Optimized and increased read performance by ~2-3x by memory mapping the read-only datafiles

.drone.yml

@@ -5,18 +5,10 @@ steps:
   - name: build
     image: golang:latest
     commands:
-      - go test -v -short -cover -coverprofile=coverage.txt ./...
+      - go test -v -short -cover -coverprofile=coverage.txt -coverpkg=$(go list) .
 
   - name: coverage
     image: plugins/codecov
     settings:
       token:
         from_secret: codecov-token
-
-  - name: notify
-    image: plugins/webhook
-    urls: https://msgbus.mills.io/ci.mills.io
-    when:
-      status:
-        - success
-        - failure

.goreleaser.yml

@@ -3,14 +3,14 @@ builds:
     binary: bitcask
     main: ./cmd/bitcask
     flags: -tags "static_build"
-    ldflags: -w -X .Version={{.Version}} -X .Commit={{.Commit}}
+    ldflags: -w -X github.com/prologic/bitcask/internal.Version={{.Version}} -X github.com/prologic/bitcask/internal.Commit={{.Commit}}
     env:
       - CGO_ENABLED=0
   - 
     binary: bitcaskd
     main: ./cmd/bitcaskd
     flags: -tags "static_build"
-    ldflags: -w -X .Version={{.Version}} -X .Commit={{.Commit}}
+    ldflags: -w -X github.com/prologic/bitcask/internal.Version={{.Version}} -X github.com/prologic/bitcask/internal.Commit={{.Commit}}
     env:
       - CGO_ENABLED=0
 sign:

Makefile

@@ -13,11 +13,11 @@ dev: build
 build: clean generate
 	@go build \
 		-tags "netgo static_build" -installsuffix netgo \
-		-ldflags "-w -X $(shell go list).Version=$(VERSION) -X $(shell go list).Commit=$(COMMIT)" \
+		-ldflags "-w -X $(shell go list)/internal.Version=$(VERSION) -X $(shell go list)/internal.Commit=$(COMMIT)" \
 		./cmd/bitcask/...
 	@go build \
 		-tags "netgo static_build" -installsuffix netgo \
-		-ldflags "-w -X $(shell go list).Version=$(VERSION) -X $(shell go list).Commit=$(COMMIT)" \
+		-ldflags "-w -X $(shell go list)/internal.Version=$(VERSION) -X $(shell go list)/internal.Commit=$(COMMIT)" \
 		./cmd/bitcaskd/...
 
 generate:
@@ -25,6 +25,7 @@ generate:
 
 install: build
 	@go install ./cmd/bitcask/...
+	@go install ./cmd/bitcaskd/...
 
 image:
 	@docker build -t prologic/bitcask .
@@ -33,13 +34,17 @@ release:
 	@./tools/release.sh
 
 profile: build
-	@go test -cpuprofile cpu.prof -memprofile mem.prof -v -bench ./...
+	@go test -cpuprofile cpu.prof -memprofile mem.prof -v -bench .
 
 bench: build
-	@go test -v -benchmem -bench=. ./...
+	@go test -v -benchmem -bench=. .
 
 test: build
-	@go test -v -cover -coverprofile=coverage.txt -covermode=atomic -coverpkg=./... -race ./...
+	@go test -v \
+		-cover -coverprofile=coverage.txt -covermode=atomic \
+		-coverpkg=$(shell go list) \
+		-race \
+		.
 
 clean:
 	@git clean -f -d -X

README.md

@@ -6,13 +6,13 @@
 [![GoDoc](https://godoc.org/github.com/prologic/bitcask?status.svg)](https://godoc.org/github.com/prologic/bitcask) 
 [![Sourcegraph](https://sourcegraph.com/github.com/prologic/bitcask/-/badge.svg)](https://sourcegraph.com/github.com/prologic/bitcask?badge)
 
-A Bitcask (LSM+WAL) Key/Value Store written in Go.
+A high performance Key/Value store written in [Go](https://golang.org) with a predictable read/write performance and high throughput. Uses a [Bitcask](https://en.wikipedia.org/wiki/Bitcask) on-disk layout (LSM+WAL) similar to [Riak](https://riak.com/).
 
 ## Features
 
-* Embeddable
-* Builtin CLI
-* Builtin Redis-compatible server
+* Embeddable (`import "github.com/prologic/bitcask"`)
+* Builtin CLI (`bitcask`)
+* Builtin Redis-compatible server (`bitcaskd`)
 * Predictable read/write performance
 * Low latecny
 * High throughput (See: [Performance](README.md#Performance)
@@ -34,16 +34,13 @@ $ go get github.com/prologic/bitcask
 ```#!go
 package main
 
-import (
-    "log"
-
-    "github.com/prologic/bitcask"
-)
+import "github.com/prologic/bitcask"
 
 func main() {
     db, _ := bitcask.Open("/tmp/db")
+    defer db.Close()
     db.Set("Hello", []byte("World"))
-    db.Close()
+    val, _ := db.Get("hello")
 }
 ```
 
@@ -97,32 +94,32 @@ Benchmarks run on a 11" Macbook with a 1.4Ghz Intel Core i7:
 ```
 $ make bench
 ...
-BenchmarkGet/128B-4         	  300000	      5178 ns/op	     400 B/op	       5 allocs/op
-BenchmarkGet/256B-4         	  300000	      5273 ns/op	     656 B/op	       5 allocs/op
-BenchmarkGet/512B-4         	  200000	      5368 ns/op	    1200 B/op	       5 allocs/op
-BenchmarkGet/1K-4           	  200000	      5800 ns/op	    2288 B/op	       5 allocs/op
-BenchmarkGet/2K-4           	  200000	      6766 ns/op	    4464 B/op	       5 allocs/op
-BenchmarkGet/4K-4           	  200000	      7857 ns/op	    9072 B/op	       5 allocs/op
-BenchmarkGet/8K-4           	  200000	      9538 ns/op	   17776 B/op	       5 allocs/op
-BenchmarkGet/16K-4          	  100000	     13188 ns/op	   34928 B/op	       5 allocs/op
-BenchmarkGet/32K-4          	  100000	     21620 ns/op	   73840 B/op	       5 allocs/op
+BenchmarkGet/128B-4         	  500000	      2537 ns/op	     672 B/op	       7 allocs/op
+BenchmarkGet/256B-4         	  500000	      2629 ns/op	    1056 B/op	       7 allocs/op
+BenchmarkGet/512B-4         	  500000	      2773 ns/op	    1888 B/op	       7 allocs/op
+BenchmarkGet/1K-4           	  500000	      3202 ns/op	    3552 B/op	       7 allocs/op
+BenchmarkGet/2K-4           	  300000	      3904 ns/op	    6880 B/op	       7 allocs/op
+BenchmarkGet/4K-4           	  300000	      5678 ns/op	   14048 B/op	       7 allocs/op
+BenchmarkGet/8K-4           	  200000	      8948 ns/op	   27360 B/op	       7 allocs/op
+BenchmarkGet/16K-4          	  100000	     14635 ns/op	   53472 B/op	       7 allocs/op
+BenchmarkGet/32K-4          	   50000	     28292 ns/op	  114912 B/op	       7 allocs/op
 
-BenchmarkPut/128B-4         	  200000	      7875 ns/op	     409 B/op	       6 allocs/op
-BenchmarkPut/256B-4         	  200000	      8712 ns/op	     538 B/op	       6 allocs/op
-BenchmarkPut/512B-4         	  200000	      9832 ns/op	     829 B/op	       6 allocs/op
-BenchmarkPut/1K-4           	  100000	     13105 ns/op	    1410 B/op	       6 allocs/op
-BenchmarkPut/2K-4           	  100000	     18601 ns/op	    2572 B/op	       6 allocs/op
-BenchmarkPut/4K-4           	   50000	     36631 ns/op	    5151 B/op	       6 allocs/op
-BenchmarkPut/8K-4           	   30000	     56128 ns/op	    9798 B/op	       6 allocs/op
-BenchmarkPut/16K-4          	   20000	     83209 ns/op	   18834 B/op	       6 allocs/op
-BenchmarkPut/32K-4          	   10000	    135899 ns/op	   41517 B/op	       6 allocs/op
+BenchmarkPut/128B-4         	  200000	      8173 ns/op	     409 B/op	       6 allocs/op
+BenchmarkPut/256B-4         	  200000	      8404 ns/op	     538 B/op	       6 allocs/op
+BenchmarkPut/512B-4         	  200000	      9741 ns/op	     829 B/op	       6 allocs/op
+BenchmarkPut/1K-4           	  100000	     13118 ns/op	    1411 B/op	       6 allocs/op
+BenchmarkPut/2K-4           	  100000	     17982 ns/op	    2573 B/op	       6 allocs/op
+BenchmarkPut/4K-4           	   50000	     35477 ns/op	    5154 B/op	       6 allocs/op
+BenchmarkPut/8K-4           	   30000	     54021 ns/op	    9804 B/op	       6 allocs/op
+BenchmarkPut/16K-4          	   20000	     96551 ns/op	   18849 B/op	       6 allocs/op
+BenchmarkPut/32K-4          	   10000	    129957 ns/op	   41561 B/op	       7 allocs/op
 
-BenchmarkScan-4             	 1000000	      1851 ns/op	     493 B/op	      25 allocs/op
+BenchmarkScan-4             	 1000000	      2011 ns/op	     493 B/op	      25 allocs/op
 ```
 
