leveldb的数据存储采用LSM的思想，将随机写入变为顺序写入，记录写入操作日志，一旦日志被以追加写的形式写入硬盘，就返回写入成功，由后台线程将写入日志作用于原有的磁盘文件生成新的磁盘数据.Leveldb在内存中维护一个数据结构memtable,采用skiplist来实现，保存当前写入的数据，当数据达到一定规模后变为不可写的内存表immutable table.新的写入操作会写入新的memtable，而immutable table会被后台线程写入到数据文件.Leveldb的数据文件是按层存放的，默认配置的最高层级是7，即level0，level1,…,level7.内存中的immutable总是写入level0,除level0之外的各个层leveli的所有数据文件的key范围都是互相不相交的.当满足一定条件时，leveli的数据文件会和leveli+1的数据文件进行merge,产生新的leveli+1层级的文件,这个磁盘文件的merge过程和immutable的dump过程叫做Compaction，在leveldb中是由一个单独的后台线程来完成的.
进行Compaction操作的条件如下:
1.产生了新的immutable table需要写入数据文件
2.某个level的数据规模过大
3.某个文件被无效查询的次数过多（在文件i中查询key,没有找到key,这次查询称为文件i的无效查询）
4.手动compaction
满足以上条件会启动Compaction过程，接下来分析详细的Compaction过程.
Leveldb进行Compaction的入口函数是db文件夹下db_impl.cc文件中的DBImpl::MaybeScheduleCompaction，该函数在每次leveldb进行读写操作时都有可能被调用.源码内容如下:
void DBImpl::MaybeScheduleCompaction() {
mutex_.AssertHeld();
if (bg_compaction_scheduled_) {
// Already scheduled
} else if (shutting_down_.Acquire_Load()) {
// DB is being deleted; no more background compactions
} else if (!bg_error_.ok()) {
// Already got an error; no more changes
} else if (imm_ == NULL &&
manual_compaction_ == NULL &&
!versions_->NeedsCompaction()) {
// No work to be done
} else {
bg_compaction_scheduled_ = true;
env_->Schedule(&DBImpl::BGWork, this); //新建后台任务并进行调度
}
}
首先调用db文件夹下version_set.h中的NeedsCompaction()判断是否需要启动Compact任务.源码内容如下：
// Returns true iff some level needs a compaction.
bool NeedsCompaction() const {
Version* v = current_;
return (v->compaction_score_ >= ) || (v->file_to_compact_ != NULL);
}
version_set.cc中compaction_score_ 的计算如下：
void VersionSet::Finalize(Version* v) {
// Precomputed best level for next compaction
int best_level = -;
double best_score = -;
for (int level = ; level < config::kNumLevels-; level++) {
double score;
if (level == ) {
// We treat level-0 specially by bounding the number of files
// instead of number of bytes for two reasons:
//
// (1) With larger write-buffer sizes, it is nice not to do too
// many level-0 compactions.
//
// (2) The files in level-0 are merged on every read and
// therefore we wish to avoid too many files when the individual
// file size is small (perhaps because of a small write-buffer
// setting, or very high compression ratios, or lots of
// overwrites/deletions).
score = v->files_[level].size() /
static_cast<double>(config::kL0_CompactionTrigger);
} else {
// Compute the ratio of current size to size limit.
const uint64_t level_bytes = TotalFileSize(v->files_[level]);
score = static_cast<double>(level_bytes) / MaxBytesForLevel(level);
}
if (score > best_score) {
best_level = level;
best_score = score;
}
}
v->compaction_level_ = best_level;
v->compaction_score_ = best_score;
}
注意，这里同时预计算了进行compaction的最佳level.
确认需要启动compaction之后，调用util文件夹下env_posix.cc文件中的PosixEnv::Schedule函数启动Compact过程.
void PosixEnv::Schedule(void (*function)(void*), void* arg) {
PthreadCall("lock", pthread_mutex_lock(&mu_));
// Start background thread if necessary
if (!started_bgthread_) {
started_bgthread_ = true;
PthreadCall(
"create thread",
pthread_create(&bgthread_, NULL, &PosixEnv::BGThreadWrapper, this));
}
// If the queue is currently empty, the background thread may currently be
// waiting.
