Site Survey#

Sample Site Survey#

General Information

Country Name

US

State/Province

California

Locality

Santa Clara

Organization Name

Example Org

Administrator Email

admin@example.org

Organizational Unit

Demo

Cluster Name

ExampleCluster

Head Node Shared IP (HA Virtual IP)

10.184.94.251

Add Failover Network?

NFS Server IP

10.160.0.4

NAS Path to /cm/shared

/nfs/data/nas/cmshared

NAS Path to /home

/nfs/data/nas/home

Timezone

US/Los_Angeles

Network Topology

Type 2

IP Offset (Compute Nodes)

0.0.0.3

Partition Type

One Big Partition

OFED Stack Version

Mellanox OFED 23.10

OOB Management BMC Username

root

BCM Head Node Admin Username

root

BCM Head Node Admin Password

Network Information

DGX BasePOD RA Name

BCM Network Name

Network Address (Base IP Address)

Netmask (/Netmaskbits)

Gateway

Compute Fabric

computenet

100.64.0.0

255.255.0.0 (/16)

Management & Storage Fabric

managementnet (internalnet)

10.184.94.0

255.255.255.0 (/24)

10.184.94.1

OOB Management Fabric

oobmanagementnet (ipminet)

10.160.6.0

255.255.255.0 (/24)

10.160.6.1

IB Storage Fabric

storagenet

Name Servers

Search Domains

Time Servers

8.8.8.8

example.org

time.nist.gov

BCM Head Node Information

Managementnet

Name/Unique ID

Hostname

BMC IP (oobmanagementnet)

BMC Credentia

Node IP (managementnet)

MAC 1 (enp37s0np0)

MAC 2 (enp226s0np0)

Head1

bcm10-headnode1

10.160.6.254

10.184.94.254

E8:EB:D3:09:27:14

E8:EB:D3:09:26:34

Head2

bcm10-headnode2

10.160.6.253

10.184.94.253

E8:EB:D3:09:26:3C

E8:EB:D3:09:26:44

DGX Node Information (1)

Managementnet

Name/Unique ID

Hostname

BMC IP (oobmanagementnet)

BMC Credentials

Node IP (managementnet)

MAC 1 (enp37s0np0)

MAC 2 (enp226s0np0)

DGX-01

dgx-01

10.160.6.31

10.184.94.11

94:6D:AE:AA:13:C9

94:6D:AE:AA:14:89

DGX-02

dgx-02

10.160.6.32

10.184.94.12

A0:88:C2:A3:44:E5

A0:88:C2:A3:4B:05

DGX-03

dgx-03

10.160.6.33

10.184.94.13

94:6D:AE:1C:80:CD

94:6D:AE:1C:80:7D

DGX-04

dgx-04

10.160.6.34

10.184.94.14

A0:88:C2:04:70:A1

A0:88:C2:04:60:E1

DGX Node Information (2)

computenet

Name/Unique ID

Hostname

ibp220s0

ibp154s0

ibp206s0

ibp192s0

ibp79s0

ibp64s0

ibp94s0

ibp24s0

DGX-01

dgx-01

100.64.0.1

100.64.1.1

100.64.2.1

100.64.3.1

100.64.4.1

100.64.5.1

100.64.6.1

100.64.7.1

DGX-02

dgx-02

100.64.0.2

100.64.1.2

100.64.2.2

100.64.3.2

100.64.4.2

100.64.5.2

100.64.6.2

100.64.7.2

DGX-03

dgx-03

100.64.0.3

100.64.1.3

100.64.2.3

100.64.3.3

100.64.4.3

100.64.5.3

100.64.6.3

100.64.7.3

DGX-04

dgx-04

100.64.0.4

100.64.1.4

100.64.2.4

100.64.3.4

100.64.4.4

100.64.5.4

100.64.6.4

100.64.7.4

Kubernetes Node Information

ManagementNet

Name/Unique ID

Hostname

BMC IP (oobmanagementnet)

BMC Credentials

Node IP (managementnet)

MAC 1 (enp37s0np0)

MAC 2 (enp226s0np0)

Knode1

k8s-control-01

10.160.6.4

10.184.94.4

10:70:FD:73:7B:BE

10:70:FD:73:7B:D6

Knode2

k8s-control-02

10.160.6.5

10.184.94.5

10:70:FD:73:7D:76

10:70:FD:73:7C:C6

Knode3

k8s-control-03

10.160.6.6

10.184.94.6

E8:EB:D3:09:26:94

B8:CE:F6:63:ED:36

Blank Site Survey#

General Information

Country Name

State/Province

Locality

Organization Name

Administrator Email

Organizational Unit

Cluster Name

Head Node Shared IP (HA Virtual IP)

Add Failover Network?

NFS Server IP

NAS Path to /cm/shared

NAS Path to /home

Timezone

Network Topology

IP Offset (Compute Nodes)

Partition Type

OFED Stack Version

OOB Management BMC Username

OOB Management BMC Password

Network Information

DGX BasePOD RA Name

BCM Network Name

Network Address

Netmask (/Netmaskbits)

Gateway

Compute Fabric

computenet

Management & Storage Fabric

managementnet (internalnet)

OOB Management Fabric

oobmanagementnet (ipminet)

IB Storage Fabric

storagenet

Name Servers

Search Domains

Time Servers

BCM Head Node Information

Name/Unique ID

Hostname

BMC IP (oobmanagementnet)

BMC Credentials

Node IP (managementnet)

MAC 1 (enp37s0np0)

MAC 2 (enp226s0np0)

Head1

Head2

DGX Node Information (1)

Managementnet

Name/Unique ID

Hostname

BMC IP (oobmanagementnet)

BMC Credentials

Node IP (managementnet)

MAC 1 (enp37s0np0)

MAC 2 (enp226s0np0

DGX-01

DGX-02

DGX-03

DGX-04

DGX Node Information (2)

Name/Unique ID

Hostname

ibp220s0

ibp154s0

ibp206s0

ibp192s0

ibp79s0

ibp64s0

ibp94s0

ibp24s0

DGX-01

DGX-02

DGX-03

DGX-04

Kubernetes Node Information

Name/Unique ID

Hostname

BMC IP (oobmanagementnet)

BMC Credentials

Node IP (managementnet)

MAC 1 (enp37s0np0)

Knode1

Knode2

Knode3