feat(v2.0.0): tsdb (#1162)

* feat: tsdb * fix(ci): remove --parseGoList=false from swag init to fix dependency resolution * fix(ci): fix swag init directory and temporary remove s390x support due to cgo issues * fix(ci): fix swag init output directory to cmd/dashboard/docs * fix(ci): set GOTOOLCHAIN=auto for gosec * feat: add system storage maintenance for SQLite and TSDB * shit * feat: add s390x support and improve service monitoring * ci: upgrade goreleaser-cross image to v1.25 * ci: add libzstd-dev:s390x for cross-compilation * ci: build libzstd for s390x from source * ci: add libzstd_linux_s390x.go for gozstd linking * ci: use vendor mode for s390x gozstd build * ci: clone zstd source for s390x build * refactor(tsdb): rename MaxDiskUsageGB to MinFreeDiskSpaceGB and optimize queries - Rename config to accurately reflect VictoriaMetrics behavior: minimum free disk space threshold - Add QueryServiceHistoryByServerID for batch query optimization - Fix hasStatus to avoid false status counting when only delay data exists - Fix service aggregation boundary: use successCount*2 >= count - Fix serviceID parsing with strconv.ParseUint error handling - Add TagFiltersCacheSize for better query performance * feat(api): add server metrics endpoint and simplify service history response - Add /server/:id/metrics API for querying TSDB server metrics - Simplify getServiceHistory by removing redundant data conversion - Change AvgDelay type from float32 to float64 - Remove generated swagger docs (to be regenerated) - Update TSDB query, writer and tests * chore: 临时禁用不支持前端 * ci: cache zstd build for s390x to speed up CI * fix(tsdb): fix race conditions, data correctness and optimize performance - Fix TOCTOU race between IsClosed() and write/query by holding RLock - Fix delay=0 excluded from stats by using hasDelay flag instead of value > 0 - Fix fmt.Sscanf -> strconv.ParseUint for server_id parsing with error logging - Fix buffer unbounded growth by flushing inside lock when over maxSize - Split makeMetricRow into makeServerMetricRow/makeServiceMetricRow - Extract InitGlobalSettings() from Open() for VictoriaMetrics globals - Remove redundant instance/GetInstance/SetInstance singleton - Add error logging for silently skipped block decode errors - Optimize WriteBatch* to build all rows in single write call - Optimize downsample to use linear scan instead of map for sorted data - Optimize query slice reuse across block iterations * 服务添加DisplayIndex (#1166) * 服务添加DisplayIndex * 根据ai建议修改 --------- Co-authored-by: huYang <306061454@qq.com> * fix(tsdb): restore SQLite fallback and monthly status reload on restart - Restore ServiceHistory model and SQLite write fallback when TSDB is disabled - Reload monthlyStatus (30-day) and serviceStatusToday from TSDB/SQLite on startup - Add SQLite fallback query for /service/:id/history and /server/:id/service - Remove breaking GET /service/:id endpoint, keep /service/:id/history only - Add QueryServiceDailyStats to TSDB for per-day aggregation - Add tests for monthly status and today stats loading from both TSDB and SQLite - Migrate ServiceHistory table only when TSDB is disabled * ci: exclude false-positive gosec rules G117, G703, G704 * feat(api): expose tsdb_enabled in setting response * ci: restore G115 exclusion accidentally dropped in previous commit * fix: update version numbers for OfficialAdmin and Official templates * chore: upgrade frontend * chore: upgrade frontend --------- Co-authored-by: 胡说丷刂 <34758853+laosan-xx@users.noreply.github.com> Co-authored-by: huYang <306061454@qq.com>
2026-05-06 05:38:50 +00:00 · 2026-02-15 13:13:33 +08:00
parent 4c4758207d
commit e61772e858
28 changed files with 3054 additions and 221 deletions
@@ -12,6 +12,7 @@ import (
 	"gorm.io/gorm"

