feat(info): Show index and bloom filter size (#1543)

This PR depends upon dgraph-io/ristretto#197
`badger info` now shows index size and bloom filter size

badger/cmd/info.go

@@ -244,15 +244,23 @@ func tableInfo(dir, valueDir string, db *badger.DB) {
 	tables := db.Tables(true)
 	fmt.Println()
 	fmt.Println("SSTable [Li, Id, Total Keys including internal keys] " +
-		"[Left Key, Version -> Right Key, Version]" + "[Index Size]")
+		"[Left Key, Version -> Right Key, Version] [Index Size] [BF Size]")
+	totalIndex := uint64(0)
+	totalBloomFilter := uint64(0)
 	for _, t := range tables {
 		lk, lt := y.ParseKey(t.Left), y.ParseTs(t.Left)
 		rk, rt := y.ParseKey(t.Right), y.ParseTs(t.Right)
 
-		fmt.Printf("SSTable [L%d, %03d, %07d] [%20X, v%d -> %20X, v%d] [%s]\n",
-			t.Level, t.ID, t.KeyCount, lk, lt, rk, rt, hbytes(int64(t.IndexSz)))
+		totalIndex += uint64(t.IndexSz)
+		totalBloomFilter += uint64(t.BloomFilterSize)
+		fmt.Printf("SSTable [L%d, %03d, %07d] [%20X, v%d -> %20X, v%d] [%s] [%s] \n",
+			t.Level, t.ID, t.KeyCount, lk, lt, rk, rt, hbytes(int64(t.IndexSz)),
+			hbytes(int64(t.BloomFilterSize)))
 	}
 	fmt.Println()
+	fmt.Printf("Total Index Size: %s\n", hbytes(int64(totalIndex)))
+	fmt.Printf("Total BloomFilter Size: %s\n", hbytes(int64(totalIndex)))
+	fmt.Println()
 }
 
 func printInfo(dir, valueDir string) error {
@@ -403,13 +411,13 @@ func printInfo(dir, valueDir string) error {
 	}
 
 	fmt.Print("\n[Summary]\n")
-	totalIndexSize := int64(0)
+	totalSSTSize := int64(0)
 	for i, sz := range levelSizes {
 		fmt.Printf("Level %d size: %12s\n", i, hbytes(sz))
-		totalIndexSize += sz
+		totalSSTSize += sz
 	}
 
-	fmt.Printf("Total index size: %8s\n", hbytes(totalIndexSize))
+	fmt.Printf("Total SST size: %8s\n", hbytes(totalSSTSize))
 	fmt.Printf("Value log size: %10s\n", hbytes(valueLogSize))
 	fmt.Println()
 	totalExtra := numExtra + numValueDirExtra

go.mod

@@ -5,17 +5,17 @@ go 1.12
 require (
 	github.com/DataDog/zstd v1.4.1
 	github.com/cespare/xxhash v1.1.0
-	github.com/dgraph-io/ristretto v0.0.4-0.20200906165740-41ebdbffecfd
+	github.com/dgraph-io/ristretto v0.0.4-0.20200930150433-e1609c8d4ca6
 	github.com/dgryski/go-farm v0.0.0-20190423205320-6a90982ecee2
 	github.com/dustin/go-humanize v1.0.0
 	github.com/golang/protobuf v1.3.1
 	github.com/golang/snappy v0.0.1
 	github.com/kr/pretty v0.1.0 // indirect
-	github.com/pkg/errors v0.8.1
+	github.com/pkg/errors v0.9.1
 	github.com/spaolacci/murmur3 v1.1.0 // indirect
 	github.com/spf13/cobra v0.0.5
 	github.com/stretchr/testify v1.4.0
 	golang.org/x/net v0.0.0-20190620200207-3b0461eec859
-	golang.org/x/sys v0.0.0-20190626221950-04f50cda93cb
+	golang.org/x/sys v0.0.0-20200918174421-af09f7315aff
 	gopkg.in/check.v1 v1.0.0-20190902080502-41f04d3bba15 // indirect
 )

