nas-burnin/app/database.py
Brandon Walter 066fbbc403
Some checks are pending
Security scan / pip-audit (push) Waiting to run
Security scan / bandit (push) Waiting to run
Security scan / gitleaks (push) Waiting to run
fix: address Codex audit findings (1.0.0-28)
Addresses 12 of 13 findings from the Codex tech-debt + security review
of versions 1.0.0-22 through 1.0.0-27. Item #5 (live pool re-check
before start_job) deferred — would add an SSH round-trip per start.

#1  Pool detection now treats zpool / lsblk / findmnt failures
    INDEPENDENTLY. Previously a single None blew away the whole map,
    so a host where lsblk lacks zfs_member info but zpool works would
    never lock pool members. Extended findmnt parser to recognise
    /dev/mapper/*, /dev/dm-*, /dev/md*, /dev/da*, /dev/ada* (LVM,
    devicemapper, MD RAID, FreeBSD CORE devnames).

#2  Admin role enforced on every settings mutation. New
    auth.require_admin() helper applied to GET /settings,
    POST /api/v1/settings, /test-smtp, /test-ssh. Previously any
    authenticated user (the CLI explicitly supports non-admin
    accounts) could rewrite SMTP/SSH/API secrets.

#3  First-user setup race closed. auth.create_user() now accepts
    bootstrap_only=True which wraps the existence check + insert in
    BEGIN IMMEDIATE so two concurrent /api/v1/auth/setup requests
    can't both create admin accounts during the bootstrap window.

#4  Case-insensitive uniqueness enforced via new
    `uniq_users_username_nocase` index. Login does NOCASE lookup so
    without this `Admin` and `admin` could coexist as distinct rows.

#6  New `session_cookie_secure` setting (default False for LAN/dev
    deploys, set True in production behind HTTPS) flips the session
    cookie's Secure flag. Defends against on-the-wire exposure when
    the dashboard is reachable over plain HTTP.

#7  Audit trail bound to authenticated identity. Burn-in start /
    cancel / unlock / drive reset all now use `_operator_for(request)`
    which reads `request.state.current_user.full_name|username`
    instead of the body's operator field. Logged-in users can no
    longer spoof attribution. Drive reset's literal-"operator"
    fallback (window._operator was never set) is also fixed by this.

#8  Login rate-limit race fixed. New `register_login_attempt()` is
    atomic check-AND-increment in synchronous code (no awaits inside),
    so a parallel burst can't slip past the threshold.
    `record_login_failure()` removed; `clear_login_failures()` now
    also drops any active lockout for a successful auth. Pre-existing
    bug where `tripped` was always False (so user_login_locked_out
    audit events never fired) also fixed.

#9  NVMe surface_validate post-format check now mirrors the SSH path:
    fails on FAILED health AND on real SMART attribute failures,
    soft-passes SSH-only failures (logged), surfaces warnings to the
    stage log without failing.

#10 retention.backup_db() now writes to `.tmp` then atomic-renames
    into the canonical daily slot — an interrupted backup leaves the
    tmp behind but doesn't corrupt the real snapshot. Scheduler marks
    last_run_date only on (prune AND backup) success so a transient
    failure gets retried within the 03:00 hour.

#11 /health DB probe now exercises the WRITE path via a temp-table
    INSERT/SELECT/COMMIT round-trip. Previously only read PRAGMA
    journal_mode + a row count, which silently passes on read-only
    mounts and broken-WAL conditions.

#12 security-scan.sh now fails loudly if `git fetch` or
    `git reset --hard origin/main` errors (was `|| true`, scanning
    stale code silently). pip-audit now runs in a throwaway
    python:3.12-slim container against requirements.txt instead of
    `docker exec`-ing into the live truenas-burnin container —
    cleaner separation, no transient package install on prod.

#13 Badblocks SSH stage no longer doubles its log_text. Previously
    appended every 20-line chunk during streaming AND the full
    accumulated output at end. Now only flushes the un-flushed tail
    (typically <20 lines). `result["output"]` stays in-memory only.