 For 128B values:
 
-* ~200,000 reads/sec
+* ~400,000 reads/sec
 * ~130,000 writes/sec
 
 The full benchmark above shows linear performance as you increase key/value sizes.

bitcask.go

@@ -1,31 +1,61 @@
 package bitcask
 
 import (
-	"fmt"
+	"errors"
 	"hash/crc32"
 	"io"
 	"io/ioutil"
 	"os"
 	"path/filepath"
 	"strings"
+	"sync"
 
 	"github.com/gofrs/flock"
 	"github.com/prologic/trie"
+
+	"github.com/prologic/bitcask/internal"
 )
 
+var (
+	// ErrKeyNotFound is the error returned when a key is not found
+	ErrKeyNotFound = errors.New("error: key not found")
+
+	// ErrKeyTooLarge is the error returned for a key that exceeds the
+	// maximum allowed key size (configured with WithMaxKeySize).
+	ErrKeyTooLarge = errors.New("error: key too large")
+
+	// ErrValueTooLarge is the error returned for a value that exceeds the
+	// maximum allowed value size (configured with WithMaxValueSize).
+	ErrValueTooLarge = errors.New("error: value too large")
+
+	// ErrChecksumFailed is the error returned if a key/valie retrieved does
+	// not match its CRC checksum
+	ErrChecksumFailed = errors.New("error: checksum failed")
+
+	// ErrDatabaseLocked is the error returned if the database is locked
+	// (typically opened by another process)
+	ErrDatabaseLocked = errors.New("error: database locked")
+)
+
+// Bitcask is a struct that represents a on-disk LSM and WAL data structure
+// and in-memory hash of key/value pairs as per the Bitcask paper and seen
+// in the Riak database.
 type Bitcask struct {
+	mu sync.RWMutex
+
 	*flock.Flock
 
 	config    *config
 	path      string
-	curr      *Datafile
-	keydir    *Keydir
-	datafiles []*Datafile
+	curr      *internal.Datafile
+	keydir    *internal.Keydir
+	datafiles []*internal.Datafile
 	trie      *trie.Trie
-
-	maxDatafileSize int64
 }
 
+// Close closes the database and removes the lock. It is important to call
+// Close() as this is the only wat to cleanup the lock held by the open
+// database.
 func (b *Bitcask) Close() error {
 	defer func() {
 		b.Flock.Unlock()
@@ -38,58 +68,70 @@ func (b *Bitcask) Close() error {
 	return b.curr.Close()
 }
 
+// Sync flushes all buffers to disk ensuring all data is written
 func (b *Bitcask) Sync() error {
 	return b.curr.Sync()
 }
 
+// Get retrieves the value of the given key. If the key is not found or an/I/O
+// error occurs a null byte slice is returend along with the error.
 func (b *Bitcask) Get(key string) ([]byte, error) {
-	var df *Datafile
+	var df *internal.Datafile
 
 	item, ok := b.keydir.Get(key)
 	if !ok {
-		return nil, fmt.Errorf("error: key not found %s", key)
+		return nil, ErrKeyNotFound
 	}
 
-	if item.FileID == b.curr.id {
+	if item.FileID == b.curr.FileID() {
 		df = b.curr
 	} else {
 		df = b.datafiles[item.FileID]
 	}
 
-	e, err := df.ReadAt(item.Offset)
+	e, err := df.ReadAt(item.Offset, item.Size)
 	if err != nil {
 		return nil, err
 	}
 
 	checksum := crc32.ChecksumIEEE(e.Value)
 	if checksum != e.Checksum {
-		return nil, fmt.Errorf("error: checksum falied %s %d != %d", key, e.Checksum, checksum)
+		return nil, ErrChecksumFailed
 	}
 
 	return e.Value, nil
 }
 
+// Has returns true if the key exists in the database, false otherwise.
+func (b *Bitcask) Has(key string) bool {
+	_, ok := b.keydir.Get(key)
+	return ok
+}
+
+// Put stores the key and value in the database.
 func (b *Bitcask) Put(key string, value []byte) error {
-	if len(key) > b.config.MaxKeySize {
-		return fmt.Errorf("error: key too large %d > %d", len(key), b.config.MaxKeySize)
+	if len(key) > b.config.maxKeySize {
+		return ErrKeyTooLarge
 	}
-	if len(value) > b.config.MaxValueSize {
-		return fmt.Errorf("error: value too large %d > %d", len(value), b.config.MaxValueSize)
+	if len(value) > b.config.maxValueSize {
+		return ErrValueTooLarge
 	}
 
-	offset, err := b.put(key, value)
+	offset, n, err := b.put(key, value)
 	if err != nil {
 		return err
 	}
 
-	item := b.keydir.Add(key, b.curr.id, offset)
+	item := b.keydir.Add(key, b.curr.FileID(), offset, n)
 	b.trie.Add(key, item)
 
 	return nil
 }
 
+// Delete deletes the named key. If the key doesn't exist or an I/O error
+// occurs the error is returned.
 func (b *Bitcask) Delete(key string) error {
-	_, err := b.put(key, []byte{})
+	_, _, err := b.put(key, []byte{})
 	if err != nil {
 		return err
 	}
@@ -100,6 +142,9 @@ func (b *Bitcask) Delete(key string) error {
 	return nil
 }
 
+// Scan performa a prefix scan of keys matching the given prefix and calling
+// the function `f` with the keys found. If the function returns an error
+// no further keys are processed and the first error returned.
 func (b *Bitcask) Scan(prefix string, f func(key string) error) error {
 	keys := b.trie.PrefixSearch(prefix)
 	for _, key := range keys {
@@ -110,6 +155,19 @@ func (b *Bitcask) Scan(prefix string, f func(key string) error) error {
 	return nil
 }
 
+// Len returns the total number of keys in the database
+func (b *Bitcask) Len() int {
+	return b.keydir.Len()
+}
+
+// Keys returns all keys in the database as a channel of string(s)
+func (b *Bitcask) Keys() chan string {
+	return b.keydir.Keys()
+}
+
+// Fold iterates over all keys in the database calling the function `f` for
+// each key. If the function returns an error, no further keys are processed
+// and the error returned.
 func (b *Bitcask) Fold(f func(key string) error) error {
 	for key := range b.keydir.Keys() {
 		if err := f(key); err != nil {
@@ -119,49 +177,46 @@ func (b *Bitcask) Fold(f func(key string) error) error {
 	return nil
 }
 
-func (b *Bitcask) put(key string, value []byte) (int64, error) {
-	size, err := b.curr.Size()
-	if err != nil {
-		return -1, err
-	}
+func (b *Bitcask) put(key string, value []byte) (int64, int64, error) {
+	b.mu.Lock()
+	defer b.mu.Unlock()
 
-	if size >= b.maxDatafileSize {
+	size := b.curr.Size()
+	if size >= int64(b.config.maxDatafileSize) {
 		err := b.curr.Close()
 		if err != nil {
-			return -1, err
+			return -1, 0, err
 		}
 
