cm/cm-dashboard
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 274 Wiki Activity

Implement hysteresis for metric status changes to prevent flapping

Browse Source 
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
This commit is contained in:
Christoffer Martinsson
2025-10-20 18:45:41 +02:00
parent e998679901
commit 00a8ed3da2
34 changed files with 1037 additions and 770 deletions
Download Patch File Download Diff File Expand all files Collapse all files

71
agent/src/collectors/backup.rs
View File

@@ -1,6 +1,6 @@
use async_trait::async_trait;
use cm_dashboard_shared::{Metric, MetricValue, Status};
use chrono::Utc;
use cm_dashboard_shared::{Metric, MetricValue, Status, StatusTracker};
use serde::{Deserialize, Serialize};
use std::collections::HashMap;
use tokio::fs;
@@ -18,7 +18,8 @@ pub struct BackupCollector {
impl BackupCollector {
pub fn new(backup_status_file: Option<String>, max_age_hours: u64) -> Self {
Self {
backup_status_file: backup_status_file.unwrap_or_else(|| "/var/lib/backup/backup-status.toml".to_string()),
backup_status_file: backup_status_file
.unwrap_or_else(|| "/var/lib/backup/backup-status.toml".to_string()),
max_age_hours,
}
}
@@ -43,10 +44,16 @@ impl BackupCollector {
Ok(dt) => dt.with_timezone(&Utc),
Err(_) => {
// Try parsing as naive datetime and assume UTC
match chrono::NaiveDateTime::parse_from_str(&backup_status.start_time, "%Y-%m-%dT%H:%M:%S%.f") {
match chrono::NaiveDateTime::parse_from_str(
&backup_status.start_time,
"%Y-%m-%dT%H:%M:%S%.f",
) {
Ok(naive_dt) => naive_dt.and_utc(),
Err(_) => {
error!("Failed to parse backup timestamp: {}", backup_status.start_time);
error!(
"Failed to parse backup timestamp: {}",
backup_status.start_time
);
return Status::Unknown;
}
}
@@ -63,7 +70,7 @@ impl BackupCollector {
} else {
Status::Ok
}
},
}
"failed" => Status::Critical,
"running" => Status::Ok, // Currently running is OK
_ => Status::Unknown,
@@ -78,7 +85,7 @@ impl BackupCollector {
} else {
Status::Critical
}
},
}
"failed" => Status::Critical,
"disabled" => Status::Warning, // Service intentionally disabled
"running" => Status::Ok,
@@ -97,7 +104,7 @@ impl Collector for BackupCollector {
"backup"
}
async fn collect(&self) -> Result<Vec<Metric>, CollectorError> {
async fn collect(&self, _status_tracker: &mut StatusTracker) -> Result<Vec<Metric>, CollectorError> {
let backup_status = self.read_backup_status().await?;
let mut metrics = Vec::new();
let timestamp = chrono::Utc::now().timestamp() as u64;
@@ -114,7 +121,10 @@ impl Collector for BackupCollector {
}),
status: overall_status,
timestamp,
description: Some(format!("Backup: {} at {}", backup_status.status, backup_status.start_time)),
description: Some(format!(
"Backup: {} at {}",
backup_status.status, backup_status.start_time
)),
unit: None,
});
@@ -129,14 +139,18 @@ impl Collector for BackupCollector {
});
// Last backup timestamp - use last_updated (when backup finished) instead of start_time
