You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
 
 
 
 
 
 
rocksdb/db/skiplist.h

428 lines
13 KiB

// Copyright (c) 2013, 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.
//
// 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.
//
// Thread safety
// -------------
//
// Writes require external synchronization, most likely a mutex.
// Reads require a guarantee that the SkipList will not be destroyed
// while the read is in progress. Apart from that, reads progress
// without any internal locking or synchronization.
//
// Invariants:
//
// (1) Allocated nodes are never deleted until the SkipList is
// destroyed. This is trivially guaranteed by the code since we
// never delete any skip list nodes.
//
// (2) The contents of a Node except for the next/prev pointers are
// immutable after the Node has been linked into the SkipList.
// Only Insert() modifies the list, and it is careful to initialize
// a node and use release-stores to publish the nodes in one or
// more lists.
//
// ... prev vs. next pointer ordering ...
//
#pragma once
#include <assert.h>
#include <stdlib.h>
#include "port/port.h"
#include "util/arena.h"
#include "util/random.h"
namespace rocksdb {
template<typename Key, class Comparator>
class SkipList {
private:
struct Node;
public:
// Create a new SkipList object that will use "cmp" for comparing keys,
// and will allocate memory using "*arena". Objects allocated in the arena
// must remain allocated for the lifetime of the skiplist object.
explicit SkipList(Comparator cmp, Arena* arena,
int32_t max_height = 12, int32_t branching_factor = 4);
// Insert key into the list.
// REQUIRES: nothing that compares equal to key is currently in the list.
void Insert(const Key& key);
// Returns true iff an entry that compares equal to key is in the list.
bool Contains(const Key& key) const;
// Iteration over the contents of a skip list
class Iterator {
public:
// Initialize an iterator over the specified list.
// The returned iterator is not valid.
explicit Iterator(const SkipList* list);
// Change the underlying skiplist used for this iterator
// This enables us not changing the iterator without deallocating
// an old one and then allocating a new one
void SetList(const SkipList* list);
// Returns true iff the iterator is positioned at a valid node.
bool Valid() const;
// Returns the key at the current position.
// REQUIRES: Valid()
const Key& key() const;
// Advances to the next position.
// REQUIRES: Valid()
void Next();
// Advances to the previous position.
// REQUIRES: Valid()
void Prev();
// Advance to the first entry with a key >= target
void Seek(const Key& target);
// Position at the first entry in list.
// Final state of iterator is Valid() iff list is not empty.
void SeekToFirst();
// Position at the last entry in list.
// Final state of iterator is Valid() iff list is not empty.
void SeekToLast();
private:
const SkipList* list_;
Node* node_;
// Intentionally copyable
};
private:
const int32_t kMaxHeight_;
const int32_t kBranching_;
// Immutable after construction
Comparator const compare_;
Arena* const arena_; // Arena used for allocations of nodes
Node* const head_;
// Modified only by Insert(). Read racily by readers, but stale
// values are ok.
port::AtomicPointer max_height_; // Height of the entire list
// Used for optimizing sequential insert patterns
Node** prev_;
int32_t prev_height_;
inline int GetMaxHeight() const {
return static_cast<int>(
reinterpret_cast<intptr_t>(max_height_.NoBarrier_Load()));
}
// Read/written only by Insert().
Random rnd_;
Node* NewNode(const Key& key, int height);
int RandomHeight();
bool Equal(const Key& a, const Key& b) const { return (compare_(a, b) == 0); }
// Return true if key is greater than the data stored in "n"
bool KeyIsAfterNode(const Key& key, Node* n) const;
// Return the earliest node that comes at or after key.
// Return nullptr if there is no such node.
//
// If prev is non-nullptr, fills prev[level] with pointer to previous
