# Dedicated CPU plans that still lose CPU time

Dedicated-CPU plans ranked by their worst minute of CPU steal. Dedicated should mean zero, which means you don't want to end up on this list.

| # | Plan | Median worst minute | Worst minute seen | Runs with a 5% minute | Runs | Dates |
| --- | --- | --- | --- | --- | --- | --- |
| 1 | [Linode](https://rackcensus.com/vps-providers/linode-benchmarks)[Dedicated 8GB](https://rackcensus.com/plans/gppofn-linode-dedicated-8gb-benchmarks) | 0.32% | [0.98%](https://rackcensus.com/benchmarks/bztbt7-linode-dedicated-8gb-se-sto-benchmark) | 0 of 3 | 3 runs, 3 locations | Oct 7 to Oct 12 |
| 2 | [RamNode](https://rackcensus.com/vps-providers/ramnode-benchmarks)[8GB VDS](https://rackcensus.com/plans/ym58nm-ramnode-8gb-vds-benchmarks) | 0.27% | [0.47%](https://rackcensus.com/benchmarks/3v630v-ramnode-8gb-vds-lax-benchmark) | 0 of 3 | 3 runs, 3 locations | Oct 11 to Oct 12 |
| 3 | [DigitalOcean](https://rackcensus.com/vps-providers/digitalocean-benchmarks)[CPU-Optimized 2 vCPU / 4 GB](https://rackcensus.com/plans/xhyrw9-digitalocean-cpu-optimized-2-vcpu-4-gb-benchmarks) | 0.18% | [5.0%](https://rackcensus.com/benchmarks/cgj40n-digitalocean-cpu-optimized-2-vcpu-4-gb-nyc1-benchmark) | 1 of 3 | 3 runs, 3 locations | Oct 5 to Oct 8 |
| 4 | [Linode](https://rackcensus.com/vps-providers/linode-benchmarks)[Dedicated 4GB](https://rackcensus.com/plans/8mq8an-linode-dedicated-4gb-benchmarks) | 0.08% | [0.12%](https://rackcensus.com/benchmarks/p7r7c5-linode-dedicated-4gb-nl-ams-benchmark) | 0 of 4 | 4 runs, 4 locations | Oct 6 to Oct 9 |
| 5 | [Linode](https://rackcensus.com/vps-providers/linode-benchmarks)[Premium 4GB](https://rackcensus.com/plans/x9uqnu-linode-premium-4gb-benchmarks) | 0.05% | [0.05%](https://rackcensus.com/benchmarks/kt91ck-linode-premium-4gb-se-sto-benchmark) | 0 of 3 | 3 runs, 3 locations | Oct 5 to Oct 12 |
| 6 | [OVHcloud](https://rackcensus.com/vps-providers/ovh-benchmarks)[C3-4](https://rackcensus.com/plans/l4t2tn-ovh-c3-4-benchmarks) | 0.03% | [0.04%](https://rackcensus.com/benchmarks/ele38y-ovh-c3-4-de1-benchmark) | 0 of 3 | 3 runs, 3 locations | Oct 5 to Oct 12 |
| 7 | [Vultr](https://rackcensus.com/vps-providers/vultr-benchmarks)[CPU Optimized AMD 1 vCPU / 2 GB](https://rackcensus.com/plans/a04uf6-vultr-cpu-optimized-amd-1-vcpu-2-gb-benchmarks) | 0.03% | [0.07%](https://rackcensus.com/benchmarks/zc03al-vultr-cpu-optimized-amd-1-vcpu-2-gb-ams-benchmark) | 0 of 3 | 3 runs, 3 locations | Oct 11 to Oct 12 |

Left out because the host never reported any steal, which usually means it isn't exposed to the server rather than that none happened: [Hetzner CCX13](https://rackcensus.com/plans/oe8cpl-hetzner-ccx13-benchmarks).

## How plans get on this list

- A plan needs at least 3 completed runs from the last 90 days, spread across at least 2 locations or 2 different days, so one bad host or one bad afternoon can't rank it.
- Plans are only compared with plans of the same CPU class. Shared CPU plans are never ranked against dedicated ones.
- Every completed run counts. We don't drop bad runs or rerun a plan until it looks better.
- Steal is measured once a second for the whole run, counting only the seconds where the server was asking for at least half its CPU. Steal on an idle server doesn't tell you much.
- A run only counts if it has at least 5 minutes of that kind of load.
- The worst minute is the worst 60-second average in a run. Single-second spikes are mostly noise, so they aren't used.
- A plan is marked stolen when at least 2 of its runs had a minute with 5% steal or more.