Add more size intervals to obj size histogram (#18772)

New intervals:
[1024B, 64KiB)
[64KiB, 256KiB)
[256KiB, 512KiB)
[512KiB, 1MiB)

The new intervals helps us see object size distribution with higher
resolution for the interval [1024B, 1MiB).

cmd/data-usage-cache.go

@@ -1,4 +1,4 @@
-// Copyright (c) 2015-2021 MinIO, Inc.
+// Copyright (c) 2015-2023 MinIO, Inc.
 //
 // This file is part of MinIO Object Storage stack
 //
@@ -32,6 +32,7 @@ import (
 	"time"
 
 	"github.com/cespare/xxhash/v2"
+	"github.com/dustin/go-humanize"
 	"github.com/klauspost/compress/zstd"
 	"github.com/minio/madmin-go/v3"
 	"github.com/minio/minio/internal/bucket/lifecycle"
@@ -46,6 +47,10 @@ import (
 // dataUsageHash is the hash type used.
 type dataUsageHash string
 
+// sizeHistogramV1 is size histogram V1, which has fewer intervals esp. between
+// 1024B and 1MiB.
+type sizeHistogramV1 [dataUsageBucketLenV1]uint64
+
 // sizeHistogram is a size histogram.
 type sizeHistogram [dataUsageBucketLen]uint64
 
@@ -204,8 +209,8 @@ func (r *replicationAllStats) clone() *replicationAllStats {
 	return &dst
 }
 
-//msgp:encode ignore dataUsageEntryV2 dataUsageEntryV3 dataUsageEntryV4 dataUsageEntryV5 dataUsageEntryV6
+//msgp:encode ignore dataUsageEntryV2 dataUsageEntryV3 dataUsageEntryV4 dataUsageEntryV5 dataUsageEntryV6 dataUsageEntryV7
-//msgp:marshal ignore dataUsageEntryV2 dataUsageEntryV3 dataUsageEntryV4 dataUsageEntryV5 dataUsageEntryV6
+//msgp:marshal ignore dataUsageEntryV2 dataUsageEntryV3 dataUsageEntryV4 dataUsageEntryV5 dataUsageEntryV6 dataUsageEntryV7
 
 //msgp:tuple dataUsageEntryV2
 type dataUsageEntryV2 struct {
@@ -263,14 +268,28 @@ type dataUsageEntryV6 struct {
 	Compacted        bool
 }
 
+type dataUsageEntryV7 struct {
+	Children dataUsageHashMap `msg:"ch"`
+	// These fields do no include any children.
+	Size             int64                `msg:"sz"`
+	Objects          uint64               `msg:"os"`
+	Versions         uint64               `msg:"vs"` // Versions that are not delete markers.
+	DeleteMarkers    uint64               `msg:"dms"`
+	ObjSizes         sizeHistogramV1      `msg:"szs"`
+	ObjVersions      versionsHistogram    `msg:"vh"`
+	ReplicationStats *replicationAllStats `msg:"rs,omitempty"`
+	AllTierStats     *allTierStats        `msg:"ats,omitempty"`
+	Compacted        bool                 `msg:"c"`
+}
+
 // dataUsageCache contains a cache of data usage entries latest version.
 type dataUsageCache struct {
 	Info  dataUsageCacheInfo
 	Cache map[string]dataUsageEntry
 }
 
-//msgp:encode ignore dataUsageCacheV2 dataUsageCacheV3 dataUsageCacheV4 dataUsageCacheV5 dataUsageCacheV6
+//msgp:encode ignore dataUsageCacheV2 dataUsageCacheV3 dataUsageCacheV4 dataUsageCacheV5 dataUsageCacheV6 dataUsageCacheV7
-//msgp:marshal ignore dataUsageCacheV2 dataUsageCacheV3 dataUsageCacheV4 dataUsageCacheV5 dataUsageCacheV6
+//msgp:marshal ignore dataUsageCacheV2 dataUsageCacheV3 dataUsageCacheV4 dataUsageCacheV5 dataUsageCacheV6 dataUsageCacheV7
 
 // dataUsageCacheV2 contains a cache of data usage entries version 2.
 type dataUsageCacheV2 struct {
@@ -302,6 +321,12 @@ type dataUsageCacheV6 struct {
 	Cache map[string]dataUsageEntryV6
 }
 
+// dataUsageCacheV7 contains a cache of data usage entries version 7.
+type dataUsageCacheV7 struct {
+	Info  dataUsageCacheInfo
+	Cache map[string]dataUsageEntryV7
+}
+
 //msgp:ignore dataUsageEntryInfo
 type dataUsageEntryInfo struct {
 	Name   string
@@ -750,11 +775,42 @@ func (h *sizeHistogram) add(size int64) {
 	}
 }
 
