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>
This commit is contained in:
奶爸
2026-02-15 13:13:33 +08:00
committed by GitHub
parent 4c4758207d
commit e61772e858
28 changed files with 3054 additions and 221 deletions
+22
View File
@@ -70,6 +70,12 @@ type Config struct {
// HTTPS 配置
HTTPS HTTPSConf `koanf:"https" json:"https"`
// TSDB 配置
TSDB TSDBConf `koanf:"tsdb" json:"tsdb"`
// 内存配置
Memory MemoryConf `koanf:"memory" json:"memory"`
k *koanf.Koanf `json:"-"`
filePath string `json:"-"`
}
@@ -81,6 +87,22 @@ type HTTPSConf struct {
TLSKeyPath string `koanf:"tls_key_path" json:"tls_key_path,omitempty"`
}
// TSDBConf TSDB 配置
type TSDBConf struct {
DataPath string `koanf:"data_path" json:"data_path,omitempty"`
RetentionDays uint16 `koanf:"retention_days" json:"retention_days,omitempty"`
MinFreeDiskSpaceGB float64 `koanf:"min_free_disk_space_gb" json:"min_free_disk_space_gb,omitempty"`
MaxMemoryMB int64 `koanf:"max_memory_mb" json:"max_memory_mb,omitempty"`
WriteBufferSize int `koanf:"write_buffer_size" json:"write_buffer_size,omitempty"`
WriteBufferFlushInterval int `koanf:"write_buffer_flush_interval" json:"write_buffer_flush_interval,omitempty"`
}
// MemoryConf 内存配置
type MemoryConf struct {
// GoMemLimitMB Go 运行时内存限制(MB),0 表示不限制
GoMemLimitMB int64 `koanf:"go_mem_limit_mb" json:"go_mem_limit_mb,omitempty"`
}
// Read 读取配置文件并应用
func (c *Config) Read(path string, frontendTemplates []FrontendTemplate) error {
c.k = koanf.New(".")
+1
View File
@@ -53,6 +53,7 @@ type Service struct {
Target string `json:"target"`
SkipServersRaw string `json:"-"`
Duration uint64 `json:"duration"`
DisplayIndex int `json:"display_index"` // 展示排序,越大越靠前
Notify bool `json:"notify,omitempty"`
NotificationGroupID uint64 `json:"notification_group_id"` // 当前服务监控所属的通知组 ID
Cover uint8 `json:"cover"`
+2 -1
View File
@@ -7,6 +7,7 @@ type ServiceForm struct {
Target string `json:"target,omitempty"`
Type uint8 `json:"type,omitempty"`
Cover uint8 `json:"cover,omitempty"`
DisplayIndex int `json:"display_index,omitempty" default:"0"` // 展示排序,越大越靠前
Notify bool `json:"notify,omitempty" validate:"optional"`
Duration uint64 `json:"duration,omitempty"`
MinLatency float32 `json:"min_latency,omitempty" default:"0.0"`
@@ -26,7 +27,7 @@ type ServiceResponseItem struct {
CurrentDown uint64 `json:"current_down"`
TotalUp uint64 `json:"total_up"`
TotalDown uint64 `json:"total_down"`
Delay *[30]float32 `json:"delay,omitempty"`
Delay *[30]float64 `json:"delay,omitempty"`
Up *[30]uint64 `json:"up,omitempty"`
Down *[30]uint64 `json:"down,omitempty"`
}
+1 -1
View File
@@ -10,7 +10,7 @@ type ServiceHistory struct {
UpdatedAt time.Time `gorm:"autoUpdateTime" json:"updated_at,omitempty"`
ServiceID uint64 `gorm:"index:idx_server_id_created_at_service_id_avg_delay" json:"service_id,omitempty"`
ServerID uint64 `gorm:"index:idx_server_id_created_at_service_id_avg_delay" json:"server_id,omitempty"`
AvgDelay float32 `gorm:"index:idx_server_id_created_at_service_id_avg_delay" json:"avg_delay,omitempty"` // 平均延迟,毫秒
