Compare commits

..

11 Commits

Author SHA1 Message Date
6e4a42799f Bump version to v0.1.213
All checks were successful
Build and Release / build-and-release (push) Successful in 1m22s
2025-11-29 16:46:16 +01:00
afb8d68e03 Implement multi-disk backup support
- Update BackupData structure to support multiple backup disks
- Scan /var/lib/backup/status/ directory for all status files
- Calculate status icons for backup and disk usage
- Aggregate repository status from all disks
- Update dashboard to display all backup disks with per-disk status
- Display repository list with count and aggregated status
2025-11-29 16:44:50 +01:00
5e08b34280 Move C-state name cleaning to agent for smaller JSON
All checks were successful
Build and Release / build-and-release (push) Successful in 1m32s
- Agent now extracts "C" + digits pattern (C3, C10) using char parsing
- Removes suffixes like "_ACPI", "_MWAIT" at source
- Reduces JSON payload size over ZMQ
- No regex dependency - uses fast char iteration (~1μs overhead)
- Robust fallback to original name if pattern not found
- Dashboard simplified to use clean names directly

Bump version to v0.1.212

Co-Authored-By: Claude <noreply@anthropic.com>
2025-11-29 14:05:55 +01:00
0d8284b69c Clean C-state display to show only CX format
All checks were successful
Build and Release / build-and-release (push) Successful in 1m18s
- Strip suffixes like "_ACPI" from C-state names
- Display changes from "C3_ACPI:51%" to "C3:51%"
- Cleaner, more concise presentation

Bump version to v0.1.211

Co-Authored-By: Claude <noreply@anthropic.com>
2025-11-29 13:34:01 +01:00
d84690cb3b Move transmission interval to ZMQ config section
All checks were successful
Build and Release / build-and-release (push) Successful in 1m43s
- Changed code to use zmq.transmission_interval_seconds instead of top-level collection_interval_seconds
- Removed collection_interval_seconds from AgentConfig
- Updated validation to check zmq.transmission_interval_seconds
- Improves config organization by grouping all ZMQ settings together

Bump version to v0.1.210

Co-Authored-By: Claude <noreply@anthropic.com>
2025-11-29 13:31:39 +01:00
7c030b33d6 Show top 3 C-states with usage percentages
All checks were successful
Build and Release / build-and-release (push) Successful in 1m21s
- Changed CpuData.cstate from String to Vec<CStateInfo>
- Added CStateInfo struct with name and percent fields
- Collector calculates percentage for each C-state based on accumulated time
- Sorts and returns top 3 C-states by usage
- Dashboard displays: "C10:79% C8:10% C6:8%"

Provides better visibility into CPU idle state distribution.

Bump version to v0.1.209

Co-Authored-By: Claude <noreply@anthropic.com>
2025-11-28 23:45:46 +01:00
c6817537a8 Replace CPU frequency with C-state monitoring
All checks were successful
Build and Release / build-and-release (push) Successful in 1m20s
- Changed CpuData.frequency_mhz to CpuData.cstate (String)
- Implemented collect_cstate() to read CPU idle depth from sysfs
- Finds deepest C-state with most accumulated time (C0-C10)
- Updated dashboard to display C-state instead of frequency
- More accurate indicator of CPU activity vs power management

Bump version to v0.1.208

Co-Authored-By: Claude <noreply@anthropic.com>
2025-11-28 23:30:14 +01:00
2189d34b16 Bump version to v0.1.207
All checks were successful
Build and Release / build-and-release (push) Successful in 1m9s
2025-11-28 23:16:33 +01:00
28cfd5758f Fix service metrics not showing - remove cache check
The service_status_cache from discovery only has active_state with
all detailed metrics set to None. During collection, get_service_status()
was returning cached data instead of fetching fresh systemctl show data.

Now always fetch fresh data to populate memory_bytes, restart_count,
and uptime_seconds properly.
2025-11-28 23:15:51 +01:00
5deb8cf8d8 Bump version to v0.1.206
All checks were successful
Build and Release / build-and-release (push) Successful in 1m10s
2025-11-28 23:07:20 +01:00
0e01813ff5 Add service metrics from systemctl (memory, uptime, restarts)
Shared:
- Add memory_bytes, restart_count, uptime_seconds to ServiceData

Agent:
- Add new fields to ServiceStatusInfo struct
- Fetch MemoryCurrent, NRestarts, ExecMainStartTimestamp from systemctl show
- Calculate uptime from start timestamp
- Parse and populate new fields in ServiceData
- Remove unused load_state and sub_state fields

Dashboard:
- Add memory_bytes, restart_count, uptime_seconds to ServiceInfo
- Update header: Service, Status, RAM, Uptime, ↻ (restarts)
- Format memory as MB/GB
- Format uptime as Xd Xh, Xh Xm, or Xm
- Show restart count with ! prefix if > 0 to indicate instability

All metrics obtained from single systemctl show call - zero overhead.
2025-11-28 23:06:13 +01:00
14 changed files with 446 additions and 250 deletions