+// mergeV1 is used to migrate data usage cache from sizeHistogramV1 to
+// sizeHistogram
+func (h *sizeHistogram) mergeV1(v sizeHistogramV1) {
+	var oidx, nidx int
+	for oidx < len(v) {
+		intOld, intNew := ObjectsHistogramIntervalsV1[oidx], ObjectsHistogramIntervals[nidx]
+		// skip intervals that aren't common to both histograms
+		if intOld.start != intNew.start || intOld.end != intNew.end {
+			nidx++
+			continue
+		}
+		h[nidx] += v[oidx]
+		oidx++
+		nidx++
+	}
+}
+
 // toMap returns the map to a map[string]uint64.
 func (h *sizeHistogram) toMap() map[string]uint64 {
 	res := make(map[string]uint64, dataUsageBucketLen)
+	var splCount uint64
 	for i, count := range h {
-		res[ObjectsHistogramIntervals[i].name] = count
+		szInt := ObjectsHistogramIntervals[i]
+		switch {
+		case humanize.KiByte == szInt.start && szInt.end == humanize.MiByte-1:
+			// spl interval: [1024B, 1MiB)
+			res[szInt.name] = splCount
+		case humanize.KiByte <= szInt.start && szInt.end <= humanize.MiByte-1:
+			// intervals that fall within the spl interval above; they
+			// appear earlier in this array of intervals, see
+			// ObjectsHistogramIntervals
+			splCount += count
+			fallthrough
+		default:
+			res[szInt.name] = count
+		}
 	}
 	return res
 }
@@ -1027,7 +1083,8 @@ func (d *dataUsageCache) save(ctx context.Context, store objectIO, name string)
 // Bumping the cache version will drop data from previous versions
 // and write new data with the new version.
 const (
-	dataUsageCacheVerCurrent = 7
+	dataUsageCacheVerCurrent = 8
+	dataUsageCacheVerV7      = 7
 	dataUsageCacheVerV6      = 6
 	dataUsageCacheVerV5      = 5
 	dataUsageCacheVerV4      = 4
@@ -1275,6 +1332,34 @@ func (d *dataUsageCache) deserialize(r io.Reader) error {
 			}
 			d.Cache[k] = due
 		}
+		return nil
+	case dataUsageCacheVerV7:
+		// Zstd compressed.
+		dec, err := zstd.NewReader(r, zstd.WithDecoderConcurrency(2))
+		if err != nil {
+			return err
+		}
+		defer dec.Close()
+		dold := &dataUsageCacheV7{}
+		if err = dold.DecodeMsg(msgp.NewReader(dec)); err != nil {
+			return err
+		}
+		d.Info = dold.Info
+		d.Cache = make(map[string]dataUsageEntry, len(dold.Cache))
+		for k, v := range dold.Cache {
+			var szHist sizeHistogram
+			szHist.mergeV1(v.ObjSizes)
+			d.Cache[k] = dataUsageEntry{
+				Children:         v.Children,
+				Size:             v.Size,
+				Objects:          v.Objects,
+				Versions:         v.Versions,
+				ObjSizes:         szHist,
+				ReplicationStats: v.ReplicationStats,
+				Compacted:        v.Compacted,
+			}
+		}
+
 		return nil
 	case dataUsageCacheVerCurrent:
 		// Zstd compressed.

cmd/data-usage-cache_gen.go

@@ -1480,6 +1480,149 @@ func (z *dataUsageCacheV6) Msgsize() (s int) {
 	return
 }
 
