Files
Fenris/src/fenris/monitor.py
T
xavierkandCommandCodeBot e27052d09a Implement runit support for Fenris monitoring (issue #84)
Deliver end-to-end native monitoring path under runit with existing
CLI/TUI controls and truthful status, preserving systemd behavior.

Changes:
- Add init system abstraction layer (src/fenris/init_system.py) that
  detects systemd vs runit and provides unified interface for timer
  control, on-demand collection, and service state queries
- Create runit service files (units/runit/) with completion-relative
  5-minute cadence, 2-minute boot delay, bounded execution (90s),
  no catch-up, and serialized runs via flock
- Update monitor.py to use abstraction layer instead of direct systemctl
- Update status.py to use abstraction layer for service state queries
- Update all packaging scripts (deb, rpm) for init-system-aware setup
- Update Makefile to install runit service files alongside systemd units
- Add 46 tests for init system abstraction layer

Spec: ADR 0008, §8.4, §8.5, §8.6, §8.7, §8.8
Closes #84

Co-authored-by: CommandCodeBot <noreply@commandcode.ai>
2026-09-15 00:15:24 +05:30

243 lines
7.6 KiB
Python

#!/usr/bin/env python3
"""fenris-monitor: privileged helper for toggle, collect, and baseline operations.
This binary is the ONLY sanctioned control path for:
- enable/disable (toggle) with monitoring-period bookkeeping
- on-demand collection trigger
- baseline set/clear persistence
Polkit authorizes this binary under com.bongbetic.fenris.monitor (auth_admin).
Spec: §8.4, §8.5, §8.6, §8.7
When run as a script, uses the fenris package from the installed wheel.
"""
import argparse
import json
import os
import sys
from datetime import datetime, timezone
from pathlib import Path
# Package dependencies are vendored independently of the host Python minor
# version. Keep the venv fallback for the legacy development install.
VENV_DIR = Path("/opt/fenris")
if VENV_DIR.exists():
vendor_dir = VENV_DIR / "vendor"
if vendor_dir.is_dir():
sys.path.insert(0, str(vendor_dir))
else:
site_packages = next((VENV_DIR / "lib").glob("python*/site-packages"), None)
if site_packages:
sys.path.insert(0, str(site_packages))
from fenris.store import init_store, get_store_path
from fenris.monitoring_periods import (
ensure_period_open,
close_period,
get_open_period,
)
from fenris.init_system import (
enable_timer,
disable_timer,
collect_now,
)
DEFAULT_STORE_PATH = Path("/var/lib/fenris/observations.db")
def is_root() -> bool:
"""Check if running as root."""
return os.geteuid() == 0
def cmd_enable(args: argparse.Namespace) -> None:
"""Enable monitoring: enable timer + open monitoring period.
Idempotent matrix (§8.6):
- First-ever enable: opens a period at the enable moment
- Resume with open period: no-op (gap stays inside as unknown)
- Resume with no open period: opens a new row
"""
store_path = getattr(args, 'store_path', DEFAULT_STORE_PATH)
conn = init_store(store_path)
now = datetime.now(timezone.utc)
try:
# Open monitoring period if none exists (§8.6)
open_period = get_open_period(conn)
if open_period is None:
ensure_period_open(conn, now)
print("Monitoring period opened at", now.isoformat())
else:
print("Monitoring period already open (id=%d)" % open_period["id"])
# Enable the timer (init-system aware)
enable_timer(args.now)
finally:
conn.close()
def cmd_disable(args: argparse.Namespace) -> None:
"""Disable monitoring: disable timer + close monitoring period.
Idempotent matrix (§8.6):
- Pause with open period: closes it user_disabled
- Pause otherwise: no-op
"""
store_path = getattr(args, 'store_path', DEFAULT_STORE_PATH)
if not store_path.exists():
print("Error: Observation store not found at", store_path, file=sys.stderr)
sys.exit(1)
conn = init_store(store_path)
now = datetime.now(timezone.utc)
try:
# Close monitoring period if open (§8.6)
open_period = get_open_period(conn)
if open_period is not None:
