Offered load ≈ 87%
Pull-based scheduler
Old · random node polling
Pull-based draining
Nodes take the oldest fitting job until their oldest eligible job has waited longer than this. Then they hold space for it. 0 means immediately; ∞ disables draining. Applies to reserved node pools too.
Reserved nodes
Labels mark hosts restricted to one job size. These jobs can also use shared nodes. Running jobs finish normally.
CPU utilization
0%
Queued jobs00 vCPU
Loading the fleet…
Centralized scheduler
New · selective draining
CPU utilization
0%
Queued jobs00 vCPU
Loading the fleet…
Jobs
Holds a
reservation
Draining host
Time
Queue waitPull-basedCentralized
Rolling · 2 min history
Shared scale · seconds
2 vCPU
4 vCPU
8 vCPU
16 vCPU
32 vCPU
Percentile tables · last 1 min
2 vCPU
| Seconds | Pull | Centralized |
|---|---|---|
4 vCPU
| Seconds | Pull | Centralized |
|---|---|---|
8 vCPU
| Seconds | Pull | Centralized |
|---|---|---|
16 vCPU
| Seconds | Pull | Centralized |
|---|---|---|
32 vCPU
| Seconds | Pull | Centralized |
|---|---|---|
Jobs started in the preceding 60 simulated seconds; queued jobs are counted separately. With fewer than 10,000 starts, empirical p99.99 equals the longest observed wait.