View File

@@ -327,9 +327,16 @@ Storage:
├─ ● Data_2: GGA04461 T: 28°C ├─ ● Data_2: GGA04461 T: 28°C
└─ ● Parity: WDZS8RY0 T: 29°C └─ ● Parity: WDZS8RY0 T: 29°C
Backup: Backup:
● Repo: 4
├─ getea
├─ vaultwarden
├─ mysql
└─ immich
● W800639Y W: 2%
├─ ● Backup: 2025-11-29T04:00:01.324623
└─ ● Usage: 8% 70GB/916GB
● WD-WCC7K1234567 T: 32°C W: 12% ● WD-WCC7K1234567 T: 32°C W: 12%
├─ Last: 2h ago (12.3GB) ├─ ● Backup: 2025-11-29T04:00:01.324623
├─ Next: in 22h
└─ ● Usage: 45% 678GB/1.5TB └─ ● Usage: 45% 678GB/1.5TB
``` ```

6
Cargo.lock generated
View File

@@ -279,7 +279,7 @@ checksum = "a1d728cc89cf3aee9ff92b05e62b19ee65a02b5702cff7d5a377e32c6ae29d8d"
[[package]] [[package]]
name = "cm-dashboard" name = "cm-dashboard"
version = "0.1.204" version = "0.1.212"
dependencies = [ dependencies = [
"anyhow", "anyhow",
"chrono", "chrono",
@@ -301,7 +301,7 @@ dependencies = [
[[package]] [[package]]
name = "cm-dashboard-agent" name = "cm-dashboard-agent"
version = "0.1.204" version = "0.1.212"
dependencies = [ dependencies = [
"anyhow", "anyhow",
"async-trait", "async-trait",
@@ -324,7 +324,7 @@ dependencies = [
[[package]] [[package]]
name = "cm-dashboard-shared" name = "cm-dashboard-shared"
version = "0.1.204" version = "0.1.212"
dependencies = [ dependencies = [
"chrono", "chrono",
"serde", "serde",

View File

@@ -1,6 +1,6 @@
[package] [package]
name = "cm-dashboard-agent" name = "cm-dashboard-agent"
version = "0.1.205" version = "0.1.213"
edition = "2021" edition = "2021"
[dependencies] [dependencies]

View File

@@ -114,7 +114,7 @@ impl Agent {
// Set up intervals // Set up intervals
let mut transmission_interval = interval(Duration::from_secs( let mut transmission_interval = interval(Duration::from_secs(
self.config.collection_interval_seconds, self.config.zmq.transmission_interval_seconds,
)); ));
let mut notification_interval = interval(Duration::from_secs(30)); // Check notifications every 30s let mut notification_interval = interval(Duration::from_secs(30)); // Check notifications every 30s

View File

@@ -1,36 +1,66 @@
use async_trait::async_trait; use async_trait::async_trait;
use cm_dashboard_shared::{AgentData, BackupData, BackupDiskData}; use cm_dashboard_shared::{AgentData, BackupData, BackupDiskData, Status};
use serde::{Deserialize, Serialize}; use serde::{Deserialize, Serialize};
use std::collections::HashMap; use std::collections::{HashMap, HashSet};
use std::fs; use std::fs;
use std::path::Path; use std::path::{Path, PathBuf};
use tracing::debug; use tracing::{debug, warn};
use super::{Collector, CollectorError}; use super::{Collector, CollectorError};
/// Backup collector that reads backup status from TOML files with structured data output /// Backup collector that reads backup status from TOML files with structured data output
pub struct BackupCollector { pub struct BackupCollector {
/// Path to backup status file /// Directory containing backup status files
status_file_path: String, status_dir: String,
} }
impl BackupCollector { impl BackupCollector {
pub fn new() -> Self { pub fn new() -> Self {
Self { Self {
status_file_path: "/var/lib/backup/backup-status.toml".to_string(), status_dir: "/var/lib/backup/status".to_string(),
} }
} }
/// Read backup status from TOML file /// Scan directory for all backup status files
async fn read_backup_status(&self) -> Result<Option<BackupStatusToml>, CollectorError> { async fn scan_status_files(&self) -> Result<Vec<PathBuf>, CollectorError> {
if !Path::new(&self.status_file_path).exists() { let status_path = Path::new(&self.status_dir);
debug!("Backup status file not found: {}", self.status_file_path);
return Ok(None); if !status_path.exists() {
debug!("Backup status directory not found: {}", self.status_dir);
return Ok(Vec::new());
} }
let content = fs::read_to_string(&self.status_file_path) let mut status_files = Vec::new();
match fs::read_dir(status_path) {
Ok(entries) => {
for entry in entries {
if let Ok(entry) = entry {
let path = entry.path();
if path.is_file() {
if let Some(filename) = path.file_name().and_then(|n| n.to_str()) {
if filename.starts_with("backup-status-") && filename.ends_with(".toml") {
status_files.push(path);
}
}
}
}
}
}
Err(e) => {
warn!("Failed to read backup status directory: {}", e);
return Ok(Vec::new());
}
}
Ok(status_files)
}
/// Read a single backup status file
async fn read_status_file(&self, path: &Path) -> Result<BackupStatusToml, CollectorError> {
let content = fs::read_to_string(path)
.map_err(|e| CollectorError::SystemRead { .map_err(|e| CollectorError::SystemRead {
path: self.status_file_path.clone(), path: path.to_string_lossy().to_string(),
error: e.to_string(), error: e.to_string(),
})?; })?;
@@ -40,66 +70,109 @@ impl BackupCollector {
error: format!("Failed to parse backup status TOML: {}", e), error: format!("Failed to parse backup status TOML: {}", e),
})?; })?;
Ok(Some(status)) Ok(status)
}
/// Calculate backup status from TOML status field
fn calculate_backup_status(status_str: &str) -> Status {
match status_str.to_lowercase().as_str() {
"success" => Status::Ok,
"warning" => Status::Warning,
"failed" | "error" => Status::Critical,
_ => Status::Unknown,
}
}
/// Calculate usage status from disk usage percentage
fn calculate_usage_status(usage_percent: f32) -> Status {
if usage_percent < 80.0 {
Status::Ok
} else if usage_percent < 90.0 {
Status::Warning
} else {
Status::Critical
}
} }
/// Convert BackupStatusToml to BackupData and populate AgentData /// Convert BackupStatusToml to BackupData and populate AgentData
