2026-06-17T17-45-54Z_pgvector-XS-throughput-c8-r5
pgvectorStufe XS · 410 MBbatchStatus: ok
Metriken
Throughput
431.4 QPS
Latenz ⌀
18.41 ms
Latenz p50
18.37 ms
Latenz p95
20.24 ms
Latenz p99
22.21 ms
Recall@1
89.10%
Recall@10
86.54%
Recall@100
62.93%
Precision@10
86.54%
NDCG@10
90.89%
Rohdaten
summary.json ↗Vollständige Run-Metrikenhttps://raw.githubusercontent.com/unrealshape/bachelor-db-benchmark/main/results/2026-06-17T17-45-54Z_pgvector-XS-throughput-c8-r5/summary.jsonconfig.json ↗Eingesetzte Konfigurationhttps://raw.githubusercontent.com/unrealshape/bachelor-db-benchmark/main/results/2026-06-17T17-45-54Z_pgvector-XS-throughput-c8-r5/config.jsonDatensatz · 410 MB ↗Generator + Bauanleitung im RepoRun-Ordner auf GitHub ↗Beide Rohdateien im Verzeichnis
Konfiguration
- Config-Name
- pgvector-XS-throughput-c8
- DB-Version
- —
- Image
- —
- Index-Typ
- hnsw
- Index-Params
- {"m":16,"ef_construction":128,"ef_search":64}
- Dataset
- XS · 150.000 Vektoren · dim 1024 · Variante A · 410 MB
- Queries
- 10.000 (Concurrency 8)
Lauf
- Gestartet
- 17.06.2026, 19:45:54
- Beendet
- 17.06.2026, 19:46:04
- Dauer
- 7210s
- Index-Bauzeit
- 73.07s
- Index-Größe
- 1158.1 MB
- CPU ⌀ / Peak
- 0.27 / 0.27 cores
- RAM ⌀ / Peak
- 2194 / 2194 MB
- Disk read (Paging)
- 0 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: 2026-06-17T17:44:42Z ingest_config: pgvector-XS-latency insert_time_s: 54.45 n_vectors_actual: 150000 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: 2026-06-17T17-44-43Z_pgvector-XS-throughput-c8 repeat_index: 5 repeat_total: 6