chore: resolve conflicts

frontend/src/container/InfraMonitoringHosts/InfraMonitoring.styles.scss

@@ -190,6 +190,11 @@
 			.ant-table-cell:nth-child(n + 3) {
 				padding-right: 24px;
 			}
+			.status-header {
+				display: flex;
+				align-items: center;
+				gap: 4px;
+			}
 			.memory-usage-header {
 				display: flex;
 				align-items: center;

frontend/src/container/InfraMonitoringHosts/utils.tsx

@@ -146,7 +146,14 @@ export const getHostsListColumns = (): ColumnType<HostRowData>[] => [
 		),
 	},
 	{
-		title: 'Status',
+		title: (
+			<div className="status-header">
+				Status
+				<Tooltip title="Sent system metrics in last 10 mins">
+					<InfoCircleOutlined />
+				</Tooltip>
+			</div>
+		),
 		dataIndex: 'active',
 		key: 'active',
 		width: 100,

pkg/query-service/app/clickhouseReader/reader.go

@@ -3541,6 +3541,45 @@ func (r *ClickHouseReader) GetCountOfThings(ctx context.Context, query string) (
 	return count, nil
 }
 
+func (r *ClickHouseReader) GetActiveHostsFromMetricMetadata(ctx context.Context, metricNames []string, hostNameAttr string, sinceUnixMilli int64) (map[string]bool, error) {
+	activeHosts := map[string]bool{}
+
+	query := fmt.Sprintf(
+		`SELECT DISTINCT attr_string_value
+		FROM %s.%s
+		WHERE metric_name IN @metricNames
+		  AND attr_name = @attrName
+		  AND last_reported_unix_milli >= @sinceUnixMilli`,
+		signozMetricDBName,
+		constants.SIGNOZ_METADATA_TABLENAME,
+	)
+
+	rows, err := r.db.Query(ctx, query,
+		clickhouse.Named("metricNames", metricNames),
+		clickhouse.Named("attrName", hostNameAttr),
+		clickhouse.Named("sinceUnixMilli", sinceUnixMilli),
+	)
+	if err != nil {
+		return nil, errorsV2.WrapInternalf(err, errorsV2.CodeInternal, "error querying active hosts")
+	}
+	defer rows.Close()
+
+	for rows.Next() {
+		var hostName string
+		if err := rows.Scan(&hostName); err != nil {
+			return nil, errorsV2.WrapInternalf(err, errorsV2.CodeInternal, "error scanning active host row")
+		}
+		if hostName != "" {
+			activeHosts[hostName] = true
+		}
+	}
+	if err := rows.Err(); err != nil {
+		return nil, errorsV2.WrapInternalf(err, errorsV2.CodeInternal, "error iterating active host rows")
+	}
+
+	return activeHosts, nil
+}
+
 func (r *ClickHouseReader) GetLatestReceivedMetric(
 	ctx context.Context, metricNames []string, labelValues map[string]string,
 ) (*model.MetricStatus, *model.ApiError) {

pkg/query-service/app/inframetrics/common.go

@@ -10,55 +10,110 @@ import (
 )
 
