Compare commits
9 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| 6fb67f8615 | |||
| e70ae6f176 | |||
| a77f6d380c | |||
| 6aae2a1dab | |||
| 85ee0e1040 | |||
| c4f09e9ced | |||
| 64710fd4cd | |||
| 1f5e7465a3 | |||
| b290b21e23 |
+1
-1
@@ -14,4 +14,4 @@ Install options:
|
||||
"""
|
||||
|
||||
__all__ = ["__version__"]
|
||||
__version__ = "5.1.7"
|
||||
__version__ = "5.1.10"
|
||||
|
||||
@@ -60,6 +60,7 @@ class OSInfoPlugin(InfoPlugin):
|
||||
"python_version": platform.python_version(),
|
||||
"python_implementation": platform.python_implementation(),
|
||||
"hbc_version": hbc_version,
|
||||
"hbc_type": "full",
|
||||
}
|
||||
|
||||
# Add Linux-specific distribution info
|
||||
|
||||
+5
-6
@@ -144,17 +144,16 @@ def cmd_notify(args):
|
||||
url=f"{base_url}/plugins" if base_url else "",
|
||||
)
|
||||
|
||||
# Bypass min_level for explicit test sends; run async channels directly
|
||||
import asyncio
|
||||
from .notify import _send_matrix_async, _send_sms_voipms_async, _DRIVERS
|
||||
ch_type = channel_cfg.get("type", "")
|
||||
print(f"Sending via {args.channel} ({ch_type}): {title} — {args.message}")
|
||||
|
||||
if ch_type in ("matrix", "sms_voipms"):
|
||||
from .notify import _send_matrix_async, _send_sms_voipms_async
|
||||
driver_async = _send_matrix_async if ch_type == "matrix" else _send_sms_voipms_async
|
||||
ok = asyncio.run(driver_async(channel_cfg, notif))
|
||||
if ch_type == "matrix":
|
||||
ok = asyncio.run(_send_matrix_async(channel_cfg, notif))
|
||||
elif ch_type == "sms_voipms":
|
||||
ok = asyncio.run(_send_sms_voipms_async(channel_cfg, notif))
|
||||
else:
|
||||
from .notify import _DRIVERS
|
||||
driver = _DRIVERS.get(ch_type)
|
||||
if driver is None:
|
||||
print(f"Error: unknown channel type '{ch_type}'", file=sys.stderr)
|
||||
|
||||
@@ -1,7 +1,11 @@
|
||||
"""HTTP server implementation using aiohttp and jinja2."""
|
||||
|
||||
import asyncio
|
||||
import datetime
|
||||
import json
|
||||
import platform
|
||||
import socket
|
||||
import sys
|
||||
import time
|
||||
import urllib.parse
|
||||
import os
|
||||
@@ -111,6 +115,7 @@ async def start(
|
||||
This function is intended to be awaited inside the main asyncio event loop.
|
||||
"""
|
||||
get_now = get_now or (lambda: time.time())
|
||||
_start_epoch = time.time()
|
||||
|
||||
async def old_index(request):
|
||||
_require_auth_redirect(request)
|
||||
@@ -806,6 +811,48 @@ async def start(
|
||||
)
|
||||
return web.Response(text=body, content_type="text/html")
|
||||
|
||||
# -------------------------------------------------------------------------
|
||||
# About page
|
||||
# -------------------------------------------------------------------------
|
||||
|
||||
async def about_page(request):
|
||||
"""GET /about — version, runtime, and project information."""
|
||||
current_user, _ = _require_auth_redirect(request)
|
||||
pkg_dir = os.path.dirname(__file__)
|
||||
templates_dir = config.get("templates_dir", os.path.join(pkg_dir, "templates"))
|
||||
env = jinja2.Environment(loader=jinja2.FileSystemLoader(templates_dir))
|
||||
from hbd import __version__ as hbd_version
|
||||
|
||||
uptime_secs = int(time.time() - _start_epoch)
|
||||
days, rem = divmod(uptime_secs, 86400)
|
||||
hours, rem = divmod(rem, 3600)
|
||||
mins, secs = divmod(rem, 60)
|
||||
if days:
|
||||
uptime_str = f"{days}d {hours}h {mins}m"
|
||||
elif hours:
|
||||
uptime_str = f"{hours}h {mins}m {secs}s"
|
||||
else:
|
||||
uptime_str = f"{mins}m {secs}s"
|
||||
|
||||
start_dt = datetime.datetime.fromtimestamp(_start_epoch)
|
||||
start_time_str = start_dt.strftime("%Y-%m-%d %H:%M:%S")
|
||||
|
||||
tmpl = env.get_template("about.html")
|
||||
body = tmpl.render(
|
||||
title="About - Heartbeat",
|
||||
header="About",
|
||||
hbd_version=hbd_version,
|
||||
python_version=f"{sys.version_info.major}.{sys.version_info.minor}.{sys.version_info.micro} ({platform.python_implementation()})",
|
||||
server_hostname=socket.gethostname(),
|
||||
start_epoch=int(_start_epoch),
|
||||
start_time_str=start_time_str,
|
||||
uptime_str=uptime_str,
|
||||
host_count=len(hbdclass.Host.hosts),
|
||||
current_user=current_user.to_dict() if current_user else None,
|
||||
active_page="about",
|
||||
)
|
||||
return web.Response(text=body, content_type="text/html")
|
||||
|
||||
# -------------------------------------------------------------------------
|
||||
# Settings page (admin only)
|
||||
# -------------------------------------------------------------------------
|
||||
@@ -859,6 +906,7 @@ async def start(
|
||||
web.get("/live", live),
|
||||
web.get("/plugins", plugins_page),
|
||||
web.get("/alerts", alerts_page),
|
||||
web.get("/about", about_page),
|
||||
web.get("/profile", profile_page),
|
||||
web.get("/settings", settings_page),
|
||||
web.get("/static/{path:.*}", static),
|
||||
|
||||
+25
-53
@@ -15,7 +15,6 @@ their own ``notification_channels`` list. When no users are configured the
|
||||
server runs silently (no notifications sent).
