c293472908
Summary: Add kTypeBlobIndex value type, which will be used by blob db only, to insert a (key, blob_offset) KV pair. The purpose is to 1. Make it possible to open existing rocksdb instance as blob db. Existing value will be of kTypeIndex type, while value inserted by blob db will be of kTypeBlobIndex. 2. Make rocksdb able to detect if the db contains value written by blob db, if so return error. 3. Make it possible to have blob db optionally store value in SST file (with kTypeValue type) or as a blob value (with kTypeBlobIndex type). The root db (DBImpl) basically pretended kTypeBlobIndex are normal value on write. On Get if is_blob is provided, return whether the value read is of kTypeBlobIndex type, or return Status::NotSupported() status if is_blob is not provided. On scan allow_blob flag is pass and if the flag is true, return wether the value is of kTypeBlobIndex type via iter->IsBlob(). Changes on blob db side will be in a separate patch. Closes https://github.com/facebook/rocksdb/pull/2886 Differential Revision: D5838431 Pulled By: yiwu-arbug fbshipit-source-id: 3c5306c62bc13bb11abc03422ec5cbcea1203cca
178 lines
5.8 KiB
C++
178 lines
5.8 KiB
C++
// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
|
|
// This source code is licensed under both the GPLv2 (found in the
|
|
// COPYING file in the root directory) and Apache 2.0 License
|
|
// (found in the LICENSE.Apache file in the root directory).
|
|
//
|
|
// 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/dbformat.h"
|
|
|
|
#ifndef __STDC_FORMAT_MACROS
|
|
#define __STDC_FORMAT_MACROS
|
|
#endif
|
|
|
|
#include <inttypes.h>
|
|
#include <stdio.h>
|
|
#include "monitoring/perf_context_imp.h"
|
|
#include "port/port.h"
|
|
#include "util/coding.h"
|
|
#include "util/string_util.h"
|
|
|
|
namespace rocksdb {
|
|
|
|
// kValueTypeForSeek defines the ValueType that should be passed when
|
|
// constructing a ParsedInternalKey object for seeking to a particular
|
|
// sequence number (since we sort sequence numbers in decreasing order
|
|
// and the value type is embedded as the low 8 bits in the sequence
|
|
// number in internal keys, we need to use the highest-numbered
|
|
// ValueType, not the lowest).
|
|
const ValueType kValueTypeForSeek = kTypeBlobIndex;
|
|
const ValueType kValueTypeForSeekForPrev = kTypeDeletion;
|
|
|
|
uint64_t PackSequenceAndType(uint64_t seq, ValueType t) {
|
|
assert(seq <= kMaxSequenceNumber);
|
|
assert(IsExtendedValueType(t));
|
|
return (seq << 8) | t;
|
|
}
|
|
|
|
void UnPackSequenceAndType(uint64_t packed, uint64_t* seq, ValueType* t) {
|
|
*seq = packed >> 8;
|
|
*t = static_cast<ValueType>(packed & 0xff);
|
|
|
|
assert(*seq <= kMaxSequenceNumber);
|
|
assert(IsExtendedValueType(*t));
|
|
}
|
|
|
|
void AppendInternalKey(std::string* result, const ParsedInternalKey& key) {
|
|
result->append(key.user_key.data(), key.user_key.size());
|
|
PutFixed64(result, PackSequenceAndType(key.sequence, key.type));
|
|
}
|
|
|
|
void AppendInternalKeyFooter(std::string* result, SequenceNumber s,
|
|
ValueType t) {
|
|
PutFixed64(result, PackSequenceAndType(s, t));
|
|
}
|
|
|
|
std::string ParsedInternalKey::DebugString(bool hex) const {
|
|
char buf[50];
|
|
snprintf(buf, sizeof(buf), "' seq:%" PRIu64 ", type:%d", sequence,
|
|
static_cast<int>(type));
|
|
std::string result = "'";
|
|
result += user_key.ToString(hex);
|
|
result += buf;
|
|
return result;
|
|
}
|
|
|
|
std::string InternalKey::DebugString(bool hex) const {
|
|
std::string result;
|
|
ParsedInternalKey parsed;
|
|
if (ParseInternalKey(rep_, &parsed)) {
|
|
result = parsed.DebugString(hex);
|