let last_updated_dt_result = chrono::DateTime::parse_from_rfc3339(&backup_status.last_updated)
.map(|dt| dt.with_timezone(&Utc))
.or_else(|_| {
// Try parsing as naive datetime and assume UTC
chrono::NaiveDateTime::parse_from_str(&backup_status.last_updated, "%Y-%m-%dT%H:%M:%S%.f")
let last_updated_dt_result =
chrono::DateTime::parse_from_rfc3339(&backup_status.last_updated)
.map(|dt| dt.with_timezone(&Utc))
.or_else(|_| {
// Try parsing as naive datetime and assume UTC
chrono::NaiveDateTime::parse_from_str(
&backup_status.last_updated,
"%Y-%m-%dT%H:%M:%S%.f",
)
.map(|naive_dt| naive_dt.and_utc())
});
});
if let Ok(last_updated_dt) = last_updated_dt_result {
metrics.push(Metric {
name: "backup_last_run_timestamp".to_string(),
@@ -147,13 +161,16 @@ impl Collector for BackupCollector {
unit: Some("unix_timestamp".to_string()),
});
} else {
error!("Failed to parse backup timestamp for last_run_timestamp: {}", backup_status.last_updated);
error!(
"Failed to parse backup timestamp for last_run_timestamp: {}",
backup_status.last_updated
);
}
// Individual service metrics
for (service_name, service) in &backup_status.services {
let service_status = self.calculate_service_status(service);
// Service status
metrics.push(Metric {
name: format!("backup_service_{}_status", service_name),
@@ -165,7 +182,10 @@ impl Collector for BackupCollector {
}),
status: service_status,
timestamp,
description: Some(format!("Backup service {} status: {}", service_name, service.status)),
description: Some(format!(
"Backup service {} status: {}",
service_name, service.status
)),
unit: None,
});
@@ -173,7 +193,11 @@ impl Collector for BackupCollector {
metrics.push(Metric {
name: format!("backup_service_{}_exit_code", service_name),
value: MetricValue::Integer(service.exit_code),
status: if service.exit_code == 0 { Status::Ok } else { Status::Critical },
status: if service.exit_code == 0 {
Status::Ok
} else {
Status::Critical
},
timestamp,
description: Some(format!("Exit code for backup service {}", service_name)),
unit: None,
@@ -222,7 +246,9 @@ impl Collector for BackupCollector {
});
// Calculate total repository size
let total_size_bytes: u64 = backup_status.services.values()
let total_size_bytes: u64 = backup_status
.services
.values()
.map(|s| s.repo_size_bytes)
.sum();
let total_size_gb = Self::bytes_to_gb(total_size_bytes);
@@ -301,7 +327,6 @@ impl Collector for BackupCollector {
unit: None,
});
}
}
// Add standalone disk identification metrics from TOML fields
@@ -372,7 +397,7 @@ pub struct DiskSpace {
pub used_gb: f64,
pub available_gb: f64,
pub usage_percent: f64,
// Optional disk identification fields
// Optional disk identification fields
pub product_name: Option<String>,
pub serial_number: Option<String>,
}
@@ -384,4 +409,4 @@ pub struct ServiceStatus {
pub repo_path: String,
pub archive_count: i64,
pub repo_size_bytes: u64,
}
}

