You maintain a relational database for a book publisher. The database contains the following tables. The most common query lists the books for a given authorId. You need to develop a non- relational…

Question

Exhibit

Options

• ACreate a container for Author and a container for Book. In each Author document, embed bookId
• BCreate Author, Book, and Bookauthorlnk documents in the same container.
• CCreate a container that contains a document for each Author and a document for each Book. In
• DCreate a container for Author and a container for Book. In each Author document and Book

• A
  71% (27)
• B
  5% (2)
• C
  8% (3)
• D
  16% (6)

Explanation

In Cosmos DB, the guiding principle is to model data around your most frequent access pattern. The dominant query is 'list all books for a given author.' Creating a container for Author and a container for Book, and embedding the list of bookIds (or full book subdocuments) within each Author document, means a single point read or efficient partition-scoped query retrieves all books for an author in one round trip. This eliminates cross-partition joins and minimizes both latency and RU cost. Storing Author and Book in the same container with a link document (option B) introduces unnecessary complexity, and separate containers without embedding (option D without denormalization) requires multiple reads.

No community discussion yet for this question.