mirror of
https://github.com/facebook/rocksdb.git
synced 2024-11-26 16:30:56 +00:00
321dfdc3ae
Summary: The leveldb API is enhanced to support different compression algorithms at different levels. This adds the option min_level_to_compress to db_bench that specifies the minimum level for which compression should be done when compression is enabled. This can be used to disable compression for levels 0 and 1 which are likely to suffer from stalls because of the CPU load for memtable flushes and (L0,L1) compaction. Level 0 is special as it gets frequent memtable flushes. Level 1 is special as it frequently gets all:all file compactions between it and level 0. But all other levels could be the same. For any level N where N > 1, the rate of sequential IO for that level should be the same. The last level is the exception because it might not be full and because files from it are not read to compact with the next larger level. The same amount of time will be spent doing compaction at any level N excluding N=0, 1 or the last level. By this standard all of those levels should use the same compression. The difference is that the loss (using more disk space) from a faster compression algorithm is less significant for N=2 than for N=3. So we might be willing to trade disk space for faster write rates with no compression for L0 and L1, snappy for L2, zlib for L3. Using a faster compression algorithm for the mid levels also allows us to reclaim some cpu without trading off much loss in disk space overhead. Also note that little is to be gained by compressing levels 0 and 1. For a 4-level tree they account for 10% of the data. For a 5-level tree they account for 1% of the data. With compression enabled: * memtable flush rate is ~18MB/second * (L0,L1) compaction rate is ~30MB/second With compression enabled but min_level_to_compress=2 * memtable flush rate is ~320MB/second * (L0,L1) compaction rate is ~560MB/second This practicaly takes the same code from https://reviews.facebook.net/D6225 but makes the leveldb api more general purpose with a few additional lines of code. Test Plan: make check Differential Revision: https://reviews.facebook.net/D6261
93 lines
2.2 KiB
C++
93 lines
2.2 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/builder.h"
|
|
|
|
#include "db/filename.h"
|
|
#include "db/dbformat.h"
|
|
#include "db/table_cache.h"
|
|
#include "db/version_edit.h"
|
|
#include "leveldb/db.h"
|
|
#include "leveldb/env.h"
|
|
#include "leveldb/iterator.h"
|
|
|
|
namespace leveldb {
|
|
|
|
Status BuildTable(const std::string& dbname,
|
|
Env* env,
|
|
const Options& options,
|
|
TableCache* table_cache,
|
|
Iterator* iter,
|
|
FileMetaData* meta) {
|
|
Status s;
|
|
meta->file_size = 0;
|
|
iter->SeekToFirst();
|
|
|
|
std::string fname = TableFileName(dbname, meta->number);
|
|
if (iter->Valid()) {
|
|
WritableFile* file;
|
|
s = env->NewWritableFile(fname, &file);
|
|
if (!s.ok()) {
|
|
return s;
|
|
}
|
|
|
|
TableBuilder* builder = new TableBuilder(options, file, 0);
|
|
meta->smallest.DecodeFrom(iter->key());
|
|
for (; iter->Valid(); iter->Next()) {
|
|
Slice key = iter->key();
|
|
meta->largest.DecodeFrom(key);
|
|
builder->Add(key, iter->value());
|
|
}
|
|
|
|
// Finish and check for builder errors
|
|
if (s.ok()) {
|
|
s = builder->Finish();
|
|
if (s.ok()) {
|
|
meta->file_size = builder->FileSize();
|
|
assert(meta->file_size > 0);
|
|
}
|
|
} else {
|
|
builder->Abandon();
|
|
}
|
|
delete builder;
|
|
|
|
// Finish and check for file errors
|
|
if (s.ok() && !options.disableDataSync) {
|
|
if (options.use_fsync) {
|
|
s = file->Fsync();
|
|
} else {
|
|
s = file->Sync();
|
|
}
|
|
}
|
|
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);
|
|
s = it->status();
|
|
delete it;
|
|
}
|
|
}
|
|
|
|
// Check for input iterator errors
|
|
if (!iter->status().ok()) {
|
|
s = iter->status();
|
|
}
|
|
|
|
if (s.ok() && meta->file_size > 0) {
|
|
// Keep it
|
|
} else {
|
|
env->DeleteFile(fname);
|
|
}
|
|
return s;
|
|
}
|
|
|
|
} // namespace leveldb
|