-		df, err := NewDatafile(b.path, b.curr.id, true)
+		df, err := internal.NewDatafile(b.path, b.curr.FileID(), true)
 		if err != nil {
-			return -1, err
+			return -1, 0, err
 		}
 
 		b.datafiles = append(b.datafiles, df)
 
-		id := b.curr.id + 1
-		curr, err := NewDatafile(b.path, id, false)
+		id := b.curr.FileID() + 1
+		curr, err := internal.NewDatafile(b.path, id, false)
 		if err != nil {
-			return -1, err
+			return -1, 0, err
 		}
 		b.curr = curr
 	}
 
-	e := NewEntry(key, value)
+	e := internal.NewEntry(key, value)
 	return b.curr.Write(e)
 }
 
-func (b *Bitcask) setMaxDatafileSize(size int64) error {
-	b.maxDatafileSize = size
-	return nil
-}
-
+// Merge merges all datafiles in the database creating hint files for faster
+// startup. Old keys are squashed and deleted keys removes. Call this function
+// periodically to reclaim disk space.
 func Merge(path string, force bool) error {
-	fns, err := getDatafiles(path)
+	fns, err := internal.GetDatafiles(path)
 	if err != nil {
 		return err
 	}
 
-	ids, err := parseIds(fns)
+	ids, err := internal.ParseIds(fns)
 	if err != nil {
 		return err
 	}
@@ -191,16 +246,16 @@ func Merge(path string, force bool) error {
 
 		id := ids[i]
 
-		keydir := NewKeydir()
+		keydir := internal.NewKeydir()
 
-		df, err := NewDatafile(path, id, true)
+		df, err := internal.NewDatafile(path, id, true)
 		if err != nil {
 			return err
 		}
 		defer df.Close()
 
 		for {
-			e, err := df.Read()
+			e, n, err := df.Read()
 			if err != nil {
 				if err == io.EOF {
 					break
@@ -214,10 +269,10 @@ func Merge(path string, force bool) error {
 				continue
 			}
 
-			keydir.Add(e.Key, ids[i], e.Offset)
+			keydir.Add(e.Key, ids[i], e.Offset, n)
 		}
 
-		tempdf, err := NewDatafile(temp, id, false)
+		tempdf, err := internal.NewDatafile(temp, id, false)
 		if err != nil {
 			return err
 		}
@@ -225,12 +280,12 @@ func Merge(path string, force bool) error {
 
 		for key := range keydir.Keys() {
 			item, _ := keydir.Get(key)
-			e, err := df.ReadAt(item.Offset)
+			e, err := df.ReadAt(item.Offset, item.Size)
 			if err != nil {
 				return err
 			}
 
-			_, err = tempdf.Write(e)
+			_, _, err = tempdf.Write(e)
 			if err != nil {
 				return err
 			}
@@ -261,7 +316,10 @@ func Merge(path string, force bool) error {
 	return nil
 }
 
-func Open(path string, options ...option) (*Bitcask, error) {
+// Open opens the database at the given path with optional options.
+// Options can be provided with the `WithXXX` functions that provide
+// configuration options as functions.
+func Open(path string, options ...Option) (*Bitcask, error) {
 	if err := os.MkdirAll(path, 0755); err != nil {
 		return nil, err
 	}
@@ -271,23 +329,23 @@ func Open(path string, options ...option) (*Bitcask, error) {
 		return nil, err
 	}
 
-	fns, err := getDatafiles(path)
+	fns, err := internal.GetDatafiles(path)
 	if err != nil {
 		return nil, err
 	}
 
-	ids, err := parseIds(fns)
+	ids, err := internal.ParseIds(fns)
 	if err != nil {
 		return nil, err
 	}
 
-	var datafiles []*Datafile
+	var datafiles []*internal.Datafile
 
-	keydir := NewKeydir()
+	keydir := internal.NewKeydir()
 	trie := trie.New()
 
 	for i, fn := range fns {
-		df, err := NewDatafile(path, ids[i], true)
+		df, err := internal.NewDatafile(path, ids[i], true)
 		if err != nil {
 			return nil, err
 		}
@@ -300,19 +358,19 @@ func Open(path string, options ...option) (*Bitcask, error) {
 			}
 			defer f.Close()
 
-			hint, err := NewKeydirFromBytes(f)
+			hint, err := internal.NewKeydirFromBytes(f)
 			if err != nil {
 				return nil, err
 			}
 
 			for key := range hint.Keys() {
 				item, _ := hint.Get(key)
-				_ = keydir.Add(key, item.FileID, item.Offset)
+				_ = keydir.Add(key, item.FileID, item.Offset, item.Size)
 				trie.Add(key, item)
 			}
 		} else {
 			for {
-				e, err := df.Read()
+				e, n, err := df.Read()
 				if err != nil {
 					if err == io.EOF {
 						break
@@ -326,7 +384,7 @@ func Open(path string, options ...option) (*Bitcask, error) {
 					continue
 				}
 
-				item := keydir.Add(e.Key, ids[i], e.Offset)
+				item := keydir.Add(e.Key, ids[i], e.Offset, n)
 				trie.Add(e.Key, item)
 			}
 		}
@@ -337,21 +395,19 @@ func Open(path string, options ...option) (*Bitcask, error) {
 		id = ids[(len(ids) - 1)]
 	}
 
-	curr, err := NewDatafile(path, id, false)
+	curr, err := internal.NewDatafile(path, id, false)
 	if err != nil {
 		return nil, err
 	}
 
 	bitcask := &Bitcask{
 		Flock:     flock.New(filepath.Join(path, "lock")),
-		config:    NewDefaultConfig(),
+		config:    newDefaultConfig(),
 		path:      path,
 		curr:      curr,
 		keydir:    keydir,
 		datafiles: datafiles,
 		trie:      trie,
-
-		maxDatafileSize: DefaultMaxDatafileSize,
 	}
 
 	for _, opt := range options {
@@ -367,7 +423,7 @@ func Open(path string, options ...option) (*Bitcask, error) {
 	}
 
 	if !locked {
-		return nil, fmt.Errorf("error: database locked %s", path)
+		return nil, ErrDatabaseLocked
 	}
 
 	return bitcask, nil

bitcask_test.go

@@ -40,12 +40,48 @@ func TestAll(t *testing.T) {
 		assert.Equal([]byte("bar"), val)
 	})
 
+	t.Run("Len", func(t *testing.T) {
+		assert.Equal(1, db.Len())
+	})
+
+	t.Run("Has", func(t *testing.T) {
+		assert.True(db.Has("foo"))
+	})
+
+	t.Run("Keys", func(t *testing.T) {
+		keys := make([]string, 0)
+		for key := range db.Keys() {
+			keys = append(keys, key)
+		}
+		assert.Equal([]string{"foo"}, keys)
+	})
+
+	t.Run("Fold", func(t *testing.T) {
+		var (
+			keys   []string
+			values [][]byte
+		)
+
+		err := db.Fold(func(key string) error {
+			value, err := db.Get(key)
+			if err != nil {
+				return err
+			}
+			keys = append(keys, key)
+			values = append(values, value)
+			return nil
+		})
+		assert.NoError(err)
+		assert.Equal([]string{"foo"}, keys)
+		assert.Equal([][]byte{[]byte("bar")}, values)
+	})
+
 	t.Run("Delete", func(t *testing.T) {
 		err := db.Delete("foo")
 		assert.NoError(err)
 		_, err = db.Get("foo")
 		assert.Error(err)
-		assert.Equal("error: key not found foo", err.Error())
+		assert.Equal(ErrKeyNotFound, err)
 	})
 
 	t.Run("Sync", func(t *testing.T) {
@@ -92,7 +128,7 @@ func TestDeletedKeys(t *testing.T) {
 			assert.NoError(err)
 			_, err = db.Get("foo")
 			assert.Error(err)
-			assert.Equal("error: key not found foo", err.Error())
+			assert.Equal(ErrKeyNotFound, err)
 		})
 
 		t.Run("Sync", func(t *testing.T) {
@@ -120,7 +156,7 @@ func TestDeletedKeys(t *testing.T) {
 		t.Run("Get", func(t *testing.T) {
 			_, err = db.Get("foo")
 			assert.Error(err)
-			assert.Equal("error: key not found foo", err.Error())
+			assert.Equal(ErrKeyNotFound, err)
 		})
 
 		t.Run("Close", func(t *testing.T) {
@@ -148,7 +184,7 @@ func TestMaxKeySize(t *testing.T) {
 		value := []byte("foobar")
 		err = db.Put(key, value)
 		assert.Error(err)
-		assert.Equal("error: key too large 17 > 16", err.Error())
+		assert.Equal(ErrKeyTooLarge, err)
 	})
 }
 
