Christoffer Martinsson 8a36472a3d Implement real-time process monitoring and fix UI hardcoded data
This commit addresses several key issues identified during development:

Major Changes:
- Replace hardcoded top CPU/RAM process display with real system data
- Add intelligent process monitoring to CpuCollector using ps command
- Fix disk metrics permission issues in systemd collector
- Optimize service collection to focus on status, memory, and disk only
- Update dashboard widgets to display live process information

Process Monitoring Implementation:
- Added collect_top_cpu_process() and collect_top_ram_process() methods
- Implemented ps-based monitoring with accurate CPU percentages
- Added filtering to prevent self-monitoring artifacts (ps commands)
- Enhanced error handling and validation for process data
- Dashboard now shows realistic values like "claude (PID 2974) 11.0%"

Service Collection Optimization:
- Removed CPU monitoring from systemd collector for efficiency
- Enhanced service directory permission error logging
- Simplified services widget to show essential metrics only
- Fixed service-to-directory mapping accuracy

UI and Dashboard Improvements:
- Reorganized dashboard layout with btop-inspired multi-panel design
- Updated system panel to include real top CPU/RAM process display
- Enhanced widget formatting and data presentation
- Removed placeholder/hardcoded data throughout the interface

Technical Details:
- Updated agent/src/collectors/cpu.rs with process monitoring
- Modified dashboard/src/ui/mod.rs for real-time process display
- Enhanced systemd collector error handling and disk metrics
- Updated CLAUDE.md documentation with implementation details
2025-10-16 23:55:05 +02:00

211 lines
7.5 KiB
Rust

use async_trait::async_trait;
use cm_dashboard_shared::{Metric, MetricValue, Status, registry};
use std::time::Duration;
use tracing::debug;
use super::{Collector, CollectorError, utils};
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
/// - Pre-calculated KB to GB conversion
/// - No regex or complex parsing
/// - <0.1ms collection time target
pub struct MemoryCollector {
config: MemoryConfig,
name: String,
}
/// Memory information parsed from /proc/meminfo
#[derive(Debug, Default)]
struct MemoryInfo {
total_kb: u64,
available_kb: u64,
free_kb: u64,
buffers_kb: u64,
cached_kb: u64,
swap_total_kb: u64,
swap_free_kb: u64,
}
impl MemoryCollector {
pub fn new(config: MemoryConfig) -> Self {
Self {
config,
name: "memory".to_string(),
}
}
/// 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
}
}
/// 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) {
match key {
"MemTotal" => info.total_kb = value_kb,
"MemAvailable" => info.available_kb = value_kb,
"MemFree" => info.free_kb = value_kb,
"Buffers" => info.buffers_kb = value_kb,
"Cached" => info.cached_kb = value_kb,
"SwapTotal" => info.swap_total_kb = value_kb,
"SwapFree" => info.swap_free_kb = value_kb,
_ => {} // Skip other fields for efficiency
}
}
}
}
}
// Validate that we got essential fields
if info.total_kb == 0 {
return Err(CollectorError::Parse {
value: "MemTotal".to_string(),
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> {
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 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()));
// 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()));
// 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()));
// 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()));
// 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
}
}
#[async_trait]
impl Collector for MemoryCollector {
fn name(&self) -> &str {
&self.name
}
async fn collect(&self) -> 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 duration = start.elapsed();
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());
}
// 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
}
}