ocdp v1

backend/internal/adapter/input/http/rest/monitoring_handler.go

@@ -0,0 +1,137 @@
+package rest
+
+import (
+	"net/http"
+
+	"github.com/gorilla/mux"
+	"github.com/ocdp/cluster-service/internal/adapter/input/http/dto"
+	"github.com/ocdp/cluster-service/internal/domain/service"
+)
+
+// MonitoringHandler 监控处理器
+type MonitoringHandler struct {
+	monitoringService *service.MonitoringService
+}
+
+// NewMonitoringHandler 创建监控处理器
+func NewMonitoringHandler(monitoringService *service.MonitoringService) *MonitoringHandler {
+	return &MonitoringHandler{
+		monitoringService: monitoringService,
+	}
+}
+
+// GetClusterMonitoring 获取单个集群的监控信息
+// @Summary 获取集群监控
+// @Tags Monitoring
+// @Produce json
+// @Security BearerAuth
+// @Param cluster_id path string true "集群 ID"
+// @Success 200 {object} dto.ClusterMetricsResponse
+// @Failure 500 {object} dto.ErrorResponse
+// @Router /monitoring/clusters/{cluster_id} [get]
+func (h *MonitoringHandler) GetClusterMonitoring(w http.ResponseWriter, r *http.Request) {
+	vars := mux.Vars(r)
+	clusterID := vars["cluster_id"]
+
+	metrics, err := h.monitoringService.GetClusterMonitoring(r.Context(), clusterID)
+	if err != nil {
+		respondError(w, http.StatusInternalServerError, "MONITORING_ERROR", err.Error())
+		return
+	}
+
+	response := dto.ToClusterMetricsResponse(metrics)
+	respondJSON(w, http.StatusOK, response)
+}
+
+// ListClusterMonitoring 获取所有集群的监控信息
+// @Summary 列出集群监控
+// @Tags Monitoring
+// @Produce json
+// @Security BearerAuth
+// @Success 200 {array} dto.ClusterMetricsResponse
+// @Failure 500 {object} dto.ErrorResponse
+// @Router /monitoring/clusters [get]
+func (h *MonitoringHandler) ListClusterMonitoring(w http.ResponseWriter, r *http.Request) {
+	monitoringList, err := h.monitoringService.ListClusterMonitoring(r.Context())
+	if err != nil {
+		respondError(w, http.StatusInternalServerError, "MONITORING_ERROR", err.Error())
+		return
+	}
+
+	// 转换为响应格式
+	response := make([]*dto.ClusterMetricsResponse, len(monitoringList))
+	for i, m := range monitoringList {
+		response[i] = dto.ToClusterMetricsResponse(m)
+	}
+
+	respondJSON(w, http.StatusOK, response)
+}
+
+// GetMonitoringSummary 获取监控汇总信息
+// @Summary 获取监控汇总
+// @Tags Monitoring
+// @Produce json
+// @Security BearerAuth
+// @Success 200 {object} dto.MonitoringSummaryResponse
+// @Failure 500 {object} dto.ErrorResponse
+// @Router /monitoring/summary [get]
+func (h *MonitoringHandler) GetMonitoringSummary(w http.ResponseWriter, r *http.Request) {
+	summary, err := h.monitoringService.GetMonitoringSummary(r.Context())
+	if err != nil {
+		respondError(w, http.StatusInternalServerError, "MONITORING_ERROR", err.Error())
+		return
+	}
+
+	response := dto.ToMonitoringSummaryResponse(summary)
+	respondJSON(w, http.StatusOK, response)
+}
+
+// GetNodeMetrics 获取集群的节点指标
+// @Summary 获取节点指标
+// @Tags Monitoring
+// @Produce json
+// @Security BearerAuth
+// @Param cluster_id path string true "集群 ID"
+// @Success 200 {array} dto.NodeMetricsResponse
+// @Failure 500 {object} dto.ErrorResponse
+// @Router /monitoring/clusters/{cluster_id}/nodes [get]
+func (h *MonitoringHandler) GetNodeMetrics(w http.ResponseWriter, r *http.Request) {
+	vars := mux.Vars(r)
+	clusterID := vars["cluster_id"]
+
+	nodes, err := h.monitoringService.GetNodeMetrics(r.Context(), clusterID)
+	if err != nil {
+		respondError(w, http.StatusInternalServerError, "MONITORING_ERROR", err.Error())
+		return
+	}
+
+	// 转换为响应格式
+	response := make([]dto.NodeMetricsResponse, len(nodes))
+	for i, node := range nodes {
+		response[i] = dto.NodeMetricsResponse{
+			NodeName:          node.NodeName,
+			Status:            node.Status,
+			Role:              node.Role,
+			Age:               node.Age,
+			PodCount:          node.PodCount,
+			CPUCapacity:       node.CPUCapacity,
+			CPUAllocatable:    node.CPUAllocatable,
+			CPUUsage:          node.CPUUsage,
+			CPUPercent:        node.CPUPercent,
+			MemoryCapacity:    node.MemoryCapacity,
+			MemoryAllocatable: node.MemoryAllocatable,
+			MemoryUsage:       node.MemoryUsage,
+			MemoryPercent:     node.MemoryPercent,
+			GPUCapacity:       node.GPUCapacity,
+			GPUUsage:          node.GPUUsage,
+			GPUPercent:        node.GPUPercent,
+			GPUType:           node.GPUType,
+			OSImage:           node.OSImage,
+			KernelVersion:     node.KernelVersion,
+			ContainerRuntime:  node.ContainerRuntime,
+			KubeletVersion:    node.KubeletVersion,
+		}
+	}
+
+	respondJSON(w, http.StatusOK, response)
+}