go.sum

@@ -13,8 +13,8 @@ github.com/cpuguy83/go-md2man v1.0.10/go.mod h1:SmD6nW6nTyfqj6ABTjUi3V3JVMnlJmwc
 github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
 github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c=
 github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
-github.com/dgraph-io/ristretto v0.0.4-0.20200906165740-41ebdbffecfd h1:KoJOtZf+6wpQaDTuOWGuo61GxcPBIfhwRxRTaTWGCTc=
-github.com/dgraph-io/ristretto v0.0.4-0.20200906165740-41ebdbffecfd/go.mod h1:YylP9MpCYGVZQrly/j/diqcdUetCRRePeBB0c2VGXsA=
+github.com/dgraph-io/ristretto v0.0.4-0.20200930150433-e1609c8d4ca6 h1:maqkH6zkcUx1PP+LpbLMef2IOSz2/mLYT3RqecFcdDI=
+github.com/dgraph-io/ristretto v0.0.4-0.20200930150433-e1609c8d4ca6/go.mod h1:bDI4cDaalvYSji3vBVDKrn9ouDZrwN974u8ZO/AhYXs=
 github.com/dgryski/go-farm v0.0.0-20190423205320-6a90982ecee2 h1:tdlZCpZ/P9DhczCTSixgIKmwPv6+wP5DGjqLYw5SUiA=
 github.com/dgryski/go-farm v0.0.0-20190423205320-6a90982ecee2/go.mod h1:SqUrOPUnsFjfmXRMNPybcSiG0BgUW2AuFH8PAnS2iTw=
 github.com/dustin/go-humanize v1.0.0 h1:VSnTsYCnlFHaM2/igO1h6X3HA71jcobQuxemgkq4zYo=
@@ -36,8 +36,8 @@ github.com/magiconair/properties v1.8.0/go.mod h1:PppfXfuXeibc/6YijjN8zIbojt8czP
 github.com/mitchellh/go-homedir v1.1.0/go.mod h1:SfyaCUpYCn1Vlf4IUYiD9fPX4A5wJrkLzIz1N1q0pr0=
 github.com/mitchellh/mapstructure v1.1.2/go.mod h1:FVVH3fgwuzCH5S8UJGiWEs2h04kUh9fWfEaFds41c1Y=
 github.com/pelletier/go-toml v1.2.0/go.mod h1:5z9KED0ma1S8pY6P1sdut58dfprrGBbd/94hg7ilaic=
-github.com/pkg/errors v0.8.1 h1:iURUrRGxPUNPdy5/HRSm+Yj6okJ6UtLINN0Q9M4+h3I=
-github.com/pkg/errors v0.8.1/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0=
+github.com/pkg/errors v0.9.1 h1:FEBLx1zS214owpjy7qsBeixbURkuhQAwrK5UwLGTwt4=
+github.com/pkg/errors v0.9.1/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0=
 github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=
 github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
 github.com/russross/blackfriday v1.5.2/go.mod h1:JO/DiYxRf+HjHt06OyowR9PTA263kcR/rfWxYHBV53g=
@@ -64,8 +64,8 @@ golang.org/x/net v0.0.0-20190620200207-3b0461eec859 h1:R/3boaszxrf1GEUWTVDzSKVwL
 golang.org/x/net v0.0.0-20190620200207-3b0461eec859/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
 golang.org/x/sys v0.0.0-20181205085412-a5c9d58dba9a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
 golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
-golang.org/x/sys v0.0.0-20190626221950-04f50cda93cb h1:fgwFCsaw9buMuxNd6+DQfAuSFqbNiQZpcgJQAgJsK6k=
-golang.org/x/sys v0.0.0-20190626221950-04f50cda93cb/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20200918174421-af09f7315aff h1:1CPUrky56AcgSpxz/KfgzQWzfG09u5YOL8MvPYBlrL8=
+golang.org/x/sys v0.0.0-20200918174421-af09f7315aff/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
 gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
 gopkg.in/check.v1 v1.0.0-20190902080502-41f04d3bba15 h1:YR8cESwS4TdDjEe65xsg0ogRM/Nc3DYOhEAlW+xobZo=

levels.go

@@ -1128,13 +1128,14 @@ func (s *levelsController) appendIterators(
 
 // TableInfo represents the information about a table.
 type TableInfo struct {
-	ID          uint64
-	Level       int
-	Left        []byte
-	Right       []byte
-	KeyCount    uint64 // Number of keys in the table
-	EstimatedSz uint64
-	IndexSz     int
+	ID              uint64
+	Level           int
+	Left            []byte
+	Right           []byte
+	KeyCount        uint64 // Number of keys in the table
+	EstimatedSz     uint64
+	IndexSz         int
+	BloomFilterSize int
 }
 
 func (s *levelsController) getTableInfo(withKeysCount bool) (result []TableInfo) {
@@ -1151,13 +1152,14 @@ func (s *levelsController) getTableInfo(withKeysCount bool) (result []TableInfo)
 			}
 
 			info := TableInfo{
-				ID:          t.ID(),
-				Level:       l.level,
-				Left:        t.Smallest(),
-				Right:       t.Biggest(),
-				KeyCount:    count,
-				EstimatedSz: t.EstimatedSize(),
-				IndexSz:     t.IndexSize(),
+				ID:              t.ID(),
+				Level:           l.level,
+				Left:            t.Smallest(),
+				Right:           t.Biggest(),
+				KeyCount:        count,
+				EstimatedSz:     t.EstimatedSize(),
+				IndexSz:         t.IndexSize(),
+				BloomFilterSize: t.BloomFilterSize(),
 			}
 			result = append(result, info)
 		}

table/table.go

@@ -669,7 +669,8 @@ func (t *Table) blockOffsetsCacheKey() uint64 {
 	return t.id
 }
 
-// IndexSize is the size of table index in bytes
+// IndexSize returns the size of table index in bytes stored in the memory. The
+// size of on-disk representation would be less than the in-memory representation.
 func (t *Table) IndexSize() int {
 	indexSz := 0
 	for _, bi := range t.blockOffsets() {
@@ -678,6 +679,12 @@ func (t *Table) IndexSize() int {
 	return indexSz
 }
 
+// BloomFilterSize returns the size of the bloom filter in bytes stored in memory. The
+// size of on-disk representation would be less than the in-memory representation.
+func (t *Table) BloomFilterSize() int {
+	return t.bf.TotalSize()
+}
+
 // EstimatedSize returns the total size of key-values stored in this table (including the
 // disk space occupied on the value log).
 func (t *Table) EstimatedSize() uint64 { return t.estimatedSize }