2026-06-12T19-56-47Z_weaviate-S-latency
weaviateStufe S · 10.00 GBtopkStatus: ok
Metriken
Throughput
76.9 QPS
Latenz ⌀
12.97 ms
Latenz p50
13.27 ms
Latenz p95
15.94 ms
Latenz p99
18.00 ms
Recall@1
81.90%
Recall@10
80.79%
Recall@100
67.98%
Precision@10
80.79%
NDCG@10
86.55%
Rohdaten
summary.json ↗Vollständige Run-Metrikenhttps://raw.githubusercontent.com/unrealshape/bachelor-db-benchmark/main/results/2026-06-12T19-56-47Z_weaviate-S-latency/summary.jsonconfig.json ↗Eingesetzte Konfigurationhttps://raw.githubusercontent.com/unrealshape/bachelor-db-benchmark/main/results/2026-06-12T19-56-47Z_weaviate-S-latency/config.jsonDatensatz · 10.00 GB ↗Generator + Bauanleitung im RepoRun-Ordner auf GitHub ↗Beide Rohdateien im Verzeichnis
Konfiguration
- Config-Name
- weaviate-S-latency
- DB-Version
- —
- Image
- —
- Index-Typ
- hnsw
- Index-Params
- {"ef":64,"ef_construction":128,"M":16,"vector_cache_max_objects":3000000,"query_vector_cache_max_objects":1000000}
- Dataset
- S · 2.650.000 Vektoren · dim 1024 · Variante A · 10.00 GB
- Queries
- 10.000 (Concurrency 1)
Lauf
- Gestartet
- 12.06.2026, 21:56:47
- Beendet
- 12.06.2026, 22:01:27
- Dauer
- 7480s
- Index-Bauzeit
- 3179.43s
- Index-Größe
- 16177.8 MB
- CPU ⌀ / Peak
- 0.58 / 1.03 cores
- RAM ⌀ / Peak
- 4648 / 6995 MB
- Disk read (Paging)
- 53290 MB
- Disk write
- 974 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: 2026-06-12T19:56:41Z ingest_config: weaviate-S-latency insert_time_s: 1401.53 n_vectors_actual: 2650000 has_metadata: true mem_limit_gb: 8 pre_run_reset: rollout-restart timeout_s: 180 gomemlimit_mib: 7000 query_mem_gb: 8 n_queries_executed: 1000 n_warmup: 1000 gt_file: ground_truth_ids.npy mode: measure-only