Compare commits
16 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| 33e700529e | |||
| d644b7d40a | |||
| f635ba9c75 | |||
| 76b6e3373e | |||
| 0a13cab897 | |||
| d33ec5d225 | |||
| d31c2384df | |||
| c8db463204 | |||
| e8e50ef9bb | |||
| 0faed9309e | |||
| c980346d05 | |||
| 3e3d3f0c2b | |||
| 9eb7444d56 | |||
| 278d1763aa | |||
| f874264e13 | |||
| 5f6e47ece5 |
@@ -113,13 +113,13 @@ jobs:
|
||||
NIX_HASH="sha256-$(python3 -c "import base64, binascii; print(base64.b64encode(binascii.unhexlify('$NEW_HASH')).decode())")"
|
||||
|
||||
# Update the NixOS configuration
|
||||
sed -i "s|version = \"v[^\"]*\"|version = \"$VERSION\"|" hosts/common/cm-dashboard.nix
|
||||
sed -i "s|sha256 = \"sha256-[^\"]*\"|sha256 = \"$NIX_HASH\"|" hosts/common/cm-dashboard.nix
|
||||
sed -i "s|version = \"v[^\"]*\"|version = \"$VERSION\"|" hosts/services/cm-dashboard.nix
|
||||
sed -i "s|sha256 = \"sha256-[^\"]*\"|sha256 = \"$NIX_HASH\"|" hosts/services/cm-dashboard.nix
|
||||
|
||||
# Commit and push changes
|
||||
git config user.name "Gitea Actions"
|
||||
git config user.email "actions@gitea.cmtec.se"
|
||||
git add hosts/common/cm-dashboard.nix
|
||||
git add hosts/services/cm-dashboard.nix
|
||||
git commit -m "Auto-update cm-dashboard to $VERSION
|
||||
|
||||
- Update version to $VERSION with automated release
|
||||
|
||||
@@ -115,7 +115,7 @@ This automatically:
|
||||
- Uploads binaries via Gitea API
|
||||
|
||||
### NixOS Configuration Updates
|
||||
Edit `~/projects/nixosbox/hosts/common/cm-dashboard.nix`:
|
||||
Edit `~/projects/nixosbox/hosts/services/cm-dashboard.nix`:
|
||||
|
||||
```nix
|
||||
version = "v0.1.X";
|
||||
|
||||
6
Cargo.lock
generated
6
Cargo.lock
generated
@@ -270,7 +270,7 @@ checksum = "a1d728cc89cf3aee9ff92b05e62b19ee65a02b5702cff7d5a377e32c6ae29d8d"
|
||||
|
||||
[[package]]
|
||||
name = "cm-dashboard"
|
||||
version = "0.1.55"
|
||||
version = "0.1.69"
|
||||
dependencies = [
|
||||
"anyhow",
|
||||
"chrono",
|
||||
@@ -292,7 +292,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "cm-dashboard-agent"
|
||||
version = "0.1.55"
|
||||
version = "0.1.69"
|
||||
dependencies = [
|
||||
"anyhow",
|
||||
"async-trait",
|
||||
@@ -315,7 +315,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "cm-dashboard-shared"
|
||||
version = "0.1.55"
|
||||
version = "0.1.69"
|
||||
dependencies = [
|
||||
"chrono",
|
||||
"serde",
|
||||
|
||||
@@ -329,7 +329,7 @@ This triggers automated:
|
||||
- Tarball upload to Gitea
|
||||
|
||||
### NixOS Integration
|
||||
Update `~/projects/nixosbox/hosts/common/cm-dashboard.nix`:
|
||||
Update `~/projects/nixosbox/hosts/services/cm-dashboard.nix`:
|
||||
|
||||
```nix
|
||||
version = "v0.1.43";
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
[package]
|
||||
name = "cm-dashboard-agent"
|
||||
version = "0.1.56"
|
||||
version = "0.1.71"
|
||||
edition = "2021"
|
||||
|
||||
[dependencies]
|
||||
|
||||
@@ -78,10 +78,11 @@ impl Agent {
|
||||
info!("Initial metric collection completed - all data cached and ready");
|
||||
}
|
||||
|
||||
// Separate intervals for collection, transmission, and email notifications
|
||||
// Separate intervals for collection, transmission, heartbeat, and email notifications
|
||||
let mut collection_interval =
|
||||
interval(Duration::from_secs(self.config.collection_interval_seconds));
|
||||
let mut transmission_interval = interval(Duration::from_secs(self.config.zmq.transmission_interval_seconds));
|
||||
let mut heartbeat_interval = interval(Duration::from_secs(self.config.zmq.heartbeat_interval_seconds));
|
||||
let mut notification_interval = interval(Duration::from_secs(self.config.notifications.aggregation_interval_seconds));
|
||||
|
||||
loop {
|
||||
@@ -98,6 +99,12 @@ impl Agent {
|
||||
error!("Failed to broadcast metrics: {}", e);
|
||||
}
|
||||
}
|
||||
_ = heartbeat_interval.tick() => {
|
||||
// Send standalone heartbeat for host connectivity detection
|
||||
if let Err(e) = self.send_heartbeat().await {
|
||||
error!("Failed to send heartbeat: {}", e);
|
||||
}
|
||||
}
|
||||
_ = notification_interval.tick() => {
|
||||
// Process batched email notifications (separate from dashboard updates)
|
||||
if let Err(e) = self.host_status_manager.process_pending_notifications(&mut self.notification_manager).await {
|
||||
@@ -180,6 +187,10 @@ impl Agent {
|
||||
let version_metric = self.get_agent_version_metric();
|
||||
metrics.push(version_metric);
|
||||
|
||||
// Add heartbeat metric for host connectivity detection
|
||||
let heartbeat_metric = self.get_heartbeat_metric();
|
||||
metrics.push(heartbeat_metric);
|
||||
|
||||
// Check for user-stopped services that are now active and clear their flags
|
||||
