Add ZMQ communication statistics tracking and display

Agent changes:
- Changed docker ps and docker images commands to run without sudo
- cm-agent user is already in docker group, so sudo is not needed
- Fixes "unable to change to root gid: Operation not permitted" error
- Systemd security restrictions were blocking sudo gid changes

This fixes Docker container and image collection on systems with
systemd security hardening enabled.

Updated to version 0.1.178

Cargo.lock

@@ -279,7 +279,7 @@ checksum = "a1d728cc89cf3aee9ff92b05e62b19ee65a02b5702cff7d5a377e32c6ae29d8d"
 
 [[package]]
 name = "cm-dashboard"
-version = "0.1.170"
+version = "0.1.185"
 dependencies = [
  "anyhow",
  "chrono",
@@ -301,7 +301,7 @@ dependencies = [
 
 [[package]]
 name = "cm-dashboard-agent"
-version = "0.1.170"
+version = "0.1.185"
 dependencies = [
  "anyhow",
  "async-trait",
@@ -324,7 +324,7 @@ dependencies = [
 
 [[package]]
 name = "cm-dashboard-shared"
-version = "0.1.170"
+version = "0.1.185"
 dependencies = [
  "chrono",
  "serde",

agent/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "cm-dashboard-agent"
-version = "0.1.170"
+version = "0.1.186"
 edition = "2021"
 
 [dependencies]

agent/src/collectors/disk.rs

@@ -386,7 +386,7 @@ impl DiskCollector {
     /// Get SMART data for drives
     async fn get_smart_data_for_drives(&self, physical_drives: &[PhysicalDrive], mergerfs_pools: &[MergerfsPool]) -> HashMap<String, SmartData> {
         let mut smart_data = HashMap::new();
-        
+
         // Collect all drive names
         let mut all_drives = std::collections::HashSet::new();
         for drive in physical_drives {
@@ -413,23 +413,24 @@ impl DiskCollector {
 
     /// Get SMART data for a single drive
     async fn get_smart_data(&self, drive_name: &str) -> Result<SmartData, CollectorError> {
-        let output = Command::new("sudo")
+        // Use direct smartctl (no sudo) - service has CAP_SYS_RAWIO and CAP_SYS_ADMIN capabilities
-            .args(&["smartctl", "-a", &format!("/dev/{}", drive_name)])
+        // For NVMe drives, specify device type explicitly
-            .output()
+        let mut cmd = Command::new("smartctl");
+        if drive_name.starts_with("nvme") {
+            cmd.args(&["-d", "nvme", "-a", &format!("/dev/{}", drive_name)]);
+        } else {
+            cmd.args(&["-a", &format!("/dev/{}", drive_name)]);
+        }
+
+        let output = cmd.output()
             .map_err(|e| CollectorError::SystemRead {
                 path: format!("SMART data for {}", drive_name),
                 error: e.to_string(),
             })?;
 
         let output_str = String::from_utf8_lossy(&output.stdout);
-        let error_str = String::from_utf8_lossy(&output.stderr);
+
-        
-        // Debug logging for SMART command results
-        debug!("SMART output for {}: status={}, stdout_len={}, stderr={}", 
-            drive_name, output.status, output_str.len(), error_str);
-        
         if !output.status.success() {
-            debug!("SMART command failed for {}: {}", drive_name, error_str);
             // Return unknown data rather than failing completely
             return Ok(SmartData {
                 health: "UNKNOWN".to_string(),

agent/src/collectors/systemd.rs

@@ -123,13 +123,30 @@ impl SystemdCollector {
                             // For now, docker containers have no additional metrics
                             // Future: could add memory_mb, cpu_percent, restart_count, etc.
                             let metrics = Vec::new();
-                            
+
                             sub_services.push(SubServiceData {
                                 name: container_name.clone(),
                                 service_status: self.calculate_service_status(&container_name, &container_status),
                                 metrics,
                             });
                         }
+
+                        // Add Docker images
+                        let docker_images = self.get_docker_images();
+                        for (image_name, image_status, image_size_str, image_size_mb) in docker_images {
+                            let mut metrics = Vec::new();
+                            metrics.push(SubServiceMetric {
+                                label: "size".to_string(),
+                                value: image_size_mb,
+                                unit: Some("MB".to_string()),
+                            });
+
+                            sub_services.push(SubServiceData {
+                                name: format!("{} ({})", image_name, image_size_str),
+                                service_status: self.calculate_service_status(&image_name, &image_status),
+                                metrics,
+                            });
+                        }
                     }
 
