DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 11/17/2025 has been entered.
This action is responsive to the Applicant’s amendments filed on 11/17/2025. Claims 1-20 remain pending in the application. Claims 1, 5, 7, 11, 14, and 18 have been amended. Any examiner’s note, objection, and rejection not repeated is withdrawn due to Applicant’s amendment.
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 07/20/2022 is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
Examiner’s Note
The Examiner cites particular columns, paragraphs, figures, and line numbers in the references as applied to the claims below for the convenience of the applicant. Although the specified citations are representative of the teachings in the art and are applied to the specific limitations within the individual claim, other passages and figures may also apply. It is respectfully requested that, in preparing responses, the Applicant fully consider the references in its entirety as potentially teaching all or part of the claimed invention, as well as the context of the passage as taught by the prior art or disclosed by the Examiner.
Claim Objections
Claim 1-20 are objected to because of the following informalities: Claims 1, 7, and 14 recite a “presentation/management subsystem”. The use of the symbol “/” should be replaced with appropriate wording to clearly convey the intended meaning. The Examiner suggests “presentation and management subsystem”. For the purposes of examination, the Examiner interprets the phrase as a “presentation and management subsystem”.
Any claim not specifically mentioned above is objected to due to dependency on an objected claim.
Appropriate correction is required.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1, 5, 7, 11, 14, 18 are rejected under 35 U.S.C. 103 as being unpatentable over Guim Bernat et al. (US 20210014303 A1) hereafter Guim Bernat, in view of Ooi et al. (US 20220156211 A1) hereafter Ooi, further in view of Hower et al. (US 20190065374 A1) hereafter Hower.
Regarding claim 1, Guim Bernat teaches:
A LCS (Paragraphs 92-96; “example computing device includes the example pooled accelerators platform 1014 with pooled accelerator resources”, and may include “pooled memory platform with pooled memory resources”, in which “the pooled QoS controller 1012... interfaces with the pooled memory platform” and can provide “pooled memory information for servicing a service request”. Pooled accelerator and memory resources are monitored and allocated by the pooled QoS controller for servicing requests. The system forms a computing configuration based on logically selected pooled resources, thereby corresponding to a logically composed system.);
receive, from the resource management system (Paragraph 23; the broker and QoS controller that manages pooled resources across multiple computing devices receives service requests and determines allocation of workloads to computing devices based on SLA/SLO requirements, corresponding to the resource management system), an identification of a first subset of the plurality of resource devices (Paragraph 23; teaches pooled resources of multiple computing devices and determining how to allocate a process to selected resources based on SLA/SLO compliance. Selecting particular computing devices from the pool inherently identifies a subset of the plurality of computing devices. Additionally, Paragraph 54 discloses allocation of resources to tenants using various schema, including bare metal, further evidencing selection and allocation of resources from a larger pool.) for providing a first system using an operating system provided by the BMS system (Paragraph 40; servers in the edge cloud include an OS and virtual computing environment forming part of the managed infrastructure. The OS is part of the platform that supports the execution environment. Paragraph 25 further describes interaction between applications, containers, and the OS of the computing device, confirming that the OS is part of the managed computing platform, thus demonstrating that the identified computing devices provide a system operating using an OS that is part of the managed server infrastructure. Paragraph 53 explicitly identifies bare metal (dedicated) servers as one of the allocation options, and the OS provided on these servers is part of the infrastructure. The allocated system runs directly on the OS of the BMS.), and first Service Level Agreement (SLA) information defining a first SLA for the first system (Paragraph 23; expressly teaches managing QoS to comply with SLA/SLO requirements, determining whether pooled resources can satisfy requested SLA requirements, and allocating workloads accordingly. The SLA/SLO requirements are used to evaluate and determine resource allocation decisions.);
receive, from the resource management system (Paragraph 23; the broker and QoS controller that manages pooled resources across multiple computing devices receives service requests and determines allocation of workloads to computing devices based on SLA/SLO requirements, corresponding to the resource management system.), an identification of a second subset of the plurality of resource devices (Paragraph 23; teaches pooled resources of multiple computing devices and determining how to allocate a process to selected resources based on SLA/SLO compliance. Selecting particular computing devices from the pool inherently identifies a subset of the plurality of computing devices. Additionally, Paragraph 54 discloses allocation of resources to tenants using various schema, including bare metal, further evidencing selection and allocation of resources from a larger pool. It does not restrict allocation to only one subset. The reference supports selecting multiple devices to simultaneously service requests, therefore the “second subset” of devices