self.clear_user_stopped_flags_for_active_services(&metrics);
|
||||
|
||||
@@ -202,7 +213,7 @@ impl Agent {
|
||||
let mut status_changed = false;
|
||||
for metric in metrics {
|
||||
// Filter excluded metrics from email notification processing only
|
||||
if self.config.exclude_email_metrics.contains(&metric.name) {
|
||||
if self.config.notifications.exclude_email_metrics.contains(&metric.name) {
|
||||
debug!("Excluding metric '{}' from email notification processing", metric.name);
|
||||
continue;
|
||||
}
|
||||
@@ -232,6 +243,34 @@ impl Agent {
|
||||
format!("v{}", env!("CARGO_PKG_VERSION"))
|
||||
}
|
||||
|
||||
/// Create heartbeat metric for host connectivity detection
|
||||
fn get_heartbeat_metric(&self) -> Metric {
|
||||
use std::time::{SystemTime, UNIX_EPOCH};
|
||||
|
||||
let timestamp = SystemTime::now()
|
||||
.duration_since(UNIX_EPOCH)
|
||||
.unwrap()
|
||||
.as_secs();
|
||||
|
||||
Metric::new(
|
||||
"agent_heartbeat".to_string(),
|
||||
MetricValue::Integer(timestamp as i64),
|
||||
Status::Ok,
|
||||
)
|
||||
}
|
||||
|
||||
/// Send standalone heartbeat for connectivity detection
|
||||
async fn send_heartbeat(&mut self) -> Result<()> {
|
||||
let heartbeat_metric = self.get_heartbeat_metric();
|
||||
let message = MetricMessage::new(
|
||||
self.hostname.clone(),
|
||||
vec![heartbeat_metric],
|
||||
);
|
||||
|
||||
self.zmq_handler.publish_metrics(&message).await?;
|
||||
debug!("Sent standalone heartbeat for connectivity detection");
|
||||
Ok(())
|
||||
}
|
||||
|
||||
async fn handle_commands(&mut self) -> Result<()> {
|
||||
// Try to receive commands (non-blocking)
|
||||
@@ -312,36 +351,40 @@ impl Agent {
|
||||
_ => {}
|
||||
}
|
||||
|
||||
let output = tokio::process::Command::new("sudo")
|
||||
.arg("systemctl")
|
||||
.arg(action_str)
|
||||
.arg(format!("{}.service", service_name))
|
||||
.output()
|
||||
.await?;
|
||||
// Spawn the systemctl command asynchronously to avoid blocking the agent
|
||||
let service_name_clone = service_name.to_string();
|
||||
let action_str_clone = action_str.to_string();
|
||||
|
||||
tokio::spawn(async move {
|
||||
let result = tokio::process::Command::new("sudo")
|
||||
.arg("systemctl")
|
||||
.arg(&action_str_clone)
|
||||
.arg(format!("{}.service", service_name_clone))
|
||||
.output()
|
||||
.await;
|
||||
|
||||
if output.status.success() {
|
||||
info!("Service {} {} completed successfully", service_name, action_str);
|
||||
if !output.stdout.is_empty() {
|
||||
debug!("stdout: {}", String::from_utf8_lossy(&output.stdout));
|
||||
match result {
|
||||
Ok(output) => {
|
||||
if output.status.success() {
|
||||
info!("Service {} {} completed successfully", service_name_clone, action_str_clone);
|
||||
if !output.stdout.is_empty() {
|
||||
debug!("stdout: {}", String::from_utf8_lossy(&output.stdout));
|
||||
}
|
||||
} else {
|
||||
let stderr = String::from_utf8_lossy(&output.stderr);
|
||||
error!("Service {} {} failed: {}", service_name_clone, action_str_clone, stderr);
|
||||
}
|
||||
}
|
||||
Err(e) => {
|
||||
error!("Failed to execute systemctl {} {}: {}", action_str_clone, service_name_clone, e);
|
||||
}
|
||||
}
|
||||
|
||||
// Note: User-stopped flag will be cleared by systemd collector
|
||||
// when service actually reaches 'active' state, not here
|
||||
} else {
|
||||
let stderr = String::from_utf8_lossy(&output.stderr);
|
||||
error!("Service {} {} failed: {}", service_name, action_str, stderr);
|
||||
return Err(anyhow::anyhow!("systemctl {} {} failed: {}", action_str, service_name, stderr));
|
||||
}
|
||||
});
|
||||
|
||||
// Force refresh metrics after service control to update service status
|
||||
if matches!(action, ServiceAction::Start | ServiceAction::Stop | ServiceAction::UserStart | ServiceAction::UserStop) {
|
||||
info!("Triggering immediate metric refresh after service control");
|
||||
if let Err(e) = self.collect_metrics_only().await {
|
||||
error!("Failed to refresh metrics after service control: {}", e);
|
||||
} else {
|
||||
info!("Service status refreshed immediately after {} {}", action_str, service_name);
|
||||
}
|
||||
}
|
||||
info!("Service {} {} command initiated (non-blocking)", service_name, action_str);
|
||||
|
||||
// Note: Service status will be updated by the normal metric collection cycle
|
||||
// once the systemctl operation completes
|
||||
|
||||
Ok(())
|
||||
}
|
||||
|
||||
@@ -66,8 +66,6 @@ impl ZmqHandler {
|
||||
}
|
||||
|
||||
|
||||
/// Send heartbeat (placeholder for future use)
|
||||
|
||||
/// Try to receive a command (non-blocking)
|
||||
pub fn try_receive_command(&self) -> Result<Option<AgentCommand>> {
|
||||
match self.command_receiver.recv_bytes(zmq::DONTWAIT) {
|
