version 5.1.16

- threshold.py: add _find_threshold() with suffix fallback so thresholds
  like ping_monitor.rtt_avg match ping_monitor.8_8_8_8_rtt_avg etc.;
  each pinged host keeps its own alert state
- hbdclass.py: format RTT as integer ms (round())
- live.html: JS RTT display rounded to nearest ms (Math.round)

Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>

hbd/__init__.py

@@ -14,4 +14,4 @@ Install options:
 """
 
 __all__ = ["__version__"]
-__version__ = "5.1.13"
+__version__ = "5.1.16"

hbd/server/hbdclass.py

@@ -95,7 +95,7 @@ class Connection:
         if not Null:
             d["addr"] = self.addr
             if self.rtts[-1]:
-                d["rtt"] = "%0.1f" % self.rtts[-1]
+                d["rtt"] = "%d" % round(self.rtts[-1])
             elif self.state == Connection.UNKNOWN:
                 d["rtt"] = ""
             else:

hbd/server/settings.py

@@ -181,6 +181,48 @@ def get_settings_sections(config: dict) -> list:
             "notification_channels": attrs.get("notification_channels", []),
         })
 
+    # ---- Threshold configurations -----------------------------------------
+    def _parse_metric_row(metric_path, metric_cfg):
+        if not isinstance(metric_cfg, dict):
+            return None
+        return {
+            "metric": metric_path,
+            "operator": metric_cfg.get("operator", ">"),
+            "warning": metric_cfg.get("warning"),
+            "critical": metric_cfg.get("critical"),
+            "hysteresis": metric_cfg.get("hysteresis"),
+            "count": metric_cfg.get("count", 1),
+            "enabled": metric_cfg.get("enabled", True),
+        }
+
+    threshold_config_list = []
+    raw_tconfigs = config.get("threshold_configs") or {}
+    if raw_tconfigs:
+        for cfg_name, cfg_data in sorted(raw_tconfigs.items()):
+            if not isinstance(cfg_data, dict):
+                continue
+            metrics = [
+                r for r in (
+                    _parse_metric_row(mp, mc)
+                    for mp, mc in (cfg_data.get("thresholds") or {}).items()
+                ) if r
+            ]
+            threshold_config_list.append({
+                "name": cfg_name,
+                "metrics": sorted(metrics, key=lambda m: m["metric"]),
+            })
+    elif config.get("thresholds"):
+        metrics = [
+            r for r in (
+                _parse_metric_row(mp, mc)
+                for mp, mc in config["thresholds"].items()
+            ) if r
+        ]
+        threshold_config_list.append({
+            "name": "default",
+            "metrics": sorted(metrics, key=lambda m: m["metric"]),
+        })
+
     # ---- Hosts summary ----------------------------------------------------
     hosts_list = []
     for hname, hcfg in (config.get("hosts") or {}).items():
@@ -312,6 +354,16 @@ def get_settings_sections(config: dict) -> list:
             "hosts": hosts_list,
             "fields": [],
         },
+        {
+            "id": "thresholds",
+            "title": "Threshold Configurations",
+            "description": "Named alert threshold sets. Each defines warning/critical levels per metric.",
+            "threshold_configs": threshold_config_list,
+            "fields": [
+                field("default_threshold_config", "Default config", "text",
+                      "Threshold config used for hosts with no explicit mapping."),
+            ],
+        },
         {
             "id": "runtime",
             "title": "Runtime",

hbd/server/templates/live.html

@@ -236,6 +236,8 @@
       color: #ff9800;
       font-weight: 700;
     }
+    #ntable a.host-link { color: inherit; text-decoration: none; }
+    #ntable a.host-link:hover { text-decoration: underline; }
   </style>
   <script type="text/javascript">
     var cnt = 0;
@@ -245,11 +247,13 @@
     var HBD_VERSION = "{{ hbd_version }}";
 
     function hostNameHtml(data) {
+      var rawName = data.raw_name || data.name.replace(/<[^>]+>/g, '').replace('*', '').trim();
       var nameHtml = data.name;
       if (!data.hbc_version || data.hbc_version !== HBD_VERSION) {
         nameHtml += ' 🥀';
       }
-      return data.dyn ? '<b>' + nameHtml + '</b>' : nameHtml;
+      var display = data.dyn ? '<b>' + nameHtml + '</b>' : nameHtml;
+      return '<a class="host-link" href="/plugins#' + encodeURIComponent(rawName) + '">' + display + '</a>';
     }
 
