Recently, I’ve been interested in DuckDB’s code and decided to take a look. DuckDB is a C++ open-source project, great for beginners to learn, especially those in the database industry.
This section will delve into the MetaPipeline of DuckDB, using an example of joining two tables.
For example:
SELECT name, score FROM student st INNER JOIN score s ON st.id = s.stu_id;
The final plan for this SQL is:
➜ debug git:(master) ./duckdb stu
v0.8.1-dev416 9d5158ccd2
Enter ".help" for usage hints.
D EXPLAIN SELECT name, score FROM student st INNER JOIN score s ON st.id = s.stu_id;
┌─────────────────────────────┐
│┌───────────────────────────┐│
││ Physical Plan ││
│└───────────────────────────┘│
└─────────────────────────────┘
┌───────────────────────────┐
│ PROJECTION │
│ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ │
│ name │
│ score │
└─────────────┬─────────────┘
┌─────────────┴─────────────┐
│ HASH_JOIN │
│ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ │
│ INNER │
│ stu_id = id ├──────────────┐
│ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ │ │
│ EC: 4 │ │
│ Cost: 4 │ │
└─────────────┬─────────────┘ │
┌─────────────┴─────────────┐┌─────────────┴─────────────┐
│ SEQ_SCAN ││ SEQ_SCAN │
│ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ││ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ │
│ score ││ student │
│ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ││ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ │
│ stu_id ││ id │
│ score ││ name │
│ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ││ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ │
│ EC: 4 ││ EC: 3 │
└───────────────────────────┘└───────────────────────────┘
Before diving into this article, let’s ask a few questions:
- What exactly happens with MetaPipeline?
- How many plans are there in the above plan?
- What is a Pipeline?
- What is a MetaPipeline?
Now, let’s get into the main content.
Top comments (0)