rocksdb/db/dbformat.cc
Aaron Gao a30a696034 do not read next datablock if upperbound is reached
Summary:
Now if we have iterate_upper_bound set, we continue read until get a key >= upper_bound. For a lot of cases that neighboring data blocks have a user key gap between them, our index key will be a user key in the middle to get a shorter size. For example, if we have blocks:
[a b c d][f g h]
Then the index key for the first block will be 'e'.
then if upper bound is any key between 'd' and 'e', for example, d1, d2, ..., d99999999999, we don't have to read the second block and also know that we have done our iteration by reaching the last key that smaller the upper bound already.

This diff can reduce RA in most cases.
Closes https://github.com/facebook/rocksdb/pull/2239

Differential Revision: D4990693

Pulled By: lightmark

fbshipit-source-id: ab30ea2e3c6edf3fddd5efed3c34fcf7739827ff
2017-05-05 23:20:01 -07:00

180 lines
6.0 KiB
C++

// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
// This source code is licensed under the BSD-style license found in the
// LICENSE file in the root directory of this source tree. An additional grant
// of patent rights can be found in the PATENTS file in the same directory.
// This source code is also licensed under the GPLv2 license found in the
// COPYING file in the root directory of this source tree.
//
// 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 = kTypeSingleDeletion;
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