     function setup() {
@@ -404,7 +408,7 @@
         );
         if (data.connections[i].state == "up") {
           state = '<span class="state-up">up</span>';
-          latency = Number.parseFloat(data.connections[i].rtts[0]).toFixed(2);
+          latency = String(Math.round(Number.parseFloat(data.connections[i].rtts[0])));
         } else {
           if (data.connections[i].state == "unknown") {
             state = "";
@@ -511,7 +515,7 @@
           <tbody id="ntablebody">
             {% for host in hosts %}
             <tr class="{% if host.alert_critical_unacked > 0 or host.alert_critical_acked > 0 %}row-critical{% elif host.alert_warning_unacked > 0 or host.alert_warning_acked > 0 %}row-warning{% endif %}">
-              <td data-name="{{ host.name }}">{{ host.name }}{% if not host.hbc_version or host.hbc_version != hbd_version %} 🥀{% endif %}</td>
+              <td data-name="{{ host.name }}"><a class="host-link" href="/plugins#{{ host.raw_name | urlencode }}">{{ host.name }}{% if not host.hbc_version or host.hbc_version != hbd_version %} 🥀{% endif %}</a></td>
               <td style="text-align: center; color: #ff9800; font-weight: bold;">
                 {%- set warning_unacked = host.alert_warning_unacked -%}
                 {%- set warning_acked = host.alert_warning_acked -%}

hbd/server/templates/plugins.html

@@ -383,7 +383,7 @@
           </div>
 
           <div class="host-body">
-            {% set plugin_order = ['os_info','cpu_monitor','memory_monitor','disk_monitor','network_monitor','nagios_runner','filesystem_info'] %}
+            {% set plugin_order = ['os_info','cpu_monitor','memory_monitor','disk_monitor','network_monitor','zfs_monitor','nagios_runner','filesystem_info'] %}
             {% for plugin in plugin_order if plugin in host.plugins %}
             <div class="plugin-accordion collapsed"
                  data-hostname="{{ host.name }}"
@@ -673,6 +673,19 @@
             text = `${count} filesystem${count !== 1 ? 's' : ''}`;
             break;
           }
+          case 'zfs_monitor': {
+            const pools = d.pools || {};
+            const names = Object.keys(pools);
+            if (names.length === 0) { text = 'No pools'; break; }
+            const degraded = names.filter(n => pools[n].health && pools[n].health !== 'ONLINE');
+            text = names.map(n => {
+              const p = pools[n];
+              const cap = p.capacity != null ? ` ${p.capacity.toFixed(0)}%` : '';
+              return `${n}${cap}`;
+            }).join(' · ');
+            if (degraded.length) text += ` ⚠ ${degraded.map(n => pools[n].health).join(',')}`;
+            break;
+          }
           default:
             text = 'Loaded';
         }
@@ -694,6 +707,7 @@
           case 'memory_monitor': html = renderMemoryTable(cached.data); break;
           case 'disk_monitor':   html = renderDiskTables(cached.data); break;
           case 'network_monitor':html = renderNetworkTables(cached.data); break;
+          case 'zfs_monitor':    html = renderZfsTables(cached.data); break;
           case 'nagios_runner':  html = renderNagiosTable(cached.data); break;
           case 'filesystem_info':html = renderFilesystemTable(cached.data); break;
           default:               html = renderGenericTable(cached.data); break;
@@ -1024,6 +1038,66 @@
         return html;
       }
 
+      function renderZfsTables(d) {
+        const pools = d.pools || {};
+        const names = Object.keys(pools);
+        if (names.length === 0) return '<div class="no-data">No ZFS pools found</div>';
+
+        const healthCls = h => {
+          if (!h || h === 'ONLINE') return 'pct-ok';
+          if (h === 'DEGRADED') return 'pct-warn';
+          return 'pct-crit';
+        };
+
+        let pt = '<table class="data-table"><thead><tr>'
+          + '<th>Pool</th><th>Health</th>'
+          + '<th class="num">Size</th><th class="num">Used</th>'
+          + '<th class="num">Free</th><th class="num">Cap %</th>'
+          + '<th class="num">Frag %</th><th class="num">Dedup</th>'
+          + '</tr></thead><tbody>';
+        for (const name of names) {
+          const p = pools[name];
+          const cap = p.capacity != null ? p.capacity : 0;
+          const capCls = cap > 90 ? 'pct-crit' : cap > 75 ? 'pct-warn' : 'pct-ok';
+          pt += `<tr>
+            <td class="iface-name">${escHtml(name)}</td>
+            <td class="${healthCls(p.health)}">${escHtml(p.health || '—')}</td>
+            <td class="num">${formatBytes(p.size || 0)}</td>
+            <td class="num">${formatBytes(p.alloc || 0)}</td>
+            <td class="num">${formatBytes(p.free || 0)}</td>
+            <td class="num ${capCls}">${cap.toFixed(1)}%</td>
+            <td class="num">${p.frag != null ? p.frag.toFixed(1) + '%' : '—'}</td>
+            <td class="num">${p.dedup != null ? p.dedup.toFixed(2) + 'x' : '—'}</td>
+          </tr>`;
+        }
+        pt += '</tbody></table>';
+
+        const hasIo = names.some(n => pools[n].read_ops != null);
+        if (!hasIo) return pt;
+
+        let iot = '<table class="data-table"><thead><tr>'
+          + '<th>Pool</th>'
+          + '<th class="num">Read ops</th><th class="num">Write ops</th>'
+          + '<th class="num">Read BW</th><th class="num">Write BW</th>'
+          + '</tr></thead><tbody>';
+        for (const name of names) {
+          const p = pools[name];
+          iot += `<tr>
+            <td class="iface-name">${escHtml(name)}</td>
+            <td class="num">${p.read_ops != null ? p.read_ops.toLocaleString() : '—'}</td>
+            <td class="num">${p.write_ops != null ? p.write_ops.toLocaleString() : '—'}</td>
+            <td class="num">${p.read_bw != null ? formatBytes(p.read_bw) : '—'}</td>
+            <td class="num">${p.write_bw != null ? formatBytes(p.write_bw) : '—'}</td>
+          </tr>`;
+        }
+        iot += '</tbody></table>';
+
+        return `<div class="flex-tables">
+          <div><div class="table-section-label">Pools</div>${pt}</div>
+          <div><div class="table-section-label">I/O (cumulative)</div>${iot}</div>
+        </div>`;
+      }
+
       function renderGenericTable(d) {
         let html = '<table class="data-table"><thead><tr><th>Field</th><th>Value</th></tr></thead><tbody>';
         for (const [k, v] of Object.entries(d)) {
@@ -1082,6 +1156,19 @@
       // ── Init ────────────────────────────────────────────────────────────────
 
