2026-06-12T08-19-56Z_pgvector-S-ivfflat-throughput-c4-r2
pgvectorStufe S · 10.00 GBbatchStatus: ok
Metriken
Throughput
6.9 QPS
Latenz ⌀
578.91 ms
Latenz p50
575.42 ms
Latenz p95
821.25 ms
Latenz p99
948.42 ms
Recall@1
69.90%
Recall@10
67.71%
Recall@100
60.81%
Precision@10
67.71%
NDCG@10
76.82%
Rohdaten
summary.json ↗Vollständige Run-Metrikenhttps://raw.githubusercontent.com/unrealshape/bachelor-db-benchmark/main/results/2026-06-12T08-19-56Z_pgvector-S-ivfflat-throughput-c4-r2/summary.jsonconfig.json ↗Eingesetzte Konfigurationhttps://raw.githubusercontent.com/unrealshape/bachelor-db-benchmark/main/results/2026-06-12T08-19-56Z_pgvector-S-ivfflat-throughput-c4-r2/config.jsonDatensatz · 10.00 GB ↗Generator + Bauanleitung im RepoRun-Ordner auf GitHub ↗Beide Rohdateien im Verzeichnis
Konfiguration
- Config-Name
- pgvector-S-ivfflat-throughput-c4
- DB-Version
- —
- Image
- —
- Index-Typ
- ivfflat
- Index-Params
- {"lists":1000,"probes":10}
- Dataset
- S · 2.650.000 Vektoren · dim 1024 · Variante A · 10.00 GB
- Queries
- 10.000 (Concurrency 4)
Lauf
- Gestartet
- 12.06.2026, 10:19:56
- Beendet
- 12.06.2026, 10:24:50
- Dauer
- 7494s
- Index-Bauzeit
- 268.8s
- Index-Größe
- 20710.9 MB
- CPU ⌀ / Peak
- 0.46 / 0.49 cores
- RAM ⌀ / Peak
- 7450 / 7483 MB
- Disk read (Paging)
- 145973 MB
- Disk write
- 0 MB
- Pod-RAM-Limit
- Default
- Warmup-Queries
- 1.000
- K8s
- v1.31.4+k3s1
- Nodes
- 4
Notizen
measured: in-cluster decoupled: true ingested_at: 2026-06-12T07:10:46Z ingest_config: pgvector-S-ivfflat insert_time_s: 1049.52 n_vectors_actual: 2650000 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: 2026-06-12T08-14-55Z_pgvector-S-ivfflat-throughput-c4 repeat_index: 2 repeat_total: 3