Christoffer Martinsson 00a8ed3da2 Implement hysteresis for metric status changes to prevent flapping
Add comprehensive hysteresis support to prevent status oscillation near
threshold boundaries while maintaining responsive alerting.

Key Features:
- HysteresisThresholds with configurable upper/lower limits
- StatusTracker for per-metric status history
- Default gaps: CPU load 10%, memory 5%, disk temp 5°C

Updated Components:
- CPU load collector (5-minute average with hysteresis)
- Memory usage collector (percentage-based thresholds)
- Disk temperature collector (SMART data monitoring)
- All collectors updated to support StatusTracker interface

Cache Interval Adjustments:
- Service status: 60s → 10s (faster response)
- Disk usage: 300s → 60s (more frequent checks)
- Backup status: 900s → 60s (quicker updates)
- SMART data: moved to 600s tier (10 minutes)

Architecture:
- Individual metric status calculation in collectors
- Centralized StatusTracker in MetricCollectionManager
- Status aggregation preserved in dashboard widgets
2025-10-20 18:45:41 +02:00

618 lines
24 KiB
Rust

use anyhow::Result;
use async_trait::async_trait;
use cm_dashboard_shared::{Metric, MetricValue, Status, StatusTracker, HysteresisThresholds};
use crate::config::DiskConfig;
use std::fs;
use std::path::Path;
use std::process::Command;
use std::time::Instant;
use tracing::debug;
use super::{Collector, CollectorError, PerformanceMetrics};
/// Information about a mounted disk
#[derive(Debug, Clone)]
struct MountedDisk {
device: String, // e.g., "/dev/nvme0n1p1"
physical_device: String, // e.g., "/dev/nvme0n1"
mount_point: String, // e.g., "/"
filesystem: String, // e.g., "ext4"
size: String, // e.g., "120G"
used: String, // e.g., "45G"
available: String, // e.g., "75G"
usage_percent: f32, // e.g., 38.5
config_name: Option<String>, // Name from config if UUID-based
}
/// Disk usage collector for monitoring filesystem sizes
pub struct DiskCollector {
config: DiskConfig,
temperature_thresholds: HysteresisThresholds,
}
impl DiskCollector {
pub fn new(config: DiskConfig) -> Self {
// Create hysteresis thresholds for disk temperature
let temperature_thresholds = HysteresisThresholds::with_custom_gaps(
60.0, // warning at 60°C
5.0, // 5°C gap for recovery
70.0, // critical at 70°C
5.0, // 5°C gap for recovery
);
Self {
config,
temperature_thresholds,
}
}
/// Calculate disk temperature status using hysteresis thresholds
fn calculate_temperature_status(&self, metric_name: &str, temperature: f32, status_tracker: &mut StatusTracker) -> Status {
status_tracker.calculate_with_hysteresis(metric_name, temperature, &self.temperature_thresholds)
}
/// Resolve UUID to actual device path
fn resolve_uuid_to_device(&self, uuid: &str) -> Result<String> {
let uuid_path = format!("/dev/disk/by-uuid/{}", uuid);
if Path::new(&uuid_path).exists() {
match fs::read_link(&uuid_path) {
Ok(target) => {
// Convert relative path to absolute
if target.is_relative() {
let parent = Path::new(&uuid_path).parent().unwrap();
let resolved = parent.join(&target);
match resolved.canonicalize() {
Ok(canonical) => Ok(canonical.to_string_lossy().to_string()),
Err(_) => Ok(target.to_string_lossy().to_string()),
}
} else {
Ok(target.to_string_lossy().to_string())
}
}
Err(e) => Err(anyhow::anyhow!("Failed to resolve UUID {}: {}", uuid, e)),
}
} else {
Err(anyhow::anyhow!("UUID {} not found in /dev/disk/by-uuid/", uuid))
}
}
/// Get configured filesystems from UUIDs