async fn populate_backup_data(&self, agent_data: &mut AgentData) -> Result<(), CollectorError> { async fn populate_backup_data(&self, agent_data: &mut AgentData) -> Result<(), CollectorError> {
if let Some(backup_status) = self.read_backup_status().await? { let status_files = self.scan_status_files().await?;
// Use raw start_time string from TOML
// Extract disk information if status_files.is_empty() {
let repository_disk = if let Some(disk_space) = &backup_status.disk_space { debug!("No backup status files found");
Some(BackupDiskData {
serial: backup_status.disk_serial_number.clone().unwrap_or_else(|| "Unknown".to_string()),
usage_percent: disk_space.usage_percent as f32,
used_gb: disk_space.used_gb as f32,
total_gb: disk_space.total_gb as f32,
wear_percent: backup_status.disk_wear_percent,
temperature_celsius: None, // Not available in current TOML
})
} else if let Some(serial) = &backup_status.disk_serial_number {
// Fallback: create minimal disk info if we have serial but no disk_space
Some(BackupDiskData {
serial: serial.clone(),
usage_percent: 0.0,
used_gb: 0.0,
total_gb: 0.0,
wear_percent: backup_status.disk_wear_percent,
temperature_celsius: None,
})
} else {
None
};
// Calculate total repository size from services
let total_size_gb = backup_status.services
.values()
.map(|service| service.repo_size_bytes as f32 / (1024.0 * 1024.0 * 1024.0))
.sum::<f32>();
let backup_data = BackupData {
status: backup_status.status,
total_size_gb: Some(total_size_gb),
repository_health: Some("ok".to_string()), // Derive from status if needed
repository_disk,
last_backup_size_gb: None, // Not available in current TOML format
start_time_raw: Some(backup_status.start_time),
};
agent_data.backup = backup_data;
} else {
// No backup status available - set default values
agent_data.backup = BackupData { agent_data.backup = BackupData {
status: "unavailable".to_string(), repositories: Vec::new(),
total_size_gb: None, repository_status: Status::Unknown,
repository_health: None, disks: Vec::new(),
repository_disk: None,
last_backup_size_gb: None,
start_time_raw: None,
}; };
return Ok(());
} }
let mut all_repositories = HashSet::new();
let mut disks = Vec::new();
let mut worst_status = Status::Ok;
for status_file in status_files {
match self.read_status_file(&status_file).await {
Ok(backup_status) => {
// Collect all service names
for service_name in backup_status.services.keys() {
all_repositories.insert(service_name.clone());
}
// Calculate backup status
let backup_status_enum = Self::calculate_backup_status(&backup_status.status);
// Calculate usage status from disk space
let (usage_percent, used_gb, total_gb, usage_status) = if let Some(disk_space) = &backup_status.disk_space {
let usage_pct = disk_space.usage_percent as f32;
(
usage_pct,
disk_space.used_gb as f32,
disk_space.total_gb as f32,
Self::calculate_usage_status(usage_pct),
)
} else {
(0.0, 0.0, 0.0, Status::Unknown)
};
// Update worst status
worst_status = worst_status.max(backup_status_enum).max(usage_status);
// Build service list for this disk
let services: Vec<String> = backup_status.services.keys().cloned().collect();
// Create disk data
let disk_data = BackupDiskData {
serial: backup_status.disk_serial_number.unwrap_or_else(|| "Unknown".to_string()),
product_name: backup_status.disk_product_name,
wear_percent: backup_status.disk_wear_percent,
temperature_celsius: None, // Not available in current TOML
last_backup_time: Some(backup_status.start_time),
backup_status: backup_status_enum,
disk_usage_percent: usage_percent,
disk_used_gb: used_gb,
disk_total_gb: total_gb,
usage_status,
services,
};
disks.push(disk_data);
}
Err(e) => {
warn!("Failed to read backup status file {:?}: {}", status_file, e);
}
}
}
let repositories: Vec<String> = all_repositories.into_iter().collect();
agent_data.backup = BackupData {
repositories,
repository_status: worst_status,
disks,
};
Ok(()) Ok(())
} }
} }

View File

@@ -119,36 +119,69 @@ impl CpuCollector {
utils::parse_u64(content.trim()) utils::parse_u64(content.trim())
} }
/// Collect CPU frequency and populate AgentData /// Collect CPU C-state (idle depth) and populate AgentData with top 3 C-states by usage
async fn collect_frequency(&self, agent_data: &mut AgentData) -> Result<(), CollectorError> { async fn collect_cstate(&self, agent_data: &mut AgentData) -> Result<(), CollectorError> {
// Try scaling frequency first (more accurate for current frequency) // Read C-state usage from first CPU (representative of overall system)
if let Ok(freq) = // C-states indicate CPU idle depth: C1=light sleep, C6=deep sleep, C10=deepest
utils::read_proc_file("/sys/devices/system/cpu/cpu0/cpufreq/scaling_cur_freq")
{
if let Ok(freq_khz) = utils::parse_u64(freq.trim()) {
let freq_mhz = freq_khz as f32 / 1000.0;
agent_data.system.cpu.frequency_mhz = freq_mhz;
return Ok(());
}
}
// Fallback: parse /proc/cpuinfo for base frequency let mut cstate_times: Vec<(String, u64)> = Vec::new();
if let Ok(content) = utils::read_proc_file("/proc/cpuinfo") { let mut total_time: u64 = 0;
for line in content.lines() {
if line.starts_with("cpu MHz") { // Collect all C-state times from CPU0
if let Some(freq_str) = line.split(':').nth(1) { for state_num in 0..=10 {
if let Ok(freq_mhz) = utils::parse_f32(freq_str) { let time_path = format!("/sys/devices/system/cpu/cpu0/cpuidle/state{}/time", state_num);
agent_data.system.cpu.frequency_mhz = freq_mhz; let name_path = format!("/sys/devices/system/cpu/cpu0/cpuidle/state{}/name", state_num);
return Ok(());
