2026-06-09T21-41-23Z_pgvector-S0-hybrid
pgvectorStufe S0 · 2.00 GBhybridStatus: ok
Metriken
Throughput
120.2 QPS
Latenz ⌀
8.30 ms
Latenz p50
4.03 ms
Latenz p95
8.84 ms
Latenz p99
88.31 ms
Recall@1
11.90%
Recall@10
32.80%
Recall@100
38.35%
Precision@10
32.80%
NDCG@10
43.64%
Rohdaten
summary.json ↗Vollständige Run-Metrikenhttps://raw.githubusercontent.com/unrealshape/bachelor-db-benchmark/main/results/2026-06-09T21-41-23Z_pgvector-S0-hybrid/summary.jsonconfig.json ↗Eingesetzte Konfigurationhttps://raw.githubusercontent.com/unrealshape/bachelor-db-benchmark/main/results/2026-06-09T21-41-23Z_pgvector-S0-hybrid/config.jsonDatensatz · 2.00 GB ↗Generator + Bauanleitung im RepoRun-Ordner auf GitHub ↗Beide Rohdateien im Verzeichnis
Konfiguration
- Config-Name
- pgvector-S0-hybrid
- 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, 23:41:23
- Beendet
- 09.06.2026, 23:51:17
- Dauer
- 7794s
- Index-Bauzeit
- 346.55s
- Index-Größe
- 4249.4 MB
- CPU ⌀ / Peak
- 1.23 / 2.00 cores
- RAM ⌀ / Peak
- 7610 / 12646 MB
- Disk read (Paging)
- 20 MB
- Disk write
- 16419 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: 209.94 n_vectors_actual: 550000 has_metadata: true gt_file: ground_truth_hybrid_alpha_50_ids.npy measured: in-cluster n_queries_executed: 1000 n_warmup: 1000 mode: real