                     // Create complete service data
@@ -151,7 +168,11 @@ impl SystemdCollector {
                 }
             }
         }
-        
+
+        // Sort services alphabetically by name
+        agent_data.services.sort_by(|a, b| a.name.cmp(&b.name));
+        complete_service_data.sort_by(|a, b| a.name.cmp(&b.name));
+
         // Update cached state
         {
             let mut state = self.state.write().unwrap();
@@ -756,9 +777,10 @@ impl SystemdCollector {
     fn get_docker_containers(&self) -> Vec<(String, String)> {
         let mut containers = Vec::new();
 
-        // Check if docker is available (use sudo for permissions)
+        // Check if docker is available (cm-agent user is in docker group)
-        let output = Command::new("sudo")
+        // Use -a to show ALL containers (running and stopped)
-            .args(&["docker", "ps", "--format", "{{.Names}},{{.Status}}"])
+        let output = Command::new("docker")
+            .args(&["ps", "-a", "--format", "{{.Names}},{{.Status}}"])
             .output();
 
         let output = match output {
@@ -783,10 +805,10 @@ impl SystemdCollector {
 
                 let container_status = if status_str.contains("Up") {
                     "active"
-                } else if status_str.contains("Exited") {
+                } else if status_str.contains("Exited") || status_str.contains("Created") {
-                    "warning" // Match original: Exited → Warning, not inactive
+                    "inactive" // Stopped/created containers are inactive
                 } else {
-                    "failed" // Other states → failed
+                    "failed" // Other states (restarting, paused, dead) → failed
                 };
                 
                 containers.push((format!("docker_{}", container_name), container_status.to_string()));
@@ -795,6 +817,87 @@ impl SystemdCollector {
 
         containers
     }
+
+    /// Get docker images as sub-services
+    fn get_docker_images(&self) -> Vec<(String, String, String, f32)> {
+        let mut images = Vec::new();
+        // Check if docker is available (cm-agent user is in docker group)
+        let output = Command::new("docker")
+            .args(&["images", "--format", "{{.Repository}}:{{.Tag}},{{.Size}}"])
+            .output();
+
+        let output = match output {
+            Ok(out) if out.status.success() => out,
+            Ok(_) => {
+                return images;
+            }
+            Err(_) => {
+                return images;
+            }
+        };
+
+        let output_str = match String::from_utf8(output.stdout) {
+            Ok(s) => s,
+            Err(_) => return images,
+        };
+
+        for line in output_str.lines() {
+            if line.trim().is_empty() {
+                continue;
+            }
+
+            let parts: Vec<&str> = line.split(',').collect();
+            if parts.len() >= 2 {
+                let image_name = parts[0].trim();
+                let size_str = parts[1].trim();
+
+                // Skip <none>:<none> images (dangling images)
+                if image_name.contains("<none>") {
+                    continue;
+                }
+
+                // Parse size to MB (sizes come as "142MB", "1.5GB", "512kB", etc.)
+                let size_mb = self.parse_docker_size(size_str);
+
+                images.push((
+                    format!("image_{}", image_name),
+                    "active".to_string(), // Images are always "active" (present)
+                    size_str.to_string(),
+                    size_mb
+                ));
+            }
+        }
+
+        images
+    }
+
+    /// Parse Docker size string to MB
+    fn parse_docker_size(&self, size_str: &str) -> f32 {
+        let size_upper = size_str.to_uppercase();
+
+        // Extract numeric part and unit
+        let mut num_str = String::new();
+        let mut unit = String::new();
+
+        for ch in size_upper.chars() {
+            if ch.is_ascii_digit() || ch == '.' {
+                num_str.push(ch);
+            } else if ch.is_alphabetic() {
+                unit.push(ch);
+            }
+        }
+
+        let value: f32 = num_str.parse().unwrap_or(0.0);
+
+        // Convert to MB
+        match unit.as_str() {
+            "KB" | "K" => value / 1024.0,
+            "MB" | "M" => value,
+            "GB" | "G" => value * 1024.0,
+            "TB" | "T" => value * 1024.0 * 1024.0,
+            _ => value, // Assume bytes if no unit
+        }
+    }
 }
 
