perf: bound lake scans and add platform Grafana dashboard

Explorer and exporter were scanning the full Parquet lake every 1–5s
(~2000 files, 200MB+), driving ~2.2 CPU cores. Limit metrics to the
last N flights, cache DuckDB views and the partition tree, slow live
polls to 2s, and keep drones alive after seal to stop restart churn.

Add node-exporter, scan-duration metrics, and a Swarm Platform Grafana
dashboard for node CPU/memory and scan health.

infra/terraform/sim-env/main.tf

@@ -63,6 +63,14 @@ resource "kubernetes_stateful_set" "drone" {
             name  = "DATA_DIR"
             value = "/data"
           }
+          env {
+            name  = "KEEP_ALIVE"
+            value = "1"
+          }
+          env {
+            name  = "IMU_HZ"
+            value = "20"
+          }
 
           volume_mount {
             name       = "lake"
@@ -118,9 +126,21 @@ resource "kubernetes_deployment" "exporter" {
             name  = "EXPORTER_PORT"
             value = "9105"
           }
+          env {
+            name  = "SCAN_INTERVAL_S"
+            value = "30"
+          }
+          env {
+            name  = "METRIC_FLIGHT_WINDOW"
+            value = "5"
+          }
           port {
             container_port = 9105
           }
+          resources {
+            requests = { cpu = "50m", memory = "64Mi" }
+            limits   = { cpu = "500m", memory = "256Mi" }
+          }
           volume_mount {
             name       = "lake"
             mount_path = "/data"
@@ -182,9 +202,25 @@ resource "kubernetes_deployment" "explorer" {
             name  = "EXPLORER_PORT"
             value = "8088"
           }
+          env {
+            name  = "VIEW_REFRESH_S"
+            value = "30"
+          }
+          env {
+            name  = "TREE_CACHE_S"
+            value = "15"
+          }
+          env {
+            name  = "METRIC_FLIGHT_WINDOW"
+            value = "5"
+          }
           port {
             container_port = 8088
           }
+          resources {
+            requests = { cpu = "50m", memory = "64Mi" }
+            limits   = { cpu = "750m", memory = "256Mi" }
+          }
           volume_mount {
             name       = "lake"
             mount_path = "/data"
@@ -226,11 +262,17 @@ resource "kubernetes_config_map" "prometheus" {
   data = {
     "prometheus.yml" = <<-EOT
       global:
-        scrape_interval: 5s
+        scrape_interval: 15s
       scrape_configs:
         - job_name: swarm
           static_configs:
             - targets: ["exporter:9105"]
+        - job_name: explorer
+          static_configs:
+            - targets: ["explorer:8088"]
+        - job_name: node
+          static_configs:
+            - targets: ["node-exporter:9100"]
     EOT
   }
 }
@@ -327,7 +369,91 @@ resource "kubernetes_config_map" "grafana_dashboard" {
     namespace = kubernetes_namespace.swarm.metadata[0].name
   }
   data = {
-    "swarm.json" = file("${path.module}/../../../simulator/monitoring/grafana/dashboards/swarm.json")
+    "swarm.json"          = file("${path.module}/../../../simulator/monitoring/grafana/dashboards/swarm.json")
+    "swarm-platform.json" = file("${path.module}/../../../simulator/monitoring/grafana/dashboards/swarm-platform.json")
+  }
+}
+
+# Host metrics for the k3d node (CPU / memory on the platform dashboard)
+resource "kubernetes_deployment" "node_exporter" {
+  metadata {
+    name      = "node-exporter"
+    namespace = kubernetes_namespace.swarm.metadata[0].name
+    labels    = local.labels
+  }
+
+  spec {
+    replicas = 1
+    selector {
+      match_labels = { app = "node-exporter" }
+    }
+    template {
+      metadata {
+        labels = merge(local.labels, { app = "node-exporter" })
+      }
+      spec {
+        host_network = true
+        host_pid     = true
+        container {
+          name  = "node-exporter"
+          image = "prom/node-exporter:v1.8.2"
+          args = [
+            "--path.procfs=/host/proc",
+            "--path.sysfs=/host/sys",
+            "--path.rootfs=/host/root",
+            "--collector.filesystem.mount-points-exclude=^/(sys|proc|dev|host|etc)($$|/)",
+          ]
+          port {
+            container_port = 9100
+          }
+          volume_mount {
+            name       = "proc"
+            mount_path = "/host/proc"
+            read_only  = true
+          }
+          volume_mount {
+            name       = "sys"
+            mount_path = "/host/sys"
+            read_only  = true
+          }
+          volume_mount {
+            name       = "root"
+            mount_path = "/host/root"
+            read_only  = true
+          }
+          resources {
+            requests = { cpu = "20m", memory = "32Mi" }
+            limits   = { cpu = "200m", memory = "64Mi" }
+          }
+        }
+        volume {
+          name = "proc"
+          host_path { path = "/proc" }
+        }
+        volume {
+          name = "sys"
+          host_path { path = "/sys" }
+        }
+        volume {
+          name = "root"
+          host_path { path = "/" }
+        }
+      }
+    }
+  }
+}
+
+resource "kubernetes_service" "node_exporter" {
+  metadata {
+    name      = "node-exporter"
+    namespace = kubernetes_namespace.swarm.metadata[0].name
+  }
+  spec {
+    selector = { app = "node-exporter" }
+    port {
+      port        = 9100
+      target_port = 9100
+    }
   }
 }