Fix data caching to prevent empty broadcasts

CRITICAL FIX: Collectors now update cached AgentData instead of
creating new empty data each cycle. This prevents the dashboard
from seeing flashing/disappearing data.

- Add cached_agent_data field to Agent struct
- Update cached data when collectors run
- Always broadcast the full cached data every 2s
- Only individual collectors respect their intervals
- Bump version to v0.1.230

CLAUDE.md

@@ -327,9 +327,16 @@ Storage:
   ├─ ● Data_2: GGA04461 T: 28°C
   └─ ● Parity: WDZS8RY0 T: 29°C
 Backup:
+● Repo: 4
+  ├─ getea
+  ├─ vaultwarden
+  ├─ mysql
+  └─ immich
+● W800639Y W: 2%
+  ├─ ● Backup: 2025-11-29T04:00:01.324623
+  └─ ● Usage: 8% 70GB/916GB
 ● WD-WCC7K1234567 T: 32°C W: 12%
-  ├─ Last: 2h ago (12.3GB)
-  ├─ Next: in 22h
+  ├─ ● Backup: 2025-11-29T04:00:01.324623
   └─ ● Usage: 45% 678GB/1.5TB
 ```
 

Cargo.lock

@@ -279,7 +279,7 @@ checksum = "a1d728cc89cf3aee9ff92b05e62b19ee65a02b5702cff7d5a377e32c6ae29d8d"
 
 [[package]]
 name = "cm-dashboard"
-version = "0.1.203"
+version = "0.1.230"
 dependencies = [
  "anyhow",
  "chrono",
@@ -301,7 +301,7 @@ dependencies = [
 
 [[package]]
 name = "cm-dashboard-agent"
-version = "0.1.203"
+version = "0.1.230"
 dependencies = [
  "anyhow",
  "async-trait",
@@ -309,6 +309,7 @@ dependencies = [
  "chrono-tz",
  "clap",
  "cm-dashboard-shared",
+ "futures",
  "gethostname",
  "lettre",
  "reqwest",
@@ -324,7 +325,7 @@ dependencies = [
 
 [[package]]
 name = "cm-dashboard-shared"
-version = "0.1.203"
+version = "0.1.230"
 dependencies = [
  "chrono",
  "serde",
@@ -552,6 +553,21 @@ dependencies = [
  "percent-encoding",
 ]
 
+[[package]]
+name = "futures"
+version = "0.3.31"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "65bc07b1a8bc7c85c5f2e110c476c7389b4554ba72af57d8445ea63a576b0876"
+dependencies = [
+ "futures-channel",
+ "futures-core",
+ "futures-executor",
+ "futures-io",
+ "futures-sink",
+ "futures-task",
+ "futures-util",
+]
+
 [[package]]
 name = "futures-channel"
 version = "0.3.31"
@@ -559,6 +575,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "2dff15bf788c671c1934e366d07e30c1814a8ef514e1af724a602e8a2fbe1b10"
 dependencies = [
  "futures-core",
+ "futures-sink",
 ]
 
 [[package]]
@@ -567,12 +584,34 @@ version = "0.3.31"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "05f29059c0c2090612e8d742178b0580d2dc940c837851ad723096f87af6663e"
 
+[[package]]
+name = "futures-executor"
+version = "0.3.31"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1e28d1d997f585e54aebc3f97d39e72338912123a67330d723fdbb564d646c9f"
+dependencies = [
+ "futures-core",
+ "futures-task",
+ "futures-util",
+]
+
 [[package]]
 name = "futures-io"
 version = "0.3.31"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "9e5c1b78ca4aae1ac06c48a526a655760685149f0d465d21f37abfe57ce075c6"
 
+[[package]]
+name = "futures-macro"
+version = "0.3.31"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "162ee34ebcb7c64a8abebc059ce0fee27c2262618d7b60ed8faf72fef13c3650"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+
 [[package]]
 name = "futures-sink"
 version = "0.3.31"
@@ -591,8 +630,11 @@ version = "0.3.31"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "9fa08315bb612088cc391249efdc3bc77536f16c91f6cf495e6fbe85b20a4a81"
 dependencies = [
+ "futures-channel",
  "futures-core",
  "futures-io",
+ "futures-macro",
+ "futures-sink",
  "futures-task",
  "memchr",
  "pin-project-lite",

agent/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "cm-dashboard-agent"
-version = "0.1.204"
+version = "0.1.230"
 edition = "2021"
 
 [dependencies]
@@ -21,3 +21,4 @@ chrono-tz = "0.8"
 toml = { workspace = true }
 async-trait = "0.1"
 reqwest = { version = "0.11", features = ["json", "blocking"] }
+futures = "0.3"

agent/src/agent.rs

@@ -1,6 +1,6 @@
 use anyhow::Result;
 use gethostname::gethostname;
-use std::time::Duration;
+use std::time::{Duration, Instant};
 use tokio::time::interval;
 use tracing::{debug, error, info};
 
@@ -19,13 +19,22 @@ use crate::collectors::{
 use crate::notifications::NotificationManager;
 use cm_dashboard_shared::AgentData;
 
+/// Wrapper for collectors with timing information
+struct TimedCollector {
+    collector: Box<dyn Collector>,
+    interval: Duration,
+    last_collection: Option<Instant>,
+    name: String,
+}
+
 pub struct Agent {
     hostname: String,
     config: AgentConfig,
     zmq_handler: ZmqHandler,
-    collectors: Vec<Box<dyn Collector>>,
+    collectors: Vec<TimedCollector>,
     notification_manager: NotificationManager,
     previous_status: Option<SystemStatus>,
+    cached_agent_data: AgentData,
 }
 
 /// Track system component status for change detection
@@ -55,36 +64,78 @@ impl Agent {
             config.zmq.publisher_port
         );
 
-        // Initialize collectors
-        let mut collectors: Vec<Box<dyn Collector>> = Vec::new();
+        // Initialize collectors with timing information
+        let mut collectors: Vec<TimedCollector> = Vec::new();
 
         // Add enabled collectors
         if config.collectors.cpu.enabled {
-            collectors.push(Box::new(CpuCollector::new(config.collectors.cpu.clone())));
+            collectors.push(TimedCollector {
+                collector: Box::new(CpuCollector::new(config.collectors.cpu.clone())),
+                interval: Duration::from_secs(config.collectors.cpu.interval_seconds),
+                last_collection: None,
+                name: "CPU".to_string(),
+            });
+            info!("CPU collector initialized with {}s interval", config.collectors.cpu.interval_seconds);
         }
 
         if config.collectors.memory.enabled {
-            collectors.push(Box::new(MemoryCollector::new(config.collectors.memory.clone())));
+            collectors.push(TimedCollector {
+                collector: Box::new(MemoryCollector::new(config.collectors.memory.clone())),
+                interval: Duration::from_secs(config.collectors.memory.interval_seconds),
+                last_collection: None,
+                name: "Memory".to_string(),
+            });
+            info!("Memory collector initialized with {}s interval", config.collectors.memory.interval_seconds);
         }
 
         if config.collectors.disk.enabled {
-            collectors.push(Box::new(DiskCollector::new(config.collectors.disk.clone())));
+            collectors.push(TimedCollector {
+                collector: Box::new(DiskCollector::new(config.collectors.disk.clone())),
+                interval: Duration::from_secs(config.collectors.disk.interval_seconds),
+                last_collection: None,
+                name: "Disk".to_string(),
+            });
+            info!("Disk collector initialized with {}s interval", config.collectors.disk.interval_seconds);
         }
 
         if config.collectors.systemd.enabled {
-            collectors.push(Box::new(SystemdCollector::new(config.collectors.systemd.clone())));
+            collectors.push(TimedCollector {
+                collector: Box::new(SystemdCollector::new(config.collectors.systemd.clone())),
+                interval: Duration::from_secs(config.collectors.systemd.interval_seconds),
+                last_collection: None,
+                name: "Systemd".to_string(),
+            });
+            info!("Systemd collector initialized with {}s interval", config.collectors.systemd.interval_seconds);
         }
 
         if config.collectors.backup.enabled {
-            collectors.push(Box::new(BackupCollector::new()));
+            collectors.push(TimedCollector {
+                collector: Box::new(BackupCollector::new()),
+                interval: Duration::from_secs(config.collectors.backup.interval_seconds),
+                last_collection: None,
+                name: "Backup".to_string(),
+            });
+            info!("Backup collector initialized with {}s interval", config.collectors.backup.interval_seconds);
         }
 
         if config.collectors.network.enabled {
-            collectors.push(Box::new(NetworkCollector::new(config.collectors.network.clone())));
+            collectors.push(TimedCollector {
+                collector: Box::new(NetworkCollector::new(config.collectors.network.clone())),
+                interval: Duration::from_secs(config.collectors.network.interval_seconds),
+                last_collection: None,
+                name: "Network".to_string(),
+            });
+            info!("Network collector initialized with {}s interval", config.collectors.network.interval_seconds);
         }
 
         if config.collectors.nixos.enabled {
-            collectors.push(Box::new(NixOSCollector::new(config.collectors.nixos.clone())));