if (queue_.empty()) {
PthreadCall("signal", pthread_cond_signal(&bgsignal_));
}
// Add to priority queue
queue_.push_back(BGItem());
queue_.back().function = function;
queue_.back().arg = arg;
PthreadCall("unlock", pthread_mutex_unlock(&mu_));
}
如果没有后台线程，则创建后台线程，否则新建一个后台执行任务BGItem压入后台线程任务队列，然后调用PosixEnv::BGThreadWrapper唤醒后台线程:
static void* BGThreadWrapper(void* arg) {
reinterpret_cast<PosixEnv*>(arg)->BGThread();
return NULL;
}
BGThreadWrapper调用PosixEnv::BGThread,不断地从后台任务队列中拿到任务，然后执行任务
void PosixEnv::BGThread() {
while (true) {
// Wait until there is an item that is ready to run
PthreadCall("lock", pthread_mutex_lock(&mu_));
while (queue_.empty()) {
PthreadCall("wait", pthread_cond_wait(&bgsignal_, &mu_));
}
void (*function)(void*) = queue_.front().function;
void* arg = queue_.front().arg;
queue_.pop_front();
PthreadCall("unlock", pthread_mutex_unlock(&mu_));
(*function)(arg);
}
}
回到DBImpl::MaybeScheduleCompaction，方便理解起见这里再重复一遍源码
void DBImpl::MaybeScheduleCompaction() {
mutex_.AssertHeld();
if (bg_compaction_scheduled_) {
// Already scheduled
} else if (shutting_down_.Acquire_Load()) {
// DB is being deleted; no more background compactions
} else if (!bg_error_.ok()) {
// Already got an error; no more changes
} else if (imm_ == NULL &&
manual_compaction_ == NULL &&
!versions_->NeedsCompaction()) {
// No work to be done
} else {
bg_compaction_scheduled_ = true;
env_->Schedule(&DBImpl::BGWork, this); //新建后台任务并进行调度
}
}
之前分析了env_->Schedule进行的调度过程，现在来分析实际进行后台任务的DBImpl::BGWork.DBImpl::BGWork在db文件夹下db_impl.cc文件中.
void DBImpl::BGWork(void* db) {
reinterpret_cast<DBImpl*>(db)->BackgroundCall();
}
DBImpl::BGWork调用DBImpl::BackgroundCall()，合并完成后可能导致有的level的文件数过多，因此会再次调用MaybeScheduleCompaction()判断是否需要继续进行合并.
void DBImpl::BackgroundCall() {
MutexLock l(&mutex_);
assert(bg_compaction_scheduled_);
if (shutting_down_.Acquire_Load()) {
// No more background work when shutting down.
} else if (!bg_error_.ok()) {
// No more background work after a background error.
} else {
BackgroundCompaction();
}
bg_compaction_scheduled_ = false;
// Previous compaction may have produced too many files in a level,
// so reschedule another compaction if needed.
MaybeScheduleCompaction();
bg_cv_.SignalAll();
}
DBImpl::BackgroundCall()调用 BackgroundCompaction()，在BackgroundCompaction()中分别完成三种不同的Compaction：对Memtable进行合并、 trivial Compaction（直接将文件移动到下一层）以及一般的合并，调用DoCompactionWork()实现.
void DBImpl::BackgroundCompaction() {
mutex_.AssertHeld();
if (imm_ != NULL) {
CompactMemTable();//1、对Memtable进行合并
return;
}
Compaction* c;
bool is_manual = (manual_compaction_ != NULL);//manual_compaction默认为NULL，则is_manual默认为false
InternalKey manual_end;
if (is_manual) { //取得手动compaction对象
ManualCompaction* m = manual_compaction_;
c = versions_->CompactRange(m->level, m->begin, m->end);
m->done = (c == NULL);
if (c != NULL) {
manual_end = c->input(, c->num_input_files() - )->largest;
}
Log(options_.info_log,
"Manual compaction at level-%d from %s .. %s; will stop at %s\n",
m->level,
(m->begin ? m->begin->DebugString().c_str() : "(begin)"),
(m->end ? m->end->DebugString().c_str() : "(end)"),
(m->done ? "(end)" : manual_end.DebugString().c_str()));
} else { //取得自动compaction对象
c = versions_->PickCompaction();
}
Status status;
if (c == NULL) {
// Nothing to do
} else if (!is_manual && c->IsTrivialMove()) {//2、IsTrivialMove 返回 True,trivial Compaction，则直接将文件移入 level + 1 层即可
// Move file to next level
assert(c->num_input_files() == );
FileMetaData* f = c->input(, );
c->edit()->DeleteFile(c->level(), f->number);
c->edit()->AddFile(c->level() + , f->number, f->file_size,
f->smallest, f->largest);
status = versions_->LogAndApply(c->edit(), &mutex_);
if (!status.ok()) {
RecordBackgroundError(status);
}
VersionSet::LevelSummaryStorage tmp;
Log(options_.info_log, "Moved #%lld to level-%d %lld bytes %s: %s\n",
static_cast<unsigned long long>(f->number),
c->level() + ,
static_cast<unsigned long long>(f->file_size),
status.ToString().c_str(),
versions_->LevelSummary(&tmp));
} else { //3、一般的合并
CompactionState* compact = new CompactionState(c);
status = DoCompactionWork(compact); //进行compaction
if (!status.ok()) {
RecordBackgroundError(status);
}
CleanupCompaction(compact);
c->ReleaseInputs(); // input的文件引用计数减少1
DeleteObsoleteFiles(); //删除无用文件
}
delete c;
if (status.ok()) {
// Done
} else if (shutting_down_.Acquire_Load()) {
// Ignore compaction errors found during shutting down
} else {
Log(options_.info_log,
"Compaction error: %s", status.ToString().c_str());
}
if (is_manual) {
ManualCompaction* m = manual_compaction_; //标记手动compaction任务完成
if (!status.ok()) {
m->done = true;
}
if (!m->done) {
// We only compacted part of the requested range. Update *m
// to the range that is left to be compacted.