 #[async_trait]

dashboard/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "cm-dashboard"
-version = "0.1.170"
+version = "0.1.186"
 edition = "2021"
 
 [dependencies]

dashboard/src/app.rs

@@ -215,7 +215,7 @@ impl Dashboard {
 
                     // Update TUI with new metrics (only if not headless)
                     if let Some(ref mut tui_app) = self.tui_app {
-                        tui_app.update_metrics(&self.metric_store);
+                        tui_app.update_metrics(&mut self.metric_store);
                     }
                 }
                 

dashboard/src/metrics/store.rs

@@ -5,6 +5,14 @@ use tracing::{debug, info, warn};
 
 use super::MetricDataPoint;
 
+/// ZMQ communication statistics per host
+#[derive(Debug, Clone)]
+pub struct ZmqStats {
+    pub packets_received: u64,
+    pub last_packet_time: Instant,
+    pub last_packet_age_secs: f64,
+}
+
 /// Central metric storage for the dashboard
 pub struct MetricStore {
     /// Current structured data: hostname -> AgentData
@@ -13,6 +21,8 @@ pub struct MetricStore {
     historical_metrics: HashMap<String, Vec<MetricDataPoint>>,
     /// Last heartbeat timestamp per host
     last_heartbeat: HashMap<String, Instant>,
+    /// ZMQ communication statistics per host
+    zmq_stats: HashMap<String, ZmqStats>,
     /// Configuration
     max_metrics_per_host: usize,
     history_retention: Duration,
@@ -24,6 +34,7 @@ impl MetricStore {
             current_agent_data: HashMap::new(),
             historical_metrics: HashMap::new(),
             last_heartbeat: HashMap::new(),
+            zmq_stats: HashMap::new(),
             max_metrics_per_host,
             history_retention: Duration::from_secs(history_retention_hours * 3600),
         }
@@ -44,6 +55,16 @@ impl MetricStore {
         self.last_heartbeat.insert(hostname.clone(), now);
         debug!("Updated heartbeat for host {}", hostname);
 
+        // Update ZMQ stats
+        let stats = self.zmq_stats.entry(hostname.clone()).or_insert(ZmqStats {
+            packets_received: 0,
+            last_packet_time: now,
+            last_packet_age_secs: 0.0,
+        });
+        stats.packets_received += 1;
+        stats.last_packet_time = now;
+        stats.last_packet_age_secs = 0.0; // Just received
+
         // Add to history
         let host_history = self
             .historical_metrics
@@ -65,6 +86,15 @@ impl MetricStore {
         self.current_agent_data.get(hostname)
     }
 
+    /// Get ZMQ communication statistics for a host
+    pub fn get_zmq_stats(&mut self, hostname: &str) -> Option<ZmqStats> {
+        let now = Instant::now();
+        self.zmq_stats.get_mut(hostname).map(|stats| {
+            // Update packet age
+            stats.last_packet_age_secs = now.duration_since(stats.last_packet_time).as_secs_f64();
+            stats.clone()
+        })
+    }
 
     /// Get connected hosts (hosts with recent heartbeats)
     pub fn get_connected_hosts(&self, timeout: Duration) -> Vec<String> {

dashboard/src/ui/mod.rs

@@ -100,7 +100,7 @@ impl TuiApp {
     }
 
     /// Update widgets with structured data from store (only for current host)
-    pub fn update_metrics(&mut self, metric_store: &MetricStore) {
+    pub fn update_metrics(&mut self, metric_store: &mut MetricStore) {
         if let Some(hostname) = self.current_host.clone() {
             // Get structured data for this host
             if let Some(agent_data) = metric_store.get_agent_data(&hostname) {
@@ -110,6 +110,14 @@ impl TuiApp {
                 host_widgets.system_widget.update_from_agent_data(agent_data);
                 host_widgets.services_widget.update_from_agent_data(agent_data);
 
+                // Update ZMQ stats
+                if let Some(zmq_stats) = metric_store.get_zmq_stats(&hostname) {
+                    host_widgets.system_widget.update_zmq_stats(
+                        zmq_stats.packets_received,
+                        zmq_stats.last_packet_age_secs
+                    );
+                }
+
                 host_widgets.last_update = Some(Instant::now());
             }
         }

dashboard/src/ui/widgets/system.rs

@@ -15,6 +15,10 @@ pub struct SystemWidget {
     nixos_build: Option<String>,
     agent_hash: Option<String>,
 