||||
|
||||
@@ -17,9 +17,6 @@ pub struct AgentConfig {
|
||||
pub notifications: NotificationConfig,
|
||||
pub status_aggregation: HostStatusConfig,
|
||||
pub collection_interval_seconds: u64,
|
||||
/// List of metric names to exclude from email notifications
|
||||
#[serde(default)]
|
||||
pub exclude_email_metrics: Vec<String>,
|
||||
}
|
||||
|
||||
/// ZMQ communication configuration
|
||||
@@ -28,9 +25,10 @@ pub struct ZmqConfig {
|
||||
pub publisher_port: u16,
|
||||
pub command_port: u16,
|
||||
pub bind_address: String,
|
||||
pub timeout_ms: u64,
|
||||
pub heartbeat_interval_ms: u64,
|
||||
pub transmission_interval_seconds: u64,
|
||||
/// Heartbeat transmission interval in seconds for host connectivity detection
|
||||
#[serde(default = "default_heartbeat_interval_seconds")]
|
||||
pub heartbeat_interval_seconds: u64,
|
||||
}
|
||||
|
||||
/// Collector configuration
|
||||
@@ -149,9 +147,23 @@ pub struct NotificationConfig {
|
||||
pub rate_limit_minutes: u64,
|
||||
/// Email notification batching interval in seconds (default: 60)
|
||||
pub aggregation_interval_seconds: u64,
|
||||
/// List of metric names to exclude from email notifications
|
||||
#[serde(default)]
|
||||
pub exclude_email_metrics: Vec<String>,
|
||||
/// Path to maintenance mode file that suppresses email notifications when present
|
||||
#[serde(default = "default_maintenance_mode_file")]
|
||||
pub maintenance_mode_file: String,
|
||||
}
|
||||
|
||||
|
||||
fn default_heartbeat_interval_seconds() -> u64 {
|
||||
5
|
||||
}
|
||||
|
||||
fn default_maintenance_mode_file() -> String {
|
||||
"/tmp/cm-maintenance".to_string()
|
||||
}
|
||||
|
||||
impl AgentConfig {
|
||||
pub fn from_file<P: AsRef<Path>>(path: P) -> Result<Self> {
|
||||
loader::load_config(path)
|
||||
|
||||
@@ -19,10 +19,6 @@ pub fn validate_config(config: &AgentConfig) -> Result<()> {
|
||||
bail!("ZMQ bind address cannot be empty");
|
||||
}
|
||||
|
||||
if config.zmq.timeout_ms == 0 {
|
||||
bail!("ZMQ timeout cannot be 0");
|
||||
}
|
||||
|
||||
// Validate collection interval
|
||||
if config.collection_interval_seconds == 0 {
|
||||
bail!("Collection interval cannot be 0");
|
||||
|
||||
@@ -59,6 +59,6 @@ impl NotificationManager {
|
||||
}
|
||||
|
||||
fn is_maintenance_mode(&self) -> bool {
|
||||
std::fs::metadata("/tmp/cm-maintenance").is_ok()
|
||||
std::fs::metadata(&self.config.maintenance_mode_file).is_ok()
|
||||
}
|
||||
}
|
||||
@@ -1,6 +1,6 @@
|
||||
[package]
|
||||
name = "cm-dashboard"
|
||||
version = "0.1.56"
|
||||
version = "0.1.71"
|
||||
edition = "2021"
|
||||
|
||||
[dependencies]
|
||||
|
||||
@@ -22,7 +22,7 @@ pub struct Dashboard {
|
||||
terminal: Option<Terminal<CrosstermBackend<io::Stdout>>>,
|
||||
headless: bool,
|
||||
initial_commands_sent: std::collections::HashSet<String>,
|
||||
_config: DashboardConfig,
|
||||
config: DashboardConfig,
|
||||
}
|
||||
|
||||
impl Dashboard {
|
||||
@@ -67,11 +67,8 @@ impl Dashboard {
|
||||
}
|
||||
};
|
||||
|
||||
// Connect to configured hosts from configuration
|
||||
let hosts: Vec<String> = config.hosts.keys().cloned().collect();
|
||||
|
||||
// Try to connect to hosts but don't fail if none are available
|
||||
match zmq_consumer.connect_to_predefined_hosts(&hosts).await {
|
||||
match zmq_consumer.connect_to_predefined_hosts(&config.hosts).await {
|
||||
Ok(_) => info!("Successfully connected to ZMQ hosts"),
|
||||
Err(e) => {
|
||||
warn!(
|
||||
@@ -133,7 +130,7 @@ impl Dashboard {
|
||||
terminal,
|
||||
headless,
|
||||
initial_commands_sent: std::collections::HashSet::new(),
|
||||
_config: config,
|
||||
config,
|
||||
})
|
||||
}
|
||||
|
||||
@@ -149,6 +146,8 @@ impl Dashboard {
|
||||
|
||||
let mut last_metrics_check = Instant::now();
|
||||
let metrics_check_interval = Duration::from_millis(100); // Check for metrics every 100ms
|
||||
let mut last_heartbeat_check = Instant::now();
|
||||
let heartbeat_check_interval = Duration::from_secs(1); // Check for host connectivity every 1 second
|
||||
|
||||
loop {
|
||||
// Handle terminal events (keyboard input) only if not headless
|
||||
@@ -191,6 +190,17 @@ impl Dashboard {
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
// Render UI immediately after handling input for responsive feedback
|
||||
if let Some(ref mut terminal) = self.terminal {
|
||||
if let Some(ref mut tui_app) = self.tui_app {
|
||||
if let Err(e) = terminal.draw(|frame| {
|
||||
tui_app.render(frame, &self.metric_store);
|
||||
}) {
|
||||
error!("Error rendering TUI after input: {}", e);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Check for new metrics
|
||||
@@ -243,14 +253,8 @@ impl Dashboard {
|
||||
}
|
||||
}
|
||||
|
||||
