Synchronisation in .NET– Part 2: Unsafe Data Structures and Padding

In the previous blog post we saw how the lock() statement in .NET scales very poorly when there is a contention on a data structure. It was clear that a performance logging framework that relies on an array with a lock on each member to store data will not scale.

Today, we will try to quantify just how much performance we should expect to get from the data structure if we somehow solve locking. We will also see how the underlying hardware primitives bubble up through the .NET framework and break the pretty object oriented abstraction you might be used to.

Because we have already proven that ConcurrentDictionary adds to much overhead, we will focus on arrays as the backing store for the data structure in all future implementations.

How do Column Stores Work?

In this blog, I will provide you with some basic information about column stores. Nothing I am writing here is vendor specific IP, but merely taken from the papers published throughout history. One of the best papers that serves as an introduction is by Stonebraker:

• Stonebraker et a, Proceedings of 31st VLDB Conference, 2005: C-Store: “C-Store: A Column-oriented DBMS”

The idea is older than that though, with the first papers published in the 1970’ies.

Shamefully standing on the shoulders of giants, I will walk you through a simple example which illustrate one of the key principles of column stores: Run Length Encoding (RLE).

The Effect of CPU Caches and Memory Access Patterns

In this blog, I will provide you with some “Grade of the Steel” background information that will help you understand CPU caches and their effects better.

As we move towards a future where power consumption in the server room begins to make a big dent in the balance sheet – it becomes important for programmers to fully understand hardware and make the best possible use of it, instead of floating around in the leaky abstractions of the virtual systems. Even when we take the old enemy of I/O out of the equation, there are other bottlenecks we need to worry about: DRAM access time being one of the most important.