       document.addEventListener('DOMContentLoaded', () => {
+        // If a host fragment is in the URL, expand and scroll to that host;
+        // otherwise expand the first host as before.
+        const hash = window.location.hash;
+        if (hash) {
+          const hostname = decodeURIComponent(hash.slice(1));
+          const card = document.querySelector(`.host-card[data-hostname="${hostname}"]`);
+          if (card) {
+            card.classList.remove('collapsed');
+            fetchHostGlance(hostname);
+            setTimeout(() => card.scrollIntoView({ behavior: 'smooth', block: 'start' }), 150);
+            return;
+          }
+        }
         const first = document.querySelector('.host-card');
         if (first) {
           first.classList.remove('collapsed');

hbd/server/templates/settings.html

@@ -254,6 +254,17 @@
     .host-bool { text-align: center; }
     .dot-yes { color: #2e7d32; font-size: 1.1em; }
     .dot-no  { color: #ddd;    font-size: 1.1em; }
+
+    /* ---- Threshold configurations ---- */
+    .thresh-config { margin: 12px 20px 20px; }
+    .thresh-config-name {
+      font-weight: 600; font-size: 0.9em; color: #1a237e;
+      margin-bottom: 6px;
+    }
+    .mini-table .warn  { color: #e65100; font-weight: 600; }
+    .mini-table .crit  { color: #b71c1c; font-weight: 600; }
+    .mini-table .dim   { color: #aaa; }
+    .mini-table .metric-path { font-family: monospace; font-size: 0.88em; }
   </style>
 
   <body>
@@ -394,6 +405,49 @@
             {% endif %}
             {% endif %}
 
+            {# ---- Threshold configurations section ---- #}
+            {% if section.id == "thresholds" %}
+            {% if section.threshold_configs %}
+            {% for tc in section.threshold_configs %}
+            <div class="thresh-config">
+              <div class="thresh-config-name">{{ tc.name }}</div>
+              {% if tc.metrics %}
+              <div style="overflow-x: auto;">
+                <table class="mini-table">
+                  <thead>
+                    <tr>
+                      <th>Metric</th>
+                      <th>Op</th>
+                      <th>Warning</th>
+                      <th>Critical</th>
+                      <th>Hysteresis</th>
+                      <th>Count</th>
+                    </tr>
+                  </thead>
+                  <tbody>
+                    {% for m in tc.metrics %}
+                    <tr {% if not m.enabled %} style="opacity:0.45"{% endif %}>
+                      <td class="metric-path">{{ m.metric }}</td>
+                      <td>{{ m.operator or '>' }}</td>
+                      <td class="warn">{{ m.warning if m.warning is not none else '—' }}</td>
+                      <td class="crit">{{ m.critical if m.critical is not none else '—' }}</td>
+                      <td class="dim">{{ '%.0f%%' % (m.hysteresis * 100) if m.hysteresis else '—' }}</td>
+                      <td class="dim">{{ m.count }}</td>
+                    </tr>
+                    {% endfor %}
+                  </tbody>
+                </table>
+              </div>
+              {% else %}
+              <span class="val-empty">No thresholds defined.</span>
+              {% endif %}
+            </div>
+            {% endfor %}
+            {% else %}
+            <div class="field-row"><span class="val-empty">No threshold configurations defined.</span></div>
+            {% endif %}
+            {% endif %}
+
             {# ---- Hosts section ---- #}
             {% if section.id == "hosts" %}
             {% if section.hosts %}

