Optimizing virtual machine storage performance in a stretched cluster

Patent metadata

Field	Value
Publication number	US-11093138-B2
Application number	US-201916684369-A
Country	US
Kind code	B2
Filing date	Nov 14, 2019
Priority date	Nov 14, 2019
Publication date	Aug 17, 2021
Grant date	Aug 17, 2021

Abstract

Techniques for optimizing virtual machine (VM) storage performance in a hyper-converged infrastructure (HCI) deployment comprising a stretched cluster of host systems are provided. In one set of embodiments, a computer system can identify one or more stretched VMs in the stretched cluster, where storage objects associated with the one or more stretched VMs are replicated across the sites of the cluster. The computer system can further determine, for each stretched VM, whether a greater number of the VM's storage objects are accessible to the VM via site-local replica copies residing at a first site where the VM is currently running, or via site-remote replica copies residing at a second site where the VM is not currently running. If a greater number of the VM's storage objects are accessible to the VM via the site-remote replica copies, the VM can be migrated from the first site to the second site.

First claim

What is claimed is:

1. A method for optimizing virtual machine (VM) storage performance in a hyper-converged infrastructure (HCI) deployment comprising a stretched cluster of host systems, the stretched cluster including at least two sites, the method comprising:
identifying, by a computer system, one or more stretched VMs in the stretched cluster, wherein storage objects associated with the one or more stretched VMs are replicated across the at least two sites; and
for each of the one or more stretched VMs:
determining, by the computer system, whether a greater number of storage objects of the stretched VM are accessible to the stretched VM via site-local replica copies residing at a first site in the at least two sites where the stretched VM is currently running, or via site-remote replica copies residing at a second site in the at least two sites where the stretched VM is not currently running, wherein determining whether a storage object of the stretched VM is accessible to the stretched VM via a site-local replica copy or via a site-remote replica copy is based on:
a count of site-local components of the site-local replica copy that are accessible to the stretched VM; and
a count of site-remote components of the site-remote replica copy that are accessible to the stretched VM; and

if a greater number of storage objects of the stretched VM are accessible to the stretched VM via the site-remote replica copies residing at the second site, causing, by the computer system, the stretched VM to be migrated from a host system at the first site to a host system at the second site.

2. The method of claim 1 further comprising:
if a greater number of storage objects of the stretched VM are accessible to the stretched VM via the site-local replica copies residing at the first site, causing the stretched VM to remain running at the first site.

3. The method of claim 1 wherein identifying the one or more stretched VMs comprises:
identifying VMs in the stretched cluster that are associated with a VM-level storage policy indicating that the VMs' storage objects should be replicated across the at least two sites.

4. The method of claim 1 wherein the determining comprises, for each storage object of the stretched VM:
for each of the site-local components:
if the site-local component is accessible to the stretched VM, adding a vote count associated with the site-local component to a total site-local vote count for the storage object.

5. The method of claim 4 wherein the storage object is determined to be accessible to the stretched VM via the site-local replica copy if the total site-local vote count is greater than half of a total number of votes assigned to components of the storage object.

6. The method of claim 1 wherein the determining comprises, for each storage object of the stretched VM:
for each of the site-remote components:
if the site-remote component is accessible to the stretched VM, adding a vote count associated with the site-remote component to a total site-remote vote count for the storage object.

7. The method of claim 6 wherein the storage object is determined to be accessible to the stretched VM via the site-remote replica copy if the total site-remote vote count is greater than half of a total number of votes assigned to components of the storage object.

8. A non-transitory computer readable storage medium having stored thereon program code executable by a computer system, the program code embodying a method for optimizing virtual machine (VM) storage performance in a hyper-converged infrastructure (HCI) deployment comprising a stretched cluster of host systems, the method comprising:
identifying one or more stretched VMs in the stretched cluster, wherein storage objects associated with the one or more stretched VMs are replicated across the at least two sites; and
for each of the one or more stretched VMs:
determining whether a greater number of storage objects of the stretched VM are accessible to the stretched VM via site-local replica copies residing at a first site in the at least two sites where the stretched VM is currently running, or via site-remote replica copies residing at a second site in the at least two sites where the stretched VM is not currently running, wherein determining whether a storage object of the stretched VM is accessible to the stretched VM via a site-local replica copy or via a site-remote replica copy is based on:
a count of site-local components of the site-local replica copy that are accessible to the stretched VM; and
a count of site-remote components of the site-remote replica copy that are accessible to the stretched VM; and

if a greater number of storage objects of the stretched VM are accessible to the stretched VM via the site-remote replica copies residing at the second site, causing the stretched VM to be migrated from a host system at the first site to a host system at the second site.

9. The non-transitory computer readable storage medium of claim 8 wherein the method further comprises:
if a greater number of storage objects of the stretched VM are accessible to the stretched VM via the site-local replica copies residing at the first site, causing the stretched VM to remain running at the first site.

10. The non-transitory computer readable storage medium of claim 8 wherein identifying the one or more stretched VMs comprises:
identifying VMs in the stretched cluster that are associated with a VM-level storage policy indicating that the VMs' storage objects should be replicated across the at least two sites.

11. The non-transitory computer readable storage medium of claim 8 wherein the determining comprises, for each storage object of the stretched VM:
for each of the site-local components:
if the site-local component is accessible to the stretched VM, adding a vote count associated with the site-local component to a total site-local vote count for the storage object.

12. The non-transitory computer readable storage medium of claim 11 wherein the storage object is determined to be accessible to the stretched VM via the site-local replica copy if the total site-local vote count is greater than half of a total number of votes assigned to components of the storage object.

13. The non-transitory computer readable storage medium of claim 8 wherein the determining comprises, for each storage object of the stretched VM:
for each of the site-remote components:
if the site-remote component is accessible to the stretched VM, adding a vote count associated with the site-remote component to a total site-remote vote count for the storage object.

14. The non-transitory computer readable storage medium of claim 13 wherein the storage object is determined to be accessible to the stretched VM via the site-remote replica copy if the total site-remote vote count is greater than half of a total number of votes assigned to components of the storage object.

15. A computer system comprising:
a processor; and
a non-transitory computer readable medium having stored thereon program code that, when executed, causes the processor to:
identify one or more stretched VMs in a stretched cluster, wherein storage objects associated with the one or more stretched VMs are replicated across at least two sites of the stretched cluster; and

for each of the one or more stretched VMs:
determine whether a greater number of storage objects of the stretched VM are accessible to the stretched VM via site-local replica copies residing at a first site in the at least two sites where the stretched VM is currently running, or via site-remote replica copies residi

Assignees

• Vmware Inc

Inventors

• Epping Duncan
• Hogan Cormac
• Denneman Frank

Classifications

• G06F3/067

  Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS] · CPC title

• G06F3/0647

  Migration mechanisms · CPC title

• G06F3/061 Primary

  Improving I/O performance · CPC title

• G06F9/45558 Primary

  Hypervisor-specific management and integration aspects · CPC title

• G06F2009/4557

  Distribution of virtual machine instances; Migration and load balancing · CPC title