+// DecodeMsg implements msgp.Decodable
+func (z *dataUsageCacheV7) DecodeMsg(dc *msgp.Reader) (err error) {
+	var field []byte
+	_ = field
+	var zb0001 uint32
+	zb0001, err = dc.ReadMapHeader()
+	if err != nil {
+		err = msgp.WrapError(err)
+		return
+	}
+	for zb0001 > 0 {
+		zb0001--
+		field, err = dc.ReadMapKeyPtr()
+		if err != nil {
+			err = msgp.WrapError(err)
+			return
+		}
+		switch msgp.UnsafeString(field) {
+		case "Info":
+			err = z.Info.DecodeMsg(dc)
+			if err != nil {
+				err = msgp.WrapError(err, "Info")
+				return
+			}
+		case "Cache":
+			var zb0002 uint32
+			zb0002, err = dc.ReadMapHeader()
+			if err != nil {
+				err = msgp.WrapError(err, "Cache")
+				return
+			}
+			if z.Cache == nil {
+				z.Cache = make(map[string]dataUsageEntryV7, zb0002)
+			} else if len(z.Cache) > 0 {
+				for key := range z.Cache {
+					delete(z.Cache, key)
+				}
+			}
+			for zb0002 > 0 {
+				zb0002--
+				var za0001 string
+				var za0002 dataUsageEntryV7
+				za0001, err = dc.ReadString()
+				if err != nil {
+					err = msgp.WrapError(err, "Cache")
+					return
+				}
+				err = za0002.DecodeMsg(dc)
+				if err != nil {
+					err = msgp.WrapError(err, "Cache", za0001)
+					return
+				}
+				z.Cache[za0001] = za0002
+			}
+		default:
+			err = dc.Skip()
+			if err != nil {
+				err = msgp.WrapError(err)
+				return
+			}
+		}
+	}
+	return
+}
+
+// UnmarshalMsg implements msgp.Unmarshaler
+func (z *dataUsageCacheV7) UnmarshalMsg(bts []byte) (o []byte, err error) {
+	var field []byte
+	_ = field
+	var zb0001 uint32
+	zb0001, bts, err = msgp.ReadMapHeaderBytes(bts)
+	if err != nil {
+		err = msgp.WrapError(err)
+		return
+	}
+	for zb0001 > 0 {
+		zb0001--
+		field, bts, err = msgp.ReadMapKeyZC(bts)
+		if err != nil {
+			err = msgp.WrapError(err)
+			return
+		}
+		switch msgp.UnsafeString(field) {
+		case "Info":
+			bts, err = z.Info.UnmarshalMsg(bts)
+			if err != nil {
+				err = msgp.WrapError(err, "Info")
+				return
+			}
+		case "Cache":
+			var zb0002 uint32
+			zb0002, bts, err = msgp.ReadMapHeaderBytes(bts)
+			if err != nil {
+				err = msgp.WrapError(err, "Cache")
+				return
+			}
+			if z.Cache == nil {
+				z.Cache = make(map[string]dataUsageEntryV7, zb0002)
+			} else if len(z.Cache) > 0 {
+				for key := range z.Cache {
+					delete(z.Cache, key)
+				}
+			}
+			for zb0002 > 0 {
+				var za0001 string
+				var za0002 dataUsageEntryV7
+				zb0002--
+				za0001, bts, err = msgp.ReadStringBytes(bts)
+				if err != nil {
+					err = msgp.WrapError(err, "Cache")
+					return
+				}
+				bts, err = za0002.UnmarshalMsg(bts)
+				if err != nil {
+					err = msgp.WrapError(err, "Cache", za0001)
+					return
+				}
+				z.Cache[za0001] = za0002
+			}
+		default:
+			bts, err = msgp.Skip(bts)
+			if err != nil {
+				err = msgp.WrapError(err)
+				return
+			}
+		}
+	}
+	o = bts
+	return
+}
+
+// Msgsize returns an upper bound estimate of the number of bytes occupied by the serialized message
+func (z *dataUsageCacheV7) Msgsize() (s int) {
+	s = 1 + 5 + z.Info.Msgsize() + 6 + msgp.MapHeaderSize
+	if z.Cache != nil {
+		for za0001, za0002 := range z.Cache {
+			_ = za0002
+			s += msgp.StringPrefixSize + len(za0001) + za0002.Msgsize()
+		}
+	}
+	return
+}
+
 // DecodeMsg implements msgp.Decodable
 func (z *dataUsageEntry) DecodeMsg(dc *msgp.Reader) (err error) {
 	var field []byte
@@ -2684,6 +2827,297 @@ func (z *dataUsageEntryV6) Msgsize() (s int) {
 	return
 }
 