@@ -170,11 +206,11 @@ func TestMaxValueSize(t *testing.T) {
 		value := []byte(strings.Repeat(" ", 17))
 		err = db.Put(key, value)
 		assert.Error(err)
-		assert.Equal("error: value too large 17 > 16", err.Error())
+		assert.Equal(ErrValueTooLarge, err)
 	})
 }
 
-func TestMerge(t *testing.T) {
+func TestOpenMerge(t *testing.T) {
 	assert := assert.New(t)
 
 	testdir, err := ioutil.TempDir("", "bitcask")
@@ -187,7 +223,7 @@ func TestMerge(t *testing.T) {
 		)
 
 		t.Run("Open", func(t *testing.T) {
-			db, err = Open(testdir, WithMaxDatafileSize(1024))
+			db, err = Open(testdir, WithMaxDatafileSize(32))
 			assert.NoError(err)
 		})
 
@@ -245,6 +281,77 @@ func TestMerge(t *testing.T) {
 	})
 }
 
+func TestMergeOpen(t *testing.T) {
+	var (
+		db  *Bitcask
+		err error
+	)
+
+	assert := assert.New(t)
+
+	testdir, err := ioutil.TempDir("", "bitcask")
+	assert.NoError(err)
+
+	t.Run("Setup", func(t *testing.T) {
+		t.Run("Open", func(t *testing.T) {
+			db, err = Open(testdir, WithMaxDatafileSize(32))
+			assert.NoError(err)
+		})
+
+		t.Run("Put", func(t *testing.T) {
+			for i := 0; i < 1024; i++ {
+				err = db.Put(string(i), []byte(strings.Repeat(" ", 1024)))
+				assert.NoError(err)
+			}
+		})
+
+		t.Run("Get", func(t *testing.T) {
+			for i := 0; i < 32; i++ {
+				err = db.Put(string(i), []byte(strings.Repeat(" ", 1024)))
+				assert.NoError(err)
+				val, err := db.Get(string(i))
+				assert.NoError(err)
+				assert.Equal([]byte(strings.Repeat(" ", 1024)), val)
+			}
+		})
+
+		t.Run("Sync", func(t *testing.T) {
+			err = db.Sync()
+			assert.NoError(err)
+		})
+
+		t.Run("Close", func(t *testing.T) {
+			err = db.Close()
+			assert.NoError(err)
+		})
+	})
+
+	t.Run("Merge", func(t *testing.T) {
+		t.Run("Merge", func(t *testing.T) {
+			err = Merge(testdir, true)
+			assert.NoError(err)
+		})
+
+		t.Run("Open", func(t *testing.T) {
+			db, err = Open(testdir)
+			assert.NoError(err)
+		})
+
+		t.Run("Get", func(t *testing.T) {
+			for i := 0; i < 32; i++ {
+				val, err := db.Get(string(i))
+				assert.NoError(err)
+				assert.Equal([]byte(strings.Repeat(" ", 1024)), val)
+			}
+		})
+
+		t.Run("Close", func(t *testing.T) {
+			err = db.Close()
+			assert.NoError(err)
+		})
+	})
+}
+
 func TestConcurrent(t *testing.T) {
 	var (
 		db  *Bitcask
@@ -387,7 +494,7 @@ func TestLocking(t *testing.T) {
 
 	_, err = Open(testdir)
 	assert.Error(err)
-	assert.Equal(fmt.Sprintf("error: database locked %s", testdir), err.Error())
+	assert.Equal(ErrDatabaseLocked, err)
 }
 
 type benchmarkTestCase struct {

cmd/bitcask/root.go

@@ -8,13 +8,13 @@ import (
 	"github.com/spf13/cobra"
 	"github.com/spf13/viper"
 
-	"github.com/prologic/bitcask"
+	"github.com/prologic/bitcask/internal"
 )
 
 // RootCmd represents the base command when called without any subcommands
 var RootCmd = &cobra.Command{
 	Use:     "bitcask",
-	Version: bitcask.FullVersion(),
+	Version: internal.FullVersion(),
 	Short:   "Command-line tools for bitcask",
 	Long: `This is the command-line tool to interact with a bitcask database.
 

cmd/bitcaskd/main.go

@@ -10,6 +10,7 @@ import (
 	"github.com/tidwall/redcon"
 
 	"github.com/prologic/bitcask"
+	"github.com/prologic/bitcask/internal"
 )
 
 var (
@@ -43,7 +44,7 @@ func main() {
 	}
 
 	if version {
-		fmt.Printf("bitcaskd version %s", bitcask.FullVersion())
+		fmt.Printf("bitcaskd version %s", internal.FullVersion())
 		os.Exit(0)
 	}
 
@@ -60,7 +61,7 @@ func main() {
 		os.Exit(1)
 	}
 
-	log.WithField("bind", bind).WithField("path", path).Infof("starting bitcaskd v%s", bitcask.FullVersion())
+	log.WithField("bind", bind).WithField("path", path).Infof("starting bitcaskd v%s", internal.FullVersion())
 
 	err = redcon.ListenAndServe(bind,
 		func(conn redcon.Conn, cmd redcon.Command) {
@@ -95,6 +96,22 @@ func main() {
 				} else {
 					conn.WriteBulk(value)
 				}
+			case "keys":
+				conn.WriteArray(db.Len())
+				for key := range db.Keys() {
+					conn.WriteBulk([]byte(key))
+				}
+			case "exists":
+				if len(cmd.Args) != 2 {
+					conn.WriteError("ERR wrong number of arguments for '" + string(cmd.Args[0]) + "' command")
+					return
+				}
+				key := string(cmd.Args[1])
+				if db.Has(key) {
+					conn.WriteInt(1)
+				} else {
+					conn.WriteInt(0)
+				}
 			case "del":
 				if len(cmd.Args) != 2 {
 					conn.WriteError("ERR wrong number of arguments for '" + string(cmd.Args[0]) + "' command")

go.mod

@@ -1,22 +1,30 @@
 module github.com/prologic/bitcask
 
 require (
-	github.com/derekparker/trie v0.0.0-20180212171413-e608c2733dc7
+	github.com/BurntSushi/toml v0.3.1 // indirect
+	github.com/coreos/etcd v3.3.12+incompatible // indirect
 	github.com/gofrs/flock v0.7.1
 	github.com/gogo/protobuf v1.2.1
-	github.com/golang/protobuf v1.2.0
-	github.com/gorilla/websocket v1.4.0 // indirect
-	github.com/jpillora/backoff v0.0.0-20180909062703-3050d21c67d7 // indirect
-	github.com/mitchellh/go-homedir v1.1.0
+	github.com/golang/protobuf v1.3.1
+	github.com/inconshreveable/mousetrap v1.0.0 // indirect
+	github.com/kisielk/errcheck v1.2.0 // indirect
+	github.com/konsorten/go-windows-terminal-sequences v1.0.2 // indirect
 	github.com/pkg/errors v0.8.1
-	github.com/prologic/msgbus v0.1.1
-	github.com/prologic/trie v0.0.0-20190316011403-395e39dac705
-	github.com/prometheus/client_golang v0.9.2 // indirect
-	github.com/sirupsen/logrus v1.3.0
+	github.com/prologic/trie v0.0.0-20190322091023-3972df81f9b5
+	github.com/sirupsen/logrus v1.4.0
+	github.com/spf13/afero v1.2.1 // indirect
 	github.com/spf13/cobra v0.0.3
+	github.com/spf13/jwalterweatherman v1.1.0 // indirect
 	github.com/spf13/pflag v1.0.3
-	github.com/spf13/viper v1.3.1
+	github.com/spf13/viper v1.3.2
 	github.com/stretchr/testify v1.3.0
-	github.com/tidwall/redcon v0.9.0
-	gopkg.in/vmihailenco/msgpack.v2 v2.9.1
+	github.com/tidwall/redcon v1.0.0
+	github.com/ugorji/go/codec v0.0.0-20190320090025-2dc34c0b8780 // indirect
+	golang.org/x/crypto v0.0.0-20190320223903-b7391e95e576 // indirect
+	golang.org/x/exp v0.0.0-20190321205749-f0864edee7f3
+	golang.org/x/net v0.0.0-20190320064053-1272bf9dcd53 // indirect
+	golang.org/x/sync v0.0.0-20190227155943-e225da77a7e6 // indirect
+	golang.org/x/sys v0.0.0-20190322080309-f49334f85ddc // indirect
+	golang.org/x/tools v0.0.0-20190321232350-e250d351ecad // indirect
+	gopkg.in/check.v1 v1.0.0-20180628173108-788fd7840127 // indirect
 )

