System and method for providing preferential I/O treatment to devices that host a critical virtual machine
Quality of service is provided to prioritized VMs and applications, based on the varied quality of different shared computing resources. Each VM or application has an associated priority. A quality rating is dynamically assigned to each shared computing resource. Requests for shared computing resources made by specific VMs or applications are received. For each specific received request, the current priority of the requesting VM or application is identified. In response to each received request, a specific shared computing resource is assigned to the specific requesting VM or application. This assignment is made based on the current priority of the requesting VM or application and the current quality rating of the shared computing resource, thereby providing quality of service to the requesting VM or application corresponding to its current priority.
1. A computer-implemented method comprising:
periodically calculating and assigning a current quality rating to a shared computing resource, wherein the current quality rating relates to a quality of service the shared computing resource can provide at the time the current quality rating is assigned, and wherein the current quality rating is calculated based on values that represent a plurality of factors, respectively, at the time the current quality rating is assigned, wherein the plurality of factors includes at least one of memory, storage capacity, latency, and input/output (I/O) bandwidth, and wherein the shared computing resource is accessible by a plurality of virtual machines;
receiving first and second requests for the shared computing resource from a first virtual machine (VM) and a second VM, respectively, from among the plurality of virtual machines, wherein the first VM is associated with a first priority rating, and wherein the second VM is associated with a second priority rating;
assigning first and second quality ratings to the first and second requests, respectively, based on the first and second priority ratings, respectively;
comparing the first and second quality ratings to the current quality rating for the shared resource;
assigning the shared computing resource to the first VM based on the comparison, of the first and second quality ratings to the current quality rating for the shared resource, producing a closer correspondence between the first VM and the current quality rating.
2. The computer-implemented method of claim 1 , wherein
the first priority rating of the first VM is based, at least in part, on a service level agreement (SLA), and
the SLA specifies a minimum level of service associated with the first VM.
3. The computer-implemented method of claim 1 , wherein
the plurality of factors related to the shared computing resource comprises a static factor.
4. The computer-implemented method of claim 1 , wherein
the plurality of factors related to the shared computing resource comprises a dynamic factor.
5. The computer-implemented method of claim 4 , further comprising:
periodically evaluating the shared computing resource, wherein
each evaluation of the shared computing resource comprises determining whether the dynamic factor has changed since a previous evaluation of the dynamic factor;
in response to determining that the dynamic factor has changed since the previous evaluation, updating the current quality rating for the shared computing resource; and
subsequent to updating the current quality rating for the shared computing resource, assigning a different shared computing resource to the first VM, wherein
the different shared computing resource is assigned to the first VM in order to maintain a minimum level of service associated with the first VM.
6. The computer-implemented method of claim 5 , wherein
the specific level of service associated with the first VM is based on a service level agreement (SLA).
7. The computer-implemented method of claim 1 , wherein
the shared computing resource is one of a plurality of shared computing resources that are accessible by the first VM.
8. A non-transitory computer-readable storage medium comprising program instructions executable to perform a method comprising:
periodically calculating and assigning a current quality rating to a shared computing resource, wherein the current quality rating of the shared computing resource relates to a quality of service the shared computing resource can provide at the time the current quality rating is assigned, and wherein the current quality rating is calculated based on values that represent a plurality of factors, respectively, at the time the current quality rating is assigned, wherein the plurality of factors includes at least one of memory, storage capacity, latency, and input/output (I/O) bandwidth, and wherein the shared computing resource is accessible by a plurality of virtual machines;
receiving first and second requests for the shared computing resource
from a first virtual machine (VM) and a second VM, respectively, from among the plurality of virtual machines, wherein the first VM is associated with a first priority rating, and wherein the second VM is associated with a second priority rating;
assigning first and second quality ratings to the first and second requests, respectively, based on the first and second priority ratings, respectively;
comparing the first and second quality ratings to the current quality rating for the shared resource;
assigning the shared computing resource to the first VM based on the comparison, of the first and second quality ratings to the current quality rating for the shared resource, producing a closer correspondence between the first VM and the current quality rating.
9. The non-transitory computer-readable storage medium of claim 8 , wherein
the priority rating of the first VM is based, at least in part, on a service level agreement (SLA), and
the SLA specifies a minimum level of service associated with the first VM.
10. The non-transitory computer-readable storage medium of claim 8 , wherein
the plurality of factors related to the shared computing resource comprises at least one of:
a static factor, and
a dynamic factor.
11. The non-transitory computer-readable storage medium of claim 10 , wherein the method further comprises:
periodically evaluating the shared computing resource, wherein
each evaluation of the shared computing resource comprises determining whether the dynamic factor has changed since a previous evaluation of the dynamic factor;
in response to determining that the dynamic factor has changed since the previous evaluation, updating the current quality rating for the shared computing resource; and
subsequent to updating the current quality rating for the shared computing resource, assigning a different shared computing resource to the first VM, wherein
the different shared computing resource is assigned to the first VM in order to maintain a minimum level of service associated with the first VM.
12. The non-transitory computer-readable storage medium of claim 11 , wherein
the specific level of service associated with the requesting VM is based on a service level agreement (SLA).
13. A system comprising:
one or more processors; and
a memory coupled to the one or more processors, wherein the memory stores program instructions executable to perform a method comprising:
periodically calculating and assigning a current quality rating to a shared computing resource, wherein the current quality rating of the shared computing resource relates to the quality of service the shared computing resource can provide at the time the current quality rating is assigned, and wherein the current quality rating is calculated based on values that represent a plurality of factors, respectively, at the time the current quality rating is assigned, wherein the plurality of factors includes at least one of memory, storage capacity, latency, and input/output (I/O) bandwidth, and wherein the shared computing resource is accessible by a plurality of virtual machines;
receiving first and second requests for the shared computing resource
from a first virtual machine (VM) and a second VM, respectively, from among the plurality of virtual machines, wherein the first VM is associated with a first priority rating, and wherein the second VM is associated with a second priority rating;
assigning first and second quality ratings to the first and second requests, respectively, based on the first and second priority ratings, respectively;
comparing the first and second quality ratings to the current quality rating for the shared resource;
assigning the shared computing resource to the first VM based on the comparison, of the first and second quality ratings to the current quality rating for the shared resource, producing a closer correspondence between the first VM and the current quality rating.
14. The system of claim 13 , wherein
the priority rating of the first VM is based, at least in part, on a service level agreement (SLA), and
the SLA specifies a minimum level of service associated with the requesting VM.
15. The system of claim 13 , wherein
the plurality of factors related to the shared computing resource comprises at least one of:
a static factor, and
a dynamic factor.
16. The system of claim 15 , wherein the method further comprises:
periodically evaluating the shared computing resource, wherein
each evaluation of the shared computing resource comprises determining whether the dynamic factor has changed since a previous evaluation of the dynamic factor;
in response to determining that the dynamic factor has changed since the previous evaluation, updating the current quality rating for the shared computing resource; and
subsequent to updating the current quality rating for the shared computing resource, assigning a different shared computing resource to the first VM, wherein
the different shared computing resource is assigned to the first VM in order to maintain a minimum level of service associated with the first VM, and
the specific level of service associated with the requesting VM is based on a service level agreement (SLA).