57
agent/src/collectors/cpu.rs
View File

@@ -1,5 +1,5 @@
use async_trait::async_trait;
use cm_dashboard_shared::{registry, Metric, MetricValue, Status};
use cm_dashboard_shared::{registry, Metric, MetricValue, Status, StatusTracker, HysteresisThresholds};
use tracing::debug;
@@ -17,41 +17,44 @@ use crate::config::CpuConfig;
pub struct CpuCollector {
config: CpuConfig,
name: String,
load_thresholds: HysteresisThresholds,
temperature_thresholds: HysteresisThresholds,
}
impl CpuCollector {
pub fn new(config: CpuConfig) -> Self {
// Create hysteresis thresholds with 10% gap for recovery
let load_thresholds = HysteresisThresholds::new(
config.load_warning_threshold,
config.load_critical_threshold,
);
let temperature_thresholds = HysteresisThresholds::new(
config.temperature_warning_threshold,
config.temperature_critical_threshold,
);
Self {
config,
name: "cpu".to_string(),
load_thresholds,
temperature_thresholds,
}
}
/// Calculate CPU load status using configured thresholds
fn calculate_load_status(&self, load: f32) -> Status {
if load >= self.config.load_critical_threshold {
Status::Critical
} else if load >= self.config.load_warning_threshold {
Status::Warning
} else {
Status::Ok
}
/// Calculate CPU load status using hysteresis thresholds
fn calculate_load_status(&self, metric_name: &str, load: f32, status_tracker: &mut StatusTracker) -> Status {
status_tracker.calculate_with_hysteresis(metric_name, load, &self.load_thresholds)
}
/// Calculate CPU temperature status using configured thresholds
fn calculate_temperature_status(&self, temp: f32) -> Status {
if temp >= self.config.temperature_critical_threshold {
Status::Critical
} else if temp >= self.config.temperature_warning_threshold {
Status::Warning
} else {
Status::Ok
}
/// Calculate CPU temperature status using hysteresis thresholds
fn calculate_temperature_status(&self, metric_name: &str, temp: f32, status_tracker: &mut StatusTracker) -> Status {
status_tracker.calculate_with_hysteresis(metric_name, temp, &self.temperature_thresholds)
}
/// Collect CPU load averages from /proc/loadavg
/// Format: "0.52 0.58 0.59 1/257 12345"
async fn collect_load_averages(&self) -> Result<Vec<Metric>, CollectorError> {
async fn collect_load_averages(&self, status_tracker: &mut StatusTracker) -> Result<Vec<Metric>, CollectorError> {
let content = utils::read_proc_file("/proc/loadavg")?;
let parts: Vec<&str> = content.trim().split_whitespace().collect();
@@ -68,7 +71,7 @@ impl CpuCollector {
// Only apply thresholds to 5-minute load average
let load_1min_status = Status::Ok; // No alerting on 1min
let load_5min_status = self.calculate_load_status(load_5min); // Only 5min triggers alerts
let load_5min_status = self.calculate_load_status(registry::CPU_LOAD_5MIN, load_5min, status_tracker); // Only 5min triggers alerts
let load_15min_status = Status::Ok; // No alerting on 15min
Ok(vec![
@@ -95,14 +98,14 @@ impl CpuCollector {
/// Collect CPU temperature from thermal zones
/// Prioritizes x86_pkg_temp over generic thermal zones (legacy behavior)
async fn collect_temperature(&self) -> Result<Option<Metric>, CollectorError> {
async fn collect_temperature(&self, status_tracker: &mut StatusTracker) -> Result<Option<Metric>, CollectorError> {
// Try x86_pkg_temp first (Intel CPU package temperature)
if let Ok(temp) = self
.read_thermal_zone("/sys/class/thermal/thermal_zone0/temp")
.await
{
let temp_celsius = temp as f32 / 1000.0;
let status = self.calculate_temperature_status(temp_celsius);
let status = self.calculate_temperature_status(registry::CPU_TEMPERATURE_CELSIUS, temp_celsius, status_tracker);
return Ok(Some(
Metric::new(
@@ -120,7 +123,7 @@ impl CpuCollector {
let path = format!("/sys/class/thermal/thermal_zone{}/temp", zone_id);
if let Ok(temp) = self.read_thermal_zone(&path).await {
let temp_celsius = temp as f32 / 1000.0;
let status = self.calculate_temperature_status(temp_celsius);
let status = self.calculate_temperature_status(registry::CPU_TEMPERATURE_CELSIUS, temp_celsius, status_tracker);
return Ok(Some(
Metric::new(
@@ -200,17 +203,17 @@ impl Collector for CpuCollector {
&self.name
}
async fn collect(&self) -> Result<Vec<Metric>, CollectorError> {
async fn collect(&self, status_tracker: &mut StatusTracker) -> Result<Vec<Metric>, CollectorError> {
debug!("Collecting CPU metrics");
let start = std::time::Instant::now();
let mut metrics = Vec::with_capacity(5); // Pre-allocate for efficiency
// Collect load averages (always available)
metrics.extend(self.collect_load_averages().await?);
metrics.extend(self.collect_load_averages(status_tracker).await?);
// Collect temperature (optional)
if let Some(temp_metric) = self.collect_temperature().await? {
if let Some(temp_metric) = self.collect_temperature(status_tracker).await? {
metrics.push(temp_metric);
}