// Update TUI with new hosts and metrics (only if not headless)
|
||||
// Update TUI with new metrics (only if not headless)
|
||||
if let Some(ref mut tui_app) = self.tui_app {
|
||||
let connected_hosts = self
|
||||
.metric_store
|
||||
.get_connected_hosts(Duration::from_secs(30));
|
||||
|
||||
|
||||
tui_app.update_hosts(connected_hosts);
|
||||
tui_app.update_metrics(&self.metric_store);
|
||||
}
|
||||
}
|
||||
@@ -269,6 +273,20 @@ impl Dashboard {
|
||||
last_metrics_check = Instant::now();
|
||||
}
|
||||
|
||||
// Check for host connectivity changes (heartbeat timeouts) periodically
|
||||
if last_heartbeat_check.elapsed() >= heartbeat_check_interval {
|
||||
let timeout = Duration::from_secs(self.config.zmq.heartbeat_timeout_seconds);
|
||||
|
||||
// Clean up metrics for offline hosts
|
||||
self.metric_store.cleanup_offline_hosts(timeout);
|
||||
|
||||
if let Some(ref mut tui_app) = self.tui_app {
|
||||
let connected_hosts = self.metric_store.get_connected_hosts(timeout);
|
||||
tui_app.update_hosts(connected_hosts);
|
||||
}
|
||||
last_heartbeat_check = Instant::now();
|
||||
}
|
||||
|
||||
// Render TUI (only if not headless)
|
||||
if !self.headless {
|
||||
if let Some(ref mut terminal) = self.terminal {
|
||||
|
||||
@@ -71,6 +71,12 @@ impl ZmqConsumer {
|
||||
pub async fn connect_to_host(&mut self, hostname: &str, port: u16) -> Result<()> {
|
||||
let address = format!("tcp://{}:{}", hostname, port);
|
||||
|
||||
// First test basic TCP connectivity to the port
|
||||
if let Err(e) = self.test_tcp_connectivity(hostname, port).await {
|
||||
error!("TCP connectivity test failed for {}: {}", address, e);
|
||||
return Err(e);
|
||||
}
|
||||
|
||||
match self.subscriber.connect(&address) {
|
||||
Ok(()) => {
|
||||
info!("Connected to agent at {}", address);
|
||||
@@ -84,13 +90,33 @@ impl ZmqConsumer {
|
||||
}
|
||||
}
|
||||
|
||||
/// Connect to predefined hosts
|
||||
pub async fn connect_to_predefined_hosts(&mut self, hosts: &[String]) -> Result<()> {
|
||||
/// Test TCP connectivity to a host and port with timeout
|
||||
async fn test_tcp_connectivity(&self, hostname: &str, port: u16) -> Result<()> {
|
||||
let timeout = std::time::Duration::from_secs(3);
|
||||
|
||||
match tokio::time::timeout(timeout, tokio::net::TcpStream::connect((hostname, port))).await {
|
||||
Ok(Ok(_stream)) => {
|
||||
debug!("TCP connectivity test passed for {}:{}", hostname, port);
|
||||
Ok(())
|
||||
}
|
||||
Ok(Err(e)) => {
|
||||
debug!("TCP connectivity test failed for {}:{}: {}", hostname, port, e);
|
||||
Err(anyhow::anyhow!("TCP connection failed: {}", e))
|
||||
}
|
||||
Err(_) => {
|
||||
debug!("TCP connectivity test timed out for {}:{}", hostname, port);
|
||||
Err(anyhow::anyhow!("TCP connection timed out"))
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// Connect to predefined hosts using their configuration
|
||||
pub async fn connect_to_predefined_hosts(&mut self, hosts: &std::collections::HashMap<String, crate::config::HostDetails>) -> Result<()> {
|
||||
let default_port = self.config.subscriber_ports[0];
|
||||
|
||||
for hostname in hosts {
|
||||
// Try to connect, but don't fail if some hosts are unreachable
|
||||
if let Err(e) = self.connect_to_host(hostname, default_port).await {
|
||||
for (hostname, host_details) in hosts {
|
||||
// Try to connect using configured IP, but don't fail if some hosts are unreachable
|
||||
if let Err(e) = self.connect_to_host_with_details(hostname, host_details, default_port).await {
|
||||
warn!("Could not connect to {}: {}", hostname, e);
|
||||
}
|
||||
}
|
||||
@@ -104,6 +130,15 @@ impl ZmqConsumer {
|
||||
Ok(())
|
||||
}
|
||||
|
||||
/// Connect to a host using its configuration details
|
||||
pub async fn connect_to_host_with_details(&mut self, hostname: &str, host_details: &crate::config::HostDetails, port: u16) -> Result<()> {
|
||||
// Get primary connection IP only - no fallbacks
|
||||
let primary_ip = host_details.get_connection_ip(hostname);
|
||||
|
||||
// Connect directly without fallback attempts
|
||||
self.connect_to_host(&primary_ip, port).await
|
||||
}
|
||||
|
||||
/// Receive command output from any connected agent (non-blocking)
|
||||
pub async fn receive_command_output(&mut self) -> Result<Option<CommandOutputMessage>> {
|
||||
match self.subscriber.recv_bytes(zmq::DONTWAIT) {
|
||||
|
||||
@@ -16,12 +16,30 @@ pub struct DashboardConfig {
|
||||
#[derive(Debug, Clone, Serialize, Deserialize)]
|
||||
pub struct ZmqConfig {
|
||||
pub subscriber_ports: Vec<u16>,
|
||||
/// Heartbeat timeout in seconds - hosts considered offline if no heartbeat received within this time
|
||||
#[serde(default = "default_heartbeat_timeout_seconds")]
