设计一种数据结构实现LRU算法,查询以及插入操作时间复杂度为O(1),并且满足最近最少使用原则。如果一个数据在最近一段时间没有被访问到,那么在将来它被访问的可能性也很小。当限定的空间已存满数据时,应当把最久没有被访问到的数据淘汰。
Design and implement a data structure for Least Recently Used (LRU) cache. It should support the following operations: get and put.
get(key) - Get the value (will always be positive) of the key if the key exists in the cache, otherwise return -1.
put(key, value) - Set or insert the value if the key is not already present. When the cache reached its capacity, it should invalidate the least recently used item before inserting a new item.
The cache is initialized with a positive capacity.
Follow up:
Could you do both operations in O(1) time complexity?
基本实现思路:
利用HashMap以及双端队列来实现,利用Map来保存key与Node节点的对应关系,实现O(1)查询操作;
利用双端队列来保存Node节点链表,当查询命中时,将Node节点移动到链表头部;当插入时,如果容量未满,则直接插入到链表头部,如果容量已满则删除链表最后元素,将新元素插入到链表头部,这样链表头部一直保存最新的Node节点,尾部保存最老的Node节点。
使用HashMap以及自定义双向链表来实现
//双向链表+HashMap来实现
//如果一个数据在最近一段时间没有被访问到,那么在将来它被访问的可能性也很小。当限定的空间已存满数据时,应当把最久没有被访问到的数据淘汰。
//查询数据时,如果命中将数据移动到链表头部
//添加数据时,如果容量未满直接插入到链表头部,如果容量已满则删除尾部元素,插入到链表头部
//当存在热点数据时,LRU的效率很好,但偶发性的、周期性的批量操作会导致LRU命中率急剧下降,缓存污染情况比较严重。
public class LRUCache {
private Node head;
private Node tail;
private HashMap<Integer, Node> map;
private int capacity;
class Node{
int key;
int value;
Node prev, next;
Node(int key, int value){
this.key = key;
this.value = value;
}
}
public LRUCache(int capacity){
map = new HashMap<>();
this.capacity = capacity;
head = new Node(0, 0);
tail = new Node(0, 0);
head.next = tail;
tail.prev = head;
}
public int get(int key){
//如果key不存在返回-1
if(!map.containsKey(key)) return -1;
//如果key存在,则将节点删除,然后重新插入到链表头部
Node n = map.get(key);
remove(n);
addToHead(n);
return n.value;
}
public void put(int key, int value){
Node n = new Node(key, value);
//如果key不存在
if(!map.containsKey(key)){
//如果容量已满,则将链表尾部元素删除 与查询操作将元素置于头部相呼应
if(map.size() == capacity){
map.remove(tail.prev.key);
remove(tail.prev);
}
}else{
remove(map.get(key));
}
//保存Node,将Node移动到链表头部
map.put(key, n);
addToHead(n);
}
//将Node移动到链表头部
private void addToHead(Node n) {
Node hnext = head.next;
n.next = hnext;
hnext.prev = n;
head.next = n;
n.prev = head;
}
//删除某个Node
private void remove(Node n) {
n.prev.next = n.next;
n.next.prev = n.prev;
}
}
初始化维持一个head以及tail指针
当插入元素时如果发现该元素已经存在需要将Node删除,并且将Node插入到链表头部;
当查询命中时,也需要将Node删除移动到链表头部;
从链表中删除一个Node节点
将一个Node节点插入到链表头部
使用JDK LinkedHashMap来实现
//JDK LinkedHashMap来实现
public class LRUCache2 extends LinkedHashMap<Integer, Integer>{
private int cacheSize;
public LRUCache2(int capacity){
super(capacity, 0.75f, true);
this.cacheSize = capacity;
}
public int get(int key){
return super.getOrDefault(key, -1);
}
public void put(int key, int value){
super.put(key, value);
}
@Override
protected boolean removeEldestEntry(java.util.Map.Entry<Integer, Integer> eldest) {
return this.size() > cacheSize;
}
}
LinkedHashMap继承HashMap
public class LinkedHashMap<K,V> extends HashMap<K,V> implements Map<K,V>
双向链表的核心结构体Entry继承HashMap Node数据结构 在Node基础之上添加before以及after指针
static class Entry<K,V> extends HashMap.Node<K,V> {
Entry<K,V> before, after;
Entry(int hash, K key, V value, Node<K,V> next) {
super(hash, key, value, next);
}
}
static class Node<K,V> implements Map.Entry<K,V> {
final int hash;
final K key;
V value;
Node<K,V> next;
}
LinkedHashMap其内部维持head以及tail指针 头部存在最老的元素,尾部存放最年轻的元素,即新插入的元素是放在尾部的。
/**
* The head (eldest) of the doubly linked list.
*/
transient LinkedHashMap.Entry<K,V> head;
/**
* The tail (youngest) of the doubly linked list.
*/
transient LinkedHashMap.Entry<K,V> tail;
属性accessOrder控制元素的迭代访问顺序,true 访问顺序 false 插入顺序
/**
* The iteration ordering method for this linked hash map: <tt>true</tt>
* for access-order, <tt>false</tt> for insertion-order.