if let Ok(time_str) = utils::read_proc_file(&time_path) {
if let Ok(time) = utils::parse_u64(time_str.trim()) {
if let Ok(name) = utils::read_proc_file(&name_path) {
let state_name = name.trim();
// Skip POLL state (not real idle)
if state_name != "POLL" && time > 0 {
// Extract "C" + digits pattern (C3, C10, etc.) to reduce JSON size
// Handles formats like "C3_ACPI", "C10_MWAIT", etc.
let clean_name = if let Some(c_pos) = state_name.find('C') {
let rest = &state_name[c_pos + 1..];
let digit_count = rest.chars().take_while(|c| c.is_ascii_digit()).count();
if digit_count > 0 {
state_name[c_pos..c_pos + 1 + digit_count].to_string()
} else {
state_name.to_string()
}
} else {
state_name.to_string()
};
cstate_times.push((clean_name, time));
total_time += time;
} }
} }
break; // Only need first CPU entry
} }
} else {
// No more states available
break;
} }
} }
debug!("CPU frequency not available"); // Sort by time descending to get top 3
// Leave frequency as 0.0 if not available cstate_times.sort_by(|a, b| b.1.cmp(&a.1));
// Calculate percentages for top 3 and populate AgentData
agent_data.system.cpu.cstates = cstate_times
.iter()
.take(3)
.map(|(name, time)| {
let percent = if total_time > 0 {
(*time as f32 / total_time as f32) * 100.0
} else {
0.0
};
cm_dashboard_shared::CStateInfo {
name: name.clone(),
percent,
}
})
.collect();
Ok(()) Ok(())
} }
} }
@@ -165,8 +198,8 @@ impl Collector for CpuCollector {
// Collect temperature (optional) // Collect temperature (optional)
self.collect_temperature(agent_data).await?; self.collect_temperature(agent_data).await?;
// Collect frequency (optional) // Collect C-state (CPU idle depth)
self.collect_frequency(agent_data).await?; self.collect_cstate(agent_data).await?;
let duration = start.elapsed(); let duration = start.elapsed();
debug!("CPU collection completed in {:?}", duration); debug!("CPU collection completed in {:?}", duration);

View File

@@ -43,9 +43,10 @@ struct ServiceCacheState {
/// Cached service status information from systemctl list-units /// Cached service status information from systemctl list-units
#[derive(Debug, Clone)] #[derive(Debug, Clone)]
struct ServiceStatusInfo { struct ServiceStatusInfo {
load_state: String,
active_state: String, active_state: String,
sub_state: String, memory_bytes: Option<u64>,
restart_count: Option<u32>,
start_timestamp: Option<u64>,
} }
impl SystemdCollector { impl SystemdCollector {
@@ -86,11 +87,20 @@ impl SystemdCollector {
let mut complete_service_data = Vec::new(); let mut complete_service_data = Vec::new();
for service_name in &monitored_services { for service_name in &monitored_services {
match self.get_service_status(service_name) { match self.get_service_status(service_name) {
Ok((active_status, _detailed_info)) => { Ok(status_info) => {
let mut sub_services = Vec::new(); let mut sub_services = Vec::new();
// Calculate uptime if we have start timestamp
let uptime_seconds = status_info.start_timestamp.and_then(|start| {
let now = std::time::SystemTime::now()
.duration_since(std::time::UNIX_EPOCH)
.ok()?
.as_secs();
Some(now.saturating_sub(start))
});
// Sub-service metrics for specific services (always include cached results) // Sub-service metrics for specific services (always include cached results)
if service_name.contains("nginx") && active_status == "active" { if service_name.contains("nginx") && status_info.active_state == "active" {
let nginx_sites = self.get_nginx_site_metrics(); let nginx_sites = self.get_nginx_site_metrics();
for (site_name, latency_ms) in nginx_sites { for (site_name, latency_ms) in nginx_sites {
let site_status = if latency_ms >= 0.0 && latency_ms < self.config.nginx_latency_critical_ms { let site_status = if latency_ms >= 0.0 && latency_ms < self.config.nginx_latency_critical_ms {
@@ -115,7 +125,7 @@ impl SystemdCollector {
} }
} }
if service_name.contains("docker") && active_status == "active" { if service_name.contains("docker") && status_info.active_state == "active" {
let docker_containers = self.get_docker_containers(); let docker_containers = self.get_docker_containers();
for (container_name, container_status) in docker_containers { for (container_name, container_status) in docker_containers {
// For now, docker containers have no additional metrics // For now, docker containers have no additional metrics
@@ -153,8 +163,11 @@ impl SystemdCollector {
let service_data = ServiceData { let service_data = ServiceData {
name: service_name.clone(), name: service_name.clone(),
user_stopped: false, // TODO: Integrate with service tracker user_stopped: false, // TODO: Integrate with service tracker
service_status: self.calculate_service_status(service_name, &active_status), service_status: self.calculate_service_status(service_name, &status_info.active_state),
sub_services, sub_services,
memory_bytes: status_info.memory_bytes,
restart_count: status_info.restart_count,
uptime_seconds,
}; };
// Add to AgentData and cache // Add to AgentData and cache
@@ -290,14 +303,13 @@ impl SystemdCollector {
let fields: Vec<&str> = line.split_whitespace().collect(); let fields: Vec<&str> = line.split_whitespace().collect();
if fields.len() >= 4 && fields[0].ends_with(".service") { if fields.len() >= 4 && fields[0].ends_with(".service") {
let service_name = fields[0].trim_end_matches(".service"); let service_name = fields[0].trim_end_matches(".service");
let load_state = fields.get(1).unwrap_or(&"unknown").to_string();
let active_state = fields.get(2).unwrap_or(&"unknown").to_string(); let active_state = fields.get(2).unwrap_or(&"unknown").to_string();