can be selected in the same manner as the first.) for providing a second system using the operating system provided by the BMS system (Paragraph 40; servers in the edge cloud include an OS and virtual computing environment forming part of the managed infrastructure. The OS is part of the platform that supports the execution environment. Paragraph 25 further describes interaction between applications, containers, and the OS of the computing device, confirming that the OS is part of the managed computing platform, thus demonstrating that the identified computing devices provide a system operating using an OS that is part of the managed server infrastructure. Paragraph 53 explicitly identifies bare metal (dedicated) servers as one of the allocation options, and the OS provided on these servers is part of the infrastructure. It further supports different subsets of resources dedicated to different tenants and managing allocation to avoid interference between tenants and workloads, ensuring that multiple systems, i.e. first and second systems, can operate simultaneously and independently using their respective allocated resources, thus corresponding to the second system being provided by the BMS system. The allocated system runs directly on the OS of the BMS.), and second SLA information defining a second SLA for the second system (Paragraph 23; expressly teaches managing QoS to comply with SLA/SLO requirements, determining whether pooled resources can satisfy requested SLA requirements, and allocating workloads accordingly. The SLA/SLO requirements are used to evaluate and determine resource allocation decisions. When the second subset of resources is selected to provide a second system, the system is allocated according to the second SLA information just as the first subset is allocated using the first SLA information.);
allocate, based on the first SLA information, a first resource device included in the BMS system to satisfy the first SLA for the first system (Paragraph 49; discloses that a pod controller oversees the partitioning and allocation of containers and resources, determining which container requires which resources and for how long to complete a workload. Each container is allocated its own portion of the underlying physical resources and assigns them to specific containers. “The pod controller receives instructions from an orchestrator (e.g., the orchestrator 460) that instructs the controller on how best to partition physical resources”, which implies that the pod controller can assign only a portion of a resource to each container. Multiple containers can run on the same resource device, meaning the pod controller may partition the resource rather than giving it entirely to one container.);
allocate, based on the second SLA information, a second part of the first resource device included in the BMS system to satisfy the second SLA for the second system, wherein the second portion of the first resource device is different than the first portion of the first resource (Paragraph 49; “The pod controller receives instructions from an orchestrator (e.g., the orchestrator 460) that instructs the controller on how best to partition physical resources”. The pod controller determines which container requires which resources and for how long to satisfy workload requirements. This implies partitioning, corresponding to portioning, a single physical resource across multiple containers. Allocation decisions for the second portion are made based on SLA information specific to the second system, corresponding to being based on the second SLA information. Each container or workload receives only the amount of resources required to meet its SLA.);
provide, to the presentation/management subsystem, a first resource device configuration instruction that is configured to cause the presentation/management subsystem to configure the BMS system to allow the first system to access and utilize the first resource device (Paragraphs 119-123; describes the pooled QoS controller transmitting a response to the broker indicating the amount and availability of resources for executing a particular request, effectively informing the presentation/management subsystem of how much of a resource is available and can be allocated, then sends the portion of the resource device to the broker, thus corresponding to providing a configuration instruction for the first resource device portion. Paragraphs 40 and 53 describe servers in the BMS environment that can host workloads, establishing the BMS-managed physical server environment.);
provide, to the presentation/management subsystem, a second resource device configuration instruction that is configured to cause the presentation/management subsystem to configure the BMS system to allow the second system to access and utilize the second resource device while the first system accesses and utilizes the first part of the system (Paragraphs 119-123; describes the pooled QoS controller transmitting a response to the broker indicating the amount and availability of resources for executing a particular request, effectively informing the presentation/management subsystem of how much of a resource is available and can be allocated, then sends the portion of the resource device to the broker, thus corresponding to providing a configuration instruction for the first resource device portion. Paragraphs 40 and 53 describe servers in the BMS environment that can host workloads, establishing the BMS-managed physical server environment. Paragraphs 23 and 53 support the idea of multiple systems running simultaneously on the BMS, each using its own allocated portion. Thus, both allocations may occur in parallel under control of the orchestrator and utilize its own resource device portion of the same partitioned physical resource device for execution.).
