我有一个自定义的“CachedEnumerable”类(灵感来自缓存 IEnumerable https://stackoverflow.com/q/1537043/5683904)我需要确保我的 ASP.NET Core Web 应用程序的线程安全。
Enumerator 线程的以下实现安全吗? (对 IList _cache 的所有其他读/写都被适当锁定)(可能与C# Yield 是否会释放锁? https://stackoverflow.com/q/4608215/5683904)
更具体地说,如果有 2 个线程访问枚举器,我如何防止一个线程递增“索引”导致第二个枚举线程从 _cache 获取错误的元素(即索引 + 1 处的元素而不是索引处的元素) ?这种竞争条件真的值得关注吗?
public IEnumerator<T> GetEnumerator()
{
var index = 0;
while (true)
{
T current;
lock (_enumeratorLock)
{
if (index >= _cache.Count && !MoveNext()) break;
current = _cache[index];
index++;
}
yield return current;
}
}
我的 CachedEnumerable 版本的完整代码:
public class CachedEnumerable<T> : IDisposable, IEnumerable<T>
{
IEnumerator<T> _enumerator;
private IList<T> _cache = new List<T>();
public bool CachingComplete { get; private set; } = false;
public CachedEnumerable(IEnumerable<T> enumerable)
{
switch (enumerable)
{
case CachedEnumerable<T> cachedEnumerable: //This case is actually dealt with by the extension method.
_cache = cachedEnumerable._cache;
CachingComplete = cachedEnumerable.CachingComplete;
_enumerator = cachedEnumerable.GetEnumerator();
break;
case IList<T> list:
//_cache = list; //without clone...
//Clone:
_cache = new T[list.Count];
list.CopyTo((T[]) _cache, 0);
CachingComplete = true;
break;
default:
_enumerator = enumerable.GetEnumerator();
break;
}
}
public CachedEnumerable(IEnumerator<T> enumerator)
{
_enumerator = enumerator;
}
private int CurCacheCount
{
get
{
lock (_enumeratorLock)
{
return _cache.Count;
}
}
}
public IEnumerator<T> GetEnumerator()
{
var index = 0;
while (true)
{
T current;
lock (_enumeratorLock)
{
if (index >= _cache.Count && !MoveNext()) break;
current = _cache[index];
index++;
}
yield return current;
}
}
//private readonly AsyncLock _enumeratorLock = new AsyncLock();
private readonly object _enumeratorLock = new object();
private bool MoveNext()
{
if (CachingComplete) return false;
if (_enumerator != null && _enumerator.MoveNext()) //The null check should have been unnecessary b/c of the lock...
{
_cache.Add(_enumerator.Current);
return true;
}
else
{
CachingComplete = true;
DisposeWrappedEnumerator(); //Release the enumerator, as it is no longer needed.
}
return false;
}
public T ElementAt(int index)
{
lock (_enumeratorLock)
{
if (index < _cache.Count)
{
return _cache[index];
}
}
EnumerateUntil(index);
lock (_enumeratorLock)
{
if (_cache.Count <= index) throw new ArgumentOutOfRangeException(nameof(index));
return _cache[index];
}
}
public bool TryGetElementAt(int index, out T value)
{
lock (_enumeratorLock)
{
value = default;
if (index < CurCacheCount)
{
value = _cache[index];
return true;
}
}
EnumerateUntil(index);
lock (_enumeratorLock)
{
if (_cache.Count <= index) return false;
value = _cache[index];
}
return true;
}
private void EnumerateUntil(int index)
{
while (true)
{
lock (_enumeratorLock)
{
if (_cache.Count > index || !MoveNext()) break;
}
}
}
public void Dispose()
{
DisposeWrappedEnumerator();
}
private void DisposeWrappedEnumerator()
{
if (_enumerator != null)
{
_enumerator.Dispose();
_enumerator = null;
if (_cache is List<T> list)
{
list.Trim();
}
}
}
IEnumerator IEnumerable.GetEnumerator()
{
return GetEnumerator();
}
public int CachedCount
{
get
{
lock (_enumeratorLock)
{
return _cache.Count;
}
}
}
public int Count()
{
if (CachingComplete)
{
return _cache.Count;
}
EnsureCachingComplete();
return _cache.Count;
}
private void EnsureCachingComplete()
{
if (CachingComplete)
{
return;
}
//Enumerate the rest of the collection
while (!CachingComplete)
{
lock (_enumeratorLock)
{
if (!MoveNext()) break;
}
}
}
public T[] ToArray()
{
EnsureCachingComplete();
//Once Caching is complete, we don't need to lock
if (!(_cache is T[] array))
{
array = _cache.ToArray();
_cache = array;
}
return array;
}
public T this[int index] => ElementAt(index);
}
public static CachedEnumerable<T> Cached<T>(this IEnumerable<T> source)
{
//no gain in caching a cache.
if (source is CachedEnumerable<T> cached)
{
return cached;
}
return new CachedEnumerable<T>(source);
}
}
基本用法:(虽然不是一个有意义的用例)
var cached = expensiveEnumerable.Cached();
foreach (var element in cached) {
Console.WriteLine(element);
}
Update
我根据 @Theodors 答案测试了当前的实现https://stackoverflow.com/a/58547863/5683904 https://stackoverflow.com/a/58547863/5683904并确认(AFAICT)使用 foreach 枚举时它是线程安全的,而不会创建重复值():
class Program
{
static async Task Main(string[] args)
{
var enumerable = Enumerable.Range(0, 1_000_000);
var cachedEnumerable = new CachedEnumerable<int>(enumerable);
var c = new ConcurrentDictionary<int, List<int>>();
var tasks = Enumerable.Range(1, 100).Select(id => Test(id, cachedEnumerable, c));
Task.WaitAll(tasks.ToArray());
foreach (var keyValuePair in c)
{
var hasDuplicates = keyValuePair.Value.Distinct().Count() != keyValuePair.Value.Count;
Console.WriteLine($"Task #{keyValuePair.Key} count: {keyValuePair.Value.Count}. Has duplicates? {hasDuplicates}");
}
}
static async Task Test(int id, IEnumerable<int> cache, ConcurrentDictionary<int, List<int>> c)
{
foreach (var i in cache)
{
//await Task.Delay(10);
c.AddOrUpdate(id, v => new List<int>() {i}, (k, v) =>
{
v.Add(i);
return v;
});
}
}
}