Fix Data_3 showing as unknown by handling smartctl warning exit codes

Root cause: sda's temperature exceeded threshold in the past, causing
smartctl to return exit code 32 (warning: "Attributes have been <= threshold
in the past"). The agent checked output.status.success() and rejected the
entire output as failed, even though the data (serial, temperature, health)
was perfectly valid.

Smartctl exit codes are bit flags for informational warnings:
- Exit 0: No warnings
- Exit 32 (bit 5): Attributes were at/below threshold in past
- Exit 64 (bit 6): Error log has entries
- etc.

The output data is valid regardless of these warning flags.

Solution: Parse output as long as it's not empty, ignore exit code.
Only return UNKNOWN if output is actually empty (command truly failed).

Result: Data_3 will now show "ZDZ4VE0B T: 31°C" instead of "? Data_3: sda"

Bump version to v0.1.225

Cargo.lock

@@ -279,7 +279,7 @@ checksum = "a1d728cc89cf3aee9ff92b05e62b19ee65a02b5702cff7d5a377e32c6ae29d8d"
 
 [[package]]
 name = "cm-dashboard"
-version = "0.1.215"
+version = "0.1.224"
 dependencies = [
  "anyhow",
  "chrono",
@@ -301,7 +301,7 @@ dependencies = [
 
 [[package]]
 name = "cm-dashboard-agent"
-version = "0.1.215"
+version = "0.1.224"
 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 = "0.1.215"
+version = "0.1.224"
 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 = "0.1.216"
+version = "0.1.225"
 edition = "2021"
 
 [dependencies]
@@ -20,4 +20,5 @@ gethostname = { workspace = true }
 chrono-tz = "0.8"
 toml = { workspace = true }
 async-trait = "0.1"
-reqwest = { version = "0.11", features = ["json", "blocking"] }
+reqwest = { version = "0.11", features = ["json", "blocking"] }
+futures = "0.3"

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 +3,8 @@ 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 as TokioCommand;
+use std::process::Command as StdCommand;
 use std::time::Instant;
 use std::collections::HashMap;
 use tracing::debug;
@@ -114,7 +115,7 @@ 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
@@ -189,7 +190,7 @@ 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 {
@@ -386,9 +387,9 @@ 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 +405,24 @@ 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 +436,7 @@ 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 +451,10 @@ 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,
@@ -444,7 +462,7 @@ impl DiskCollector {
                 wear_percent: None,
             });
         }
-        
+
         let mut health = "UNKNOWN".to_string();
         let mut serial_number = None;
         let mut temperature = None;
@@ -763,7 +781,7 @@ 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))?;
@@ -785,20 +803,13 @@ 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)
+            ))
+        }
     }
 }
 

dashboard/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "cm-dashboard"
-version = "0.1.216"
+version = "0.1.225"
 edition = "2021"
 
 [dependencies]

dashboard/src/ui/widgets/system.rs

@@ -566,9 +566,15 @@ impl SystemWidget {
             }
 
             // 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",
-                disk.total_archives,
+                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 = "0.1.216"
+version = "0.1.225"
 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 {