Cockroach Labs Estate economics What idle nodes, provisioned bytes and peak-sized bills cost, worked out from your estate.
  1. Nodes 150 baseline
  2. Avg CPU utilization 15.0% idle hardware
  3. Storage provisioned 3.0 TB 500 GB of data
  4. Est. monthly saving 0%

Step 7 of 8 - Pricing

You pay for the area, not the rectangle

Provisioned capacity is a flat ceiling sized to the busiest fifteen minutes of the day, plus headroom for the peak you didn't forecast. The gap under that ceiling is hardware you rented and didn't use.

Run a day, 40% headroom Steady Business hours Batch spike

Provisioned capacity left unused

not started

Pick a day above. The ceiling is already drawn: it's sized to a peak of 762 vCPU plus 40%, and you pay for all of it whether the workload turns up or not. That's under the 1,200 vCPU the estate runs on today, which was bought a cluster at a time and works at 15.0%, not sized to this curve.

0534106700:0006:0012:0018:0024:00vCPUProvisioned1067 vCPUConsumed180 vCPU avgProvisioned capacity versus consumption over 24 hoursOver 24 hours, a ceiling of 1067 vCPU, set above a peak of 762 vCPU, costs 25619 vCPU-hours, while the workload actually consumes 4320 vCPU-hours: 83% of the provisioned capacity goes unused.
Provisioned
0 vCPU-hours
Consumed
0 vCPU-hours
Paid for, not used
0 vCPU-hours
Read this chart as a table
Mean demand per hour against provisioned capacity, in vCPU
HourDemandProvisionedUnused
00:00 92 1,067 976
01:00 304 1,067 764
02:00 463 1,067 605
03:00 96 1,067 971
04:00 91 1,067 976
05:00 93 1,067 974
06:00 93 1,067 975
07:00 111 1,067 956
08:00 165 1,067 903
09:00 207 1,067 861
10:00 247 1,067 820
11:00 273 1,067 795
12:00 287 1,067 780
13:00 289 1,067 778
14:00 278 1,067 789
15:00 252 1,067 815
16:00 218 1,067 850
17:00 174 1,067 893
18:00 126 1,067 941
19:00 91 1,067 976
20:00 93 1,067 975
21:00 91 1,067 976
22:00 93 1,067 975
23:00 93 1,067 974
How this is worked out
  • Demand is this estate's 180 vCPU mean, shaped by the preset you picked, which also drives step 1.
  • Capacity is sized at the day's peak of 762 vCPU plus the 40% headroom you picked, giving a ceiling of 1,067 vCPU. The headroom is an assumption rather than a published figure, so it's yours to argue with.
  • That peak is the 50 clusters' own peaks added up, because a provisioned estate buys each of them separately. Step 1's aggregate peak of 262 vCPU is the later, smaller question: what one pool needs once the workloads share it.
  • A ceiling that high averages 16.9% CPU across the day, which is the whole day's 83.1% of unused capacity counted the other way round. The pooled cluster on step 1 runs at 35.2% against a 37.5% setpoint. Neither number sets the other: this one is how far above the peak you buy, that one is what a controller is told to hold.
Where the storage number comes from

3 Raft copies at 50% utilization (3/0.5 = 6), on top of the block store's own internal replication.

500 GB of logical data becomes 3.0 TB provisioned , a factor of 6× before the cost model sees it.