Improve host disconnection detection and fix notification exclusions
All checks were successful
Build and Release / build-and-release (push) Successful in 1m34s
All checks were successful
Build and Release / build-and-release (push) Successful in 1m34s
- Add dedicated heartbeat transmission every 5 seconds independent of metric collection - Fix host offline detection by clearing metrics for disconnected hosts - Move exclude_email_metrics to NotificationConfig for better organization - Add cleanup_offline_hosts method to remove stale metrics after heartbeat timeout - Ensure offline hosts show proper status icons and visual indicators Version 0.1.63
This commit is contained in:
@@ -1,6 +1,6 @@
|
||||
[package]
|
||||
name = "cm-dashboard-agent"
|
||||
version = "0.1.62"
|
||||
version = "0.1.63"
|
||||
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 {
|
||||
@@ -206,7 +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;
|
||||
}
|
||||
@@ -252,6 +259,19 @@ impl Agent {
|
||||
)
|
||||
}
|
||||
|
||||
/// 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)
|
||||
match self.zmq_handler.try_receive_command() {
|
||||
|
||||
@@ -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
|
||||
@@ -29,6 +26,9 @@ pub struct ZmqConfig {
|
||||
pub command_port: u16,
|
||||
pub bind_address: String,
|
||||
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
|
||||
@@ -147,9 +147,16 @@ 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>,
|
||||
}
|
||||
|
||||
|
||||
fn default_heartbeat_interval_seconds() -> u64 {
|
||||
5
|
||||
}
|
||||
|
||||
impl AgentConfig {
|
||||
pub fn from_file<P: AsRef<Path>>(path: P) -> Result<Self> {
|
||||
loader::load_config(path)
|
||||
|
||||
Reference in New Issue
Block a user