 var dotMetricMap = map[string]string{
-	"system_filesystem_usage":               "system.filesystem.usage",
-	"system_cpu_time":                       "system.cpu.time",
-	"system_memory_usage":                   "system.memory.usage",
-	"system_cpu_load_average_15m":           "system.cpu.load_average.15m",
-	"host_name":                             "host.name",
-	"k8s_cluster_name":                      "k8s.cluster.name",
-	"k8s_node_name":                         "k8s.node.name",
-	"k8s_pod_memory_usage":                  "k8s.pod.memory.usage",
-	"k8s_pod_cpu_request_utilization":       "k8s.pod.cpu_request_utilization",
-	"k8s_pod_memory_request_utilization":    "k8s.pod.memory_request_utilization",
-	"k8s_pod_cpu_limit_utilization":         "k8s.pod.cpu_limit_utilization",
-	"k8s_pod_memory_limit_utilization":      "k8s.pod.memory_limit_utilization",
-	"k8s_container_restarts":                "k8s.container.restarts",
-	"k8s_pod_phase":                         "k8s.pod.phase",
-	"k8s_node_allocatable_cpu":              "k8s.node.allocatable_cpu",
-	"k8s_node_allocatable_memory":           "k8s.node.allocatable_memory",
-	"k8s_node_memory_usage":                 "k8s.node.memory.usage",
-	"k8s_node_condition_ready":              "k8s.node.condition_ready",
-	"k8s_daemonset_desired_scheduled_nodes": "k8s.daemonset.desired_scheduled_nodes",
-	"k8s_daemonset_current_scheduled_nodes": "k8s.daemonset.current_scheduled_nodes",
-	"k8s_deployment_desired":                "k8s.deployment.desired",
-	"k8s_deployment_available":              "k8s.deployment.available",
-	"k8s_job_desired_successful_pods":       "k8s.job.desired_successful_pods",
-	"k8s_job_active_pods":                   "k8s.job.active_pods",
-	"k8s_job_failed_pods":                   "k8s.job.failed_pods",
-	"k8s_job_successful_pods":               "k8s.job.successful_pods",
-	"k8s_statefulset_desired_pods":          "k8s.statefulset.desired_pods",
-	"k8s_statefulset_current_pods":          "k8s.statefulset.current_pods",
-	"k8s_namespace_name":                    "k8s.namespace.name",
-	"k8s_deployment_name":                   "k8s.deployment.name",
-	"k8s_cronjob_name":                      "k8s.cronjob.name",
-	"k8s_job_name":                          "k8s.job.name",
-	"k8s_daemonset_name":                    "k8s.daemonset.name",
-	"os_type":                               "os.type",
-	"process_cgroup":                        "process.cgroup",
-	"process_pid":                           "process.pid",
-	"process_parent_pid":                    "process.parent_pid",
-	"process_owner":                         "process.owner",
-	"process_executable_path":               "process.executable.path",
-	"process_executable_name":               "process.executable.name",
-	"process_command_line":                  "process.command_line",
-	"process_command":                       "process.command",
-	"process_memory_usage":                  "process.memory.usage",
-	"k8s_persistentvolumeclaim_name":        "k8s.persistentvolumeclaim.name",
-	"k8s_volume_available":                  "k8s.volume.available",
-	"k8s_volume_capacity":                   "k8s.volume.capacity",
-	"k8s_volume_inodes":                     "k8s.volume.inodes",
-	"k8s_volume_inodes_free":                "k8s.volume.inodes.free",
-	// add additional mappings as needed
+	"system_uptime":                  "system.uptime",
+	"system_cpu_physical_count":      "system.cpu.physical.count",
+	"system_cpu_logical_count":       "system.cpu.logical.count",
+	"system_cpu_time":                "system.cpu.time",
+	"system_cpu_frequency":           "system.cpu.frequency",
+	"system_cpu_utilization":         "system.cpu.utilization",
+	"system_cpu_load_average_15m":    "system.cpu.load_average.15m",
+	"system_memory_usage":            "system.memory.usage",
+	"system_memory_limit":            "system.memory.limit",
+	"system_memory_utilization":      "system.memory.utilization",
+	"system_memory_linux_available":  "system.memory.linux.available",
+	"system_memory_linux_shared":     "system.memory.linux.shared",
+	"system_memory_linux_slab_usage": "system.memory.linux.slab.usage",
+	"system_paging_usage":            "system.paging.usage",
+	"system_paging_utilization":      "system.paging.utilization",
+	"system_paging_faults":           "system.paging.faults",
+	"system_paging_operations":       "system.paging.operations",
+	"system_disk_io":                 "system.disk.io",
+	"system_disk_operations":         "system.disk.operations",
+	"system_disk_io_time":            "system.disk.io_time",
+	"system_disk_operation_time":     "system.disk.operation_time",
+	"system_disk_merged":             "system.disk.merged",
+	"system_disk_limit":              "system.disk.limit",
+	"system_filesystem_usage":        "system.filesystem.usage",
+	"system_filesystem_utilization":  "system.filesystem.utilization",
+	"system_filesystem_limit":        "system.filesystem.limit",
+	"system_network_errors":          "system.network.errors",
+	"system_network_io":              "system.network.io",
+	"system_network_connections":     "system.network.connections",