m->tmp_storage = manual_end;
m->begin = &m->tmp_storage;
}
manual_compaction_ = NULL;
}
}
首行mutex_.AssertHeld()，Mutex的AssertHeld函数实现默认为空，在很多函数的实现内有调用，其作用如下：
As you have observed it does nothing in the default implementation. The function seems to be a placeholder for checking whether a particular thread holds a mutex and optionally abort if it doesn’t. This would be equivalent to the normal asserts we use for variables but applied on mutexes.
I think the reason it is not implemented yet is we don’t have an equivalent light weight function to assert whether a thread holds a lock in pthread_mutex_t used in the default implementation. Some platforms which has that capability could fill this implementation as part of porting process. Searching online I did find some implementation for this function in the windows port of leveldb. I can see one way to implement it using a wrapper class over pthread_mutex_t and setting some sort of a thread id variable to indicate which thread(s) currently holds the mutex, but it will have to be carefully implemented given the race conditions that can arise.
Memtable的合并
Compaction首先检查imm_，及时将已写满的memtable写入磁盘sstable文件，对Memtable的合并，调用DBImpl::CompactMemTable()完成：
void DBImpl::CompactMemTable() {
mutex_.AssertHeld();
assert(imm_ != NULL);//imm_不能为空
VersionEdit edit;
Version* base = versions_->current();
base->Ref();
Status s = WriteLevel0Table(imm_, &edit, base);//将Memtable转化为.sst文件，写入level0 sst table,并写入到edit中
base->Unref();
if (s.ok()) {
edit.SetPrevLogNumber();
edit.SetLogNumber(logfile_number_); // Earlier logs no longer needed
s = versions_->LogAndApply(&edit, &mutex_);//应用edit中记录的变化，来生成新的版本
}
if (s.ok()) {
// Commit to the new state
imm_->Unref();
imm_ = NULL;
has_imm_.Release_Store(NULL);
DeleteObsoleteFiles();
} else {
RecordBackgroundError(s);
}
}
其中CompactMemTable()主要调用了两个函数：WriteLevel0Table()和versions_->LogAndApply()
CompactMemTable()首先调用WriteLevel0Table()，源码内容如下：
Status DBImpl::WriteLevel0Table(MemTable* mem, VersionEdit* edit,
Version* base) {
mutex_.AssertHeld();
FileMetaData meta;
meta.number = versions_->NewFileNumber();//获取新生成的.sst文件的编号
pending_outputs_.insert(meta.number);
Iterator* iter = mem->NewIterator();//用于遍历Memtable中的数据 Status s;
{
mutex_.Unlock();
s = BuildTable(dbname_, env_, options_, table_cache_, iter, &meta);//创建.sst文件，并将其相关信息记录在meta中
mutex_.Lock();
} delete iter; //iter用完之后一定要删除
pending_outputs_.erase(meta.number); int level = ;
if (s.ok() && meta.file_size > ) {
const Slice min_user_key = meta.smallest.user_key();
const Slice max_user_key = meta.largest.user_key();
if (base != NULL) {
level = base->PickLevelForMemTableOutput(min_user_key, max_user_key);//为合并的输出文件选择合适的level
}
edit->AddFile(level, meta.number, meta.file_size,meta.smallest, meta.largest);//将生成的.sst文件加入到该level
}
return s;
}
WriteLevel0Table()首先调用BuildTable()将Immutable Memtable中所有的数据写入到一个.sst文件中，并将.sst文件的信息（文件编号，Key值范围，文件大小）记录到变量meta中.由于Memtable是基于Skiplist的，是一个有序表，因此在写入.sst文件时，Key值也是从小到大来排列的.可以发现，将Memtable中的数据转换为SSTable时，是将所有记录都写入SSTable的，要删除的记录也一样.删除操作会在更高level的Compaction中完成.因此level 0中可能会存在Key值相同的记录.
