Compare commits

..

9 Commits

Author SHA1 Message Date
cac836601b Add NVMe device type flag for SMART data collection
All checks were successful
Build and Release / build-and-release (push) Successful in 1m19s
2025-11-27 13:34:30 +01:00
bd22ce265b Use direct smartctl with CAP_SYS_RAWIO instead of sudo
All checks were successful
Build and Release / build-and-release (push) Successful in 1m9s
2025-11-27 13:22:13 +01:00
bbc8b7b1cb Add info-level logging for SMART data collection debugging
All checks were successful
Build and Release / build-and-release (push) Successful in 1m19s
2025-11-27 13:15:53 +01:00
5dd8cadef3 Remove debug logging from Docker collection code
All checks were successful
Build and Release / build-and-release (push) Successful in 1m19s
2025-11-27 12:50:20 +01:00
fefe30ec51 Remove sudo from docker commands - use docker group membership instead
All checks were successful
Build and Release / build-and-release (push) Successful in 1m19s
Agent changes:
- Changed docker ps and docker images commands to run without sudo
- cm-agent user is already in docker group, so sudo is not needed
- Fixes "unable to change to root gid: Operation not permitted" error
- Systemd security restrictions were blocking sudo gid changes

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

Updated to version 0.1.178
2025-11-27 12:35:38 +01:00
fb40cce748 Add stderr logging for Docker images command failure
All checks were successful
Build and Release / build-and-release (push) Successful in 1m9s
Agent changes:
- Log stderr output when docker images command fails
- This will show the actual error message (e.g., permission denied, docker not found)
- Helps diagnose why docker images collection is failing

Updated to version 0.1.177
2025-11-27 12:28:55 +01:00
eaa057b284 Change Docker collection logging from debug to info level
All checks were successful
Build and Release / build-and-release (push) Successful in 1m10s
Agent changes:
- Changed debug!() to info!() for Docker collection logs
- This allows logs to show with default RUST_LOG=info setting
- Added info import to tracing use statement

Now logs will be visible in journalctl without needing to change log level:
- "Collecting Docker sub-services for service: docker"
- "Found X Docker containers"
- "Found X Docker images"
- "Total Docker sub-services added: X"

Updated to version 0.1.176
2025-11-27 12:18:17 +01:00
f23a1b5cec Add debug logging for Docker container and image collection
All checks were successful
Build and Release / build-and-release (push) Successful in 1m10s
Agent changes:
- Added debug logging to Docker images collection function
- Log when Docker sub-services are being collected for a service
- Log count of containers and images found
- Log total sub-services added
- Show command failure details instead of silently returning empty vec

This will help diagnose why Docker images aren't showing up as sub-services
on some hosts. The logs will show if the docker commands are failing or if
the collection is working but data isn't being transmitted properly.

Updated to version 0.1.175
2025-11-27 12:04:51 +01:00
3f98f68b51 Show Docker images as sub-services under docker service
All checks were successful
Build and Release / build-and-release (push) Successful in 1m23s
Agent changes:
- Added get_docker_images() function to list all Docker images
- Use docker images to show stored images with repository:tag and size
- Display images as sub-services under docker service with size in parentheses
- Skip dangling images (<none>:<none>)
- Images shown with active status (always present when listed)

Example display:
● docker                      active     139M     1MB
  ├─ ● docker_gitea           active
  ├─ ○ docker_old-app         inactive
  ├─ ● image_nginx:latest     (142MB)
  ├─ ● image_postgres:15      (379MB)
  └─ ● image_gitea:latest     (256MB)

Updated to version 0.1.174
2025-11-27 11:43:35 +01:00
6 changed files with 87 additions and 20 deletions

