p3.2xlarge as an EKS node
8 vCPU61 GiBx86_64Intel Xeon E5-2686 v4 (Broadwell)1 GPUAWS us-east-1P3 High Performance GPU Double Extra Large
Where the p3.2xlarge goes
Default EKS setup: EKS, VPC CNI default (ENI limit).
CPU7.71 of 8 vCPU left for your pods
Memory59.74 GiB of 61 GiB left for your pods
your podsDaemonSets (200m, 300 MiB assumed)kubelet reservedeviction
58max pods per node
$2,233.80on demand / month · $3.06/h
$312.73spot / month (varies)
p3.2xlarge EKS max pods and allocatable memory — quick answers
- How many pods can a p3.2xlarge run as a node with EKS, VPC CNI default (ENI limit)? Up to 58; kubelet keeps 993 MiB of memory and 90m CPU, leaving 60.03 GiB and 7.91 vCPU for pods.
- How many pods can a p3.2xlarge run as a node with EKS, prefix delegation? Up to 110; kubelet keeps 1565 MiB of memory and 90m CPU, leaving 59.47 GiB and 7.91 vCPU for pods.
- How many 500m / 1 GiB pods fit? 15 per node after DaemonSets; 1 nodes for 10 replicas, about $2,233.80/month on demand.
What kubelet reserves on p3.2xlarge
| Setup | Max pods | kube-reserved CPU | Memory reserved + eviction | Allocatable CPU | Allocatable memory | Memory usable |
|---|---|---|---|---|---|---|
| EKS, VPC CNI default (ENI limit) secondary IPs per ENI | 58 | 90m | 893 Mi + 100 Mi | 7.91 | 60.03 GiB | 98.4% |
| EKS, prefix delegation ENABLE_PREFIX_DELEGATION=true | 110 | 90m | 1465 Mi + 100 Mi | 7.91 | 59.47 GiB | 97.5% |
How these numbers are computed: reservation formulas. How many subnet IPs a p3.2xlarge takes with the VPC CNI: EKS max pods and IP calculator. Check a live node with kubectl describe node → Allocatable.
How many pods fit on one p3.2xlarge
Assumes DaemonSets (CNI, kube-proxy, log and metrics agents) request 200m CPU, 300 Mi and 3 pods per node. Try your own numbers in the node calculator.
| Pod requests (CPU / memory) | EKS, VPC CNI default (ENI limit) | EKS, prefix delegation | $ per pod / month |
|---|---|---|---|
| 100m / 128 Mi | 55 | 77 | $40.61 |
| 250m / 256 Mi | 30 | 30 | $74.46 |
| 250m / 512 Mi | 30 | 30 | $74.46 |
| 500m / 512 Mi | 15 | 15 | $148.92 |
| 500m / 1024 Mi | 15 | 15 | $148.92 |
| 1000m / 1024 Mi | 7 | 7 | $319.11 |
| 1000m / 2048 Mi | 7 | 7 | $319.11 |
| 2000m / 4096 Mi | 3 | 3 | $744.60 |
| 4000m / 8192 Mi | 1 | 1 | $2,233.80 |
Similar EKS node types
| Type | vCPU | GiB | Alloc CPU | Alloc memory | Max pods | $/month | $ per alloc GiB |
|---|---|---|---|---|---|---|---|
| g6e.2xlarge | 8 | 64 | 7.91 | 63.03 GiB | 58 | $1,636.72 | $25.97 |
| g7e.2xlarge | 8 | 64 | 7.91 | 60.92 GiB | 254 | $2,455.08 | $40.30 |
| g6f.2xlarge | 8 | 32 | 7.91 | 31.03 GiB | 58 | $346.75 | $11.17 |
| g4ad.2xlarge | 8 | 32 | 7.91 | 31.57 GiB | 8 | $395.05 | $12.51 |
| g4dn.2xlarge | 8 | 32 | 7.91 | 31.34 GiB | 29 | $548.96 | $17.52 |
| g6.2xlarge | 8 | 32 | 7.91 | 31.03 GiB | 58 | $713.65 | $23.00 |
| g5.2xlarge | 8 | 32 | 7.91 | 31.03 GiB | 58 | $884.76 | $28.51 |
| g7.2xlarge | 8 | 32 | 7.91 | 28.92 GiB | 254 | $1,839.60 | $63.60 |
Closest match on other clouds
| Type | vCPU | GiB | Alloc CPU | Alloc memory | Max pods | $/month | $ per alloc GiB |
|---|---|---|---|---|---|---|---|
| g2-standard-8 | 8 | 32 | 7.91 | 28.34 GiB | 110 | $214.32 | $7.56 |
| g2-standard-12 | 12 | 48 | 11.90 | 43.38 GiB | 110 | $321.47 | $7.41 |
| a2-highgpu-1g | 12 | 85 | 11.90 | 78.16 GiB | 110 | $539.82 | $6.91 |
| g2-standard-16 | 16 | 64 | 15.89 | 58.42 GiB | 110 | $428.63 | $7.34 |
| a2-ultragpu-1g | 12 | 170 | 11.90 | 159.74 GiB | 110 | $832.72 | $5.21 |
| g2-standard-24 | 24 | 96 | 23.87 | 88.50 GiB | 110 | $642.95 | $7.26 |