Status BuildTable(const std::string& dbname,
Env* env,
const Options& options,
TableCache* table_cache,
Iterator* iter,
FileMetaData* meta) {
Status s;
meta->file_size = ;
iter->SeekToFirst();
std::string fname = TableFileName(dbname, meta->number);//获得新建表名字
if (iter->Valid()) {
WritableFile* file;
s = env->NewWritableFile(fname, &file); //建立新的表文件，后续写入数据
if (!s.ok()) {
return s;
}
TableBuilder* builder = new TableBuilder(options, file); //建立TableBuilder
meta->smallest.DecodeFrom(iter->key());
for (; iter->Valid(); iter->Next()) { //将key/value对加入builder
Slice key = iter->key();
meta->largest.DecodeFrom(key);
builder->Add(key, iter->value());
} // Finish and check for builder errors
s = builder->Finish(); //构建indexhandler,metahandler,写入文件
if (s.ok()) {
meta->file_size = builder->FileSize();
assert(meta->file_size > );
}
delete builder; // Finish and check for file errors
if (s.ok()) {
s = file->Sync(); //写入文件
}
if (s.ok()) {
s = file->Close();
}
delete file;
file = NULL; if (s.ok()) {
// Verify that the table is usable
Iterator* it = table_cache->NewIterator(ReadOptions(),
meta->number,
meta->file_size); //将表结构加入表缓存
s = it->status();
delete it;
}
} // Check for input iterator errors
if (!iter->status().ok()) {
s = iter->status();
} if (s.ok() && meta->file_size > ) {
// Keep it
} else {
env->DeleteFile(fname);
}
return s;
}
该函数利用iter向TableBuilder中加入key/value对，然后写入文件并同步，将新生成的Table结构加入tablecache以备后用.
table_builder文件在table文件夹下，其中TableBuilder::Add函数流程如下：
void TableBuilder::Add(const Slice& key, const Slice& value) {
Rep* r = rep_;
assert(!r->closed);
if (!ok()) return;
if (r->num_entries > ) {
assert(r->options.comparator->Compare(key, Slice(r->last_key)) > );
}
if (r->pending_index_entry) {//新的block开始
assert(r->data_block.empty());
r->options.comparator->FindShortestSeparator(&r->last_key, key);
std::string handle_encoding;
r->pending_handle.EncodeTo(&handle_encoding);
r->index_block.Add(r->last_key, Slice(handle_encoding));
r->pending_index_entry = false;
}
//计算filter
if (r->filter_block != NULL) {
r->filter_block->AddKey(key);
}
//加入blockbuilder
r->last_key.assign(key.data(), key.size());
r->num_entries++;
r->data_block.Add(key, value);
// block大于配置的尺寸(默认为4k)则结束该block，输出后开启新的Block。
const size_t estimated_block_size = r->data_block.CurrentSizeEstimate();
if (estimated_block_size >= r->options.block_size) {
Flush();
}
}
将Block结构写入文件的TableBuilder::WriteBlock函数流程如下：
void TableBuilder::WriteBlock(BlockBuilder* block, BlockHandle* handle) {
// File format contains a sequence of blocks where each block has:
// block_data: uint8[n]
// type: uint8
// crc: uint32
assert(ok());
Rep* r = rep_;
Slice raw = block->Finish(); //取得block格式化数据
Slice block_contents;
//获取是否压缩配置选项
CompressionType type = r->options.compression;
// TODO(postrelease): Support more compression options: zlib?