fn get_configured_filesystems(&self) -> Result<Vec<MountedDisk>> {
let mut configured_disks = Vec::new();
for fs_config in &self.config.filesystems {
if !fs_config.monitor {
continue;
}
// Resolve UUID to device
match self.resolve_uuid_to_device(&fs_config.uuid) {
Ok(device_path) => {
// Get filesystem stats for the mount point
match self.get_filesystem_info(&fs_config.mount_point) {
Ok((total_bytes, used_bytes)) => {
let available_bytes = total_bytes - used_bytes;
let usage_percent = if total_bytes > 0 {
(used_bytes as f64 / total_bytes as f64) * 100.0
} else {
0.0
};
// Convert bytes to human-readable format
let size = self.bytes_to_human_readable(total_bytes);
let used = self.bytes_to_human_readable(used_bytes);
let available = self.bytes_to_human_readable(available_bytes);
// Get physical device for SMART monitoring
let physical_device = self.get_physical_device(&device_path)?;
configured_disks.push(MountedDisk {
device: device_path.clone(),
physical_device,
mount_point: fs_config.mount_point.clone(),
filesystem: fs_config.fs_type.clone(),
size,
used,
available,
usage_percent: usage_percent as f32,
config_name: Some(fs_config.name.clone()),
});
debug!(
"Configured filesystem '{}' (UUID: {}) mounted at {} using {}",
fs_config.name, fs_config.uuid, fs_config.mount_point, device_path
);
}
Err(e) => {
debug!(
"Failed to get filesystem info for configured filesystem '{}': {}",
fs_config.name, e
);
}
}
}
Err(e) => {
debug!(
"Failed to resolve UUID for configured filesystem '{}': {}",
fs_config.name, e
);
}
}
}
Ok(configured_disks)
}
/// Convert bytes to human-readable format
fn bytes_to_human_readable(&self, bytes: u64) -> String {
const UNITS: &[&str] = &["B", "K", "M", "G", "T"];
let mut size = bytes as f64;
let mut unit_index = 0;
while size >= 1024.0 && unit_index < UNITS.len() - 1 {
size /= 1024.0;
unit_index += 1;
}
if unit_index == 0 {
format!("{:.0}{}", size, UNITS[unit_index])
} else {
format!("{:.1}{}", size, UNITS[unit_index])
}
}
/// Get directory size using du command (efficient for single directory)
fn get_directory_size(&self, path: &str) -> Result<u64> {
let output = Command::new("du")
.arg("-s")
.arg("--block-size=1")
.arg(path)
.output()?;
// du returns success even with permission denied warnings in stderr
// We only care if the command completely failed or produced no stdout
let output_str = String::from_utf8(output.stdout)?;
if output_str.trim().is_empty() {
return Err(anyhow::anyhow!(
"du command produced no output for {}",
path
));
}
let size_str = output_str
.split_whitespace()
.next()
.ok_or_else(|| anyhow::anyhow!("Failed to parse du output"))?;
let size_bytes = size_str.parse::<u64>()?;
Ok(size_bytes)
}
/// Get filesystem info using df command
fn get_filesystem_info(&self, path: &str) -> Result<(u64, u64)> {
let output = Command::new("df")
.arg("--block-size=1")
.arg(path)
.output()?;
if !output.status.success() {
return Err(anyhow::anyhow!("df command failed for {}", path));
}
let output_str = String::from_utf8(output.stdout)?;
let lines: Vec<&str> = output_str.lines().collect();
if lines.len() < 2 {
return Err(anyhow::anyhow!("Unexpected df output format"));
}
let fields: Vec<&str> = lines[1].split_whitespace().collect();
if fields.len() < 4 {
return Err(anyhow::anyhow!("Unexpected df fields count"));
}
let total_bytes = fields[1].parse::<u64>()?;
let used_bytes = fields[2].parse::<u64>()?;
Ok((total_bytes, used_bytes))
}
/// Get the physical device for a given device (resolves symlinks, gets parent device)
