← zurück zur Übersicht

2026-06-14T19-13-35Z_pgvector-S1-B-throughput-c16-r3

pgvectorStufe S1 · 5.00 GBbatchStatus: ok

Metriken

Throughput
24.0 QPS
Latenz ⌀
661.94 ms
Latenz p50
662.76 ms
Latenz p95
804.81 ms
Latenz p99
850.44 ms
Recall@1
66.10%
Recall@10
62.99%
Recall@100
56.23%
Precision@10
62.99%
NDCG@10
73.00%

Rohdaten

Konfiguration

Config-Name
pgvector-S1-B-throughput-c16
DB-Version
Image
Index-Typ
ivfflat
Index-Params
{"lists":1200,"probes":10}
Dataset
S1 · 1.350.000 Vektoren · dim 1024 · Variante B · 5.00 GB
Queries
2.000 (Concurrency 16)

Lauf

Gestartet
14.06.2026, 21:13:35
Beendet
14.06.2026, 21:15:05
Dauer
7290s
Index-Bauzeit
156.23s
Index-Größe
10556.3 MB
CPU ⌀ / Peak
0.42 / 0.47 cores
RAM ⌀ / Peak
7442 / 7447 MB
Disk read (Paging)
17258 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: 2026-06-14T18:44:31Z
ingest_config: pgvector-S1-B-ivfflat
insert_time_s: 466.49
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: 2026-06-14T19-10-31Z_pgvector-S1-B-throughput-c16
repeat_index: 3
repeat_total: 3