36a5f8ed7f
- Replace raw slice comparison with a call to user comparator. Added test for custom comparators. - Fix end of namespace comments. - Fixed bug in picking inputs for a level-0 compaction. When finding overlapping files, the covered range may expand as files are added to the input set. We now correctly expand the range when this happens instead of continuing to use the old range. For example, suppose L0 contains files with the following ranges: F1: a .. d F2: c .. g F3: f .. j and the initial compaction target is F3. We used to search for range f..j which yielded {F2,F3}. However we now expand the range as soon as another file is added. In this case, when F2 is added, we expand the range to c..j and restart the search. That picks up file F1 as well. This change fixes a bug related to deleted keys showing up incorrectly after a compaction as described in Issue 44. (Sync with upstream @25072954)
216 lines
7.1 KiB
C++
216 lines
7.1 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.
|
|
|
|
#ifndef STORAGE_LEVELDB_DB_FORMAT_H_
|
|
#define STORAGE_LEVELDB_DB_FORMAT_H_
|
|
|
|
#include <stdio.h>
|
|
#include "leveldb/comparator.h"
|
|
#include "leveldb/db.h"
|
|
#include "leveldb/slice.h"
|
|
#include "leveldb/table_builder.h"
|
|
#include "util/coding.h"
|
|
#include "util/logging.h"
|
|
|
|
namespace leveldb {
|
|
|
|
// Grouping of constants. We may want to make some of these
|
|
// parameters set via options.
|
|
namespace config {
|
|
static const int kNumLevels = 7;
|
|
|
|
// Level-0 compaction is started when we hit this many files.
|
|
static const int kL0_CompactionTrigger = 4;
|
|
|
|
// Soft limit on number of level-0 files. We slow down writes at this point.
|
|
static const int kL0_SlowdownWritesTrigger = 8;
|
|
|
|
// Maximum number of level-0 files. We stop writes at this point.
|
|
static const int kL0_StopWritesTrigger = 12;
|
|
|
|
// Maximum level to which a new compacted memtable is pushed if it
|
|
// does not create overlap. We try to push to level 2 to avoid the
|
|
// relatively expensive level 0=>1 compactions and to avoid some
|
|
// expensive manifest file operations. We do not push all the way to
|
|
// the largest level since that can generate a lot of wasted disk
|
|
// space if the same key space is being repeatedly overwritten.
|
|
static const int kMaxMemCompactLevel = 2;
|
|
|
|
} // namespace config
|
|
|
|
class InternalKey;
|
|
|
|
// Value types encoded as the last component of internal keys.
|
|
// DO NOT CHANGE THESE ENUM VALUES: they are embedded in the on-disk
|
|
// data structures.
|
|
enum ValueType {
|
|
kTypeDeletion = 0x0,
|
|
kTypeValue = 0x1
|
|
};
|
|
// 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).
|
|
static const ValueType kValueTypeForSeek = kTypeValue;
|
|
|
|
typedef uint64_t SequenceNumber;
|
|
|
|
// We leave eight bits empty at the bottom so a type and sequence#
|
|
// can be packed together into 64-bits.
|
|
static const SequenceNumber kMaxSequenceNumber =
|
|
((0x1ull << 56) - 1);
|
|
|
|
struct ParsedInternalKey {
|
|
Slice user_key;
|
|
SequenceNumber sequence;
|
|
ValueType type;
|
|
|
|
ParsedInternalKey() { } // Intentionally left uninitialized (for speed)
|
|
ParsedInternalKey(const Slice& u, const SequenceNumber& seq, ValueType t)
|
|
: user_key(u), sequence(seq), type(t) { }
|
|
std::string DebugString() const;
|
|
};
|
|
|
|
// Return the length of the encoding of "key".
|
|
inline size_t InternalKeyEncodingLength(const ParsedInternalKey& key) {
|
|
return key.user_key.size() + 8;
|
|
}
|
|
|
|
// Append the serialization of "key" to *result.
|
|
extern void AppendInternalKey(std::string* result,
|
|
const ParsedInternalKey& key);
|
|
|
|
// Attempt to parse an internal key from "internal_key". On success,
|
|
// stores the parsed data in "*result", and returns true.
|
|
//
|
|
// On error, returns false, leaves "*result" in an undefined state.
|
|
extern bool ParseInternalKey(const Slice& internal_key,
|
|
ParsedInternalKey* result);
|
|
|
|
// Returns the user key portion of an internal key.
