Compare commits

...

3 Commits

Author SHA1 Message Date
5394164123 Remove agent heartbeat causing dashboard zero dropouts
All checks were successful
Build and Release / build-and-release (push) Successful in 1m9s
Agent heartbeat was sending empty AgentData every few seconds, causing
dashboard to display zero values for all metrics intermittently. Since
agent already transmits complete data every 1 second, heartbeat is
redundant. Dashboard will detect offline hosts via data timestamps.
2025-11-24 15:03:20 +01:00
4329cd26e0 Make disk collector filesystems field optional for auto-discovery
All checks were successful
Build and Release / build-and-release (push) Successful in 1m32s
Allow agent configuration without explicit filesystems list by making
the field optional with serde default, enabling pure auto-discovery mode.

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-11-24 13:47:53 +01:00
b85bd6b153 Fix agent collector timing to prevent intermittent data gaps
All checks were successful
Build and Release / build-and-release (push) Successful in 1m42s
Update last_collection timestamp even when collectors fail to prevent
immediate retry loops that cause data transmission gaps every 5 seconds.

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-11-24 13:42:29 +01:00
7 changed files with 12 additions and 18 deletions

6
Cargo.lock generated
View File

@@ -279,7 +279,7 @@ checksum = "a1d728cc89cf3aee9ff92b05e62b19ee65a02b5702cff7d5a377e32c6ae29d8d"
[[package]]
name = "cm-dashboard"
version = "0.1.132"
version = "0.1.135"
dependencies = [
"anyhow",
"chrono",
@@ -301,7 +301,7 @@ dependencies = [
[[package]]
name = "cm-dashboard-agent"
version = "0.1.132"
version = "0.1.135"
dependencies = [
"anyhow",
"async-trait",
@@ -324,7 +324,7 @@ dependencies = [
[[package]]
name = "cm-dashboard-shared"
version = "0.1.132"
version = "0.1.135"
dependencies = [
"chrono",
"serde",

View File

@@ -1,6 +1,6 @@
[package]
name = "cm-dashboard-agent"
version = "0.1.133"
version = "0.1.136"
edition = "2021"
[dependencies]

View File

@@ -78,11 +78,10 @@ impl Agent {
info!("Initial metric collection completed - all data cached and ready");
}
// Separate intervals for collection, transmission, heartbeat, and email notifications
// Separate intervals for collection, transmission, 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 {
@@ -99,12 +98,6 @@ 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 {
@@ -187,9 +180,7 @@ 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);
// Heartbeat removed - dashboard detects connectivity via regular transmission timestamps
// Check for user-stopped services that are now active and clear their flags
self.clear_user_stopped_flags_for_active_services(&metrics);

View File

@@ -74,7 +74,8 @@ pub struct DiskConfig {
pub usage_warning_percent: f32,
/// Disk usage critical threshold (percentage)
pub usage_critical_percent: f32,
/// Filesystem configurations
/// Filesystem configurations (optional - auto-discovery used if empty)
#[serde(default)]
pub filesystems: Vec<FilesystemConfig>,
/// SMART monitoring thresholds
pub temperature_warning_celsius: f32,

View File

@@ -232,6 +232,8 @@ impl MetricCollectionManager {
}
Err(e) => {
error!("Collector {} failed: {}", timed_collector.name, e);
// Update last_collection time even on failure to prevent immediate retries
timed_collector.last_collection = Some(now);
}
}
}

View File

@@ -1,6 +1,6 @@
[package]
name = "cm-dashboard"
version = "0.1.133"
version = "0.1.136"
edition = "2021"
[dependencies]

View File

@@ -1,6 +1,6 @@
[package]
name = "cm-dashboard-shared"
version = "0.1.133"
version = "0.1.136"
edition = "2021"
[dependencies]