|
||||
"""
|
||||
|
||||
import asyncio
|
||||
import asyncio
|
||||
import logging
|
||||
import smtplib
|
||||
@@ -30,13 +29,10 @@ from . import ws as ws_mod
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
msg_to_websockets = ws_mod.broadcast
|
||||
|
||||
# Module-level state set via setup()
|
||||
_config: dict = {}
|
||||
_loop: Optional[asyncio.AbstractEventLoop] = None
|
||||
|
||||
# Tracks which channels fired a WARNING/CRITICAL per host.
|
||||
# {host_name: set of channel_names} — used to route RECOVER to the same channels.
|
||||
@@ -73,11 +69,9 @@ class Notification:
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
def setup(cfg: dict, loop: Optional[asyncio.AbstractEventLoop] = None):
|
||||
"""Initialize notifier from configuration dict and event loop."""
|
||||
global _config, _loop
|
||||
"""Initialize notifier from configuration dict."""
|
||||
global _config
|
||||
_config = dict(cfg)
|
||||
if loop is not None:
|
||||
_loop = loop
|
||||
|
||||
|
||||
def reload_config(cfg: dict):
|
||||
@@ -299,17 +293,6 @@ async def _send_sms_voipms_async(channel_cfg: dict, notif: Notification) -> bool
|
||||
return False
|
||||
|
||||
|
||||
def _send_sms_voipms(channel_cfg: dict, notif: Notification) -> bool:
|
||||
"""Dispatch voip.ms SMS send onto the shared event loop."""
|
||||
if _loop is None:
|
||||
logger.warning("sms_voipms: event loop not available")
|
||||
return False
|
||||
future = asyncio.run_coroutine_threadsafe(_send_sms_voipms_async(channel_cfg, notif), _loop)
|
||||
try:
|
||||
return future.result(timeout=15)
|
||||
except Exception as e:
|
||||
logger.error("sms_voipms send timed out or failed: %s", e)
|
||||
return False
|
||||
|
||||
|
||||
async def _send_matrix_async(channel_cfg: dict, notif: Notification) -> bool:
|
||||
@@ -357,40 +340,23 @@ async def _send_matrix_async(channel_cfg: dict, notif: Notification) -> bool:
|
||||
await client.close()
|
||||
|
||||
|
||||
def _send_matrix(channel_cfg: dict, notif: Notification) -> bool:
|
||||
"""Dispatch matrix send onto the shared event loop."""
|
||||
if _loop is None:
|
||||
logger.warning("matrix: event loop not available")
|
||||
return False
|
||||
future = asyncio.run_coroutine_threadsafe(_send_matrix_async(channel_cfg, notif), _loop)
|
||||
try:
|
||||
return future.result(timeout=15)
|
||||
except Exception as e:
|
||||
logger.error("matrix send timed out or failed: %s", e)
|
||||
return False
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Channel dispatcher
|
||||
# Channel dispatcher (all async — sync drivers run in a thread executor)
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
# Sync drivers kept for `hbd notify` CLI usage (asyncio.run wraps them there).
|
||||
_DRIVERS = {
|
||||
"pushover": _send_pushover,
|
||||
"email": _send_email,
|
||||
"mattermost": _send_mattermost,
|
||||
"signal": _send_signal,
|
||||
"sms_voipms": _send_sms_voipms,
|
||||
"matrix": _send_matrix,
|
||||
}
|
||||
|
||||
_TIMEOUT = 15 # seconds per channel send
|
||||
|
||||
def _dispatch_to_channel(channel_name: str, channel_cfg: dict, notif: Notification) -> bool:
|
||||
"""Send *notif* to a single named channel, honouring min_level.
|
||||
|
||||
RECOVER always bypasses min_level — a recovery is always relevant if the
|
||||
channel was configured for any alerting (handles the restart-then-recover case
|
||||
where _alerted_channels is empty and we fall through to the normal loop).
|
||||
"""
|
||||
async def _dispatch_to_channel(channel_name: str, channel_cfg: dict, notif: Notification) -> bool:
|
||||
"""Send *notif* to a single named channel, honouring min_level."""