|
||||
pub heartbeat_timeout_seconds: u64,
|
||||
}
|
||||
|
||||
fn default_heartbeat_timeout_seconds() -> u64 {
|
||||
10 // Default to 10 seconds - allows for multiple missed heartbeats
|
||||
}
|
||||
|
||||
/// Individual host configuration details
|
||||
#[derive(Debug, Clone, Serialize, Deserialize)]
|
||||
pub struct HostDetails {
|
||||
pub mac_address: Option<String>,
|
||||
/// Primary IP address (local network)
|
||||
pub ip: Option<String>,
|
||||
}
|
||||
|
||||
|
||||
impl HostDetails {
|
||||
/// Get the IP address for connection (uses ip field or hostname as fallback)
|
||||
pub fn get_connection_ip(&self, hostname: &str) -> String {
|
||||
self.ip.as_ref().unwrap_or(&hostname.to_string()).clone()
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
/// System configuration
|
||||
|
||||
@@ -11,8 +11,8 @@ pub struct MetricStore {
|
||||
current_metrics: HashMap<String, HashMap<String, Metric>>,
|
||||
/// Historical metrics for trending
|
||||
historical_metrics: HashMap<String, Vec<MetricDataPoint>>,
|
||||
/// Last update timestamp per host
|
||||
last_update: HashMap<String, Instant>,
|
||||
/// Last heartbeat timestamp per host
|
||||
last_heartbeat: HashMap<String, Instant>,
|
||||
/// Configuration
|
||||
max_metrics_per_host: usize,
|
||||
history_retention: Duration,
|
||||
@@ -23,7 +23,7 @@ impl MetricStore {
|
||||
Self {
|
||||
current_metrics: HashMap::new(),
|
||||
historical_metrics: HashMap::new(),
|
||||
last_update: HashMap::new(),
|
||||
last_heartbeat: HashMap::new(),
|
||||
max_metrics_per_host,
|
||||
history_retention: Duration::from_secs(history_retention_hours * 3600),
|
||||
}
|
||||
@@ -56,10 +56,13 @@ impl MetricStore {
|
||||
|
||||
// Add to history
|
||||
host_history.push(MetricDataPoint { received_at: now });
|
||||
}
|
||||
|
||||
// Update last update timestamp
|
||||
self.last_update.insert(hostname.to_string(), now);
|
||||
// Track heartbeat metrics for connectivity detection
|
||||
if metric_name == "agent_heartbeat" {
|
||||
self.last_heartbeat.insert(hostname.to_string(), now);
|
||||
debug!("Updated heartbeat for host {}", hostname);
|
||||
}
|
||||
}
|
||||
|
||||
// Get metrics count before cleanup
|
||||
let metrics_count = host_metrics.len();
|
||||
@@ -88,22 +91,46 @@ impl MetricStore {
|
||||
}
|
||||
}
|
||||
|
||||
/// Get connected hosts (hosts with recent updates)
|
||||
/// Get connected hosts (hosts with recent heartbeats)
|
||||
pub fn get_connected_hosts(&self, timeout: Duration) -> Vec<String> {
|
||||
let now = Instant::now();
|
||||
|
||||
self.last_update
|
||||
self.last_heartbeat
|
||||
.iter()
|
||||
.filter_map(|(hostname, &last_update)| {
|
||||
if now.duration_since(last_update) <= timeout {
|
||||
.filter_map(|(hostname, &last_heartbeat)| {
|
||||
if now.duration_since(last_heartbeat) <= timeout {
|
||||
Some(hostname.clone())
|
||||
} else {
|
||||
debug!("Host {} considered offline - last heartbeat was {:?} ago",
|
||||
hostname, now.duration_since(last_heartbeat));
|
||||
None
|
||||
}
|
||||
})
|
||||
.collect()
|
||||
}
|
||||
|
||||
/// Clean up data for offline hosts
|
||||
pub fn cleanup_offline_hosts(&mut self, timeout: Duration) {
|
||||
let now = Instant::now();
|
||||
let mut hosts_to_cleanup = Vec::new();
|
||||
|
||||
// Find hosts that are offline (no recent heartbeat)
|
||||
for (hostname, &last_heartbeat) in &self.last_heartbeat {
|
||||
if now.duration_since(last_heartbeat) > timeout {
|
||||
hosts_to_cleanup.push(hostname.clone());
|
||||
}
|
||||
}
|
||||
|
||||
// Clear metrics for offline hosts
|
||||
for hostname in hosts_to_cleanup {
|
||||
if let Some(metrics) = self.current_metrics.remove(&hostname) {
|
||||
info!("Cleared {} metrics for offline host: {}", metrics.len(), hostname);
|
||||
}
|
||||
// Keep heartbeat timestamp for reconnection detection
|
||||
// Don't remove from last_heartbeat to track when host was last seen
|
||||
}
|
||||
}
|
||||
|
||||
/// Cleanup old data and enforce limits
|
||||
fn cleanup_host_data(&mut self, hostname: &str) {
|
||||
let now = Instant::now();
|
||||
|
||||
@@ -90,10 +90,13 @@ pub struct TuiApp {
|
||||
user_navigated_away: bool,
|
||||
/// Dashboard configuration
|
||||
config: DashboardConfig,
|
||||
/// Cached localhost hostname to avoid repeated system calls
|
||||
localhost: String,
|
||||
}
|
||||
|
||||
impl TuiApp {
|
||||
pub fn new(config: DashboardConfig) -> Self {
|
||||
let localhost = gethostname::gethostname().to_string_lossy().to_string();
|
||||
let mut app = Self {
|
||||
host_widgets: HashMap::new(),
|
||||
current_host: None,
|
||||
@@ -102,6 +105,7 @@ impl TuiApp {
|
||||
should_quit: false,
|
||||
user_navigated_away: false,
|
||||
config,
|
