2026-06-16T21-38-01Z_pgvector-S-B-throughput-c16-r4
pgvectorStufe S · 10.00 GBbatchStatus: ok
Metriken
Throughput
6.8 QPS
Latenz ⌀
2336.64 ms
Latenz p50
2323.80 ms
Latenz p95
2980.38 ms
Latenz p99
3363.25 ms
Recall@1
68.70%
Recall@10
66.41%
Recall@100
59.16%
Precision@10
66.41%
NDCG@10
75.80%
Rohdaten
summary.json ↗Vollständige Run-Metrikenhttps://raw.githubusercontent.com/unrealshape/bachelor-db-benchmark/main/results/2026-06-16T21-38-01Z_pgvector-S-B-throughput-c16-r4/summary.jsonconfig.json ↗Eingesetzte Konfigurationhttps://raw.githubusercontent.com/unrealshape/bachelor-db-benchmark/main/results/2026-06-16T21-38-01Z_pgvector-S-B-throughput-c16-r4/config.jsonDatensatz · 10.00 GB ↗Generator + Bauanleitung im RepoRun-Ordner auf GitHub ↗Beide Rohdateien im Verzeichnis
Konfiguration
- Config-Name
- pgvector-S-B-throughput-c16
- DB-Version
- —
- Image
- —
- Index-Typ
- ivfflat
- Index-Params
- {"lists":1000,"probes":10}
- Dataset
- S · 2.650.000 Vektoren · dim 1024 · Variante B · 10.00 GB
- Queries
- 2.000 (Concurrency 16)
Lauf
- Gestartet
- 16.06.2026, 23:38:01
- Beendet
- 16.06.2026, 23:42:51
- Dauer
- 7490s
- Index-Bauzeit
- 256.48s
- Index-Größe
- 20710.9 MB
- CPU ⌀ / Peak
- 0.47 / 0.55 cores
- RAM ⌀ / Peak
- 7454 / 7526 MB
- Disk read (Paging)
- 126844 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: 2026-06-16T18:58:00Z ingest_config: pgvector-S-B-ivfflat insert_time_s: 915.51 n_vectors_actual: 2650000 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: 2026-06-16T21-23-47Z_pgvector-S-B-throughput-c16 repeat_index: 4 repeat_total: 6