Cockroach Labs Estate economics What idle nodes, provisioned bytes and peak-sized bills cost, worked out from your estate.

Estate summary

  1. Nodes 4 down from 7
  2. Avg CPU utilization 26.2% up from 15.0%
  3. Storage provisioned 60 GB 10 GB of data
  4. Est. monthly saving 43% $1,000/m becomes $570/m

Step 1 of 8 - Virtualization

You're running an estate, not a cluster

Every cluster below was sized for its own peak, so every one of them idles.

Deployment model
1 private host cluster, 1 virtual clusterPrivate Host cluster4 nodes on average, 7 at peakvc-01own connection stringShared, auto-scaled node pool4 of 7 nodes at peakEstate after consolidationOne private host cluster carrying 1 virtual cluster on 4 nodes on average and 7 at peak, averaging 26.2% CPU utilization.
26%Average CPUAverage CPU CPU utilization26.2% of provisioned CPU is in use.

4 nodes running 8 vCPU of actual work.

Pooled and sized once for the peak, 7 nodes would average 15.0%. Auto-scaling brings it to 4 nodes at 26.2%, moving between 9.5% and 42.4% across the day against a 38% setpoint.

The arithmetic, in full
StepWorkingResult
Provisioned today1 cluster of 7 nodes x 8 vCPU56 vCPU
Mean demand56 vCPU x 15.0% estate average utilization8 vCPU
Aggregate peak8.4 vCPU x (1 + (2.23 - 1) / sqrt(1)), a pooled peak-to-mean of 2.22819 vCPU
Consolidated, sized once for the peakmax(3, ceil(18.7 vCPU / (8 vCPU x 37.5% target))) = max(3, ceil(6.24)); the mean sits well under that peak7 nodes, averaging 15.0%
Auto-scaled through the daythe pool follows the pooled curve in whole nodes, 30 minutes behind it, holding its size for 2 hours before shrinking4 nodes on average, at 26.2% CPU
Utilization across the day9.5% to 42.4% against a 37.5% setpoint: the pool runs hot while it's a bucket behind a rise, and cool while the cooldown is still holding capacity after a peak9.5%-42.4%

Assumptions

  • 8 vCPU per node. Standalone clusters are drawn around 7 nodes, snapped to an odd number for quorum and held between 3 and 15; this estate is one cluster of 7.
  • Each standalone cluster's CPU is a draw from a normal distribution centred on 15.0% and held between 0% and 100%; with one cluster there's nothing to average against, so it sits on 15.0% exactly. The published band is 10-15% today against a 30-45% auto-scaled target, and this Private Host Cluster is set to 37.5%.
  • The Private Host Cluster floors at 3 nodes and must reach 7 at peak.
  • The auto-scaler sizes for what it saw 30 minutes ago and waits 2 hours before shrinking, so the pool averages 26.2% rather than sitting on its 37.5% setpoint.
  • Workloads are independent; consolidation moves where work runs, not how much there is.
What a virtual cluster gives an app team

Its own connection string, databases, schemas, users, roles and backups, and no visibility into the Private Host Cluster or any other virtual cluster.