2026-06-09T22-29-04Z_pgvector-S0-throughput-c16-r2
pgvectorStufe S0 · 2.00 GBbatchStatus: ok
Metriken
Throughput
359.1 QPS
Latenz ⌀
44.07 ms
Latenz p50
44.36 ms
Latenz p95
47.40 ms
Latenz p99
49.45 ms
Recall@1
87.80%
Recall@10
83.41%
Recall@100
60.52%
Precision@10
83.41%
NDCG@10
88.64%
Rohdaten
summary.json ↗Vollständige Run-Metrikenhttps://raw.githubusercontent.com/unrealshape/bachelor-db-benchmark/main/results/2026-06-09T22-29-04Z_pgvector-S0-throughput-c16-r2/summary.jsonconfig.json ↗Eingesetzte Konfigurationhttps://raw.githubusercontent.com/unrealshape/bachelor-db-benchmark/main/results/2026-06-09T22-29-04Z_pgvector-S0-throughput-c16-r2/config.jsonDatensatz · 2.00 GB ↗Generator + Bauanleitung im RepoRun-Ordner auf GitHub ↗Beide Rohdateien im Verzeichnis
Konfiguration
- Config-Name
- pgvector-S0-throughput-c16
- 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
- 10.000 (Concurrency 16)
Lauf
- Gestartet
- 10.06.2026, 00:29:04
- Beendet
- 10.06.2026, 00:38:14
- Dauer
- 7750s
- Index-Bauzeit
- 322.22s
- Index-Größe
- 4249.5 MB
- CPU ⌀ / Peak
- 1.27 / 2.00 cores
- RAM ⌀ / Peak
- 7843 / 12646 MB
- Disk read (Paging)
- 15 MB
- Disk write
- 15968 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: 202.03 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 repeat_group: 2026-06-09T22-19-52Z_pgvector-S0-throughput-c16 repeat_index: 2 repeat_total: 3