receive, from the first resource device, telemetry data and analytics data during the use of the first portion of the first resource device by the first system and the use of the second portion of the first resource device by the second system (Paragraph 77; mesh proxies may obtain telemetry data from hardware components, corresponding to receiving telemetry and analytics data during use of the resource devices from the first resource device. It further describes multiple applications operating simultaneously with mesh proxies monitoring each application’s resource usage. Each application corresponds to its own system (first, second) and can monitor distinct portions of the same resource device for each application. Telemetry is explicitly analyzed to determine if SLA/SLO requirements are satisfied and produces analytics data.);
and use the telemetry data and analytics data to determine whether the use of the first portion of the first resource device is satisfying the first SLA for the first system, and to determine whether the use of the second portion of the first resource device is satisfying the second SLA for the second system (Paragraph 77; teaches that mesh proxies analyze telemetry data to determine if SLA/SLO requirements are satisfied, including hardware performance metrics from analytics data, corresponding to using the telemetry and analytics data to determine whether the first portion of the first resource device is satisfying the first SLA for the first system. Paragraph 77 further describes multiple applications simultaneously operating, each monitored by its own mesh proxy which monitors a distinct portion of the first resource device allocated to its corresponding system. Therefore, the first portion of the resource device is monitored for the first system, and the second portion of the first resource device is monitored for the second system, and so forth. The analysis performed by mesh proxies converts telemetry into SLA/SLO compliance information, which corresponds to the use of analytics data to determine whether the resource is satisfying the SLA.).
Guim Bernat does not teach a resource management system; a presentation/management subsystem that is included in the BMS; and an orchestrator device that is included in the BMS system and that is coupled to the resource management system, the plurality of resource devices, and the presentation/management subsystem; or allocating portions of resource devices.
However, Ooi teaches:
A resource device access control and management system, comprising: a resource management system (Paragraph 45, Fig. 7; where the system of Fig. 7 corresponds to the resource management system); a plurality of resource devices (Paragraph 40; where the PCIe device physical functions for system device provisioning correspond to a plurality of resource devices); a Bare Metal Server (BMS) that includes a first resource device included in the plurality of resource devices (Paragraph 33; bare metal mode host server 102 used to provision devices/functions including a plurality PCIe devices corresponds to a BMS that includes a first resource device included in the plurality of resource devices);
a presentation/management subsystem that is included in the BMS (Paragraph 48; “The FPGA 70 receives a request to add or remove devices (block 202). The request may be made from the host processor 131 based on a user inputting a request into the bare metal mode host server 102. The request may indicate how many devices to add, may indicate a specific device (e.g., via indexing or naming), indicate a device type, or a combination thereof”, the orchestration controller SoC and device provisioning entity within the bare metal mode host server correspond to the presentation/management subsystem included in the BMS. It may accept user or system commands to add/remove devices corresponding to the role of presenting/managing resources);
and an orchestrator device that is included in the BMS system and that is coupled to the resource management system, the plurality of resource devices, and the presentation/management subsystem (Paragraph 48; orchestrator controller SoC corresponds to the orchestrator device in which the bare metal mode host server, corresponding to the BMS, contains the orchestrator controller SoC, corresponding to being included in the BMS system. The orchestration controller SoC interacts with the device provisioning entity, corresponding to being coupled to the resource management system, and interacts with the FPGA and configuration registers to control device visibility and provisioning, corresponding to being coupled to the presentation/management subsystem).
Guim Bernat and Ooi are considered to be analogous to the claimed invention because they are in the same field of resource orchestration. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Guim Bernat to incorporate the teachings of Ooi and have a resource management system, a presentation/management subsystem in the BMS, and an orchestrator device that is included in the BMS system and that is coupled to the resource management system, the plurality of resource devices, and the presentation/management subsystem. A person of ordinary skill in the art would have recognized the use of the known method of centralized resource orchestration and management would yield the predictable result of coordinated allocation of computing resources within a bare metal system.
While Guim Bernat in view of Ooi teaches allocating portions of resources from a resource pool, Guim Bernat in view of Ooi does not teach allocation of portions of a resource device.