+            collectors.push(TimedCollector {
+                collector: Box::new(NixOSCollector::new(config.collectors.nixos.clone())),
+                interval: Duration::from_secs(config.collectors.nixos.interval_seconds),
+                last_collection: None,
+                name: "NixOS".to_string(),
+            });
+            info!("NixOS collector initialized with {}s interval", config.collectors.nixos.interval_seconds);
         }
 
         info!("Initialized {} collectors", collectors.len());
@@ -93,6 +144,9 @@ impl Agent {
         let notification_manager = NotificationManager::new(&config.notifications, &hostname)?;
         info!("Notification manager initialized");
 
+        // Initialize cached agent data
+        let cached_agent_data = AgentData::new(hostname.clone(), env!("CARGO_PKG_VERSION").to_string());
+
         Ok(Self {
             hostname,
             config,
@@ -100,6 +154,7 @@ impl Agent {
             collectors,
             notification_manager,
             previous_status: None,
+            cached_agent_data,
         })
     }
 
@@ -114,7 +169,7 @@ impl Agent {
 
         // Set up intervals
         let mut transmission_interval = interval(Duration::from_secs(
-            self.config.collection_interval_seconds,
+            self.config.zmq.transmission_interval_seconds,
         ));
         let mut notification_interval = interval(Duration::from_secs(30)); // Check notifications every 30s
 
@@ -149,24 +204,47 @@ impl Agent {
     async fn collect_and_broadcast(&mut self) -> Result<()> {
         debug!("Starting structured data collection");
 
-        // Initialize empty AgentData
-        let mut agent_data = AgentData::new(self.hostname.clone(), env!("CARGO_PKG_VERSION").to_string());
+        // Collect data from collectors whose intervals have elapsed
+        // Update cached_agent_data with new data
+        let now = Instant::now();
+        for timed_collector in &mut self.collectors {
+            let should_collect = match timed_collector.last_collection {
+                None => true, // First collection
+                Some(last_time) => now.duration_since(last_time) >= timed_collector.interval,
+            };
 
-        // Collect data from all collectors
-        for collector in &self.collectors {
-            if let Err(e) = collector.collect_structured(&mut agent_data).await {
-                error!("Collector failed: {}", e);
-                // Continue with other collectors even if one fails
+            if should_collect {
+                if let Err(e) = timed_collector.collector.collect_structured(&mut self.cached_agent_data).await {
+                    error!("Collector {} failed: {}", timed_collector.name, e);
+                    // Update last_collection time even on failure to prevent immediate retries
+                    timed_collector.last_collection = Some(now);
+                } else {
+                    timed_collector.last_collection = Some(now);
+                    debug!(
+                        "Collected from {} ({}s interval)",
+                        timed_collector.name,
+                        timed_collector.interval.as_secs()
+                    );
+                }
             }
         }
 
+        // Update timestamp on cached data
+        self.cached_agent_data.timestamp = std::time::SystemTime::now()
+            .duration_since(std::time::UNIX_EPOCH)
+            .unwrap()
+            .as_secs();
+
+        // Clone for notification check (to avoid borrow issues)
+        let agent_data_snapshot = self.cached_agent_data.clone();
+
         // Check for status changes and send notifications
-        if let Err(e) = self.check_status_changes_and_notify(&agent_data).await {
+        if let Err(e) = self.check_status_changes_and_notify(&agent_data_snapshot).await {
             error!("Failed to check status changes: {}", e);
         }
 
-        // Broadcast the structured data via ZMQ
-        if let Err(e) = self.zmq_handler.publish_agent_data(&agent_data).await {
+        // Broadcast the cached structured data via ZMQ
+        if let Err(e) = self.zmq_handler.publish_agent_data(&agent_data_snapshot).await {
             error!("Failed to broadcast agent data: {}", e);
         } else {
             debug!("Successfully broadcast structured agent data");

agent/src/collectors/backup.rs

@@ -1,36 +1,66 @@
 use async_trait::async_trait;
-use cm_dashboard_shared::{AgentData, BackupData, BackupDiskData};
+use cm_dashboard_shared::{AgentData, BackupData, BackupDiskData, Status};
 use serde::{Deserialize, Serialize};
-use std::collections::HashMap;
+use std::collections::{HashMap, HashSet};
 use std::fs;
-use std::path::Path;
-use tracing::debug;
+use std::path::{Path, PathBuf};
+use tracing::{debug, warn};
 
 use super::{Collector, CollectorError};
 
 /// Backup collector that reads backup status from TOML files with structured data output
 pub struct BackupCollector {
-    /// Path to backup status file
-    status_file_path: String,
+    /// Directory containing backup status files
+    status_dir: String,
 }
 
 impl BackupCollector {
     pub fn new() -> Self {
         Self {
-            status_file_path: "/var/lib/backup/backup-status.toml".to_string(),
+            status_dir: "/var/lib/backup/status".to_string(),
         }
     }
 
-    /// Read backup status from TOML file
-    async fn read_backup_status(&self) -> Result<Option<BackupStatusToml>, CollectorError> {
-        if !Path::new(&self.status_file_path).exists() {
-            debug!("Backup status file not found: {}", self.status_file_path);
-            return Ok(None);
+    /// Scan directory for all backup status files
+    async fn scan_status_files(&self) -> Result<Vec<PathBuf>, CollectorError> {
+        let status_path = Path::new(&self.status_dir);
+
+        if !status_path.exists() {
+            debug!("Backup status directory not found: {}", self.status_dir);
+            return Ok(Vec::new());
         }
 
-        let content = fs::read_to_string(&self.status_file_path)
+        let mut status_files = Vec::new();
+
+        match fs::read_dir(status_path) {
+            Ok(entries) => {
+                for entry in entries {
+                    if let Ok(entry) = entry {
+                        let path = entry.path();
+                        if path.is_file() {
+                            if let Some(filename) = path.file_name().and_then(|n| n.to_str()) {
+                                if filename.starts_with("backup-status-") && filename.ends_with(".toml") {
+                                    status_files.push(path);
+                                }
+                            }
+                        }
+                    }
+                }
+            }
+            Err(e) => {
+                warn!("Failed to read backup status directory: {}", e);
+                return Ok(Vec::new());
+            }
+        }
+
+        Ok(status_files)
+    }
+
+    /// Read a single backup status file
+    async fn read_status_file(&self, path: &Path) -> Result<BackupStatusToml, CollectorError> {
+        let content = fs::read_to_string(path)
             .map_err(|e| CollectorError::SystemRead {
-                path: self.status_file_path.clone(),
+                path: path.to_string_lossy().to_string(),
                 error: e.to_string(),
             })?;
 
@@ -40,66 +70,122 @@ impl BackupCollector {
                 error: format!("Failed to parse backup status TOML: {}", e),
             })?;
 
-        Ok(Some(status))
+        Ok(status)
+    }
+
+    /// Calculate backup status from TOML status field
+    fn calculate_backup_status(status_str: &str) -> Status {
+        match status_str.to_lowercase().as_str() {
+            "success" => Status::Ok,
+            "warning" => Status::Warning,
+            "failed" | "error" => Status::Critical,
+            _ => Status::Unknown,
+        }
+    }
+
+    /// Calculate usage status from disk usage percentage
+    fn calculate_usage_status(usage_percent: f32) -> Status {
+        if usage_percent < 80.0 {
+            Status::Ok
+        } else if usage_percent < 90.0 {
+            Status::Warning
+        } else {
+            Status::Critical
+        }
     }
 
     /// Convert BackupStatusToml to BackupData and populate AgentData
     async fn populate_backup_data(&self, agent_data: &mut AgentData) -> Result<(), CollectorError> {
-        if let Some(backup_status) = self.read_backup_status().await? {
-            // Use raw start_time string from TOML
+        let status_files = self.scan_status_files().await?;
 