+	"system_network_dropped":         "system.network.dropped",
+	"system_network_packets":         "system.network.packets",
+	"system_processes_count":         "system.processes.count",
+	"system_processes_created":       "system.processes.created",
+	"system_disk_pending_operations": "system.disk.pending_operations",
+	"system_disk_weighted_io_time":   "system.disk.weighted_io_time",
+	"system_filesystem_inodes_usage": "system.filesystem.inodes.usage",
+	"system_network_conntrack_count": "system.network.conntrack.count",
+	"system_network_conntrack_max":   "system.network.conntrack.max",
+	"system_cpu_load_average_1m":     "system.cpu.load_average.1m",
+	"system_cpu_load_average_5m":     "system.cpu.load_average.5m",
+
+	"host_name":                              "host.name",
+	"k8s_cluster_name":                       "k8s.cluster.name",
+	"k8s_node_name":                          "k8s.node.name",
+	"k8s_pod_memory_usage":                   "k8s.pod.memory.usage",
+	"k8s_pod_cpu_request_utilization":        "k8s.pod.cpu_request_utilization",
+	"k8s_pod_memory_request_utilization":     "k8s.pod.memory_request_utilization",
+	"k8s_pod_cpu_limit_utilization":          "k8s.pod.cpu_limit_utilization",
+	"k8s_pod_memory_limit_utilization":       "k8s.pod.memory_limit_utilization",
+	"k8s_container_restarts":                 "k8s.container.restarts",
+	"k8s_pod_phase":                          "k8s.pod.phase",
+	"k8s_node_allocatable_cpu":               "k8s.node.allocatable_cpu",
+	"k8s_node_allocatable_memory":            "k8s.node.allocatable_memory",
+	"k8s_node_memory_usage":                  "k8s.node.memory.usage",
+	"k8s_node_condition_ready":               "k8s.node.condition_ready",
+	"k8s_daemonset_desired_scheduled_nodes":  "k8s.daemonset.desired_scheduled_nodes",
+	"k8s_daemonset_current_scheduled_nodes":  "k8s.daemonset.current_scheduled_nodes",
+	"k8s_deployment_desired":                 "k8s.deployment.desired",
+	"k8s_deployment_available":               "k8s.deployment.available",
+	"k8s_job_desired_successful_pods":        "k8s.job.desired_successful_pods",
+	"k8s_job_active_pods":                    "k8s.job.active_pods",
+	"k8s_job_failed_pods":                    "k8s.job.failed_pods",
+	"k8s_job_successful_pods":                "k8s.job.successful_pods",
+	"k8s_statefulset_desired_pods":           "k8s.statefulset.desired_pods",
+	"k8s_statefulset_current_pods":           "k8s.statefulset.current_pods",
+	"k8s_namespace_name":                     "k8s.namespace.name",
+	"k8s_deployment_name":                    "k8s.deployment.name",
+	"k8s_cronjob_name":                       "k8s.cronjob.name",
+	"k8s_job_name":                           "k8s.job.name",
+	"k8s_daemonset_name":                     "k8s.daemonset.name",
+	"os_type":                                "os.type",
+	"process_cgroup":                         "process.cgroup",
+	"process_pid":                            "process.pid",
+	"process_parent_pid":                     "process.parent_pid",
+	"process_owner":                          "process.owner",
+	"process_executable_path":                "process.executable.path",
+	"process_executable_name":                "process.executable.name",
+	"process_command_line":                   "process.command_line",
+	"process_command":                        "process.command",
+	"process_memory_usage":                   "process.memory.usage",
+	"process_memory_virtual":                 "process.memory.virtual",
+	"process_cpu_time":                       "process.cpu.time",
+	"process_disk_io":                        "process.disk.io",
+	"nfs_client_net_count":                   "nfs.client.net.count",
+	"nfs_client_net_tcp_connection_accepted": "nfs.client.net.tcp.connection.accepted",
+	"nfs_client_operation_count":             "nfs.client.operation.count",
+	"nfs_client_procedure_count":             "nfs.client.procedure.count",
+	"nfs_client_rpc_authrefresh_count":       "nfs.client.rpc.authrefresh.count",
+	"nfs_client_rpc_count":                   "nfs.client.rpc.count",
+	"nfs_client_rpc_retransmit_count":        "nfs.client.rpc.retransmit.count",
+	"nfs_server_fh_stale_count":              "nfs.server.fh.stale.count",
+	"nfs_server_io":                          "nfs.server.io",
+	"nfs_server_net_count":                   "nfs.server.net.count",
+	"nfs_server_net_tcp_connection_accepted": "nfs.server.net.tcp.connection.accepted",
+	"nfs_server_operation_count":             "nfs.server.operation.count",
+	"nfs_server_procedure_count":             "nfs.server.procedure.count",
+	"nfs_server_repcache_requests":           "nfs.server.repcache.requests",
+	"nfs_server_rpc_count":                   "nfs.server.rpc.count",
+	"nfs_server_thread_count":                "nfs.server.thread.count",
+	"k8s_persistentvolumeclaim_name":         "k8s.persistentvolumeclaim.name",
+	"k8s_volume_available":                   "k8s.volume.available",
+	"k8s_volume_capacity":                    "k8s.volume.capacity",
+	"k8s_volume_inodes":                      "k8s.volume.inodes",
+	"k8s_volume_inodes_free":                 "k8s.volume.inodes.free",
 
