2026-06-16T10-57-23Z_pgvector-S0-tune-ivfprobes-p010-r5
pgvectorStufe S0 · 2.00 GBtopkStatus: ok
Metriken
Throughput
97.2 QPS
Latenz ⌀
10.26 ms
Latenz p50
9.98 ms
Latenz p95
14.39 ms
Latenz p99
17.14 ms
Recall@1
71.70%
Recall@10
67.38%
Recall@100
60.22%
Precision@10
67.38%
NDCG@10
76.71%
Rohdaten
summary.json ↗Vollständige Run-Metrikenhttps://raw.githubusercontent.com/unrealshape/bachelor-db-benchmark/main/results/2026-06-16T10-57-23Z_pgvector-S0-tune-ivfprobes-p010-r5/summary.jsonconfig.json ↗Eingesetzte Konfigurationhttps://raw.githubusercontent.com/unrealshape/bachelor-db-benchmark/main/results/2026-06-16T10-57-23Z_pgvector-S0-tune-ivfprobes-p010-r5/config.jsonDatensatz · 2.00 GB ↗Generator + Bauanleitung im RepoRun-Ordner auf GitHub ↗Beide Rohdateien im Verzeichnis
Konfiguration
- Config-Name
- pgvector-S0-tune-ivfprobes-p010
- DB-Version
- —
- Image
- —
- Index-Typ
- ivfflat
- Index-Params
- {"lists":500,"probes":10}
- Dataset
- S0 · 550.000 Vektoren · dim 1024 · Variante A · 2.00 GB
- Queries
- 1.000 (Concurrency 1)
Lauf
- Gestartet
- 16.06.2026, 12:57:23
- Beendet
- 16.06.2026, 12:57:49
- Dauer
- 7226s
- Index-Bauzeit
- 40.8s
- Index-Größe
- 4300.8 MB
- CPU ⌀ / Peak
- 0.66 / 0.67 cores
- RAM ⌀ / Peak
- 7578 / 7582 MB
- Disk read (Paging)
- 7 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: 2026-06-16T10-55-05Z_pgvector-S0-tune-ivfprobes-p010 repeat_index: 5 repeat_total: 6