-            // Extract disk information
-            let repository_disk = if let Some(disk_space) = &backup_status.disk_space {
-                Some(BackupDiskData {
-                    serial: backup_status.disk_serial_number.clone().unwrap_or_else(|| "Unknown".to_string()),
-                    usage_percent: disk_space.usage_percent as f32,
-                    used_gb: disk_space.used_gb as f32,
-                    total_gb: disk_space.total_gb as f32,
-                    wear_percent: backup_status.disk_wear_percent,
-                    temperature_celsius: None, // Not available in current TOML
-                })
-            } else if let Some(serial) = &backup_status.disk_serial_number {
-                // Fallback: create minimal disk info if we have serial but no disk_space
-                Some(BackupDiskData {
-                    serial: serial.clone(),
-                    usage_percent: 0.0,
-                    used_gb: 0.0,
-                    total_gb: 0.0,
-                    wear_percent: backup_status.disk_wear_percent,
-                    temperature_celsius: None,
-                })
-            } else {
-                None
-            };
-
-            // Calculate total repository size from services
-            let total_size_gb = backup_status.services
-                .values()
-                .map(|service| service.repo_size_bytes as f32 / (1024.0 * 1024.0 * 1024.0))
-                .sum::<f32>();
-
-            let backup_data = BackupData {
-                status: backup_status.status,
-                total_size_gb: Some(total_size_gb),
-                repository_health: Some("ok".to_string()), // Derive from status if needed
-                repository_disk,
-                last_backup_size_gb: None, // Not available in current TOML format
-                start_time_raw: Some(backup_status.start_time),
-            };
-
-            agent_data.backup = backup_data;
-        } else {
-            // No backup status available - set default values
+        if status_files.is_empty() {
+            debug!("No backup status files found");
             agent_data.backup = BackupData {
-                status: "unavailable".to_string(),
-                total_size_gb: None,
-                repository_health: None,
-                repository_disk: None,
-                last_backup_size_gb: None,
-                start_time_raw: None,
+                repositories: Vec::new(),
+                repository_status: Status::Unknown,
+                disks: Vec::new(),
             };
+            return Ok(());
         }
 
+        let mut all_repositories = HashSet::new();
+        let mut disks = Vec::new();
+        let mut worst_status = Status::Ok;
+
+        for status_file in status_files {
+            match self.read_status_file(&status_file).await {
+                Ok(backup_status) => {
+                    // Collect all service names
+                    for service_name in backup_status.services.keys() {
+                        all_repositories.insert(service_name.clone());
+                    }
+
+                    // Calculate backup status
+                    let backup_status_enum = Self::calculate_backup_status(&backup_status.status);
+
+                    // Calculate usage status from disk space
+                    let (usage_percent, used_gb, total_gb, usage_status) = if let Some(disk_space) = &backup_status.disk_space {
+                        let usage_pct = disk_space.usage_percent as f32;
+                        (
+                            usage_pct,
+                            disk_space.used_gb as f32,
+                            disk_space.total_gb as f32,
+                            Self::calculate_usage_status(usage_pct),
+                        )
+                    } else {
+                        (0.0, 0.0, 0.0, Status::Unknown)
+                    };
+
+                    // Update worst status
+                    worst_status = worst_status.max(backup_status_enum).max(usage_status);
+
+                    // Build service list for this disk
+                    let services: Vec<String> = backup_status.services.keys().cloned().collect();
+
+                    // Get min and max archive counts to detect inconsistencies
+                    let archives_min: i64 = backup_status.services.values()
+                        .map(|service| service.archive_count)
+                        .min()
+                        .unwrap_or(0);
+
+                    let archives_max: i64 = backup_status.services.values()
+                        .map(|service| service.archive_count)
+                        .max()
+                        .unwrap_or(0);
+
+                    // Create disk data
+                    let disk_data = BackupDiskData {
+                        serial: backup_status.disk_serial_number.unwrap_or_else(|| "Unknown".to_string()),
+                        product_name: backup_status.disk_product_name,
+                        wear_percent: backup_status.disk_wear_percent,
+                        temperature_celsius: None, // Not available in current TOML
+                        last_backup_time: Some(backup_status.start_time),
+                        backup_status: backup_status_enum,
+                        disk_usage_percent: usage_percent,
+                        disk_used_gb: used_gb,
+                        disk_total_gb: total_gb,
+                        usage_status,
+                        services,
+                        archives_min,
+                        archives_max,
+                    };
+
+                    disks.push(disk_data);
+                }
+                Err(e) => {
+                    warn!("Failed to read backup status file {:?}: {}", status_file, e);
+                }
+            }
+        }
+
+        let repositories: Vec<String> = all_repositories.into_iter().collect();
+
+        agent_data.backup = BackupData {
+            repositories,
+            repository_status: worst_status,
+            disks,
+        };
+
         Ok(())
     }
 }

agent/src/collectors/cpu.rs

@@ -119,36 +119,69 @@ impl CpuCollector {
         utils::parse_u64(content.trim())
     }
 
-    /// Collect CPU frequency and populate AgentData
-    async fn collect_frequency(&self, agent_data: &mut AgentData) -> Result<(), CollectorError> {
-        // Try scaling frequency first (more accurate for current frequency)
-        if let Ok(freq) =
-            utils::read_proc_file("/sys/devices/system/cpu/cpu0/cpufreq/scaling_cur_freq")
-        {
-            if let Ok(freq_khz) = utils::parse_u64(freq.trim()) {
-                let freq_mhz = freq_khz as f32 / 1000.0;
-                agent_data.system.cpu.frequency_mhz = freq_mhz;
-                return Ok(());
-            }
-        }
+    /// Collect CPU C-state (idle depth) and populate AgentData with top 3 C-states by usage
+    async fn collect_cstate(&self, agent_data: &mut AgentData) -> Result<(), CollectorError> {
+        // Read C-state usage from first CPU (representative of overall system)
+        // C-states indicate CPU idle depth: C1=light sleep, C6=deep sleep, C10=deepest
 
-        // Fallback: parse /proc/cpuinfo for base frequency
-        if let Ok(content) = utils::read_proc_file("/proc/cpuinfo") {
-            for line in content.lines() {
-                if line.starts_with("cpu MHz") {
-                    if let Some(freq_str) = line.split(':').nth(1) {
-                        if let Ok(freq_mhz) = utils::parse_f32(freq_str) {
-                            agent_data.system.cpu.frequency_mhz = freq_mhz;
-                            return Ok(());
+        let mut cstate_times: Vec<(String, u64)> = Vec::new();
+        let mut total_time: u64 = 0;
+
+        // Collect all C-state times from CPU0
+        for state_num in 0..=10 {
+            let time_path = format!("/sys/devices/system/cpu/cpu0/cpuidle/state{}/time", state_num);
+            let name_path = format!("/sys/devices/system/cpu/cpu0/cpuidle/state{}/name", state_num);
+
+            if let Ok(time_str) = utils::read_proc_file(&time_path) {
+                if let Ok(time) = utils::parse_u64(time_str.trim()) {
+                    if let Ok(name) = utils::read_proc_file(&name_path) {
+                        let state_name = name.trim();
+                        // Skip POLL state (not real idle)
+                        if state_name != "POLL" && time > 0 {
+                            // Extract "C" + digits pattern (C3, C10, etc.) to reduce JSON size
+                            // Handles formats like "C3_ACPI", "C10_MWAIT", etc.