However, Hower teaches:
allocation of portions of resource devices (Paragraph 25; “each of the allocation indicators 114(0)-114(C), 114′(0)-114′(C) for a given one of the resource clients 106(0)-106(C) may vary across different partitions 108(0)-108(P). As a result, a resource client such as the resource client 106(0) may be allocated different portions of each of the partitions 108(0)-108(P). By interpolating the different allocation indicators 114(0)-114(C), 114′(0)-114′(C), a higher allocation resolution may be attained, thus enabling a smaller portion of the partitioned resource 104 to be allocated to each of the resource clients 106(0)-106(C) if desired.”).
Guim Bernat, Ooi, and Hower are considered to be analogous to the claimed invention because they are in the same field of resource allocation. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Ooi to incorporate the teachings of Hower and implement the capability to portion a resource device for assignment to simultaneous consumers. A person of ordinary skill in the art would have modified the FPGA provisioning logic of Guim Bernat in view of Ooi such that the underlying hardware resources are partitioned into multiple portions prior to device exposure, allowing each partition to be mapped to a provisioned device or PF exposed to the bare metal host server. Such partitioning occurs within the FPGA hardware without requiring virtualization, preserving the bare metal constraints, utilizing techniques known to a person of ordinary skill in the art such as FPGA resource slicing, hardware QoS, cache partitioning, and memory region allocation.
Claim 7 recites similar limitations as those of claim 1, directed towards a system. Claim 7 is rejected for similar reasons as those of claim 1.
Claim 14 recites similar limitation as those of claim 1, directed towards a method. Claim 14 is rejected for similar reasons as those of claim 1.
Regarding claim 5, Guim Bernat in view of Ooi, further in view of Hower teach the system of claim 1. Guim Bernat teaches:
A LCS (Paragraphs 92-96; “example computing device includes the example pooled accelerators platform 1014 with pooled accelerator resources”, and may include “pooled memory platform with pooled memory resources”, in which “the pooled QoS controller 1012... interfaces with the pooled memory platform” and can provide “pooled memory information for servicing a service request”. Pooled accelerator and memory resources are monitored and allocated by the pooled QoS controller for servicing requests. The system forms a computing configuration based on logically selected pooled resources, thereby corresponding to a logically composed system.);
monitor, using the telemetry data and analytics data and the first SLA information for the first system, the first resource device during its providing of the first system (Paragraphs 76-77; “telemetry data includes data that is used to monitor performance and availability of hardware components”, where the mesh proxy actively collects telemetry data to monitor performance. “Additionally, the example mesh proxies... may analyze the telemetry data to determine if the SLA/SLO requirements are satisfied”, where the telemetry data being obtained and analyzed corresponds to using telemetry and analytics data. “Applications 800, 802 can transmit SLA/SLO requirements to the example respective mesh proxies 804, 806, and the mesh proxies 804, 806 can convert the SLA/SLO requirements into resource-based attributes”, where SLA info is communicated to the mesh proxy. “Telemetry data includes data... of hardware components 810”, where specific hardware components constitute a plurality of portions thereof. “Because the processing of telemetry data is performed by the mesh proxies 804, 806... the applications 800, 802 can be freely migrated or replicated for load balancing, elastic scaling, etc.” Monitoring occurs while the applications are executing, thereby corresponding to being during providing of the first system.);
identify, in response to the monitoring of the first resource device during its providing of the first system, whether the first resource device is performing first resource device functionality that is not satisfying the first SLA for the first system (Paragraphs 76-77; ”example mesh proxies 804, 806 may obtain telemetry data from the OS 808... [and] may analyze the telemetry data” shows that mesh proxies both monitor and analyze hardware components, corresponding to identifying performance based on monitoring. “Because the processing of telemetry data is performed by the mesh proxies 804, 806... the applications 800, 802 can be freely migrated or replicated for load balancing, elastic scaling, etc.” Monitoring occurs while the applications are executing, thereby corresponding to being during providing of the first system. “The example mesh proxies 804, 806 may analyze the telemetry data to determine if the SLA/SLO requirements are satisfied and/or may transmit the telemetry data and/or a compliance indication to the respective applications 800, 802”, where mesh proxies explicitly determine whether hardware resources meet SLA requirements.).
