2026-06-14T12-54-50Z_pgvector-M-filtered-r2
pgvectorStufe M · 20.00 GBfilteredStatus: ok
Metriken
Throughput
15.3 QPS
Latenz ⌀
65.14 ms
Latenz p50
57.07 ms
Latenz p95
128.12 ms
Latenz p99
203.06 ms
Recall@1
62.90%
Recall@10
56.70%
Recall@100
47.83%
Precision@10
56.70%
NDCG@10
67.63%
Rohdaten
summary.json ↗Vollständige Run-Metrikenhttps://raw.githubusercontent.com/unrealshape/bachelor-db-benchmark/main/results/2026-06-14T12-54-50Z_pgvector-M-filtered-r2/summary.jsonconfig.json ↗Eingesetzte Konfigurationhttps://raw.githubusercontent.com/unrealshape/bachelor-db-benchmark/main/results/2026-06-14T12-54-50Z_pgvector-M-filtered-r2/config.jsonDatensatz · 20.00 GB ↗Generator + Bauanleitung im RepoRun-Ordner auf GitHub ↗Beide Rohdateien im Verzeichnis
Konfiguration
- Config-Name
- pgvector-M-filtered
- DB-Version
- —
- Image
- —
- Index-Typ
- ivfflat
- Index-Params
- {"lists":4900,"probes":10}
- Dataset
- M · 5.250.000 Vektoren · dim 1024 · Variante A · 20.00 GB
- Queries
- 2.000 (Concurrency 1)
Lauf
- Gestartet
- 14.06.2026, 14:54:50
- Beendet
- 14.06.2026, 14:56:53
- Dauer
- 7323s
- Index-Bauzeit
- 2381.09s
- Index-Größe
- 41053.9 MB
- CPU ⌀ / Peak
- 0.40 / 0.48 cores
- RAM ⌀ / Peak
- 19402 / 19804 MB
- Disk read (Paging)
- 28759 MB
- Disk write
- 25 MB
- Pod-RAM-Limit
- 20 GiB
- Warmup-Queries
- 1.000
- K8s
- v1.31.4+k3s1
- Nodes
- 4
Notizen
measured: in-cluster decoupled: true ingested_at: 2026-06-14T12:52:14Z ingest_config: pgvector-M-pressure-20gb insert_time_s: 2196.77 n_vectors_actual: 5250000 has_metadata: true mem_limit_gb: 20 pre_run_reset: skipped (decoupled, warmup-discard) n_queries_executed: 1000 n_warmup: 1000 gt_file: ground_truth_filter_rating_gte_4_ids.npy mode: measure-only repeat_group: 2026-06-14T12-52-16Z_pgvector-M-filtered repeat_index: 2 repeat_total: 3