go.sum

@@ -1,15 +1,15 @@
+github.com/BurntSushi/toml v0.3.1 h1:WXkYYl6Yr3qBf1K79EBnL4mak0OimBfB0XUf9Vl28OQ=
+github.com/BurntSushi/toml v0.3.1/go.mod h1:xHWCNGjB5oqiDr8zfno3MHue2Ht5sIBksp03qcyfWMU=
+github.com/BurntSushi/xgb v0.0.0-20160522181843-27f122750802/go.mod h1:IVnqGOEym/WlBOVXweHU+Q+/VP0lqqI8lqeDx9IjBqo=
 github.com/armon/consul-api v0.0.0-20180202201655-eb2c6b5be1b6/go.mod h1:grANhF5doyWs3UAsr3K4I6qtAmlQcZDesFNEHPZAzj8=
-github.com/beorn7/perks v0.0.0-20180321164747-3a771d992973 h1:xJ4a3vCFaGF/jqvzLMYoU8P317H5OQ+Via4RmuPwCS0=
-github.com/beorn7/perks v0.0.0-20180321164747-3a771d992973/go.mod h1:Dwedo/Wpr24TaqPxmxbtue+5NUziq4I4S80YR8gNf3Q=
 github.com/coreos/etcd v3.3.10+incompatible/go.mod h1:uF7uidLiAD3TWHmW31ZFd/JWoc32PjwdhPthX9715RE=
+github.com/coreos/etcd v3.3.12+incompatible/go.mod h1:uF7uidLiAD3TWHmW31ZFd/JWoc32PjwdhPthX9715RE=
 github.com/coreos/go-etcd v2.0.0+incompatible/go.mod h1:Jez6KQU2B/sWsbdaef3ED8NzMklzPG4d5KIOhIy30Tk=
 github.com/coreos/go-semver v0.2.0/go.mod h1:nnelYz7RCh+5ahJtPPxZlU+153eP4D4r3EedlOD2RNk=
 github.com/davecgh/go-spew v1.1.0 h1:ZDRjVQ15GmhC3fiQ8ni8+OwkZQO4DARzQgrnXU1Liz8=
 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/derekparker/trie v0.0.0-20180212171413-e608c2733dc7 h1:Cab9yoTQh1TxObKfis1DzZ6vFLK5kbeenMjRES/UE3o=
-github.com/derekparker/trie v0.0.0-20180212171413-e608c2733dc7/go.mod h1:D6ICZm05D9VN1n/8iOtBxLpXtoGp6HDFUJ1RNVieOSE=
 github.com/fsnotify/fsnotify v1.4.7 h1:IXs+QLmnXW2CcXuY+8Mzv/fWEsPGWxqefPtCP5CnV9I=
 github.com/fsnotify/fsnotify v1.4.7/go.mod h1:jwhsz4b93w/PPRr/qN1Yymfu8t87LnFCMoQvtojpjFo=
 github.com/gofrs/flock v0.7.1 h1:DP+LD/t0njgoPBvT5MJLeliUIVQR03hiKR6vezdwHlc=
@@ -18,21 +18,20 @@ github.com/gogo/protobuf v1.2.1 h1:/s5zKNz0uPFCZ5hddgPdo2TK2TVrUNMn0OOX8/aZMTE=
 github.com/gogo/protobuf v1.2.1/go.mod h1:hp+jE20tsWTFYpLwKvXlhS1hjn+gTNwPg2I6zVXpSg4=
 github.com/golang/protobuf v1.2.0 h1:P3YflyNX/ehuJFLhxviNdFxQPkGK5cDcApsge1SqnvM=
 github.com/golang/protobuf v1.2.0/go.mod h1:6lQm79b+lXiMfvg/cZm0SGofjICqVBUtrP5yJMmIC1U=
-github.com/gorilla/websocket v1.4.0 h1:WDFjx/TMzVgy9VdMMQi2K2Emtwi2QcUQsztZ/zLaH/Q=
-github.com/gorilla/websocket v1.4.0/go.mod h1:E7qHFY5m1UJ88s3WnNqhKjPHQ0heANvMoAMk2YaljkQ=
+github.com/golang/protobuf v1.3.1 h1:YF8+flBXS5eO826T4nzqPrxfhQThhXl0YzfuUPu4SBg=
+github.com/golang/protobuf v1.3.1/go.mod h1:6lQm79b+lXiMfvg/cZm0SGofjICqVBUtrP5yJMmIC1U=
 github.com/hashicorp/hcl v1.0.0 h1:0Anlzjpi4vEasTeNFn2mLJgTSwt0+6sfsiTG8qcWGx4=
 github.com/hashicorp/hcl v1.0.0/go.mod h1:E5yfLk+7swimpb2L/Alb/PJmXilQ/rhwaUYs4T20WEQ=
-github.com/jpillora/backoff v0.0.0-20180909062703-3050d21c67d7 h1:K//n/AqR5HjG3qxbrBCL4vJPW0MVFSs9CPK1OOJdRME=
-github.com/jpillora/backoff v0.0.0-20180909062703-3050d21c67d7/go.mod h1:2iMrUgbbvHEiQClaW2NsSzMyGHqN+rDFqY705q49KG0=
+github.com/inconshreveable/mousetrap v1.0.0 h1:Z8tu5sraLXCXIcARxBp/8cbvlwVa7Z1NHg9XEKhtSvM=
+github.com/inconshreveable/mousetrap v1.0.0/go.mod h1:PxqpIevigyE2G7u3NXJIT2ANytuPF1OarO4DADm73n8=
 github.com/kisielk/errcheck v1.1.0/go.mod h1:EZBBE59ingxPouuu3KfxchcWSUPOHkagtvWXihfKN4Q=
+github.com/kisielk/errcheck v1.2.0/go.mod h1:/BMXB+zMLi60iA8Vv6Ksmxu/1UDYcXs4uQLJ+jE2L00=
 github.com/kisielk/gotool v1.0.0/go.mod h1:XhKaO+MFFWcvkIS/tQcRk01m1F5IRFswLeQ+oQHNcck=
+github.com/konsorten/go-windows-terminal-sequences v1.0.1 h1:mweAR1A6xJ3oS2pRaGiHgQ4OO8tzTaLawm8vnODuwDk=
 github.com/konsorten/go-windows-terminal-sequences v1.0.1/go.mod h1:T0+1ngSBFLxvqU3pZ+m/2kptfBszLMUkC4ZK/EgS/cQ=
+github.com/konsorten/go-windows-terminal-sequences v1.0.2/go.mod h1:T0+1ngSBFLxvqU3pZ+m/2kptfBszLMUkC4ZK/EgS/cQ=
 github.com/magiconair/properties v1.8.0 h1:LLgXmsheXeRoUOBOjtwPQCWIYqM/LU1ayDtDePerRcY=
 github.com/magiconair/properties v1.8.0/go.mod h1:PppfXfuXeibc/6YijjN8zIbojt8czPbwD3XqdrwzmxQ=
-github.com/matttproud/golang_protobuf_extensions v1.0.1 h1:4hp9jkHxhMHkqkrB3Ix0jegS5sx/RkqARlsWZ6pIwiU=
-github.com/matttproud/golang_protobuf_extensions v1.0.1/go.mod h1:D8He9yQNgCq6Z5Ld7szi9bcBfOoFv/3dc6xSMkL2PC0=
-github.com/mitchellh/go-homedir v1.1.0 h1:lukF9ziXFxDFPkA1vsr5zpc1XuPDn/wFntq5mG+4E0Y=
-github.com/mitchellh/go-homedir v1.1.0/go.mod h1:SfyaCUpYCn1Vlf4IUYiD9fPX4A5wJrkLzIz1N1q0pr0=
 github.com/mitchellh/mapstructure v1.1.2 h1:fmNYVwqnSfB9mZU6OS2O6GsXM+wcskZDuKQzvN1EDeE=
 github.com/mitchellh/mapstructure v1.1.2/go.mod h1:FVVH3fgwuzCH5S8UJGiWEs2h04kUh9fWfEaFds41c1Y=
 github.com/pelletier/go-toml v1.2.0 h1:T5zMGML61Wp+FlcbWjRDT7yAxhJNAiPPLOFECq181zc=
@@ -41,31 +40,32 @@ 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/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=
 github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
-github.com/prologic/msgbus v0.1.1/go.mod h1:B3Qu4/U2FP08x93jUzp9E8bl155+cIgDH2DUGRK6OZk=
 github.com/prologic/trie v0.0.0-20190316011403-395e39dac705 h1:2J+cSlAeECj0lfMKSmM7n5OlIio+yLovaKLZJzwLc6U=
 github.com/prologic/trie v0.0.0-20190316011403-395e39dac705/go.mod h1:LFuDmpHJGmciXd8Rl5YMhVlLMps9gz2GtYLzwxrFhzs=
-github.com/prometheus/client_golang v0.9.2 h1:awm861/B8OKDd2I/6o1dy3ra4BamzKhYOiGItCeZ740=
-github.com/prometheus/client_golang v0.9.2/go.mod h1:OsXs2jCmiKlQ1lTBmv21f2mNfw4xf/QclQDMrYNZzcM=
-github.com/prometheus/client_model v0.0.0-20180712105110-5c3871d89910 h1:idejC8f05m9MGOsuEi1ATq9shN03HrxNkD/luQvxCv8=
-github.com/prometheus/client_model v0.0.0-20180712105110-5c3871d89910/go.mod h1:MbSGuTsp3dbXC40dX6PRTWyKYBIrTGTE9sqQNg2J8bo=
-github.com/prometheus/common v0.0.0-20181126121408-4724e9255275 h1:PnBWHBf+6L0jOqq0gIVUe6Yk0/QMZ640k6NvkxcBf+8=
-github.com/prometheus/common v0.0.0-20181126121408-4724e9255275/go.mod h1:daVV7qP5qjZbuso7PdcryaAu0sAZbrN9i7WWcTMWvro=
-github.com/prometheus/procfs v0.0.0-20181204211112-1dc9a6cbc91a h1:9a8MnZMP0X2nLJdBg+pBmGgkJlSaKC2KaQmTCk1XDtE=
-github.com/prometheus/procfs v0.0.0-20181204211112-1dc9a6cbc91a/go.mod h1:c3At6R/oaqEKCNdg8wHV1ftS6bRYblBhIjjI8uT2IGk=
+github.com/prologic/trie v0.0.0-20190322091023-3972df81f9b5 h1:H8dTZzU3aWNQnuRyiT45J9szv7EFakAhFzsFq27t3Uo=
+github.com/prologic/trie v0.0.0-20190322091023-3972df81f9b5/go.mod h1:LFuDmpHJGmciXd8Rl5YMhVlLMps9gz2GtYLzwxrFhzs=
 github.com/sirupsen/logrus v1.3.0 h1:hI/7Q+DtNZ2kINb6qt/lS+IyXnHQe9e90POfeewL/ME=
 github.com/sirupsen/logrus v1.3.0/go.mod h1:LxeOpSwHxABJmUn/MG1IvRgCAasNZTLOkJPxbbu5VWo=