// node at "level" for every level in [0..max_height_-1].
Node* FindGreaterOrEqual(const Key& key, Node** prev) const;
// Return the latest node with a key < key.
// Return head_ if there is no such node.
Node* FindLessThan(const Key& key) const;
// Return the last node in the list.
// Return head_ if list is empty.
Node* FindLast() const;
// No copying allowed
SkipList(const SkipList&);
void operator=(const SkipList&);
};
// Implementation details follow
template<typename Key, class Comparator>
struct SkipList<Key,Comparator>::Node {
explicit Node(const Key& k) : key(k) { }
Key const key;
// Accessors/mutators for links. Wrapped in methods so we can
// add the appropriate barriers as necessary.
Node* Next(int n) {
assert(n >= 0);
// Use an 'acquire load' so that we observe a fully initialized
// version of the returned Node.
return reinterpret_cast<Node*>(next_[n].Acquire_Load());
}
void SetNext(int n, Node* x) {
assert(n >= 0);
// Use a 'release store' so that anybody who reads through this
// pointer observes a fully initialized version of the inserted node.
next_[n].Release_Store(x);
}
// No-barrier variants that can be safely used in a few locations.
Node* NoBarrier_Next(int n) {
assert(n >= 0);
return reinterpret_cast<Node*>(next_[n].NoBarrier_Load());
}
void NoBarrier_SetNext(int n, Node* x) {
assert(n >= 0);
next_[n].NoBarrier_Store(x);
}
private:
// Array of length equal to the node height. next_[0] is lowest level link.
port::AtomicPointer next_[1];
};
template<typename Key, class Comparator>
typename SkipList<Key,Comparator>::Node*
SkipList<Key,Comparator>::NewNode(const Key& key, int height) {
char* mem = arena_->AllocateAligned(
sizeof(Node) + sizeof(port::AtomicPointer) * (height - 1));
return new (mem) Node(key);
}
template<typename Key, class Comparator>
inline SkipList<Key,Comparator>::Iterator::Iterator(const SkipList* list) {
SetList(list);
}
template<typename Key, class Comparator>
inline void SkipList<Key,Comparator>::Iterator::SetList(const SkipList* list) {
list_ = list;
node_ = nullptr;
}
template<typename Key, class Comparator>
inline bool SkipList<Key,Comparator>::Iterator::Valid() const {
return node_ != nullptr;
}
template<typename Key, class Comparator>
inline const Key& SkipList<Key,Comparator>::Iterator::key() const {
assert(Valid());
return node_->key;
}
template<typename Key, class Comparator>
inline void SkipList<Key,Comparator>::Iterator::Next() {
assert(Valid());
node_ = node_->Next(0);
}
template<typename Key, class Comparator>
inline void SkipList<Key,Comparator>::Iterator::Prev() {
// Instead of using explicit "prev" links, we just search for the
// last node that falls before key.
assert(Valid());
node_ = list_->FindLessThan(node_->key);
if (node_ == list_->head_) {
node_ = nullptr;
}
}
template<typename Key, class Comparator>
inline void SkipList<Key,Comparator>::Iterator::Seek(const Key& target) {
node_ = list_->FindGreaterOrEqual(target, nullptr);
}
template<typename Key, class Comparator>
inline void SkipList<Key,Comparator>::Iterator::SeekToFirst() {
node_ = list_->head_->Next(0);
}
template<typename Key, class Comparator>
inline void SkipList<Key,Comparator>::Iterator::SeekToLast() {
node_ = list_->FindLast();
if (node_ == list_->head_) {
node_ = nullptr;
}
}
template<typename Key, class Comparator>
int SkipList<Key,Comparator>::RandomHeight() {
// Increase height with probability 1 in kBranching
int height = 1;
while (height < kMaxHeight_ && ((rnd_.Next() % kBranching_) == 0)) {
height++;
}
assert(height > 0);
assert(height <= kMaxHeight_);
return height;
}
template<typename Key, class Comparator>
bool SkipList<Key,Comparator>::KeyIsAfterNode(const Key& key, Node* n) const {
// nullptr n is considered infinite
return (n != nullptr) && (compare_(n->key, key) < 0);
}
template<typename Key, class Comparator>
typename SkipList<Key,Comparator>::Node* SkipList<Key,Comparator>::FindGreaterOrEqual(const Key& key, Node** prev)
const {
