How to implement ConcurrentHashSet in .Net

Sebastian picture Sebastian · Nov 29, 2010 · Viewed 16.7k times · Source

I am trying to implement a ConcurrentHashSet in the spirit of ConcurrentDictionary, approach taken is to use a internal backing ConcurrentDictionary and write small delegating methods, this is how far i got, but well the set theoretic methods are I am stuck on, esp. I am not sure if I can use a foreach and still not violate concurrency

public class ConcurrentHashSet<TElement> : ISet<TElement>
{
    private readonly ConcurrentDictionary<TElement, object> _internal;

    public ConcurrentHashSet(IEnumerable<TElement> elements = null)
    {
        _internal = new ConcurrentDictionary<TElement, object>();
        if (elements != null)
            UnionWith(elements);
    }

    public void UnionWith(IEnumerable<TElement> other)
    {
        if (other == null) throw new ArgumentNullException("other");

        foreach (var otherElement in other)
            Add(otherElement);
    }

    public void IntersectWith(IEnumerable<TElement> other)
    {
        throw new NotImplementedException();
    }

    public void ExceptWith(IEnumerable<TElement> other)
    {
        throw new NotImplementedException();
    }

    public void SymmetricExceptWith(IEnumerable<TElement> other)
    {
        throw new NotImplementedException();
    }

    public bool IsSubsetOf(IEnumerable<TElement> other)
    {
        throw new NotImplementedException();
    }

    public bool IsSupersetOf(IEnumerable<TElement> other)
    {
        throw new NotImplementedException();
    }

    public bool IsProperSupersetOf(IEnumerable<TElement> other)
    {
        throw new NotImplementedException();
    }

    public bool IsProperSubsetOf(IEnumerable<TElement> other)
    {
        throw new NotImplementedException();
    }

    public bool Overlaps(IEnumerable<TElement> other)
    {
        return other.Any(otherElement => _internal.ContainsKey(otherElement));
    }

    public bool SetEquals(IEnumerable<TElement> other)
    {
        int otherCount = 0;
        int thisCount = Count;
        foreach (var otherElement in other)
        {
            otherCount++;
            if (!_internal.ContainsKey(otherElement))
                return false;
        }
        return otherCount == thisCount;
    }

    public bool Add(TElement item)
    {
        return _internal.TryAdd(item, null);
    }

    public void Clear()
    {
        _internal.Clear();
    }

    // I am not sure here if that fullfills contract correctly
    void ICollection<TElement>.Add(TElement item)
    {
        Add(item);
    }

    public bool Contains(TElement item)
    {
        return _internal.ContainsKey(item);
    }

    public void CopyTo(TElement[] array, int arrayIndex)
    {
        _internal.Keys.CopyTo(array, arrayIndex);
    }

    public bool Remove(TElement item)
    {
        object ignore;
        return _internal.TryRemove(item, out ignore);
    }

    public int Count
    {
        get { return _internal.Count; }
    }

    public bool IsReadOnly
    {
        get { return false; }
    }

    public IEnumerator<TElement> GetEnumerator()
    {
        return _internal.Keys.GetEnumerator();
    }

    IEnumerator IEnumerable.GetEnumerator()
    {
        return GetEnumerator();
    }
}

Answer

Ben Mosher picture Ben Mosher · Jun 14, 2012

I just ran into a similar scenario ("I am interested in a fast Add and Contains and Remove") and implemented this sucker:

using System.Collections.Generic;
using System.Threading;

namespace BlahBlah.Utilities
{
    public class ConcurrentHashSet<T> : IDisposable
    {
        private readonly ReaderWriterLockSlim _lock = new ReaderWriterLockSlim(LockRecursionPolicy.SupportsRecursion);
        private readonly HashSet<T> _hashSet = new HashSet<T>();

        #region Implementation of ICollection<T> ...ish
        public bool Add(T item)
        {
            try
            {
                _lock.EnterWriteLock();
                return _hashSet.Add(item);
            }
            finally
            {
                if (_lock.IsWriteLockHeld) _lock.ExitWriteLock();
            }
        }

        public void Clear()
        {
            try
            {
                _lock.EnterWriteLock();
                _hashSet.Clear();
            }
            finally
            {
                if (_lock.IsWriteLockHeld) _lock.ExitWriteLock();
            }
        }

        public bool Contains(T item)
        {
            try
            {
                _lock.EnterReadLock();
                return _hashSet.Contains(item);
            }
            finally
            {
                if (_lock.IsReadLockHeld) _lock.ExitReadLock();
            }
        }

        public bool Remove(T item)
        {
            try
            {
                _lock.EnterWriteLock();
                return _hashSet.Remove(item);
            }
            finally
            {
                if (_lock.IsWriteLockHeld) _lock.ExitWriteLock();
            }
        }

        public int Count
        {
            get
            {
                try
                {
                    _lock.EnterReadLock();
                    return _hashSet.Count;
                }
                finally
                {
                    if (_lock.IsReadLockHeld) _lock.ExitReadLock();
                }
            }
        }
        #endregion

        #region Dispose
        public void Dispose()
        {
            if (_lock != null) _lock.Dispose();
        }
        #endregion
    }
}

Haven't really tested it (performance- or reliability-wise). YMMV.