bolt/db.go

package bolt

import (
	"fmt"
	"hash/fnv"
	"os"
	"runtime"
	"runtime/debug"
	"strings"
	"sync"
	"time"
	"unsafe"
)

// The largest step that can be taken when remapping the mmap.
const maxMmapStep = 1 << 30 // 1GB

// The data file format version.
const version = 2

// Represents a marker value to indicate that a file is a Bolt DB.
const magic uint32 = 0xED0CDAED

// IgnoreNoSync specifies whether the NoSync field of a DB is ignored when
// syncing changes to a file.  This is required as some operating systems,
// such as OpenBSD, do not have a unified buffer cache (UBC) and writes
// must be synchronzied using the msync(2) syscall.
const IgnoreNoSync = runtime.GOOS == "openbsd"

// Default values if not set in a DB instance.
const (
	DefaultMaxBatchSize  int = 1000
	DefaultMaxBatchDelay     = 10 * time.Millisecond
)

// DB represents a collection of buckets persisted to a file on disk.
// All data access is performed through transactions which can be obtained through the DB.
// All the functions on DB will return a ErrDatabaseNotOpen if accessed before Open() is called.
type DB struct {
	// When enabled, the database will perform a Check() after every commit.
	// A panic is issued if the database is in an inconsistent state. This
	// flag has a large performance impact so it should only be used for
	// debugging purposes.
	StrictMode bool

	// Setting the NoSync flag will cause the database to skip fsync()
	// calls after each commit. This can be useful when bulk loading data
	// into a database and you can restart the bulk load in the event of
	// a system failure or database corruption. Do not set this flag for
	// normal use.
	//
	// If the package global IgnoreNoSync constant is true, this value is
	// ignored.  See the comment on that constant for more details.
	//
	// THIS IS UNSAFE. PLEASE USE WITH CAUTION.
	NoSync bool

	// MaxBatchSize is the maximum size of a batch. Default value is
	// copied from DefaultMaxBatchSize in Open.
	//
	// If <=0, disables batching.
	//
	// Do not change concurrently with calls to Batch.
	MaxBatchSize int

	// MaxBatchDelay is the maximum delay before a batch starts.
	// Default value is copied from DefaultMaxBatchDelay in Open.
	//
	// If <=0, effectively disables batching.
	//
	// Do not change concurrently with calls to Batch.
	MaxBatchDelay time.Duration

	path     string
	file     *os.File
	dataref  []byte // mmap'ed readonly, write throws SEGV
	data     *[maxMapSize]byte
	datasz   int
	meta0    *meta
	meta1    *meta
	pageSize int
	opened   bool
	rwtx     *Tx
	txs      []*Tx
	freelist *freelist
	stats    Stats

	batchMu sync.Mutex
	batch   *batch

	rwlock   sync.Mutex   // Allows only one writer at a time.
	metalock sync.Mutex   // Protects meta page access.
	mmaplock sync.RWMutex // Protects mmap access during remapping.
	statlock sync.RWMutex // Protects stats access.

	ops struct {
		writeAt func(b []byte, off int64) (n int, err error)
	}
}

// Path returns the path to currently open database file.
func (db *DB) Path() string {
	return db.path
}

// GoString returns the Go string representation of the database.
func (db *DB) GoString() string {
	return fmt.Sprintf("bolt.DB{path:%q}", db.path)
}

// String returns the string representation of the database.
func (db *DB) String() string {
	return fmt.Sprintf("DB<%q>", db.path)
}

// Open creates and opens a database at the given path.
// If the file does not exist then it will be created automatically.
// Passing in nil options will cause Bolt to open the database with the default options.
func Open(path string, mode os.FileMode, options *Options) (*DB, error) {
	var db = &DB{opened: true}

	// Set default options if no options are provided.
	if options == nil {
		options = DefaultOptions
	}

	// Set default values for later DB operations.
	db.MaxBatchSize = DefaultMaxBatchSize
	db.MaxBatchDelay = DefaultMaxBatchDelay

	// Open data file and separate sync handler for metadata writes.
	db.path = path

	var err error
	if db.file, err = os.OpenFile(db.path, os.O_RDWR|os.O_CREATE, mode); err != nil {
		_ = db.close()
		return nil, err
	}