fn get_physical_device(&self, device: &str) -> Result<String> {
// For NVMe: /dev/nvme0n1p1 -> /dev/nvme0n1
if device.contains("nvme") && device.contains("p") {
if let Some(base) = device.split('p').next() {
return Ok(base.to_string());
}
}
// For SATA: /dev/sda1 -> /dev/sda
if device.starts_with("/dev/sd") && device.len() > 8 {
return Ok(device[..8].to_string()); // Keep /dev/sdX
}
// For VirtIO: /dev/vda1 -> /dev/vda
if device.starts_with("/dev/vd") && device.len() > 8 {
return Ok(device[..8].to_string());
}
// If no partition detected, return as-is
Ok(device.to_string())
}
/// Get SMART health for a specific physical device
fn get_smart_health(&self, device: &str) -> (String, f32) {
if let Ok(output) = Command::new("sudo")
.arg("smartctl")
.arg("-H")
.arg(device)
.output()
{
if output.status.success() {
let output_str = String::from_utf8_lossy(&output.stdout);
let health_status = if output_str.contains("PASSED") {
"PASSED"
} else if output_str.contains("FAILED") {
"FAILED"
} else {
"UNKNOWN"
};
// Try to get temperature
let temperature = if let Ok(temp_output) = Command::new("sudo")
.arg("smartctl")
.arg("-A")
.arg(device)
.output()
{
let temp_str = String::from_utf8_lossy(&temp_output.stdout);
// Look for temperature in SMART attributes
for line in temp_str.lines() {
if line.contains("Temperature") && line.contains("Celsius") {
if let Some(temp_part) = line.split_whitespace().nth(9) {
if let Ok(temp) = temp_part.parse::<f32>() {
return (health_status.to_string(), temp);
}
}
}
}
0.0
} else {
0.0
};
return (health_status.to_string(), temperature);
}
}
("UNKNOWN".to_string(), 0.0)
}
/// Calculate status based on usage percentage
fn calculate_usage_status(&self, used_bytes: u64, total_bytes: u64) -> Status {
if total_bytes == 0 {
return Status::Unknown;
}
let usage_percent = (used_bytes as f64 / total_bytes as f64) * 100.0;
// Thresholds for disk usage
if usage_percent >= 95.0 {
Status::Critical
} else if usage_percent >= 85.0 {
Status::Warning
} else {
Status::Ok
}
}
/// Parse size string (e.g., "120G", "45M") to GB value
fn parse_size_to_gb(&self, size_str: &str) -> f32 {
let size_str = size_str.trim();
if size_str.is_empty() || size_str == "-" {
return 0.0;
}
// Extract numeric part and unit
let (num_str, unit) = if let Some(last_char) = size_str.chars().last() {
if last_char.is_alphabetic() {
let num_part = &size_str[..size_str.len() - 1];
let unit_part = &size_str[size_str.len() - 1..];
(num_part, unit_part)
} else {
(size_str, "")
}
} else {
(size_str, "")
};
let number: f32 = num_str.parse().unwrap_or(0.0);
match unit.to_uppercase().as_str() {
"T" | "TB" => number * 1024.0,
"G" | "GB" => number,
"M" | "MB" => number / 1024.0,
"K" | "KB" => number / (1024.0 * 1024.0),
"B" | "" => number / (1024.0 * 1024.0 * 1024.0),
_ => number, // Assume GB if unknown unit
}
}
}
#[async_trait]
impl Collector for DiskCollector {
fn name(&self) -> &str {
"disk"
}
async fn collect(&self, status_tracker: &mut StatusTracker) -> Result<Vec<Metric>, CollectorError> {
let start_time = Instant::now();
debug!("Collecting multi-disk metrics");
let mut metrics = Vec::new();
// Use UUID-based configured filesystems
let mounted_disks = match self.get_configured_filesystems() {
Ok(configured) => {
debug!("Using UUID-based filesystems: {} found", configured.len());
configured
}
Err(e) => {
debug!("Failed to get configured filesystems: {}", e);
Vec::new()
}
};
// Process discovered/configured disks