close_period(conn, now, "user_disabled")
print("Monitoring period closed (id=%d)" % open_period["id"])
else:
print("No open monitoring period (no-op)")
# Disable the timer (init-system aware)
disable_timer(args.now)
finally:
conn.close()
def cmd_collect(args: argparse.Namespace) -> None:
"""Trigger on-demand collection.
Starts fenris-collect, blocks until exit, reports outcome.
Spec §8.7: fenris sample routes through fenris-monitor → collect,
which blocks until the collection exits; outcome reported synchronously.
"""
collect_now()
def cmd_baseline_set(args: argparse.Namespace) -> None:
"""Persist a baseline row after CLI-side validation.
Spec §8.4: fenris-monitor persists CLI-validated baseline rows.
Spec PR-14: baseline set persists through polkit-guarded helper.
"""
store_path = getattr(args, 'store_path', DEFAULT_STORE_PATH)
if not store_path.exists():
print("Error: Observation store not found at", store_path, file=sys.stderr)
sys.exit(1)
conn = init_store(store_path)
now = datetime.now(timezone.utc)
try:
# Parse and validate baseline data
data = json.loads(args.baseline_json)
required_fields = [
"tbw_terabytes",
"source_url",
"document_revision",
"entry_date",
"model_string",
"nominal_capacity_bytes",
]
for field in required_fields:
if field not in data:
print(f"Error: Missing required field: {field}", file=sys.stderr)
sys.exit(1)
# One active row replaced on edit (§6.2)
conn.execute("DELETE FROM endurance_baseline")
conn.execute(
"""
INSERT INTO endurance_baseline (
tbw_terabytes, source_url, document_revision,
entry_date, model_string, nominal_capacity_bytes,
validated_by, verified, created_at, updated_at
) VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?)
""",
(
data["tbw_terabytes"],
data["source_url"],
data["document_revision"],
data["entry_date"],
data["model_string"],
data["nominal_capacity_bytes"],
data.get("validated_by", "user"),
data.get("verified", False),
now.isoformat(),
now.isoformat(),
),
)
conn.commit()
print("Baseline persisted")
finally:
conn.close()
def cmd_baseline_clear(args: argparse.Namespace) -> None:
"""Clear the endurance baseline.
Spec PR-14: baseline clear persists through polkit-guarded helper.
"""
store_path = getattr(args, 'store_path', DEFAULT_STORE_PATH)
if not store_path.exists():
print("Error: Observation store not found at", store_path, file=sys.stderr)
sys.exit(1)
conn = init_store(store_path)
try:
conn.execute("DELETE FROM endurance_baseline")
conn.commit()
print("Baseline cleared")
finally:
conn.close()
def main() -> None:
parser = argparse.ArgumentParser(
prog="fenris-monitor",
description="Fenris privileged helper for toggle, collect, and baseline operations.",
)
subparsers = parser.add_subparsers(dest="command", required=True)
# enable/disable
enable_parser = subparsers.add_parser("enable", help="Enable monitoring")
enable_parser.add_argument(
"--now", action="store_true", help="Also start the timer immediately"
)
enable_parser.set_defaults(func=cmd_enable)
disable_parser = subparsers.add_parser("disable", help="Disable monitoring")
disable_parser.add_argument(
"--now", action="store_true", help="Also stop the timer immediately"
)
disable_parser.set_defaults(func=cmd_disable)
# collect
collect_parser = subparsers.add_parser("collect", help="Trigger on-demand collection")
collect_parser.set_defaults(func=cmd_collect)
# baseline
baseline_parser = subparsers.add_parser("baseline", help="Baseline operations")
baseline_sub = baseline_parser.add_subparsers(dest="baseline_action", required=True)
baseline_set = baseline_sub.add_parser("set", help="Persist baseline")
baseline_set.add_argument("baseline_json", help="Baseline JSON data")
baseline_set.set_defaults(func=cmd_baseline_set)
baseline_clear = baseline_sub.add_parser("clear", help="Clear baseline")
baseline_clear.set_defaults(func=cmd_baseline_clear)
args = parser.parse_args()
args.func(args)
if __name__ == "__main__":
main()