Parallelism and Granularity
In this chapter, I have mentioned the unit of work and granularity. In this section I will talk more about these subjects. You will learn how the unit of work is defined, and how its granularity affects load balancing and performance. These subjects fall under the broader topic known as parallelism. Parallelism is the capability of a system to operate on several different machines in parallel.
A unit of work begins when a client calls CoCreateInstance(). The request is forwarded to the load-balancing router, which decides to which cluster machine the request will be delegated. The router returns a reference to the client, ending its involvement in that particular request. From that point on, the client and the selected ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access