Verification: all 44 unit tests pass in container; /health 200;
security scan returns 0 findings; deployed maple build is green.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-02 18:48:16 -04:00

175 lines
6.8 KiB
Python

import aiosqlite
from pathlib import Path
from app.config import settings
SCHEMA = """
CREATE TABLE IF NOT EXISTS drives (
id INTEGER PRIMARY KEY AUTOINCREMENT,
truenas_disk_id TEXT UNIQUE NOT NULL,
devname TEXT NOT NULL,
serial TEXT,
model TEXT,
size_bytes INTEGER,
temperature_c INTEGER,
smart_health TEXT DEFAULT 'UNKNOWN',
last_seen_at TEXT NOT NULL,
last_polled_at TEXT NOT NULL,
notes TEXT,
location TEXT
);
CREATE TABLE IF NOT EXISTS smart_tests (
id INTEGER PRIMARY KEY AUTOINCREMENT,
drive_id INTEGER NOT NULL REFERENCES drives(id) ON DELETE CASCADE,
test_type TEXT NOT NULL CHECK(test_type IN ('short', 'long')),
state TEXT NOT NULL DEFAULT 'idle',
percent INTEGER DEFAULT 0,
truenas_job_id INTEGER,
started_at TEXT,
eta_at TEXT,
finished_at TEXT,
error_text TEXT,
UNIQUE(drive_id, test_type)
);
CREATE TABLE IF NOT EXISTS burnin_jobs (
id INTEGER PRIMARY KEY AUTOINCREMENT,
drive_id INTEGER NOT NULL REFERENCES drives(id),
profile TEXT NOT NULL,
state TEXT NOT NULL DEFAULT 'queued',
percent INTEGER DEFAULT 0,
stage_name TEXT,
operator TEXT NOT NULL,
created_at TEXT NOT NULL,
started_at TEXT,
finished_at TEXT,
error_text TEXT
);
CREATE TABLE IF NOT EXISTS burnin_stages (
id INTEGER PRIMARY KEY AUTOINCREMENT,
burnin_job_id INTEGER NOT NULL REFERENCES burnin_jobs(id) ON DELETE CASCADE,
stage_name TEXT NOT NULL,
state TEXT NOT NULL DEFAULT 'pending',
percent INTEGER DEFAULT 0,
started_at TEXT,
finished_at TEXT,
duration_seconds REAL,
error_text TEXT
);
CREATE TABLE IF NOT EXISTS audit_events (
id INTEGER PRIMARY KEY AUTOINCREMENT,
event_type TEXT NOT NULL,
drive_id INTEGER REFERENCES drives(id),
burnin_job_id INTEGER REFERENCES burnin_jobs(id),
operator TEXT,
message TEXT NOT NULL,
created_at TEXT NOT NULL DEFAULT (strftime('%Y-%m-%dT%H:%M:%fZ', 'now'))
);
CREATE INDEX IF NOT EXISTS idx_smart_drive_type ON smart_tests(drive_id, test_type);
CREATE INDEX IF NOT EXISTS idx_burnin_jobs_drive ON burnin_jobs(drive_id, state);
CREATE INDEX IF NOT EXISTS idx_burnin_stages_job ON burnin_stages(burnin_job_id);
CREATE INDEX IF NOT EXISTS idx_audit_events_job ON audit_events(burnin_job_id);
"""
# Migrations for existing databases that predate schema additions.
# Each entry is tried with try/except — SQLite raises OperationalError
# ("duplicate column name") if the column already exists, which is safe to ignore.
_MIGRATIONS = [
"ALTER TABLE drives ADD COLUMN notes TEXT",
"ALTER TABLE drives ADD COLUMN location TEXT",
# Stage 7: SSH command output + SMART attribute storage
"ALTER TABLE burnin_stages ADD COLUMN log_text TEXT",
"ALTER TABLE burnin_stages ADD COLUMN bad_blocks INTEGER DEFAULT 0",
"ALTER TABLE drives ADD COLUMN smart_attrs TEXT",
"ALTER TABLE smart_tests ADD COLUMN raw_output TEXT",