|
||||
level = notif.level.upper()
|
||||
if level != "RECOVER":
|
||||
min_level = channel_cfg.get("min_level", "WARNING").upper()
|
||||
@@ -398,14 +364,24 @@ def _dispatch_to_channel(channel_name: str, channel_cfg: dict, notif: Notificati
|
||||
logger.debug(
|
||||
"channel '%s': skipping level %s (min_level=%s)", channel_name, level, min_level
|
||||
)
|
||||
return True # not an error — filtered intentionally
|
||||
return True # filtered intentionally
|
||||
|
||||
ch_type = channel_cfg.get("type", "")
|
||||
driver = _DRIVERS.get(ch_type)
|
||||
if driver is None:
|
||||
try:
|
||||
if ch_type == "matrix":
|
||||
return await asyncio.wait_for(_send_matrix_async(channel_cfg, notif), timeout=_TIMEOUT)
|
||||
if ch_type == "sms_voipms":
|
||||
return await asyncio.wait_for(_send_sms_voipms_async(channel_cfg, notif), timeout=_TIMEOUT)
|
||||
sync_driver = _DRIVERS.get(ch_type)
|
||||
if sync_driver is None:
|
||||
logger.warning("unknown channel type '%s' for channel '%s'", ch_type, channel_name)
|
||||
return False
|
||||
return driver(channel_cfg, notif)
|
||||
return await asyncio.wait_for(
|
||||
asyncio.to_thread(sync_driver, channel_cfg, notif), timeout=_TIMEOUT
|
||||
)
|
||||
except asyncio.TimeoutError:
|
||||
logger.error("channel '%s' timed out after %ds", channel_name, _TIMEOUT)
|
||||
return False
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
@@ -419,7 +395,7 @@ def _build_url(host_name: str) -> str:
|
||||
return f"{base_url}/plugins#{host_name}"
|
||||
|
||||
|
||||
def send_notification(host_name: str, notif: Notification) -> dict:
|
||||
async def send_notification(host_name: str, notif: Notification) -> dict:
|
||||
"""Dispatch *notif* to all managers/owner of *host_name*.
|
||||
|
||||
Looks up the host's owner + managers, resolves each user's
|
||||
@@ -469,16 +445,12 @@ def send_notification(host_name: str, notif: Notification) -> dict:
|
||||
if not channel_cfg:
|
||||
continue
|
||||
try:
|
||||
ch_type = channel_cfg.get("type", "")
|
||||
driver = _DRIVERS.get(ch_type)
|
||||
if driver:
|
||||
ok = driver(channel_cfg, notif)
|
||||
ok = await _dispatch_to_channel(channel_name, channel_cfg, notif)
|
||||
results[channel_name] = ok
|
||||
if ok:
|
||||
logger.info("recover sent to channel '%s': %s", channel_name, notif.title)
|
||||
except Exception as e:
|
||||
logger.error("error sending recover to channel '%s': %s", channel_name, e)
|
||||
# Clear the alerted set once recovery is delivered
|
||||
del _alerted_channels[host_name]
|
||||
return results
|
||||
|
||||
@@ -489,14 +461,14 @@ def send_notification(host_name: str, notif: Notification) -> dict:
|
||||
continue
|
||||
for channel_name in user.notification_channels:
|
||||
if channel_name in results:
|
||||
continue # already dispatched to this channel this notification
|
||||
continue
|
||||
channel_cfg = global_channels.get(channel_name)
|
||||
if not channel_cfg:
|
||||
logger.warning("channel '%s' not defined in notification_channels", channel_name)
|
||||
results[channel_name] = False
|
||||
continue
|
||||
try:
|
||||
ok = _dispatch_to_channel(channel_name, channel_cfg, notif)
|
||||
ok = await _dispatch_to_channel(channel_name, channel_cfg, notif)
|
||||
results[channel_name] = ok
|
||||
if ok:
|
||||
logger.info("notification sent to channel '%s': %s", channel_name, notif.title)
|
||||
|
||||
@@ -0,0 +1,199 @@
|
||||
<!DOCTYPE html>
|
||||
<html>
|
||||
{% include 'head.html' %}
|
||||
|
||||
<style>
|
||||
html, body { overflow: visible; }
|
||||
|
||||
.container {
|
||||
max-width: 700px;
|
||||
margin: 0 auto;
|
||||
}
|
||||
|
||||
h1 {
|
||||
color: #333;
|
||||
margin-bottom: 4px;
|
||||
font-size: 1.5em;
|
||||
}
|
||||
|
||||
.subtitle {
|
||||
color: #666;
|
||||
margin-bottom: 24px;
|
||||
font-size: 0.9em;
|
||||
}
|
||||
|
||||
.section {
|
||||
background: #fff;
|
||||
border-radius: 8px;
|
||||
box-shadow: 0 1px 6px rgba(0,0,0,0.1);
|
||||
padding: 20px 24px;
|
||||
margin-bottom: 20px;
|
||||
}
|
||||
|
||||
.section h2 {
|
||||
font-size: 1em;
|
||||
font-weight: 700;
|
||||
color: #333;
|
||||
margin: 0 0 16px;
|
||||
padding-bottom: 10px;
|
||||
border-bottom: 1px solid #eee;