let sub_state = fields.get(3).unwrap_or(&"unknown").to_string();
status_cache.insert(service_name.to_string(), ServiceStatusInfo { status_cache.insert(service_name.to_string(), ServiceStatusInfo {
load_state,
active_state, active_state,
sub_state, memory_bytes: None,
restart_count: None,
start_timestamp: None,
}); });
} }
} }
@@ -306,9 +318,10 @@ impl SystemdCollector {
for service_name in &all_service_names { for service_name in &all_service_names {
if !status_cache.contains_key(service_name) { if !status_cache.contains_key(service_name) {
status_cache.insert(service_name.to_string(), ServiceStatusInfo { status_cache.insert(service_name.to_string(), ServiceStatusInfo {
load_state: "not-loaded".to_string(),
active_state: "inactive".to_string(), active_state: "inactive".to_string(),
sub_state: "dead".to_string(), memory_bytes: None,
restart_count: None,
start_timestamp: None,
}); });
} }
} }
@@ -340,36 +353,60 @@ impl SystemdCollector {
Ok((services, status_cache)) Ok((services, status_cache))
} }
/// Get service status from cache (if available) or fallback to systemctl /// Get service status with detailed metrics from systemctl
fn get_service_status(&self, service: &str) -> Result<(String, String)> { fn get_service_status(&self, service: &str) -> Result<ServiceStatusInfo> {
// Try to get status from cache first // Always fetch fresh data to get detailed metrics (memory, restarts, uptime)
if let Ok(state) = self.state.read() { // Note: Cache in service_status_cache only has basic active_state from discovery,
if let Some(cached_info) = state.service_status_cache.get(service) { // with all detailed metrics set to None. We need fresh systemctl show data.
let active_status = cached_info.active_state.clone();
let detailed_info = format!( let output = Command::new("timeout")
"LoadState={}\nActiveState={}\nSubState={}", .args(&[
cached_info.load_state, "2",
cached_info.active_state, "systemctl",
cached_info.sub_state "show",
); &format!("{}.service", service),
return Ok((active_status, detailed_info)); "--property=LoadState,ActiveState,SubState,MemoryCurrent,NRestarts,ExecMainStartTimestamp"
])
.output()?;
let output_str = String::from_utf8(output.stdout)?;
// Parse properties
let mut active_state = String::new();
let mut memory_bytes = None;
let mut restart_count = None;
let mut start_timestamp = None;
for line in output_str.lines() {
if let Some(value) = line.strip_prefix("ActiveState=") {
active_state = value.to_string();
} else if let Some(value) = line.strip_prefix("MemoryCurrent=") {
if value != "[not set]" {
memory_bytes = value.parse().ok();
}
} else if let Some(value) = line.strip_prefix("NRestarts=") {
restart_count = value.parse().ok();
} else if let Some(value) = line.strip_prefix("ExecMainStartTimestamp=") {
if value != "[not set]" && !value.is_empty() {
// Parse timestamp to seconds since epoch
if let Ok(output) = Command::new("date")
.args(&["+%s", "-d", value])
.output()
{
if let Ok(timestamp_str) = String::from_utf8(output.stdout) {
start_timestamp = timestamp_str.trim().parse().ok();
}
}
}
} }
} }
// Fallback to systemctl if not in cache (with 2 second timeout) Ok(ServiceStatusInfo {
let output = Command::new("timeout") active_state,
.args(&["2", "systemctl", "is-active", &format!("{}.service", service)]) memory_bytes,
.output()?; restart_count,
start_timestamp,
let active_status = String::from_utf8(output.stdout)?.trim().to_string(); })
// Get more detailed info (with 2 second timeout)
let output = Command::new("timeout")
.args(&["2", "systemctl", "show", &format!("{}.service", service), "--property=LoadState,ActiveState,SubState"])
.output()?;
let detailed_info = String::from_utf8(output.stdout)?;
Ok((active_status, detailed_info))
} }
/// Check if service name matches pattern (supports wildcards like nginx*) /// Check if service name matches pattern (supports wildcards like nginx*)

View File

@@ -13,7 +13,6 @@ pub struct AgentConfig {
pub collectors: CollectorConfig, pub collectors: CollectorConfig,
pub cache: CacheConfig, pub cache: CacheConfig,
pub notifications: NotificationConfig, pub notifications: NotificationConfig,
pub collection_interval_seconds: u64,
} }
/// ZMQ communication configuration /// ZMQ communication configuration

View File

@@ -11,9 +11,9 @@ pub fn validate_config(config: &AgentConfig) -> Result<()> {
bail!("ZMQ bind address cannot be empty"); bail!("ZMQ bind address cannot be empty");
} }
// Validate collection interval // Validate ZMQ transmission interval
if config.collection_interval_seconds == 0 { if config.zmq.transmission_interval_seconds == 0 {
bail!("Collection interval cannot be 0"); bail!("ZMQ transmission interval cannot be 0");
} }
// Validate CPU thresholds // Validate CPU thresholds

View File

@@ -1,6 +1,6 @@
[package] [package]
name = "cm-dashboard" name = "cm-dashboard"
version = "0.1.205" version = "0.1.213"
edition = "2021" edition = "2021"
[dependencies] [dependencies]

View File

@@ -31,6 +31,9 @@ struct ServiceInfo {
metrics: Vec<(String, f32, Option<String>)>, // (label, value, unit) metrics: Vec<(String, f32, Option<String>)>, // (label, value, unit)
widget_status: Status, widget_status: Status,
service_type: String, // "nginx_site", "container", "image", or empty for parent services service_type: String, // "nginx_site", "container", "image", or empty for parent services
memory_bytes: Option<u64>,
restart_count: Option<u32>,
uptime_seconds: Option<u64>,
} }
impl ServicesWidget { impl ServicesWidget {
@@ -84,7 +87,7 @@ impl ServicesWidget {
