2026-06-15T22-18-00Z_pgvector-S0-ivfflat-r6
pgvectorStufe S0 · 2.00 GBtopkStatus: ok
Metriken
Throughput
98.8 QPS
Latenz ⌀
10.09 ms
Latenz p50
9.79 ms
Latenz p95
14.39 ms
Latenz p99
18.35 ms
Recall@1
70.40%
Recall@10
68.20%
Recall@100
60.77%
Precision@10
68.20%
NDCG@10
77.39%
Rohdaten
summary.json ↗Vollständige Run-Metrikenhttps://raw.githubusercontent.com/unrealshape/bachelor-db-benchmark/main/results/2026-06-15T22-18-00Z_pgvector-S0-ivfflat-r6/summary.jsonconfig.json ↗Eingesetzte Konfigurationhttps://raw.githubusercontent.com/unrealshape/bachelor-db-benchmark/main/results/2026-06-15T22-18-00Z_pgvector-S0-ivfflat-r6/config.jsonDatensatz · 2.00 GB ↗Generator + Bauanleitung im RepoRun-Ordner auf GitHub ↗Beide Rohdateien im Verzeichnis
Konfiguration
- Config-Name
- pgvector-S0-ivfflat
- DB-Version
- —
- Image
- —
- Index-Typ
- ivfflat
- Index-Params
- {"lists":500,"probes":10}
- Dataset
- S0 · 550.000 Vektoren · dim 1024 · Variante A · 2.00 GB
- Queries
- 2.000 (Concurrency 1)
Lauf
- Gestartet
- 16.06.2026, 00:18:00
- Beendet
- 16.06.2026, 00:18:26
- Dauer
- 7226s
- Index-Bauzeit
- 40.59s
- Index-Größe
- 4300.8 MB
- CPU ⌀ / Peak
- 0.65 / 0.97 cores
- RAM ⌀ / Peak
- 7340 / 7340 MB
- Disk read (Paging)
- 0 MB
- Disk write
- 11 MB
- Pod-RAM-Limit
- Default
- Warmup-Queries
- 1.000
- K8s
- v1.31.4+k3s1
- Nodes
- 4
Notizen
measured: in-cluster decoupled: true ingested_at: 2026-06-15T22:15:09Z ingest_config: pgvector-S0-ivfflat insert_time_s: 204.04 n_vectors_actual: 550000 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: 2026-06-15T22-15-10Z_pgvector-S0-ivfflat repeat_index: 6 repeat_total: 6