|
||||
text-transform: uppercase;
|
||||
letter-spacing: 0.5px;
|
||||
}
|
||||
|
||||
.info-row {
|
||||
display: flex;
|
||||
align-items: baseline;
|
||||
padding: 8px 0;
|
||||
border-bottom: 1px solid #f5f5f5;
|
||||
font-size: 0.9em;
|
||||
}
|
||||
.info-row:last-child { border-bottom: none; }
|
||||
|
||||
.info-label {
|
||||
width: 160px;
|
||||
flex-shrink: 0;
|
||||
color: #666;
|
||||
font-size: 0.88em;
|
||||
}
|
||||
|
||||
.info-value {
|
||||
color: #222;
|
||||
word-break: break-all;
|
||||
}
|
||||
|
||||
.info-value a {
|
||||
color: #0066cc;
|
||||
text-decoration: none;
|
||||
}
|
||||
.info-value a:hover { text-decoration: underline; }
|
||||
|
||||
.version-badge {
|
||||
display: inline-block;
|
||||
padding: 3px 12px;
|
||||
background: #e8f0fe;
|
||||
color: #1a73e8;
|
||||
border-radius: 12px;
|
||||
font-size: 0.85em;
|
||||
font-weight: 600;
|
||||
font-family: monospace;
|
||||
}
|
||||
|
||||
.hb-logo {
|
||||
font-size: 2.5em;
|
||||
font-weight: 700;
|
||||
color: #0066cc;
|
||||
letter-spacing: -1px;
|
||||
margin-bottom: 6px;
|
||||
}
|
||||
|
||||
.hb-tagline {
|
||||
color: #555;
|
||||
font-size: 0.95em;
|
||||
}
|
||||
|
||||
.logo-section {
|
||||
display: flex;
|
||||
align-items: center;
|
||||
gap: 20px;
|
||||
padding: 8px 0 4px;
|
||||
}
|
||||
|
||||
.logo-text { flex: 1; }
|
||||
</style>
|
||||
|
||||
<body>
|
||||
{% include 'nav.html' %}
|
||||
|
||||
<div class="container">
|
||||
<h1>{{ header }}</h1>
|
||||
<p class="subtitle">Heartbeat monitoring system</p>
|
||||
|
||||
<div class="section">
|
||||
<div class="logo-section">
|
||||
<div class="logo-text">
|
||||
<div class="hb-logo">Heartbeat</div>
|
||||
<div class="hb-tagline">Lightweight host monitoring over UDP</div>
|
||||
</div>
|
||||
<span class="version-badge">v{{ hbd_version }}</span>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<div class="section">
|
||||
<h2>Version</h2>
|
||||
<div class="info-row">
|
||||
<span class="info-label">Server version</span>
|
||||
<span class="info-value">{{ hbd_version }}</span>
|
||||
</div>
|
||||
<div class="info-row">
|
||||
<span class="info-label">Python</span>
|
||||
<span class="info-value">{{ python_version }}</span>
|
||||
</div>
|
||||
<div class="info-row">
|
||||
<span class="info-label">License</span>
|
||||
<span class="info-value">MIT</span>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<div class="section">
|
||||
<h2>Runtime</h2>
|
||||
<div class="info-row">
|
||||
<span class="info-label">Host</span>
|
||||
<span class="info-value">{{ server_hostname }}</span>
|
||||
</div>
|
||||
<div class="info-row">
|
||||
<span class="info-label">Started</span>
|
||||
<span class="info-value">{{ start_time_str }}</span>
|
||||
</div>
|
||||
<div class="info-row">
|
||||
<span class="info-label">Uptime</span>
|
||||
<span class="info-value" id="uptime-value">{{ uptime_str }}</span>
|
||||
</div>
|
||||
<div class="info-row">
|
||||
<span class="info-label">Hosts monitored</span>
|
||||
<span class="info-value">{{ host_count }}</span>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<div class="section">
|
||||
<h2>Contact & Source</h2>
|
||||
<div class="info-row">
|
||||
<span class="info-label">Author</span>
|
||||
<span class="info-value">Andreas Wrede</span>
|
||||
</div>
|
||||
<div class="info-row">
|
||||
<span class="info-label">Email</span>
|
||||
<span class="info-value"><a href="mailto:aew@wrede.ca">aew@wrede.ca</a></span>
|
||||
</div>
|
||||
<div class="info-row">
|
||||
<span class="info-label">Repository</span>
|
||||
<span class="info-value"><a href="https://git.wrede.ca/andreas/heartbeat" target="_blank" rel="noopener">git.wrede.ca/andreas/heartbeat</a></span>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
</div>
|
||||
|
||||
<script>
|
||||
(function() {
|
||||
var startEpoch = {{ start_epoch }};
|
||||
var el = document.getElementById('uptime-value');
|
||||
if (!el) return;
|
||||
function fmt(s) {
|
||||
var d = Math.floor(s / 86400);
|
||||
var h = Math.floor((s % 86400) / 3600);
|
||||
var m = Math.floor((s % 3600) / 60);
|
||||
var sec = s % 60;
|
||||
if (d > 0) return d + 'd ' + h + 'h ' + m + 'm';