hbd/server/threshold.py

@@ -803,6 +803,29 @@ class ThresholdChecker:
             self._check_pending_or_renotify(host_name, alert_state, metric_path, value, threshold, None)
 
         return None
+    def _find_threshold(
+        self, thresholds: Dict[str, "ThresholdConfig"], metric_path: str
+    ) -> Optional["ThresholdConfig"]:
+        """Return the threshold for *metric_path*, falling back to suffix matches.
+
+        Allows generic thresholds like ``ping_monitor.rtt_avg`` to match
+        fully-qualified paths like ``ping_monitor.8_8_8_8_rtt_avg``.
+        The exact match is always tried first; then successive leading
+        underscore-delimited segments are stripped from the field name until
+        a match is found or no segments remain.
+        """
+        if metric_path in thresholds:
+            return thresholds[metric_path]
+        plugin, sep, field = metric_path.partition(".")
+        if not sep:
+            return None
+        parts = field.split("_")
+        for i in range(1, len(parts)):
+            candidate = plugin + "." + "_".join(parts[i:])
+            if candidate in thresholds:
+                return thresholds[candidate]
+        return None
+
     def check_plugin_data(
         self,
         host_name: str,
@@ -831,11 +854,10 @@ class ThresholdChecker:
         for metric_name, value in data.items():
             metric_path = f"{plugin_name}.{metric_name}"
             
-            if metric_path not in thresholds:
+            threshold = self._find_threshold(thresholds, metric_path)
+            if threshold is None:
                 continue
             
-            threshold = thresholds[metric_path]
-            
             # Get or create alert state
             if metric_path not in alert_states:
                 alert_states[metric_path] = AlertState(metric_path)
@@ -1114,7 +1136,9 @@ class ThresholdChecker:
     ) -> None:
         """Handle a state-change transition with grace-period logic.
 
-        Transitioning INTO alert: defers the notification for grace_seconds.
+        Transitioning INTO alert (worsening): defers the notification for grace_seconds.
+        De-escalation within alert states (e.g. CRITICAL→WARNING): no new notification;
+          the metric is still alerting so no RECOVER was sent.
         Transitioning TO OK:
           - Still in grace window (pending_since set): suppresses both the alert
             and the recovery — the spike never warranted a page.
@@ -1134,12 +1158,20 @@ class ThresholdChecker:
                 alert_state.pending_since = None
             else:
                 self._send_notification(host_name, lvl, message, metric_path, old_level, new_level, value)
-        else:
+        elif new_level.value > old_level.value:
+            # Worsening (OK→WARNING, OK→CRITICAL, WARNING→CRITICAL): schedule notification.
             alert_state.pending_since = time.time()
             logger.debug(
                 "Alert deferred (%.0fs grace): %s on %s = %s",
                 self.grace_seconds, metric_path, host_name, value,
             )
+        else:
+            # De-escalation within alert states (e.g. CRITICAL→WARNING): metric is still
+            # alerting but did not recover, so no new notification.
+            logger.debug(
+                "De-escalation %s→%s for %s on %s, no notification",
+                old_level.name, new_level.name, metric_path, host_name,
+            )
 
     def _check_pending_or_renotify(
         self,

hbd/server/udp.py

@@ -440,14 +440,18 @@ def handle_datagram(msg: dict, addr, transport, ctx: dict):
         if not newh:
             if d == 0 or lasts == "unknown":
                 m = "%s is up" % (conn.afam)
+            elif d < 4:
+                # Transient blip (likely client restart) — skip log and notification
+                m = None
             else:
                 m = "%s back after being %s for %s" % (conn.afam, lasts, dur(d))
-            eventlog(uname, "RECOVER", m)
-            if host.watched:
-                asyncio.create_task(notify_mod.send_notification(
-                    uname,
-                    notify_mod.Notification(title=f"[RECOVER] {uname}", body=m, level="RECOVER"),
-                ))
+            if m:
+                eventlog(uname, "RECOVER", m)
+                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

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "hbd"
-version = "5.1.13"
+version = "5.1.16"
 description = "Heartbeat monitoring system — client (hbc) and server (hbd)"
 readme = "README.md"
 requires-python = ">=3.11"

scripts/hbc_mini.py

@@ -41,7 +41,7 @@ from pathlib import Path
 from typing import Any, Dict, List, Optional, Tuple
 
 # updated by scripts/bumpminor.sh
-__version__ = "5.1.13"
+__version__ = "5.1.16"
 
 # ---------------------------------------------------------------------------
 # Protocol  (mirrors hbd/common/proto.py)