||||
localhost,
|
||||
};
|
||||
|
||||
// Sort predefined hosts
|
||||
@@ -131,31 +135,31 @@ impl TuiApp {
|
||||
// Only update widgets if we have metrics for this host
|
||||
let all_metrics = metric_store.get_metrics_for_host(&hostname);
|
||||
if !all_metrics.is_empty() {
|
||||
// Get metrics first while hostname is borrowed
|
||||
let cpu_metrics: Vec<&Metric> = all_metrics
|
||||
.iter()
|
||||
.filter(|m| {
|
||||
m.name.starts_with("cpu_")
|
||||
|| m.name.contains("c_state_")
|
||||
|| m.name.starts_with("process_top_")
|
||||
})
|
||||
.copied()
|
||||
.collect();
|
||||
let memory_metrics: Vec<&Metric> = all_metrics
|
||||
.iter()
|
||||
.filter(|m| m.name.starts_with("memory_") || m.name.starts_with("disk_tmp_"))
|
||||
.copied()
|
||||
.collect();
|
||||
let service_metrics: Vec<&Metric> = all_metrics
|
||||
.iter()
|
||||
.filter(|m| m.name.starts_with("service_"))
|
||||
.copied()
|
||||
.collect();
|
||||
let all_backup_metrics: Vec<&Metric> = all_metrics
|
||||
.iter()
|
||||
.filter(|m| m.name.starts_with("backup_"))
|
||||
.copied()
|
||||
.collect();
|
||||
// Single pass metric categorization for better performance
|
||||
let mut cpu_metrics = Vec::new();
|
||||
let mut memory_metrics = Vec::new();
|
||||
let mut service_metrics = Vec::new();
|
||||
let mut backup_metrics = Vec::new();
|
||||
let mut nixos_metrics = Vec::new();
|
||||
let mut disk_metrics = Vec::new();
|
||||
|
||||
for metric in all_metrics {
|
||||
if metric.name.starts_with("cpu_")
|
||||
|| metric.name.contains("c_state_")
|
||||
|| metric.name.starts_with("process_top_") {
|
||||
cpu_metrics.push(metric);
|
||||
} else if metric.name.starts_with("memory_") || metric.name.starts_with("disk_tmp_") {
|
||||
memory_metrics.push(metric);
|
||||
} else if metric.name.starts_with("service_") {
|
||||
service_metrics.push(metric);
|
||||
} else if metric.name.starts_with("backup_") {
|
||||
backup_metrics.push(metric);
|
||||
} else if metric.name == "system_nixos_build" || metric.name == "system_active_users" || metric.name == "agent_version" {
|
||||
nixos_metrics.push(metric);
|
||||
} else if metric.name.starts_with("disk_") {
|
||||
disk_metrics.push(metric);
|
||||
}
|
||||
}
|
||||
|
||||
// Clear completed transitions first
|
||||
self.clear_completed_transitions(&hostname, &service_metrics);
|
||||
@@ -166,21 +170,7 @@ impl TuiApp {
|
||||
// Collect all system metrics (CPU, memory, NixOS, disk/storage)
|
||||
let mut system_metrics = cpu_metrics;
|
||||
system_metrics.extend(memory_metrics);
|
||||
|
||||
// Add NixOS metrics - using exact matching for build display fix
|
||||
let nixos_metrics: Vec<&Metric> = all_metrics
|
||||
.iter()
|
||||
.filter(|m| m.name == "system_nixos_build" || m.name == "system_active_users" || m.name == "agent_version")
|
||||
.copied()
|
||||
.collect();
|
||||
system_metrics.extend(nixos_metrics);
|
||||
|
||||
// Add disk/storage metrics
|
||||
let disk_metrics: Vec<&Metric> = all_metrics
|
||||
.iter()
|
||||
.filter(|m| m.name.starts_with("disk_"))
|
||||
.copied()
|
||||
.collect();
|
||||
system_metrics.extend(disk_metrics);
|
||||
|
||||
host_widgets.system_widget.update_from_metrics(&system_metrics);
|
||||
@@ -189,7 +179,7 @@ impl TuiApp {
|
||||
.update_from_metrics(&service_metrics);
|
||||
host_widgets
|
||||
.backup_widget
|
||||
.update_from_metrics(&all_backup_metrics);
|
||||
.update_from_metrics(&backup_metrics);
|
||||
|
||||
host_widgets.last_update = Some(Instant::now());
|
||||
}
|
||||
@@ -221,13 +211,12 @@ impl TuiApp {
|
||||
self.available_hosts = all_hosts;
|
||||
|
||||
// Get the current hostname (localhost) for auto-selection
|
||||
let localhost = gethostname::gethostname().to_string_lossy().to_string();
|
||||
if !self.available_hosts.is_empty() {
|
||||
if self.available_hosts.contains(&localhost) && !self.user_navigated_away {
|
||||
if self.available_hosts.contains(&self.localhost) && !self.user_navigated_away {
|
||||
// Localhost is available and user hasn't navigated away - switch to it
|
||||
self.current_host = Some(localhost.clone());
|
||||
self.current_host = Some(self.localhost.clone());
|
||||
// Find the actual index of localhost in the sorted list
|
||||
self.host_index = self.available_hosts.iter().position(|h| h == &localhost).unwrap_or(0);
|
||||
self.host_index = self.available_hosts.iter().position(|h| h == &self.localhost).unwrap_or(0);
|
||||
} else if self.current_host.is_none() {
|
||||
// No current host - select first available (which is localhost if available)
|
||||
self.current_host = Some(self.available_hosts[0].clone());
|
||||
@@ -262,12 +251,14 @@ impl TuiApp {
|
||||
KeyCode::Char('r') => {
|
||||
// System rebuild command - works on any panel for current host