if !mounted_disks.is_empty() {
debug!("Found {} mounted disks", mounted_disks.len());
// Group disks by physical device to avoid duplicate SMART checks
let mut physical_devices: std::collections::HashMap<String, Vec<&MountedDisk>> =
std::collections::HashMap::new();
for disk in &mounted_disks {
physical_devices
.entry(disk.physical_device.clone())
.or_insert_with(Vec::new)
.push(disk);
}
// Generate metrics for each mounted disk
for (disk_index, disk) in mounted_disks.iter().enumerate() {
let timestamp = chrono::Utc::now().timestamp() as u64;
// Always use index for metric names to maintain dashboard compatibility
let disk_name = disk_index.to_string();
// Parse size strings to get actual values for calculations
let size_gb = self.parse_size_to_gb(&disk.size);
let used_gb = self.parse_size_to_gb(&disk.used);
let avail_gb = self.parse_size_to_gb(&disk.available);
// Calculate status based on configured thresholds
let status = if disk.usage_percent >= self.config.usage_critical_percent {
Status::Critical
} else if disk.usage_percent >= self.config.usage_warning_percent {
Status::Warning
} else {
Status::Ok
};
// Device and mount point info
metrics.push(Metric {
name: format!("disk_{}_device", disk_name),
value: MetricValue::String(disk.device.clone()),
unit: None,
description: Some(format!("Device: {}", disk.device)),
status: Status::Ok,
timestamp,
});
metrics.push(Metric {
name: format!("disk_{}_mount_point", disk_name),
value: MetricValue::String(disk.mount_point.clone()),
unit: None,
description: Some(format!("Mount: {}", disk.mount_point)),
status: Status::Ok,
timestamp,
});
metrics.push(Metric {
name: format!("disk_{}_filesystem", disk_name),
value: MetricValue::String(disk.filesystem.clone()),
unit: None,
description: Some(format!("FS: {}", disk.filesystem)),
status: Status::Ok,
timestamp,
});
// Size metrics
metrics.push(Metric {
name: format!("disk_{}_total_gb", disk_name),
value: MetricValue::Float(size_gb),
unit: Some("GB".to_string()),
description: Some(format!("Total: {}", disk.size)),
status: Status::Ok,
timestamp,
});
metrics.push(Metric {
name: format!("disk_{}_used_gb", disk_name),
value: MetricValue::Float(used_gb),
unit: Some("GB".to_string()),
description: Some(format!("Used: {}", disk.used)),
status,
timestamp,
});
metrics.push(Metric {
name: format!("disk_{}_available_gb", disk_name),
value: MetricValue::Float(avail_gb),
unit: Some("GB".to_string()),
description: Some(format!("Available: {}", disk.available)),
status: Status::Ok,
timestamp,
});
metrics.push(Metric {
name: format!("disk_{}_usage_percent", disk_name),
value: MetricValue::Float(disk.usage_percent),
unit: Some("%".to_string()),
description: Some(format!("Usage: {:.1}%", disk.usage_percent)),
status,
timestamp,
});
// Physical device name (for SMART health grouping)
let physical_device_name = disk
.physical_device
.strip_prefix("/dev/")
.unwrap_or(&disk.physical_device);
metrics.push(Metric {
name: format!("disk_{}_physical_device", disk_name),
value: MetricValue::String(physical_device_name.to_string()),
unit: None,
description: Some(format!("Physical: {}", physical_device_name)),
status: Status::Ok,
timestamp,
});
}
// Add SMART health metrics for each unique physical device
for (physical_device, _disks) in physical_devices {
let (health_status, temperature) = self.get_smart_health(&physical_device);
let device_name = physical_device
.strip_prefix("/dev/")
.unwrap_or(&physical_device);
let timestamp = chrono::Utc::now().timestamp() as u64;