+    // ZMQ communication stats
+    zmq_packets_received: Option<u64>,
+    zmq_last_packet_age: Option<f64>,
+
     // Network interfaces
     network_interfaces: Vec<cm_dashboard_shared::NetworkInterfaceData>,
 
@@ -92,6 +96,8 @@ impl SystemWidget {
         Self {
             nixos_build: None,
             agent_hash: None,
+            zmq_packets_received: None,
+            zmq_last_packet_age: None,
             network_interfaces: Vec::new(),
             cpu_load_1min: None,
             cpu_load_5min: None,
@@ -154,6 +160,12 @@ impl SystemWidget {
     pub fn _get_agent_hash(&self) -> Option<&String> {
         self.agent_hash.as_ref()
     }
+
+    /// Update ZMQ communication statistics
+    pub fn update_zmq_stats(&mut self, packets_received: u64, last_packet_age_secs: f64) {
+        self.zmq_packets_received = Some(packets_received);
+        self.zmq_last_packet_age = Some(last_packet_age_secs);
+    }
 }
 
 use super::Widget;
@@ -629,10 +641,20 @@ impl SystemWidget {
         let virtual_interfaces: Vec<_> = self.network_interfaces.iter().filter(|i| !i.is_physical).collect();
 
         // Find standalone virtual interfaces (those without a parent)
-        let standalone_virtual: Vec<_> = virtual_interfaces.iter()
+        let mut standalone_virtual: Vec<_> = virtual_interfaces.iter()
             .filter(|i| i.parent_interface.is_none())
             .collect();
 
+        // Sort standalone virtual: VLANs first (by VLAN ID), then others alphabetically
+        standalone_virtual.sort_by(|a, b| {
+            match (a.vlan_id, b.vlan_id) {
+                (Some(vlan_a), Some(vlan_b)) => vlan_a.cmp(&vlan_b),
+                (Some(_), None) => std::cmp::Ordering::Less,
+                (None, Some(_)) => std::cmp::Ordering::Greater,
+                (None, None) => a.name.cmp(&b.name),
+            }
+        });
+
         // Render physical interfaces with their children
         for (phy_idx, interface) in physical.iter().enumerate() {
             let is_last_physical = phy_idx == physical.len() - 1 && standalone_virtual.is_empty();
@@ -646,7 +668,7 @@ impl SystemWidget {
             lines.push(Line::from(header_spans));
 
             // Find child interfaces for this physical interface
-            let children: Vec<_> = virtual_interfaces.iter()
+            let mut children: Vec<_> = virtual_interfaces.iter()
                 .filter(|vi| {
                     if let Some(parent) = &vi.parent_interface {
                         parent == &interface.name
@@ -656,6 +678,16 @@ impl SystemWidget {
                 })
                 .collect();
 
+            // Sort children: VLANs first (by VLAN ID), then others alphabetically
+            children.sort_by(|a, b| {
+                match (a.vlan_id, b.vlan_id) {
+                    (Some(vlan_a), Some(vlan_b)) => vlan_a.cmp(&vlan_b),
+                    (Some(_), None) => std::cmp::Ordering::Less,
+                    (None, Some(_)) => std::cmp::Ordering::Greater,
+                    (None, None) => a.name.cmp(&b.name),
+                }
+            });
+
             // Count total items under this physical interface (IPs + children)
             let ip_count = interface.ipv4_addresses.len() + interface.ipv6_addresses.len();
             let total_children = ip_count + children.len();
@@ -776,6 +808,18 @@ impl SystemWidget {
             Span::styled(format!("Agent: {}", agent_version_text), Typography::secondary())
         ]));
 
+        // ZMQ communication stats
+        if let (Some(packets), Some(age)) = (self.zmq_packets_received, self.zmq_last_packet_age) {
+            let age_text = if age < 1.0 {
+                format!("{:.0}ms ago", age * 1000.0)
+            } else {
+                format!("{:.1}s ago", age)
+            };
+            lines.push(Line::from(vec![
+                Span::styled(format!("ZMQ: {} pkts, last {}", packets, age_text), Typography::secondary())
+            ]));
+        }
+
         // CPU section
         lines.push(Line::from(vec![
             Span::styled("CPU:", Typography::widget_title())

shared/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "cm-dashboard-shared"
-version = "0.1.170"
+version = "0.1.186"
 edition = "2021"
 
 [dependencies]