// Convert Status enum to display text // Convert Status enum to display text
let status_str = match info.widget_status { let status_str = match info.widget_status {
Status::Ok => "active", Status::Ok => "active",
Status::Inactive => "inactive", Status::Inactive => "inactive",
Status::Critical => "failed", Status::Critical => "failed",
Status::Pending => "pending", Status::Pending => "pending",
Status::Warning => "warning", Status::Warning => "warning",
@@ -92,9 +95,43 @@ impl ServicesWidget {
Status::Offline => "offline", Status::Offline => "offline",
}; };
// Format memory
let memory_str = info.memory_bytes.map_or("-".to_string(), |bytes| {
let mb = bytes as f64 / (1024.0 * 1024.0);
if mb >= 1000.0 {
format!("{:.1}G", mb / 1024.0)
} else {
format!("{:.0}M", mb)
}
});
// Format uptime
let uptime_str = info.uptime_seconds.map_or("-".to_string(), |secs| {
let days = secs / 86400;
let hours = (secs % 86400) / 3600;
let mins = (secs % 3600) / 60;
if days > 0 {
format!("{}d{}h", days, hours)
} else if hours > 0 {
format!("{}h{}m", hours, mins)
} else {
format!("{}m", mins)
}
});
// Format restarts (show "!" if > 0 to indicate instability)
let restart_str = info.restart_count.map_or("-".to_string(), |count| {
if count > 0 {
format!("!{}", count)
} else {
"0".to_string()
}
});
format!( format!(
"{:<23} {:<10}", "{:<23} {:<10} {:<8} {:<8} {:<5}",
short_name, status_str short_name, status_str, memory_str, uptime_str, restart_str
) )
} }
@@ -280,6 +317,9 @@ impl Widget for ServicesWidget {
metrics: Vec::new(), // Parent services don't have custom metrics metrics: Vec::new(), // Parent services don't have custom metrics
widget_status: service.service_status, widget_status: service.service_status,
service_type: String::new(), // Parent services have no type service_type: String::new(), // Parent services have no type
memory_bytes: service.memory_bytes,
restart_count: service.restart_count,
uptime_seconds: service.uptime_seconds,
}; };
self.parent_services.insert(service.name.clone(), parent_info); self.parent_services.insert(service.name.clone(), parent_info);
@@ -296,6 +336,9 @@ impl Widget for ServicesWidget {
metrics, metrics,
widget_status: sub_service.service_status, widget_status: sub_service.service_status,
service_type: sub_service.service_type.clone(), service_type: sub_service.service_type.clone(),
memory_bytes: None, // Sub-services don't have individual metrics yet
restart_count: None,
uptime_seconds: None,
}; };
sub_list.push((sub_service.name.clone(), sub_info)); sub_list.push((sub_service.name.clone(), sub_info));
} }
@@ -338,6 +381,9 @@ impl ServicesWidget {
metrics: Vec::new(), metrics: Vec::new(),
widget_status: Status::Unknown, widget_status: Status::Unknown,
service_type: String::new(), service_type: String::new(),
memory_bytes: None,
restart_count: None,
uptime_seconds: None,
}); });
if metric.name.ends_with("_status") { if metric.name.ends_with("_status") {
@@ -364,6 +410,9 @@ impl ServicesWidget {
metrics: Vec::new(), metrics: Vec::new(),
widget_status: Status::Unknown, widget_status: Status::Unknown,
service_type: String::new(), // Unknown type in legacy path service_type: String::new(), // Unknown type in legacy path
memory_bytes: None,
restart_count: None,
uptime_seconds: None,
}, },
)); ));
&mut sub_service_list.last_mut().unwrap().1 &mut sub_service_list.last_mut().unwrap().1
@@ -429,8 +478,8 @@ impl ServicesWidget {
// Header // Header
let header = format!( let header = format!(
"{:<25} {:<10}", "{:<25} {:<10} {:<8} {:<8} {:<5}",
"Service:", "Status:" "Service:", "Status:", "RAM:", "Uptime:", "↻:"
); );
let header_para = Paragraph::new(header).style(Typography::muted()); let header_para = Paragraph::new(header).style(Typography::muted());
frame.render_widget(header_para, content_chunks[0]); frame.render_widget(header_para, content_chunks[0]);

View File

@@ -26,7 +26,7 @@ pub struct SystemWidget {
cpu_load_1min: Option<f32>, cpu_load_1min: Option<f32>,
cpu_load_5min: Option<f32>, cpu_load_5min: Option<f32>,
cpu_load_15min: Option<f32>, cpu_load_15min: Option<f32>,
cpu_frequency: Option<f32>, cpu_cstates: Vec<cm_dashboard_shared::CStateInfo>,
cpu_status: Status, cpu_status: Status,
// Memory metrics // Memory metrics
@@ -45,15 +45,9 @@ pub struct SystemWidget {
storage_pools: Vec<StoragePool>, storage_pools: Vec<StoragePool>,
// Backup metrics // Backup metrics
backup_status: String, backup_repositories: Vec<String>,
backup_start_time_raw: Option<String>, backup_repository_status: Status,
backup_disk_serial: Option<String>, backup_disks: Vec<cm_dashboard_shared::BackupDiskData>,
backup_disk_usage_percent: Option<f32>,
backup_disk_used_gb: Option<f32>,
backup_disk_total_gb: Option<f32>,
backup_disk_wear_percent: Option<f32>,
backup_disk_temperature: Option<f32>,
backup_last_size_gb: Option<f32>,
// Overall status // Overall status
has_data: bool, has_data: bool,
@@ -102,7 +96,7 @@ impl SystemWidget {
cpu_load_1min: None, cpu_load_1min: None,
cpu_load_5min: None, cpu_load_5min: None,
cpu_load_15min: None, cpu_load_15min: None,
cpu_frequency: None, cpu_cstates: Vec::new(),
cpu_status: Status::Unknown, cpu_status: Status::Unknown,
memory_usage_percent: None, memory_usage_percent: None,
memory_used_gb: None, memory_used_gb: None,
@@ -114,15 +108,9 @@ impl SystemWidget {
tmp_status: Status::Unknown, tmp_status: Status::Unknown,
tmpfs_mounts: Vec::new(), tmpfs_mounts: Vec::new(),
storage_pools: Vec::new(), storage_pools: Vec::new(),
backup_status: "unknown".to_string(), backup_repositories: Vec::new(),