# Stage 8: track last reset time so dashboard burn-in col clears after reset
"ALTER TABLE drives ADD COLUMN last_reset_at TEXT",
# 1.0.0-15: pool-membership lock
"ALTER TABLE drives ADD COLUMN pool_name TEXT",
"ALTER TABLE drives ADD COLUMN pool_role TEXT",
"ALTER TABLE drives ADD COLUMN pool_seen_at TEXT",
# 1.0.0-19: enforce one active burn-in per drive at the storage layer.
# Closes the read-then-insert race in burnin.start_job — without this,
# two concurrent /api/v1/burnin/start requests for the same drive could
# both observe zero active jobs and both insert queued rows.
"""CREATE UNIQUE INDEX IF NOT EXISTS uniq_active_burnin_per_drive
ON burnin_jobs (drive_id) WHERE state IN ('queued', 'running')""",
# 1.0.0-22: app-level login (username + bcrypt password)
"""CREATE TABLE IF NOT EXISTS users (
id INTEGER PRIMARY KEY AUTOINCREMENT,
username TEXT UNIQUE NOT NULL,
password_hash TEXT NOT NULL,
full_name TEXT,
is_admin INTEGER NOT NULL DEFAULT 0,
created_at TEXT NOT NULL,
last_login_at TEXT
)""",
# 1.0.0-28: case-insensitive uniqueness. The base UNIQUE on username
# is case-sensitive but login does NOCASE — without this index two
# users `Admin` and `admin` could coexist and shadow each other.
"""CREATE UNIQUE INDEX IF NOT EXISTS uniq_users_username_nocase
ON users (username COLLATE NOCASE)""",
]
async def _run_migrations(db: aiosqlite.Connection) -> None:
for sql in _MIGRATIONS:
try:
await db.execute(sql)
except Exception:
pass # Column already exists — harmless
# Remove the old CHECK(profile IN ('quick','full')) constraint if present.
# SQLite can't ALTER a CHECK — requires a full table rebuild.
cur = await db.execute(
"SELECT sql FROM sqlite_master WHERE type='table' AND name='burnin_jobs'"
)
row = await cur.fetchone()
if row and "CHECK" in (row[0] or ""):
await db.executescript("""
PRAGMA foreign_keys=OFF;
CREATE TABLE burnin_jobs_new (
id INTEGER PRIMARY KEY AUTOINCREMENT,
drive_id INTEGER NOT NULL REFERENCES drives(id),
profile TEXT NOT NULL,
state TEXT NOT NULL DEFAULT 'queued',
percent INTEGER DEFAULT 0,
stage_name TEXT,
operator TEXT NOT NULL,
created_at TEXT NOT NULL,
started_at TEXT,
finished_at TEXT,
error_text TEXT
);
INSERT INTO burnin_jobs_new SELECT * FROM burnin_jobs;
DROP TABLE burnin_jobs;
ALTER TABLE burnin_jobs_new RENAME TO burnin_jobs;
CREATE INDEX IF NOT EXISTS idx_burnin_jobs_drive ON burnin_jobs(drive_id, state);
PRAGMA foreign_keys=ON;
""")
async def init_db() -> None:
Path(settings.db_path).parent.mkdir(parents=True, exist_ok=True)
async with aiosqlite.connect(settings.db_path) as db:
await db.execute("PRAGMA journal_mode=WAL")
await db.execute("PRAGMA foreign_keys=ON")
await db.executescript(SCHEMA)
await _run_migrations(db)
await db.commit()
async def get_db():
db = await aiosqlite.connect(settings.db_path)
db.row_factory = aiosqlite.Row
try:
await db.execute("PRAGMA journal_mode=WAL")
await db.execute("PRAGMA foreign_keys=ON")
yield db
finally:
await db.close()