	// Lock file so that other processes using Bolt cannot use the database
	// at the same time. This would cause corruption since the two processes
	// would write meta pages and free pages separately.
	if err := flock(db.file, options.Timeout); err != nil {
		_ = db.close()
		return nil, err
	}

	// Default values for test hooks
	db.ops.writeAt = db.file.WriteAt

	// Initialize the database if it doesn't exist.
	if info, err := db.file.Stat(); err != nil {
		return nil, fmt.Errorf("stat error: %s", err)
	} else if info.Size() == 0 {
		// Initialize new files with meta pages.
		if err := db.init(); err != nil {
			return nil, err
		}
	} else {
		// Read the first meta page to determine the page size.
		var buf [0x1000]byte
		if _, err := db.file.ReadAt(buf[:], 0); err == nil {
			m := db.pageInBuffer(buf[:], 0).meta()
			if err := m.validate(); err != nil {
				return nil, fmt.Errorf("meta0 error: %s", err)
			}
			db.pageSize = int(m.pageSize)
		}
	}

	// Memory map the data file.
	if err := db.mmap(0); err != nil {
		_ = db.close()
		return nil, err
	}

	// Read in the freelist.
	db.freelist = newFreelist()
	db.freelist.read(db.page(db.meta().freelist))

	// Mark the database as opened and return.
	return db, nil
}

// mmap opens the underlying memory-mapped file and initializes the meta references.
// minsz is the minimum size that the new mmap can be.
func (db *DB) mmap(minsz int) error {
	db.mmaplock.Lock()
	defer db.mmaplock.Unlock()

	info, err := db.file.Stat()
	if err != nil {
		return fmt.Errorf("mmap stat error: %s", err)
	} else if int(info.Size()) < db.pageSize*2 {
		return fmt.Errorf("file size too small")
	}

	// Ensure the size is at least the minimum size.
	var size = int(info.Size())
	if size < minsz {
		size = minsz
	}
	size, err = db.mmapSize(size)
	if err != nil {
		return err
	}

	// Dereference all mmap references before unmapping.
	if db.rwtx != nil {
		db.rwtx.root.dereference()
	}

	// Unmap existing data before continuing.
	if err := db.munmap(); err != nil {
		return err
	}

	// Memory-map the data file as a byte slice.
	if err := mmap(db, size); err != nil {
		return err
	}

	// Save references to the meta pages.
	db.meta0 = db.page(0).meta()
	db.meta1 = db.page(1).meta()

	// Validate the meta pages.
	if err := db.meta0.validate(); err != nil {
		return fmt.Errorf("meta0 error: %s", err)
	}
	if err := db.meta1.validate(); err != nil {
		return fmt.Errorf("meta1 error: %s", err)
	}

	return nil
}

// munmap unmaps the data file from memory.
func (db *DB) munmap() error {
	if err := munmap(db); err != nil {
		return fmt.Errorf("unmap error: " + err.Error())
	}
	return nil
}

// mmapSize determines the appropriate size for the mmap given the current size
// of the database. The minimum size is 1MB and doubles until it reaches 1GB.
// Returns an error if the new mmap size is greater than the max allowed.
func (db *DB) mmapSize(size int) (int, error) {
	// Double the size from 1MB until 1GB.
	for i := uint(20); i <= 30; i++ {
		if size <= 1<<i {
			return 1 << i, nil
		}
	}

	// Verify the requested size is not above the maximum allowed.
	if size > maxMapSize {
		return 0, fmt.Errorf("mmap too large")
	}

	// If larger than 1GB then grow by 1GB at a time.
	sz := int64(size)
	if remainder := sz % int64(maxMmapStep); remainder > 0 {
		sz += int64(maxMmapStep) - remainder
	}

	// Ensure that the mmap size is a multiple of the page size.
	// This should always be true since we're incrementing in MBs.
	pageSize := int64(db.pageSize)
	if (sz % pageSize) != 0 {
		sz = ((sz / pageSize) + 1) * pageSize
	}

	// If we've exceeded the max size then only grow up to the max size.
	if sz > maxMapSize {
		sz = maxMapSize
	}

	return int(sz), nil
}

// init creates a new database file and initializes its meta pages.
func (db *DB) init() error {
	// Set the page size to the OS page size.
	db.pageSize = os.Getpagesize()