+// DecodeMsg implements msgp.Decodable
+func (z *dataUsageEntryV7) DecodeMsg(dc *msgp.Reader) (err error) {
+	var field []byte
+	_ = field
+	var zb0001 uint32
+	zb0001, err = dc.ReadMapHeader()
+	if err != nil {
+		err = msgp.WrapError(err)
+		return
+	}
+	for zb0001 > 0 {
+		zb0001--
+		field, err = dc.ReadMapKeyPtr()
+		if err != nil {
+			err = msgp.WrapError(err)
+			return
+		}
+		switch msgp.UnsafeString(field) {
+		case "ch":
+			err = z.Children.DecodeMsg(dc)
+			if err != nil {
+				err = msgp.WrapError(err, "Children")
+				return
+			}
+		case "sz":
+			z.Size, err = dc.ReadInt64()
+			if err != nil {
+				err = msgp.WrapError(err, "Size")
+				return
+			}
+		case "os":
+			z.Objects, err = dc.ReadUint64()
+			if err != nil {
+				err = msgp.WrapError(err, "Objects")
+				return
+			}
+		case "vs":
+			z.Versions, err = dc.ReadUint64()
+			if err != nil {
+				err = msgp.WrapError(err, "Versions")
+				return
+			}
+		case "dms":
+			z.DeleteMarkers, err = dc.ReadUint64()
+			if err != nil {
+				err = msgp.WrapError(err, "DeleteMarkers")
+				return
+			}
+		case "szs":
+			var zb0002 uint32
+			zb0002, err = dc.ReadArrayHeader()
+			if err != nil {
+				err = msgp.WrapError(err, "ObjSizes")
+				return
+			}
+			if zb0002 != uint32(dataUsageBucketLenV1) {
+				err = msgp.ArrayError{Wanted: uint32(dataUsageBucketLenV1), Got: zb0002}
+				return
+			}
+			for za0001 := range z.ObjSizes {
+				z.ObjSizes[za0001], err = dc.ReadUint64()
+				if err != nil {
+					err = msgp.WrapError(err, "ObjSizes", za0001)
+					return
+				}
+			}
+		case "vh":
+			var zb0003 uint32
+			zb0003, err = dc.ReadArrayHeader()
+			if err != nil {
+				err = msgp.WrapError(err, "ObjVersions")
+				return
+			}
+			if zb0003 != uint32(dataUsageVersionLen) {
+				err = msgp.ArrayError{Wanted: uint32(dataUsageVersionLen), Got: zb0003}
+				return
+			}
+			for za0002 := range z.ObjVersions {
+				z.ObjVersions[za0002], err = dc.ReadUint64()
+				if err != nil {
+					err = msgp.WrapError(err, "ObjVersions", za0002)
+					return
+				}
+			}
+		case "rs":
+			if dc.IsNil() {
+				err = dc.ReadNil()
+				if err != nil {
+					err = msgp.WrapError(err, "ReplicationStats")
+					return
+				}
+				z.ReplicationStats = nil
+			} else {
+				if z.ReplicationStats == nil {
+					z.ReplicationStats = new(replicationAllStats)
+				}
+				err = z.ReplicationStats.DecodeMsg(dc)
+				if err != nil {
+					err = msgp.WrapError(err, "ReplicationStats")
+					return
+				}
+			}
+		case "ats":
+			if dc.IsNil() {
+				err = dc.ReadNil()
+				if err != nil {
+					err = msgp.WrapError(err, "AllTierStats")
+					return
+				}
+				z.AllTierStats = nil
+			} else {
+				if z.AllTierStats == nil {
+					z.AllTierStats = new(allTierStats)
+				}
+				err = z.AllTierStats.DecodeMsg(dc)
+				if err != nil {
+					err = msgp.WrapError(err, "AllTierStats")
+					return
+				}
+			}
+		case "c":
+			z.Compacted, err = dc.ReadBool()
+			if err != nil {
+				err = msgp.WrapError(err, "Compacted")
+				return
+			}
+		default:
+			err = dc.Skip()
+			if err != nil {
+				err = msgp.WrapError(err)
+				return
+			}
+		}
+	}
+	return
+}
+
+// UnmarshalMsg implements msgp.Unmarshaler
+func (z *dataUsageEntryV7) UnmarshalMsg(bts []byte) (o []byte, err error) {
+	var field []byte
+	_ = field
+	var zb0001 uint32
+	zb0001, bts, err = msgp.ReadMapHeaderBytes(bts)
+	if err != nil {
+		err = msgp.WrapError(err)
+		return
+	}
+	for zb0001 > 0 {
+		zb0001--
+		field, bts, err = msgp.ReadMapKeyZC(bts)
+		if err != nil {
+			err = msgp.WrapError(err)
+			return
+		}
+		switch msgp.UnsafeString(field) {
+		case "ch":
+			bts, err = z.Children.UnmarshalMsg(bts)
+			if err != nil {
+				err = msgp.WrapError(err, "Children")
+				return
+			}
+		case "sz":
+			z.Size, bts, err = msgp.ReadInt64Bytes(bts)
+			if err != nil {
+				err = msgp.WrapError(err, "Size")
+				return
+			}
+		case "os":
+			z.Objects, bts, err = msgp.ReadUint64Bytes(bts)
+			if err != nil {
+				err = msgp.WrapError(err, "Objects")
+				return
+			}
+		case "vs":
+			z.Versions, bts, err = msgp.ReadUint64Bytes(bts)
+			if err != nil {
+				err = msgp.WrapError(err, "Versions")
+				return
+			}
+		case "dms":
+			z.DeleteMarkers, bts, err = msgp.ReadUint64Bytes(bts)
+			if err != nil {
+				err = msgp.WrapError(err, "DeleteMarkers")
+				return
+			}
+		case "szs":
+			var zb0002 uint32
+			zb0002, bts, err = msgp.ReadArrayHeaderBytes(bts)
+			if err != nil {
+				err = msgp.WrapError(err, "ObjSizes")
+				return
+			}
+			if zb0002 != uint32(dataUsageBucketLenV1) {
+				err = msgp.ArrayError{Wanted: uint32(dataUsageBucketLenV1), Got: zb0002}
+				return
+			}
+			for za0001 := range z.ObjSizes {
+				z.ObjSizes[za0001], bts, err = msgp.ReadUint64Bytes(bts)
+				if err != nil {
+					err = msgp.WrapError(err, "ObjSizes", za0001)
+					return
+				}
+			}
+		case "vh":
+			var zb0003 uint32
+			zb0003, bts, err = msgp.ReadArrayHeaderBytes(bts)
+			if err != nil {
+				err = msgp.WrapError(err, "ObjVersions")
+				return
+			}
+			if zb0003 != uint32(dataUsageVersionLen) {
+				err = msgp.ArrayError{Wanted: uint32(dataUsageVersionLen), Got: zb0003}
+				return
+			}
+			for za0002 := range z.ObjVersions {
+				z.ObjVersions[za0002], bts, err = msgp.ReadUint64Bytes(bts)
+				if err != nil {
+					err = msgp.WrapError(err, "ObjVersions", za0002)
+					return
+				}
+			}
+		case "rs":
+			if msgp.IsNil(bts) {
+				bts, err = msgp.ReadNilBytes(bts)
+				if err != nil {
+					return
+				}
+				z.ReplicationStats = nil
+			} else {
+				if z.ReplicationStats == nil {
+					z.ReplicationStats = new(replicationAllStats)
+				}
+				bts, err = z.ReplicationStats.UnmarshalMsg(bts)
+				if err != nil {
+					err = msgp.WrapError(err, "ReplicationStats")
+					return
+				}
+			}
+		case "ats":
+			if msgp.IsNil(bts) {
+				bts, err = msgp.ReadNilBytes(bts)
+				if err != nil {
+					return
+				}
+				z.AllTierStats = nil
+			} else {
+				if z.AllTierStats == nil {
+					z.AllTierStats = new(allTierStats)
+				}
+				bts, err = z.AllTierStats.UnmarshalMsg(bts)
+				if err != nil {
+					err = msgp.WrapError(err, "AllTierStats")
+					return
+				}
+			}
+		case "c":
+			z.Compacted, bts, err = msgp.ReadBoolBytes(bts)
+			if err != nil {
+				err = msgp.WrapError(err, "Compacted")
+				return
+			}
+		default:
+			bts, err = msgp.Skip(bts)
+			if err != nil {
+				err = msgp.WrapError(err)
+				return
+			}
+		}
+	}
+	o = bts
+	return
+}
+
+// Msgsize returns an upper bound estimate of the number of bytes occupied by the serialized message
+func (z *dataUsageEntryV7) Msgsize() (s int) {
+	s = 1 + 3 + z.Children.Msgsize() + 3 + msgp.Int64Size + 3 + msgp.Uint64Size + 3 + msgp.Uint64Size + 4 + msgp.Uint64Size + 4 + msgp.ArrayHeaderSize + (dataUsageBucketLenV1 * (msgp.Uint64Size)) + 3 + msgp.ArrayHeaderSize + (dataUsageVersionLen * (msgp.Uint64Size)) + 3
+	if z.ReplicationStats == nil {
+		s += msgp.NilSize
+	} else {
+		s += z.ReplicationStats.Msgsize()
+	}
+	s += 4
+	if z.AllTierStats == nil {
+		s += msgp.NilSize
+	} else {
+		s += z.AllTierStats.Msgsize()
+	}
+	s += 2 + msgp.BoolSize
+	return
+}
+
 // DecodeMsg implements msgp.Decodable
 func (z *dataUsageHash) DecodeMsg(dc *msgp.Reader) (err error) {
 	{
@@ -3705,6 +4139,84 @@ func (z *sizeHistogram) Msgsize() (s int) {
 	return
 }
 