 	"k8s_pod_uid":              "k8s.pod.uid",
 	"k8s_pod_name":             "k8s.pod.name",

pkg/query-service/app/inframetrics/hosts.go

@@ -73,6 +73,53 @@ var (
 		"load15":     GetDotMetrics("system_cpu_load_average_15m"),
 		"wait":       GetDotMetrics("system_cpu_time"),
 	}
+	uniqueMetricNamesForHosts = []string{
+		GetDotMetrics("system_uptime"),
+		GetDotMetrics("system_cpu_time"),
+		GetDotMetrics("system_cpu_load_average_1m"),
+		GetDotMetrics("system_cpu_load_average_5m"),
+		GetDotMetrics("system_cpu_load_average_15m"),
+		GetDotMetrics("system_memory_usage"),
+		GetDotMetrics("system_paging_usage"),
+		GetDotMetrics("system_paging_faults"),
+		GetDotMetrics("system_paging_operations"),
+		GetDotMetrics("system_disk_io"),
+		GetDotMetrics("system_disk_operations"),
+		GetDotMetrics("system_disk_io_time"),
+		GetDotMetrics("system_disk_operation_time"),
+		GetDotMetrics("system_disk_merged"),
+		GetDotMetrics("system_disk_pending_operations"),
+		GetDotMetrics("system_disk_weighted_io_time"),
+		GetDotMetrics("system_filesystem_usage"),
+		GetDotMetrics("system_filesystem_inodes_usage"),
+		GetDotMetrics("system_network_io"),
+		GetDotMetrics("system_network_errors"),
+		GetDotMetrics("system_network_connections"),
+		GetDotMetrics("system_network_dropped"),
+		GetDotMetrics("system_network_packets"),
+		GetDotMetrics("system_processes_count"),
+		GetDotMetrics("system_processes_created"),
+		GetDotMetrics("process_cpu_time"),
+		GetDotMetrics("process_disk_io"),
+		GetDotMetrics("process_memory_usage"),
+		GetDotMetrics("process_memory_virtual"),
+		GetDotMetrics("nfs_client_net_count"),
+		GetDotMetrics("nfs_client_net_tcp_connection_accepted"),
+		GetDotMetrics("nfs_client_operation_count"),
+		GetDotMetrics("nfs_client_procedure_count"),
+		GetDotMetrics("nfs_client_rpc_authrefresh_count"),
+		GetDotMetrics("nfs_client_rpc_count"),
+		GetDotMetrics("nfs_client_rpc_retransmit_count"),
+		GetDotMetrics("nfs_server_fh_stale_count"),
+		GetDotMetrics("nfs_server_io"),
+		GetDotMetrics("nfs_server_net_count"),
+		GetDotMetrics("nfs_server_net_tcp_connection_accepted"),
+		GetDotMetrics("nfs_server_operation_count"),
+		GetDotMetrics("nfs_server_procedure_count"),
+		GetDotMetrics("nfs_server_repcache_requests"),
+		GetDotMetrics("nfs_server_rpc_count"),
+		GetDotMetrics("nfs_server_thread_count"),
+	}
 )
 
 func NewHostsRepo(reader interfaces.Reader, querierV2 interfaces.Querier) *HostsRepo {
@@ -131,62 +178,9 @@ func (h *HostsRepo) GetHostAttributeValues(ctx context.Context, req v3.FilterAtt
 	return &v3.FilterAttributeValueResponse{StringAttributeValues: hostNames}, nil
 }
 