+github.com/sirupsen/logrus v1.4.0 h1:yKenngtzGh+cUSSh6GWbxW2abRqhYUSR/t/6+2QqNvE=
+github.com/sirupsen/logrus v1.4.0/go.mod h1:LxeOpSwHxABJmUn/MG1IvRgCAasNZTLOkJPxbbu5VWo=
 github.com/spf13/afero v1.1.2 h1:m8/z1t7/fwjysjQRYbP0RD+bUIF/8tJwPdEZsI83ACI=
 github.com/spf13/afero v1.1.2/go.mod h1:j4pytiNVoe2o6bmDsKpLACNPDBIoEAkihy7loJ1B0CQ=
+github.com/spf13/afero v1.2.1 h1:qgMbHoJbPbw579P+1zVY+6n4nIFuIchaIjzZ/I/Yq8M=
+github.com/spf13/afero v1.2.1/go.mod h1:9ZxEEn6pIJ8Rxe320qSDBk6AsU0r9pR7Q4OcevTdifk=
 github.com/spf13/cast v1.3.0 h1:oget//CVOEoFewqQxwr0Ej5yjygnqGkvggSE/gB35Q8=
 github.com/spf13/cast v1.3.0/go.mod h1:Qx5cxh0v+4UWYiBimWS+eyWzqEqokIECu5etghLkUJE=
 github.com/spf13/cobra v0.0.3 h1:ZlrZ4XsMRm04Fr5pSFxBgfND2EBVa1nLpiy1stUsX/8=
 github.com/spf13/cobra v0.0.3/go.mod h1:1l0Ry5zgKvJasoi3XT1TypsSe7PqH0Sj9dhYf7v3XqQ=
 github.com/spf13/jwalterweatherman v1.0.0 h1:XHEdyB+EcvlqZamSM4ZOMGlc93t6AcsBEu9Gc1vn7yk=
 github.com/spf13/jwalterweatherman v1.0.0/go.mod h1:cQK4TGJAtQXfYWX+Ddv3mKDzgVb68N+wFjFa4jdeBTo=
+github.com/spf13/jwalterweatherman v1.1.0 h1:ue6voC5bR5F8YxI5S67j9i582FU4Qvo2bmqnqMYADFk=
+github.com/spf13/jwalterweatherman v1.1.0/go.mod h1:aNWZUN0dPAAO/Ljvb5BEdw96iTZ0EXowPYD95IqWIGo=
 github.com/spf13/pflag v1.0.3 h1:zPAT6CGy6wXeQ7NtTnaTerfKOsV6V6F8agHXFiazDkg=
 github.com/spf13/pflag v1.0.3/go.mod h1:DYY7MBk1bdzusC3SYhjObp+wFpr4gzcvqqNjLnInEg4=
 github.com/spf13/viper v1.3.1 h1:5+8j8FTpnFV4nEImW/ofkzEt8VoOiLXxdYIDsB73T38=
 github.com/spf13/viper v1.3.1/go.mod h1:ZiWeW+zYFKm7srdB9IoDzzZXaJaI5eL9QjNiN/DMA2s=
+github.com/spf13/viper v1.3.2 h1:VUFqw5KcqRf7i70GOzW7N+Q7+gxVBkSSqiXB12+JQ4M=
+github.com/spf13/viper v1.3.2/go.mod h1:ZiWeW+zYFKm7srdB9IoDzzZXaJaI5eL9QjNiN/DMA2s=
 github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME=
 github.com/stretchr/objx v0.1.1/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME=
 github.com/stretchr/testify v1.2.2/go.mod h1:a8OnRcib4nhh0OaRAV+Yts87kKdq0PP7pXfy6kDkUVs=
@@ -73,21 +73,42 @@ github.com/stretchr/testify v1.3.0 h1:TivCn/peBQ7UY8ooIcPgZFpTNSz0Q2U6UrFlUfqbe0
 github.com/stretchr/testify v1.3.0/go.mod h1:M5WIy9Dh21IEIfnGCwXGc5bZfKNJtfHm1UVUgZn+9EI=
 github.com/tidwall/redcon v0.9.0 h1:tiT9DLAoohsdNaFg9Si5dRsv9+FjvZYnhMOEtSFwBqA=
 github.com/tidwall/redcon v0.9.0/go.mod h1:bdYBm4rlcWpst2XMwKVzWDF9CoUxEbUmM7CQrKeOZas=
+github.com/tidwall/redcon v1.0.0 h1:D4AzzJ81Afeh144fgnj5H0aSVPBBJ5RI9Rzj0zThU+E=
+github.com/tidwall/redcon v1.0.0/go.mod h1:bdYBm4rlcWpst2XMwKVzWDF9CoUxEbUmM7CQrKeOZas=
+github.com/ugorji/go v1.1.2/go.mod h1:hnLbHMwcvSihnDhEfx2/BzKp2xb0Y+ErdfYcrs9tkJQ=
 github.com/ugorji/go/codec v0.0.0-20181204163529-d75b2dcb6bc8/go.mod h1:VFNgLljTbGfSG7qAOspJ7OScBnGdDN/yBr0sguwnwf0=
+github.com/ugorji/go/codec v0.0.0-20190320090025-2dc34c0b8780/go.mod h1:iT03XoTwV7xq/+UGwKO3UbC1nNNlopQiY61beSdrtOA=
 github.com/xordataexchange/crypt v0.0.3-0.20170626215501-b2862e3d0a77/go.mod h1:aYKd//L2LvnjZzWKhF00oedf4jCCReLcmhLdhm1A27Q=
 golang.org/x/crypto v0.0.0-20180904163835-0709b304e793/go.mod h1:6SG95UA2DQfeDnfUPMdvaQW0Q7yPrPDi9nlGo2tz2b4=
 golang.org/x/crypto v0.0.0-20181203042331-505ab145d0a9 h1:mKdxBk7AujPs8kU4m80U72y/zjbZ3UcXC7dClwKbUI0=
 golang.org/x/crypto v0.0.0-20181203042331-505ab145d0a9/go.mod h1:6SG95UA2DQfeDnfUPMdvaQW0Q7yPrPDi9nlGo2tz2b4=
-golang.org/x/net v0.0.0-20181201002055-351d144fa1fc/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
+golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w=
+golang.org/x/crypto v0.0.0-20190320223903-b7391e95e576 h1:aUX/1G2gFSs4AsJJg2cL3HuoRhCSCz733FE5GUSuaT4=
+golang.org/x/crypto v0.0.0-20190320223903-b7391e95e576/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w=
+golang.org/x/exp v0.0.0-20190321205749-f0864edee7f3 h1:Ep4L2ibjtJcW6IP73KbcJAU0cpNKsLNSSP2jE1xlCys=
+golang.org/x/exp v0.0.0-20190321205749-f0864edee7f3/go.mod h1:ZjyILWgesfNpC6sMxTJOJm9Kp84zZh5NQWvqDGG3Qr8=
+golang.org/x/image v0.0.0-20190227222117-0694c2d4d067/go.mod h1:kZ7UVZpmo3dzQBMxlp+ypCbDeSB+sBbTgSJuh5dn5js=
+golang.org/x/mobile v0.0.0-20190312151609-d3739f865fa6/go.mod h1:z+o9i4GpDbdi3rU15maQ/Ox0txvL9dWGYEHz965HBQE=
+golang.org/x/net v0.0.0-20190311183353-d8887717615a/go.mod h1:t9HGtf8HONx5eT2rtn7q6eTqICYqUVnKs3thJo3Qplg=
+golang.org/x/net v0.0.0-20190320064053-1272bf9dcd53/go.mod h1:t9HGtf8HONx5eT2rtn7q6eTqICYqUVnKs3thJo3Qplg=
+golang.org/x/sync v0.0.0-20181108010431-42b317875d0f h1:Bl/8QSvNqXvPGPGXa2z5xUTmV7VDcZyvRZ+QQXkXTZQ=
 golang.org/x/sync v0.0.0-20181108010431-42b317875d0f/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
+golang.org/x/sync v0.0.0-20190227155943-e225da77a7e6/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sys v0.0.0-20180905080454-ebe1bf3edb33/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
 golang.org/x/sys v0.0.0-20181205085412-a5c9d58dba9a h1:1n5lsVfiQW3yfsRGu98756EH1YthsFqr/5mxHduZW2A=
 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 v0.0.0-20190312061237-fead79001313/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20190322080309-f49334f85ddc h1:4gbWbmmPFp4ySWICouJl6emP0MyS31yy9SrTlAGFT+g=
+golang.org/x/sys v0.0.0-20190322080309-f49334f85ddc/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/text v0.3.0 h1:g61tztE5qeGQ89tm6NTjjM9VPIm088od1l6aSorWRWg=
 golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
 golang.org/x/tools v0.0.0-20180221164845-07fd8470d635/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
+golang.org/x/tools v0.0.0-20181030221726-6c7e314b6563/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
+golang.org/x/tools v0.0.0-20190312151545-0bb0c0a6e846/go.mod h1:LCzVGOaR6xXOjkQ3onu1FJEFr0SW1gC7cKk1uF8kGRs=
+golang.org/x/tools v0.0.0-20190321232350-e250d351ecad/go.mod h1:LCzVGOaR6xXOjkQ3onu1FJEFr0SW1gC7cKk1uF8kGRs=
+gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405 h1:yhCVgyC4o1eVCa2tZl7eS0r+SDo693bJlVdllGtEeKM=
 gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
-gopkg.in/vmihailenco/msgpack.v2 v2.9.1 h1:kb0VV7NuIojvRfzwslQeP3yArBqJHW9tOl4t38VS1jM=
-gopkg.in/vmihailenco/msgpack.v2 v2.9.1/go.mod h1:/3Dn1Npt9+MYyLpYYXjInO/5jvMLamn+AEGwNEOatn8=
+gopkg.in/check.v1 v1.0.0-20180628173108-788fd7840127/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
 gopkg.in/yaml.v2 v2.2.2 h1:ZCJp+EgiOT7lHqUV2J862kp8Qj64Jo6az82+3Td9dZw=
 gopkg.in/yaml.v2 v2.2.2/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=

