mirror of
https://github.com/sandronator/finetuning_aufgabe4.git
synced 2026-09-04 00:26:06 +02:00
Sandro Fuetsch TitanandClaude Opus 4.7
d8a906e2d4
The Manager previously called setupBoth() on every test step, which dropped both PostgreSQL and MariaDB tables and re-imported the full DBLP TSVs (~9 reloads across 2 DBs in a single run, even though only PostgreSQL was used). Now data is loaded once via load_data_postgres() and only the indexes are swapped between tests via apply_indexes_postgres(). A reset_postgres(config, reload_data=False) helper lets callers force a full reload when needed -- used after 'cl-both' tests, since CLUSTER physically reorders the table and dropping the index alone does not restore the original layout. Also fixes two bugs found while reading the code: - baseStrategy.run iterated 'self.queries' instead of '.items()', which would crash on the first unpack. - main.py was missing an execute() call after the Aufgabe 3 'cl-both' setup, silently skipping that test. Co-Authored-By: Claude Opus 4.7 <[email protected]>
48 lines
2.0 KiB
Python
48 lines
2.0 KiB
Python
from manager import Manager
|
|
from baseStrategy import BaseStrategy
|
|
from nestedInnerLoopStrategy import NestedInnerLoopStrategy
|
|
from sortMergeStrategy import SortMergeStrategy
|
|
from hashJoinStrategy import HashJoinStrategy
|
|
from setup import get_connection, load_data_postgres
|
|
from repositories.all_queries import queries_postgres
|
|
|
|
if __name__ == '__main__':
|
|
db_post, conn_postsql = get_connection(maria=False)
|
|
|
|
# Daten einmalig laden; danach werden zwischen den Tests nur die Indexe getauscht.
|
|
load_data_postgres()
|
|
|
|
# Aufgabe 1
|
|
join_manager = Manager(BaseStrategy(conn_postsql, db_post, queries_postgres["with_index"]))
|
|
# join_manager.setup_db("no-index")
|
|
# join_manager.execute() # 3 Mrd. Tupel via Kreuzprodukt -> > 10 min
|
|
join_manager.setup_db("unique-publ")
|
|
join_manager.execute()
|
|
join_manager.setup_db("cl-both")
|
|
join_manager.execute()
|
|
|
|
# Aufgabe 2 — vorheriger Lauf war 'cl-both' (CLUSTER hat Tabelle physisch sortiert);
|
|
# reload_data=True stellt die ursprüngliche Ladereihenfolge wieder her.
|
|
join_manager.setStrategy(NestedInnerLoopStrategy(conn_postsql, db_post, queries_postgres["with_index"]))
|
|
join_manager.setup_db("nc-publ", reload_data=True)
|
|
join_manager.execute()
|
|
join_manager.setup_db("nc-auth")
|
|
join_manager.execute()
|
|
join_manager.setup_db("nc-both")
|
|
join_manager.execute()
|
|
|
|
# Aufgabe 3 — Tabelle ist noch im Original-Layout, kein Reload nötig.
|
|
join_manager.setStrategy(SortMergeStrategy(conn_postsql, db_post, queries_postgres["no_index"]))
|
|
join_manager.setup_db("no-index")
|
|
join_manager.execute()
|
|
join_manager.setQueries(queries_postgres["with_index"])
|
|
join_manager.setup_db("nc-both")
|
|
join_manager.execute()
|
|
join_manager.setup_db("cl-both")
|
|
join_manager.execute()
|
|
|
|
# Aufgabe 4 — wieder vom CLUSTER-Zustand wegkommen.
|
|
join_manager.setStrategy(HashJoinStrategy(conn_postsql, db_post, queries_postgres["no_index"]))
|
|
join_manager.setup_db("no-index", reload_data=True)
|
|
join_manager.execute()
|