frostfs-node/pkg/local_object_storage/metabase/exists.go

213 lines
5.9 KiB
Go
Raw Normal View History

package meta
import (
"context"
"fmt"
"time"
objectV2 "git.frostfs.info/TrueCloudLab/frostfs-api-go/v2/object"
"git.frostfs.info/TrueCloudLab/frostfs-node/pkg/local_object_storage/internal/metaerr"
"git.frostfs.info/TrueCloudLab/frostfs-node/pkg/local_object_storage/util/logicerr"
"git.frostfs.info/TrueCloudLab/frostfs-observability/tracing"
apistatus "git.frostfs.info/TrueCloudLab/frostfs-sdk-go/client/status"
cid "git.frostfs.info/TrueCloudLab/frostfs-sdk-go/container/id"
objectSDK "git.frostfs.info/TrueCloudLab/frostfs-sdk-go/object"
oid "git.frostfs.info/TrueCloudLab/frostfs-sdk-go/object/id"
"go.etcd.io/bbolt"
"go.opentelemetry.io/otel/attribute"
"go.opentelemetry.io/otel/trace"
)
// ExistsPrm groups the parameters of Exists operation.
type ExistsPrm struct {
addr oid.Address
}
// ExistsRes groups the resulting values of Exists operation.
type ExistsRes struct {
exists bool
}
var ErrLackSplitInfo = logicerr.New("no split info on parent object")
// SetAddress is an Exists option to set object checked for existence.
func (p *ExistsPrm) SetAddress(addr oid.Address) {
p.addr = addr
}
// Exists returns the fact that the object is in the metabase.
func (p ExistsRes) Exists() bool {
return p.exists
}
// Exists returns ErrAlreadyRemoved if addr was marked as removed. Otherwise it
// returns true if addr is in primary index or false if it is not.
//
// Returns an error of type apistatus.ObjectAlreadyRemoved if object has been placed in graveyard.
// Returns the object.ErrObjectIsExpired if the object is presented but already expired.
func (db *DB) Exists(ctx context.Context, prm ExistsPrm) (res ExistsRes, err error) {
var (
startedAt = time.Now()
success = false
)
defer func() {
db.metrics.AddMethodDuration("Exists", time.Since(startedAt), success)
}()
_, span := tracing.StartSpanFromContext(ctx, "metabase.Exists",
trace.WithAttributes(
attribute.String("address", prm.addr.EncodeToString()),
))
defer span.End()
db.modeMtx.RLock()
defer db.modeMtx.RUnlock()
if db.mode.NoMetabase() {
return res, ErrDegradedMode
}
select {
case <-ctx.Done():
return res, ctx.Err()
default:
}
currEpoch := db.epochState.CurrentEpoch()
err = db.boltDB.View(func(tx *bbolt.Tx) error {
res.exists, err = db.exists(tx, prm.addr, currEpoch)
return err
})
success = err == nil
return res, metaerr.Wrap(err)
}
func (db *DB) exists(tx *bbolt.Tx, addr oid.Address, currEpoch uint64) (exists bool, err error) {
// check graveyard and object expiration first
switch objectStatus(tx, addr, currEpoch) {
case 1:
return false, logicerr.Wrap(new(apistatus.ObjectNotFound))
case 2:
return false, logicerr.Wrap(new(apistatus.ObjectAlreadyRemoved))
case 3:
return false, ErrObjectIsExpired
}
objKey := objectKey(addr.Object(), make([]byte, objectKeySize))
cnr := addr.Container()
key := make([]byte, bucketKeySize)
// if graveyard is empty, then check if object exists in primary bucket
if inBucket(tx, primaryBucketName(cnr, key), objKey) {
return true, nil
}
// if primary bucket is empty, then check if object exists in parent bucket
if inBucket(tx, parentBucketName(cnr, key), objKey) {
splitInfo, err := getSplitInfo(tx, cnr, objKey)
if err != nil {
return false, err
}
return false, logicerr.Wrap(objectSDK.NewSplitInfoError(splitInfo))
}
// if parent bucket is empty, then check if object exists in typed buckets
return firstIrregularObjectType(tx, cnr, objKey) != objectSDK.TypeRegular, nil
}
// objectStatus returns:
// - 0 if object is available;
// - 1 if object with GC mark;
// - 2 if object is covered with tombstone;
// - 3 if object is expired.