Hower teaches:
allocation of portions of resource devices (Paragraph 25; “each of the allocation indicators 114(0)-114(C), 114′(0)-114′(C) for a given one of the resource clients 106(0)-106(C) may vary across different partitions 108(0)-108(P). As a result, a resource client such as the resource client 106(0) may be allocated different portions of each of the partitions 108(0)-108(P). By interpolating the different allocation indicators 114(0)-114(C), 114′(0)-114′(C), a higher allocation resolution may be attained, thus enabling a smaller portion of the partitioned resource 104 to be allocated to each of the resource clients 106(0)-106(C) if desired.”).
Claim 11 recites similar limitations as those of claim 5, directed towards a system. Claim 11 is rejected for similar reasons as those of claim 5.
Claim 18 recites similar limitation as those of claim 5, directed towards a method. Claim 18 is rejected for similar reasons as those of claim 5.
Claims 2-3, 6, 8-9, 12, 15-16, and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Guim Bernat in view of Ooi, further in view of Hower, further in view of Sun et al. (US 20180302299 A1) hereafter Sun.
Regarding claim 2, Guim Bernat in view of Ooi, further in view of Hower teach the system of claim 1. Guim Bernat in view of Ooi, further in view of Hower does not teach wherein the first/second SLA information is received in a first/second SLA data model that identifies each of the first/second subset of the plurality of resource devices and at least one respective first/second SLA requirement for each of the first/second subset of the plurality of resource devices.
However, Sun teaches:
wherein the first SLA information is received in a first SLA data model that identifies each of the first subset of the plurality of resource devices and at least one respective first SLA requirement for each of the first subset of the plurality of resource devices (Paragraph 140, Fig. 15; “CMS deploys the pod groups or the service specification” corresponds to the first SLA data model that identifies each of the first subset of the plurality of resource devices, because the service specification dictates how resources, the pods, are allocated and grouped. “modifies it to meet the networking SLA as needed” corresponds to at least one respective first SLA requirement for each of the first subset of the plurality of resource devices because the modification ensures compliance with SLA requirements for the identified resources);
and the second SLA information is received in a second SLA data model that identifies each of the second subset of the plurality of resource devices and at least one respective second SLA requirement for each of the second subset of the plurality of resource devices (Paragraph 140, Fig. 15; “CMS deploys the pod groups or the service specification” corresponds to the first SLA data model that identifies each of the first subset of the plurality of resource devices, because the service specification dictates how resources, the pods, are allocated and grouped. “modifies it to meet the networking SLA as needed” corresponds to at least one respective first SLA requirement for each of the first subset of the plurality of resource devices because the modification ensures compliance with SLA requirements for the identified resources. While the “first SLA data model” is interpreted as read on by the initial service specification governing a first set of pods, corresponding to a first subset of resources, the “second data model” is read on by the same service specification applied to a second set of pods, corresponding to a second subset of resources, and its SLA constraints. The monitoring and modification process necessarily applies to multiple subsets of deployed resources to ensure compliance with SLA requirements).
Guim Bernat, Ooi, Hower, and Sun are considered to be analogous to the claimed invention because they are in the same field of resource orchestration. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Guim Bernat in view of Ooi, further in view of Hower to incorporate the teachings of Sun and utilize SLA information received in an SLA data model that identifies a subset of resource devices and SLA requirements for the subset of resource devices. Further, a person of ordinary skill in the art having knowledge of a first SLA information in a first SLA data model identifying a first subset of resource devices and a first SLA requirement would find it obvious to extend the deployment of pod groups to a plurality of pods having second service specifications corresponding to second SLA requirements received in a second SLA data model. A person of ordinary skill in the art would be motivated by the need to optimize resource group usage in an orchestration system for each subset of resources in a system with different parts necessitating different resource requirements.
Claim 8 recites similar limitations as those of claim 2, directed towards a system. Claim 8 is rejected for similar reasons as those of claim 2.
Claim 15 recites similar limitation as those of claim 2, directed towards a method. Claim 15 is rejected for similar reasons as those of claim 2.
Regarding claim 3, Guim Bernat in view of Ooi, further in view of Hower teach the system of claim 1. Guim Bernat teachs:
A LCS (Paragraphs 92-96; “example computing device includes the example pooled accelerators platform 1014 with pooled accelerator resources”, and may include “pooled memory platform with pooled memory resources”, in which “the pooled QoS controller 1012... interfaces with the pooled memory platform” and can provide “pooled memory information for servicing a service request”. Pooled accelerator and memory resources are monitored and allocated by the pooled QoS controller for servicing requests. The system forms a computing configuration based on logically selected pooled resources, thereby corresponding to a logically composed system.)