switch (type) {
case kNoCompression:
block_contents = raw;
break;
case kSnappyCompression: {
std::string* compressed = &r->compressed_output;
if (port::Snappy_Compress(raw.data(), raw.size(), compressed) &&
compressed->size() < raw.size() - (raw.size() / 8u)) {
block_contents = *compressed;
} else {
// Snappy not supported, or compressed less than 12.5%, so just
// store uncompressed form
block_contents = raw;
type = kNoCompression;
}
break;
}
}
//进行压缩后，然后写入文件，blockdata+type+crc32
WriteRawBlock(block_contents, type, handle);
r->compressed_output.clear();
block->Reset();
}
而TableBuilder::Finish的函数定义如下：
Status TableBuilder::Finish() {
Rep* r = rep_;
Flush();//将block数据写入,可能不是满的block
assert(!r->closed);
r->closed = true;
BlockHandle filter_block_handle, metaindex_block_handle, index_block_handle;
// Write filter block
if (ok() && r->filter_block != NULL) {
WriteRawBlock(r->filter_block->Finish(), kNoCompression,
&filter_block_handle);
}
// Write metaindex block
if (ok()) {
BlockBuilder meta_index_block(&r->options);
if (r->filter_block != NULL) {
// Add mapping from "filter.Name" to location of filter data
std::string key = "filter.";
key.append(r->options.filter_policy->Name());
std::string handle_encoding;
filter_block_handle.EncodeTo(&handle_encoding);
meta_index_block.Add(key, handle_encoding);
}
// TODO(postrelease): Add stats and other meta blocks
WriteBlock(&meta_index_block, &metaindex_block_handle);
}
// Write index block
if (ok()) {
if (r->pending_index_entry) {
r->options.comparator->FindShortSuccessor(&r->last_key);
std::string handle_encoding;
r->pending_handle.EncodeTo(&handle_encoding);
r->index_block.Add(r->last_key, Slice(handle_encoding));
r->pending_index_entry = false;
}
WriteBlock(&r->index_block, &index_block_handle);
}
// Write footer
if (ok()) {
Footer footer;
footer.set_metaindex_handle(metaindex_block_handle);
footer.set_index_handle(index_block_handle);
std::string footer_encoding;
footer.EncodeTo(&footer_encoding);
r->status = r->file->Append(footer_encoding);
if (r->status.ok()) {
r->offset += footer_encoding.size();
}
}
return r->status;
}
以上代码中调用的flush源码内容如下：
void TableBuilder::Flush() {
Rep* r = rep_;
assert(!r->closed);
if (!ok()) return;
if (r->data_block.empty()) return;
assert(!r->pending_index_entry);
WriteBlock(&r->data_block, &r->pending_handle);
if (ok()) {
r->pending_index_entry = true;
r->status = r->file->Flush();
}
if (r->filter_block != NULL) {
r->filter_block->StartBlock(r->offset);
}
}
然后WriteLevel0Table()调用PickLevelForMemTableOutput()为Memtable合并的输出文件选择合适的level，并调用edit->AddFile()将生成的.sst文件加入到该level中.
WriteLevel0Table()结束后，CompactMemTable()调用db文件夹下version_set.cc文件中的versions_->LogAndApply()基于当前版本和更改edit来得到一个新版本.之后会对versions_->LogAndApply()进行分析.
Trivial Compaction
由之前的分析可知，is_manual默认为false，会调用PickCompaction()来选出要进行合并的level和相应的输入文件.当c->IsTrivialMove()满足时，则直接将文件移动到下一level.
c = versions_->PickCompaction(); Status status;
if (c == NULL) {
// Nothing to do
} else if (!is_manual && c->IsTrivialMove()) {
// Move file to next level
assert(c->num_input_files() == );
FileMetaData* f = c->input(, );
c->edit()->DeleteFile(c->level(), f->number); //将文件从该层删除
c->edit()->AddFile(c->level() + , f->number, f->file_size, //将该文件加入到下一level
f->smallest, f->largest);
status = versions_->LogAndApply(c->edit(), &mutex_); //应用更改，创建新的Version
}
首先调用db文件夹下version_set.cc文件中的VersionSet::PickCompaction()为接下来的Compaction操作准备输入数据,由之前对Compaction的数据结构分析可知，Compaction操作有两种触发方式：某一level的文件数太多和某一文件的查找次数超过允许值，在进行合并时，将优先考虑文件数过多的情况.
Compaction* VersionSet::PickCompaction() {
Compaction* c;
int level;
const bool size_compaction = (current_->compaction_score_ >= );//文件数过多
const bool seek_compaction = (current_->file_to_compact_ != NULL);//某一文件的查找次数太多
if (size_compaction) {//文件数太多优先考虑
level = current_->compaction_level_; //要进行Compaction的level
c = new Compaction(level);
//每一层有一个compact_pointer，用于记录compaction key，这样可以进行循环compaction
for (size_t i = ; i < current_->files_[level].size(); i++) { //从待合并的level中选择合适的文件完成合并操作
