2 Chapter 15. Parallel Query
6 15.1. How Parallel Query Works
7 15.2. When Can Parallel Query Be Used?
10 15.3.1. Parallel Scans
11 15.3.2. Parallel Joins
12 15.3.3. Parallel Aggregation
13 15.3.4. Parallel Append
14 15.3.5. Parallel Plan Tips
18 15.4.1. Parallel Labeling for Functions and Aggregates
20 PostgreSQL can devise query plans that can leverage multiple CPUs in
21 order to answer queries faster. This feature is known as parallel
22 query. Many queries cannot benefit from parallel query, either due to
23 limitations of the current implementation or because there is no
24 imaginable query plan that is any faster than the serial query plan.
25 However, for queries that can benefit, the speedup from parallel query
26 is often very significant. Many queries can run more than twice as fast
27 when using parallel query, and some queries can run four times faster
28 or even more. Queries that touch a large amount of data but return only
29 a few rows to the user will typically benefit most. This chapter
30 explains some details of how parallel query works and in which
31 situations it can be used so that users who wish to make use of it can
32 understand what to expect.