|
||||
if (h > 0) return h + 'h ' + m + 'm ' + sec + 's';
|
||||
return m + 'm ' + sec + 's';
|
||||
}
|
||||
function tick() {
|
||||
var up = Math.floor(Date.now() / 1000 - startEpoch);
|
||||
el.textContent = fmt(up);
|
||||
}
|
||||
tick();
|
||||
setInterval(tick, 1000);
|
||||
})();
|
||||
</script>
|
||||
</body>
|
||||
</html>
|
||||
@@ -9,7 +9,7 @@
|
||||
margin: 0 auto;
|
||||
}
|
||||
|
||||
h1 { color: #333; margin-bottom: 10px; font-size: 1.5em; }
|
||||
h1 { color: #333; margin-bottom: 5px; margin-top: 15px; font-size: 1.5em; }
|
||||
|
||||
.subtitle {
|
||||
color: #666;
|
||||
|
||||
@@ -15,6 +15,7 @@
|
||||
body {
|
||||
margin: 0;
|
||||
padding: 10px;
|
||||
padding-top: 60px;
|
||||
background: #f5f5f5;
|
||||
}
|
||||
h1 { font-size: 1.5em; color: #333; margin: 0 0 5px; }
|
||||
@@ -23,11 +24,14 @@
|
||||
|
||||
/* Navigation bar — shared across all pages */
|
||||
.nav {
|
||||
position: fixed;
|
||||
top: 0;
|
||||
left: 0;
|
||||
right: 0;
|
||||
z-index: 200;
|
||||
background: #fff;
|
||||
padding: 6px 12px;
|
||||
margin-bottom: 10px;
|
||||
box-shadow: 0 2px 4px rgba(0,0,0,.1);
|
||||
border-radius: 4px;
|
||||
display: flex;
|
||||
align-items: center;
|
||||
justify-content: space-between;
|
||||
|
||||
@@ -45,6 +45,7 @@
|
||||
h1 {
|
||||
color: #333;
|
||||
margin-bottom: 5px;
|
||||
margin-top: 15px;
|
||||
font-size: 1.5em;
|
||||
}
|
||||
|
||||
|
||||
@@ -9,6 +9,7 @@
|
||||
{% if current_user and current_user.admin %}
|
||||
<a href="/settings"{% if active_page == "settings" %} class="active"{% endif %}>Settings</a>
|
||||
{% endif %}
|
||||
<a href="/about"{% if active_page == "about" %} class="active"{% endif %}>About</a>
|
||||
</div>
|
||||
<div class="nav-clock" title="Click for full-screen clock">
|
||||
<canvas id="swiss-clock" width="44" height="44"></canvas>
|
||||
|
||||
@@ -16,6 +16,7 @@
|
||||
h1 {
|
||||
color: #333;
|
||||
margin-bottom: 5px;
|
||||
margin-top: 15px;
|
||||
font-size: 1.5em;
|
||||
}
|
||||
|
||||
|
||||
@@ -9,7 +9,7 @@
|
||||
max-width: 960px;
|
||||
}
|
||||
|
||||
h1 { color: #333; margin-bottom: 4px; font-size: 1.5em; }
|
||||
h1 { color: #333; margin-bottom: 5px; margin-top: 15px; font-size: 1.5em; }
|
||||
.subtitle { color: #666; margin-bottom: 24px; font-size: 0.9em; }
|
||||
|
||||
/* ---- Sidebar + content layout ---- */
|
||||
@@ -23,7 +23,7 @@
|
||||
width: 180px;
|
||||
flex-shrink: 0;
|
||||
position: sticky;
|
||||
top: 20px;
|
||||
top: 60px;
|
||||
}
|
||||
|
||||
.sidebar-nav a {
|
||||
|
||||
+4
-11
@@ -987,18 +987,14 @@ class ThresholdChecker:
|
||||
value: Any,
|
||||
):
|
||||
"""Send notification and log to journal/eventlog."""
|
||||
try:
|
||||
notify_mod.send_notification(
|
||||
asyncio.get_event_loop().create_task(notify_mod.send_notification(
|
||||
host_name,
|
||||
notify_mod.Notification(
|
||||
title=f"[{lvl}] {host_name}",
|
||||
body=message,
|
||||
level=lvl,
|
||||
),
|
||||
)
|
||||
logger.info("Notification sent: %s", message)
|
||||
except Exception as e:
|
||||
logger.error("Failed to send notification: %s", e)
|
||||
))
|
||||
|
||||
# Log to journal
|
||||
if self.journal is not None:
|
||||
@@ -1195,20 +1191,17 @@ class ThresholdChecker:
|
||||
else:
|
||||
message = f"REMINDER ({alert_state.level.name}): {host_name} - {metric_path} = {value} (ongoing for {int(now - alert_state.since)}s)"
|
||||
|
||||
try:
|
||||
notify_mod.send_notification(
|
||||
asyncio.get_event_loop().create_task(notify_mod.send_notification(
|
||||
host_name,
|
||||
notify_mod.Notification(
|
||||
title=f"[REMINDER/{alert_state.level.name}] {host_name}",
|
||||
body=message,
|
||||
level=alert_state.level.name,
|
||||
),
|
||||
)
|
||||
))
|
||||
alert_state.last_notification = now
|
||||
alert_state.notification_count += 1
|
||||
logger.info("Re-notification sent: %s", message)
|
||||
except Exception as e:
|
||||
logger.error("Failed to send re-notification: %s", e)
|
||||
|
||||
def get_active_alerts(self, alert_states: Dict[str, AlertState]) -> list:
|
||||
"""
|
||||
|
||||
+10
-10
@@ -211,10 +211,10 @@ def _make_timer_callbacks(uname, host, ctx):
|
||||