FileMetaData* f = current_->files_[level][i]; //level层中的第i个文件
if (compact_pointer_[level].empty() || //compact_pointer_中记录的是下次合并的起始Key值，为空时都可以进行合并
icmp_.Compare(f->largest.Encode(), compact_pointer_[level]) > ) { //或者f的最大Key值大于起始值
c->inputs_[].push_back(f);//则该文件可以参与合并，将其加入到level输入文件中
break;
}
}
if (c->inputs_[].empty()) { //若level输入为空，则将level的第一个文件加入到输入中
c->inputs_[].push_back(current_->files_[level][]);
}
} else if (seek_compaction) {//然后考虑查找次数过多的情况
level = current_->file_to_compact_level_;
c = new Compaction(level);
c->inputs_[].push_back(current_->file_to_compact_);//将待合并的文件作为level层的输入
} else {
return NULL;
}
c->input_version_ = current_;
c->input_version_->Ref();
//level 0中的Key值是可以重复的，因此Key值范围可能相互覆盖，把所有重叠都找出来，一起做compaction
if (level == ) {
InternalKey smallest, largest;
GetRange(c->inputs_[], &smallest, &largest);//待合并的level层的文件的Key值范围
current_->GetOverlappingInputs(, &smallest, &largest, &c->inputs_[]);
assert(!c->inputs_[].empty());
}
SetupOtherInputs(c);//获取待合并的level+1层的输入
return c;
}
然后判断是否为trivial Compaction,当为trivial Compaction时，只需要简单的将level层的文件移动到level +1 层即可
bool Compaction::IsTrivialMove() const {
return (num_input_files() == && //level层只有1个文件
num_input_files() == && //level+1层没有文件
TotalFileSize(grandparents_) <= kMaxGrandParentOverlapBytes);//level+2层文件总大小不超过最大覆盖范围，否则会导致后面的merge需要很大的开销
}
最终完成完成Compaction操作
c->edit()->DeleteFile(c->level(), f->number);
c->edit()->AddFile(c->level() + , f->number, f->file_size,f->smallest, f->largest);
status = versions_->LogAndApply(c->edit(), &mutex_);
一般的合并
一般的合并调用DBImpl::DoCompactionWork()完成，compact是调用VersionSet::PickCompacttion()得到的，与之前的trivial Compaction相同.不同level之间，可能存在Key值相同的记录，但是记录的seq不同.由之前的分析可知，最新的数据存放在较低的level中，其对应的seq也一定比level+1中的记录的seq要大，因此当出现相同Key值的记录时，只需要记录第一条记录，后面的都可以丢弃.level 0中也可能存在Key值相同的数据，其后面的seq也不同.数据越新，其对应的seq越大，且记录在level 0中的记录是按照user_key递增，seq递减的方式存储的，则相同user_key对应的记录是聚集在一起的，且按照seq递减的方式存放的.在更高层的Compaction时，只需要处理第一条出现的user_key相同的记录即可，后面的相同user_key的记录都可以丢弃.因此合并后的level +1层的文件中不会存在Key值相同的记录.删除记录的操作也会在此时完成，删除数据的记录会被丢弃，而不会被写入到更高level的文件中.
Status DBImpl::DoCompactionWork(CompactionState* compact) {
if (snapshots_.empty()) {
compact->smallest_snapshot = versions_->LastSequence();
} else {
compact->smallest_snapshot = snapshots_.oldest()->number_;
}
mutex_.Unlock();
//生成iterator:遍历要compaction的数据
Iterator* input = versions_->MakeInputIterator(compact->compaction);//用于遍历待合并的每一个文件
input->SeekToFirst();
Status status;
ParsedInternalKey ikey;
std::string current_user_key;
bool has_current_user_key = false;
SequenceNumber last_sequence_for_key = kMaxSequenceNumber;
for (; input->Valid() && !shutting_down_.Acquire_Load(); ) {
if (has_imm_.NoBarrier_Load() != NULL) { //immutable memtable的优先级最高
mutex_.Lock();
if (imm_ != NULL) { //当imm_非空时，合并Memtable
CompactMemTable();
bg_cv_.SignalAll(); // Wakeup MakeRoomForWrite() if necessary
}
mutex_.Unlock();
}
Slice key = input->key();
if (compact->compaction->ShouldStopBefore(key) && //是否需要停止Compaction，中途输出compaction的结果，避免compaction结果和level N+2 files有过多的重叠
compact->builder != NULL) {
status = FinishCompactionOutputFile(compact, input);
}
bool drop = false;
if (!ParseInternalKey(key, &ikey)) {
current_user_key.clear();
has_current_user_key = false;
last_sequence_for_key = kMaxSequenceNumber;
} else {
if (!has_current_user_key || //获取当前的user_key和sequence
user_comparator()->Compare(ikey.user_key,
Slice(current_user_key)) != ) { //可能存在Key值相同但seq不同的记录
// 此时是这个Key第一次出现
current_user_key.assign(ikey.user_key.data(), ikey.user_key.size());
has_current_user_key = true;
last_sequence_for_key = kMaxSequenceNumber;//则将其seq设为最大值，表示第一次出现
}
if (last_sequence_for_key <= compact->smallest_snapshot) {//表示key已经出现过，否则seq应为KMaxSequenceNumber
drop = true; // (A) //之前已经存在Key值相同的记录，丢弃
} else if (ikey.type == kTypeDeletion && //要删除该记录
ikey.sequence <= compact->smallest_snapshot && //记录的序号比数据库之前的最小序号还小
compact->compaction->IsBaseLevelForKey(ikey.user_key)) { //高的level中没有数据
drop = true; //此时要丢弃该记录
}
