👻 Ghostfleet run report

🖥️ 1000 nodes · 🎮 8000 GPUs · 📦 1000 pods · snapshot 2026-07-19T07:04:47Z

📋 Cluster shape

🖥️ Nodes
1000
🎮 GPUs
8000
📦 Pods
1000
🗄️ etcd DB size
14.5MB
⚡ Scheduler throughput
—pods/s (5m avg)
⏱️ Scheduling e2e p99
—s

🌐 API request p99 latency by verb

GET
4.95 ms
POST
5.00 ms
PUT
24.20 ms
LIST
114.99 ms
APPLY
no data
PATCH
4.98 ms
DELETE
no data
Table view
Verbp99
GET4.95 ms
POST5.00 ms
PUT24.20 ms
LIST114.99 ms
APPLYno data
PATCH4.98 ms
DELETEno data

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

🗄️ etcd request p99 latency by operation

update
4.98 ms
create
4.98 ms
get
4.96 ms
list
4.95 ms
listWithCount
no data
Table view
Operationp99
update4.98 ms
create4.98 ms
get4.96 ms
list4.95 ms
listWithCountno data

⚖️ Priority & Fairness

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

👀 Watchers & inflight requests

No watcher data in this window.

Inflight requests
KindCount
mutating0
readOnly0

Generated from results/20260719-090446/ — raw PromQL snapshots in that folder are the source of truth.