connection.newstate(connection.__class__.OVERDUE, now, cfg.get("grace", 2))
|
||||
msg = f"{connection.afam} overdue"
|
||||
eventlog(uname, "CRITICAL", msg)
|
||||
notify_mod.send_notification(
|
||||
asyncio.create_task(notify_mod.send_notification(
|
||||
uname,
|
||||
notify_mod.Notification(title=f"[CRITICAL] {uname}", body=msg, level="CRITICAL"),
|
||||
)
|
||||
))
|
||||
# Track in alert_states so the Alerts Dashboard shows this
|
||||
_set_connectivity_alert(host, connection.afam, "CRITICAL")
|
||||
if threshold_checker:
|
||||
@@ -407,10 +407,10 @@ def handle_datagram(msg: dict, addr, transport, ctx: dict):
|
||||
|
||||
if res:
|
||||
eventlog(uname, "WARNING", res)
|
||||
notify_mod.send_notification(
|
||||
asyncio.create_task(notify_mod.send_notification(
|
||||
uname,
|
||||
notify_mod.Notification(title=f"[WARNING] {uname}", body=res, level="WARNING"),
|
||||
)
|
||||
))
|
||||
|
||||
interval = int(msg.get("interval", 0) or 0)
|
||||
shutdown = msg.get("shutdown", 0)
|
||||
@@ -420,10 +420,10 @@ def handle_datagram(msg: dict, addr, transport, ctx: dict):
|
||||
|
||||
if boot:
|
||||
eventlog(uname, "INFO", "booted")
|
||||
notify_mod.send_notification(
|
||||
asyncio.create_task(notify_mod.send_notification(
|
||||
uname,
|
||||
notify_mod.Notification(title=f"[INFO] {uname}", body=f"{host.name} booted", level="INFO"),
|
||||
)
|
||||
))
|
||||
if message:
|
||||
eventlog(uname, "INFO", "msg: %s" % message, service=service)
|
||||
|
||||
@@ -440,10 +440,10 @@ def handle_datagram(msg: dict, addr, transport, ctx: dict):
|
||||
else:
|
||||
m = "%s back after being %s for %s" % (conn.afam, lasts, dur(d))
|
||||
eventlog(uname, "RECOVER", m)
|
||||
notify_mod.send_notification(
|
||||
asyncio.create_task(notify_mod.send_notification(
|
||||
uname,
|
||||
notify_mod.Notification(title=f"[RECOVER] {uname}", body=m, level="RECOVER"),
|
||||
)
|
||||
))
|
||||
|
||||
if boot or newh:
|
||||
host.upcount = host.doesack
|
||||
@@ -453,10 +453,10 @@ def handle_datagram(msg: dict, addr, transport, ctx: dict):
|
||||
if shutdown:
|
||||
m = "%s shutdown" % conn.afam
|
||||
eventlog(uname, "INFO", m)
|
||||
notify_mod.send_notification(
|
||||
asyncio.create_task(notify_mod.send_notification(
|
||||
uname,
|
||||
notify_mod.Notification(title=f"[INFO] {uname}", body=m, level="INFO"),
|
||||
)
|
||||
))
|
||||
conn.newstate(hbdcls.Connection.DOWN, now)
|
||||
_set_connectivity_alert(host, conn.afam, "CRITICAL")
|
||||
|
||||
|
||||
+4
-1
@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
|
||||
|
||||
[project]
|
||||
name = "hbd"
|
||||
version = "5.1.7"
|
||||
version = "5.1.10"
|
||||
description = "Heartbeat monitoring system — client (hbc) and server (hbd)"
|
||||
readme = "README.md"
|
||||
requires-python = ">=3.11"
|
||||
@@ -34,6 +34,9 @@ server = [
|
||||
"matrix-nio>=0.24",
|
||||
]
|
||||
|
||||
# Minimal client — hbc_mini only, no external dependencies
|
||||
mini = []
|
||||
|
||||
# Install both client and server
|
||||
all = [
|
||||
"hbd[client,server]",
|
||||
|
||||
@@ -4,12 +4,14 @@ set -e
|
||||
uv version --bump patch
|
||||
VER=$(uv version --short)
|
||||
sed -i".bak" "s/__version__ = \"[0-9.]*\"\(.*\)$/__version__ = \"$VER\"\1/" hbd/__init__.py
|
||||
sed -i".bak" "s/__version__ = \"[0-9.]*\"\(.*\)$/__version__ = \"$VER\"\1/" scripts/hbc_mini.py
|
||||
|
||||
# commit pyproject.toml
|
||||
git commit -m "version $VER" pyproject.toml hbd/__init__.py
|
||||
git commit -m "version $VER" pyproject.toml hbd/__init__.py scripts/hbc_mini.py
|
||||
git push
|
||||
# tag version
|
||||
git tag -a v$VER -m "Version $VER"
|
||||
git push --tags
|
||||
|
||||
rm hbd/__init__.py.bak
|
||||
rm scripts/hbc_mini.py.bak
|
||||
|
||||
+47
-12
@@ -12,11 +12,15 @@
|
||||
set -e
|
||||
what=$1
|
||||
on_ha=0
|
||||
where=""
|
||||
venv=""
|
||||
prog=$(realpath $0)
|
||||
[ "$2" = "HA" ] && on_ha=1
|
||||
[ -z "$what" ] && what="client"
|
||||
|
||||
if [ -d /homeassistant ]; then
|
||||
echo "cannot install in HA, running \"docker exec homeassistant $0 $@\""
|
||||
docker exec homeassistant $0 $@
|
||||
echo "HA, running \"docker exec homeassistant $prog $@\""
|
||||
docker exec homeassistant $prog $@ HA
|
||||
rc=$?