backup_start_time_raw: None, backup_repository_status: Status::Unknown,
backup_disk_serial: None, backup_disks: Vec::new(),
backup_disk_usage_percent: None,
backup_disk_used_gb: None,
backup_disk_total_gb: None,
backup_disk_wear_percent: None,
backup_disk_temperature: None,
backup_last_size_gb: None,
has_data: false, has_data: false,
} }
} }
@@ -137,12 +125,19 @@ impl SystemWidget {
} }
} }
/// Format CPU frequency /// Format CPU C-states (idle depth) with percentages
fn format_cpu_frequency(&self) -> String { fn format_cpu_cstate(&self) -> String {
match self.cpu_frequency { if self.cpu_cstates.is_empty() {
Some(freq) => format!("{:.0} MHz", freq), return "".to_string();
None => "— MHz".to_string(),
} }
// Format top 3 C-states with percentages: "C10:79% C8:10% C6:8%"
// Agent already sends clean names (C3, C10, etc.)
self.cpu_cstates
.iter()
.map(|cs| format!("{}:{:.0}%", cs.name, cs.percent))
.collect::<Vec<_>>()
.join(" ")
} }
/// Format memory usage /// Format memory usage
@@ -188,7 +183,7 @@ impl Widget for SystemWidget {
self.cpu_load_1min = Some(cpu.load_1min); self.cpu_load_1min = Some(cpu.load_1min);
self.cpu_load_5min = Some(cpu.load_5min); self.cpu_load_5min = Some(cpu.load_5min);
self.cpu_load_15min = Some(cpu.load_15min); self.cpu_load_15min = Some(cpu.load_15min);
self.cpu_frequency = Some(cpu.frequency_mhz); self.cpu_cstates = cpu.cstates.clone();
self.cpu_status = Status::Ok; self.cpu_status = Status::Ok;
// Extract memory data directly // Extract memory data directly
@@ -214,25 +209,9 @@ impl Widget for SystemWidget {
// Extract backup data // Extract backup data
let backup = &agent_data.backup; let backup = &agent_data.backup;
self.backup_status = backup.status.clone(); self.backup_repositories = backup.repositories.clone();
self.backup_start_time_raw = backup.start_time_raw.clone(); self.backup_repository_status = backup.repository_status;
self.backup_last_size_gb = backup.last_backup_size_gb; self.backup_disks = backup.disks.clone();
if let Some(disk) = &backup.repository_disk {
self.backup_disk_serial = Some(disk.serial.clone());
self.backup_disk_usage_percent = Some(disk.usage_percent);
self.backup_disk_used_gb = Some(disk.used_gb);
self.backup_disk_total_gb = Some(disk.total_gb);
self.backup_disk_wear_percent = disk.wear_percent;
self.backup_disk_temperature = disk.temperature_celsius;
} else {
self.backup_disk_serial = None;
self.backup_disk_usage_percent = None;
self.backup_disk_used_gb = None;
self.backup_disk_total_gb = None;
self.backup_disk_wear_percent = None;
self.backup_disk_temperature = None;
}
} }
} }
@@ -532,14 +511,32 @@ impl SystemWidget {
fn render_backup(&self) -> Vec<Line<'_>> { fn render_backup(&self) -> Vec<Line<'_>> {
let mut lines = Vec::new(); let mut lines = Vec::new();
// First line: serial number with temperature and wear // First section: Repository status and list
if let Some(serial) = &self.backup_disk_serial { if !self.backup_repositories.is_empty() {
let truncated_serial = truncate_serial(serial); let repo_text = format!("Repo: {}", self.backup_repositories.len());
let repo_spans = StatusIcons::create_status_spans(self.backup_repository_status, &repo_text);
lines.push(Line::from(repo_spans));
// List all repositories
let repo_count = self.backup_repositories.len();
for (idx, repo) in self.backup_repositories.iter().enumerate() {
let tree_char = if idx == repo_count - 1 { "└─" } else { "├─" };
lines.push(Line::from(vec![
Span::styled(format!(" {} ", tree_char), Typography::tree()),
Span::styled(repo, Typography::secondary()),
]));
}
}
// Second section: Per-disk backup information
for disk in &self.backup_disks {
let truncated_serial = truncate_serial(&disk.serial);
let mut details = Vec::new(); let mut details = Vec::new();
if let Some(temp) = self.backup_disk_temperature {
if let Some(temp) = disk.temperature_celsius {
details.push(format!("T: {}°C", temp as i32)); details.push(format!("T: {}°C", temp as i32));
} }
if let Some(wear) = self.backup_disk_wear_percent { if let Some(wear) = disk.wear_percent {
details.push(format!("W: {}%", wear as i32)); details.push(format!("W: {}%", wear as i32));
} }
@@ -549,44 +546,33 @@ impl SystemWidget {
truncated_serial truncated_serial
}; };
let backup_status = match self.backup_status.as_str() { // Overall disk status (worst of backup and usage)
"completed" | "success" => Status::Ok, let disk_status = disk.backup_status.max(disk.usage_status);
"running" => Status::Pending, let disk_spans = StatusIcons::create_status_spans(disk_status, &disk_text);
"failed" => Status::Critical,
_ => Status::Unknown,
};
let disk_spans = StatusIcons::create_status_spans(backup_status, &disk_text);
lines.push(Line::from(disk_spans)); lines.push(Line::from(disk_spans));
// Show backup time from TOML if available // Show backup time with status
if let Some(start_time) = &self.backup_start_time_raw { if let Some(backup_time) = &disk.last_backup_time {
let time_text = if let Some(size) = self.backup_last_size_gb { let time_text = format!("Backup: {}", backup_time);
format!("Time: {} ({:.1}GB)", start_time, size) let mut time_spans = vec![
} else {
format!("Time: {}", start_time)
};
lines.push(Line::from(vec![
Span::styled(" ├─ ", Typography::tree()), Span::styled(" ├─ ", Typography::tree()),
Span::styled(time_text, Typography::secondary()) ];
])); time_spans.extend(StatusIcons::create_status_spans(disk.backup_status, &time_text));
lines.push(Line::from(time_spans));
} }
// Usage information // Show usage with status
