ocdp v1

backend/internal/domain/service/monitoring_service.go

@@ -0,0 +1,102 @@
+package service
+
+import (
+	"context"
+	"fmt"
+
+	"github.com/ocdp/cluster-service/internal/domain/entity"
+	"github.com/ocdp/cluster-service/internal/domain/repository"
+)
+
+// MonitoringService 监控服务
+type MonitoringService struct {
+	clusterRepo  repository.ClusterRepository
+	metricsClient repository.MetricsClient
+}
+
+// NewMonitoringService 创建监控服务
+func NewMonitoringService(
+	clusterRepo repository.ClusterRepository,
+	metricsClient repository.MetricsClient,
+) *MonitoringService {
+	return &MonitoringService{
+		clusterRepo:  clusterRepo,
+		metricsClient: metricsClient,
+	}
+}
+
+// GetClusterMonitoring 获取单个集群的监控信息
+func (s *MonitoringService) GetClusterMonitoring(ctx context.Context, clusterID string) (*entity.ClusterMetrics, error) {
+	metrics, err := s.metricsClient.GetClusterMetrics(ctx, clusterID)
+	if err != nil {
+		return nil, fmt.Errorf("failed to get cluster metrics: %w", err)
+	}
+	return metrics, nil
+}
+
+// ListClusterMonitoring 获取所有集群的监控信息
+func (s *MonitoringService) ListClusterMonitoring(ctx context.Context) ([]*entity.ClusterMetrics, error) {
+	// 获取所有集群
+	clusters, err := s.clusterRepo.List(ctx)
+	if err != nil {
+		return nil, fmt.Errorf("failed to list clusters: %w", err)
+	}
+
+	// 获取每个集群的监控数据
+	result := make([]*entity.ClusterMetrics, 0, len(clusters))
+	for _, cluster := range clusters {
+		metrics, err := s.metricsClient.GetClusterMetrics(ctx, cluster.ID)
+		if err != nil {
+			// 如果某个集群获取失败，记录错误但继续
+			fmt.Printf("Warning: failed to get metrics for cluster %s: %v\n", cluster.ID, err)
+			// 返回基本信息
+			metrics = &entity.ClusterMetrics{
+				ClusterID:   cluster.ID,
+				ClusterName: cluster.Name,
+				Status:      "unknown",
+			}
+		}
+		result = append(result, metrics)
+	}
+
+	return result, nil
+}
+
+// GetMonitoringSummary 获取监控汇总信息
+func (s *MonitoringService) GetMonitoringSummary(ctx context.Context) (*entity.MonitoringSummary, error) {
+	// 获取所有集群监控数据
+	monitoringList, err := s.ListClusterMonitoring(ctx)
+	if err != nil {
+		return nil, fmt.Errorf("failed to list monitoring: %w", err)
+	}
+
+	// 统计汇总
+	summary := &entity.MonitoringSummary{
+		TotalClusters: len(monitoringList),
+	}
+
+	for _, m := range monitoringList {
+		switch m.Status {
+		case "healthy":
+			summary.HealthyClusters++
+		case "warning":
+			summary.WarningClusters++
+		case "error":
+			summary.ErrorClusters++
+		}
+		summary.TotalNodes += m.NodeCount
+		summary.TotalPods += m.PodCount
+	}
+
+	return summary, nil
+}
+
+// GetNodeMetrics 获取集群的节点指标
+func (s *MonitoringService) GetNodeMetrics(ctx context.Context, clusterID string) ([]*entity.NodeMetrics, error) {
+	nodes, err := s.metricsClient.GetNodeMetrics(ctx, clusterID)
+	if err != nil {
+		return nil, fmt.Errorf("failed to get node metrics: %w", err)
+	}
+	return nodes, nil
+}
+