+                            let clean_name = if let Some(c_pos) = state_name.find('C') {
+                                let rest = &state_name[c_pos + 1..];
+                                let digit_count = rest.chars().take_while(|c| c.is_ascii_digit()).count();
+                                if digit_count > 0 {
+                                    state_name[c_pos..c_pos + 1 + digit_count].to_string()
+                                } else {
+                                    state_name.to_string()
+                                }
+                            } else {
+                                state_name.to_string()
+                            };
+                            cstate_times.push((clean_name, time));
+                            total_time += time;
                         }
                     }
-                    break; // Only need first CPU entry
                 }
+            } else {
+                // No more states available
+                break;
             }
         }
 
-        debug!("CPU frequency not available");
-        // Leave frequency as 0.0 if not available
+        // Sort by time descending to get top 3
+        cstate_times.sort_by(|a, b| b.1.cmp(&a.1));
+
+        // Calculate percentages for top 3 and populate AgentData
+        agent_data.system.cpu.cstates = cstate_times
+            .iter()
+            .take(3)
+            .map(|(name, time)| {
+                let percent = if total_time > 0 {
+                    (*time as f32 / total_time as f32) * 100.0
+                } else {
+                    0.0
+                };
+                cm_dashboard_shared::CStateInfo {
+                    name: name.clone(),
+                    percent,
+                }
+            })
+            .collect();
+
         Ok(())
     }
 }
@@ -165,8 +198,8 @@ impl Collector for CpuCollector {
         // Collect temperature (optional)
         self.collect_temperature(agent_data).await?;
 
-        // Collect frequency (optional)
-        self.collect_frequency(agent_data).await?;
+        // Collect C-state (CPU idle depth)
+        self.collect_cstate(agent_data).await?;
 
         let duration = start.elapsed();
         debug!("CPU collection completed in {:?}", duration);

agent/src/collectors/disk.rs

@@ -3,10 +3,9 @@ use async_trait::async_trait;
 use cm_dashboard_shared::{AgentData, DriveData, FilesystemData, PoolData, HysteresisThresholds, Status};
 
 use crate::config::DiskConfig;
-use std::process::Command;
-use std::time::Instant;
+use tokio::process::Command as TokioCommand;
+use std::process::Command as StdCommand;
 use std::collections::HashMap;
-use tracing::debug;
 
 use super::{Collector, CollectorError};
 
@@ -67,9 +66,6 @@ impl DiskCollector {
 
     /// Collect all storage data and populate AgentData
     async fn collect_storage_data(&self, agent_data: &mut AgentData) -> Result<(), CollectorError> {
-        let start_time = Instant::now();
-        debug!("Starting clean storage collection");
-
         // Step 1: Get mount points and their backing devices
         let mount_devices = self.get_mount_devices().await?;
         
@@ -104,9 +100,6 @@ impl DiskCollector {
         self.populate_drives_data(&physical_drives, &smart_data, agent_data)?;
         self.populate_pools_data(&mergerfs_pools, &smart_data, agent_data)?;
 
-        let elapsed = start_time.elapsed();
-        debug!("Storage collection completed in {:?}", elapsed);
-
         Ok(())
     }
 
@@ -114,7 +107,7 @@ impl DiskCollector {
     async fn get_mount_devices(&self) -> Result<HashMap<String, String>, CollectorError> {
         use super::run_command_with_timeout;
 
-        let mut cmd = Command::new("lsblk");
+        let mut cmd = TokioCommand::new("lsblk");
         cmd.args(&["-rn", "-o", "NAME,MOUNTPOINT"]);
 
         let output = run_command_with_timeout(cmd, 2).await
@@ -141,7 +134,6 @@ impl DiskCollector {
             }
         }
 
-        debug!("Found {} mounted block devices", mount_devices.len());
         Ok(mount_devices)
     }
 
@@ -154,8 +146,8 @@ impl DiskCollector {
                 Ok((total, used)) => {
                     filesystem_usage.insert(mount_point.clone(), (total, used));
                 }
-                Err(e) => {
-                    debug!("Failed to get filesystem info for {}: {}", mount_point, e);
+                Err(_e) => {
+                    // Silently skip filesystems we can't read
                 }
             }
         }
@@ -176,8 +168,6 @@ impl DiskCollector {
                 // Only add if we don't already have usage data for this mount point
                 if !filesystem_usage.contains_key(&mount_point) {
                     if let Ok((total, used)) = self.get_filesystem_info(&mount_point) {
-                        debug!("Added MergerFS filesystem usage for {}: {}GB total, {}GB used", 
-                            mount_point, total as f32 / (1024.0 * 1024.0 * 1024.0), used as f32 / (1024.0 * 1024.0 * 1024.0));
                         filesystem_usage.insert(mount_point, (total, used));
                     }
                 }
@@ -189,7 +179,7 @@ impl DiskCollector {
 
     /// Get filesystem info for a single mount point
     fn get_filesystem_info(&self, mount_point: &str) -> Result<(u64, u64), CollectorError> {
-        let output = std::process::Command::new("timeout")
+        let output = StdCommand::new("timeout")
             .args(&["2", "df", "--block-size=1", mount_point])
             .output()
             .map_err(|e| CollectorError::SystemRead {
@@ -254,7 +244,6 @@ impl DiskCollector {
                 };
 
                 if pool_name.is_empty() {
-                    debug!("Skipping mergerfs pool with empty name: {}", mount_point);
                     continue;
                 }
                 
@@ -282,8 +271,7 @@ impl DiskCollector {
                 // Categorize as data vs parity drives
                 let (data_drives, parity_drives) = match self.categorize_pool_drives(&all_member_paths) {
                     Ok(drives) => drives,
-                    Err(e) => {
-                        debug!("Failed to categorize drives for pool {}: {}. Skipping.", mount_point, e);
+                    Err(_e) => {
                         continue;
                     }
                 };
@@ -299,7 +287,6 @@ impl DiskCollector {
             }
         }
 
-        debug!("Found {} mergerfs pools", pools.len());
         Ok(pools)
     }
 
@@ -386,9 +373,9 @@ impl DiskCollector {
         device.to_string()
     }
 
-    /// Get SMART data for drives
+    /// Get SMART data for drives in parallel
     async fn get_smart_data_for_drives(&self, physical_drives: &[PhysicalDrive], mergerfs_pools: &[MergerfsPool]) -> HashMap<String, SmartData> {
-        let mut smart_data = HashMap::new();
+        use futures::future::join_all;
 
         // Collect all drive names
         let mut all_drives = std::collections::HashSet::new();
@@ -404,9 +391,24 @@ impl DiskCollector {
             }
         }
 
-        // Get SMART data for each drive
-        for drive_name in all_drives {
-            if let Ok(data) = self.get_smart_data(&drive_name).await {
+        // Collect SMART data for all drives in parallel
+        let futures: Vec<_> = all_drives
+            .iter()
+            .map(|drive_name| {
+                let drive = drive_name.clone();
+                async move {
+                    let result = self.get_smart_data(&drive).await;
+                    (drive, result)
+                }
+            })
+            .collect();
+
+        let results = join_all(futures).await;
+
+        // Build HashMap from results
+        let mut smart_data = HashMap::new();
+        for (drive_name, result) in results {
+            if let Ok(data) = result {
                 smart_data.insert(drive_name, data);
             }
         }
@@ -420,7 +422,7 @@ impl DiskCollector {
 
         // Use direct smartctl (no sudo) - service has CAP_SYS_RAWIO and CAP_SYS_ADMIN capabilities
         // For NVMe drives, specify device type explicitly
-        let mut cmd = Command::new("smartctl");
+        let mut cmd = TokioCommand::new("smartctl");
         if drive_name.starts_with("nvme") {
             cmd.args(&["-d", "nvme", "-a", &format!("/dev/{}", drive_name)]);
         } else {
@@ -435,8 +437,10 @@ impl DiskCollector {
 
         let output_str = String::from_utf8_lossy(&output.stdout);
 
-        if !output.status.success() {
-            // Return unknown data rather than failing completely
+        // Note: smartctl returns non-zero exit codes for warnings (like exit code 32
+        // for "temperature was high in the past"), but the output data is still valid.
+        // Only check if we got any output at all, don't reject based on exit code.
