Micro-level monitoring, visibility and control of shared resources internal to a processor of a host machine for a virtual environment

Patent metadata

Field	Value
Publication number	US-2018285166-A1
Application number	US-201715797098-A
Country	US
Kind code	A1
Filing date	Oct 30, 2017
Priority date	Mar 29, 2017
Publication date	Oct 4, 2018
Grant date	—

Abstract

Aspects of this disclosure relate to monitoring use of shared resources to identify processes using such shared resources in a manner that may be affecting the performance of other processes. In one example, a method comprises: monitoring, by a computing device, usage metrics for a shared cache that is shared by one or more processors of the computing device; mapping the usage metrics to each of a plurality of virtual computing environments executing on the one or more processors, wherein the plurality of virtual computing environments includes a first virtual computing environment and a second virtual computing environment; determining, based on the mapped usage metrics, that the first virtual computing environment is using the shared cache in a manner that adversely affects the performance of the second virtual computing environment; and restricting, by the computing device, access to the shared cache by the first virtual computing environment.

First claim

What is claimed is:

1 . A method comprising:
generating, by a policy controller, a policy to apply within a data center; distributing, by the policy controller, the policy to a policy agent executing on a computing device included within the data center, wherein the computing device includes processing circuitry having a plurality of processor cores; monitoring usage metrics relating to a resource shared by the plurality of processor cores; mapping a first subset of the usage metrics to a first virtual computing environment and mapping a second subset of the usage metrics to a second virtual computing environment, wherein both the first virtual computing environment and the second virtual computing environment execute on the processing circuitry; determining, based on the mapped usage metrics and the policy, that the first virtual computing environment is using the resource in a manner that adversely affects the performance of the second virtual computing environment; and responsive to determining, restricting access to the resource by the first virtual computing environment.

2 . The method of claim 1 , wherein the resource is a cache shared by the processor cores.

3 . The method of claim 1 , wherein the resource is a memory bus.

4 . The method of claim 2 , further comprising:
prior to determining that the first virtual computing environment is using the cache in a manner that adversely affects the performance of the second virtual computing environment, allocating a substantially equal portion of the cache to each of the first virtual computing environment and the second virtual computing environment.

5 . The method of claim 2 , wherein the first virtual computing process has access to a portion of the cache, and wherein restricting access to the cache includes:
reducing the portion of the shared cache accessible by the first virtual computing process.

6 . The method of claim 1 ,
wherein the first virtual computing environment includes a first process and a second process; wherein determining includes determining that the first process is using resource in a manner that adversely affects the performance of the second virtual computing environment; and wherein restricting includes restricting access to the resource by the first process without restricting access to the resource by the second process.

7 . The method of claim 1 , wherein monitoring usage metrics includes monitoring usage metrics using Resource Director Technology.

8 . The method of claim 1 , wherein the first virtual computing environment is a virtual machine executing on a hypervisor.

9 . The method of claim 1 , wherein the first virtual computing environment is a container executing on the computing device.

10 . A system comprising:
a policy controller configured to generate a policy to apply within a data center; and a computing system comprising processing circuitry and one or more storage devices, wherein the processing circuitry includes a plurality of processor cores, and wherein the one or more storage devices store instructions that, when executed, configure the processing circuitry to: receive, from the policy controller, the policy, monitor usage metrics relating to a resource shared by the plurality of processor cores, map a first subset of the usage metrics to a first virtual computing environment and map a second subset of the usage metrics to a second virtual computing environment, wherein both the first virtual computing environment and the second virtual computing environment execute on the processing circuitry; determine, based on the mapped usage metrics and the policy, that the first virtual computing environment is using the resource in a manner that adversely affects the performance of the second virtual computing environment, and responsive to determining, restrict access to the resource by the first virtual computing environment.

11 . The computing system of claim 10 , wherein the resource is a cache shared by each of the processor cores.

12 . The computing system of claim 10 , wherein the resource is a memory bus.

13 . The computing system of claim 11 , wherein the instructions, when executed, further configure the processing circuitry to:
prior to determining that the first virtual computing environment is using the cache in a manner that adversely affects the performance of the second virtual computing environment, allocate a substantially equal portion of the cache to each of the first virtual computing environment and the second virtual computing environment.

14 . The computing system of claim 11 , wherein the first virtual computing process has access to a portion of the cache, and wherein restricting access to the cache includes:
reducing the portion of the shared cache accessible by the first virtual computing process.

15 . The computing system of claim 10 ,
wherein the first virtual computing environment includes a first process and a second process; wherein determining includes determining that the first process is using resource in a manner that adversely affects the performance of the second virtual computing environment; and wherein restricting includes restricting access to the resource by the first process without restricting access to the resource by the second process.

16 . The computing system of claim 10 , wherein monitoring usage metrics includes monitoring usage metrics using Resource Director Technology.

17 . The computing system of claim 10 , wherein the first virtual computing environment is a virtual machine executing on a hypervisor.

18 . The computing system of claim 10 , wherein the first virtual computing environment is a container executing on the computing device.

19 . A computer readable storage medium comprising instructions that, when executed, configure processing circuitry of a computing system to:
receive, from the policy controller, a policy; monitor usage metrics relating to a resource shared by a plurality of processor cores included within the processing circuitry; map the usage metrics to each of a plurality of virtual computing environments executing on the processing circuitry, wherein the plurality of virtual computing environments includes a first virtual computing environment and a second virtual computing environment; determine, based on the mapped usage metrics and the policy, that the first virtual computing environment is using the resource in a manner that adversely affects the performance of the second virtual computing environment; and restrict, by the computing device, access to the resource by the first virtual computing environment.

20 . The computer readable storage medium of claim 19 , wherein the resource is a cache shared by each of the processor cores.

21 . The computer readable storage medium of claim 19 , wherein the resource is a memory bus.

22 . The computer readable storage medium of claim 20 , wherein the instructions, when executed, further configure the processing circuitry to:
prior to determining that the first virtual computing environment is using the cache in a manner that adversely affects the performance of the second virtual computing environment, allocate a substantially equal portion of the cache to each of the first virtual computing environment and the second virtual computing environment.

23 . The computer readable storage medium of claim 20 , wherein the first virtual computing process has access to a

Assignees

• Juniper Networks Inc

Inventors

• Roy Parantap
• Singh Sumeet
• Newhouse Travis Gregory

Classifications

• G06F12/0842

  for multiprocessing or multitasking · CPC title

• G06F9/5016

  the resource being the memory · CPC title

• G06F11/3452

  Performance evaluation by statistical analysis · CPC title

• G06F2009/45575

  Starting, stopping, suspending or resuming virtual machine instances · CPC title

• G06F11/3006

  where the computing system is distributed, e.g. networked systems, clusters, multiprocessor systems (multiprogramming arrangements G06F9/46; allocation of resources G06F9/50) · CPC title