	// Create two meta pages on a buffer.
	buf := make([]byte, db.pageSize*4)
	for i := 0; i < 2; i++ {
		p := db.pageInBuffer(buf[:], pgid(i))
		p.id = pgid(i)
		p.flags = metaPageFlag

		// Initialize the meta page.
		m := p.meta()
		m.magic = magic
		m.version = version
		m.pageSize = uint32(db.pageSize)
		m.freelist = 2
		m.root = bucket{root: 3}
		m.pgid = 4
		m.txid = txid(i)
	}

	// Write an empty freelist at page 3.
	p := db.pageInBuffer(buf[:], pgid(2))
	p.id = pgid(2)
	p.flags = freelistPageFlag
	p.count = 0

	// Write an empty leaf page at page 4.
	p = db.pageInBuffer(buf[:], pgid(3))
	p.id = pgid(3)
	p.flags = leafPageFlag
	p.count = 0

	// Write the buffer to our data file.
	if _, err := db.ops.writeAt(buf, 0); err != nil {
		return err
	}
	if err := fdatasync(db); err != nil {
		return err
	}

	return nil
}

// Close releases all database resources.
// All transactions must be closed before closing the database.
func (db *DB) Close() error {
	db.metalock.Lock()
	defer db.metalock.Unlock()
	return db.close()
}

func (db *DB) close() error {
	db.opened = false

	db.freelist = nil
	db.path = ""

	// Clear ops.
	db.ops.writeAt = nil

	// Close the mmap.
	if err := db.munmap(); err != nil {
		return err
	}

	// Close file handles.
	if db.file != nil {
		// Unlock the file.
		_ = funlock(db.file)

		// Close the file descriptor.
		if err := db.file.Close(); err != nil {
			return fmt.Errorf("db file close: %s", err)
		}
		db.file = nil
	}

	return nil
}

// Begin starts a new transaction.
// Multiple read-only transactions can be used concurrently but only one
// write transaction can be used at a time. Starting multiple write transactions
// will cause the calls to block and be serialized until the current write
// transaction finishes.
//
// IMPORTANT: You must close read-only transactions after you are finished or
// else the database will not reclaim old pages.
func (db *DB) Begin(writable bool) (*Tx, error) {
	if writable {
		return db.beginRWTx()
	}
	return db.beginTx()
}

func (db *DB) beginTx() (*Tx, error) {
	// Lock the meta pages while we initialize the transaction. We obtain
	// the meta lock before the mmap lock because that's the order that the
	// write transaction will obtain them.
	db.metalock.Lock()

	// Obtain a read-only lock on the mmap. When the mmap is remapped it will
	// obtain a write lock so all transactions must finish before it can be
	// remapped.
	db.mmaplock.RLock()

	// Exit if the database is not open yet.
	if !db.opened {
		db.mmaplock.RUnlock()
		db.metalock.Unlock()
		return nil, ErrDatabaseNotOpen
	}

	// Create a transaction associated with the database.
	t := &Tx{}
	t.init(db)

	// Keep track of transaction until it closes.
	db.txs = append(db.txs, t)
	n := len(db.txs)

	// Unlock the meta pages.
	db.metalock.Unlock()

	// Update the transaction stats.
	db.statlock.Lock()
	db.stats.TxN++
	db.stats.OpenTxN = n
	db.statlock.Unlock()

	return t, nil
}

func (db *DB) beginRWTx() (*Tx, error) {
	// Obtain writer lock. This is released by the transaction when it closes.
	// This enforces only one writer transaction at a time.
	db.rwlock.Lock()

	// Once we have the writer lock then we can lock the meta pages so that
	// we can set up the transaction.
	db.metalock.Lock()
	defer db.metalock.Unlock()

	// Exit if the database is not open yet.
	if !db.opened {
		db.rwlock.Unlock()
		return nil, ErrDatabaseNotOpen
	}

	// Create a transaction associated with the database.
	t := &Tx{writable: true}
	t.init(db)
	db.rwtx = t