let health_status_enum = match health_status.as_str() {
"PASSED" => Status::Ok,
"FAILED" => Status::Critical,
_ => Status::Unknown,
};
metrics.push(Metric {
name: format!("disk_smart_{}_health", device_name),
value: MetricValue::String(health_status.clone()),
unit: None,
description: Some(format!("SMART Health: {}", health_status)),
status: health_status_enum,
timestamp,
});
if temperature > 0.0 {
let metric_name = format!("disk_smart_{}_temperature", device_name);
let temp_status = self.calculate_temperature_status(&metric_name, temperature, status_tracker);
metrics.push(Metric {
name: format!("disk_smart_{}_temperature", device_name),
value: MetricValue::Float(temperature),
unit: Some("°C".to_string()),
description: Some(format!("Temperature: {:.0}°C", temperature)),
status: temp_status,
timestamp,
});
}
}
// Add disk count metric
metrics.push(Metric {
name: "disk_count".to_string(),
value: MetricValue::Integer(mounted_disks.len() as i64),
unit: None,
description: Some(format!("Total mounted disks: {}", mounted_disks.len())),
status: Status::Ok,
timestamp: chrono::Utc::now().timestamp() as u64,
});
} else {
// No disks configured - add zero count metric
metrics.push(Metric {
name: "disk_count".to_string(),
value: MetricValue::Integer(0),
unit: None,
description: Some("No disks configured for monitoring".to_string()),
status: Status::Warning,
timestamp: chrono::Utc::now().timestamp() as u64,
});
}
// Monitor /tmp directory size (keep existing functionality)
match self.get_directory_size("/tmp") {
Ok(tmp_size_bytes) => {
let tmp_size_mb = tmp_size_bytes as f64 / (1024.0 * 1024.0);
// Get /tmp filesystem info (usually tmpfs with 2GB limit)
let (total_bytes, _) = match self.get_filesystem_info("/tmp") {
Ok((total, used)) => (total, used),
Err(_) => {
// Fallback: assume 2GB limit for tmpfs
(2 * 1024 * 1024 * 1024, tmp_size_bytes)
}
};
let total_mb = total_bytes as f64 / (1024.0 * 1024.0);
let usage_percent = (tmp_size_bytes as f64 / total_bytes as f64) * 100.0;
let status = self.calculate_usage_status(tmp_size_bytes, total_bytes);
metrics.push(Metric {
name: "disk_tmp_size_mb".to_string(),
value: MetricValue::Float(tmp_size_mb as f32),
unit: Some("MB".to_string()),
description: Some(format!("Used: {:.1} MB", tmp_size_mb)),
status,
timestamp: chrono::Utc::now().timestamp() as u64,
});
metrics.push(Metric {
name: "disk_tmp_total_mb".to_string(),
value: MetricValue::Float(total_mb as f32),
unit: Some("MB".to_string()),
description: Some(format!("Total: {:.1} MB", total_mb)),
status: Status::Ok,
timestamp: chrono::Utc::now().timestamp() as u64,
});
metrics.push(Metric {
name: "disk_tmp_usage_percent".to_string(),
value: MetricValue::Float(usage_percent as f32),
unit: Some("%".to_string()),
description: Some(format!("Usage: {:.1}%", usage_percent)),
status,
timestamp: chrono::Utc::now().timestamp() as u64,
});
}
Err(e) => {
debug!("Failed to get /tmp size: {}", e);
metrics.push(Metric {
name: "disk_tmp_size_mb".to_string(),
value: MetricValue::String("error".to_string()),
unit: Some("MB".to_string()),
description: Some(format!("Error: {}", e)),
status: Status::Unknown,
timestamp: chrono::Utc::now().timestamp() as u64,
});
}
}
let collection_time = start_time.elapsed();
debug!(
"Multi-disk collection completed in {:?} with {} metrics",
collection_time,
metrics.len()
);
Ok(metrics)
}
fn get_performance_metrics(&self) -> Option<PerformanceMetrics> {
None // Performance tracking handled by cache system
}
}