From 77bf08a9786a3f4c065de60300eb381779138acd Mon Sep 17 00:00:00 2001
From: Christoffer Martinsson <cm@cmtec.se>
Date: Sat, 29 Nov 2025 21:09:04 +0100
Subject: [PATCH] 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                   |  6 +++---
 agent/Cargo.toml             |  2 +-
 agent/src/collectors/disk.rs |  4 ++--
 agent/src/collectors/mod.rs  | 32 ++++++++++++++++++++++----------
 dashboard/Cargo.toml         |  2 +-
 shared/Cargo.toml            |  2 +-
 6 files changed, 30 insertions(+), 18 deletions(-)

diff --git a/Cargo.lock b/Cargo.lock
index e62a609..7b26541 100644
--- a/Cargo.lock
+++ b/Cargo.lock
@@ -279,7 +279,7 @@ checksum = "a1d728cc89cf3aee9ff92b05e62b19ee65a02b5702cff7d5a377e32c6ae29d8d"
 
 [[package]]
 name = "cm-dashboard"
-version = "0.1.217"
+version = "0.1.219"
 dependencies = [
  "anyhow",
  "chrono",
@@ -301,7 +301,7 @@ dependencies = [
 
 [[package]]
 name = "cm-dashboard-agent"
-version = "0.1.217"
+version = "0.1.219"
 dependencies = [
  "anyhow",
  "async-trait",
@@ -324,7 +324,7 @@ dependencies = [
 
 [[package]]
 name = "cm-dashboard-shared"
-version = "0.1.217"
+version = "0.1.219"
 dependencies = [
  "chrono",
  "serde",
diff --git a/agent/Cargo.toml b/agent/Cargo.toml
index 750977c..19a1dd9 100644
--- a/agent/Cargo.toml
+++ b/agent/Cargo.toml
@@ -1,6 +1,6 @@
 [package]
 name = "cm-dashboard-agent"
-version = "0.1.219"
+version = "0.1.220"
 edition = "2021"
 
 [dependencies]
diff --git a/agent/src/collectors/disk.rs b/agent/src/collectors/disk.rs
index 71c53cf..cd3af2c 100644
--- a/agent/src/collectors/disk.rs
+++ b/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))?;
diff --git a/agent/src/collectors/mod.rs b/agent/src/collectors/mod.rs
index db338f3..2f3027e 100644
--- a/agent/src/collectors/mod.rs
+++ b/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)
+            ))
+        }
     }
 }
 
diff --git a/dashboard/Cargo.toml b/dashboard/Cargo.toml
index 696be87..577f153 100644
--- a/dashboard/Cargo.toml
+++ b/dashboard/Cargo.toml
@@ -1,6 +1,6 @@
 [package]
 name = "cm-dashboard"
-version = "0.1.219"
+version = "0.1.220"
 edition = "2021"
 
 [dependencies]
diff --git a/shared/Cargo.toml b/shared/Cargo.toml
index 4f85700..61cb8d7 100644
--- a/shared/Cargo.toml
+++ b/shared/Cargo.toml
@@ -1,6 +1,6 @@
 [package]
 name = "cm-dashboard-shared"
-version = "0.1.219"
+version = "0.1.220"
 edition = "2021"
 
 [dependencies]