|
} else {
|
|
result = "(bad)";
|
|
result.append(EscapeString(rep_));
|
|
}
|
|
return result;
|
|
}
|
|
|
|
const char* InternalKeyComparator::Name() const {
|
|
return name_.c_str();
|
|
}
|
|
|
|
int InternalKeyComparator::Compare(const Slice& akey, const Slice& bkey) const {
|
|
// Order by:
|
|
// increasing user key (according to user-supplied comparator)
|
|
// decreasing sequence number
|
|
// decreasing type (though sequence# should be enough to disambiguate)
|
|
int r = user_comparator_->Compare(ExtractUserKey(akey), ExtractUserKey(bkey));
|
|
PERF_COUNTER_ADD(user_key_comparison_count, 1);
|
|
if (r == 0) {
|
|
const uint64_t anum = DecodeFixed64(akey.data() + akey.size() - 8);
|
|
const uint64_t bnum = DecodeFixed64(bkey.data() + bkey.size() - 8);
|
|
if (anum > bnum) {
|
|
r = -1;
|
|
} else if (anum < bnum) {
|
|
r = +1;
|
|
}
|
|
}
|
|
return r;
|
|
}
|
|
|
|
int InternalKeyComparator::Compare(const ParsedInternalKey& a,
|
|
const ParsedInternalKey& b) const {
|
|
// Order by:
|
|
// increasing user key (according to user-supplied comparator)
|
|
// decreasing sequence number
|
|
// decreasing type (though sequence# should be enough to disambiguate)
|
|
int r = user_comparator_->Compare(a.user_key, b.user_key);
|
|
PERF_COUNTER_ADD(user_key_comparison_count, 1);
|
|
if (r == 0) {
|
|
if (a.sequence > b.sequence) {
|
|
r = -1;
|
|
} else if (a.sequence < b.sequence) {
|
|
r = +1;
|
|
} else if (a.type > b.type) {
|
|
r = -1;
|
|
} else if (a.type < b.type) {
|
|
r = +1;
|
|
}
|
|
}
|
|
return r;
|
|
}
|
|
|
|
void InternalKeyComparator::FindShortestSeparator(
|
|
std::string* start,
|
|
const Slice& limit) const {
|
|
// Attempt to shorten the user portion of the key
|
|
Slice user_start = ExtractUserKey(*start);
|
|
Slice user_limit = ExtractUserKey(limit);
|
|
std::string tmp(user_start.data(), user_start.size());
|
|
user_comparator_->FindShortestSeparator(&tmp, user_limit);
|
|
if (tmp.size() <= user_start.size() &&
|
|
user_comparator_->Compare(user_start, tmp) < 0) {
|
|
// User key has become shorter physically, but larger logically.
|
|
// Tack on the earliest possible number to the shortened user key.
|
|
PutFixed64(&tmp, PackSequenceAndType(kMaxSequenceNumber,kValueTypeForSeek));
|
|
assert(this->Compare(*start, tmp) < 0);
|
|
assert(this->Compare(tmp, limit) < 0);
|
|
start->swap(tmp);
|
|
}
|
|
}
|
|
|
|
void InternalKeyComparator::FindShortSuccessor(std::string* key) const {
|
|
Slice user_key = ExtractUserKey(*key);
|
|
std::string tmp(user_key.data(), user_key.size());
|
|
user_comparator_->FindShortSuccessor(&tmp);
|
|
if (tmp.size() <= user_key.size() &&
|
|
user_comparator_->Compare(user_key, tmp) < 0) {
|
|
// User key has become shorter physically, but larger logically.
|
|
// Tack on the earliest possible number to the shortened user key.
|
|
PutFixed64(&tmp, PackSequenceAndType(kMaxSequenceNumber,kValueTypeForSeek));
|
|
assert(this->Compare(*key, tmp) < 0);
|
|
key->swap(tmp);
|
|
}
|
|
}
|
|
|
|
LookupKey::LookupKey(const Slice& _user_key, SequenceNumber s) {
|
|
size_t usize = _user_key.size();
|
|
size_t needed = usize + 13; // A conservative estimate
|
|
char* dst;
|
|
if (needed <= sizeof(space_)) {
|
|
dst = space_;
|
|
} else {
|
|
dst = new char[needed];
|
|
}
|
|
start_ = dst;
|
|
// NOTE: We don't support users keys of more than 2GB :)
|
|
dst = EncodeVarint32(dst, static_cast<uint32_t>(usize + 8));
|
|
kstart_ = dst;
|
|
memcpy(dst, _user_key.data(), usize);
|
|
dst += usize;
|
|
EncodeFixed64(dst, PackSequenceAndType(s, kValueTypeForSeek));
|
|
dst += 8;
|
|
end_ = dst;
|
|
}
|
|
|
|
} // namespace rocksdb
|