+// DecodeMsg implements msgp.Decodable
+func (z *sizeHistogramV1) DecodeMsg(dc *msgp.Reader) (err error) {
+	var zb0001 uint32
+	zb0001, err = dc.ReadArrayHeader()
+	if err != nil {
+		err = msgp.WrapError(err)
+		return
+	}
+	if zb0001 != uint32(dataUsageBucketLenV1) {
+		err = msgp.ArrayError{Wanted: uint32(dataUsageBucketLenV1), Got: zb0001}
+		return
+	}
+	for za0001 := range z {
+		z[za0001], err = dc.ReadUint64()
+		if err != nil {
+			err = msgp.WrapError(err, za0001)
+			return
+		}
+	}
+	return
+}
+
+// EncodeMsg implements msgp.Encodable
+func (z *sizeHistogramV1) EncodeMsg(en *msgp.Writer) (err error) {
+	err = en.WriteArrayHeader(uint32(dataUsageBucketLenV1))
+	if err != nil {
+		err = msgp.WrapError(err)
+		return
+	}
+	for za0001 := range z {
+		err = en.WriteUint64(z[za0001])
+		if err != nil {
+			err = msgp.WrapError(err, za0001)
+			return
+		}
+	}
+	return
+}
+
+// MarshalMsg implements msgp.Marshaler
+func (z *sizeHistogramV1) MarshalMsg(b []byte) (o []byte, err error) {
+	o = msgp.Require(b, z.Msgsize())
+	o = msgp.AppendArrayHeader(o, uint32(dataUsageBucketLenV1))
+	for za0001 := range z {
+		o = msgp.AppendUint64(o, z[za0001])
+	}
+	return
+}
+
+// UnmarshalMsg implements msgp.Unmarshaler
+func (z *sizeHistogramV1) UnmarshalMsg(bts []byte) (o []byte, err error) {
+	var zb0001 uint32
+	zb0001, bts, err = msgp.ReadArrayHeaderBytes(bts)
+	if err != nil {
+		err = msgp.WrapError(err)
+		return
+	}
+	if zb0001 != uint32(dataUsageBucketLenV1) {
+		err = msgp.ArrayError{Wanted: uint32(dataUsageBucketLenV1), Got: zb0001}
+		return
+	}
+	for za0001 := range z {
+		z[za0001], bts, err = msgp.ReadUint64Bytes(bts)
+		if err != nil {
+			err = msgp.WrapError(err, za0001)
+			return
+		}
+	}
+	o = bts
+	return
+}
+
+// Msgsize returns an upper bound estimate of the number of bytes occupied by the serialized message
+func (z *sizeHistogramV1) Msgsize() (s int) {
+	s = msgp.ArrayHeaderSize + (dataUsageBucketLenV1 * (msgp.Uint64Size))
+	return
+}
+
 // DecodeMsg implements msgp.Decodable
 func (z *tierStats) DecodeMsg(dc *msgp.Reader) (err error) {
 	var field []byte

