2026-06-09T21-19-44Z_pgvector-S0-latency
pgvectorStufe S0 · 2.00 GBtopkStatus: ok
Metriken
Throughput
377.9 QPS
Latenz ⌀
2.62 ms
Latenz p50
2.60 ms
Latenz p95
3.13 ms
Latenz p99
3.41 ms
Recall@1
87.40%
Recall@10
83.10%
Recall@100
60.33%
Precision@10
83.10%
NDCG@10
88.36%
Rohdaten
summary.json ↗Vollständige Run-Metrikenhttps://raw.githubusercontent.com/unrealshape/bachelor-db-benchmark/main/results/2026-06-09T21-19-44Z_pgvector-S0-latency/summary.jsonconfig.json ↗Eingesetzte Konfigurationhttps://raw.githubusercontent.com/unrealshape/bachelor-db-benchmark/main/results/2026-06-09T21-19-44Z_pgvector-S0-latency/config.jsonDatensatz · 2.00 GB ↗Generator + Bauanleitung im RepoRun-Ordner auf GitHub ↗Beide Rohdateien im Verzeichnis
Konfiguration
- Config-Name
- pgvector-S0-latency
- 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
- 2.000 (Concurrency 1)
Lauf
- Gestartet
- 09.06.2026, 23:19:44
- Beendet
- 09.06.2026, 23:31:24
- Dauer
- 7900s
- Index-Bauzeit
- 436.59s
- Index-Größe
- 4249.4 MB
- CPU ⌀ / Peak
- 1.19 / 2.00 cores
- RAM ⌀ / Peak
- 8099 / 13737 MB
- Disk read (Paging)
- 2699 MB
- Disk write
- 15963 MB
- Pod-RAM-Limit
- Default
- Warmup-Queries
- 1.000
- K8s
- v1.31.4+k3s1
- Nodes
- 4
Notizen
pre_run_reset: rollout-restart timeout_s: 180 insert_time_s: 232.2 n_vectors_actual: 550000 has_metadata: true gt_file: ground_truth_ids.npy measured: in-cluster n_queries_executed: 1000 n_warmup: 1000 mode: real