Publishing configuration patterns for storage resources and storage performance models from client systems to share with client systems in a network computing environment
AssigneeInternational Business Machines Corporation
InventorsRakesh Jain, Ramani R. Routray, Sumant Padbidri, Yang Song
Provided are a method, system and program for publishing configuration patterns for storage resources and storage performance models from client systems to share with client systems in a network computing environment. A determination is made of a configuration pattern of storage resources within the client computing environment and storage performance metrics for the configuration pattern of storage resources within the client. At least one storage performance model is created based on the determined storage performance metrics. Information on the at least one storage performance model and the configuration pattern of the storage resources for which the storage performance metrics were determined are published to the service provider.
Drawings
Claims17
A computer program product for managing storage resources at a client computing environment in communication with a service provider, wherein the computer program product comprises a non-transitory computer readable storage medium having program code that when executed by a processor to cause operations to be performed, the operations comprising:
determining a configuration pattern of the storage resources within the client computing environment, including disk types, encryption settings, and storage configuration of storage devices;
determining storage performance metrics for the configuration pattern of the storage resources within the client computing environment;
creating at least one storage performance model based on the determined storage performance metrics as a function of workloads at the configuration pattern of the storage resources to model how the configuration pattern of the storage resources responds to different workloads;
and
publishing, to the service provider, a published configuration pattern including the configuration pattern of the storage resources including attribute values for storage attributes of the storage resources deployed at the client computing environment, the storage performance model created for the workloads at the configuration pattern of the storage resources for which the storage performance metrics were determined, and a confidence level indicating a degree of detail of an internal structure of the storage resources considered in determining the determined storage performance metrics, wherein the confidence level is based on whether one of black box testing, white box testing, and grey box testing is used to determine the confidence level, wherein the white box testing results in a highest confidence level, the grey box testing results in a next highest confidence level below the highest confidence level, and the black box testing results in a lowest confidence level.
2 more elements
A system implementing a client computing environment having storage resources and in communication with a service provider, comprising:
a processor;
a non-transitory computer readable storage medium having program code that when executed causes operations to be performed, the operations comprising:
determining a configuration pattern of the storage resources within the client computing environment, including disk types, encryption settings, and storage configuration of storage devices;
determining storage performance metrics for the configuration pattern of the storage resources within the client computing environment;
creating at least one storage performance model based on the determined storage performance metrics as a function of workloads at the configuration pattern of the storage resources to model how the configuration pattern of the storage resources responds to different workloads;
and
publishing, to the service provider, a published configuration pattern including the configuration pattern of the storage resources including attribute values for storage attributes of the storage resources deployed at the client computing environment, the storage performance model created for the workloads at the configuration pattern of the storage resources for which the storage performance metrics were determined, and a confidence level indicating a degree of detail of an internal structure of the storage resources considered in determining the determined storage performance metrics wherein the confidence level is based on whether one of black box testing, white box testing, and grey box testing is used to determine the confidence level, wherein the white box testing results in a highest confidence level, the grey box testing results in a next highest confidence level below the highest confidence level, and the black box testing results in a lowest confidence level.
4 more elements
A method for managing storage resources at a client computing environment in communication with a service provider, comprising:
determining a configuration pattern of the storage resources within the client computing environment, including disk types, encryption settings, and storage configuration of storage devices;
determining storage performance metrics for the configuration pattern of the storage resources within the client computing environment;
creating at least one storage performance model based on the determined storage performance metrics as a function of workloads at the configuration pattern of the storage resources to model how the configuration pattern of the storage resources responds to different workloads;
and
publishing, to the service provider, a published configuration pattern including the configuration pattern of the storage resources including attribute values for storage attributes of the storage resources deployed at the client computing environment, the storage performance model created for the workloads at the configuration pattern of the storage resources for which the storage performance metrics were determined, and a confidence level indicating a degree of detail of an internal structure of the storage resources considered in determining the determined storage performance metrics, wherein the confidence level is based on whether one of black box testing, white box testing, and grey box testing is used to determine the confidence level, wherein the white box testing results in a highest confidence level, the grey box testing results in a next highest confidence level below the highest confidence level, and the black box testing results in a lowest confidence level.
