2026-06-19T03-24-44Z_pgvector-M-throughput-c8-r1
pgvectorStufe M · 20.00 GBbatchStatus: ok
Metriken
Throughput
2.7 QPS
Latenz ⌀
2930.81 ms
Latenz p50
2942.01 ms
Latenz p95
3537.58 ms
Latenz p99
3817.32 ms
Recall@1
71.70%
Recall@10
68.03%
Recall@100
62.47%
Precision@10
68.03%
NDCG@10
77.12%
Rohdaten
summary.json ↗Vollständige Run-Metrikenhttps://raw.githubusercontent.com/unrealshape/bachelor-db-benchmark/main/results/2026-06-19T03-24-44Z_pgvector-M-throughput-c8-r1/summary.jsonconfig.json ↗Eingesetzte Konfigurationhttps://raw.githubusercontent.com/unrealshape/bachelor-db-benchmark/main/results/2026-06-19T03-24-44Z_pgvector-M-throughput-c8-r1/config.jsonDatensatz · 20.00 GB ↗Generator + Bauanleitung im RepoRun-Ordner auf GitHub ↗Beide Rohdateien im Verzeichnis
Konfiguration
- Config-Name
- pgvector-M-throughput-c8
- 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 8)
Lauf
- Gestartet
- 19.06.2026, 05:24:44
- Beendet
- 19.06.2026, 05:37:17
- Dauer
- 7953s
- Index-Bauzeit
- 500.1s
- Index-Größe
- 41023.4 MB
- CPU ⌀ / Peak
- 0.47 / 1.00 cores
- RAM ⌀ / Peak
- 7292 / 7482 MB
- Disk read (Paging)
- 493731 MB
- Disk write
- 2145 MB
- Pod-RAM-Limit
- Default
- Warmup-Queries
- 1.000
- K8s
- v1.31.4+k3s1
- Nodes
- 4
Notizen
measured: in-cluster decoupled: true ingested_at: 2026-06-19T03:24:44Z ingest_config: pgvector-M-ivfflat insert_time_s: 2051.38 n_vectors_actual: 5250000 has_metadata: true mem_limit_gb: null pre_run_reset: skipped (decoupled, warmup-discard) n_queries_executed: 1000 n_warmup: 1000 gt_file: ground_truth_ids.npy mode: measure-only repeat_group: 2026-06-19T03-24-44Z_pgvector-M-throughput-c8 repeat_index: 1 repeat_total: 6