|
||||
if let Some(hostname) = self.current_host.clone() {
|
||||
let connection_ip = self.get_connection_ip(&hostname);
|
||||
// Create command that shows logo, rebuilds, and waits for user input
|
||||
let logo_and_rebuild = format!(
|
||||
"bash -c 'cat << \"EOF\"\nNixOS System Rebuild\nTarget: {}\n\nEOF\nssh -tt {}@{} \"bash -ic {}\"\necho\necho \"========================================\"\necho \"Rebuild completed. Press any key to close...\"\necho \"========================================\"\nread -n 1 -s\nexit'",
|
||||
"bash -c 'cat << \"EOF\"\nNixOS System Rebuild\nTarget: {} ({})\n\nEOF\nssh -tt {}@{} \"bash -ic {}\"\necho\necho \"========================================\"\necho \"Rebuild completed. Press any key to close...\"\necho \"========================================\"\nread -n 1 -s\nexit'",
|
||||
hostname,
|
||||
connection_ip,
|
||||
self.config.ssh.rebuild_user,
|
||||
hostname,
|
||||
connection_ip,
|
||||
self.config.ssh.rebuild_alias
|
||||
);
|
||||
|
||||
@@ -300,10 +291,11 @@ impl TuiApp {
|
||||
KeyCode::Char('J') => {
|
||||
// Show service logs via journalctl in tmux split window
|
||||
if let (Some(service_name), Some(hostname)) = (self.get_selected_service(), self.current_host.clone()) {
|
||||
let connection_ip = self.get_connection_ip(&hostname);
|
||||
let journalctl_command = format!(
|
||||
"bash -c \"ssh -tt {}@{} 'sudo journalctl -u {}.service -f --no-pager -n 50'; exit\"",
|
||||
self.config.ssh.rebuild_user,
|
||||
hostname,
|
||||
connection_ip,
|
||||
service_name
|
||||
);
|
||||
|
||||
@@ -323,10 +315,11 @@ impl TuiApp {
|
||||
// Check if this service has a custom log file configured
|
||||
if let Some(host_logs) = self.config.service_logs.get(&hostname) {
|
||||
if let Some(log_config) = host_logs.iter().find(|config| config.service_name == service_name) {
|
||||
let connection_ip = self.get_connection_ip(&hostname);
|
||||
let tail_command = format!(
|
||||
"bash -c \"ssh -tt {}@{} 'sudo tail -n 50 -f {}'; exit\"",
|
||||
self.config.ssh.rebuild_user,
|
||||
hostname,
|
||||
connection_ip,
|
||||
log_config.log_file_path
|
||||
);
|
||||
|
||||
@@ -376,6 +369,26 @@ impl TuiApp {
|
||||
}
|
||||
}
|
||||
}
|
||||
KeyCode::Char('t') => {
|
||||
// Open SSH terminal session in tmux window
|
||||
if let Some(hostname) = self.current_host.clone() {
|
||||
let connection_ip = self.get_connection_ip(&hostname);
|
||||
let ssh_command = format!(
|
||||
"ssh -tt {}@{}",
|
||||
self.config.ssh.rebuild_user,
|
||||
connection_ip
|
||||
);
|
||||
|
||||
std::process::Command::new("tmux")
|
||||
.arg("split-window")
|
||||
.arg("-v")
|
||||
.arg("-p")
|
||||
.arg("30") // Use 30% like other commands
|
||||
.arg(&ssh_command)
|
||||
.spawn()
|
||||
.ok(); // Ignore errors, tmux will handle them
|
||||
}
|
||||
}
|
||||
KeyCode::Tab => {
|
||||
// Tab cycles to next host
|
||||
self.navigate_host(1);
|
||||
@@ -424,9 +437,8 @@ impl TuiApp {
|
||||
self.current_host = Some(self.available_hosts[self.host_index].clone());
|
||||
|
||||
// Check if user navigated away from localhost
|
||||
let localhost = gethostname::gethostname().to_string_lossy().to_string();
|
||||
if let Some(ref current) = self.current_host {
|
||||
if current != &localhost {
|
||||
if current != &self.localhost {
|
||||
self.user_navigated_away = true;
|
||||
} else {
|
||||
self.user_navigated_away = false; // User navigated back to localhost
|
||||
@@ -570,6 +582,21 @@ impl TuiApp {
|
||||
])
|
||||
.split(main_chunks[1]); // main_chunks[1] is now the content area (between title and statusbar)
|
||||
|
||||
// Check if current host is offline
|
||||
let current_host_offline = if let Some(hostname) = self.current_host.clone() {
|
||||
self.calculate_host_status(&hostname, metric_store) == Status::Offline
|
||||
} else {
|
||||
true // No host selected is considered offline
|
||||
};
|
||||
|
||||
// If host is offline, render wake-up message instead of panels
|
||||
if current_host_offline {
|
||||
self.render_offline_host_message(frame, main_chunks[1]);
|
||||
self.render_btop_title(frame, main_chunks[0], metric_store);
|
||||
self.render_statusbar(frame, main_chunks[2]);
|
||||
return;
|
||||
}
|
||||
|
||||
// Check if backup panel should be shown
|
||||
let show_backup = if let Some(hostname) = self.current_host.clone() {
|
||||
let host_widgets = self.get_or_create_host_widgets(&hostname);
|
||||
@@ -802,8 +829,10 @@ impl TuiApp {
|
||||
let host_widgets = self.get_or_create_host_widgets(&hostname);
|
||||
host_widgets.system_scroll_offset
|
||||
};
|
||||
// Clone the config to avoid borrowing issues
|
||||
let config = self.config.clone();
|
||||
let host_widgets = self.get_or_create_host_widgets(&hostname);
