Files
nezha_domains/model/service.go
T
奶爸 e61772e858 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>
2026-02-15 13:13:33 +08:00

142 lines
3.5 KiB
Go

package model
import (
"fmt"
"log"
"github.com/goccy/go-json"
"github.com/robfig/cron/v3"
"gorm.io/gorm"
pb "github.com/nezhahq/nezha/proto"
)
const (
_ = iota
TaskTypeHTTPGet
TaskTypeICMPPing
TaskTypeTCPPing
TaskTypeCommand
TaskTypeTerminal
TaskTypeUpgrade
TaskTypeKeepalive
TaskTypeTerminalGRPC
TaskTypeNAT
TaskTypeReportHostInfoDeprecated
TaskTypeFM
TaskTypeReportConfig
TaskTypeApplyConfig
)
type TerminalTask struct {
StreamID string
}
type TaskNAT struct {
StreamID string
Host string
}
type TaskFM struct {
StreamID string
}
const (
ServiceCoverAll = iota
ServiceCoverIgnoreAll
)
type Service struct {
Common
Name string `json:"name"`
Type uint8 `json:"type"`
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"`
EnableTriggerTask bool `gorm:"default: false" json:"enable_trigger_task,omitempty"`
EnableShowInService bool `gorm:"default: false" json:"enable_show_in_service,omitempty"`
FailTriggerTasksRaw string `gorm:"default:'[]'" json:"-"`
RecoverTriggerTasksRaw string `gorm:"default:'[]'" json:"-"`
FailTriggerTasks []uint64 `gorm:"-" json:"fail_trigger_tasks"` // 失败时执行的触发任务id
RecoverTriggerTasks []uint64 `gorm:"-" json:"recover_trigger_tasks"` // 恢复时执行的触发任务id
MinLatency float32 `json:"min_latency"`
MaxLatency float32 `json:"max_latency"`
LatencyNotify bool `json:"latency_notify,omitempty"`
SkipServers map[uint64]bool `gorm:"-" json:"skip_servers"`
CronJobID cron.EntryID `gorm:"-" json:"-"`
}
func (m *Service) PB() *pb.Task {
return &pb.Task{
Id: m.ID,
Type: uint64(m.Type),
Data: m.Target,
}
}
// CronSpec 返回服务监控请求间隔对应的 cron 表达式
func (m *Service) CronSpec() string {
if m.Duration == 0 {
// 默认间隔 30 秒
m.Duration = 30
}
return fmt.Sprintf("@every %ds", m.Duration)
}
func (m *Service) BeforeSave(tx *gorm.DB) error {
if data, err := json.Marshal(m.SkipServers); err != nil {
return err
} else {
m.SkipServersRaw = string(data)
}
if data, err := json.Marshal(m.FailTriggerTasks); err != nil {
return err
} else {
m.FailTriggerTasksRaw = string(data)
}
if data, err := json.Marshal(m.RecoverTriggerTasks); err != nil {
return err
} else {
m.RecoverTriggerTasksRaw = string(data)
}
return nil
}
func (m *Service) AfterFind(tx *gorm.DB) error {
m.SkipServers = make(map[uint64]bool)
if err := json.Unmarshal([]byte(m.SkipServersRaw), &m.SkipServers); err != nil {
log.Println("NEZHA>> Service.AfterFind:", err)
return nil
}
// 加载触发任务列表
if err := json.Unmarshal([]byte(m.FailTriggerTasksRaw), &m.FailTriggerTasks); err != nil {
return err
}
if err := json.Unmarshal([]byte(m.RecoverTriggerTasksRaw), &m.RecoverTriggerTasks); err != nil {
return err
}
return nil
}
// IsServiceSentinelNeeded 判断该任务类型是否需要进行服务监控 需要则返回true
func IsServiceSentinelNeeded(t uint64) bool {
switch t {
case TaskTypeCommand, TaskTypeTerminalGRPC, TaskTypeUpgrade,
TaskTypeKeepalive, TaskTypeNAT, TaskTypeFM,
TaskTypeReportConfig, TaskTypeApplyConfig:
return false
default:
return true
}
}