|
|
inline Slice ExtractUserKey(const Slice& internal_key) {
|
|
assert(internal_key.size() >= 8);
|
|
return Slice(internal_key.data(), internal_key.size() - 8);
|
|
}
|
|
|
|
inline ValueType ExtractValueType(const Slice& internal_key) {
|
|
assert(internal_key.size() >= 8);
|
|
const size_t n = internal_key.size();
|
|
uint64_t num = DecodeFixed64(internal_key.data() + n - 8);
|
|
unsigned char c = num & 0xff;
|
|
return static_cast<ValueType>(c);
|
|
}
|
|
|
|
// A comparator for internal keys that uses a specified comparator for
|
|
// the user key portion and breaks ties by decreasing sequence number.
|
|
class InternalKeyComparator : public Comparator {
|
|
private:
|
|
const Comparator* user_comparator_;
|
|
public:
|
|
explicit InternalKeyComparator(const Comparator* c) : user_comparator_(c) { }
|
|
virtual const char* Name() const;
|
|
virtual int Compare(const Slice& a, const Slice& b) const;
|
|
virtual void FindShortestSeparator(
|
|
std::string* start,
|
|
const Slice& limit) const;
|
|
virtual void FindShortSuccessor(std::string* key) const;
|
|
|
|
const Comparator* user_comparator() const { return user_comparator_; }
|
|
|
|
int Compare(const InternalKey& a, const InternalKey& b) const;
|
|
};
|
|
|
|
// Modules in this directory should keep internal keys wrapped inside
|
|
// the following class instead of plain strings so that we do not
|
|
// incorrectly use string comparisons instead of an InternalKeyComparator.
|
|
class InternalKey {
|
|
private:
|
|
std::string rep_;
|
|
public:
|
|
InternalKey() { } // Leave rep_ as empty to indicate it is invalid
|
|
InternalKey(const Slice& user_key, SequenceNumber s, ValueType t) {
|
|
AppendInternalKey(&rep_, ParsedInternalKey(user_key, s, t));
|
|
}
|
|
|
|
void DecodeFrom(const Slice& s) { rep_.assign(s.data(), s.size()); }
|
|
Slice Encode() const {
|
|
assert(!rep_.empty());
|
|
return rep_;
|
|
}
|
|
|
|
Slice user_key() const { return ExtractUserKey(rep_); }
|
|
|
|
void SetFrom(const ParsedInternalKey& p) {
|
|
rep_.clear();
|
|
AppendInternalKey(&rep_, p);
|
|
}
|
|
|
|
void Clear() { rep_.clear(); }
|
|
|
|
std::string DebugString() const;
|
|
};
|
|
|
|
inline int InternalKeyComparator::Compare(
|
|
const InternalKey& a, const InternalKey& b) const {
|
|
return Compare(a.Encode(), b.Encode());
|
|
}
|
|
|
|
inline bool ParseInternalKey(const Slice& internal_key,
|
|
ParsedInternalKey* result) {
|
|
const size_t n = internal_key.size();
|
|
if (n < 8) return false;
|
|
uint64_t num = DecodeFixed64(internal_key.data() + n - 8);
|
|
unsigned char c = num & 0xff;
|
|
result->sequence = num >> 8;
|
|
result->type = static_cast<ValueType>(c);
|
|
result->user_key = Slice(internal_key.data(), n - 8);
|
|
return (c <= static_cast<unsigned char>(kTypeValue));
|
|
}
|
|
|
|
// A helper class useful for DBImpl::Get()
|
|
class LookupKey {
|
|
public:
|
|
// Initialize *this for looking up user_key at a snapshot with
|
|
// the specified sequence number.
|
|
LookupKey(const Slice& user_key, SequenceNumber sequence);
|
|
|
|
~LookupKey();
|
|
|
|
// Return a key suitable for lookup in a MemTable.
|
|
Slice memtable_key() const { return Slice(start_, end_ - start_); }
|
|
|
|
// Return an internal key (suitable for passing to an internal iterator)
|
|
Slice internal_key() const { return Slice(kstart_, end_ - kstart_); }
|
|
|
|
// Return the user key
|
|
Slice user_key() const { return Slice(kstart_, end_ - kstart_ - 8); }
|
|
|
|
private:
|
|
// We construct a char array of the form:
|
|
// klength varint32 <-- start_
|
|
// userkey char[klength] <-- kstart_
|
|
// tag uint64
|
|
// <-- end_
|
|
// The array is a suitable MemTable key.
|
|
// The suffix starting with "userkey" can be used as an InternalKey.
|
|
const char* start_;
|
|
const char* kstart_;
|
|
const char* end_;
|
|
char space_[200]; // Avoid allocation for short keys
|
|
|
|
// No copying allowed
|
|
LookupKey(const LookupKey&);
|
|
void operator=(const LookupKey&);
|
|
};
|
|
|
|
inline LookupKey::~LookupKey() {
|
|
if (start_ != space_) delete[] start_;
|
|
}
|
|
|
|
} // namespace leveldb
|
|
|
|
#endif // STORAGE_LEVELDB_DB_FORMAT_H_
|