andreas/heartbeat
Public Access
1
0
Fork 1
Code Issues Pull Requests Actions Packages Projects Releases 44 Wiki Activity

feat: host-level watch flag suppresses notifications; filter dashboard/overview by owner/manager; add ZFS monitor plugin

Browse Source 
- watch: true (default) per host; watch: false suppresses all notifications
  for that host in udp.py and threshold.py
- Live Dashboard and Host Overview now show only hosts where the logged-in
  user is owner or manager (admins see all); WebSocket broadcasts filtered
  per-connection by the same rule
- Add hbd/client/plugins/zfs_monitor.py: collects per-pool health, capacity,
  fragmentation, dedup ratio, and cumulative I/O ops/bandwidth via zpool(8)

Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Andreas Wrede
2026-05-02 12:42:35 -04:00
parent cffc9805f9
commit 691f62aa69
8 changed files with 234 additions and 45 deletions
Download Patch File Download Diff File Expand all files Collapse all files
hbd/server/udp.py
+25 -20
View File
@@ -211,10 +211,11 @@ 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)
asyncio.create_task(notify_mod.send_notification(
uname,
notify_mod.Notification(title=f"[CRITICAL] {uname}", body=msg, level="CRITICAL"),
))
if host.watched:
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 +408,11 @@ def handle_datagram(msg: dict, addr, transport, ctx: dict):
if res:
eventlog(uname, "WARNING", res)
asyncio.create_task(notify_mod.send_notification(
uname,
notify_mod.Notification(title=f"[WARNING] {uname}", body=res, level="WARNING"),
))
if host.watched:
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 +422,11 @@ def handle_datagram(msg: dict, addr, transport, ctx: dict):
if boot:
eventlog(uname, "INFO", "booted")
asyncio.create_task(notify_mod.send_notification(
uname,
notify_mod.Notification(title=f"[INFO] {uname}", body=f"{host.name} booted", level="INFO"),
))
if host.watched:
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 +443,11 @@ 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)
asyncio.create_task(notify_mod.send_notification(
uname,
notify_mod.Notification(title=f"[RECOVER] {uname}", body=m, level="RECOVER"),
))
if host.watched:
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 +457,11 @@ def handle_datagram(msg: dict, addr, transport, ctx: dict):
if shutdown:
m = "%s shutdown" % conn.afam
eventlog(uname, "INFO", m)
asyncio.create_task(notify_mod.send_notification(
uname,
notify_mod.Notification(title=f"[INFO] {uname}", body=m, level="INFO"),
))
if host.watched:
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")