func objectStatus(tx *bbolt.Tx, addr oid.Address, currEpoch uint64) uint8 {
// locked object could not be removed/marked with GC/expired
if objectLocked(tx, addr.Container(), addr.Object()) {
return 0
}
// we check only if the object is expired in the current
// epoch since it is considered the only corner case: the
// GC is expected to collect all the objects that have
// expired previously for less than the one epoch duration
expired := isExpiredWithAttribute(tx, objectV2.SysAttributeExpEpoch, addr, currEpoch)
if !expired {
expired = isExpiredWithAttribute(tx, objectV2.SysAttributeExpEpochNeoFS, addr, currEpoch)
}
if expired {
return 3
}
graveyardBkt := tx.Bucket(graveyardBucketName)
garbageBkt := tx.Bucket(garbageBucketName)
addrKey := addressKey(addr, make([]byte, addressKeySize))
return inGraveyardWithKey(addrKey, graveyardBkt, garbageBkt)
}
[#1516] metabase: Cache graveyard buckets in `ListWithCursor` ``` name old time/op new time/op delta ListWithCursor/1_item-8 6.40µs ±13% 6.45µs ±14% ~ (p=0.739 n=10+10) ListWithCursor/10_items-8 30.9µs ±21% 20.9µs ±17% -32.49% (p=0.000 n=10+10) ListWithCursor/100_items-8 274µs ±27% 153µs ±12% -44.09% (p=0.000 n=10+10) name old alloc/op new alloc/op delta ListWithCursor/1_item-8 2.26kB ± 0% 2.31kB ± 0% +2.46% (p=0.000 n=10+10) ListWithCursor/10_items-8 10.8kB ± 0% 6.9kB ± 0% -36.07% (p=0.000 n=8+8) ListWithCursor/100_items-8 96.8kB ± 0% 53.3kB ± 0% -44.98% (p=0.000 n=10+10) name old allocs/op new allocs/op delta ListWithCursor/1_item-8 39.0 ± 0% 40.0 ± 0% +2.56% (p=0.000 n=10+10) ListWithCursor/10_items-8 192 ± 0% 121 ± 0% -36.98% (p=0.000 n=10+10) ListWithCursor/100_items-8 1.72k ± 0% 0.93k ± 0% -45.93% (p=0.000 n=10+10) ``` Signed-off-by: Evgenii Stratonikov <evgeniy@nspcc.ru> name old time/op new time/op delta ListWithCursor/1_item-8 5.23µs ±19% 5.26µs ±15% ~ (p=0.853 n=10+10) ListWithCursor/10_items-8 27.2µs ±15% 18.0µs ±19% -33.80% (p=0.000 n=10+10) ListWithCursor/100_items-8 250µs ±13% 139µs ±15% -44.27% (p=0.000 n=10+10) name old alloc/op new alloc/op delta ListWithCursor/1_item-8 1.99kB ± 0% 2.04kB ± 0% +2.82% (p=0.000 n=8+8) ListWithCursor/10_items-8 10.3kB ± 0% 6.4kB ± 0% -37.83% (p=0.000 n=8+10) ListWithCursor/100_items-8 93.9kB ± 0% 50.4kB ± 0% -46.37% (p=0.000 n=10+10) name old allocs/op new allocs/op delta ListWithCursor/1_item-8 35.0 ± 0% 36.0 ± 0% +2.86% (p=0.000 n=10+10) ListWithCursor/10_items-8 184 ± 0% 113 ± 0% -38.59% (p=0.000 n=10+10) ListWithCursor/100_items-8 1.67k ± 0% 0.88k ± 0% -47.29% (p=0.000 n=10+10) ``` Signed-off-by: Evgenii Stratonikov <evgeniy@nspcc.ru>
2022-06-14 16:09:06 +00:00
func inGraveyardWithKey(addrKey []byte, graveyard, garbageBCK *bbolt.Bucket) uint8 {
if graveyard == nil {
// incorrect metabase state, does not make
// sense to check garbage bucket
return 0
}
val := graveyard.Get(addrKey)
if val == nil {
if garbageBCK == nil {
// incorrect node state
return 0
}
val = garbageBCK.Get(addrKey)
if val != nil {
// object has been marked with GC
return 1
}
// neither in the graveyard
// nor was marked with GC mark
return 0
}
// object in the graveyard
return 2
}
// inBucket checks if key <key> is present in bucket <name>.
func inBucket(tx *bbolt.Tx, name, key []byte) bool {
bkt := tx.Bucket(name)
if bkt == nil {
return false
}
// using `get` as `exists`: https://github.com/boltdb/bolt/issues/321
val := bkt.Get(key)
return len(val) != 0
}
// getSplitInfo returns SplitInfo structure from root index. Returns error
// if there is no `key` record in root index.
func getSplitInfo(tx *bbolt.Tx, cnr cid.ID, key []byte) (*objectSDK.SplitInfo, error) {
bucketName := rootBucketName(cnr, make([]byte, bucketKeySize))
rawSplitInfo := getFromBucket(tx, bucketName, key)
if len(rawSplitInfo) == 0 {
return nil, ErrLackSplitInfo
}
splitInfo := objectSDK.NewSplitInfo()
err := splitInfo.Unmarshal(rawSplitInfo)
if err != nil {
return nil, fmt.Errorf("can't unmarshal split info from root index: %w", err)
}
return splitInfo, nil
}