Plain DuckDB
Versions
| Run as | Image | Server | DuckDB | Digest |
|---|---|---|---|---|
| DuckDB 1.4.3 | dbench/duckdb:1.4.3 | DuckDB 1.4.3 | 1.4.3 | sha256:ddf68226fc6361bcd0fdf4dde5d9d28ab686f9a9088dd2fb94a31611baa935ed |
| DuckDB 1.5.2-dev736 | dbench/duckdb:1.5.2-dev736 | DuckDB 1.5.2-dev736 | 1.5.2-dev736 | sha256:efb098aaee0cd53609beef05736a7ca12adccba95d809269db9c7db3ec06c16b |
| DuckDB 1.5.3 | dbench/duckdb:1.5.3 | DuckDB 1.5.3 | 1.5.3 | sha256:697dc58e59ee554c9943c43367e0d03b562571019c1bb642727285f07ef35394 |
| DuckDB 1.5.5 | dbench/duckdb:1.5.5 | DuckDB 1.5.5 | 1.5.5 | sha256:fa9ddda0848b69773a2bf83efd4762061d19d422d1b609d4c710ab38cbb37c06 |
| DuckDB 2.0.0 | dbench/duckdb:2.0.0 | DuckDB 2.0.0 | 2.0.0 | sha256:f2528d483b1fc8b08b446e6cb88f5f0e4eb13b74d305bdc4c12320553df57131 |
Observed in this run
Generated the same way for every system from its result files: record counts per measure and status, and the reasons given for anything that is not ok.
DuckDB 1.4.3
- M1: ok 22
- M4: crashed 1, ok 4
- M4 streams=32 (crashed): the container was killed by its memory limit during the run (OOMKilled, exit 137) (219 crashed, 43 timeout, 442 ok of 704 queries); no throughput is reported; first errors: [['q21', 'timeout', 'InterruptException: INTERRUPT Error: Interrupted!'], ['q09', 'crashed', 'ConnectionError: server closed the connection'], ['q11', 'crashed', 'StopIteration: ']]
DuckDB 1.5.2-dev736
- M1: ok 22
- M4: crashed 2, ok 3
- M4 streams=16 (crashed): the container was killed by its memory limit during the run (OOMKilled, exit 137) (318 crashed, 34 ok of 352 queries); no throughput is reported; first errors: [['q07', 'crashed', 'ConnectionError: server closed the connection'], ['q22', 'crashed', 'StopIteration: '], ['q12', 'crashed', 'StopIteration: ']]
- M4 streams=32 (crashed): the container was killed by its memory limit during the run (OOMKilled, exit 137) (86 crashed, 551 error, 31 timeout, 36 ok of 704 queries); no throughput is reported; first errors: [['q21', 'timeout', 'no response from server within timeout + margin'], ['q02', 'error', 'TimeoutError: timed out'], ['q06', 'error', 'TimeoutError: timed out']]
DuckDB 1.5.3
- M1: ok 22
- M4: crashed 1, ok 4
- M4 streams=32 (crashed): the container was killed by its memory limit during the run (OOMKilled, exit 137) (123 crashed, 15 timeout, 566 ok of 704 queries); no throughput is reported; first errors: [['q09', 'timeout', 'InterruptException: INTERRUPT Error: Interrupted!'], ['q05', 'crashed', 'ConnectionError: server closed the connection'], ['q22', 'crashed', 'StopIteration: ']]
DuckDB 1.5.5
- M1: n/a 4, ok 44
- M4: crashed 1, ok 9
- M1 join_innodb (n/a): plain DuckDB has no MySQL table to join; the join is VillageSQL's documented JSON_TABLE pattern
- M1 join_innodb_segment_filter (n/a): plain DuckDB has no database table to join; the hybrid joins are measured on VillageSQL (JSON_TABLE over duckdb_query()) and pg_duckdb (read_parquet() joined to heap tables)
- M1 join_innodb_supplier_region (n/a): plain DuckDB has no database table to join; the hybrid joins are measured on VillageSQL (JSON_TABLE over duckdb_query()) and pg_duckdb (read_parquet() joined to heap tables)
- M1 join_innodb_top_customers (n/a): plain DuckDB has no database table to join; the hybrid joins are measured on VillageSQL (JSON_TABLE over duckdb_query()) and pg_duckdb (read_parquet() joined to heap tables)
- M4 streams=32 (crashed): the container was killed by its memory limit during the run (OOMKilled, exit 137) (149 crashed, 18 timeout, 537 ok of 704 queries); no throughput is reported; first errors: [['q09', 'timeout', 'InterruptException: INTERRUPT Error: Interrupted!'], ['q17', 'crashed', 'ConnectionError: server closed the connection'], ['q09', 'timeout', 'InterruptException: INTERRUPT Error: Interrupted!']]
DuckDB 2.0.0
- M1: ok 22
- M4: ok 5
Settings that differ from the defaults
No settings files for this system.
README
Plain DuckDB reference
DuckDB behind a small TCP JSON-lines query server (server.py), so query timing is measured server-side and excludes client startup. One cursor per TCP connection on the database file /var/lib/duckdb/tpch.duckdb.
Images (dbench/duckdb:<version>):
docker build -t dbench/duckdb:1.4.3 --build-arg DUCKDB_VERSION=1.4.3 systems/duckdb
docker build -t dbench/duckdb:1.5.5 --build-arg DUCKDB_VERSION=1.5.5 systems/duckdb
docker build -t dbench/duckdb:2.0.0 --build-arg DUCKDB_VERSION=2.0.0 systems/duckdb
# AliSQL snapshot (duckdb/duckdb commit 8a66223), built from source, version v1.5.2-dev736
docker build -t dbench/duckdb:1.5.2-dev736 \
--build-arg DUCKDB_VERSION=1.5.2-dev736 \
--build-arg DUCKDB_SOURCE_COMMIT=8a66223119b16000f3814fa7150cfa7370b63209 \
--build-arg DUCKDB_PYTHON_TAG=v1.5.2 \
--build-arg DUCKDB_GIT_DESCRIBE=v1.5.1-736-g8a6622311 systems/duckdb
Settings (from the container limits): threads = cores in the DB cpuset, memory_limit = 80% of the container memory (headroom for non-buffer allocations).
Schema: TPC-H tables with primary keys, no other indexes. There is no row store, so M11 and M12 are n/a.