if let (Some(used), Some(total), Some(usage_percent)) = ( let usage_text = format!(
self.backup_disk_used_gb, "Usage: {:.0}% {:.0}GB/{:.0}GB",
self.backup_disk_total_gb, disk.disk_usage_percent,
self.backup_disk_usage_percent disk.disk_used_gb,
) { disk.disk_total_gb
let usage_text = format!("Usage: {:.0}% {:.0}GB/{:.0}GB", usage_percent, used, total); );
let usage_spans = StatusIcons::create_status_spans(Status::Ok, &usage_text); let mut usage_spans = vec![
let mut full_spans = vec![ Span::styled(" └─ ", Typography::tree()),
Span::styled(" └─ ", Typography::tree()), ];
]; usage_spans.extend(StatusIcons::create_status_spans(disk.usage_status, &usage_text));
full_spans.extend(usage_spans); lines.push(Line::from(usage_spans));
lines.push(Line::from(full_spans));
}
} }
lines lines
@@ -832,10 +818,10 @@ impl SystemWidget {
); );
lines.push(Line::from(cpu_spans)); lines.push(Line::from(cpu_spans));
let freq_text = self.format_cpu_frequency(); let cstate_text = self.format_cpu_cstate();
lines.push(Line::from(vec![ lines.push(Line::from(vec![
Span::styled(" └─ ", Typography::tree()), Span::styled(" └─ ", Typography::tree()),
Span::styled(format!("Freq: {}", freq_text), Typography::secondary()) Span::styled(format!("C-state: {}", cstate_text), Typography::secondary())
])); ]));
// RAM section // RAM section
@@ -894,7 +880,7 @@ impl SystemWidget {
lines.extend(storage_lines); lines.extend(storage_lines);
// Backup section (if available) // Backup section (if available)
if self.backup_status != "unavailable" && self.backup_status != "unknown" { if !self.backup_repositories.is_empty() || !self.backup_disks.is_empty() {
lines.push(Line::from(vec![ lines.push(Line::from(vec![
Span::styled("Backup:", Typography::widget_title()) Span::styled("Backup:", Typography::widget_title())
])); ]));

View File

@@ -1,6 +1,6 @@
[package] [package]
name = "cm-dashboard-shared" name = "cm-dashboard-shared"
version = "0.1.205" version = "0.1.213"
edition = "2021" edition = "2021"
[dependencies] [dependencies]

View File

@@ -40,13 +40,20 @@ pub struct NetworkInterfaceData {
pub vlan_id: Option<u16>, pub vlan_id: Option<u16>,
} }
/// CPU C-state usage information
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct CStateInfo {
pub name: String,
pub percent: f32,
}
/// CPU monitoring data /// CPU monitoring data
#[derive(Debug, Clone, Serialize, Deserialize)] #[derive(Debug, Clone, Serialize, Deserialize)]
pub struct CpuData { pub struct CpuData {
pub load_1min: f32, pub load_1min: f32,
pub load_5min: f32, pub load_5min: f32,
pub load_15min: f32, pub load_15min: f32,
pub frequency_mhz: f32, pub cstates: Vec<CStateInfo>, // C-state usage percentages (C1, C6, C10, etc.) - indicates CPU idle depth distribution
pub temperature_celsius: Option<f32>, pub temperature_celsius: Option<f32>,
pub load_status: Status, pub load_status: Status,
pub temperature_status: Status, pub temperature_status: Status,
@@ -139,6 +146,12 @@ pub struct ServiceData {
pub user_stopped: bool, pub user_stopped: bool,
pub service_status: Status, pub service_status: Status,
pub sub_services: Vec<SubServiceData>, pub sub_services: Vec<SubServiceData>,
/// Memory usage in bytes (from MemoryCurrent)
pub memory_bytes: Option<u64>,
/// Number of service restarts (from NRestarts)
pub restart_count: Option<u32>,
/// Uptime in seconds (calculated from ExecMainStartTimestamp)
pub uptime_seconds: Option<u64>,
} }
/// Sub-service data (nginx sites, docker containers, etc.) /// Sub-service data (nginx sites, docker containers, etc.)
@@ -163,23 +176,25 @@ pub struct SubServiceMetric {
/// Backup system data /// Backup system data
#[derive(Debug, Clone, Serialize, Deserialize)] #[derive(Debug, Clone, Serialize, Deserialize)]
pub struct BackupData { pub struct BackupData {
pub status: String, pub repositories: Vec<String>,
pub total_size_gb: Option<f32>, pub repository_status: Status,
pub repository_health: Option<String>, pub disks: Vec<BackupDiskData>,
pub repository_disk: Option<BackupDiskData>,
pub last_backup_size_gb: Option<f32>,
pub start_time_raw: Option<String>,
} }
/// Backup repository disk information /// Backup repository disk information
#[derive(Debug, Clone, Serialize, Deserialize)] #[derive(Debug, Clone, Serialize, Deserialize)]
pub struct BackupDiskData { pub struct BackupDiskData {
pub serial: String, pub serial: String,
pub usage_percent: f32, pub product_name: Option<String>,
pub used_gb: f32,
pub total_gb: f32,
pub wear_percent: Option<f32>, pub wear_percent: Option<f32>,
pub temperature_celsius: Option<f32>, pub temperature_celsius: Option<f32>,
pub last_backup_time: Option<String>,
pub backup_status: Status,
pub disk_usage_percent: f32,
pub disk_used_gb: f32,
pub disk_total_gb: f32,
pub usage_status: Status,
pub services: Vec<String>,
} }
impl AgentData { impl AgentData {
@@ -198,7 +213,7 @@ impl AgentData {
load_1min: 0.0, load_1min: 0.0,
load_5min: 0.0, load_5min: 0.0,
load_15min: 0.0, load_15min: 0.0,
frequency_mhz: 0.0, cstates: Vec::new(),
temperature_celsius: None, temperature_celsius: None,
load_status: Status::Unknown, load_status: Status::Unknown,
temperature_status: Status::Unknown, temperature_status: Status::Unknown,
@@ -220,12 +235,9 @@ impl AgentData {
}, },
services: Vec::new(), services: Vec::new(),
backup: BackupData { backup: BackupData {
status: "unknown".to_string(), repositories: Vec::new(),
total_size_gb: None, repository_status: Status::Unknown,
repository_health: None, disks: Vec::new(),
repository_disk: None,
last_backup_size_gb: None,
start_time_raw: None,
}, },
} }
} }