2026-06-09T21-51-18Z_pgvector-S0-throughput-c4-r1
pgvectorStufe S0 · 2.00 GBbatchStatus: ok
Metriken
Throughput
368.9 QPS
Latenz ⌀
10.76 ms
Latenz p50
10.73 ms
Latenz p95
12.16 ms
Latenz p99
13.15 ms
Recall@1
87.40%
Recall@10
83.19%
Recall@100
60.40%
Precision@10
83.19%
NDCG@10
88.45%
Rohdaten
summary.json ↗Vollständige Run-Metrikenhttps://raw.githubusercontent.com/unrealshape/bachelor-db-benchmark/main/results/2026-06-09T21-51-18Z_pgvector-S0-throughput-c4-r1/summary.jsonconfig.json ↗Eingesetzte Konfigurationhttps://raw.githubusercontent.com/unrealshape/bachelor-db-benchmark/main/results/2026-06-09T21-51-18Z_pgvector-S0-throughput-c4-r1/config.jsonDatensatz · 2.00 GB ↗Generator + Bauanleitung im RepoRun-Ordner auf GitHub ↗Beide Rohdateien im Verzeichnis
Konfiguration
- Config-Name
- pgvector-S0-throughput-c4
- 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 4)
Lauf
- Gestartet
- 09.06.2026, 23:51:18
- Beendet
- 10.06.2026, 00:00:54
- Dauer
- 7776s
- Index-Bauzeit
- 342.16s
- Index-Größe
- 4249.4 MB
- CPU ⌀ / Peak
- 1.25 / 2.00 cores
- RAM ⌀ / Peak
- 7839 / 12644 MB
- Disk read (Paging)
- 17 MB
- Disk write
- 15961 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: 205.46 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: 2026-06-09T21-51-18Z_pgvector-S0-throughput-c4 repeat_index: 1 repeat_total: 3