	// Free any pages associated with closed read-only transactions.
	var minid txid = 0xFFFFFFFFFFFFFFFF
	for _, t := range db.txs {
		if t.meta.txid < minid {
			minid = t.meta.txid
		}
	}
	if minid > 0 {
		db.freelist.release(minid - 1)
	}

	return t, nil
}

// removeTx removes a transaction from the database.
func (db *DB) removeTx(tx *Tx) {
	// Release the read lock on the mmap.
	db.mmaplock.RUnlock()

	// Use the meta lock to restrict access to the DB object.
	db.metalock.Lock()

	// Remove the transaction.
	for i, t := range db.txs {
		if t == tx {
			db.txs = append(db.txs[:i], db.txs[i+1:]...)
			break
		}
	}
	n := len(db.txs)

	// Unlock the meta pages.
	db.metalock.Unlock()

	// Merge statistics.
	db.statlock.Lock()
	db.stats.OpenTxN = n
	db.stats.TxStats.add(&tx.stats)
	db.statlock.Unlock()
}

// Update executes a function within the context of a read-write managed transaction.
// If no error is returned from the function then the transaction is committed.
// If an error is returned then the entire transaction is rolled back.
// Any error that is returned from the function or returned from the commit is
// returned from the Update() method.
//
// Attempting to manually commit or rollback within the function will cause a panic.
func (db *DB) Update(fn func(*Tx) error) error {
	t, err := db.Begin(true)
	if err != nil {
		return err
	}

	// Make sure the transaction rolls back in the event of a panic.
	defer func() {
		if t.db != nil {
			t.rollback()
		}
	}()

	// Mark as a managed tx so that the inner function cannot manually commit.
	t.managed = true

	// If an error is returned from the function then rollback and return error.
	err = fn(t)
	t.managed = false
	if err != nil {
		_ = t.Rollback()
		return err
	}

	return t.Commit()
}

// View executes a function within the context of a managed read-only transaction.
// Any error that is returned from the function is returned from the View() method.
//
// Attempting to manually rollback within the function will cause a panic.
func (db *DB) View(fn func(*Tx) error) error {
	t, err := db.Begin(false)
	if err != nil {
		return err
	}

	// Make sure the transaction rolls back in the event of a panic.
	defer func() {
		if t.db != nil {
			t.rollback()
		}
	}()

	// Mark as a managed tx so that the inner function cannot manually rollback.
	t.managed = true

	// If an error is returned from the function then pass it through.
	err = fn(t)
	t.managed = false
	if err != nil {
		_ = t.Rollback()
		return err
	}

	if err := t.Rollback(); err != nil {
		return err
	}

	return nil
}

// Stats retrieves ongoing performance stats for the database.
// This is only updated when a transaction closes.
func (db *DB) Stats() Stats {
	db.statlock.RLock()
	defer db.statlock.RUnlock()
	return db.stats
}

// This is for internal access to the raw data bytes from the C cursor, use
// carefully, or not at all.
func (db *DB) Info() *Info {
	return &Info{uintptr(unsafe.Pointer(&db.data[0])), db.pageSize}
}

// page retrieves a page reference from the mmap based on the current page size.
func (db *DB) page(id pgid) *page {
	pos := id * pgid(db.pageSize)
	return (*page)(unsafe.Pointer(&db.data[pos]))
}

// pageInBuffer retrieves a page reference from a given byte array based on the current page size.
func (db *DB) pageInBuffer(b []byte, id pgid) *page {
	return (*page)(unsafe.Pointer(&b[id*pgid(db.pageSize)]))
}

// meta retrieves the current meta page reference.
func (db *DB) meta() *meta {
	if db.meta0.txid > db.meta1.txid {
		return db.meta0
	}
	return db.meta1
}

// allocate returns a contiguous block of memory starting at a given page.
func (db *DB) allocate(count int) (*page, error) {
	// Allocate a temporary buffer for the page.
	buf := make([]byte, count*db.pageSize)
	p := (*page)(unsafe.Pointer(&buf[0]))
	p.overflow = uint32(count - 1)

	// Use pages from the freelist if they are available.
	if p.id = db.freelist.allocate(count); p.id != 0 {
		return p, nil
	}

