cleanup task registration and execution ### Documentation - Architekture.md: Document cleanup task, update schema/diagram - Backend-Development.md: Add retention policy documentation ## Behavior When an IP is accessed, its last_seen is refreshed. After 90 days of no access, an IP is purged by the nightly cleanup. On next encounter, the IP is re-resolved from MaxMind MMDB or ip-api.com (if configured). This is acceptable because: 1. Stale geolocation data may become inaccurate over time 2. Re-resolution cost is minimal compared to unbounded storage growth 3. Active IPs maintain fresh data through their last_seen updates Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
This commit is contained in:
@@ -17,7 +17,8 @@ async def _create_geo_cache_table(db: aiosqlite.Connection) -> None:
|
||||
country_name TEXT,
|
||||
asn TEXT,
|
||||
org TEXT,
|
||||
cached_at TEXT NOT NULL DEFAULT (strftime('%Y-%m-%dT%H:%M:%fZ', 'now'))
|
||||
cached_at TEXT NOT NULL DEFAULT (strftime('%Y-%m-%dT%H:%M:%fZ', 'now')),
|
||||
last_seen TEXT NOT NULL DEFAULT (strftime('%Y-%m-%dT%H:%M:%fZ', 'now'))
|
||||
)
|
||||
"""
|
||||
)
|
||||
@@ -183,3 +184,82 @@ async def test_bulk_upsert_entries_and_neg_entries(tmp_path: Path) -> None:
|
||||
row = await cur.fetchone()
|
||||
assert row is not None
|
||||
assert int(row[0]) == 4
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_delete_stale_entries_removes_old_entries(tmp_path: Path) -> None:
|
||||
db_path = str(tmp_path / "geo_cache.db")
|
||||
async with aiosqlite.connect(db_path) as db:
|
||||
await _create_geo_cache_table(db)
|
||||
|
||||
# Insert entries with various last_seen times
|
||||
await db.execute(
|
||||
"INSERT INTO geo_cache (ip, country_code, last_seen) VALUES (?, ?, ?)",
|
||||
("1.1.1.1", "US", "2020-01-01T00:00:00Z"),
|
||||
)
|
||||
await db.execute(
|
||||
"INSERT INTO geo_cache (ip, country_code, last_seen) VALUES (?, ?, ?)",
|
||||
("2.2.2.2", "DE", "2024-12-01T00:00:00Z"),
|
||||
)
|
||||
await db.execute(
|
||||
"INSERT INTO geo_cache (ip, country_code, last_seen) VALUES (?, ?, ?)",
|
||||
("3.3.3.3", "FR", "2025-01-01T00:00:00Z"),
|
||||
)
|
||||
await db.commit()
|
||||
|
||||
async with aiosqlite.connect(db_path) as db:
|
||||
# Delete entries older than 2024-06-01
|
||||
deleted = await geo_cache_repo.delete_stale_entries(db, "2024-06-01T00:00:00Z")
|
||||
await db.commit()
|
||||
|
||||
assert deleted == 1
|
||||
|
||||
# Verify the correct entry was deleted
|
||||
async with aiosqlite.connect(db_path) as db, db.execute("SELECT ip FROM geo_cache ORDER BY ip") as cur:
|
||||
rows = await cur.fetchall()
|
||||
ips = [row[0] for row in rows]
|
||||
assert sorted(ips) == ["2.2.2.2", "3.3.3.3"]
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_delete_stale_entries_returns_zero_when_none_stale(tmp_path: Path) -> None:
|
||||
db_path = str(tmp_path / "geo_cache.db")
|
||||
async with aiosqlite.connect(db_path) as db:
|
||||
await _create_geo_cache_table(db)
|
||||
|
||||
# Insert entries with recent last_seen times
|
||||
await db.execute(
|
||||
"INSERT INTO geo_cache (ip, country_code, last_seen) VALUES (?, ?, ?)",
|
||||
("1.1.1.1", "US", "2025-01-01T00:00:00Z"),
|
||||
)
|
||||
await db.execute(
|
||||
"INSERT INTO geo_cache (ip, country_code, last_seen) VALUES (?, ?, ?)",
|
||||
("2.2.2.2", "DE", "2025-01-02T00:00:00Z"),
|
||||
)
|
||||
await db.commit()
|
||||
|
||||
async with aiosqlite.connect(db_path) as db:
|
||||
# Try to delete entries older than 2020-01-01 (all are newer)
|
||||
deleted = await geo_cache_repo.delete_stale_entries(db, "2020-01-01T00:00:00Z")
|
||||
await db.commit()
|
||||
|
||||
assert deleted == 0
|
||||
|
||||
# Verify no entries were deleted
|
||||
async with aiosqlite.connect(db_path) as db, db.execute("SELECT COUNT(*) FROM geo_cache") as cur:
|
||||
row = await cur.fetchone()
|
||||
assert row is not None
|
||||
assert int(row[0]) == 2
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_delete_stale_entries_with_empty_table(tmp_path: Path) -> None:
|
||||
db_path = str(tmp_path / "geo_cache.db")
|
||||
async with aiosqlite.connect(db_path) as db:
|
||||
await _create_geo_cache_table(db)
|
||||
|
||||
async with aiosqlite.connect(db_path) as db:
|
||||
deleted = await geo_cache_repo.delete_stale_entries(db, "2024-01-01T00:00:00Z")
|
||||
await db.commit()
|
||||
|
||||
assert deleted == 0
|
||||
|
||||
Reference in New Issue
Block a user