Fix blocking smartctl commands with proper async/timeout handling

- Changed disk collector to use tokio::process::Command instead of std::process::Command
- Updated run_command_with_timeout to properly kill processes on timeout
- Fixes issue where smartctl hangs on problematic drives (/dev/sda) freezing entire agent
- Timeout now force-kills hung processes using kill -9, preventing orphaned smartctl processes

This resolves the issue where Data_3 showed unknown status because smartctl was hanging
indefinitely trying to read from a problematic drive, blocking the entire collector.

Bump version to v0.1.220

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

Cargo.lock

@@ -279,7 +279,7 @@ checksum = "a1d728cc89cf3aee9ff92b05e62b19ee65a02b5702cff7d5a377e32c6ae29d8d"
 
 [[package]]
 name = "cm-dashboard"
-version = "0.1.214"
+version = "0.1.219"
 dependencies = [
  "anyhow",
  "chrono",
@@ -301,7 +301,7 @@ dependencies = [
 
 [[package]]
 name = "cm-dashboard-agent"
-version = "0.1.214"
+version = "0.1.219"
 dependencies = [
  "anyhow",
  "async-trait",
@@ -324,7 +324,7 @@ dependencies = [
 
 [[package]]
 name = "cm-dashboard-shared"
-version = "0.1.214"
+version = "0.1.219"
 dependencies = [
  "chrono",
  "serde",

agent/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "cm-dashboard-agent"
-version = "0.1.215"
+version = "0.1.220"
 edition = "2021"
 
 [dependencies]

agent/src/collectors/backup.rs

@@ -142,10 +142,16 @@ impl BackupCollector {
                     // Build service list for this disk
                     let services: Vec<String> = backup_status.services.keys().cloned().collect();
 
-                    // Calculate total archives across all services on this disk
-                    let total_archives: i64 = backup_status.services.values()
+                    // Get min and max archive counts to detect inconsistencies
+                    let archives_min: i64 = backup_status.services.values()
                         .map(|service| service.archive_count)
-                        .sum();
+                        .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 {
@@ -160,7 +166,8 @@ impl BackupCollector {
                         disk_total_gb: total_gb,
                         usage_status,
                         services,
-                        total_archives,
+                        archives_min,
+                        archives_max,
                     };
 
                     disks.push(disk_data);

agent/src/collectors/disk.rs

@@ -3,7 +3,7 @@ use async_trait::async_trait;
 use cm_dashboard_shared::{AgentData, DriveData, FilesystemData, PoolData, HysteresisThresholds, Status};
 
 use crate::config::DiskConfig;
-use std::process::Command;
+use tokio::process::Command;
 use std::time::Instant;
 use std::collections::HashMap;
 use tracing::debug;
@@ -763,7 +763,7 @@ 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 = std::process::Command::new("timeout")
             .args(&["2", "lsblk", "-rn", "-o", "NAME,MOUNTPOINT"])
             .output()
             .map_err(|e| anyhow::anyhow!("Failed to run lsblk: {}", e))?;

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 +15,29 @@ 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;
     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)
-        )),
+    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)
+            ))
+        }
     }
 }
 

dashboard/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "cm-dashboard"
-version = "0.1.215"
+version = "0.1.220"
 edition = "2021"
 
 [dependencies]

dashboard/src/ui/widgets/system.rs

@@ -544,9 +544,6 @@ impl SystemWidget {
                 details.push(format!("W: {}%", wear as i32));
             }
 
-            // Add archive count
-            details.push(format!("Archives: {}", disk.total_archives));
-
             let disk_text = if !details.is_empty() {
                 format!("{} {}", truncated_serial, details.join(" "))
             } else {
@@ -568,9 +565,16 @@ impl SystemWidget {
                 lines.push(Line::from(time_spans));
             }
 
-            // Show usage with status
+            // 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",
+                "Usage: ({}) {:.0}% {:.0}GB/{:.0}GB",
+                archive_display,
                 disk.disk_usage_percent,
                 disk.disk_used_gb,
                 disk.disk_total_gb

shared/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "cm-dashboard-shared"
-version = "0.1.215"
+version = "0.1.220"
 edition = "2021"
 
 [dependencies]

shared/src/agent_data.rs

@@ -195,7 +195,8 @@ pub struct BackupDiskData {
     pub disk_total_gb: f32,
     pub usage_status: Status,
     pub services: Vec<String>,
-    pub total_archives: i64,
+    pub archives_min: i64,
+    pub archives_max: i64,
 }
 
 impl AgentData {