|
||||
if [ $rc -ne 0 ]; then
|
||||
echo "Failed to install heartbeat in HA, please check the logs for more details"
|
||||
@@ -24,11 +28,11 @@ if [ -d /homeassistant ]; then
|
||||
fi
|
||||
exit 0
|
||||
fi
|
||||
if [ -d /config ]; then
|
||||
echo "Installing on HA"
|
||||
|
||||
if [ $on_ha -eq 1 ]; then
|
||||
echo "Installing under docker on Home Assistant OS, using /config/bin for executables and /config/venvs for virtual environments "
|
||||
where="/config/bin"
|
||||
venv="/config/venvs"
|
||||
on_ha=1
|
||||
else
|
||||
if [ ! -d $HOME/.local/bin ] && [ ! -d $HOME/bin ]; then
|
||||
echo "No suitable bin directory found in PATH, please add either $HOME/.local/bin or $HOME/bin to your PATH"
|
||||
@@ -43,18 +47,23 @@ else
|
||||
echo "No suitable bin directory found in PATH, please add either $HOME/.local/bin or $HOME/bin to your PATH"
|
||||
exit 1
|
||||
fi
|
||||
if [ "$what" = "mini" ]; then
|
||||
venv=""
|
||||
else
|
||||
venv="$HOME/venvs"
|
||||
fi
|
||||
fi
|
||||
|
||||
echo "Installing heartbeat $what"
|
||||
|
||||
if [ ! -d $venv/hbd ]; then
|
||||
if [ "$venv" != "" ] && [ ! -d $venv/hbd ]; then
|
||||
set +e
|
||||
python3 -m pip --version > /dev/null 2>&1
|
||||
rc=$?
|
||||
set -e
|
||||
arg=""
|
||||
if [ $rc -ne 0 ]; then
|
||||
# truenas does not have pip installed by default, so we need to fetch get-pip.py and install pip
|
||||
# some systems do not have pip installed by default, so we need to fetch get-pip.py and install pip
|
||||
echo "pip is not installed, fetching get-pip.py and installing pip"
|
||||
arg="--without-pip"
|
||||
fi
|
||||
@@ -74,19 +83,39 @@ if [ ! -d $venv/hbd ]; then
|
||||
deactivate
|
||||
fi
|
||||
|
||||
. $venv/hbd/bin/activate
|
||||
python3 -mpip install --upgrade --index-url https://git.wrede.ca/api/packages/andreas/pypi/simple/ --extra-index-url https://pypi.org/simple hbd[$what]
|
||||
if [ -z "$venv" ]; then
|
||||
echo "Installing heartbeat $what globally"
|
||||
else
|
||||
echo "Installing heartbeat $what in virtual environment $venv/hbd"
|
||||
. $venv/hbd/bin/activate
|
||||
fi
|
||||
if [ "$what" = "mini" ]; then
|
||||
echo "Installing hbc mini, which has no external dependencies and is meant for quick setup and testing. For the full client with all features, please run this script with the 'client' argument."
|
||||
curl -s -o $where/hbc_mini https://git.wrede.ca/andreas/heartbeat/raw/branch/master/scripts/hbc_mini.py
|
||||
chmod +x $where/hbc_mini
|
||||
else
|
||||
echo "Installing heartbeat $what, which includes the full client with all features. If you want to install the minimal client with no external dependencies, please run this script with the 'mini' argument."
|
||||
python3 -mpip install --upgrade --index-url https://git.wrede.ca/api/packages/andreas/pypi/simple/ --extra-index-url https://pypi.org/simple hbd[$what]
|
||||
fi
|
||||
|
||||
if [ "$what" = "server" ]; then
|
||||
rm -f $where/hbd
|
||||
ln -sf $(which hbd) $where/hbd
|
||||
echo "hbd installed, you can run it with \"$where/hbd\" or \"hbd\" if $where is in your PATH"
|
||||
else
|
||||
elif [ "$what" = "client" ]; then
|
||||
hbc_path=$(which hbc)
|
||||
if [ -z "$hbc_path" ]; then
|
||||
echo "hbc not found in PATH, installation failed"
|
||||
exit 1
|
||||
fi
|
||||
if [ "$hbc_path" != "$where/hbc" ]; then
|
||||
rm -f $where/hbc
|
||||
ln -sf $(which hbc) $where/hbc
|
||||
# rm -f $where/hb_install.sh
|
||||
cp "$0" $where/hb_install.sh
|
||||
fi
|
||||
if [ "$prog" != "$where/hb_install.sh" ]; then
|
||||
cp "$prog" $where/hb_install.sh
|
||||
chmod +x $where/hb_install.sh
|
||||
fi
|
||||
if [ $on_ha -eq 1 ]; then
|
||||
echo "restarting hbc "
|
||||
job=$(grep run_hbc configuration.yaml | sed 's/run_hbc://')
|
||||
@@ -94,4 +123,10 @@ else
|
||||
else
|
||||
echo "hbc installed, you can run it with \"$where/hbc\" or \"hbc\" if $where is in your PATH"
|
||||
fi
|
||||
elif [ "$what" = "mini" ]; then
|
||||
hbc_path=$(which hbc_mini)
|
||||
if [ "$hbc_path" != "$where/hbc_mini" ]; then
|
||||
ln -sf $hbc_path $where/hbc_mini
|
||||
fi
|
||||
echo "hbc mini installed, you can run it with \"$where/hbc_mini\" or \"hbc_mini\" if $where is in your PATH"
|
||||
fi
|
||||
|
||||
+41
-22
@@ -40,6 +40,9 @@ from logging.handlers import SysLogHandler
|
||||
from pathlib import Path
|
||||
from typing import Any, Dict, List, Optional, Tuple
|
||||
|
||||
# updated by scripts/bumpminor.sh
|
||||
