// 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 synchronized using the msync(2) syscall.
const IgnoreNoSync = runtime.GOOS == "openbsd"
// Default values if not set in a DB instance.
const (
DefaultMaxBatchSize int =s 1000
DefaultMaxBatchDelay = 10 * time.Millisecond
// 16k
DefaultAllocSize = 16 * 1024 * 1024
)
// default page size for db is set to the OS page size.
var defaultPageSize = os.Getpagesize()
// 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
// When true, skips the truncate call when growing the database.
// Setting this to true is only safe on non-ext3/ext4 systems.
// Skipping truncation avoids preallocation of hard drive space and
// bypasses a truncate() and fsync() syscall on remapping.
//
// https://github.com/boltdb/bolt/issues/284
NoGrowSync bool
// If you want to read the entire database fast, you can set MmapFlag to
// syscall.MAP_POPULATE on Linux 2.6.23+ for sequential read-ahead.
MmapFlags int
// 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
// AllocSize is the amount of space allocated when the database
// needs to create new pages. This is done to amortize the cost
// of truncate() and fsync() when growing the data file.
AllocSize int
path string
file *os.File // 真实存储数据的磁盘文件
lockfile *os.File // windows only
dataref []byte // mmap'ed readonly, write throws SEGV
// 通过mmap映射进来的地址
data *[maxMapSize]byte
datasz int
filesz int // current on disk file size
// 元数据
meta0 *meta
meta1 *meta
pageSize int
opened bool
rwtx *Tx // 写事务锁
txs []*Tx // 读事务数组
freelist *freelist // 空闲列表
stats Stats
pagePool sync.Pool
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)
}
// Read only mode.
// When true, Update() and Begin(true) return ErrDatabaseReadOnly immediately.
readOnly bool
}
Open()方法主要用来创建一个boltdb的DB对象，底层会执行新建或者打开存储数据的文件，当指定的文件不存在时， boltdb就会新建一个数据文件。否则的话，就直接加载指定的数据库文件内容。
// 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
}
db.NoGrowSync = options.NoGrowSync
db.MmapFlags = options.MmapFlags
// Set default values for later DB operations.
db.MaxBatchSize = DefaultMaxBatchSize
db.MaxBatchDelay = DefaultMaxBatchDelay
db.AllocSize = DefaultAllocSize
flag := os.O_RDWR
if options.ReadOnly {
flag = os.O_RDONLY
db.readOnly = true
}
// Open data file and separate sync handler for metadata writes.
db.path = path
var err error
// 打开db文件
if db.file, err = os.OpenFile(db.path, flag|os.O_CREATE, mode); err != nil {
_ = db.close()
return nil, err
}
// Lock file so that other processes using Bolt in read-write mode cannot
// use the database at the same time. This would cause corruption since
// the two processes would write meta pages and free pages separately.
// The database file is locked exclusively (only one process can grab the lock)
// if !options.ReadOnly.
// The database file is locked using the shared lock (more than one process may
// hold a lock at the same time) otherwise (options.ReadOnly is set).
if err := flock(db, mode, !db.readOnly, 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, err
} else if info.Size() == 0 {
// Initialize new files with meta pages.
// 初始化新db文件
if err := db.init(); err != nil {
return nil, err
}
} else {
// 不是新文件，读取第一页元数据
// Read the first meta page to determine the page size.
// 2^12,正好是4k
var buf [0x1000]byte
if _, err := db.file.ReadAt(buf[:], 0); err == nil {
// 仅仅是读取了pageSize
m := db.pageInBuffer(buf[:], 0).meta()
if err := m.validate(); err != nil {
// If we can't read the page size, we can assume it's the same
// as the OS -- since that's how the page size was chosen in the
// first place.
//
// If the first page is invalid and this OS uses a different
// page size than what the database was created with then we
// are out of luck and cannot access the database.
db.pageSize = os.Getpagesize()
} else {
db.pageSize = int(m.pageSize)
}
}
}
// Memory map the data file.
// mmap映射db文件数据到内存
if err := db.mmap(options.InitialMmapSize); err != nil {
_ = db.close()
return nil, err
}
// Read in the freelist.
db.freelist = newFreelist()
// 读第二页的数据，然后建立起freelist中
db.freelist.read(db.page(db.meta().freelist)) // db.meta().freelist=2
// Mark the database as opened and return.
return db, nil
}
新建时：
会调用init()方法，内部主要是新建一个文件，然后第0页、第1页写入元数据信息；第2页写入freelist信息；第3页写入bucket leaf信息。并最终刷盘。
// 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)
// 第0页和第1页存放元数据
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)
m.checksum = m.sum64()
}
// Write an empty freelist at page 3.
// 拿到第2页存放freelist
p := db.pageInBuffer(buf[:], pgid(2))
p.id = pgid(2)
p.flags = freelistPageFlag
p.count = 0
// 第三块存放叶子page
// 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.
// 写入4页的数据
if _, err := db.ops.writeAt(buf, 0); err != nil {
return err
}
// 刷盘
if err := fdatasync(db); err != nil {
return err
}
return nil
}
加载时：
会读取第0页内容，也就是元信息。然后对其进行校验和校验，当校验通过后获取pageSize。否则的话，读取操作系统默认的pagesize(一般4k)
// 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)]))
}
最后都会通过mmap来映射数据。
// 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.
// 获取元数据信息
db.meta0 = db.page(0).meta()
db.meta1 = db.page(1).meta()
// Validate the meta pages. We only return an error if both meta pages fail
// validation, since meta0 failing validation means that it wasn't saved
// properly -- but we can recover using meta1. And vice-versa.
err0 := db.meta0.validate()
err1 := db.meta1.validate()
if err0 != nil && err1 != nil {
return err0
}
return nil
}
// mmapSize determines the appropriate size for the mmap given the current size
// of the database. The minimum size is 32KB 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 32KB until 1GB.
for i := uint(15); 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
}
为什么这里需要MMAP?
一般来说，因为内存比磁盘小，一般会实现 page cache 缓存部分 page，比如使用 LRU 算法。boltdb 没有实现，而是使用 mmap() 创建共享、只读的文件映射并调用 madvise(MADV_RANDOM)，由操作系统 管理 page cache；
网友评论