Compare commits

...

2 Commits

Author SHA1 Message Date
c62c7fa698 Remove debug logging from disk collector
All checks were successful
Build and Release / build-and-release (push) Successful in 1m11s
Removed all debug! statements from disk collector to reduce log noise.

Bump version to v0.1.226
2025-11-30 00:44:38 +01:00
0b1d8c0a73 Fix Data_3 showing as unknown by handling smartctl warning exit codes
All checks were successful
Build and Release / build-and-release (push) Successful in 1m11s
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
2025-11-30 00:35:19 +01:00
5 changed files with 16 additions and 28 deletions

6
Cargo.lock generated
View File

@@ -279,7 +279,7 @@ checksum = "a1d728cc89cf3aee9ff92b05e62b19ee65a02b5702cff7d5a377e32c6ae29d8d"
[[package]]
name = "cm-dashboard"
version = "0.1.223"
version = "0.1.225"
dependencies = [
"anyhow",
"chrono",
@@ -301,7 +301,7 @@ dependencies = [
[[package]]
name = "cm-dashboard-agent"
version = "0.1.223"
version = "0.1.225"
dependencies = [
"anyhow",
"async-trait",
@@ -325,7 +325,7 @@ dependencies = [
[[package]]
name = "cm-dashboard-shared"
version = "0.1.223"
version = "0.1.225"
dependencies = [
"chrono",
"serde",

View File

@@ -1,6 +1,6 @@
[package]
name = "cm-dashboard-agent"
version = "0.1.224"
version = "0.1.226"
edition = "2021"
[dependencies]

View File

@@ -5,9 +5,7 @@ use cm_dashboard_shared::{AgentData, DriveData, FilesystemData, PoolData, Hyster
use crate::config::DiskConfig;
use tokio::process::Command as TokioCommand;
use std::process::Command as StdCommand;
use std::time::Instant;
use std::collections::HashMap;
use tracing::debug;
use super::{Collector, CollectorError};
@@ -68,9 +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?;
@@ -105,9 +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(())
}
@@ -142,7 +134,6 @@ impl DiskCollector {
}
}
debug!("Found {} mounted block devices", mount_devices.len());
Ok(mount_devices)
}
@@ -155,8 +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
}
}
}
@@ -177,8 +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));
}
}
@@ -253,9 +242,8 @@ impl DiskCollector {
} else {
mount_point.trim_start_matches('/').replace('/', "_")
};
if pool_name.is_empty() {
debug!("Skipping mergerfs pool with empty name: {}", mount_point);
continue;
}
@@ -283,8 +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;
}
};
@@ -299,8 +286,7 @@ impl DiskCollector {
});
}
}
debug!("Found {} mergerfs pools", pools.len());
Ok(pools)
}
@@ -451,8 +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,
@@ -460,7 +448,7 @@ impl DiskCollector {
wear_percent: None,
});
}
let mut health = "UNKNOWN".to_string();
let mut serial_number = None;
let mut temperature = None;

View File

@@ -1,6 +1,6 @@
[package]
name = "cm-dashboard"
version = "0.1.224"
version = "0.1.226"
edition = "2021"
[dependencies]

View File

@@ -1,6 +1,6 @@
[package]
name = "cm-dashboard-shared"
version = "0.1.224"
version = "0.1.226"
edition = "2021"
[dependencies]