+        if output_str.is_empty() {
             return Ok(SmartData {
                 health: "UNKNOWN".to_string(),
                 serial_number: None,
@@ -763,7 +767,7 @@ impl DiskCollector {
     /// Get drive information for a mount path
     fn get_drive_info_for_path(&self, path: &str) -> anyhow::Result<PoolDrive> {
         // Use lsblk to find the backing device with timeout
-        let output = Command::new("timeout")
+        let output = StdCommand::new("timeout")
             .args(&["2", "lsblk", "-rn", "-o", "NAME,MOUNTPOINT"])
             .output()
             .map_err(|e| anyhow::anyhow!("Failed to run lsblk: {}", e))?;
@@ -786,19 +790,12 @@ impl DiskCollector {
         // Extract base device name (e.g., "sda1" -> "sda")
         let base_device = self.extract_base_device(&format!("/dev/{}", device));
 
-        // Get temperature from SMART data if available
-        let temperature = if let Ok(smart_data) = tokio::task::block_in_place(|| {
-            tokio::runtime::Handle::current().block_on(self.get_smart_data(&base_device))
-        }) {
-            smart_data.temperature_celsius
-        } else {
-            None
-        };
-        
+        // Temperature will be filled in later from parallel SMART collection
+        // Don't collect it here to avoid sequential blocking with problematic async nesting
         Ok(PoolDrive {
             name: base_device,
             mount_point: path.to_string(),
-            temperature_celsius: temperature,
+            temperature_celsius: None,
         })
     }
 

agent/src/collectors/mod.rs

@@ -1,8 +1,7 @@
 use async_trait::async_trait;
 use cm_dashboard_shared::{AgentData};
-use std::process::{Command, Output};
+use std::process::Output;
 use std::time::Duration;
-use tokio::time::timeout;
 
 pub mod backup;
 pub mod cpu;
@@ -16,16 +15,34 @@ pub mod systemd;
 pub use error::CollectorError;
 
 /// Run a command with a timeout to prevent blocking
-pub async fn run_command_with_timeout(mut cmd: Command, timeout_secs: u64) -> std::io::Result<Output> {
+/// Properly kills the process if timeout is exceeded
+pub async fn run_command_with_timeout(mut cmd: tokio::process::Command, timeout_secs: u64) -> std::io::Result<Output> {
+    use tokio::time::timeout;
+    use std::process::Stdio;
     let timeout_duration = Duration::from_secs(timeout_secs);
 
-    match timeout(timeout_duration, tokio::task::spawn_blocking(move || cmd.output())).await {
-        Ok(Ok(result)) => result,
-        Ok(Err(e)) => Err(std::io::Error::new(std::io::ErrorKind::Other, e)),
-        Err(_) => Err(std::io::Error::new(
-            std::io::ErrorKind::TimedOut,
-            format!("Command timed out after {} seconds", timeout_secs)
-        )),
+    // Configure stdio to capture output
+    cmd.stdout(Stdio::piped());
+    cmd.stderr(Stdio::piped());
+
+    let child = cmd.spawn()?;
+    let pid = child.id();
+
+    match timeout(timeout_duration, child.wait_with_output()).await {
+        Ok(result) => result,
+        Err(_) => {
+            // Timeout - force kill the process using system kill command
+            if let Some(process_id) = pid {
+                let _ = tokio::process::Command::new("kill")
+                    .args(&["-9", &process_id.to_string()])
+                    .output()
+                    .await;
+            }
+            Err(std::io::Error::new(
+                std::io::ErrorKind::TimedOut,
+                format!("Command timed out after {} seconds", timeout_secs)
+            ))
+        }
     }
 }
 

agent/src/collectors/systemd.rs

@@ -43,9 +43,10 @@ struct ServiceCacheState {
 /// Cached service status information from systemctl list-units
 #[derive(Debug, Clone)]
 struct ServiceStatusInfo {
-    load_state: String,
     active_state: String,
-    sub_state: String,
+    memory_bytes: Option<u64>,
+    restart_count: Option<u32>,
+    start_timestamp: Option<u64>,
 }
 
 impl SystemdCollector {
@@ -86,11 +87,20 @@ impl SystemdCollector {
         let mut complete_service_data = Vec::new();
         for service_name in &monitored_services {
             match self.get_service_status(service_name) {
-                Ok((active_status, _detailed_info)) => {
+                Ok(status_info) => {
                     let mut sub_services = Vec::new();
 
+                    // Calculate uptime if we have start timestamp
+                    let uptime_seconds = status_info.start_timestamp.and_then(|start| {
+                        let now = std::time::SystemTime::now()
+                            .duration_since(std::time::UNIX_EPOCH)
+                            .ok()?
+                            .as_secs();
+                        Some(now.saturating_sub(start))
+                    });
+
                     // Sub-service metrics for specific services (always include cached results)
-                    if service_name.contains("nginx") && active_status == "active" {
+                    if service_name.contains("nginx") && status_info.active_state == "active" {
                         let nginx_sites = self.get_nginx_site_metrics();
                         for (site_name, latency_ms) in nginx_sites {
                             let site_status = if latency_ms >= 0.0 && latency_ms < self.config.nginx_latency_critical_ms {
@@ -115,7 +125,7 @@ impl SystemdCollector {
                         }
                     }
 
-                    if service_name.contains("docker") && active_status == "active" {
+                    if service_name.contains("docker") && status_info.active_state == "active" {
                         let docker_containers = self.get_docker_containers();
                         for (container_name, container_status) in docker_containers {
                             // For now, docker containers have no additional metrics
@@ -153,8 +163,11 @@ impl SystemdCollector {
                     let service_data = ServiceData {
                         name: service_name.clone(),
                         user_stopped: false, // TODO: Integrate with service tracker
-                        service_status: self.calculate_service_status(service_name, &active_status),
+                        service_status: self.calculate_service_status(service_name, &status_info.active_state),
                         sub_services,
+                        memory_bytes: status_info.memory_bytes,
+                        restart_count: status_info.restart_count,
+                        uptime_seconds,
                     };
 
                     // Add to AgentData and cache
@@ -290,14 +303,13 @@ impl SystemdCollector {
             let fields: Vec<&str> = line.split_whitespace().collect();
             if fields.len() >= 4 && fields[0].ends_with(".service") {
                 let service_name = fields[0].trim_end_matches(".service");
-                let load_state = fields.get(1).unwrap_or(&"unknown").to_string();
                 let active_state = fields.get(2).unwrap_or(&"unknown").to_string();
-                let sub_state = fields.get(3).unwrap_or(&"unknown").to_string();
 
                 status_cache.insert(service_name.to_string(), ServiceStatusInfo {
-                    load_state,
                     active_state,
-                    sub_state,
+                    memory_bytes: None,
+                    restart_count: None,
+                    start_timestamp: None,
                 });
             }
         }
@@ -306,9 +318,10 @@ impl SystemdCollector {
         for service_name in &all_service_names {
             if !status_cache.contains_key(service_name) {
                 status_cache.insert(service_name.to_string(), ServiceStatusInfo {
-                    load_state: "not-loaded".to_string(),
                     active_state: "inactive".to_string(),
-                    sub_state: "dead".to_string(),
+                    memory_bytes: None,
+                    restart_count: None,
+                    start_timestamp: None,
                 });
             }
         }
@@ -340,36 +353,60 @@ impl SystemdCollector {
         Ok((services, status_cache))
     }
 
-    /// Get service status from cache (if available) or fallback to systemctl
-    fn get_service_status(&self, service: &str) -> Result<(String, String)> {
-        // Try to get status from cache first
-        if let Ok(state) = self.state.read() {
-            if let Some(cached_info) = state.service_status_cache.get(service) {
-                let active_status = cached_info.active_state.clone();
-                let detailed_info = format!(
-                    "LoadState={}\nActiveState={}\nSubState={}",
-                    cached_info.load_state,
-                    cached_info.active_state,
-                    cached_info.sub_state
-                );
-                return Ok((active_status, detailed_info));
+    /// Get service status with detailed metrics from systemctl
+    fn get_service_status(&self, service: &str) -> Result<ServiceStatusInfo> {
+        // Always fetch fresh data to get detailed metrics (memory, restarts, uptime)
+        // Note: Cache in service_status_cache only has basic active_state from discovery,
+        // with all detailed metrics set to None. We need fresh systemctl show data.
