2026-06-16T23-19-44Z_pgvector-S1-B-throughput-c4-r3
pgvectorStufe S1 · 5.00 GBbatchStatus: ok
Metriken
Throughput
27.8 QPS
Latenz ⌀
143.47 ms
Latenz p50
139.23 ms
Latenz p95
202.87 ms
Latenz p99
228.80 ms
Recall@1
67.60%
Recall@10
64.28%
Recall@100
55.48%
Precision@10
64.28%
NDCG@10
74.18%
Rohdaten
summary.json ↗Vollständige Run-Metrikenhttps://raw.githubusercontent.com/unrealshape/bachelor-db-benchmark/main/results/2026-06-16T23-19-44Z_pgvector-S1-B-throughput-c4-r3/summary.jsonconfig.json ↗Eingesetzte Konfigurationhttps://raw.githubusercontent.com/unrealshape/bachelor-db-benchmark/main/results/2026-06-16T23-19-44Z_pgvector-S1-B-throughput-c4-r3/config.jsonDatensatz · 5.00 GB ↗Generator + Bauanleitung im RepoRun-Ordner auf GitHub ↗Beide Rohdateien im Verzeichnis
Konfiguration
- Config-Name
- pgvector-S1-B-throughput-c4
- DB-Version
- —
- Image
- —
- Index-Typ
- ivfflat
- Index-Params
- {"lists":1200,"probes":10}
- Dataset
- S1 · 1.350.000 Vektoren · dim 1024 · Variante B · 5.00 GB
- Queries
- 2.000 (Concurrency 4)
Lauf
- Gestartet
- 17.06.2026, 01:19:44
- Beendet
- 17.06.2026, 01:20:59
- Dauer
- 7275s
- Index-Bauzeit
- 153.23s
- Index-Größe
- 10556.3 MB
- CPU ⌀ / Peak
- 0.45 / 0.56 cores
- RAM ⌀ / Peak
- 7462 / 7495 MB
- Disk read (Paging)
- 15720 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: 2026-06-16T22:34:30Z ingest_config: pgvector-S1-B-ivfflat insert_time_s: 464.93 n_vectors_actual: 1350000 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_ids.npy mode: measure-only repeat_group: 2026-06-16T23-17-25Z_pgvector-S1-B-throughput-c4 repeat_index: 3 repeat_total: 6