last_sequence_for_key = ikey.sequence;//上次出现的记录对应的sequence，用于判断后面出现相同Key值的情况
}
if (!drop) { //如果不需要丢弃该记录
if (compact->builder == NULL) {
status = OpenCompactionOutputFile(compact);//若需要，则创建一个.sst文件，用于存放合并后的数据
}
if (compact->builder->NumEntries() == ) {
compact->current_output()->smallest.DecodeFrom(key);
}
compact->current_output()->largest.DecodeFrom(key);
compact->builder->Add(key, input->value());//将记录写入.sst文件
if (compact->builder->FileSize() >=
compact->compaction->MaxOutputFileSize()) { //当.sst文件超过最大值时
status = FinishCompactionOutputFile(compact, input);//完成Compaction输出文件
}
}
input->Next(); //处理下一个文件
}
if (status.ok() && compact->builder != NULL) {
status = FinishCompactionOutputFile(compact, input);
}
if (status.ok()) {
status = input->status();
}
delete input;
input = NULL;
//更新compaction的一些统计数据
CompactionStats stats;
stats.micros = env_->NowMicros() - start_micros - imm_micros;
for (int which = ; which < ; which++) {
for (int i = ; i < compact->compaction->num_input_files(which); i++) {
stats.bytes_read += compact->compaction->input(which, i)->file_size;
}
}
for (size_t i = ; i < compact->outputs.size(); i++) {
stats.bytes_written += compact->outputs[i].file_size;
}
mutex_.Lock();
stats_[compact->compaction->level() + ].Add(stats);
if (status.ok()) {
status = InstallCompactionResults(compact);//完成合并
}
if (!status.ok()) {
RecordBackgroundError(status);
}
VersionSet::LevelSummaryStorage tmp;
Log(options_.info_log,
"compacted to: %s", versions_->LevelSummary(&tmp));
return status;
}
首先将可以留下的记录写入到.sst文件中，并将相关信息保存在变量compact中，然后调用InstallCompactionResults()将所做的改动加入到VersionEdit中，再调用LogAndApply()来得到新的版本.
Status DBImpl::InstallCompactionResults(CompactionState* compact) {
mutex_.AssertHeld();
Log(options_.info_log, "Compacted %d@%d + %d@%d files => %lld bytes",
compact->compaction->num_input_files(),
compact->compaction->level(),
compact->compaction->num_input_files(),
compact->compaction->level() + ,
static_cast<long long>(compact->total_bytes));
// Add compaction outputs
compact->compaction->AddInputDeletions(compact->compaction->edit());
const int level = compact->compaction->level();
for (size_t i = ; i < compact->outputs.size(); i++) {
const CompactionState::Output& out = compact->outputs[i];
compact->compaction->edit()->AddFile(
level + ,
out.number, out.file_size, out.smallest, out.largest);
}
return versions_->LogAndApply(compact->compaction->edit(), &mutex_);
}
LogAndApply()
在上面三种不同的Compaction操作中，最终当对当前版本的更改VersionEdit全部完成后，都会调用VersionSet::LogAndApply()来应用更改，创建新版本.edit中保存了level和level+1层要删除和增加的文件.
Status VersionSet::LogAndApply(VersionEdit* edit, port::Mutex* mu) {
Version* v = new Version(this); //创建一个新Version
{
Builder builder(this, current_);//基于当前Version创建一个builder变量
builder.Apply(edit);//将edit中记录的要增加、删除的文件加入到builder类中
builder.SaveTo(v);//然后将edit中的记录保存到新创建的Version中，这样就得到了一个新的版本
}
Finalize(v);//根据各层文件数来判断是否还需要进行Compaction
std::string new_manifest_file;
Status s;
if (descriptor_log_ == NULL) { //只会在第一次调用时进入
assert(descriptor_file_ == NULL);
new_manifest_file = DescriptorFileName(dbname_, manifest_file_number_);//创建一个新的Manifest文件
edit->SetNextFile(next_file_number_);
s = env_->NewWritableFile(new_manifest_file, &descriptor_file_);
if (s.ok()) {
descriptor_log_ = new log::Writer(descriptor_file_);
s = WriteSnapshot(descriptor_log_);//快照，系统开始时完整记录数据库的所有信息
}
}
{
mu->Unlock();
if (s.ok()) {
std::string record;
edit->EncodeTo(&record);
s = descriptor_log_->AddRecord(record);//将数据库的变化记录到Manifest文件中
if (s.ok()) {
s = descriptor_file_->Sync();
}
}
if (s.ok() && !new_manifest_file.empty()) {
s = SetCurrentFile(env_, dbname_, manifest_file_number_);
}
mu->Lock();
}
if (s.ok()) {
AppendVersion(v); //将新得到的Version插入到所有Version形成的双向链表的尾部
log_number_ = edit->log_number_;
prev_log_number_ = edit->prev_log_number_;
}
}
return s;
}
为了重启之后能恢复数据库之前的状态，就需要将数据库的历史变化信息记录下来，这些信息都是记录在Manifest文件中的.为了节省空间和时间，leveldb采用的是在系统开始完整的所有数据库的信息（WriteSnapShot()），以后则只记录数据库的变化，即VersionEdit中的信息（descriptor_log_->AddRecord()）.恢复时，只需要根据Manifest中的信息就可以一步步的恢复到上次的状态.