+
+        let output = Command::new("timeout")
+            .args(&[
+                "2",
+                "systemctl",
+                "show",
+                &format!("{}.service", service),
+                "--property=LoadState,ActiveState,SubState,MemoryCurrent,NRestarts,ExecMainStartTimestamp"
+            ])
+            .output()?;
+
+        let output_str = String::from_utf8(output.stdout)?;
+
+        // Parse properties
+        let mut active_state = String::new();
+        let mut memory_bytes = None;
+        let mut restart_count = None;
+        let mut start_timestamp = None;
+
+        for line in output_str.lines() {
+            if let Some(value) = line.strip_prefix("ActiveState=") {
+                active_state = value.to_string();
+            } else if let Some(value) = line.strip_prefix("MemoryCurrent=") {
+                if value != "[not set]" {
+                    memory_bytes = value.parse().ok();
+                }
+            } else if let Some(value) = line.strip_prefix("NRestarts=") {
+                restart_count = value.parse().ok();
+            } else if let Some(value) = line.strip_prefix("ExecMainStartTimestamp=") {
+                if value != "[not set]" && !value.is_empty() {
+                    // Parse timestamp to seconds since epoch
+                    if let Ok(output) = Command::new("date")
+                        .args(&["+%s", "-d", value])
+                        .output()
+                    {
+                        if let Ok(timestamp_str) = String::from_utf8(output.stdout) {
+                            start_timestamp = timestamp_str.trim().parse().ok();
+                        }
+                    }
+                }
             }
         }
 
-        // Fallback to systemctl if not in cache (with 2 second timeout)
-        let output = Command::new("timeout")
-            .args(&["2", "systemctl", "is-active", &format!("{}.service", service)])
-            .output()?;
-
-        let active_status = String::from_utf8(output.stdout)?.trim().to_string();
-
-        // Get more detailed info (with 2 second timeout)
-        let output = Command::new("timeout")
-            .args(&["2", "systemctl", "show", &format!("{}.service", service), "--property=LoadState,ActiveState,SubState"])
-            .output()?;
-
-        let detailed_info = String::from_utf8(output.stdout)?;
-        Ok((active_status, detailed_info))
+        Ok(ServiceStatusInfo {
+            active_state,
+            memory_bytes,
+            restart_count,
+            start_timestamp,
+        })
     }
 
     /// Check if service name matches pattern (supports wildcards like nginx*)

agent/src/config/mod.rs

@@ -13,7 +13,6 @@ pub struct AgentConfig {
     pub collectors: CollectorConfig,
     pub cache: CacheConfig,
     pub notifications: NotificationConfig,
-    pub collection_interval_seconds: u64,
 }
 
 /// ZMQ communication configuration

agent/src/config/validation.rs

@@ -11,9 +11,9 @@ pub fn validate_config(config: &AgentConfig) -> Result<()> {
         bail!("ZMQ bind address cannot be empty");
     }
 
-    // Validate collection interval
-    if config.collection_interval_seconds == 0 {
-        bail!("Collection interval cannot be 0");
+    // Validate ZMQ transmission interval
+    if config.zmq.transmission_interval_seconds == 0 {
+        bail!("ZMQ transmission interval cannot be 0");
     }
 
     // Validate CPU thresholds

dashboard/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "cm-dashboard"
-version = "0.1.204"
+version = "0.1.230"
 edition = "2021"
 
 [dependencies]

dashboard/src/ui/widgets/services.rs

@@ -11,6 +11,74 @@ use tracing::debug;
 use crate::ui::theme::{Components, StatusIcons, Theme, Typography};
 use ratatui::style::Style;
 
+/// Column visibility configuration based on terminal width
+#[derive(Debug, Clone, Copy)]
+struct ColumnVisibility {
+    show_name: bool,
+    show_status: bool,
+    show_ram: bool,
+    show_uptime: bool,
+    show_restarts: bool,
+}
+
+impl ColumnVisibility {
+    /// Calculate actual width needed for all columns
+    const NAME_WIDTH: u16 = 23;
+    const STATUS_WIDTH: u16 = 10;
+    const RAM_WIDTH: u16 = 8;
+    const UPTIME_WIDTH: u16 = 8;
+    const RESTARTS_WIDTH: u16 = 5;
+    const COLUMN_SPACING: u16 = 1; // Space between columns
+
+    /// Determine which columns to show based on available width
+    /// Priority order: Name > Status > RAM > Uptime > Restarts
+    fn from_width(width: u16) -> Self {
+        // Calculate cumulative widths for each configuration
+        let minimal = Self::NAME_WIDTH + Self::COLUMN_SPACING + Self::STATUS_WIDTH; // 34
+        let with_ram = minimal + Self::COLUMN_SPACING + Self::RAM_WIDTH; // 43
+        let with_uptime = with_ram + Self::COLUMN_SPACING + Self::UPTIME_WIDTH; // 52
+        let full = with_uptime + Self::COLUMN_SPACING + Self::RESTARTS_WIDTH; // 58
+
+        if width >= full {
+            // Show all columns
+            Self {
+                show_name: true,
+                show_status: true,
+                show_ram: true,
+                show_uptime: true,
+                show_restarts: true,
+            }
+        } else if width >= with_uptime {
+            // Hide restarts
+            Self {
+                show_name: true,
+                show_status: true,
+                show_ram: true,
+                show_uptime: true,
+                show_restarts: false,
+            }
+        } else if width >= with_ram {
+            // Hide uptime and restarts
+            Self {
+                show_name: true,
+                show_status: true,
+                show_ram: true,
+                show_uptime: false,
+                show_restarts: false,
+            }
+        } else {
+            // Minimal: Name + Status only
+            Self {
+                show_name: true,
+                show_status: true,
+                show_ram: false,
+                show_uptime: false,
+                show_restarts: false,
+            }
+        }
+    }
+}
+
 /// Services widget displaying hierarchical systemd service statuses
 #[derive(Clone)]
 pub struct ServicesWidget {
@@ -31,6 +99,9 @@ struct ServiceInfo {
     metrics: Vec<(String, f32, Option<String>)>, // (label, value, unit)
     widget_status: Status,
     service_type: String, // "nginx_site", "container", "image", or empty for parent services
+    memory_bytes: Option<u64>,
+    restart_count: Option<u32>,
+    uptime_seconds: Option<u64>,
 }
 
 impl ServicesWidget {
@@ -73,10 +144,12 @@ impl ServicesWidget {
     }
 
     /// Format parent service line - returns text without icon for span formatting
-    fn format_parent_service_line(&self, name: &str, info: &ServiceInfo) -> String {
-        // Truncate long service names to fit layout (account for icon space)
-        let short_name = if name.len() > 22 {
-            format!("{}...", &name[..19])
+    fn format_parent_service_line(&self, name: &str, info: &ServiceInfo, columns: ColumnVisibility) -> String {
+        // Truncate long service names to fit layout
+        // NAME_WIDTH - 3 chars for "..." = max displayable chars
+        let max_name_len = (ColumnVisibility::NAME_WIDTH - 3) as usize;
+        let short_name = if name.len() > max_name_len {
+            format!("{}...", &name[..max_name_len.saturating_sub(3)])
         } else {
             name.to_string()
         };
@@ -92,10 +165,59 @@ impl ServicesWidget {
             Status::Offline => "offline",
         };
 
-        format!(
-            "{:<23} {:<10}",
-            short_name, status_str
-        )
+        // Format memory
+        let memory_str = info.memory_bytes.map_or("-".to_string(), |bytes| {
+            let mb = bytes as f64 / (1024.0 * 1024.0);
+            if mb >= 1000.0 {
+                format!("{:.1}G", mb / 1024.0)
+            } else {
+                format!("{:.0}M", mb)
+            }
+        });
+
+        // Format uptime
+        let uptime_str = info.uptime_seconds.map_or("-".to_string(), |secs| {
+            let days = secs / 86400;
+            let hours = (secs % 86400) / 3600;
+            let mins = (secs % 3600) / 60;
+
+            if days > 0 {
+                format!("{}d{}h", days, hours)
+            } else if hours > 0 {
+                format!("{}h{}m", hours, mins)
+            } else {
+                format!("{}m", mins)
+            }
+        });
+
+        // Format restarts (show "!" if > 0 to indicate instability)
+        let restart_str = info.restart_count.map_or("-".to_string(), |count| {
+            if count > 0 {
+                format!("!{}", count)
+            } else {
+                "0".to_string()
+            }
+        });
+
+        // Build format string based on column visibility
+        let mut parts = Vec::new();
+        if columns.show_name {
+            parts.push(format!("{:<width$}", short_name, width = ColumnVisibility::NAME_WIDTH as usize));
+        }
+        if columns.show_status {
+            parts.push(format!("{:<width$}", status_str, width = ColumnVisibility::STATUS_WIDTH as usize));
+        }
+        if columns.show_ram {
+            parts.push(format!("{:<width$}", memory_str, width = ColumnVisibility::RAM_WIDTH as usize));
+        }
+        if columns.show_uptime {
+            parts.push(format!("{:<width$}", uptime_str, width = ColumnVisibility::UPTIME_WIDTH as usize));
+        }
+        if columns.show_restarts {
+            parts.push(format!("{:<width$}", restart_str, width = ColumnVisibility::RESTARTS_WIDTH as usize));
