From d89b3ac881f6104bc8c112ccba28a2f1b18e2e8e Mon Sep 17 00:00:00 2001 From: Christoffer Martinsson Date: Mon, 24 Nov 2025 23:24:00 +0100 Subject: [PATCH] Fix nginx sub-services persistent caching with complete service data storage Resolves nginx sites appearing only briefly during collection cycles by implementing proper caching of complete service data including sub-services. Changes: - Add cached_service_data field to store complete ServiceData with sub-services - Modify collection logic to cache full service objects instead of basic ServiceInfo - Update cache retrieval to use complete cached data preserving nginx site metrics - Eliminate flickering of nginx sites between collection cycles Version bump to v0.1.148 --- Cargo.lock | 6 ++--- agent/Cargo.toml | 2 +- agent/src/collectors/systemd.rs | 48 +++++++++++++++++++-------------- dashboard/Cargo.toml | 2 +- shared/Cargo.toml | 2 +- 5 files changed, 34 insertions(+), 26 deletions(-) diff --git a/Cargo.lock b/Cargo.lock index 0544753..c38efdc 100644 --- a/Cargo.lock +++ b/Cargo.lock @@ -279,7 +279,7 @@ checksum = "a1d728cc89cf3aee9ff92b05e62b19ee65a02b5702cff7d5a377e32c6ae29d8d" [[package]] name = "cm-dashboard" -version = "0.1.146" +version = "0.1.147" dependencies = [ "anyhow", "chrono", @@ -301,7 +301,7 @@ dependencies = [ [[package]] name = "cm-dashboard-agent" -version = "0.1.146" +version = "0.1.147" dependencies = [ "anyhow", "async-trait", @@ -324,7 +324,7 @@ dependencies = [ [[package]] name = "cm-dashboard-shared" -version = "0.1.146" +version = "0.1.147" dependencies = [ "chrono", "serde", diff --git a/agent/Cargo.toml b/agent/Cargo.toml index e708893..fae63e5 100644 --- a/agent/Cargo.toml +++ b/agent/Cargo.toml @@ -1,6 +1,6 @@ [package] name = "cm-dashboard-agent" -version = "0.1.147" +version = "0.1.148" edition = "2021" [dependencies] diff --git a/agent/src/collectors/systemd.rs b/agent/src/collectors/systemd.rs index 3c4aa41..68c0663 100644 --- a/agent/src/collectors/systemd.rs +++ b/agent/src/collectors/systemd.rs @@ -24,6 +24,8 @@ struct ServiceCacheState { last_collection: Option, /// Cached service data services: Vec, + /// Cached complete service data with sub-services + cached_service_data: Vec, /// Interesting services to monitor (cached after discovery) monitored_services: Vec, /// Cached service status information from discovery @@ -62,6 +64,7 @@ impl SystemdCollector { let state = ServiceCacheState { last_collection: None, services: Vec::new(), + cached_service_data: Vec::new(), monitored_services: Vec::new(), service_status_cache: std::collections::HashMap::new(), last_discovery_time: None, @@ -93,6 +96,7 @@ impl SystemdCollector { // Collect service data for each monitored service let mut services = Vec::new(); + let mut complete_service_data = Vec::new(); for service_name in &monitored_services { match self.get_service_status(service_name) { Ok((active_status, _detailed_info)) => { @@ -149,15 +153,19 @@ impl SystemdCollector { }; services.push(service_info); - // Add to AgentData with hierarchical structure - agent_data.services.push(ServiceData { + // Create complete service data + let service_data = ServiceData { name: service_name.clone(), memory_mb, disk_gb, user_stopped: false, // TODO: Integrate with service tracker service_status: self.calculate_service_status(service_name, &active_status), sub_services, - }); + }; + + // Add to AgentData and cache + agent_data.services.push(service_data.clone()); + complete_service_data.push(service_data); } Err(e) => { debug!("Failed to get status for service {}: {}", service_name, e); @@ -170,6 +178,7 @@ impl SystemdCollector { let mut state = self.state.write().unwrap(); state.last_collection = Some(start_time); state.services = services; + state.cached_service_data = complete_service_data; } let elapsed = start_time.elapsed(); @@ -232,10 +241,6 @@ impl SystemdCollector { if needs_refresh { // Only check nginx sites if nginx service is active if state.monitored_services.iter().any(|s| s.contains("nginx")) { - debug!( - "Refreshing nginx site latency metrics (interval: {}s)", - state.nginx_check_interval_seconds - ); let fresh_metrics = self.get_nginx_sites_internal(); state.nginx_site_metrics = fresh_metrics; state.last_nginx_check_time = Some(Instant::now()); @@ -564,6 +569,16 @@ impl SystemdCollector { } } + /// Get cached complete service data with sub-services if available and fresh + fn get_cached_complete_services(&self) -> Option> { + if !self.should_update_cache() { + let state = self.state.read().unwrap(); + Some(state.cached_service_data.clone()) + } else { + None + } + } + /// Get nginx sites with latency checks (internal - no caching) fn get_nginx_sites_internal(&self) -> Vec<(String, f32)> { let mut sites = Vec::new(); @@ -571,13 +586,14 @@ impl SystemdCollector { // Discover nginx sites from configuration let discovered_sites = self.discover_nginx_sites(); + // Always add all discovered sites, even if checks fail (like old version) for (site_name, url) in &discovered_sites { match self.check_site_latency(url) { Ok(latency_ms) => { sites.push((site_name.clone(), latency_ms)); } Err(_) => { - // Site is unreachable - use -1.0 to indicate error + // Site is unreachable - use -1.0 to indicate error (like old version) sites.push((site_name.clone(), -1.0)); } } @@ -835,18 +851,10 @@ impl SystemdCollector { #[async_trait] impl Collector for SystemdCollector { async fn collect_structured(&self, agent_data: &mut AgentData) -> Result<(), CollectorError> { - // Use cached data if available and fresh - if let Some(cached_services) = self.get_cached_services() { - debug!("Using cached systemd services data"); - for service in cached_services { - agent_data.services.push(ServiceData { - name: service.name.clone(), - memory_mb: service.memory_mb, - disk_gb: service.disk_gb, - user_stopped: false, // TODO: Integrate with service tracker - service_status: self.calculate_service_status(&service.name, &service.status), - sub_services: Vec::new(), // Cached services don't have sub-services - }); + // Use cached complete data if available and fresh + if let Some(cached_complete_services) = self.get_cached_complete_services() { + for service_data in cached_complete_services { + agent_data.services.push(service_data); } Ok(()) } else { diff --git a/dashboard/Cargo.toml b/dashboard/Cargo.toml index 02a0621..98b1502 100644 --- a/dashboard/Cargo.toml +++ b/dashboard/Cargo.toml @@ -1,6 +1,6 @@ [package] name = "cm-dashboard" -version = "0.1.147" +version = "0.1.148" edition = "2021" [dependencies] diff --git a/shared/Cargo.toml b/shared/Cargo.toml index 76d1112..faaafb5 100644 --- a/shared/Cargo.toml +++ b/shared/Cargo.toml @@ -1,6 +1,6 @@ [package] name = "cm-dashboard-shared" -version = "0.1.147" +version = "0.1.148" edition = "2021" [dependencies]