38
agent/src/collectors/disk.rs
View File

@@ -1,6 +1,6 @@
use anyhow::Result;
use async_trait::async_trait;
use cm_dashboard_shared::{Metric, MetricValue, Status};
use cm_dashboard_shared::{Metric, MetricValue, Status, StatusTracker, HysteresisThresholds};
use crate::config::DiskConfig;
use std::fs;
@@ -28,11 +28,28 @@ struct MountedDisk {
/// Disk usage collector for monitoring filesystem sizes
pub struct DiskCollector {
config: DiskConfig,
temperature_thresholds: HysteresisThresholds,
}
impl DiskCollector {
pub fn new(config: DiskConfig) -> Self {
Self { config }
// 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
@@ -203,12 +220,6 @@ impl DiskCollector {
Ok((total_bytes, used_bytes))
}
/// Get root filesystem disk usage
fn get_root_filesystem_usage(&self) -> Result<(u64, u64, f32)> {
let (total_bytes, used_bytes) = self.get_filesystem_info("/")?;
let usage_percent = (used_bytes as f64 / total_bytes as f64) * 100.0;
Ok((total_bytes, used_bytes, usage_percent as f32))
}
/// Get the physical device for a given device (resolves symlinks, gets parent device)
@@ -339,7 +350,7 @@ impl Collector for DiskCollector {
"disk"
}
async fn collect(&self) -> Result<Vec<Metric>, CollectorError> {
async fn collect(&self, status_tracker: &mut StatusTracker) -> Result<Vec<Metric>, CollectorError> {
let start_time = Instant::now();
debug!("Collecting multi-disk metrics");
@@ -497,13 +508,8 @@ impl Collector for DiskCollector {
});
if temperature > 0.0 {
let temp_status = if temperature >= 70.0 {
Status::Critical
} else if temperature >= 60.0 {
Status::Warning
} else {
Status::Ok
};
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),

4
agent/src/collectors/error.rs
View File

@@ -4,7 +4,7 @@ use thiserror::Error;
pub enum CollectorError {
#[error("Failed to read system file {path}: {error}")]
SystemRead { path: String, error: String },
#[error("Failed to parse value '{value}': {error}")]
Parse { value: String, error: String },
}
}

