From 45179d89a5eb0d4b433c1f3cb983a8bbe6d266bd Mon Sep 17 00:00:00 2001
From: Jared Vititoe <jjvititoe1@gmail.com>
Date: Fri, 13 Dec 2024 18:41:13 -0500
Subject: [PATCH] Only sets has_ecc to True if it finds actual ECC controller
 rows

---
 hwmonDaemon.py | 60 +++++++++++++++++++++++---------------------------
 1 file changed, 27 insertions(+), 33 deletions(-)

diff --git a/hwmonDaemon.py b/hwmonDaemon.py
index 1670ca3..5ec050e 100644
--- a/hwmonDaemon.py
+++ b/hwmonDaemon.py
@@ -431,40 +431,34 @@ class SystemHealthMonitor:
             bytes_value /= 1024.0
         return f"{bytes_value:.1f}Y{suffix}"
 
-    def _check_memory_usage(self) -> Dict[str, Any]:
-        """
-        Check for ECC memory errors if ECC memory is present.
-        
-        :return: Dictionary with memory health metrics and ECC status.
-        """
-        memory_health = {
-            'has_ecc': False,
-            'ecc_errors': [],
-            'status': 'OK'
-        }
-        
-        try:
-            # Check if ECC memory is present by looking at edac_mc
-            result = subprocess.run(
-                ['ls', '/sys/devices/system/edac/mc'],
-                stdout=subprocess.PIPE,
-                stderr=subprocess.PIPE,
-                text=True
-            )
-            
-            if result.returncode == 0:
-                memory_health['has_ecc'] = True
-                
-                # Check for ECC errors in mcX/csrowY/ue_count and ce_count files
-                for mc_dir in glob.glob('/sys/devices/system/edac/mc/mc[0-9]*'):
-                    mc_name = os.path.basename(mc_dir)
+def _check_memory_usage(self) -> Dict[str, Any]:
+    """
+    Check for ECC memory errors if ECC memory is present.
+    """
+    memory_health = {
+        'has_ecc': False,
+        'ecc_errors': [],
+        'status': 'OK',
+        'total_memory': self._convert_bytes(psutil.virtual_memory().total),
+        'used_memory': self._convert_bytes(psutil.virtual_memory().used),
+        'memory_percent': psutil.virtual_memory().percent
+    }
+    
+    try:
+        # More robust ECC detection - check both directory existence and content
+        edac_path = '/sys/devices/system/edac/mc'
+        if os.path.exists(edac_path) and os.listdir(edac_path):
+            # Verify actual ECC controller presence
+            for mc_dir in glob.glob('/sys/devices/system/edac/mc/mc[0-9]*'):
+                if os.path.exists(f"{mc_dir}/csrow0"):
+                    memory_health['has_ecc'] = True
                     
                     # Check uncorrectable errors
                     ue_count = self._read_ecc_count(f"{mc_dir}/csrow0/ue_count")
                     if ue_count > 0:
                         memory_health['status'] = 'CRITICAL'
                         memory_health['ecc_errors'].append(
-                            f"Uncorrectable ECC errors detected in {mc_name}: {ue_count}"
+                            f"Uncorrectable ECC errors detected in {os.path.basename(mc_dir)}: {ue_count}"
                         )
                     
                     # Check correctable errors
@@ -473,14 +467,14 @@ class SystemHealthMonitor:
                         if memory_health['status'] != 'CRITICAL':
                             memory_health['status'] = 'WARNING'
                         memory_health['ecc_errors'].append(
-                            f"Correctable ECC errors detected in {mc_name}: {ce_count}"
+                            f"Correctable ECC errors detected in {os.path.basename(mc_dir)}: {ce_count}"
                         )
                         
-        except Exception as e:
-            memory_health['status'] = 'ERROR'
-            memory_health['ecc_errors'].append(f"Error checking ECC status: {str(e)}")
+    except Exception as e:
+        memory_health['status'] = 'ERROR'
+        memory_health['ecc_errors'].append(f"Error checking ECC status: {str(e)}")
             
-        return memory_health
+    return memory_health
 
     def _read_ecc_count(self, filepath: str) -> int:
         """