2026-06-09T21-31-25Z_pgvector-S0-filtered
pgvectorStufe S0 · 2.00 GBfilteredStatus: ok
Metriken
Throughput
388.8 QPS
Latenz ⌀
2.55 ms
Latenz p50
2.54 ms
Latenz p95
3.05 ms
Latenz p99
3.43 ms
Recall@1
85.10%
Recall@10
77.86%
Recall@100
46.34%
Precision@10
81.56%
NDCG@10
84.20%
Rohdaten
summary.json ↗Vollständige Run-Metrikenhttps://raw.githubusercontent.com/unrealshape/bachelor-db-benchmark/main/results/2026-06-09T21-31-25Z_pgvector-S0-filtered/summary.jsonconfig.json ↗Eingesetzte Konfigurationhttps://raw.githubusercontent.com/unrealshape/bachelor-db-benchmark/main/results/2026-06-09T21-31-25Z_pgvector-S0-filtered/config.jsonDatensatz · 2.00 GB ↗Generator + Bauanleitung im RepoRun-Ordner auf GitHub ↗Beide Rohdateien im Verzeichnis
Konfiguration
- Config-Name
- pgvector-S0-filtered
- DB-Version
- —
- Image
- —
- Index-Typ
- hnsw
- Index-Params
- {"m":16,"ef_construction":128,"ef_search":64}
- Dataset
- S0 · 550.000 Vektoren · dim 1024 · Variante A · 2.00 GB
- Queries
- 2.000 (Concurrency 1)
Lauf
- Gestartet
- 09.06.2026, 23:31:25
- Beendet
- 09.06.2026, 23:41:22
- Dauer
- 7797s
- Index-Bauzeit
- 348.42s
- Index-Größe
- 4249.4 MB
- CPU ⌀ / Peak
- 1.22 / 2.00 cores
- RAM ⌀ / Peak
- 7822 / 13973 MB
- Disk read (Paging)
- 2605 MB
- Disk write
- 15797 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: 216.95 n_vectors_actual: 550000 has_metadata: true gt_file: ground_truth_filter_rating_gte_4_ids.npy measured: in-cluster n_queries_executed: 1000 n_warmup: 1000 mode: real