196
agent/src/collectors/memory.rs
View File

@@ -1,13 +1,13 @@
use async_trait::async_trait;
use cm_dashboard_shared::{Metric, MetricValue, Status, registry};
use cm_dashboard_shared::{registry, Metric, MetricValue, Status, StatusTracker, HysteresisThresholds};
use tracing::debug;
use super::{Collector, CollectorError, utils};
use super::{utils, Collector, CollectorError};
use crate::config::MemoryConfig;
/// Extremely efficient memory metrics collector
///
///
/// EFFICIENCY OPTIMIZATIONS:
/// - Single /proc/meminfo read for all memory metrics
/// - Minimal string parsing with split operations
@@ -17,6 +17,7 @@ use crate::config::MemoryConfig;
pub struct MemoryCollector {
config: MemoryConfig,
name: String,
usage_thresholds: HysteresisThresholds,
}
/// Memory information parsed from /proc/meminfo
@@ -33,36 +34,38 @@ struct MemoryInfo {
impl MemoryCollector {
pub fn new(config: MemoryConfig) -> Self {
// Create hysteresis thresholds with 5% gap for memory usage
let usage_thresholds = HysteresisThresholds::with_custom_gaps(
config.usage_warning_percent,
5.0, // 5% gap for warning recovery
config.usage_critical_percent,
5.0, // 5% gap for critical recovery
);
Self {
config,
name: "memory".to_string(),
usage_thresholds,
}
}
/// Calculate memory usage status using configured thresholds
fn calculate_usage_status(&self, usage_percent: f32) -> Status {
if usage_percent >= self.config.usage_critical_percent {
Status::Critical
} else if usage_percent >= self.config.usage_warning_percent {
Status::Warning
} else {
Status::Ok
}
/// Calculate memory usage status using hysteresis thresholds
fn calculate_usage_status(&self, metric_name: &str, usage_percent: f32, status_tracker: &mut StatusTracker) -> Status {
status_tracker.calculate_with_hysteresis(metric_name, usage_percent, &self.usage_thresholds)
}
/// Parse /proc/meminfo efficiently
/// Format: "MemTotal: 16384000 kB"
async fn parse_meminfo(&self) -> Result<MemoryInfo, CollectorError> {
let content = utils::read_proc_file("/proc/meminfo")?;
let mut info = MemoryInfo::default();
// Parse each line efficiently - only extract what we need
for line in content.lines() {
if let Some(colon_pos) = line.find(':') {
let key = &line[..colon_pos];
let value_part = &line[colon_pos + 1..];
// Extract number from value part (format: " 12345 kB")
if let Some(number_str) = value_part.split_whitespace().next() {
if let Ok(value_kb) = utils::parse_u64(number_str) {
@@ -80,7 +83,7 @@ impl MemoryCollector {
}
}
}
// Validate that we got essential fields
if info.total_kb == 0 {
return Err(CollectorError::Parse {
@@ -88,87 +91,105 @@ impl MemoryCollector {
error: "MemTotal not found or zero in /proc/meminfo".to_string(),
});
}
// If MemAvailable is not available (older kernels), calculate it
if info.available_kb == 0 {
info.available_kb = info.free_kb + info.buffers_kb + info.cached_kb;
}
Ok(info)
}
/// Convert KB to GB efficiently (avoiding floating point in hot path)
fn kb_to_gb(kb: u64) -> f32 {
kb as f32 / 1_048_576.0 // 1024 * 1024
}
/// Calculate memory metrics from parsed info
fn calculate_metrics(&self, info: &MemoryInfo) -> Vec<Metric> {
fn calculate_metrics(&self, info: &MemoryInfo, status_tracker: &mut StatusTracker) -> Vec<Metric> {
let mut metrics = Vec::with_capacity(6);
// Calculate derived values
let used_kb = info.total_kb - info.available_kb;
let usage_percent = (used_kb as f32 / info.total_kb as f32) * 100.0;
let usage_status = self.calculate_usage_status(usage_percent);
let usage_status = self.calculate_usage_status(registry::MEMORY_USAGE_PERCENT, usage_percent, status_tracker);
let swap_used_kb = info.swap_total_kb - info.swap_free_kb;
// Convert to GB for metrics
let total_gb = Self::kb_to_gb(info.total_kb);
let used_gb = Self::kb_to_gb(used_kb);
let available_gb = Self::kb_to_gb(info.available_kb);
let swap_total_gb = Self::kb_to_gb(info.swap_total_kb);
let swap_used_gb = Self::kb_to_gb(swap_used_kb);
// Memory usage percentage (primary metric with status)
metrics.push(Metric::new(
registry::MEMORY_USAGE_PERCENT.to_string(),
