feat(admin): overview dashboard sections + system temperature/load sensors (0.85.0) (#11)

backend/src/api/admin/system.rs

@@ -18,7 +18,7 @@ use axum::extract::State;
 use axum::routing::get;
 use axum::{Json, Router};
 use serde::Serialize;
-use sysinfo::{CpuRefreshKind, MemoryRefreshKind, RefreshKind, System};
+use sysinfo::{Components, CpuRefreshKind, MemoryRefreshKind, RefreshKind, System};
 
 use crate::app::AppState;
 use crate::auth::extractor::RequireAdmin;
@@ -35,6 +35,10 @@ pub struct SystemStats {
     pub disk: Option<DiskStats>,
     pub memory: MemoryStats,
     pub cpu: CpuStats,
+    /// Hardware temperature sensors. Empty when the platform doesn't
+    /// expose any (common inside containers without `/sys` access) —
+    /// the frontend renders an "unavailable" state, not an error.
+    pub temperatures: Vec<TempStat>,
     pub alerts: Vec<Alert>,
 }
 
@@ -56,6 +60,26 @@ pub struct MemoryStats {
 #[derive(Debug, Serialize)]
 pub struct CpuStats {
     pub percent_used: f64,
+    pub load_avg: LoadAvg,
+    /// Per-core usage percentages, one entry per logical core.
+    pub per_core: Vec<f64>,
+}
+
+#[derive(Debug, Serialize)]
+pub struct LoadAvg {
+    pub one: f64,
+    pub five: f64,
+    pub fifteen: f64,
+}
+
+#[derive(Debug, Serialize)]
+pub struct TempStat {
+    pub label: String,
+    pub celsius: f64,
+    /// Highest reading seen since boot, when the kernel exposes it.
+    pub max_celsius: Option<f64>,
+    /// Vendor critical/shutdown threshold, when available.
+    pub critical_celsius: Option<f64>,
 }
 
 #[derive(Debug, Serialize)]
@@ -76,6 +100,7 @@ async fn system(
 ) -> AppResult<Json<SystemStats>> {
     let disk = state.storage.local_root().and_then(disk_stats_for);
     let (memory, cpu) = memory_and_cpu().await;
+    let temperatures = temperatures();
     let mut alerts = Vec::new();
     if let Some(d) = &disk {
         if d.percent_used >= ALERT_THRESHOLD_PERCENT {
@@ -97,14 +122,53 @@ async fn system(
             ),
         });
     }
+    for t in &temperatures {
+        if let Some(crit) = t.critical_celsius {
+            if t.celsius >= crit {
+                alerts.push(Alert {
+                    level: AlertLevel::Warning,
+                    message: format!(
+                        "{} temperature critical ({:.0}°C / {:.0}°C)",
+                        t.label, t.celsius, crit
+                    ),
+                });
+            }
+        }
+    }
     Ok(Json(SystemStats {
         disk,
         memory,
         cpu,
+        temperatures,
         alerts,
     }))
 }
 
+/// Hardware temperature sensors via `sysinfo`'s `Components`. Components
+/// whose temperature can't be read report `f32::NAN` on Linux — we skip
+/// those so the dashboard never shows a bogus "NaN°C" row. Returns an
+/// empty Vec when no sensors are exposed at all.
+fn temperatures() -> Vec<TempStat> {
+    let components = Components::new_with_refreshed_list();
+    components
+        .list()
+        .iter()
+        .filter_map(|c| {
+            let celsius = c.temperature();
+            if celsius.is_nan() {
+                return None;
+            }
+            let max = c.max();
+            Some(TempStat {
+                label: c.label().to_string(),
+                celsius: celsius as f64,
+                max_celsius: (!max.is_nan()).then_some(max as f64),
+                critical_celsius: c.critical().map(|v| v as f64),
+            })
+        })
+        .collect()
+}
+
 pub(crate) fn disk_stats_for(root: &Path) -> Option<DiskStats> {
     let s = nix::sys::statvfs::statvfs(root).ok()?;
     // statvfs reports `f_frsize * f_blocks` for total bytes. `f_bavail`
@@ -156,8 +220,15 @@ async fn memory_and_cpu() -> (MemoryStats, CpuStats) {
         percent_used: mem_pct,
     };
 
+    let load = System::load_average();
     let cpu = CpuStats {
         percent_used: sys.global_cpu_usage() as f64,
+        load_avg: LoadAvg {
+            one: load.one,
+            five: load.five,
+            fifteen: load.fifteen,
+        },
+        per_core: sys.cpus().iter().map(|c| c.cpu_usage() as f64).collect(),
     };
     (memory, cpu)
 }