AvgDelay float64 `gorm:"index:idx_server_id_created_at_service_id_avg_delay" json:"avg_delay,omitempty"` // 平均延迟,毫秒
Up uint64 `json:"up,omitempty"` // 检查状态良好计数
Down uint64 `json:"down,omitempty"` // 检查状态异常计数
Data string `json:"data,omitempty"`
+52 -6
View File
@@ -1,10 +1,56 @@
package model
// ServiceInfos 服务监控信息(兼容旧API)
type ServiceInfos struct {
ServiceID uint64 `json:"monitor_id"`
ServerID uint64 `json:"server_id"`
ServiceName string `json:"monitor_name"`
ServerName string `json:"server_name"`
CreatedAt []int64 `json:"created_at"`
AvgDelay []float32 `json:"avg_delay"`
ServiceID uint64 `json:"monitor_id"`
ServerID uint64 `json:"server_id"`
ServiceName string `json:"monitor_name"`
ServerName string `json:"server_name"`
DisplayIndex int `json:"display_index"` // 展示排序,越大越靠前
CreatedAt []int64 `json:"created_at"`
AvgDelay []float64 `json:"avg_delay"`
}
// DataPoint 数据点
type DataPoint struct {
Timestamp int64 `json:"ts"`
Delay float64 `json:"delay"`
Status uint8 `json:"status"` // 1=成功, 0=失败
}
// ServiceHistorySummary 服务历史统计摘要
type ServiceHistorySummary struct {
AvgDelay float64 `json:"avg_delay"`
UpPercent float32 `json:"up_percent"`
TotalUp uint64 `json:"total_up"`
TotalDown uint64 `json:"total_down"`
DataPoints []DataPoint `json:"data_points,omitempty"`
}
// ServerServiceStats 某服务器对某服务的统计
type ServerServiceStats struct {
ServerID uint64 `json:"server_id"`
ServerName string `json:"server_name,omitempty"`
Stats ServiceHistorySummary `json:"stats"`
}
// ServiceHistoryResponse 服务历史查询响应
type ServiceHistoryResponse struct {
ServiceID uint64 `json:"service_id"`
ServiceName string `json:"service_name,omitempty"`
Servers []ServerServiceStats `json:"servers"`
}
// ServerMetricsDataPoint 服务器指标数据点
type ServerMetricsDataPoint struct {
Timestamp int64 `json:"ts"`
Value float64 `json:"value"`
}
// ServerMetricsResponse 服务器指标历史查询响应
type ServerMetricsResponse struct {
ServerID uint64 `json:"server_id"`
ServerName string `json:"server_name,omitempty"`
Metric string `json:"metric"`
DataPoints []ServerMetricsDataPoint `json:"data_points"`
}
+3 -2
View File
@@ -10,8 +10,8 @@ type SettingForm struct {
InstallHost string `json:"install_host,omitempty" validate:"optional"`
CustomCode string `json:"custom_code,omitempty" validate:"optional"`
CustomCodeDashboard string `json:"custom_code_dashboard,omitempty" validate:"optional"`
WebRealIPHeader string `json:"web_real_ip_header,omitempty" validate:"optional"` // 前端真实IP
AgentRealIPHeader string `json:"agent_real_ip_header,omitempty" validate:"optional"` // Agent真实IP
WebRealIPHeader string `json:"web_real_ip_header,omitempty" validate:"optional"` // 前端真实IP
AgentRealIPHeader string `json:"agent_real_ip_header,omitempty" validate:"optional"` // Agent真实IP
UserTemplate string `json:"user_template,omitempty" validate:"optional"`
AgentTLS bool `json:"tls,omitempty" validate:"optional"`
@@ -42,4 +42,5 @@ type SettingResponse struct {
Version string `json:"version,omitempty"`
FrontendTemplates []FrontendTemplate `json:"frontend_templates,omitempty"`
TSDBEnabled bool `json:"tsdb_enabled"`
}