__version__ = "5.1.10"
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Protocol (mirrors hbd/common/proto.py)
|
||||
# ---------------------------------------------------------------------------
|
||||
@@ -233,6 +236,8 @@ class OSInfoPlugin(InfoPlugin):
|
||||
"machine": platform.machine(),
|
||||
"architecture": platform.architecture()[0],
|
||||
"python_version": platform.python_version(),
|
||||
"hbc_version": __version__,
|
||||
"hbc_type": "mini",
|
||||
}
|
||||
if platform.system() == "Linux":
|
||||
data.update(_linux_distro())
|
||||
@@ -529,19 +534,27 @@ class MemoryMonitorPlugin(MonitorPlugin):
|
||||
return {}
|
||||
total = mi.get("MemTotal", 0)
|
||||
avail = mi.get("MemAvailable", mi.get("MemFree", 0))
|
||||
free = mi.get("MemFree", 0)
|
||||
used = total - avail
|
||||
data: Dict[str, Any] = {
|
||||
"mem_total_kb": total,
|
||||
"mem_used_kb": used,
|
||||
"mem_available_kb": avail,
|
||||
"mem_percent": round(100.0 * used / total, 1) if total else 0.0,
|
||||
"memory_total": total * 1024,
|
||||
"memory_used": used * 1024,
|
||||
"memory_available": avail * 1024,
|
||||
"memory_free": free * 1024,
|
||||
"memory_percent": round(100.0 * used / total, 1) if total else 0.0,
|
||||
}
|
||||
for field, key in (("Buffers", "memory_buffers"), ("Cached", "memory_cached"),
|
||||
("Active", "memory_active"), ("Inactive", "memory_inactive")):
|
||||
if field in mi:
|
||||
data[key] = mi[field] * 1024
|
||||
stotal = mi.get("SwapTotal", 0)
|
||||
if stotal:
|
||||
sfree = mi.get("SwapFree", 0)
|
||||
data["swap_total_kb"] = stotal
|
||||
data["swap_used_kb"] = stotal - sfree
|
||||
data["swap_percent"] = round(100.0 * (stotal - sfree) / stotal, 1)
|
||||
sused = stotal - sfree
|
||||
data["swap_total"] = stotal * 1024
|
||||
data["swap_used"] = sused * 1024
|
||||
data["swap_free"] = sfree * 1024
|
||||
data["swap_percent"] = round(100.0 * sused / stotal, 1)
|
||||
return data
|
||||
|
||||
|
||||
@@ -577,7 +590,7 @@ class DiskMonitorPlugin(MonitorPlugin):
|
||||
except Exception as e:
|
||||
self.logger.warning("df failed: %s", e)
|
||||
return {}
|
||||
data: Dict[str, Any] = {}
|
||||
partitions: Dict[str, Any] = {}
|
||||
for line in out.decode(errors="replace").splitlines()[1:]:
|
||||
parts = line.split()
|
||||
if len(parts) < 6:
|
||||
@@ -586,14 +599,19 @@ class DiskMonitorPlugin(MonitorPlugin):
|
||||
if self.mounts and mount not in self.mounts:
|
||||
continue
|
||||
try:
|
||||
key = re.sub(r"[^a-zA-Z0-9_]", "_", mount).strip("_") or "root"
|
||||
data[f"{key}_total_kb"] = int(parts[1])
|
||||
data[f"{key}_used_kb"] = int(parts[2])
|
||||
data[f"{key}_avail_kb"] = int(parts[3])
|
||||
data[f"{key}_percent"] = int(parts[4].rstrip("%"))
|
||||
total_kb = int(parts[1])
|
||||
used_kb = int(parts[2])
|
||||
avail_kb = int(parts[3])
|
||||
pct = int(parts[4].rstrip("%"))
|
||||
partitions[mount] = {
|
||||
"total": total_kb * 1024,
|
||||
"used": used_kb * 1024,
|
||||
"free": avail_kb * 1024,
|
||||
"percent": pct,
|
||||
}
|
||||
except (ValueError, IndexError):
|
||||
continue
|
||||
return data
|
||||
return {"partitions": partitions} if partitions else {}
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
@@ -649,17 +667,18 @@ class NetworkMonitorPlugin(MonitorPlugin):
|
||||
self._prev = (now, curr)
|
||||
if dt <= 0:
|
||||
return {}
|
||||
data: Dict[str, Any] = {}
|
||||
interfaces: Dict[str, Any] = {}
|
||||
for iface, (rx, tx) in curr.items():
|
||||
if iface in self.skip_ifaces or iface not in prev:
|
||||
continue
|
||||
prx, ptx = prev[iface]
|
||||
key = re.sub(r"[^a-zA-Z0-9_]", "_", iface)
|
||||
data[f"{key}_rx_bps"] = round((rx - prx) / dt)
|
||||
data[f"{key}_tx_bps"] = round((tx - ptx) / dt)
|
||||
data[f"{key}_rx_bytes"] = rx
|
||||
data[f"{key}_tx_bytes"] = tx
|
||||
return data
|
||||
interfaces[iface] = {
|
||||
"bytes_recv": rx,
|
||||
"bytes_sent": tx,
|
||||
"bytes_recv_delta": rx - prx,
|
||||
"bytes_sent_delta": tx - ptx,
|
||||
}
|
||||
return {"interfaces": interfaces} if interfaces else {}
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
@@ -859,7 +878,7 @@ async def _handle_update(conn: AsyncConnection):
|
||||
log.info("running installer: %s", installer)
|
||||
try:
|
||||
proc = await asyncio.create_subprocess_exec(
|
||||
installer, "client",
|
||||
installer, "mini",
|
||||
stdout=asyncio.subprocess.PIPE,
|
||||
stderr=asyncio.subprocess.STDOUT,
|
||||
)
|
||||
|
||||
Reference in New Issue
Block a user