rocksdb/db/table_cache.cc
Dhruba Borthakur c1bb32e1ba Trigger read compaction only if seeks to storage are incurred.
Summary:
In the current code, a Get() call can trigger compaction if it has to look at more than one file. This causes unnecessary compaction because looking at more than one file is a penalty only if the file is not yet in the cache. Also, th current code counts these files before the bloom filter check is applied.

This patch counts a 'seek' only if the file fails the bloom filter
check and has to read in data block(s) from the storage.

This patch also counts a 'seek' if a file is not present in the file-cache, because opening a file means that its index blocks need to be read into cache.

Test Plan: unit test attached. I will probably add one more unti tests.

Reviewers: heyongqiang

Reviewed By: heyongqiang

CC: MarkCallaghan

Differential Revision: https://reviews.facebook.net/D5709
2012-09-28 11:10:52 -07:00

134 lines
3.9 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 "db/db_statistics.h"
#include "leveldb/env.h"
#include "leveldb/table.h"
#include "util/coding.h"
namespace leveldb {
struct TableAndFile {
RandomAccessFile* file;
Table* table;
};
static class DBStatistics* dbstatistics;
static void DeleteEntry(const Slice& key, void* value) {
TableAndFile* tf = reinterpret_cast<TableAndFile*>(value);
delete tf->table;
delete tf->file;
dbstatistics ? dbstatistics->incNumFileCloses() : (void)0;
delete tf;
}
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,
int entries)
: env_(options->env),
dbname_(dbname),
options_(options),
cache_(NewLRUCache(entries)) {
dbstatistics = (DBStatistics*)options->statistics;
}
TableCache::~TableCache() {
delete cache_;
}
Status TableCache::FindTable(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));
DBStatistics* stats = (DBStatistics*) options_->statistics;
*handle = cache_->Lookup(key);
if (*handle == NULL) {
if (tableIO != NULL) {
*tableIO = true; // we had to do IO from storage
}
std::string fname = TableFileName(dbname_, file_number);
RandomAccessFile* file = NULL;
Table* table = NULL;
s = env_->NewRandomAccessFile(fname, &file);
stats ? stats->incNumFileOpens() : (void)0;
if (s.ok()) {
s = Table::Open(*options_, file, file_size, &table);
}
if (!s.ok()) {
assert(table == NULL);
delete file;
stats ? stats->incNumFileErrors() : (void)0;
// We do not cache error results so that if the error is transient,
// or somebody repairs the file, we recover automatically.
} else {
TableAndFile* tf = new TableAndFile;
tf->file = file;
tf->table = table;
*handle = cache_->Insert(key, tf, 1, &DeleteEntry);
}
}
return s;
}
Iterator* TableCache::NewIterator(const ReadOptions& options,
uint64_t file_number,
uint64_t file_size,
Table** tableptr) {
if (tableptr != NULL) {
*tableptr = NULL;
}
Cache::Handle* handle = NULL;
Status s = FindTable(file_number, file_size, &handle);
if (!s.ok()) {
return NewErrorIterator(s);
}
Table* table = reinterpret_cast<TableAndFile*>(cache_->Value(handle))->table;
Iterator* result = table->NewIterator(options);
result->RegisterCleanup(&UnrefEntry, cache_, handle);
if (tableptr != NULL) {
*tableptr = table;
}
return result;
}
Status TableCache::Get(const ReadOptions& options,
uint64_t file_number,
uint64_t file_size,
const Slice& k,
void* arg,
void (*saver)(void*, const Slice&, const Slice&, bool),
bool* tableIO) {
Cache::Handle* handle = NULL;
Status s = FindTable(file_number, file_size, &handle, tableIO);
if (s.ok()) {
Table* t = reinterpret_cast<TableAndFile*>(cache_->Value(handle))->table;
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