 	"github.com/nezhahq/nezha/model"
+	"github.com/nezhahq/nezha/pkg/tsdb"
 	pb "github.com/nezhahq/nezha/proto"
 	"github.com/nezhahq/nezha/service/singleton"
 )
@@ -366,3 +367,89 @@ func batchMoveServer(c *gin.Context) (any, error) {

 	return nil, nil
 }
+
+var serverMetricMap = map[string]tsdb.MetricType{
+	"cpu":              tsdb.MetricServerCPU,
+	"memory":           tsdb.MetricServerMemory,
+	"swap":             tsdb.MetricServerSwap,
+	"disk":             tsdb.MetricServerDisk,
+	"net_in_speed":     tsdb.MetricServerNetInSpeed,
+	"net_out_speed":    tsdb.MetricServerNetOutSpeed,
+	"net_in_transfer":  tsdb.MetricServerNetInTransfer,
+	"net_out_transfer": tsdb.MetricServerNetOutTransfer,
+	"load1":            tsdb.MetricServerLoad1,
+	"load5":            tsdb.MetricServerLoad5,
+	"load15":           tsdb.MetricServerLoad15,
+	"tcp_conn":         tsdb.MetricServerTCPConn,
+	"udp_conn":         tsdb.MetricServerUDPConn,
+	"process_count":    tsdb.MetricServerProcessCount,
+	"temperature":      tsdb.MetricServerTemperature,
+	"uptime":           tsdb.MetricServerUptime,
+	"gpu":              tsdb.MetricServerGPU,
+}
+
+// Get server metrics history
+// @Summary Get server metrics history
+// @Security BearerAuth
+// @Schemes
+// @Description Get server metrics history for a specific server
+// @Tags common
+// @param id path uint true "Server ID"
+// @param metric query string true "Metric name: cpu, memory, swap, disk, net_in_speed, net_out_speed, net_in_transfer, net_out_transfer, load1, load5, load15, tcp_conn, udp_conn, process_count, temperature, uptime, gpu"
+// @param period query string false "Time period: 1d, 7d, 30d (default: 1d)"
+// @Produce json
+// @Success 200 {object} model.CommonResponse[model.ServerMetricsResponse]
+// @Router /server/{id}/metrics [get]
+func getServerMetrics(c *gin.Context) (*model.ServerMetricsResponse, error) {
+	idStr := c.Param("id")
+	serverID, err := strconv.ParseUint(idStr, 10, 64)
+	if err != nil {
+		return nil, err
+	}
+
+	server, ok := singleton.ServerShared.Get(serverID)
+	if !ok {
+		return nil, singleton.Localizer.ErrorT("server not found")
+	}
+
+	_, isMember := c.Get(model.CtxKeyAuthorizedUser)
+	if server.HideForGuest && !isMember {
+		return nil, singleton.Localizer.ErrorT("unauthorized")
+	}
+
+	metricName := c.Query("metric")
+	metricType, ok := serverMetricMap[metricName]
+	if !ok {
+		return nil, singleton.Localizer.ErrorT("invalid metric name")
+	}
+
+	periodStr := c.DefaultQuery("period", "1d")
+	period, err := tsdb.ParseQueryPeriod(periodStr)
+	if err != nil {
+		return nil, err
+	}
+
+	if !isMember && period != tsdb.Period1Day {
+		return nil, singleton.Localizer.ErrorT("unauthorized: only 1d data available for guests")
+	}
+
+	response := &model.ServerMetricsResponse{
+		ServerID:   serverID,
+		ServerName: server.Name,
+		Metric:     metricName,
+		DataPoints: make([]model.ServerMetricsDataPoint, 0),
+	}
+
+	if !singleton.TSDBEnabled() {
+		return response, nil
+	}
+
+	points, err := singleton.TSDBShared.QueryServerMetrics(serverID, metricType, period)
+	if err != nil {
+		return nil, err
+	}
+
+	response.DataPoints = points
+
+	return response, nil
+}