cmd/data-usage-cache_gen_test.go

@@ -1084,6 +1084,119 @@ func BenchmarkDecodesizeHistogram(b *testing.B) {
 	}
 }
 
+func TestMarshalUnmarshalsizeHistogramV1(t *testing.T) {
+	v := sizeHistogramV1{}
+	bts, err := v.MarshalMsg(nil)
+	if err != nil {
+		t.Fatal(err)
+	}
+	left, err := v.UnmarshalMsg(bts)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if len(left) > 0 {
+		t.Errorf("%d bytes left over after UnmarshalMsg(): %q", len(left), left)
+	}
+
+	left, err = msgp.Skip(bts)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if len(left) > 0 {
+		t.Errorf("%d bytes left over after Skip(): %q", len(left), left)
+	}
+}
+
+func BenchmarkMarshalMsgsizeHistogramV1(b *testing.B) {
+	v := sizeHistogramV1{}
+	b.ReportAllocs()
+	b.ResetTimer()
+	for i := 0; i < b.N; i++ {
+		v.MarshalMsg(nil)
+	}
+}
+
+func BenchmarkAppendMsgsizeHistogramV1(b *testing.B) {
+	v := sizeHistogramV1{}
+	bts := make([]byte, 0, v.Msgsize())
+	bts, _ = v.MarshalMsg(bts[0:0])
+	b.SetBytes(int64(len(bts)))
+	b.ReportAllocs()
+	b.ResetTimer()
+	for i := 0; i < b.N; i++ {
+		bts, _ = v.MarshalMsg(bts[0:0])
+	}
+}
+
+func BenchmarkUnmarshalsizeHistogramV1(b *testing.B) {
+	v := sizeHistogramV1{}
+	bts, _ := v.MarshalMsg(nil)
+	b.ReportAllocs()
+	b.SetBytes(int64(len(bts)))
+	b.ResetTimer()
+	for i := 0; i < b.N; i++ {
+		_, err := v.UnmarshalMsg(bts)
+		if err != nil {
+			b.Fatal(err)
+		}
+	}
+}
+
+func TestEncodeDecodesizeHistogramV1(t *testing.T) {
+	v := sizeHistogramV1{}
+	var buf bytes.Buffer
+	msgp.Encode(&buf, &v)
+
+	m := v.Msgsize()
+	if buf.Len() > m {
+		t.Log("WARNING: TestEncodeDecodesizeHistogramV1 Msgsize() is inaccurate")
+	}
+
+	vn := sizeHistogramV1{}
+	err := msgp.Decode(&buf, &vn)
+	if err != nil {
+		t.Error(err)
+	}
+
+	buf.Reset()
+	msgp.Encode(&buf, &v)
+	err = msgp.NewReader(&buf).Skip()
+	if err != nil {
+		t.Error(err)
+	}
+}
+
+func BenchmarkEncodesizeHistogramV1(b *testing.B) {
+	v := sizeHistogramV1{}
+	var buf bytes.Buffer
+	msgp.Encode(&buf, &v)
+	b.SetBytes(int64(buf.Len()))
+	en := msgp.NewWriter(msgp.Nowhere)
+	b.ReportAllocs()
+	b.ResetTimer()
+	for i := 0; i < b.N; i++ {
+		v.EncodeMsg(en)
+	}
+	en.Flush()
+}
+
+func BenchmarkDecodesizeHistogramV1(b *testing.B) {
+	v := sizeHistogramV1{}
+	var buf bytes.Buffer
+	msgp.Encode(&buf, &v)
+	b.SetBytes(int64(buf.Len()))
+	rd := msgp.NewEndlessReader(buf.Bytes(), b)
+	dc := msgp.NewReader(rd)
+	b.ReportAllocs()
+	b.ResetTimer()
+	for i := 0; i < b.N; i++ {
+		err := v.DecodeMsg(dc)
+		if err != nil {
+			b.Fatal(err)
+		}
+	}
+}
+
 func TestMarshalUnmarshaltierStats(t *testing.T) {
 	v := tierStats{}
 	bts, err := v.MarshalMsg(nil)

