sql-benchmarks-dagster/sql_benchmarks/experiments/queue/quack_execution_modes.yaml at main · rctruta/sql-benchmarks-dagster · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
meta:
  name: "Quack Execution Modes: Attach vs Pushdown vs In-Process"
  description: >
    Mechanism experiment for the Quack protocol (DuckDB 1.5.3 beta).
    An earlier exploratory run showed attach-mode protocol
    overhead GROWS with scan size (2.7x at 100K rows, 4.9x at 1M) even
    though the analytical_wall result set is a constant 12 rows.
    Hypothesis: in attach mode (ATTACH + USE) the client plans the query
    and streams table data over HTTP; remote.query() pushdown executes
    fully server-side, so its overhead curve should stay flat at the
    constant cost of shipping 12 result rows.
    Three variants, identical data, identical SQL, identical cold-cache
    discipline: duckdb (in-process floor), quack (attach), quack_pushdown.

dataset:
  source: sql_benchmarks.plugins.data_sources.declarative_gen
  tables:
    analytical_data:
      rows: rows
      columns:
        - name: id
          provider: sequence
          primary_key: true
        - name: region
          provider: choice
          options: ["North", "South", "East", "West"]
        - name: category
          provider: choice
          options: ["A", "B", "C"]
        - name: price
          provider: random_float
          min_value: 10.0
          max_value: 500.0
        - name: quantity
          provider: random_int
          min_value: 1
          max_value: 100
        - name: discount
          provider: random_float
          min_value: 0.0
          max_value: 0.30

definitions:
  rows:
    tiny:   1_000
    small:  100_000
    medium: 1_000_000
    large:  10_000_000

execution:
  test_suite: analytical_wall
  engines:
    - duckdb
    - quack
    - quack_pushdown
  replication: 5
  matrix:
    rows:
      - tiny
      - small
      - medium
      - large