2026-06-17T01-04-28Z_pgvector-S1-tune-ivfprobes-p040-r1
pgvectorStufe S1 · 5.00 GBtopkStatus: ok
Metriken
Throughput
8.5 QPS
Latenz ⌀
117.87 ms
Latenz p50
109.28 ms
Latenz p95
196.78 ms
Latenz p99
252.73 ms
Recall@1
84.00%
Recall@10
83.47%
Recall@100
78.01%
Precision@10
83.47%
NDCG@10
88.77%
Rohdaten
summary.json ↗Vollständige Run-Metrikenhttps://raw.githubusercontent.com/unrealshape/bachelor-db-benchmark/main/results/2026-06-17T01-04-28Z_pgvector-S1-tune-ivfprobes-p040-r1/summary.jsonconfig.json ↗Eingesetzte Konfigurationhttps://raw.githubusercontent.com/unrealshape/bachelor-db-benchmark/main/results/2026-06-17T01-04-28Z_pgvector-S1-tune-ivfprobes-p040-r1/config.jsonDatensatz · 5.00 GB ↗Generator + Bauanleitung im RepoRun-Ordner auf GitHub ↗Beide Rohdateien im Verzeichnis
Konfiguration
- Config-Name
- pgvector-S1-tune-ivfprobes-p040
- DB-Version
- —
- Image
- —
- Index-Typ
- ivfflat
- Index-Params
- {"lists":1200,"probes":40}
- Dataset
- S1 · 1.350.000 Vektoren · dim 1024 · Variante A · 5.00 GB
- Queries
- 1.000 (Concurrency 1)
Lauf
- Gestartet
- 17.06.2026, 03:04:28
- Beendet
- 17.06.2026, 03:08:29
- Dauer
- 7441s
- Index-Bauzeit
- 158.76s
- Index-Größe
- 10556.3 MB
- CPU ⌀ / Peak
- 0.58 / 0.64 cores
- RAM ⌀ / Peak
- 7614 / 7679 MB
- Disk read (Paging)
- 70152 MB
- Disk write
- 8 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: 2026-06-17T00:52:16Z ingest_config: pgvector-S1-ivfflat insert_time_s: 568.25 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_ids.npy mode: measure-only repeat_group: 2026-06-17T01-04-28Z_pgvector-S1-tune-ivfprobes-p040 repeat_index: 1 repeat_total: 6