2026-06-16T22-49-55Z_pgvector-S1-B-filtered-r5
pgvectorStufe S1 · 5.00 GBfilteredStatus: ok
Metriken
Throughput
22.8 QPS
Latenz ⌀
43.87 ms
Latenz p50
39.47 ms
Latenz p95
83.63 ms
Latenz p99
129.23 ms
Recall@1
65.40%
Recall@10
60.06%
Recall@100
50.32%
Precision@10
60.06%
NDCG@10
70.79%
Rohdaten
summary.json ↗Vollständige Run-Metrikenhttps://raw.githubusercontent.com/unrealshape/bachelor-db-benchmark/main/results/2026-06-16T22-49-55Z_pgvector-S1-B-filtered-r5/summary.jsonconfig.json ↗Eingesetzte Konfigurationhttps://raw.githubusercontent.com/unrealshape/bachelor-db-benchmark/main/results/2026-06-16T22-49-55Z_pgvector-S1-B-filtered-r5/config.jsonDatensatz · 5.00 GB ↗Generator + Bauanleitung im RepoRun-Ordner auf GitHub ↗Beide Rohdateien im Verzeichnis
Konfiguration
- Config-Name
- pgvector-S1-B-filtered
- DB-Version
- —
- Image
- —
- Index-Typ
- ivfflat
- Index-Params
- {"lists":1200,"probes":10}
- Dataset
- S1 · 1.350.000 Vektoren · dim 1024 · Variante B · 5.00 GB
- Queries
- 2.000 (Concurrency 1)
Lauf
- Gestartet
- 17.06.2026, 00:49:55
- Beendet
- 17.06.2026, 00:51:29
- Dauer
- 7294s
- Index-Bauzeit
- 153.23s
- Index-Größe
- 10556.3 MB
- CPU ⌀ / Peak
- 0.42 / 0.50 cores
- RAM ⌀ / Peak
- 7531 / 7662 MB
- Disk read (Paging)
- 16547 MB
- Disk write
- 6 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: 2026-06-16T22:34:30Z ingest_config: pgvector-S1-B-ivfflat insert_time_s: 464.93 n_vectors_actual: 1350000 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_filter_rating_gte_4_ids.npy mode: measure-only repeat_group: 2026-06-16T22-43-02Z_pgvector-S1-B-filtered repeat_index: 5 repeat_total: 6