2026-06-16T08-49-44Z_pgvector-S0-tune-hnsw-notune-r4
pgvectorStufe S0 · 2.00 GBtopkStatus: ok
Metriken
Throughput
787.4 QPS
Latenz ⌀
1.24 ms
Latenz p50
1.21 ms
Latenz p95
1.65 ms
Latenz p99
1.88 ms
Recall@1
46.40%
Recall@10
43.73%
Recall@100
9.25%
Precision@10
43.73%
NDCG@10
53.73%
Rohdaten
summary.json ↗Vollständige Run-Metrikenhttps://raw.githubusercontent.com/unrealshape/bachelor-db-benchmark/main/results/2026-06-16T08-49-44Z_pgvector-S0-tune-hnsw-notune-r4/summary.jsonconfig.json ↗Eingesetzte Konfigurationhttps://raw.githubusercontent.com/unrealshape/bachelor-db-benchmark/main/results/2026-06-16T08-49-44Z_pgvector-S0-tune-hnsw-notune-r4/config.jsonDatensatz · 2.00 GB ↗Generator + Bauanleitung im RepoRun-Ordner auf GitHub ↗Beide Rohdateien im Verzeichnis
Konfiguration
- Config-Name
- pgvector-S0-tune-hnsw-notune
- DB-Version
- —
- Image
- —
- Index-Typ
- hnsw
- Index-Params
- {"M":8,"ef_construction":32,"ef_search":10}
- Dataset
- S0 · 550.000 Vektoren · dim 1024 · Variante A · 2.00 GB
- Queries
- 1.000 (Concurrency 1)
Lauf
- Gestartet
- 16.06.2026, 10:49:44
- Beendet
- 16.06.2026, 10:49:51
- Dauer
- 7207s
- Index-Bauzeit
- 300.28s
- Index-Größe
- 4296.7 MB
- CPU ⌀ / Peak
- 0.11 / 0.12 cores
- RAM ⌀ / Peak
- 5864 / 5864 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: 2026-06-16T08:48:56Z ingest_config: pgvector-S0-tune-hnsw-notune insert_time_s: 236.83 n_vectors_actual: 550000 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: 2026-06-16T08-48-56Z_pgvector-S0-tune-hnsw-notune repeat_index: 4 repeat_total: 6