| 摘要 |
Techniques are described herein which minimize the impact of virtual machine snapshots on the performance virtual machines and hypervisors. In the context of a volume snapshot which may involve (i) taking virtual machine snapshots of all virtual machines associated with the volume, (ii) taking the volume snapshot, and (iii) removing all the virtual machine snapshots, the virtual machine snapshots may be created in a first order and removed in a second order. Specifically, snapshots for busy virtual machines (i.e., virtual machines with higher disk write activity) may be created last and removed first. Consequently, snapshots of busy virtual machines are retained for the shorter periods of time, thereby minimizing the effect of virtual machine snapshots on those virtual machines (and their associated hypervisors) that would be most negatively impacted by virtual machine snapshots. |
| 主权项 |
1. A method for creating and removing snapshots of a plurality of virtual machines instantiated on a host, all of the virtual machines storing data on a volume of a storage system communicatively coupled to the host, the method comprising:
receiving by a hypervisor manager a first request to create snapshots of all of the virtual machines associated with the volume so as to maintain a state of each of the virtual machines, wherein the first request includes a first order of the virtual machines, and the first order is based on a first group of one or more metrics associated with the virtual machines; instructing by the hypervisor manager one or more hypervisors instantiated on the host to create, via a plurality of snapshot creation operations, the snapshots of all of the virtual machines associated with the volume, wherein the virtual machine snapshot creation operations are initiated in the first order; subsequent to the storage system taking a snapshot of the volume, receiving by the hypervisor manager a second request to remove the snapshots of all of the virtual machines associated with the volume, wherein the second request includes a second order of the virtual machines, the second order is based on a second group of one or more metrics associated with the virtual machines, and at least one metric from the second group does not belong to the first group; and instructing by the hypervisor manager one or more of the hypervisors to remove, via a plurality of snapshot removal operations, the snapshots of all of the virtual machines associated with the volume, wherein the virtual machine snapshot removal operations are initiated in the second order, and wherein the removal of all the virtual machine snapshots associated with the volume occurs without removal of the volume snapshot. |
