2026-06-16T11-03-10Z_pgvector-S0-tune-ivfprobes-p040-r4
pgvectorStufe S0 · 2.00 GBtopkStatus: ok
Metriken
Throughput
24.6 QPS
Latenz ⌀
40.60 ms
Latenz p50
39.78 ms
Latenz p95
52.86 ms
Latenz p99
57.90 ms
Recall@1
88.80%
Recall@10
87.14%
Recall@100
83.66%
Precision@10
87.14%
NDCG@10
91.42%
Rohdaten
summary.json ↗Vollständige Run-Metrikenhttps://raw.githubusercontent.com/unrealshape/bachelor-db-benchmark/main/results/2026-06-16T11-03-10Z_pgvector-S0-tune-ivfprobes-p040-r4/summary.jsonconfig.json ↗Eingesetzte Konfigurationhttps://raw.githubusercontent.com/unrealshape/bachelor-db-benchmark/main/results/2026-06-16T11-03-10Z_pgvector-S0-tune-ivfprobes-p040-r4/config.jsonDatensatz · 2.00 GB ↗Generator + Bauanleitung im RepoRun-Ordner auf GitHub ↗Beide Rohdateien im Verzeichnis
Konfiguration
- Config-Name
- pgvector-S0-tune-ivfprobes-p040
- DB-Version
- —
- Image
- —
- Index-Typ
- ivfflat
- Index-Params
- {"lists":500,"probes":40}
- Dataset
- S0 · 550.000 Vektoren · dim 1024 · Variante A · 2.00 GB
- Queries
- 1.000 (Concurrency 1)
Lauf
- Gestartet
- 16.06.2026, 13:03:10
- Beendet
- 16.06.2026, 13:04:38
- Dauer
- 7288s
- Index-Bauzeit
- 40.8s
- Index-Größe
- 4300.8 MB
- CPU ⌀ / Peak
- 0.84 / 1.00 cores
- RAM ⌀ / Peak
- 7631 / 7636 MB
- Disk read (Paging)
- 1 MB
- Disk write
- 16 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: 2026-06-16T10:53:19Z ingest_config: pgvector-S0-tune-ivfprobes-p010 insert_time_s: 201.13 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: 2026-06-16T10-58-29Z_pgvector-S0-tune-ivfprobes-p040 repeat_index: 4 repeat_total: 6