cmd/data-usage-cache_test.go

@@ -0,0 +1,98 @@
+// Copyright (c) 2015-2023 MinIO, Inc.
+//
+// This file is part of MinIO Object Storage stack
+//
+// This program is free software: you can redistribute it and/or modify
+// it under the terms of the GNU Affero General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+//
+// This program is distributed in the hope that it will be useful
+// but WITHOUT ANY WARRANTY; without even the implied warranty of
+// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+// GNU Affero General Public License for more details.
+//
+// You should have received a copy of the GNU Affero General Public License
+// along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+package cmd
+
+import (
+	"fmt"
+	"testing"
+
+	"github.com/dustin/go-humanize"
+)
+
+func TestSizeHistogramToMap(t *testing.T) {
+	tests := []struct {
+		sizes []int64
+		want  map[string]uint64
+	}{
+		{
+			sizes: []int64{100, 1000, 72_000, 100_000},
+			want: map[string]uint64{
+				"LESS_THAN_1024_B":         2,
+				"BETWEEN_64_KB_AND_256_KB": 2,
+				"BETWEEN_1024B_AND_1_MB":   2,
+			},
+		},
+		{
+			sizes: []int64{100, 1000, 2000, 100_000, 13 * humanize.MiByte},
+			want: map[string]uint64{
+				"LESS_THAN_1024_B":         2,
+				"BETWEEN_1024_B_AND_64_KB": 1,
+				"BETWEEN_64_KB_AND_256_KB": 1,
+				"BETWEEN_1024B_AND_1_MB":   2,
+				"BETWEEN_10_MB_AND_64_MB":  1,
+			},
+		},
+	}
+	for i, test := range tests {
+		t.Run(fmt.Sprintf("Test-%d", i), func(t *testing.T) {
+			var h sizeHistogram
+			for _, sz := range test.sizes {
+				h.add(sz)
+			}
+			got := h.toMap()
+			exp := test.want
+			// what is in exp is in got
+			for k := range exp {
+				if exp[k] != got[k] {
+					t.Fatalf("interval %s: Expected %d values but got %d values\n", k, exp[k], got[k])
+				}
+			}
+			// what is absent in exp is absent in got too
+			for k := range got {
+				if _, ok := exp[k]; !ok && got[k] > 0 {
+					t.Fatalf("Unexpected interval: %s has value %d\n", k, got[k])
+				}
+			}
+		})
+	}
+}
+
+func TestMigrateSizeHistogramFromV1(t *testing.T) {
+	tests := []struct {
+		v    sizeHistogramV1
+		want sizeHistogram
+	}{
+		{
+			v:    sizeHistogramV1{0: 10, 1: 20, 2: 3},
+			want: sizeHistogram{0: 10, 5: 20, 6: 3},
+		},
+		{
+			v:    sizeHistogramV1{0: 10, 1: 20, 2: 3, 3: 4, 4: 5, 5: 6, 6: 7},
+			want: sizeHistogram{0: 10, 5: 20, 6: 3, 7: 4, 8: 5, 9: 6, 10: 7},
+		},
+	}
+	for i, test := range tests {
+		t.Run(fmt.Sprintf("test-%d", i), func(t *testing.T) {
+			var got sizeHistogram
+			got.mergeV1(test.v)
+			if got != test.want {
+				t.Fatalf("Expected %v but got %v", test.want, got)
+			}
+		})
+	}
+}

