mirror of
https://github.com/facebook/rocksdb.git
synced 2024-11-27 02:44:18 +00:00
05e8854085
Summary: This diff introduces a new Merge operation into rocksdb. The purpose of this review is mostly getting feedback from the team (everyone please) on the design. Please focus on the four files under include/leveldb/, as they spell the client visible interface change. include/leveldb/db.h include/leveldb/merge_operator.h include/leveldb/options.h include/leveldb/write_batch.h Please go over local/my_test.cc carefully, as it is a concerete use case. Please also review the impelmentation files to see if the straw man implementation makes sense. Note that, the diff does pass all make check and truly supports forward iterator over db and a version of Get that's based on iterator. Future work: - Integration with compaction - A raw Get implementation I am working on a wiki that explains the design and implementation choices, but coding comes just naturally and I think it might be a good idea to share the code earlier. The code is heavily commented. Test Plan: run all local tests Reviewers: dhruba, heyongqiang Reviewed By: dhruba CC: leveldb, zshao, sheki, emayanke, MarkCallaghan Differential Revision: https://reviews.facebook.net/D9651
124 lines
3.8 KiB
C++
124 lines
3.8 KiB
C++
// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
|
|
// Use of this source code is governed by a BSD-style license that can be
|
|
// found in the LICENSE file. See the AUTHORS file for names of contributors.
|
|
|
|
#include "db/table_cache.h"
|
|
|
|
#include "db/filename.h"
|
|
|
|
#include "leveldb/statistics.h"
|
|
#include "table/table.h"
|
|
#include "util/coding.h"
|
|
|
|
namespace leveldb {
|
|
|
|
static void DeleteEntry(const Slice& key, void* value) {
|
|
Table* table = reinterpret_cast<Table*>(value);
|
|
delete table;
|
|
}
|
|
|
|
static void UnrefEntry(void* arg1, void* arg2) {
|
|
Cache* cache = reinterpret_cast<Cache*>(arg1);
|
|
Cache::Handle* h = reinterpret_cast<Cache::Handle*>(arg2);
|
|
cache->Release(h);
|
|
}
|
|
|
|
TableCache::TableCache(const std::string& dbname,
|
|
const Options* options,
|
|
const StorageOptions& storage_options,
|
|
int entries)
|
|
: env_(options->env),
|
|
dbname_(dbname),
|
|
options_(options),
|
|
storage_options_(storage_options),
|
|
cache_(NewLRUCache(entries, options->table_cache_numshardbits)) {}
|
|
|
|
TableCache::~TableCache() {
|
|
}
|
|
|
|
Status TableCache::FindTable(const EnvOptions& toptions,
|
|
uint64_t file_number, uint64_t file_size,
|
|
Cache::Handle** handle, bool* tableIO) {
|
|
Status s;
|
|
char buf[sizeof(file_number)];
|
|
EncodeFixed64(buf, file_number);
|
|
Slice key(buf, sizeof(buf));
|
|
*handle = cache_->Lookup(key);
|
|
if (*handle == nullptr) {
|
|
if (tableIO != nullptr) {
|
|
*tableIO = true; // we had to do IO from storage
|
|
}
|
|
std::string fname = TableFileName(dbname_, file_number);
|
|
unique_ptr<RandomAccessFile> file;
|
|
unique_ptr<Table> table;
|
|
s = env_->NewRandomAccessFile(fname, &file, toptions);
|
|
RecordTick(options_->statistics, NO_FILE_OPENS);
|
|
if (s.ok()) {
|
|
s = Table::Open(*options_, toptions, std::move(file), file_size, &table);
|
|
}
|
|
|
|
if (!s.ok()) {
|
|
assert(table == nullptr);
|
|
RecordTick(options_->statistics, NO_FILE_ERRORS);
|
|
// We do not cache error results so that if the error is transient,
|
|
// or somebody repairs the file, we recover automatically.
|
|
} else {
|
|
assert(file.get() == nullptr);
|
|
*handle = cache_->Insert(key, table.release(), 1, &DeleteEntry);
|
|
}
|
|
}
|
|
return s;
|
|
}
|
|
|
|
Iterator* TableCache::NewIterator(const ReadOptions& options,
|
|
const EnvOptions& toptions,
|
|
uint64_t file_number,
|
|
uint64_t file_size,
|
|
Table** tableptr) {
|
|
if (tableptr != nullptr) {
|
|
*tableptr = nullptr;
|
|
}
|
|
|
|
Cache::Handle* handle = nullptr;
|
|
Status s = FindTable(toptions, file_number, file_size, &handle);
|
|
if (!s.ok()) {
|
|
return NewErrorIterator(s);
|
|
}
|
|
|
|
Table* table =
|
|
reinterpret_cast<Table*>(cache_->Value(handle));
|
|
Iterator* result = table->NewIterator(options);
|
|
result->RegisterCleanup(&UnrefEntry, cache_.get(), handle);
|
|
if (tableptr != nullptr) {
|
|
*tableptr = table;
|
|
}
|
|
return result;
|
|
}
|
|
|
|
Status TableCache::Get(const ReadOptions& options,
|
|
uint64_t file_number,
|
|
uint64_t file_size,
|
|
const Slice& k,
|
|
void* arg,
|
|
bool (*saver)(void*, const Slice&, const Slice&, bool),
|
|
bool* tableIO) {
|
|
Cache::Handle* handle = nullptr;
|
|
Status s = FindTable(storage_options_, file_number, file_size,
|
|
&handle, tableIO);
|
|
if (s.ok()) {
|
|
Table* t =
|
|
reinterpret_cast<Table*>(cache_->Value(handle));
|
|
s = t->InternalGet(options, k, arg, saver);
|
|
cache_->Release(handle);
|
|
}
|
|
return s;
|
|
}
|
|
|
|
void TableCache::Evict(uint64_t file_number) {
|
|
char buf[sizeof(file_number)];
|
|
EncodeFixed64(buf, file_number);
|
|
cache_->Erase(Slice(buf, sizeof(buf)));
|
|
}
|
|
|
|
} // namespace leveldb
|