MetricValue::Float(usage_percent),
usage_status,
).with_description("Memory usage percentage".to_string())
.with_unit("%".to_string()));
metrics.push(
Metric::new(
registry::MEMORY_USAGE_PERCENT.to_string(),
MetricValue::Float(usage_percent),
usage_status,
)
.with_description("Memory usage percentage".to_string())
.with_unit("%".to_string()),
);
// Total memory
metrics.push(Metric::new(
registry::MEMORY_TOTAL_GB.to_string(),
MetricValue::Float(total_gb),
Status::Ok, // Total memory doesn't have status
).with_description("Total system memory".to_string())
.with_unit("GB".to_string()));
metrics.push(
Metric::new(
registry::MEMORY_TOTAL_GB.to_string(),
MetricValue::Float(total_gb),
Status::Ok, // Total memory doesn't have status
)
.with_description("Total system memory".to_string())
.with_unit("GB".to_string()),
);
// Used memory
metrics.push(Metric::new(
registry::MEMORY_USED_GB.to_string(),
MetricValue::Float(used_gb),
Status::Ok, // Used memory absolute value doesn't have status
).with_description("Used system memory".to_string())
.with_unit("GB".to_string()));
metrics.push(
Metric::new(
registry::MEMORY_USED_GB.to_string(),
MetricValue::Float(used_gb),
Status::Ok, // Used memory absolute value doesn't have status
)
.with_description("Used system memory".to_string())
.with_unit("GB".to_string()),
);
// Available memory
metrics.push(Metric::new(
registry::MEMORY_AVAILABLE_GB.to_string(),
MetricValue::Float(available_gb),
Status::Ok, // Available memory absolute value doesn't have status
).with_description("Available system memory".to_string())
.with_unit("GB".to_string()));
metrics.push(
Metric::new(
registry::MEMORY_AVAILABLE_GB.to_string(),
MetricValue::Float(available_gb),
Status::Ok, // Available memory absolute value doesn't have status
)
.with_description("Available system memory".to_string())
.with_unit("GB".to_string()),
);
// Swap metrics (only if swap exists)
if info.swap_total_kb > 0 {
metrics.push(Metric::new(
registry::MEMORY_SWAP_TOTAL_GB.to_string(),
MetricValue::Float(swap_total_gb),
Status::Ok,
).with_description("Total swap space".to_string())
.with_unit("GB".to_string()));
metrics.push(Metric::new(
registry::MEMORY_SWAP_USED_GB.to_string(),
MetricValue::Float(swap_used_gb),
Status::Ok,
).with_description("Used swap space".to_string())
.with_unit("GB".to_string()));
metrics.push(
Metric::new(
registry::MEMORY_SWAP_TOTAL_GB.to_string(),
MetricValue::Float(swap_total_gb),
Status::Ok,
)
.with_description("Total swap space".to_string())
.with_unit("GB".to_string()),
);
metrics.push(
Metric::new(
registry::MEMORY_SWAP_USED_GB.to_string(),
MetricValue::Float(swap_used_gb),
Status::Ok,
)
.with_description("Used swap space".to_string())
.with_unit("GB".to_string()),
);
}
metrics
}
}
@@ -178,34 +199,39 @@ impl Collector for MemoryCollector {
fn name(&self) -> &str {
&self.name
}
async fn collect(&self) -> Result<Vec<Metric>, CollectorError> {
async fn collect(&self, status_tracker: &mut StatusTracker) -> Result<Vec<Metric>, CollectorError> {
debug!("Collecting memory metrics");
let start = std::time::Instant::now();
// Parse memory info from /proc/meminfo
let info = self.parse_meminfo().await?;
// Calculate all metrics from parsed info
let metrics = self.calculate_metrics(&info);
let metrics = self.calculate_metrics(&info, status_tracker);
let duration = start.elapsed();
debug!("Memory collection completed in {:?} with {} metrics", duration, metrics.len());
debug!(
"Memory collection completed in {:?} with {} metrics",
duration,
metrics.len()
);
// Efficiency check: warn if collection takes too long
if duration.as_millis() > 1 {
debug!("Memory collection took {}ms - consider optimization", duration.as_millis());
debug!(
"Memory collection took {}ms - consider optimization",
duration.as_millis()
);
}
// Store performance metrics
// Performance tracking handled by cache system
Ok(metrics)
}
fn get_performance_metrics(&self) -> Option<super::PerformanceMetrics> {
None // Performance tracking handled by cache system
}
}
}