cmd/data-usage_test.go

@@ -82,7 +82,7 @@ func TestDataUsageUpdate(t *testing.T) {
 			size:    1322310,
 			flatten: true,
 			objs:    8,
-			oSizes:  sizeHistogram{0: 2, 1: 6},
+			oSizes:  sizeHistogram{0: 2, 1: 3, 2: 2, 4: 1},
 		},
 		{
 			path:   "/",
@@ -94,7 +94,7 @@ func TestDataUsageUpdate(t *testing.T) {
 			path:   "/dir1",
 			size:   1302010,
 			objs:   5,
-			oSizes: sizeHistogram{0: 1, 1: 4},
+			oSizes: sizeHistogram{0: 1, 1: 1, 2: 2, 4: 1},
 		},
 		{
 			path:  "/dir1/dira",
@@ -167,7 +167,6 @@ func TestDataUsageUpdate(t *testing.T) {
 			size: 200,
 		},
 	}
-
 	createUsageTestFiles(t, base, bucket, files)
 	err = os.RemoveAll(filepath.Join(base, bucket, "dir1/dira/dirasub/dcfile"))
 	if err != nil {
@@ -194,14 +193,14 @@ func TestDataUsageUpdate(t *testing.T) {
 			size:    363515,
 			flatten: true,
 			objs:    14,
-			oSizes:  sizeHistogram{0: 7, 1: 7},
+			oSizes:  sizeHistogram{0: 7, 1: 5, 2: 2},
 		},
 		{
 			path:    "/dir1",
 			size:    342210,
 			objs:    7,
 			flatten: false,
-			oSizes:  sizeHistogram{0: 2, 1: 5},
+			oSizes:  sizeHistogram{0: 2, 1: 3, 2: 2},
 		},
 		{
 			path:   "/newfolder",
@@ -308,7 +307,7 @@ func TestDataUsageUpdatePrefix(t *testing.T) {
 			path:   "flat",
 			size:   1322310 + expectSize,
 			objs:   8 + expectSize,
-			oSizes: sizeHistogram{0: 2 + expectSize, 1: 6},
+			oSizes: sizeHistogram{0: 2 + expectSize, 1: 3, 2: 2, 4: 1},
 		},
 		{
 			path:   "bucket/",
@@ -321,7 +320,7 @@ func TestDataUsageUpdatePrefix(t *testing.T) {
 			path:   "bucket/dir1",
 			size:   1302010,
 			objs:   5,
-			oSizes: sizeHistogram{0: 1, 1: 4},
+			oSizes: sizeHistogram{0: 1, 1: 1, 2: 2, 4: 1},
 		},
 		{
 			// Gets compacted at this level...
@@ -436,13 +435,13 @@ func TestDataUsageUpdatePrefix(t *testing.T) {
 			path:   "flat",
 			size:   363515 + expectSize,
 			objs:   14 + expectSize,
-			oSizes: sizeHistogram{0: 7 + expectSize, 1: 7},
+			oSizes: sizeHistogram{0: 7 + expectSize, 1: 5, 2: 2},
 		},
 		{
 			path:   "bucket/dir1",
 			size:   342210,
 			objs:   7,
-			oSizes: sizeHistogram{0: 2, 1: 5},
+			oSizes: sizeHistogram{0: 2, 1: 3, 2: 2},
 		},
 		{
 			path:   "bucket/",

cmd/object-api-datatypes.go

@@ -54,16 +54,35 @@ type objectHistogramInterval struct {
 }
 
 const (
+	// dataUsageBucketLenV1 must be length of ObjectsHistogramIntervalsV1
+	dataUsageBucketLenV1 = 7
 	// dataUsageBucketLen must be length of ObjectsHistogramIntervals
-	dataUsageBucketLen  = 7
+	dataUsageBucketLen  = 11
 	dataUsageVersionLen = 7
 )
 
+// ObjectsHistogramIntervalsV1 is the list of all intervals
+// of object sizes to be included in objects histogram(V1).
+var ObjectsHistogramIntervalsV1 = [dataUsageBucketLenV1]objectHistogramInterval{
+	{"LESS_THAN_1024_B", 0, humanize.KiByte - 1},
+	{"BETWEEN_1024B_AND_1_MB", humanize.KiByte, humanize.MiByte - 1},
+	{"BETWEEN_1_MB_AND_10_MB", humanize.MiByte, humanize.MiByte*10 - 1},
+	{"BETWEEN_10_MB_AND_64_MB", humanize.MiByte * 10, humanize.MiByte*64 - 1},
+	{"BETWEEN_64_MB_AND_128_MB", humanize.MiByte * 64, humanize.MiByte*128 - 1},
+	{"BETWEEN_128_MB_AND_512_MB", humanize.MiByte * 128, humanize.MiByte*512 - 1},
+	{"GREATER_THAN_512_MB", humanize.MiByte * 512, math.MaxInt64},
+}
+
 // ObjectsHistogramIntervals is the list of all intervals
 // of object sizes to be included in objects histogram.
+// Note: this histogram expands 1024B-1MB to incl. 1024B-64KB, 64KB-256KB, 256KB-512KB and 512KB-1MiB
 var ObjectsHistogramIntervals = [dataUsageBucketLen]objectHistogramInterval{
 	{"LESS_THAN_1024_B", 0, humanize.KiByte - 1},
-	{"BETWEEN_1024_B_AND_1_MB", humanize.KiByte, humanize.MiByte - 1},
+	{"BETWEEN_1024_B_AND_64_KB", humanize.KiByte, 64*humanize.KiByte - 1},         // not exported, for support use only
+	{"BETWEEN_64_KB_AND_256_KB", 64 * humanize.KiByte, 256*humanize.KiByte - 1},   // not exported, for support use only
+	{"BETWEEN_256_KB_AND_512_KB", 256 * humanize.KiByte, 512*humanize.KiByte - 1}, // not exported, for support use only
+	{"BETWEEN_512_KB_AND_1_MB", 512 * humanize.KiByte, humanize.MiByte - 1},       // not exported, for support use only
+	{"BETWEEN_1024B_AND_1_MB", humanize.KiByte, humanize.MiByte - 1},
 	{"BETWEEN_1_MB_AND_10_MB", humanize.MiByte, humanize.MiByte*10 - 1},
 	{"BETWEEN_10_MB_AND_64_MB", humanize.MiByte * 10, humanize.MiByte*64 - 1},
 	{"BETWEEN_64_MB_AND_128_MB", humanize.MiByte * 64, humanize.MiByte*128 - 1},