2026-06-09T20-21-19Z_pgvector-S0-ivfflat
pgvectorStufe S0 · 2.00 GBtopkStatus: ok
Metriken
Throughput
93.1 QPS
Latenz ⌀
10.71 ms
Latenz p50
10.66 ms
Latenz p95
14.53 ms
Latenz p99
15.85 ms
Recall@1
68.80%
Recall@10
67.77%
Recall@100
60.18%
Precision@10
67.77%
NDCG@10
77.04%
Rohdaten
summary.json ↗Vollständige Run-Metrikenhttps://raw.githubusercontent.com/unrealshape/bachelor-db-benchmark/main/results/2026-06-09T20-21-19Z_pgvector-S0-ivfflat/summary.jsonconfig.json ↗Eingesetzte Konfigurationhttps://raw.githubusercontent.com/unrealshape/bachelor-db-benchmark/main/results/2026-06-09T20-21-19Z_pgvector-S0-ivfflat/config.jsonDatensatz · 2.00 GB ↗Generator + Bauanleitung im RepoRun-Ordner auf GitHub ↗Beide Rohdateien im Verzeichnis
Konfiguration
- Config-Name
- pgvector-S0-ivfflat
- DB-Version
- —
- Image
- —
- Index-Typ
- ivfflat
- Index-Params
- {"lists":500,"probes":10}
- Dataset
- S0 · 550.000 Vektoren · dim 1024 · Variante A · 2.00 GB
- Queries
- 2.000 (Concurrency 1)
Lauf
- Gestartet
- 09.06.2026, 22:21:19
- Beendet
- 09.06.2026, 22:26:22
- Dauer
- 7503s
- Index-Bauzeit
- 51.24s
- Index-Größe
- 4300.8 MB
- CPU ⌀ / Peak
- 0.41 / 1.71 cores
- RAM ⌀ / Peak
- 2521 / 6566 MB
- Disk read (Paging)
- 15 MB
- Disk write
- 13363 MB
- Pod-RAM-Limit
- Default
- Warmup-Queries
- 1.000
- K8s
- v1.31.4+k3s1
- Nodes
- 4
Notizen
pre_run_reset: rollout-restart timeout_s: 180 insert_time_s: 206.45 n_vectors_actual: 550000 has_metadata: true gt_file: ground_truth_ids.npy measured: in-cluster n_queries_executed: 1000 n_warmup: 1000 mode: real