👻 Ghostfleet run report

🖥️ 1000 nodes · 🎮 8000 GPUs · 📦 8000 pods · snapshot 2026-07-19T07:09:25Z

📋 Cluster shape

🖥️ Nodes
1000
🎮 GPUs
8000
📦 Pods
8000
🗄️ etcd DB size
116.6MB
⚡ Scheduler throughput
28.2pods/s (5m avg)
⏱️ Scheduling e2e p99
0.154s

🌐 API request p99 latency by verb

GET
4.97 ms
POST
19.78 ms
PUT
20.35 ms
LIST
80.28 ms
APPLY
no data
PATCH
21.92 ms
DELETE
no data
Table view
Verbp99
GET4.97 ms
POST19.78 ms
PUT20.35 ms
LIST80.28 ms
APPLYno data
PATCH21.92 ms
DELETEno data

SLO: mutating < 1s · read-only namespaced < 5s · read-only cluster-scoped < 30s

🗄️ etcd request p99 latency by operation

list
4.95 ms
listWithCount
4.95 ms
update
11.55 ms
delete
no data
create
15.67 ms
get
4.97 ms
Table view
Operationp99
list4.95 ms
listWithCount4.95 ms
update11.55 ms
deleteno data
create15.67 ms
get4.97 ms

⚖️ Priority & Fairness

✓ No APF rejections or queue wait observed in this window.

👀 Watchers & inflight requests

No watcher data in this window.

Inflight requests
KindCount
mutating14
readOnly0

Generated from results/20260719-090923/ — raw PromQL snapshots in that folder are the source of truth.