Files
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

118 lines
2.5 KiB
Go

package tsdb
import (
"fmt"
"log"
"path/filepath"
"sync"
"time"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/storage"
)
// TSDB 封装 VictoriaMetrics 存储
type TSDB struct {
storage *storage.Storage
config *Config
mu sync.RWMutex
closed bool
writer *bufferedWriter
}
// InitGlobalSettings 初始化 VictoriaMetrics 包级别的全局设置。
// 这些设置是进程级别的,应在 Open() 之前调用且只调用一次。
func InitGlobalSettings(config *Config) {
memBytes := int(config.MaxMemoryMB * 1024 * 1024)
storage.SetTSIDCacheSize(memBytes * 35 / 100)
storage.SetMetricNameCacheSize(memBytes * 10 / 100)
storage.SetTagFiltersCacheSize(memBytes * 5 / 100)
storage.SetMetadataStorageSize(memBytes * 1 / 100)
storage.SetDedupInterval(config.DedupInterval)
storage.SetFreeDiskSpaceLimit(config.MinFreeDiskSpaceBytes())
storage.SetDataFlushInterval(5 * time.Second)
}
// Open 打开或创建 TSDB 存储
func Open(config *Config) (*TSDB, error) {
if config == nil {
config = DefaultConfig()
}
config.Validate()
dataPath := config.DataPath
if !filepath.IsAbs(dataPath) {
absPath, err := filepath.Abs(dataPath)
if err != nil {
return nil, fmt.Errorf("failed to get absolute path: %w", err)
}
dataPath = absPath
}
InitGlobalSettings(config)
opts := storage.OpenOptions{
Retention: time.Duration(config.RetentionDays) * 24 * time.Hour,
}
stor := storage.MustOpenStorage(dataPath, opts)
db := &TSDB{
storage: stor,
config: config,
}
db.writer = newBufferedWriter(db, config.WriteBufferSize, config.WriteBufferFlushInterval)
log.Printf("NEZHA>> TSDB opened at %s, retention: %d days, min free disk: %.1f GB, max memory: %d MB",
dataPath, config.RetentionDays, config.MinFreeDiskSpaceGB, config.MaxMemoryMB)
return db, nil
}
// Close 关闭 TSDB 存储
func (db *TSDB) Close() error {
db.mu.Lock()
defer db.mu.Unlock()
if db.closed {
return nil
}
if db.writer != nil {
db.writer.stop()
}
db.storage.MustClose()
db.closed = true
log.Println("NEZHA>> TSDB closed")
return nil
}
// Storage 返回底层存储对象(用于高级查询)
func (db *TSDB) Storage() *storage.Storage {
return db.storage
}
// Config 返回配置
func (db *TSDB) Config() *Config {
return db.config
}
// IsClosed 检查是否已关闭
func (db *TSDB) IsClosed() bool {
db.mu.RLock()
defer db.mu.RUnlock()
return db.closed
}
// Flush 强制刷盘(主要用于测试)
func (db *TSDB) Flush() {
if db.writer != nil {
db.writer.flush()
}
db.storage.DebugFlush()
}