Managing computing system configurations for security quality of service (QoS)
The technology described herein includes determining a security quality of service (Qos) profile matching configuration attributes of a first computing system, generating an interdependency flow graph based at least in part on the security QoS profile and the configuration attributes, generating a recommended configuration for the first computing system from the interdependency flow graph, and sending the recommended configuration to a second computing system.
1 . A first computing system comprising:
a memory to store a plurality of security quality of service (QoS) profiles and configuration attributes of the first computing system;
a plurality of components having respective performance monitoring units to provide real-time telemetry data about the respective components; and
a processor to:
determine a security QoS profile matching the configuration attributes;
generate an interdependency flow graph based at least in part on the security QoS profile and the configuration attributes;
generate a recommended configuration for the first computing system based on the interdependency flow graph and the real-time telemetry data;
send the recommended configuration to a second computing system; and
configure the first computing system based at least in part on the recommended configuration.
2 . The system of claim 1 , comprising the processor to generate feedback from machine learning on real-time telemetry data of the first computing system and generate the recommended configuration for the first computing system based at least in part on the feedback.
3 . The system of claim 2 , comprising the processor to store the plurality of security QoS profiles, configuration attributes, interdependency flow graph, real-time telemetry data and feedback in a secure database providing a secure audit trail.
4 . The system of claim 1 , wherein the security QoS profile comprises a set of security QoS requirements of the plurality of components of the first computing system, the plurality of components including a central processing unit (CPU), a graphics processing unit (GPU), an application specific integrated circuit (ASIC), or a field programmable gate array (FPGA).
5 . The system of claim 4 , wherein the set of security QoS requirements comprises a processor version and security characteristics of the processor version of at least one of the plurality of components of the first computing system.
6 . The system of claim 1 , wherein configuration attributes comprise a number, a type, and attributes of the plurality of components and software components of the first computing system.
7 . The system of claim 1 , comprising the processor to determine a security QoS profile matching the configuration attributes by identifying a security QoS profile that meets service level agreement (SLA) requirements of an application to be run on the first computing system.
8 . The system of claim 1 , comprising the processor to perform remote attestation of components of the first computing system exposed by the configuration attributes.
9 . The system of claim 1 , comprising the processor to generate the interdependency flow graph as a function of an interaction matrix, QoS attributes, application service level objectives (SLO), or feedback from machine learning on the real-time telemetry data of the first computing system.
10 . The system of claim 1 , comprising the processor to regenerate the interdependency flow graph and the recommended configuration in response to a hardware component of the plurality of components of the first computing system being added to the first computing system or removed from the first computing system during runtime.
11 . A method comprising:
determining a security quality of service (QoS) profile matching configuration attributes of a first computing system;
generating an interdependency flow graph based at least in part on the security QoS profile and the configuration attributes;
generating a recommended configuration for the first computing system based on the interdependency flow graph and real-time telemetry data from a plurality of components of the first computing system;
sending the recommended configuration to a second computing system; and
configuring the first computing system based at least in part on the recommended configuration.
12 . The method of claim 11 , comprising generating feedback from machine learning on the real-time telemetry data of the first computing system and generating the recommended configuration of the first computing system based at least in part on the feedback.
13 . The method of claim 12 , comprising storing the security QoS profile, configuration attributes, interdependency flow graph, the real-time telemetry data and feedback in a secure database providing a secure audit trail.
14 . The method of claim 11 , wherein the security QoS profile comprises a set of security QoS requirements of the plurality of components of the first computing system, the plurality of components including a central processing unit (CPU), a graphics processing unit (GPU), an application specific integrated circuit (ASIC), or a field programmable gate array (FPGA).
15 . The method of claim 14 , wherein the set of security QoS requirements comprises a processor version and security characteristics of the processor version of at least one of the plurality of components of the first computing system.
16 . At least one non-transitory machine-readable storage medium comprising instructions which, when executed by at least one processor, cause the at least one processor to:
determine a security quality of service (QoS) profile matching configuration attributes of a first computing system;
generate an interdependency flow graph based at least in part on the security QoS profile and the configuration attributes;
generate a recommended configuration for the first computing system from the interdependency flow graph and real-time telemetry data from a plurality of components of the first computing system;
send the recommended configuration to a second computing system; and
configure the first computing system based at least in part on the recommended configuration.
17 . The at least one non-transitory machine-readable storage medium of claim 16 , comprising instructions which, when executed by the at least one processor, cause the at least one processor to generate feedback from machine learning on the real-time telemetry data of the first computing system and generate the recommended configuration of the first computing system based at least in part on the feedback.
18 . The at least one non-transitory machine-readable storage medium of claim 17 , comprising instructions which, when executed by the at least one processor, cause the at least one processor to store the security QoS profile, configuration attributes, interdependency flow graph, the real-time telemetry data and feedback in a secure database providing a secure audit trail.
19 . The at least one non-transitory machine-readable storage medium of claim 16 , wherein the security QoS profile comprises a set of security QoS requirements of the plurality of components of the first computing system, the plurality of components including a central processing unit (CPU), a graphics processing unit (GPU), an application specific integrated circuit (ASIC), or a field programmable gate array (FPGA).
20 . The at least one non-transitory machine-readable storage medium of claim 19 , wherein the set of security QoS requirements comprises a processor version and security characteristics of the processor version of at least one of the plurality of components of the first computing system.