← zurück zur Übersicht

2026-06-16T12-58-58Z_weaviate-S0-tune-hnsw-high-r2

weaviateStufe S0 · 2.00 GBtopkStatus: ok

Metriken

Throughput
291.5 QPS
Latenz ⌀
3.40 ms
Latenz p50
3.41 ms
Latenz p95
3.85 ms
Latenz p99
4.04 ms
Recall@1
94.40%
Recall@10
93.57%
Recall@100
84.79%
Precision@10
93.57%
NDCG@10
95.76%

Rohdaten

Konfiguration

Config-Name
weaviate-S0-tune-hnsw-high
DB-Version
Image
Index-Typ
hnsw
Index-Params
{"M":32,"ef_construction":256,"ef":128}
Dataset
S0 · 550.000 Vektoren · dim 1024 · Variante A · 2.00 GB
Queries
1.000 (Concurrency 1)

Lauf

Gestartet
16.06.2026, 14:58:58
Beendet
16.06.2026, 14:59:33
Dauer
7235s
Index-Bauzeit
1367.39s
Index-Größe
3493.2 MB
CPU ⌀ / Peak
0.37 / 0.37 cores
RAM ⌀ / Peak
3665 / 3665 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: 2026-06-16T12:58:16Z
ingest_config: weaviate-S0-tune-hnsw-high
insert_time_s: 201.39
n_vectors_actual: 550000
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
server_latency_ms: {"source":"weaviate_prometheus","metric":"queries_durations_ms","class_name":"Bench","query_type":"get_graphql","count":1000,"count_all_types":1000,"mean_ms":2.374,"windowed":true,"p50_ms":5,"p95_ms":9.5,"p99_ms":9.9}
mode: measure-only
repeat_group: 2026-06-16T12-58-16Z_weaviate-S0-tune-hnsw-high
repeat_index: 2
repeat_total: 6