22 Jan 2035Estimated · howhide20 years from earliest known nonprovisional domestic filing plus recorded patent term adjustment. Maintenance-fee lapses, terminal disclaimers and statutory extensions have not been checked. The continuity chain may be incomplete; this is not an enforceability determination.
Arrangements for monitoring or testing data switching networks: testing arrangements
Life of this patent
About 8 years 3 months of term left · ends 22 Jan 2035 (estimated)
Priority22 Jan 2015
Filed12 Jun 2019
Published26 Sep 2019
Granted9 Mar 2021
Today12 Oct 2026
Term ends22 Jan 2035
Priority22 Jan 2015
Granted9 Mar 2021
Term ends22 Jan 2035
Priority claimedParent application 14/603,264
Application filedUS 16/439,608
Assigned to International Business Machines Corporationassignment of assignor's interest
PublishedUS 2019/0297145 A1
GrantedUS 10,944,827 B2
TodayWithin its term
Term endsEstimated
Description7,289 words
Summary278 words
#The present invention relates to a computer program product, system, and method for publishing configuration patterns for storage resources and storage performance models from client systems to share with client systems in a network computing environment.
#Cloud computing and software defined environments often utilize the Software As Service (SaaS) software distribution model where applications are hosted by a service provider and made available to service consumers over the network. In a typical multi-tenant SaaS architecture, data from multiple companies is stored on a single service provider instance, usually separated by a tenancy partition to prevent the visibility of data from one tenant to another. Standardized logical tenancy partitions are established for the different tenants housed on the same service provider instance. In such a model, service provider application resources (such as repository/database instance(s), application server instance(s)) are multiplexed and used. However, the storage devices used by the tenants are separately managed so that the tenants have separate storage resources to store their data, which may be confidential and cannot be shared.
#Provided are a method, system and program for publishing configuration patterns for storage resources and storage performance models from client systems to share with client systems in a network computing environment. A determination is made of a configuration pattern of storage resources within the client computing environment and storage performance metrics for the configuration pattern of storage resources within the client. At least one storage performance model is created based on the determined storage performance metrics. Information on the at least one storage performance model and the configuration pattern of the storage resources for which the storage performance metrics were determined are published to the service provider.
Brief description of the drawings12 figures
#FIG. 1 illustrates an embodiment of a client computing environment.
#FIG. 2 illustrates an embodiment of components of a client computing environment.
#FIG. 3 illustrates an embodiment of components of a service provider.
Detailed description6,829 words
#Described embodiments provide techniques for allowing client systems or computing environments to publish information on their storage configuration patterns of storage resources and a storage performance model providing a model of the performance of the storage configuration pattern with a central service provider. The central service provider may then make the published storage configurations and storage performance models available to other client systems to access when they deploy similar storage configuration patterns. The clients may want to obtain a storage performance model for a similar published storage configuration pattern to use to determine how to deploy storage resources. This allows clients to share storage performance models from other clients in the system, which may be sharing a same software service. By sharing the published configuration patterns, a client does not have to construct the storage performance model for a newly deployed storage configuration pattern for which the client does not have information.
#FIG. 1 illustrates an embodiment of a network service provider environment 100, such as a cloud computing environment, having one or more client computing environments 2001, 2002 . . . 200n and a central service provider 300 that communicate over a network 102. Each client computing environment 2001, 2002 . . . 200n has storage resources configured for use with a software service managed by the service provider 300. In one embodiment, the service provider 300 may provide a software as a service (SaaS) architecture to the clients 2001, 2002 . . . 200n, which may comprise tenants that receive the software service from the service provider 300. For instance, in a multi-tenant architecture, the service provider 300 provides every tenant/client a dedicated share of the instance including its data, configuration, user management, tenant individual functionality and non-functional properties. In an alternative embodiment, the service provider 300 may implement a multi-instance architecture where separate software service instances operate on behalf of the different tenants 2001, 2002 . . . 200n. Although each client 2001, 2002 . . . 200n may receive the software services from the service provider 300, each client 2001, 2002 . . . 200n maintains separate storage resources for use in the environment 100.
#The network 102 may comprise a Storage Area Network (SAN), Local Area Network (LAN), Intranet, the Internet, Wide Area Network (WAN), peer-to-peer network, wireless network, arbitrated loop network, etc.