140
agent/src/collectors/mod.rs
View File

@@ -1,16 +1,7 @@
use async_trait::async_trait;
use cm_dashboard_shared::Metric;
use cm_dashboard_shared::{Metric, StatusTracker};
use std::time::Duration;
pub mod cpu;
pub mod memory;
pub mod disk;
pub mod systemd;
pub mod backup;
pub mod error;
pub use error::CollectorError;
/// Performance metrics for a collector
#[derive(Debug, Clone)]
pub struct PerformanceMetrics {
@@ -18,69 +9,78 @@ pub struct PerformanceMetrics {
pub collection_efficiency_percent: f32,
}
pub mod backup;
pub mod cpu;
pub mod disk;
pub mod error;
pub mod memory;
pub mod systemd;
pub use error::CollectorError;
/// Base trait for all collectors with extreme efficiency requirements
#[async_trait]
pub trait Collector: Send + Sync {
/// Name of this collector
fn name(&self) -> &str;
/// Collect all metrics this collector provides
async fn collect(&self) -> Result<Vec<Metric>, CollectorError>;
async fn collect(&self, status_tracker: &mut StatusTracker) -> Result<Vec<Metric>, CollectorError>;
/// Get performance metrics for monitoring collector efficiency
fn get_performance_metrics(&self) -> Option<PerformanceMetrics> {
None
}
}
/// CPU efficiency rules for all collectors
pub mod efficiency {
/// CRITICAL: All collectors must follow these efficiency rules to minimize system impact
/// 1. FILE READING RULES
/// - Read entire files in single syscall when possible
/// - Use BufReader only for very large files (>4KB)
/// - Never read files character by character
/// - Cache file descriptors when safe (immutable paths)
/// 2. PARSING RULES
/// - Use split() instead of regex for simple patterns
/// - Parse numbers with from_str() not complex parsing
/// - Avoid string allocations in hot paths
/// - Use str::trim() before parsing numbers
/// 3. MEMORY ALLOCATION RULES
/// - Reuse Vec buffers when possible
/// - Pre-allocate collections with known sizes
/// - Use str slices instead of String when possible
/// - Avoid clone() in hot paths
/// 4. SYSTEM CALL RULES
/// - Minimize syscalls - prefer single reads over multiple
/// - Use /proc filesystem efficiently
/// - Avoid spawning processes when /proc data available
/// - Cache static data (like CPU count)
/// 5. ERROR HANDLING RULES
/// - Use Result<> but minimize allocation in error paths
/// - Log errors at debug level only to avoid I/O overhead
/// - Graceful degradation - missing metrics better than failing
/// - Never panic in collectors
/// 6. CONCURRENCY RULES
/// - Collectors must be thread-safe but avoid locks
/// - Use atomic operations for simple counters
/// - Avoid shared mutable state between collections
/// - Each collection should be independent
pub const PERFORMANCE_TARGET_OVERHEAD_PERCENT: f32 = 0.1;
//! CRITICAL: All collectors must follow these efficiency rules to minimize system impact
//!
//! # FILE READING RULES
//! - Read entire files in single syscall when possible
//! - Use BufReader only for very large files (>4KB)
//! - Never read files character by character
//! - Cache file descriptors when safe (immutable paths)
//!
//! # PARSING RULES
//! - Use split() instead of regex for simple patterns
//! - Parse numbers with from_str() not complex parsing
//! - Avoid string allocations in hot paths
//! - Use str::trim() before parsing numbers
//!
//! # MEMORY ALLOCATION RULES
//! - Reuse Vec buffers when possible
//! - Pre-allocate collections with known sizes
//! - Use str slices instead of String when possible
//! - Avoid clone() in hot paths
//!
//! # SYSTEM CALL RULES
//! - Minimize syscalls - prefer single reads over multiple
//! - Use /proc filesystem efficiently
//! - Avoid spawning processes when /proc data available
//! - Cache static data (like CPU count)
//!
//! # ERROR HANDLING RULES
//! - Use Result<> but minimize allocation in error paths
//! - Log errors at debug level only to avoid I/O overhead
//! - Graceful degradation - missing metrics better than failing
//! - Never panic in collectors
//!
//! # CONCURRENCY RULES
//! - Collectors must be thread-safe but avoid locks
//! - Use atomic operations for simple counters
//! - Avoid shared mutable state between collections
//! - Each collection should be independent
}
/// Utility functions for efficient system data collection
pub mod utils {
use std::fs;
use super::CollectorError;
use std::fs;
/// Read entire file content efficiently
pub fn read_proc_file(path: &str) -> Result<String, CollectorError> {
fs::read_to_string(path).map_err(|e| CollectorError::SystemRead {
@@ -88,25 +88,25 @@ pub mod utils {
error: e.to_string(),
})
}
/// Parse float from string slice efficiently
pub fn parse_f32(s: &str) -> Result<f32, CollectorError> {
s.trim().parse().map_err(|e: std::num::ParseFloatError| CollectorError::Parse {
value: s.to_string(),
error: e.to_string(),
})
s.trim()
.parse()
.map_err(|e: std::num::ParseFloatError| CollectorError::Parse {
value: s.to_string(),
error: e.to_string(),
})
}
/// Parse integer from string slice efficiently
pub fn parse_u64(s: &str) -> Result<u64, CollectorError> {
s.trim().parse().map_err(|e: std::num::ParseIntError| CollectorError::Parse {
value: s.to_string(),
error: e.to_string(),
})
s.trim()
.parse()
.map_err(|e: std::num::ParseIntError| CollectorError::Parse {
value: s.to_string(),
error: e.to_string(),
})
}
/// Split string and get nth element safely
pub fn split_nth<'a>(s: &'a str, delimiter: char, n: usize) -> Option<&'a str> {
s.split(delimiter).nth(n)
}
}
}

4
agent/src/collectors/systemd.rs
View File

@@ -1,6 +1,6 @@
use anyhow::Result;
use async_trait::async_trait;
use cm_dashboard_shared::{Metric, MetricValue, Status};
use cm_dashboard_shared::{Metric, MetricValue, Status, StatusTracker};
use std::process::Command;
use std::sync::RwLock;
use std::time::Instant;
@@ -401,7 +401,7 @@ impl Collector for SystemdCollector {
"systemd"
}
async fn collect(&self) -> Result<Vec<Metric>, CollectorError> {
async fn collect(&self, _status_tracker: &mut StatusTracker) -> Result<Vec<Metric>, CollectorError> {
let start_time = Instant::now();
debug!("Collecting systemd services metrics");