2026-06-17T18-02-43Z_pgvector-S0-throughput-c8-r6
pgvectorStufe S0 · 2.00 GBbatchStatus: ok
Metriken
Throughput
320.3 QPS
Latenz ⌀
24.81 ms
Latenz p50
24.82 ms
Latenz p95
27.36 ms
Latenz p99
28.58 ms
Recall@1
87.90%
Recall@10
83.27%
Recall@100
60.44%
Precision@10
83.27%
NDCG@10
88.54%
Rohdaten
summary.json ↗Vollständige Run-Metrikenhttps://raw.githubusercontent.com/unrealshape/bachelor-db-benchmark/main/results/2026-06-17T18-02-43Z_pgvector-S0-throughput-c8-r6/summary.jsonconfig.json ↗Eingesetzte Konfigurationhttps://raw.githubusercontent.com/unrealshape/bachelor-db-benchmark/main/results/2026-06-17T18-02-43Z_pgvector-S0-throughput-c8-r6/config.jsonDatensatz · 2.00 GB ↗Generator + Bauanleitung im RepoRun-Ordner auf GitHub ↗Beide Rohdateien im Verzeichnis
Konfiguration
- Config-Name
- pgvector-S0-throughput-c8
- 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 8)
Lauf
- Gestartet
- 17.06.2026, 20:02:43
- Beendet
- 17.06.2026, 20:02:55
- Dauer
- 7212s
- Index-Bauzeit
- 635.26s
- Index-Größe
- 4249.4 MB
- CPU ⌀ / Peak
- 0.25 / 0.30 cores
- RAM ⌀ / Peak
- 6796 / 6799 MB
- Disk read (Paging)
- 0 MB
- Disk write
- 0 MB
- Pod-RAM-Limit
- Default
- Warmup-Queries
- 1.000
- K8s
- v1.31.4+k3s1
- Nodes
- 4
Notizen
measured: in-cluster decoupled: true ingested_at: 2026-06-17T18:00:51Z ingest_config: pgvector-S0-latency insert_time_s: 212.62 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: 2026-06-17T18-00-51Z_pgvector-S0-throughput-c8 repeat_index: 6 repeat_total: 6