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"
|
||||
version = "0.1.62"
|
||||
version = "0.1.63"
|
||||
edition = "2021"
|
||||
|
||||
[dependencies]
|
||||
|
||||
@@ -278,11 +278,13 @@ impl Dashboard {
|
||||
|
||||
// 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(Duration::from_secs(self.config.zmq.heartbeat_timeout_seconds));
|
||||
|
||||
let connected_hosts = self.metric_store.get_connected_hosts(timeout);
|
||||
tui_app.update_hosts(connected_hosts);
|
||||
}
|
||||
last_heartbeat_check = Instant::now();
|
||||
|
||||
@@ -109,6 +109,28 @@ impl MetricStore {
|
||||
.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();
|
||||
|
||||
Reference in New Issue
Block a user