2026-06-16T10-37-20Z_pgvector-S0-tune-hybrid-a30-r1
pgvectorStufe S0 · 2.00 GBhybridStatus: ok
Metriken
Throughput
111.8 QPS
Latenz ⌀
8.92 ms
Latenz p50
4.46 ms
Latenz p95
9.75 ms
Latenz p99
102.35 ms
Recall@1
5.50%
Recall@10
6.54%
Recall@100
9.01%
Precision@10
6.54%
NDCG@10
7.71%
Rohdaten
summary.json ↗Vollständige Run-Metrikenhttps://raw.githubusercontent.com/unrealshape/bachelor-db-benchmark/main/results/2026-06-16T10-37-20Z_pgvector-S0-tune-hybrid-a30-r1/summary.jsonconfig.json ↗Eingesetzte Konfigurationhttps://raw.githubusercontent.com/unrealshape/bachelor-db-benchmark/main/results/2026-06-16T10-37-20Z_pgvector-S0-tune-hybrid-a30-r1/config.jsonDatensatz · 2.00 GB ↗Generator + Bauanleitung im RepoRun-Ordner auf GitHub ↗Beide Rohdateien im Verzeichnis
Konfiguration
- Config-Name
- pgvector-S0-tune-hybrid-a30
- 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
- 1.000 (Concurrency 1)
Lauf
- Gestartet
- 16.06.2026, 12:37:20
- Beendet
- 16.06.2026, 12:37:44
- Dauer
- 7224s
- Index-Bauzeit
- 620.94s
- Index-Größe
- 4249.4 MB
- CPU ⌀ / Peak
- 0.82 / 1.06 cores
- RAM ⌀ / Peak
- 7320 / 7342 MB
- Disk read (Paging)
- 0 MB
- Disk write
- 0 MB
- Pod-RAM-Limit
- 8 GiB
- Warmup-Queries
- 1.000
- K8s
- v1.31.4+k3s1
- Nodes
- 4
Notizen
measured: in-cluster decoupled: true ingested_at: 2026-06-16T10:24:48Z ingest_config: pgvector-S0-tune-efsweep-ef064 insert_time_s: 203.94 n_vectors_actual: 550000 has_metadata: true mem_limit_gb: 8 pre_run_reset: skipped (decoupled, warmup-discard) n_queries_executed: 1000 n_warmup: 1000 gt_file: ground_truth_hybrid_alpha_30_ids.npy mode: measure-only repeat_group: 2026-06-16T10-37-20Z_pgvector-S0-tune-hybrid-a30 repeat_index: 1 repeat_total: 6