NCM-MCI-6.5 Exam Questions & Answers

Correct Answer: A

One possible reason why the SQL03 VM was not powered back on after a host failure is that the cluster was configured with the default (best effort) VM high availability mode, which does not guarantee the availability of VMs in case of

insufficient resources on the remaining hosts. To resolve this issue, I suggest changing the VM high availability mode to guarantee (reserved segments), which reserves some memory on each host for failover of VMs from a failed host. This

way, the SQL03 VM will have a higher chance of being restarted on another host in case of a host failure. To change the VM high availability mode to guarantee (reserved segments), you can follow these steps:

Log in to Prism Central and select the cluster where the SQL VMs are running. Click on the gear icon on the top right corner and select Cluster Settings. Under Cluster Services, click on Virtual Machine High Availability. Select Guarantee

(Reserved Segments) from the drop-down menu and click Save. To configure the environment to ensure any single host failure affects a minimal number of SQL VMs, I suggest using anti-affinity rules, which prevent VMs that belong to the

same group from running on the same host. This way, if one host fails, only one SQL VM will be affected and the other SQL VMs will continue running on different hosts. To create an anti-affinity rule for the SQL VMs, you can follow these

steps:

Log in to Prism Central and click on Entities on the left menu. Select Virtual Machines from the drop-down menu and click on Create Group. Enter a name for the group, such as SQL Group, and click Next. Select the SQL VMs (SQL01,

SQL02, SQL03) from the list and click Next. Select Anti-Affinity from the drop-down menu and click Next.

Review the group details and click Finish.

I hope this helps. How else can I help?

https://portal.nutanix.com/page/documents/details?targetId=AHV-Admin-Guide-v6_5:ahv- affinity-policies-c.html

A screenshot of a computer

Description automatically generated with medium confidence

Correct Answer: A

To configure the VM to better leverage AHV Turbo, you can follow these steps:

Log in to Prism Element of cluster A using the credentials provided.

Go to VM > Table and select the VM named Turbo.

Click on Update and go to Hardware tab.

Increase the number of vCPUs to match the number of multiqueues that you want to enable. For example, if you want to enable 8 multiqueues, set the vCPUs to 8. This will improve the performance of multi-threaded workloads by allowing

them to use multiple processors.

Change the SCSI Controller type from SATA to VirtIO. This will enable the use of VirtIO drivers, which are required for AHV Turbo.

Click Save to apply the changes.

Power off the VM if it is running and mount the Nutanix VirtIO ISO image as a CD-ROM device. You can download the ISO image fromNutanix Portal. Power on the VM and install the latest Nutanix VirtIO drivers for Windows 10. You can

follow the instructions fromNutanix Support Portal. After installing the drivers, power off the VM and unmount the Nutanix VirtIO ISO image.

Power on the VM and log in to Windows 10.

Open a command prompt as administrator and run the following command to enable multiqueue for the VirtIO NIC:

ethtool -L eth0 combined 8

Replaceeth0with the name of your network interface and8with the number of multiqueues that you want to enable. You can useipconfig /allto find out your network interface name.

Restart the VM for the changes to take effect.

You have now configured the VM to better leverage AHV Turbo. You can run your stress test application again and observe the performance gains.

https://portal.nutanix.com/page/documents/kbs/details?targetId=kA00e000000LKPdCAO change vCPU to 2/4 ?

Change SATA Controller to SCSI:

acli vm.get Turbo

Output Example:

Turbo {

config {

agent_vm: False

allow_live_migrate: True

boot {

boot_device_order: "kCdrom"

boot_device_order: "kDisk"

boot_device_order: "kNetwork"

uefi_boot: False

}

cpu_passthrough: False

disable_branding: False

disk_list {

addr {

bus: "ide"

index: 0

}

cdrom: True

device_uuid: "994b7840-dc7b-463e-a9bb-1950d7138671" empty: True

}

disk_list {

addr {

bus: "sata"

index: 0

}

container_id: 4

container_uuid: "49b3e1a4-4201-4a3a-8abc-447c663a2a3e" device_uuid: "622550e4-fb91-49dd-8fc7-9e90e89a7b0e" naa_id: "naa.6506b8dcda1de6e9ce911de7d3a22111"

storage_vdisk_uuid: "7e98a626-4cb3-47df-a1e2-8627cf90eae6" vmdisk_size: 10737418240

vmdisk_uuid: "17e0413b-9326-4572-942f-68101f2bc716" }

flash_mode: False

hwclock_timezone: "UTC"

machine_type: "pc"

memory_mb: 2048

name: "Turbo"

nic_list {

connected: True

mac_addr: "50:6b:8d:b2:a5:e4"

network_name: "network"

network_type: "kNativeNetwork"

network_uuid: "86a0d7ca-acfd-48db-b15c-5d654ff39096" type: "kNormalNic"

uuid: "b9e3e127-966c-43f3-b33c-13608154c8bf"

vlan_mode: "kAccess"

}

num_cores_per_vcpu: 2

num_threads_per_core: 1

num_vcpus: 2

num_vnuma_nodes: 0

vga_console: True

vm_type: "kGuestVM"

}

is_rf1_vm: False

logical_timestamp: 2

state: "Off"

uuid: "9670901f-8c5b-4586-a699-41f0c9ab26c3"

}

acli vm.disk_create Turbo clone_from_vmdisk=17e0413b-9326-4572-942f-68101f2bc716 bus=scsi

remove the old disk

acli vm.disk_delete 17e0413b-9326-4572-942f-68101f2bc716 disk_addr=sata.0

Correct Answer: A

To configure a DR solution that meets the stated requirements, you can follow these steps:

Log in to the Web Console of the source cluster where the VMs are running. Click on Protection Domains on the left menu and click on Create Protection Domain. Enter a name for the protection domain, such as PD_Mkt01, and a description

if required.

Click Next.

Select Mkt01 from the list of VMs and click Next. Select Schedule Based from the drop-down menu and enter 2 hours as the interval. Click Next.

Select Remote Site from the drop-down menu and choose the remote site where you want to replicate the VM. Click Next.

Enter 5 as the number of snapshots to retain on both local and remote sites. Click Next. Review the protection domain details and click Finish. Repeat the same steps for Fin01 and Dev01, using PD_Fin01 and PD_Dev01 as the protection

domain names, and adjusting the interval and retention values according to the requirements.