	// Resize mmap() if we're at the end.
	p.id = db.rwtx.meta.pgid
	var minsz = int((p.id+pgid(count))+1) * db.pageSize
	if minsz >= db.datasz {
		if err := db.mmap(minsz); err != nil {
			return nil, fmt.Errorf("mmap allocate error: %s", err)
		}
	}

	// Move the page id high water mark.
	db.rwtx.meta.pgid += pgid(count)

	return p, nil
}

// Options represents the options that can be set when opening a database.
type Options struct {
	// Timeout is the amount of time to wait to obtain a file lock.
	// When set to zero it will wait indefinitely. This option is only
	// available on Darwin and Linux.
	Timeout time.Duration
}

// DefaultOptions represent the options used if nil options are passed into Open().
// No timeout is used which will cause Bolt to wait indefinitely for a lock.
var DefaultOptions = &Options{
	Timeout: 0,
}

// Stats represents statistics about the database.
type Stats struct {
	// Freelist stats
	FreePageN     int // total number of free pages on the freelist
	PendingPageN  int // total number of pending pages on the freelist
	FreeAlloc     int // total bytes allocated in free pages
	FreelistInuse int // total bytes used by the freelist

	// Transaction stats
	TxN     int // total number of started read transactions
	OpenTxN int // number of currently open read transactions

	TxStats TxStats // global, ongoing stats.
}

// Sub calculates and returns the difference between two sets of database stats.
// This is useful when obtaining stats at two different points and time and
// you need the performance counters that occurred within that time span.
func (s *Stats) Sub(other *Stats) Stats {
	if other == nil {
		return *s
	}
	var diff Stats
	diff.FreePageN = s.FreePageN
	diff.PendingPageN = s.PendingPageN
	diff.FreeAlloc = s.FreeAlloc
	diff.FreelistInuse = s.FreelistInuse
	diff.TxN = other.TxN - s.TxN
	diff.TxStats = s.TxStats.Sub(&other.TxStats)
	return diff
}

func (s *Stats) add(other *Stats) {
	s.TxStats.add(&other.TxStats)
}

type Info struct {
	Data     uintptr
	PageSize int
}

type meta struct {
	magic    uint32
	version  uint32
	pageSize uint32
	flags    uint32
	root     bucket
	freelist pgid
	pgid     pgid
	txid     txid
	checksum uint64
}

// validate checks the marker bytes and version of the meta page to ensure it matches this binary.
func (m *meta) validate() error {
	if m.checksum != 0 && m.checksum != m.sum64() {
		return ErrChecksum
	} else if m.magic != magic {
		return ErrInvalid
	} else if m.version != version {
		return ErrVersionMismatch
	}
	return nil
}

// copy copies one meta object to another.
func (m *meta) copy(dest *meta) {
	*dest = *m
}

// write writes the meta onto a page.
func (m *meta) write(p *page) {
	if m.root.root >= m.pgid {
		panic(fmt.Sprintf("root bucket pgid (%d) above high water mark (%d)", m.root.root, m.pgid))
	} else if m.freelist >= m.pgid {
		panic(fmt.Sprintf("freelist pgid (%d) above high water mark (%d)", m.freelist, m.pgid))
	}

	// Page id is either going to be 0 or 1 which we can determine by the transaction ID.
	p.id = pgid(m.txid % 2)
	p.flags |= metaPageFlag

	// Calculate the checksum.
	m.checksum = m.sum64()

	m.copy(p.meta())
}

// generates the checksum for the meta.
func (m *meta) sum64() uint64 {
	var h = fnv.New64a()
	_, _ = h.Write((*[unsafe.Offsetof(meta{}.checksum)]byte)(unsafe.Pointer(m))[:])
	return h.Sum64()
}

// _assert will panic with a given formatted message if the given condition is false.
func _assert(condition bool, msg string, v ...interface{}) {
	if !condition {
		panic(fmt.Sprintf("assertion failed: "+msg, v...))
	}
}

func warn(v ...interface{})              { fmt.Fprintln(os.Stderr, v...) }
func warnf(msg string, v ...interface{}) { fmt.Fprintf(os.Stderr, msg+"\n", v...) }

func printstack() {
	stack := strings.Join(strings.Split(string(debug.Stack()), "\n")[2:], "\n")
	fmt.Fprintln(os.Stderr, stack)
}