g7e.2xlarge as an EKS node

8 vCPU64 GiBx86_64Intel Xeon Scalable (Emerald Rapids)1 GPUAWS us-east-1G7E Double Extra Large

Where the g7e.2xlarge goes

Default EKS setup: EKS, VPC CNI default (ENI limit).

CPU7.71 of 8 vCPU left for your pods
Memory60.63 GiB of 64 GiB left for your pods
your podsDaemonSets (200m, 300 MiB assumed)kubelet reservedeviction
254max pods per node
$2,455.08on demand / month · $3.36/h
$1,620.02spot / month (varies)

Will my pods fit on one g7e.2xlarge?

g7e.2xlarge EKS max pods and allocatable memory — quick answers

What kubelet reserves on g7e.2xlarge

SetupMax podskube-reserved CPUMemory reserved + evictionAllocatable CPUAllocatable memoryMemory usable
EKS, VPC CNI default (ENI limit)
secondary IPs per ENI
25490m3049 Mi + 100 Mi7.9160.92 GiB95.2%
EKS, prefix delegation
ENABLE_PREFIX_DELEGATION=true
11090m1465 Mi + 100 Mi7.9162.47 GiB97.6%

How these numbers are computed: reservation formulas. How many subnet IPs a g7e.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 g7e.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 Mi7777$31.88
250m / 256 Mi3030$81.84
250m / 512 Mi3030$81.84
500m / 512 Mi1515$163.67
500m / 1024 Mi1515$163.67
1000m / 1024 Mi77$350.73
1000m / 2048 Mi77$350.73
2000m / 4096 Mi33$818.36
4000m / 8192 Mi11$2,455.08

Similar EKS node types

TypevCPUGiBAlloc CPUAlloc memoryMax pods$/month$ per alloc GiB
g6e.2xlarge8647.9163.03 GiB58$1,636.72$25.97
p3.2xlarge8617.9160.03 GiB58$2,233.80$37.21
g6f.2xlarge8327.9131.03 GiB58$346.75$11.17
g4ad.2xlarge8327.9131.57 GiB8$395.05$12.51
g4dn.2xlarge8327.9131.34 GiB29$548.96$17.52
g4ad.4xlarge166415.8963.34 GiB29$632.91$9.99
g6f.4xlarge166415.8961.14 GiB234$693.50$11.34
g6.2xlarge8327.9131.03 GiB58$713.65$23.00

Closest match on other clouds

TypevCPUGiBAlloc CPUAlloc memoryMax pods$/month$ per alloc GiB
a2-highgpu-1g128511.9078.16 GiB110$539.82$6.91
g2-standard-88327.9128.34 GiB110$214.32$7.56
g2-standard-12124811.9043.38 GiB110$321.47$7.41
g2-standard-16166415.8958.42 GiB110$428.63$7.34
a2-ultragpu-1g1217011.90159.74 GiB110$832.72$5.21
g2-standard-24249623.8788.50 GiB110$642.95$7.26