version 5.1.19

memory_monitor / hbc_mini: ZFS ARC is reclaimable but not reflected in
MemAvailable by the Linux kernel (not in SReclaimable). Read ARC size
from /proc/spl/kstat/zfs/arcstats and add it to available memory before
computing memory_percent and memory_used. No-op on systems without ZFS.

cpu_monitor: report uptime_seconds via psutil.boot_time() (full client)
and /proc/uptime (hbc_mini).

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

hbd/__init__.py

@@ -14,4 +14,4 @@ Install options:
 """
 
 __all__ = ["__version__"]
-__version__ = "5.1.18"
+__version__ = "5.1.19"

hbd/client/main.py

@@ -463,18 +463,14 @@ async def cleanup(connections: List[AsyncConnection]):
     logger = logging.getLogger("hbc.cleanup")
     logger.info("Cleaning up connections")
     
-    for conn in connections:
+    target = next((c for c in connections if c.transport), connections[0] if connections else None)
+    if target:
         try:
-            msg = {
-                "shutdown": 1,
-                "acks": conn.ackcount
-            }
-            await conn.sendto(msg)
+            await target.sendto({"shutdown": 1, "acks": target.ackcount})
         except Exception as e:
             logger.error(f"Error sending shutdown: {e}")
-        
+    for conn in connections:
         conn.close()
-        break  # Only send shutdown on first connection to avoid duplicates
     
     # Give messages time to send
     await asyncio.sleep(0.5)
@@ -539,9 +535,8 @@ async def async_main(args, config):
             boot_msg["msg"] = args.message
         
         boot_msg["acks"] = 0
-        for conn in connections:
-            await conn.sendto(boot_msg)
-            break  # Only send message on first connection to avoid duplicates
+        target = next((c for c in connections if c.transport), connections[0])
+        await target.sendto(boot_msg)
         
         if args.message and not args.daemon:
             # Message-only mode

hbd/client/plugins/cpu_monitor.py

@@ -118,6 +118,13 @@ class CPUMonitorPlugin(MonitorPlugin):
                     data["cpu_iowait"] = round(cpu_times.iowait, 1)
             except Exception as e:
                 self.logger.debug(f"Could not get CPU times: {e}")
+
+            # Uptime in seconds
+            try:
+                import time
+                data["uptime_seconds"] = int(time.time() - self.psutil.boot_time())
+            except Exception as e:
+                self.logger.debug(f"Could not get uptime: {e}")
             
             self.logger.debug(
                 f"Collected CPU metrics: {data.get('cpu_percent', 'N/A')}% usage"

hbd/client/plugins/memory_monitor.py

@@ -14,6 +14,24 @@ except ImportError:
 
 from hbd.client.plugin import MonitorPlugin
 
+
+def _zfs_arc_bytes() -> int:
+    """Return current ZFS ARC size in bytes, or 0 if ZFS is not present.
+
+    ZFS ARC is reclaimable but is not included in MemAvailable by the Linux
+    kernel (it is not in SReclaimable), so it would otherwise be counted as
+    used memory.
+    """
+    try:
+        with open("/proc/spl/kstat/zfs/arcstats") as fh:
+            for line in fh:
+                parts = line.split()
+                if len(parts) >= 3 and parts[0] == "size":
+                    return int(parts[2])
+    except (OSError, ValueError):
+        pass
+    return 0
+
 logger = logging.getLogger(__name__)
 
 
@@ -101,11 +119,21 @@ class MemoryMonitorPlugin(MonitorPlugin):
         
         # Virtual (physical) memory statistics
         vmem = psutil.virtual_memory()
+
+        # psutil's available already excludes page cache / file buffers
+        # (uses MemAvailable on Linux). Add ZFS ARC on top because the kernel
+        # does not include it in SReclaimable / MemAvailable even though it is
+        # reclaimable.
+        arc_bytes = _zfs_arc_bytes()
+        available = min(vmem.available + arc_bytes, vmem.total)
+        used = vmem.total - available
+        percent = round(used / vmem.total * 100, 1) if vmem.total else 0.0
+
         metrics['memory_total'] = vmem.total
-        metrics['memory_available'] = vmem.available
-        metrics['memory_used'] = vmem.used
+        metrics['memory_available'] = available
+        metrics['memory_used'] = used
         metrics['memory_free'] = vmem.free
-        metrics['memory_percent'] = vmem.percent
+        metrics['memory_percent'] = percent
         
         # Platform-specific memory details
         if hasattr(vmem, 'active'):

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "hbd"
-version = "5.1.18"
+version = "5.1.19"
 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__ = "5.1.18"
+__version__ = "5.1.19"
 
 # ---------------------------------------------------------------------------
 # Protocol  (mirrors hbd/common/proto.py)
@@ -487,6 +487,12 @@ class CPUMonitorPlugin(MonitorPlugin):
         except Exception:
             pass
 
+        try:
+            with open("/proc/uptime") as fh:
+                data["uptime_seconds"] = int(float(fh.read().split()[0]))
+        except Exception:
+            pass
+
         return data
 
 
@@ -535,6 +541,20 @@ class MemoryMonitorPlugin(MonitorPlugin):
         total = mi.get("MemTotal", 0)
         avail = mi.get("MemAvailable", mi.get("MemFree", 0))
         free = mi.get("MemFree", 0)
+
+        # ZFS ARC is reclaimable but not included in MemAvailable; add it.
+        arc_kb = 0
+        try:
+            with open("/proc/spl/kstat/zfs/arcstats") as _f:
+                for _line in _f:
+                    _p = _line.split()
+                    if len(_p) >= 3 and _p[0] == "size":
+                        arc_kb = int(_p[2]) // 1024
+                        break
+        except (OSError, ValueError):
+            pass
+
+        avail = min(avail + arc_kb, total)
         used = total - avail
         data: Dict[str, Any] = {
             "memory_total": total * 1024,
@@ -1052,9 +1072,8 @@ async def _async_main(args, cfg: Dict[str, Any]) -> int:
         if args.message:
             bmsg["service"] = "service"
             bmsg["msg"] = args.message
-        for c in connections:
-            await c.sendto(bmsg)
-            break
+        target = next((c for c in connections if c._transport), connections[0])
+        await target.sendto(bmsg)
         if args.message and not args.daemon:
             await asyncio.sleep(0.3)
             for c in connections:
@@ -1086,12 +1105,12 @@ async def _async_main(args, cfg: Dict[str, Any]) -> int:
         pass
 
     log.info("shutting down")
-    for conn in connections:
+    target = next((c for c in connections if c._transport), connections[0] if connections else None)
+    if target:
         try:
-            await conn.sendto({"shutdown": 1, "acks": conn.ackcount})
+            await target.sendto({"shutdown": 1, "acks": target.ackcount})
         except Exception:
             pass
-        break
     for conn in connections:
         conn.close()
     await asyncio.sleep(0.3)