internal/datafile.go

@@ -1,15 +1,17 @@
-package bitcask
+package internal
 
 import (
+	"bytes"
 	"fmt"
 	"os"
 	"path/filepath"
 	"sync"
 
 	"github.com/pkg/errors"
+	"golang.org/x/exp/mmap"
 
-	pb "github.com/prologic/bitcask/proto"
-	"github.com/prologic/bitcask/streampb"
+	pb "github.com/prologic/bitcask/internal/proto"
+	"github.com/prologic/bitcask/internal/streampb"
 )
 
 const (
@@ -17,7 +19,8 @@ const (
 )
 
 var (
-	ErrReadonly = errors.New("error: read only datafile")
+	ErrReadonly  = errors.New("error: read only datafile")
+	ErrReadError = errors.New("error: read error")
 )
 
 type Datafile struct {
@@ -25,6 +28,7 @@ type Datafile struct {
 
 	id     int
 	r      *os.File
+	ra     *mmap.ReaderAt
 	w      *os.File
 	offset int64
 	dec    *streampb.Decoder
@@ -34,6 +38,7 @@ type Datafile struct {
 func NewDatafile(path string, id int, readonly bool) (*Datafile, error) {
 	var (
 		r   *os.File
+		ra  *mmap.ReaderAt
 		w   *os.File
 		err error
 	)
@@ -56,6 +61,11 @@ func NewDatafile(path string, id int, readonly bool) (*Datafile, error) {
 		return nil, errors.Wrap(err, "error calling Stat()")
 	}
 
+	ra, err = mmap.Open(fn)
+	if err != nil {
+		return nil, err
+	}
+
 	offset := stat.Size()
 
 	dec := streampb.NewDecoder(r)
@@ -64,6 +74,7 @@ func NewDatafile(path string, id int, readonly bool) (*Datafile, error) {
 	return &Datafile{
 		id:     id,
 		r:      r,
+		ra:     ra,
 		w:      w,
 		offset: offset,
 		dec:    dec,
@@ -71,12 +82,20 @@ func NewDatafile(path string, id int, readonly bool) (*Datafile, error) {
 	}, nil
 }
 
+func (df *Datafile) FileID() int {
+	return df.id
+}
+
 func (df *Datafile) Name() string {
 	return df.r.Name()
 }
 
 func (df *Datafile) Close() error {
 	if df.w == nil {
+		err := df.ra.Close()
+		if err != nil {
+			return err
+		}
 		return df.r.Close()
 	}
 