+        }
+
+        parts.join(" ")
     }
 
 
@@ -280,6 +402,9 @@ impl Widget for ServicesWidget {
                 metrics: Vec::new(), // Parent services don't have custom metrics
                 widget_status: service.service_status,
                 service_type: String::new(), // Parent services have no type
+                memory_bytes: service.memory_bytes,
+                restart_count: service.restart_count,
+                uptime_seconds: service.uptime_seconds,
             };
             self.parent_services.insert(service.name.clone(), parent_info);
 
@@ -296,6 +421,9 @@ impl Widget for ServicesWidget {
                         metrics,
                         widget_status: sub_service.service_status,
                         service_type: sub_service.service_type.clone(),
+                        memory_bytes: None, // Sub-services don't have individual metrics yet
+                        restart_count: None,
+                        uptime_seconds: None,
                     };
                     sub_list.push((sub_service.name.clone(), sub_info));
                 }
@@ -338,6 +466,9 @@ impl ServicesWidget {
                                     metrics: Vec::new(),
                                     widget_status: Status::Unknown,
                                     service_type: String::new(),
+                                    memory_bytes: None,
+                                    restart_count: None,
+                                    uptime_seconds: None,
                                 });
 
                         if metric.name.ends_with("_status") {
@@ -364,6 +495,9 @@ impl ServicesWidget {
                                     metrics: Vec::new(),
                                     widget_status: Status::Unknown,
                                     service_type: String::new(), // Unknown type in legacy path
+                                    memory_bytes: None,
+                                    restart_count: None,
+                                    uptime_seconds: None,
                                 },
                             ));
                             &mut sub_service_list.last_mut().unwrap().1
@@ -427,11 +561,28 @@ impl ServicesWidget {
             .constraints([Constraint::Length(1), Constraint::Min(0)])
             .split(inner_area);
 
-        // Header
-        let header = format!(
-            "{:<25} {:<10} {:<8} {:<8}",
-            "Service:", "Status:", "RAM:", "Disk:"
-        );
+        // Determine which columns to show based on available width
+        let columns = ColumnVisibility::from_width(inner_area.width);
+
+        // Build header based on visible columns
+        let mut header_parts = Vec::new();
+        if columns.show_name {
+            header_parts.push(format!("{:<width$}", "Service:", width = ColumnVisibility::NAME_WIDTH as usize));
+        }
+        if columns.show_status {
+            header_parts.push(format!("{:<width$}", "Status:", width = ColumnVisibility::STATUS_WIDTH as usize));
+        }
+        if columns.show_ram {
+            header_parts.push(format!("{:<width$}", "RAM:", width = ColumnVisibility::RAM_WIDTH as usize));
+        }
+        if columns.show_uptime {
+            header_parts.push(format!("{:<width$}", "Uptime:", width = ColumnVisibility::UPTIME_WIDTH as usize));
+        }
+        if columns.show_restarts {
+            header_parts.push(format!("{:<width$}", "↻:", width = ColumnVisibility::RESTARTS_WIDTH as usize));
+        }
+        let header = header_parts.join(" ");
+
         let header_para = Paragraph::new(header).style(Typography::muted());
         frame.render_widget(header_para, content_chunks[0]);
 
@@ -443,11 +594,11 @@ impl ServicesWidget {
         }
 
         // Render the services list
-        self.render_services(frame, content_chunks[1], is_focused);
+        self.render_services(frame, content_chunks[1], is_focused, columns);
     }
 
     /// Render services list
-    fn render_services(&mut self, frame: &mut Frame, area: Rect, is_focused: bool) {
+    fn render_services(&mut self, frame: &mut Frame, area: Rect, is_focused: bool, columns: ColumnVisibility) {
         // Build hierarchical service list for display
         let mut display_lines: Vec<(String, Status, bool, Option<(ServiceInfo, bool)>)> = Vec::new();
 
@@ -457,7 +608,7 @@ impl ServicesWidget {
 
         for (parent_name, parent_info) in parent_services {
             // Add parent service line
-            let parent_line = self.format_parent_service_line(parent_name, parent_info);
+            let parent_line = self.format_parent_service_line(parent_name, parent_info, columns);
             display_lines.push((parent_line, parent_info.widget_status, false, None));
 
             // Add sub-services for this parent (if any)

dashboard/src/ui/widgets/system.rs

@@ -26,7 +26,7 @@ pub struct SystemWidget {
     cpu_load_1min: Option<f32>,
     cpu_load_5min: Option<f32>,
     cpu_load_15min: Option<f32>,
-    cpu_frequency: Option<f32>,
+    cpu_cstates: Vec<cm_dashboard_shared::CStateInfo>,
     cpu_status: Status,
     
     // Memory metrics
@@ -45,15 +45,9 @@ pub struct SystemWidget {
     storage_pools: Vec<StoragePool>,
     
     // Backup metrics
-    backup_status: String,
-    backup_start_time_raw: Option<String>,
-    backup_disk_serial: Option<String>,
-    backup_disk_usage_percent: Option<f32>,
-    backup_disk_used_gb: Option<f32>,
-    backup_disk_total_gb: Option<f32>,
-    backup_disk_wear_percent: Option<f32>,
-    backup_disk_temperature: Option<f32>,
-    backup_last_size_gb: Option<f32>,
+    backup_repositories: Vec<String>,
+    backup_repository_status: Status,
+    backup_disks: Vec<cm_dashboard_shared::BackupDiskData>,
     
     // Overall status
     has_data: bool,
@@ -102,7 +96,7 @@ impl SystemWidget {
             cpu_load_1min: None,
             cpu_load_5min: None,
             cpu_load_15min: None,
-            cpu_frequency: None,
+            cpu_cstates: Vec::new(),
             cpu_status: Status::Unknown,
             memory_usage_percent: None,
             memory_used_gb: None,
@@ -114,15 +108,9 @@ impl SystemWidget {
             tmp_status: Status::Unknown,
             tmpfs_mounts: Vec::new(),
             storage_pools: Vec::new(),
-            backup_status: "unknown".to_string(),
-            backup_start_time_raw: None,
-            backup_disk_serial: None,
-            backup_disk_usage_percent: None,
-            backup_disk_used_gb: None,
-            backup_disk_total_gb: None,
-            backup_disk_wear_percent: None,
-            backup_disk_temperature: None,
-            backup_last_size_gb: None,
+            backup_repositories: Vec::new(),
+            backup_repository_status: Status::Unknown,
+            backup_disks: Vec::new(),
             has_data: false,
         }
     }
@@ -137,12 +125,19 @@ impl SystemWidget {
         }
     }
 
-    /// Format CPU frequency
-    fn format_cpu_frequency(&self) -> String {
-        match self.cpu_frequency {
-            Some(freq) => format!("{:.0} MHz", freq),
-            None => "— MHz".to_string(),
+    /// Format CPU C-states (idle depth) with percentages
+    fn format_cpu_cstate(&self) -> String {
+        if self.cpu_cstates.is_empty() {
+            return "—".to_string();
         }
+
+        // Format top 3 C-states with percentages: "C10:79% C8:10% C6:8%"
+        // Agent already sends clean names (C3, C10, etc.)
+        self.cpu_cstates
+            .iter()
+            .map(|cs| format!("{}:{:.0}%", cs.name, cs.percent))
+            .collect::<Vec<_>>()
+            .join(" ")
     }
 
     /// Format memory usage
@@ -188,7 +183,7 @@ impl Widget for SystemWidget {
         self.cpu_load_1min = Some(cpu.load_1min);
         self.cpu_load_5min = Some(cpu.load_5min);
         self.cpu_load_15min = Some(cpu.load_15min);
-        self.cpu_frequency = Some(cpu.frequency_mhz);
+        self.cpu_cstates = cpu.cstates.clone();
         self.cpu_status = Status::Ok;
 
         // Extract memory data directly
@@ -214,25 +209,9 @@ impl Widget for SystemWidget {
 
         // Extract backup data
         let backup = &agent_data.backup;
-        self.backup_status = backup.status.clone();
-        self.backup_start_time_raw = backup.start_time_raw.clone();
-        self.backup_last_size_gb = backup.last_backup_size_gb;
-
-        if let Some(disk) = &backup.repository_disk {
-            self.backup_disk_serial = Some(disk.serial.clone());
-            self.backup_disk_usage_percent = Some(disk.usage_percent);
-            self.backup_disk_used_gb = Some(disk.used_gb);
-            self.backup_disk_total_gb = Some(disk.total_gb);
-            self.backup_disk_wear_percent = disk.wear_percent;
-            self.backup_disk_temperature = disk.temperature_celsius;
-        } else {
-            self.backup_disk_serial = None;
-            self.backup_disk_usage_percent = None;
-            self.backup_disk_used_gb = None;
-            self.backup_disk_total_gb = None;
-            self.backup_disk_wear_percent = None;
-            self.backup_disk_temperature = None;
-        }
+        self.backup_repositories = backup.repositories.clone();
+        self.backup_repository_status = backup.repository_status;
+        self.backup_disks = backup.disks.clone();
     }
 }
 
@@ -532,14 +511,36 @@ impl SystemWidget {
     fn render_backup(&self) -> Vec<Line<'_>> {
         let mut lines = Vec::new();
 