VersionSet::LogAndApply首先创建一个新的Version，然后调用builder.Apply(edit)将edit中所有要删除、增加的文件编号记录下来，其源码如下：
// Apply all of the edits in *edit to the current state.
void Apply(VersionEdit* edit) {
// 更新每一层下次合并的起始Key值
for (size_t i = ; i < edit->compact_pointers_.size(); i++) {
const int level = edit->compact_pointers_[i].first;
vset_->compact_pointer_[level] =
edit->compact_pointers_[i].second.Encode().ToString();
}
//将所有要删除的文件加入到levels_[level].deleted_files变量中
const VersionEdit::DeletedFileSet& del = edit->deleted_files_;
for (VersionEdit::DeletedFileSet::const_iterator iter = del.begin();
iter != del.end();++iter) {
const int level = iter->first;
const uint64_t number = iter->second;
levels_[level].deleted_files.insert(number);
}
// 将所有新增加的文件加入到levels_[level].added_files中
for (size_t i = ; i < edit->new_files_.size(); i++) {
const int level = edit->new_files_[i].first;
FileMetaData* f = new FileMetaData(edit->new_files_[i].second);
f->refs = ;
f->allowed_seeks = (f->file_size / );
if (f->allowed_seeks < ) f->allowed_seeks = ;
levels_[level].deleted_files.erase(f->number);
levels_[level].added_files->insert(f);
}
}
然后VersionSet::LogAndApply再调用builder.SaveTo(v)将更改保存到新的Version中，其源码如下：
void SaveTo(Version* v) {
BySmallestKey cmp;
cmp.internal_comparator = &vset_->icmp_;
for (int level = ; level < config::kNumLevels; level++) {
const std::vector<FileMetaData*>& base_files = base_->files_[level];//当前Version中原有的各个level的.sst文件
std::vector<FileMetaData*>::const_iterator base_iter = base_files.begin();
std::vector<FileMetaData*>::const_iterator base_end = base_files.end();
const FileSet* added = levels_[level].added_files;//对应level新增加的文件
v->files_[level].reserve(base_files.size() + added->size());
for (FileSet::const_iterator added_iter = added->begin();
added_iter != added->end();++added_iter) {
// 将原有文件中编号比added小的加入到新的Version
for (std::vector<FileMetaData*>::const_iterator bpos
= std::upper_bound(base_iter, base_end, *added_iter, cmp);
base_iter != bpos;++base_iter) {
MaybeAddFile(v, level, *base_iter);
}
MaybeAddFile(v, level, *added_iter);//再将新增的文件依次加入到新的Version
}
for (; base_iter != base_end; ++base_iter) {
MaybeAddFile(v, level, *base_iter);//再将原有文件中剩余的部分加入到新的Version
}
}
}
bpos = std::upper_bound(base_iter,base_end,*added_iter,cmp); // 返回base_iter到base_end之间，第一个大于*added_iter的iter.假设原有文件的编号为1、3、4、6、8，新增文件的编号为2、5、7，则第一次循环时，bpos为3对应的迭代器，因此base_iter只遍历一个元素，即将编号1加入到新的Version中.总体对新增文件来说，就是首先加入base中编号比它小的，然后再将其加入，然后再继续比那里下一个新增文件，因此最终得到的文件编号顺序是 1、2、3、4、5、6、7、8，即每一层的.sst文件都是按照编号从小到大排列的.这样就得到了新的Version的每一层的所有文件.
参考文献:
1.http://blog.csdn.net/u012658346/article/details/45787233
2.http://blog.csdn.net/u012658346/article/details/45788939
3.http://blog.csdn.net/joeyon1985/article/details/47154249
4.http://www.blogjava.net/sandy/archive/2012/03/15/leveldb6.html
5.http://www.pandademo.com/2016/04/compaction-of-sstable-leveldb-part-1-source-dissect-9/
