Concurrency: "having the smallest locks is not cool anymore"

Original quote from the author: «batch your locks. Don’t make critical sections too small. Having the smallest locks is not cool anymore.» http://halobates.de/blog/p/231

In the whitepaper: «The longer lock region has potentially longer block times, but minimizes the communication overhead of transferring the lock too frequently. This is a simple case with only two threads. With more cores in each socket, the queueing delays of transferring will increase. Similarly, on larger systems that have more sockets, the communication delays will also increase. Having too many small lock regions increases communication overhead, while having too many large lock regions increases blocking time.»