*
* @serial
*/
final boolean accessOrder;
查询方法
public V getOrDefault(Object key, V defaultValue) {
Node<K,V> e;
if ((e = getNode(hash(key), key)) == null)
return defaultValue;
if (accessOrder)
afterNodeAccess(e);
return e.value;
}
调用hashmap的getNode方法 计算keyhash值,找到数组索引,根据数组位置是单链表以及红黑树来检索元素。
final Node<K,V> getNode(int hash, Object key) {
Node<K,V>[] tab; Node<K,V> first, e; int n; K k;
if ((tab = table) != null && (n = tab.length) > 0 &&
(first = tab[(n - 1) & hash]) != null) {
if (first.hash == hash && // always check first node
((k = first.key) == key || (key != null && key.equals(k))))
return first;
if ((e = first.next) != null) {
if (first instanceof TreeNode)
return ((TreeNode<K,V>)first).getTreeNode(hash, key);
do {
if (e.hash == hash &&
((k = e.key) == key || (key != null && key.equals(k))))
return e;
} while ((e = e.next) != null);
}
}
return null;
}
由于此处accessOrder=true,调用afterNodeAccess方法,实现将新访问的node移动到链表尾部,首先实现将node p删除,然后添加到链表尾部。
void afterNodeAccess(Node<K,V> e) { // move node to last
LinkedHashMap.Entry<K,V> last;
if (accessOrder && (last = tail) != e) {
LinkedHashMap.Entry<K,V> p =
(LinkedHashMap.Entry<K,V>)e, b = p.before, a = p.after;
p.after = null;
if (b == null)
head = a;
else
b.after = a;
if (a != null)
a.before = b;
else
last = b;
if (last == null)
head = p;
else {
p.before = last;
last.after = p;
}
tail = p;
++modCount;
}
}
插入方法
public V put(K key, V value) {
return putVal(hash(key), key, value, false, true);
}
hashmap的putVal方法
final V putVal(int hash, K key, V value, boolean onlyIfAbsent,
boolean evict) {
Node<K,V>[] tab; Node<K,V> p; int n, i;
if ((tab = table) == null || (n = tab.length) == 0)
n = (tab = resize()).length;
if ((p = tab[i = (n - 1) & hash]) == null)
tab[i] = newNode(hash, key, value, null);
else {
Node<K,V> e; K k;
if (p.hash == hash &&
((k = p.key) == key || (key != null && key.equals(k))))
e = p;
else if (p instanceof TreeNode)
e = ((TreeNode<K,V>)p).putTreeVal(this, tab, hash, key, value);
else {
for (int binCount = 0; ; ++binCount) {
if ((e = p.next) == null) {
p.next = newNode(hash, key, value, null);
if (binCount >= TREEIFY_THRESHOLD - 1) // -1 for 1st
treeifyBin(tab, hash);
break;
}
if (e.hash == hash &&
((k = e.key) == key || (key != null && key.equals(k))))
break;
p = e;
}
}
if (e != null) { // existing mapping for key
V oldValue = e.value;
if (!onlyIfAbsent || oldValue == null)
e.value = value;
afterNodeAccess(e);
return oldValue;
}
}
++modCount;
if (++size > threshold)
resize();
afterNodeInsertion(evict);
return null;
}
首先执行hashmap的插入操作,如果待插入的key已经存在,则更新value值,返回旧value值,并且执行afterNodeAccess操作,实现将最近被访问的元素置于链表尾部;
插入结束之后会执行afterNodeInsertion方法,此处evict=true
void afterNodeInsertion(boolean evict) { // possibly remove eldest
LinkedHashMap.Entry<K,V> first;
if (evict && (first = head) != null && removeEldestEntry(first)) {
K key = first.key;
removeNode(hash(key), key, null, false, true);
}
}
由于removeEldestEntry方法已经重写 当元素数量超过容量,则需要执行removeNode操作。
@Override
protected boolean removeEldestEntry(java.util.Map.Entry<Integer, Integer> eldest) {
return this.size() > cacheSize;
}
final Node<K,V> removeNode(int hash, Object key, Object value,
boolean matchValue, boolean movable) {
Node<K,V>[] tab; Node<K,V> p; int n, index;
if ((tab = table) != null && (n = tab.length) > 0 &&
(p = tab[index = (n - 1) & hash]) != null) {
Node<K,V> node = null, e; K k; V v;
if (p.hash == hash &&
((k = p.key) == key || (key != null && key.equals(k))))
node = p;
else if ((e = p.next) != null) {
if (p instanceof TreeNode)
node = ((TreeNode<K,V>)p).getTreeNode(hash, key);
else {
do {
if (e.hash == hash &&
((k = e.key) == key ||
(key != null && key.equals(k)))) {
node = e;
break;
}
p = e;
} while ((e = e.next) != null);
}
}
if (node != null && (!matchValue || (v = node.value) == value ||
(value != null && value.equals(v)))) {
if (node instanceof TreeNode)
((TreeNode<K,V>)node).removeTreeNode(this, tab, movable);
else if (node == p)
tab[index] = node.next;
else
p.next = node.next;
++modCount;
--size;
afterNodeRemoval(node);
return node;
}
}
return null;
}
将node节点删除之后,将node p从双向链表中删除,删除时从头部删除
void afterNodeRemoval(Node<K,V> e) { // unlink
LinkedHashMap.Entry<K,V> p =
(LinkedHashMap.Entry<K,V>)e, b = p.before, a = p.after;
p.before = p.after = null;
if (b == null)
head = a;
else
b.after = a;
if (a == null)
tail = b;
else
a.before = b;
}