|
||||
host_widgets.system_widget.render_with_scroll(frame, inner_area, scroll_offset, &hostname);
|
||||
host_widgets.system_widget.render_with_scroll(frame, inner_area, scroll_offset, &hostname, Some(&config));
|
||||
}
|
||||
}
|
||||
|
||||
@@ -823,7 +852,87 @@ impl TuiApp {
|
||||
}
|
||||
}
|
||||
|
||||
/// Render offline host message with wake-up option
|
||||
fn render_offline_host_message(&self, frame: &mut Frame, area: Rect) {
|
||||
use ratatui::layout::Alignment;
|
||||
use ratatui::style::Modifier;
|
||||
use ratatui::text::{Line, Span};
|
||||
use ratatui::widgets::{Block, Borders, Paragraph};
|
||||
|
||||
// Get hostname for message
|
||||
let hostname = self.current_host.as_ref()
|
||||
.map(|h| h.as_str())
|
||||
.unwrap_or("Unknown");
|
||||
|
||||
// Check if host has MAC address for wake-on-LAN
|
||||
let has_mac = self.current_host.as_ref()
|
||||
.and_then(|hostname| self.config.hosts.get(hostname))
|
||||
.and_then(|details| details.mac_address.as_ref())
|
||||
.is_some();
|
||||
|
||||
// Create message content
|
||||
let mut lines = vec![
|
||||
Line::from(Span::styled(
|
||||
format!("Host '{}' is offline", hostname),
|
||||
Style::default().fg(Theme::muted_text()).add_modifier(Modifier::BOLD),
|
||||
)),
|
||||
Line::from(""),
|
||||
];
|
||||
|
||||
if has_mac {
|
||||
lines.push(Line::from(Span::styled(
|
||||
"Press 'w' to wake up host",
|
||||
Style::default().fg(Theme::primary_text()).add_modifier(Modifier::BOLD),
|
||||
)));
|
||||
} else {
|
||||
lines.push(Line::from(Span::styled(
|
||||
"No MAC address configured - cannot wake up",
|
||||
Style::default().fg(Theme::muted_text()),
|
||||
)));
|
||||
}
|
||||
|
||||
// Create centered message
|
||||
let message = Paragraph::new(lines)
|
||||
.block(Block::default()
|
||||
.borders(Borders::ALL)
|
||||
.border_style(Style::default().fg(Theme::muted_text()))
|
||||
.title(" Offline Host ")
|
||||
.title_style(Style::default().fg(Theme::muted_text()).add_modifier(Modifier::BOLD)))
|
||||
.style(Style::default().bg(Theme::background()).fg(Theme::primary_text()))
|
||||
.alignment(Alignment::Center);
|
||||
|
||||
// Center the message in the available area
|
||||
let popup_area = ratatui::layout::Layout::default()
|
||||
.direction(Direction::Vertical)
|
||||
.constraints([
|
||||
Constraint::Percentage(40),
|
||||
Constraint::Length(6),
|
||||
Constraint::Percentage(40),
|
||||
])
|
||||
.split(area)[1];
|
||||
|
||||
let popup_area = ratatui::layout::Layout::default()
|
||||
.direction(Direction::Horizontal)
|
||||
.constraints([
|
||||
Constraint::Percentage(25),
|
||||
Constraint::Percentage(50),
|
||||
Constraint::Percentage(25),
|
||||
])
|
||||
.split(popup_area)[1];
|
||||
|
||||
frame.render_widget(message, popup_area);
|
||||
}
|
||||
|
||||
/// Parse MAC address string (e.g., "AA:BB:CC:DD:EE:FF") to [u8; 6]
|
||||
/// Get the connection IP for a hostname based on host configuration
|
||||
fn get_connection_ip(&self, hostname: &str) -> String {
|
||||
if let Some(host_details) = self.config.hosts.get(hostname) {
|
||||
host_details.get_connection_ip(hostname)
|
||||
} else {
|
||||
hostname.to_string()
|
||||
}
|
||||
}
|
||||
|
||||
fn parse_mac_address(mac_str: &str) -> Result<[u8; 6], &'static str> {
|
||||
let parts: Vec<&str> = mac_str.split(':').collect();
|
||||
if parts.len() != 6 {
|
||||
|
||||
@@ -439,7 +439,7 @@ impl Widget for SystemWidget {
|
||||
|
||||
impl SystemWidget {
|
||||
/// Render with scroll offset support
|
||||
pub fn render_with_scroll(&mut self, frame: &mut Frame, area: Rect, scroll_offset: usize, hostname: &str) {
|
||||
pub fn render_with_scroll(&mut self, frame: &mut Frame, area: Rect, scroll_offset: usize, hostname: &str, config: Option<&crate::config::DashboardConfig>) {
|
||||
let mut lines = Vec::new();
|
||||
|
||||
// NixOS section
|
||||
@@ -457,6 +457,16 @@ impl SystemWidget {
|
||||
Span::styled(format!("Agent: {}", agent_version_text), Typography::secondary())
|
||||
]));
|
||||
|
||||
// Display detected connection IP
|
||||
if let Some(config) = config {
|
||||
if let Some(host_details) = config.hosts.get(hostname) {
|
||||
let detected_ip = host_details.get_connection_ip(hostname);
|
||||
lines.push(Line::from(vec![
|
||||
Span::styled(format!("IP: {}", detected_ip), Typography::secondary())
|
||||
]));
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
// CPU section
|
||||
lines.push(Line::from(vec![
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
[package]
|
||||
name = "cm-dashboard-shared"
|
||||
version = "0.1.56"
|
||||
version = "0.1.71"
|
||||
edition = "2021"
|
||||
|
||||
[dependencies]
|
||||
|
||||
Reference in New Issue
Block a user