storj/cmd/segment-reaper/detect.go
Ivan Fraixedes 7288d01781
cmd/segment-reaper: several refactorings (#3637)
* Move the observer implementation and the type definitions related with
  it and helper functions to its own file.
* Cluster struct type is used as a key for a ObjectsMap type.
  Observer struct type has a field of ObjectsMap.
  Cluster has a field for project ID.
  Observer processSegment method uses its ObjectMap field for tracking
  objects.

  However Observer processSegment clears the map once the projectID
  diverges from the one kept in the Observer lastProjectID field, meaning
  that it isn't needed to keep the projectID as part of the ObjectMap key.

  For this reason, ObjectMap can use as a key just only the bucket name
  and Cluster struct isn't needed.

  Because of such change, the ObjectMap type has been renamed to a more
  descriptive name.
* Make the types defined for this specific package not being exported.
* Create a constructor function for observer to encapsulate the map
  allocation.
* Don't throw away the entirely buckets objects map when an empty one
  is used to reuse part of the allocations.

  Encapsulate the clearing up logic into a method.
* Make the analyzeProject function to be a method of observer.
2019-11-27 10:28:43 +01:00

94 lines
2.2 KiB
Go

// Copyright (C) 2019 Storj Labs, Inc.
// See LICENSE for copying information.
package main
import (
"encoding/csv"
"os"
"github.com/spf13/cobra"
"github.com/zeebo/errs"
"go.uber.org/zap"
"storj.io/storj/pkg/cfgstruct"
"storj.io/storj/pkg/process"
"storj.io/storj/satellite/metainfo"
)
const maxNumOfSegments = byte(64)
var (
detectCmd = &cobra.Command{
Use: "detect",
Short: "Detects zombie segments in DB",
Args: cobra.OnlyValidArgs,
RunE: cmdDetect,
}
detectCfg struct {
DatabaseURL string `help:"the database connection string to use" default:"postgres://"`
From string `help:"begin of date range for detecting zombie segments" default:""`
To string `help:"end of date range for detecting zombie segments" default:""`
File string `help:"location of file with report" default:"zombie-segments.csv"`
}
)
func init() {
rootCmd.AddCommand(detectCmd)
defaults := cfgstruct.DefaultsFlag(rootCmd)
process.Bind(detectCmd, &detectCfg, defaults)
}
func cmdDetect(cmd *cobra.Command, args []string) (err error) {
ctx, _ := process.Ctx(cmd)
log := zap.L()
db, err := metainfo.NewStore(log.Named("pointerdb"), detectCfg.DatabaseURL)
if err != nil {
return errs.New("error connecting database: %+v", err)
}
defer func() {
err = errs.Combine(err, db.Close())
}()
file, err := os.Create(detectCfg.File)
if err != nil {
return errs.New("error creating result file: %+v", err)
}
defer func() {
err = errs.Combine(err, file.Close())
}()
writer := csv.NewWriter(file)
defer func() {
writer.Flush()
err = errs.Combine(err, writer.Error())
}()
headers := []string{
"ProjectID",
"SegmentIndex",
"Bucket",
"EncodedEncryptedPath",
"CreationDate",
}
err = writer.Write(headers)
if err != nil {
return err
}
observer := newObserver(db, writer)
err = metainfo.IterateDatabase(ctx, db, observer)
if err != nil {
return err
}
log.Info("number of inline segments", zap.Int("segments", observer.inlineSegments))
log.Info("number of last inline segments", zap.Int("segments", observer.lastInlineSegments))
log.Info("number of remote segments", zap.Int("segments", observer.remoteSegments))
return nil
}