2026-06-16T15-37-53Z_pgvector-S0-B-throughput-c16-r2
pgvectorStufe S0 · 2.00 GBbatchStatus: ok
Metriken
Throughput
96.4 QPS
Latenz ⌀
164.70 ms
Latenz p50
165.78 ms
Latenz p95
180.58 ms
Latenz p99
190.00 ms
Recall@1
67.50%
Recall@10
65.74%
Recall@100
58.70%
Precision@10
65.74%
NDCG@10
75.42%
Rohdaten
summary.json ↗Vollständige Run-Metrikenhttps://raw.githubusercontent.com/unrealshape/bachelor-db-benchmark/main/results/2026-06-16T15-37-53Z_pgvector-S0-B-throughput-c16-r2/summary.jsonconfig.json ↗Eingesetzte Konfigurationhttps://raw.githubusercontent.com/unrealshape/bachelor-db-benchmark/main/results/2026-06-16T15-37-53Z_pgvector-S0-B-throughput-c16-r2/config.jsonDatensatz · 2.00 GB ↗Generator + Bauanleitung im RepoRun-Ordner auf GitHub ↗Beide Rohdateien im Verzeichnis
Konfiguration
- Config-Name
- pgvector-S0-B-throughput-c16
- DB-Version
- —
- Image
- —
- Index-Typ
- ivfflat
- Index-Params
- {"lists":500,"probes":10}
- Dataset
- S0 · 550.000 Vektoren · dim 1024 · Variante B · 2.00 GB
- Queries
- 2.000 (Concurrency 16)
Lauf
- Gestartet
- 16.06.2026, 17:37:53
- Beendet
- 16.06.2026, 17:38:19
- Dauer
- 7226s
- Index-Bauzeit
- 41.8s
- Index-Größe
- 4300.8 MB
- CPU ⌀ / Peak
- 0.62 / 0.97 cores
- RAM ⌀ / Peak
- 7865 / 7869 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: 2026-06-16T15:21:23Z ingest_config: pgvector-S0-B-ivfflat insert_time_s: 190.1 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: 2026-06-16T15-37-18Z_pgvector-S0-B-throughput-c16 repeat_index: 2 repeat_total: 6