6
Cargo.lock generated
View File

@@ -279,7 +279,7 @@ checksum = "a1d728cc89cf3aee9ff92b05e62b19ee65a02b5702cff7d5a377e32c6ae29d8d"
[[package]] [[package]]
name = "cm-dashboard" name = "cm-dashboard"
version = "0.1.173" version = "0.1.181"
dependencies = [ dependencies = [
"anyhow", "anyhow",
"chrono", "chrono",
@@ -301,7 +301,7 @@ dependencies = [
[[package]] [[package]]
name = "cm-dashboard-agent" name = "cm-dashboard-agent"
version = "0.1.173" version = "0.1.181"
dependencies = [ dependencies = [
"anyhow", "anyhow",
"async-trait", "async-trait",
@@ -324,7 +324,7 @@ dependencies = [
[[package]] [[package]]
name = "cm-dashboard-shared" name = "cm-dashboard-shared"
version = "0.1.173" version = "0.1.181"
dependencies = [ dependencies = [
"chrono", "chrono",
"serde", "serde",

View File

@@ -1,6 +1,6 @@
[package] [package]
name = "cm-dashboard-agent" name = "cm-dashboard-agent"
version = "0.1.173" version = "0.1.182"
edition = "2021" edition = "2021"
[dependencies] [dependencies]

View File

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

View File

@@ -130,6 +130,23 @@ impl SystemdCollector {
metrics, metrics,
}); });
} }
// Add Docker images
let docker_images = self.get_docker_images();
for (image_name, image_status, image_size) in docker_images {
let mut metrics = Vec::new();
metrics.push(SubServiceMetric {
label: "size".to_string(),
value: 0.0, // Size as string in name instead
unit: None,
});
sub_services.push(SubServiceData {
name: format!("{} ({})", image_name, image_size),
service_status: self.calculate_service_status(&image_name, &image_status),
metrics,
});
}
} }
// Create complete service data // Create complete service data
@@ -756,10 +773,10 @@ impl SystemdCollector {
fn get_docker_containers(&self) -> Vec<(String, String)> { fn get_docker_containers(&self) -> Vec<(String, String)> {
let mut containers = Vec::new(); let mut containers = Vec::new();
// Check if docker is available (use sudo for permissions) // Check if docker is available (cm-agent user is in docker group)
// Use -a to show ALL containers (running and stopped) // Use -a to show ALL containers (running and stopped)
let output = Command::new("sudo") let output = Command::new("docker")
.args(&["docker", "ps", "-a", "--format", "{{.Names}},{{.Status}}"]) .args(&["ps", "-a", "--format", "{{.Names}},{{.Status}}"])
.output(); .output();
let output = match output { let output = match output {
@@ -796,6 +813,55 @@ impl SystemdCollector {
containers containers
} }
/// Get docker images as sub-services
fn get_docker_images(&self) -> Vec<(String, String, String)> {
let mut images = Vec::new();
// Check if docker is available (cm-agent user is in docker group)
let output = Command::new("docker")
.args(&["images", "--format", "{{.Repository}}:{{.Tag}},{{.Size}}"])
.output();
let output = match output {
Ok(out) if out.status.success() => out,
Ok(_) => {
return images;
}
Err(_) => {
return images;
}
};
let output_str = match String::from_utf8(output.stdout) {
Ok(s) => s,
Err(_) => return images,
};
for line in output_str.lines() {
if line.trim().is_empty() {
continue;
}
let parts: Vec<&str> = line.split(',').collect();
if parts.len() >= 2 {
let image_name = parts[0].trim();
let size = parts[1].trim();
// Skip <none>:<none> images (dangling images)
if image_name.contains("<none>") {
continue;
}
images.push((
format!("image_{}", image_name),
"active".to_string(), // Images are always "active" (present)
size.to_string()
));
}
}
images
}
} }
#[async_trait] #[async_trait]

View File

@@ -1,6 +1,6 @@
[package] [package]
name = "cm-dashboard" name = "cm-dashboard"
version = "0.1.173" version = "0.1.182"
edition = "2021" edition = "2021"
[dependencies] [dependencies]

View File

@@ -1,6 +1,6 @@
[package] [package]
name = "cm-dashboard-shared" name = "cm-dashboard-shared"
version = "0.1.173" version = "0.1.182"
edition = "2021" edition = "2021"
[dependencies] [dependencies]