-        // First line: serial number with temperature and wear
-        if let Some(serial) = &self.backup_disk_serial {
-            let truncated_serial = truncate_serial(serial);
+        // First section: Repository status and list
+        if !self.backup_repositories.is_empty() {
+            let repo_text = format!("Repo: {}", self.backup_repositories.len());
+            let repo_spans = StatusIcons::create_status_spans(self.backup_repository_status, &repo_text);
+            lines.push(Line::from(repo_spans));
+
+            // List all repositories (sorted for consistent display)
+            let mut sorted_repos = self.backup_repositories.clone();
+            sorted_repos.sort();
+            let repo_count = sorted_repos.len();
+            for (idx, repo) in sorted_repos.iter().enumerate() {
+                let tree_char = if idx == repo_count - 1 { "└─" } else { "├─" };
+                lines.push(Line::from(vec![
+                    Span::styled(format!("  {} ", tree_char), Typography::tree()),
+                    Span::styled(repo.clone(), Typography::secondary()),
+                ]));
+            }
+        }
+
+        // Second section: Per-disk backup information (sorted by serial for consistent display)
+        let mut sorted_disks = self.backup_disks.clone();
+        sorted_disks.sort_by(|a, b| a.serial.cmp(&b.serial));
+        for disk in &sorted_disks {
+            let truncated_serial = truncate_serial(&disk.serial);
             let mut details = Vec::new();
-            if let Some(temp) = self.backup_disk_temperature {
+
+            if let Some(temp) = disk.temperature_celsius {
                 details.push(format!("T: {}°C", temp as i32));
             }
-            if let Some(wear) = self.backup_disk_wear_percent {
+            if let Some(wear) = disk.wear_percent {
                 details.push(format!("W: {}%", wear as i32));
             }
 
@@ -549,44 +550,40 @@ impl SystemWidget {
                 truncated_serial
             };
 
-            let backup_status = match self.backup_status.as_str() {
-                "completed" | "success" => Status::Ok,
-                "running" => Status::Pending,
-                "failed" => Status::Critical,
-                _ => Status::Unknown,
-            };
-
-            let disk_spans = StatusIcons::create_status_spans(backup_status, &disk_text);
+            // Overall disk status (worst of backup and usage)
+            let disk_status = disk.backup_status.max(disk.usage_status);
+            let disk_spans = StatusIcons::create_status_spans(disk_status, &disk_text);
             lines.push(Line::from(disk_spans));
 
-            // Show backup time from TOML if available
-            if let Some(start_time) = &self.backup_start_time_raw {
-                let time_text = if let Some(size) = self.backup_last_size_gb {
-                    format!("Time: {} ({:.1}GB)", start_time, size)
-                } else {
-                    format!("Time: {}", start_time)
-                };
-                
-                lines.push(Line::from(vec![
+            // Show backup time with status
+            if let Some(backup_time) = &disk.last_backup_time {
+                let time_text = format!("Backup: {}", backup_time);
+                let mut time_spans = vec![
                     Span::styled("  ├─ ", Typography::tree()),
-                    Span::styled(time_text, Typography::secondary())
-                ]));
+                ];
+                time_spans.extend(StatusIcons::create_status_spans(disk.backup_status, &time_text));
+                lines.push(Line::from(time_spans));
             }
 
-            // Usage information
-            if let (Some(used), Some(total), Some(usage_percent)) = (
-                self.backup_disk_used_gb, 
-                self.backup_disk_total_gb,
-                self.backup_disk_usage_percent
-            ) {
-                let usage_text = format!("Usage: {:.0}% {:.0}GB/{:.0}GB", usage_percent, used, total);
-                let usage_spans = StatusIcons::create_status_spans(Status::Ok, &usage_text);
-                let mut full_spans = vec![
-                    Span::styled("  └─ ", Typography::tree()),
-                ];
-                full_spans.extend(usage_spans);
-                lines.push(Line::from(full_spans));
-            }
+            // Show usage with status and archive count
+            let archive_display = if disk.archives_min == disk.archives_max {
+                format!("{}", disk.archives_min)
+            } else {
+                format!("{}-{}", disk.archives_min, disk.archives_max)
+            };
+
+            let usage_text = format!(
+                "Usage: ({}) {:.0}% {:.0}GB/{:.0}GB",
+                archive_display,
+                disk.disk_usage_percent,
+                disk.disk_used_gb,
+                disk.disk_total_gb
+            );
+            let mut usage_spans = vec![
+                Span::styled("  └─ ", Typography::tree()),
+            ];
+            usage_spans.extend(StatusIcons::create_status_spans(disk.usage_status, &usage_text));
+            lines.push(Line::from(usage_spans));
         }
 
         lines
@@ -832,10 +829,10 @@ impl SystemWidget {
         );
         lines.push(Line::from(cpu_spans));
 
-        let freq_text = self.format_cpu_frequency();
+        let cstate_text = self.format_cpu_cstate();
         lines.push(Line::from(vec![
             Span::styled("  └─ ", Typography::tree()),
-            Span::styled(format!("Freq: {}", freq_text), Typography::secondary())
+            Span::styled(format!("C-state: {}", cstate_text), Typography::secondary())
         ]));
 
         // RAM section
@@ -894,7 +891,7 @@ impl SystemWidget {
         lines.extend(storage_lines);
 
         // Backup section (if available)
-        if self.backup_status != "unavailable" && self.backup_status != "unknown" {
+        if !self.backup_repositories.is_empty() || !self.backup_disks.is_empty() {
             lines.push(Line::from(vec![
                 Span::styled("Backup:", Typography::widget_title())
             ]));

shared/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "cm-dashboard-shared"
-version = "0.1.204"
+version = "0.1.230"
 edition = "2021"
 
 [dependencies]

shared/src/agent_data.rs

@@ -40,13 +40,20 @@ pub struct NetworkInterfaceData {
     pub vlan_id: Option<u16>,
 }
 
+/// CPU C-state usage information
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct CStateInfo {
+    pub name: String,
+    pub percent: f32,
+}
+
 /// CPU monitoring data
 #[derive(Debug, Clone, Serialize, Deserialize)]
 pub struct CpuData {
     pub load_1min: f32,
     pub load_5min: f32,
     pub load_15min: f32,
-    pub frequency_mhz: f32,
+    pub cstates: Vec<CStateInfo>, // C-state usage percentages (C1, C6, C10, etc.) - indicates CPU idle depth distribution
     pub temperature_celsius: Option<f32>,
     pub load_status: Status,
     pub temperature_status: Status,
@@ -139,6 +146,12 @@ pub struct ServiceData {
     pub user_stopped: bool,
     pub service_status: Status,
     pub sub_services: Vec<SubServiceData>,
+    /// Memory usage in bytes (from MemoryCurrent)
+    pub memory_bytes: Option<u64>,
+    /// Number of service restarts (from NRestarts)
+    pub restart_count: Option<u32>,
+    /// Uptime in seconds (calculated from ExecMainStartTimestamp)
+    pub uptime_seconds: Option<u64>,
 }
 
 /// Sub-service data (nginx sites, docker containers, etc.)
@@ -163,23 +176,27 @@ pub struct SubServiceMetric {
 /// Backup system data
 #[derive(Debug, Clone, Serialize, Deserialize)]
 pub struct BackupData {
-    pub status: String,
-    pub total_size_gb: Option<f32>,
-    pub repository_health: Option<String>,
-    pub repository_disk: Option<BackupDiskData>,
-    pub last_backup_size_gb: Option<f32>,
-    pub start_time_raw: Option<String>,
+    pub repositories: Vec<String>,
+    pub repository_status: Status,
+    pub disks: Vec<BackupDiskData>,
 }
 
 /// Backup repository disk information
 #[derive(Debug, Clone, Serialize, Deserialize)]
 pub struct BackupDiskData {
     pub serial: String,
-    pub usage_percent: f32,
-    pub used_gb: f32,
-    pub total_gb: f32,
+    pub product_name: Option<String>,
     pub wear_percent: Option<f32>,
     pub temperature_celsius: Option<f32>,
+    pub last_backup_time: Option<String>,
+    pub backup_status: Status,
+    pub disk_usage_percent: f32,
+    pub disk_used_gb: f32,
+    pub disk_total_gb: f32,
+    pub usage_status: Status,
+    pub services: Vec<String>,
+    pub archives_min: i64,
+    pub archives_max: i64,
 }
 
 impl AgentData {
@@ -198,7 +215,7 @@ impl AgentData {
                     load_1min: 0.0,
                     load_5min: 0.0,
                     load_15min: 0.0,
-                    frequency_mhz: 0.0,
+                    cstates: Vec::new(),
                     temperature_celsius: None,
                     load_status: Status::Unknown,
                     temperature_status: Status::Unknown,
@@ -220,12 +237,9 @@ impl AgentData {
             },
             services: Vec::new(),
             backup: BackupData {
-                status: "unknown".to_string(),
-                total_size_gb: None,
-                repository_health: None,
-                repository_disk: None,
-                last_backup_size_gb: None,
-                start_time_raw: None,
+                repositories: Vec::new(),
+                repository_status: Status::Unknown,
+                disks: Vec::new(),
             },
         }
     }