// Use prev as an optimization hint and fallback to slow path
if (prev && !KeyIsAfterNode(key, prev[0]->Next(0))) {
Node* x = prev[0];
Node* next = x->Next(0);
if ((x == head_) || KeyIsAfterNode(key, x)) {
// Adjust all relevant insertion points to the previous entry
for (int i = 1; i < prev_height_; i++) {
prev[i] = x;
}
return next;
}
}
// Normal lookup
Node* x = head_;
int level = GetMaxHeight() - 1;
while (true) {
Node* next = x->Next(level);
// Make sure the lists are sorted.
// If x points to head_ or next points nullptr, it is trivially satisfied.
assert((x == head_) || (next == nullptr) || KeyIsAfterNode(next->key, x));
if (KeyIsAfterNode(key, next)) {
// Keep searching in this list
x = next;
} else {
if (prev != nullptr) prev[level] = x;
if (level == 0) {
return next;
} else {
// Switch to next list
level--;
}
}
}
}
template<typename Key, class Comparator>
typename SkipList<Key,Comparator>::Node*
SkipList<Key,Comparator>::FindLessThan(const Key& key) const {
Node* x = head_;
int level = GetMaxHeight() - 1;
while (true) {
assert(x == head_ || compare_(x->key, key) < 0);
Node* next = x->Next(level);
if (next == nullptr || compare_(next->key, key) >= 0) {
if (level == 0) {
return x;
} else {
// Switch to next list
level--;
}
} else {
x = next;
}
}
}
template<typename Key, class Comparator>
typename SkipList<Key,Comparator>::Node* SkipList<Key,Comparator>::FindLast()
const {
Node* x = head_;
int level = GetMaxHeight() - 1;
while (true) {
Node* next = x->Next(level);
if (next == nullptr) {
if (level == 0) {
return x;
} else {
// Switch to next list
level--;
}
} else {
x = next;
}
}
}
template<typename Key, class Comparator>
SkipList<Key,Comparator>::SkipList(Comparator cmp, Arena* arena,
int32_t max_height,
int32_t branching_factor)
: kMaxHeight_(max_height),
kBranching_(branching_factor),
compare_(cmp),
arena_(arena),
head_(NewNode(0 /* any key will do */, max_height)),
max_height_(reinterpret_cast<void*>(1)),
prev_height_(1),
rnd_(0xdeadbeef) {
assert(kMaxHeight_ > 0);
assert(kBranching_ > 0);
// Allocate the prev_ Node* array, directly from the passed-in arena.
// prev_ does not need to be freed, as its life cycle is tied up with
// the arena as a whole.
prev_ = (Node**) arena_->AllocateAligned(sizeof(Node*) * kMaxHeight_);
for (int i = 0; i < kMaxHeight_; i++) {
head_->SetNext(i, nullptr);
prev_[i] = head_;
}
}
template<typename Key, class Comparator>
void SkipList<Key,Comparator>::Insert(const Key& key) {
// TODO(opt): We can use a barrier-free variant of FindGreaterOrEqual()
// here since Insert() is externally synchronized.
Node* x = FindGreaterOrEqual(key, prev_);
// Our data structure does not allow duplicate insertion
assert(x == nullptr || !Equal(key, x->key));
int height = RandomHeight();
if (height > GetMaxHeight()) {
for (int i = GetMaxHeight(); i < height; i++) {
prev_[i] = head_;
}
//fprintf(stderr, "Change height from %d to %d\n", max_height_, height);
// It is ok to mutate max_height_ without any synchronization
// with concurrent readers. A concurrent reader that observes
// the new value of max_height_ will see either the old value of
// new level pointers from head_ (nullptr), or a new value set in
// the loop below. In the former case the reader will
// immediately drop to the next level since nullptr sorts after all
// keys. In the latter case the reader will use the new node.
max_height_.NoBarrier_Store(reinterpret_cast<void*>(height));
}
x = NewNode(key, height);
for (int i = 0; i < height; i++) {
// NoBarrier_SetNext() suffices since we will add a barrier when
// we publish a pointer to "x" in prev[i].
x->NoBarrier_SetNext(i, prev_[i]->NoBarrier_Next(i));
prev_[i]->SetNext(i, x);
}
prev_[0] = x;
prev_height_ = height;
}
template<typename Key, class Comparator>
bool SkipList<Key,Comparator>::Contains(const Key& key) const {
Node* x = FindGreaterOrEqual(key, nullptr);
if (x != nullptr && Equal(key, x->key)) {
return true;
} else {
return false;
}
}
} // namespace rocksdb