-func (h *HostsRepo) getActiveHosts(ctx context.Context, orgID valuer.UUID, req model.HostListRequest) (map[string]bool, error) {
-	activeStatus := map[string]bool{}
-	step := common.MinAllowedStepInterval(req.Start, req.End)
-
-	hasHostName := false
-	for _, key := range req.GroupBy {
-		if key.Key == hostNameAttrKey {
-			hasHostName = true
-		}
-	}
-
-	if !hasHostName {
-		req.GroupBy = append(req.GroupBy, v3.AttributeKey{Key: hostNameAttrKey})
-	}
-
-	params := v3.QueryRangeParamsV3{
-		Start: time.Now().Add(-time.Minute * 10).UTC().UnixMilli(),
-		End:   time.Now().UTC().UnixMilli(),
-		Step:  step,
-		CompositeQuery: &v3.CompositeQuery{
-			BuilderQueries: map[string]*v3.BuilderQuery{
-				"A": {
-					QueryName:    "A",
-					StepInterval: step,
-					DataSource:   v3.DataSourceMetrics,
-					AggregateAttribute: v3.AttributeKey{
-						Key:      metricToUseForHostAttributes,
-						DataType: v3.AttributeKeyDataTypeFloat64,
-					},
-					Temporality:      v3.Unspecified,
-					Filters:          req.Filters,
-					GroupBy:          req.GroupBy,
-					Expression:       "A",
-					TimeAggregation:  v3.TimeAggregationAvg,
-					SpaceAggregation: v3.SpaceAggregationAvg,
-					Disabled:         false,
-				},
-			},
-			QueryType: v3.QueryTypeBuilder,
-			PanelType: v3.PanelTypeGraph,
-		},
-	}
-
-	queryResponse, _, err := h.querierV2.QueryRange(ctx, orgID, &params)
-	if err != nil {
-		return nil, err
-	}
-
-	for _, result := range queryResponse {
-		for _, series := range result.Series {
-			name := series.Labels[hostNameAttrKey]
-			activeStatus[name] = true
-		}
-	}
-
-	return activeStatus, nil
+func (h *HostsRepo) getActiveHosts(ctx context.Context) (map[string]bool, error) {
+	tenMinAgo := time.Now().Add(-10 * time.Minute).UTC().UnixMilli()
+	return h.reader.GetActiveHostsFromMetricMetadata(ctx, uniqueMetricNamesForHosts, hostNameAttrKey, tenMinAgo)
 }
 
 func (h *HostsRepo) getMetadataAttributes(ctx context.Context, req model.HostListRequest) (map[string]map[string]string, error) {
@@ -450,7 +444,7 @@ func (h *HostsRepo) GetHostList(ctx context.Context, orgID valuer.UUID, req mode
 		return resp, err
 	}
 
-	activeHosts, err := h.getActiveHosts(ctx, orgID, req)
+	activeHosts, err := h.getActiveHosts(ctx)
 	if err != nil {
 		return resp, err
 	}

pkg/query-service/interfaces/interface.go

@@ -99,6 +99,7 @@ type Reader interface {
 	SubscribeToQueryProgress(queryId string) (<-chan model.QueryProgress, func(), *model.ApiError)
 
 	GetCountOfThings(ctx context.Context, query string) (uint64, error)
+	GetActiveHostsFromMetricMetadata(ctx context.Context, metricNames []string, hostNameAttr string, sinceUnixMilli int64) (map[string]bool, error)
 
 	GetMetricsExistenceAndEarliestTime(ctx context.Context, metricNames []string) (uint64, uint64, error)