@@ -94,34 +113,51 @@ func (df *Datafile) Sync() error {
 	return df.w.Sync()
 }
 
-func (df *Datafile) Size() (int64, error) {
+func (df *Datafile) Size() int64 {
 	df.RLock()
 	defer df.RUnlock()
-	return df.offset, nil
+	return df.offset
 }
 
-func (df *Datafile) Read() (e pb.Entry, err error) {
+func (df *Datafile) Read() (e pb.Entry, n int64, err error) {
 	df.Lock()
 	defer df.Unlock()
 
-	return e, df.dec.Decode(&e)
-}
-
-func (df *Datafile) ReadAt(index int64) (e pb.Entry, err error) {
-	df.Lock()
-	defer df.Unlock()
-
-	_, err = df.r.Seek(index, os.SEEK_SET)
+	n, err = df.dec.Decode(&e)
 	if err != nil {
 		return
 	}
 
-	return e, df.dec.Decode(&e)
+	return
 }
 
-func (df *Datafile) Write(e pb.Entry) (int64, error) {
+func (df *Datafile) ReadAt(index, size int64) (e pb.Entry, err error) {
+	var n int
+
+	b := make([]byte, size)
+
 	if df.w == nil {
-		return -1, ErrReadonly
+		n, err = df.ra.ReadAt(b, index)
+	} else {
+		n, err = df.r.ReadAt(b, index)
+	}
+	if err != nil {
+		return
+	}
+	if int64(n) != size {
+		err = ErrReadError
+		return
+	}
+
+	buf := bytes.NewBuffer(b)
+	dec := streampb.NewDecoder(buf)
+	_, err = dec.Decode(&e)
+	return
+}
+
+func (df *Datafile) Write(e pb.Entry) (int64, int64, error) {
+	if df.w == nil {
+		return -1, 0, ErrReadonly
 	}
 
 	df.Lock()
@@ -131,9 +167,9 @@ func (df *Datafile) Write(e pb.Entry) (int64, error) {
 
 	n, err := df.enc.Encode(&e)
 	if err != nil {
-		return -1, err
+		return -1, 0, err
 	}
 	df.offset += n
 
-	return e.Offset, nil
+	return e.Offset, n, nil
 }

internal/entry.go

@@ -1,9 +1,9 @@
-package bitcask
+package internal
 
 import (
 	"hash/crc32"
 
-	pb "github.com/prologic/bitcask/proto"
+	pb "github.com/prologic/bitcask/internal/proto"
 )
 
 func NewEntry(key string, value []byte) pb.Entry {

internal/keydir.go

@@ -1,4 +1,4 @@
-package bitcask
+package internal
 
 import (
 	"bytes"
@@ -11,6 +11,7 @@ import (
 type Item struct {
 	FileID int
 	Offset int64
+	Size   int64
 }
 
 type Keydir struct {
@@ -24,10 +25,11 @@ func NewKeydir() *Keydir {
 	}
 }
 
-func (k *Keydir) Add(key string, fileid int, offset int64) Item {
+func (k *Keydir) Add(key string, fileid int, offset, size int64) Item {
 	item := Item{
 		FileID: fileid,
 		Offset: offset,
+		Size:   size,
 	}
 
 	k.Lock()
@@ -52,11 +54,17 @@ func (k *Keydir) Delete(key string) {
 	delete(k.kv, key)
 }
 
+func (k *Keydir) Len() int {
+	return len(k.kv)
+}
+
 func (k *Keydir) Keys() chan string {
 	ch := make(chan string)
 	go func() {
-		for k := range k.kv {
-			ch <- k
+		k.RLock()
+		defer k.RUnlock()
+		for key := range k.kv {
+			ch <- key
 		}
 		close(ch)
 	}()

internal/streampb/stream.go

@@ -66,12 +66,12 @@ type Decoder struct {
 
 // Decode takes a proto.Message and unmarshals the next payload in the
 // underlying io.Reader. It returns an EOF when it's done.
-func (d *Decoder) Decode(v proto.Message) error {
+func (d *Decoder) Decode(v proto.Message) (int64, error) {
 	prefixBuf := make([]byte, prefixSize)
 
 	_, err := io.ReadFull(d.r, prefixBuf)
 	if err != nil {
-		return err
+		return 0, err
 	}
 
 	n := binary.BigEndian.Uint64(prefixBuf)
@@ -82,11 +82,11 @@ func (d *Decoder) Decode(v proto.Message) error {
 	for idx < n {
 		m, err := d.r.Read(buf[idx:n])
 		if err != nil {
-			return errors.Wrap(translateError(err), "failed reading marshaled data")
+			return 0, errors.Wrap(translateError(err), "failed reading marshaled data")
 		}
 		idx += uint64(m)
 	}
-	return proto.Unmarshal(buf[:n], v)
+	return int64(idx + prefixSize), proto.Unmarshal(buf[:n], v)
 }
 
 func translateError(err error) error {

internal/utils.go

@@ -1,4 +1,4 @@
-package bitcask
+package internal
 
 import (
 	"fmt"
@@ -8,7 +8,7 @@ import (
 	"strings"
 )
 
-func getDatafiles(path string) ([]string, error) {
+func GetDatafiles(path string) ([]string, error) {
 	fns, err := filepath.Glob(fmt.Sprintf("%s/*.data", path))
 	if err != nil {
 		return nil, err
@@ -17,7 +17,7 @@ func getDatafiles(path string) ([]string, error) {
 	return fns, nil
 }
 
-func parseIds(fns []string) ([]int, error) {
+func ParseIds(fns []string) ([]int, error) {
 	var ids []int
 	for _, fn := range fns {
 		fn = filepath.Base(fn)

internal/version.go

@@ -1,4 +1,4 @@
-package bitcask
+package internal
 
 import (
 	"fmt"

internal/version_test.go

@@ -1,4 +1,4 @@
-package bitcask
+package internal
 
 import (
 	"fmt"

options.go

@@ -1,47 +1,53 @@
 package bitcask
 
 const (
+	// DefaultMaxDatafileSize is the default maximum datafile size in bytes
 	DefaultMaxDatafileSize = 1 << 20 // 1MB
-	DefaultMaxKeySize      = 64      // 64 bytes
-	DefaultMaxValueSize    = 1 << 16 // 65KB
+
+	// DefaultMaxKeySize is the default maximum key size in bytes
+	DefaultMaxKeySize = 64 // 64 bytes
+
+	// DefaultMaxValueSize is the default value size in bytes
+	DefaultMaxValueSize = 1 << 16 // 65KB
 )
 
-// Option ...
-type Option option
-
-type option func(*config) error
+// Option is a function that takes a config struct and modifies it
+type Option func(*config) error
 
 type config struct {
-	MaxDatafileSize int
-	MaxKeySize      int
-	MaxValueSize    int
+	maxDatafileSize int
+	maxKeySize      int
+	maxValueSize    int
 }
 
-func NewDefaultConfig() *config {
+func newDefaultConfig() *config {
 	return &config{
-		MaxDatafileSize: DefaultMaxDatafileSize,
-		MaxKeySize:      DefaultMaxKeySize,
-		MaxValueSize:    DefaultMaxValueSize,
+		maxDatafileSize: DefaultMaxDatafileSize,
+		maxKeySize:      DefaultMaxKeySize,
+		maxValueSize:    DefaultMaxValueSize,
 	}
 }
 
-func WithMaxDatafileSize(size int) option {
+// WithMaxDatafileSize sets the maximum datafile size option
+func WithMaxDatafileSize(size int) Option {
 	return func(cfg *config) error {
-		cfg.MaxDatafileSize = size
+		cfg.maxDatafileSize = size
 		return nil
 	}
 }
 
-func WithMaxKeySize(size int) option {
+// WithMaxKeySize sets the maximum key size option
+func WithMaxKeySize(size int) Option {
 	return func(cfg *config) error {
-		cfg.MaxKeySize = size
+		cfg.maxKeySize = size
 		return nil
 	}
 }
 
-func WithMaxValueSize(size int) option {
+// WithMaxValueSize sets the maximum value size option
+func WithMaxValueSize(size int) Option {
 	return func(cfg *config) error {
-		cfg.MaxValueSize = size
+		cfg.maxValueSize = size
 		return nil
 	}
 }