Ooi teaches:
presenting a first physical or virtual function to the first resource system that allows the first resource system to use the first resource device (Paragraph 36; “the system 100 may dynamically hide or expose any of the devices/PFs in the PCIe add-in card 104”, exposing PFs of the PCIe card corresponds to presenting a physical function to the first LCS to allow the LCS to access the device);
and presenting a second physical or virtual function to the second system that allows the second system to use the first resource device (Paragraph 36; “the system 100 may dynamically hide or expose any of the devices/PFs in the PCIe add-in card 104”, exposing PFs of the PCIe card corresponds to presenting a physical function to the second LCS to allow the LCS to access the device).
Hower teaches:
allocating portions of resource devices (Paragraph 25; “each of the allocation indicators 114(0)-114(C), 114′(0)-114′(C) for a given one of the resource clients 106(0)-106(C) may vary across different partitions 108(0)-108(P). As a result, a resource client such as the resource client 106(0) may be allocated different portions of each of the partitions 108(0)-108(P). By interpolating the different allocation indicators 114(0)-114(C), 114′(0)-114′(C), a higher allocation resolution may be attained, thus enabling a smaller portion of the partitioned resource 104 to be allocated to each of the resource clients 106(0)-106(C) if desired.”).
Guim Bernat in view of Ooi, further in view of Hower does not teach allocation resource devices to satisfy SLAs.
However, Sun teaches:
allocating the first resource devices to satisfy the first SLA (Paragraph 140, Fig. 15; “deploys the pod groups… [and] modifies it to meet the networking SLA” corresponds to allocating the first resource device to satisfy the first SLA for the first LCS. Deploying and modifying pod groups is a form of resource allocation to satisfy the SLA requirements)
allocating the second resource devices to satisfy the second SLA (Paragraph 140, Fig. 15; “deploys the pod groups… [and] modifies it to meet the networking SLA” corresponds to allocating the second resource device to satisfy the second SLA for the second LCS. Deploying and modifying pod groups is a form of resource allocation to satisfy the SLA requirements. The ongoing adjustment of resources applies to different pods based on the service specification, corresponding to a second resource devices to satisfy the second SLA)
Guim Bernat, Ooi, Hower, and Sun are considered to be analogous to the claimed invention because they are in the same field of resource orchestration. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Guim Bernat in view of Ooi, further in view of Hower to incorporate the teachings of Sun and utilize SLA information and SLA requirements for allocation of subsets of portions of resource devices. Further, it would have been obvious to a person of ordinary skill in the art to present additional PFs for the PCIe card, corresponding to a second physical function to allow the LCS to access the device; and to continue the allocating step for multiple SLAs and LCSs. A person of ordinary skill in the art would be motivated by the need to optimize resource portion subset usage in an orchestration system, utilizing the known method of optimizing resource allocation, yielding the predictable result of optimal resource costs for the end user.
Claim 9 recites similar limitations as those of claim 3, directed towards a system. Claim 9 is rejected for similar reasons as those of claim 3.
Claim 16 recites similar limitation as those of claim 3, directed towards a method. Claim 16 is rejected for similar reasons as those of claim 3.
Regarding claim 6, Guim Bernat in view of Ooi, further in view of Hower teach the system of claim 5. Guim Bernat teaches:
A LCS (Paragraphs 92-96; “example computing device includes the example pooled accelerators platform 1014 with pooled accelerator resources”, and may include “pooled memory platform with pooled memory resources”, in which “the pooled QoS controller 1012... interfaces with the pooled memory platform” and can provide “pooled memory information for servicing a service request”. Pooled accelerator and memory resources are monitored and allocated by the pooled QoS controller for servicing requests. The system forms a computing configuration based on logically selected pooled resources, thereby corresponding to a logically composed system.).
Hower teaches:
allocation of portions of resource devices (Paragraph 25; “each of the allocation indicators 114(0)-114(C), 114′(0)-114′(C) for a given one of the resource clients 106(0)-106(C) may vary across different partitions 108(0)-108(P). As a result, a resource client such as the resource client 106(0) may be allocated different portions of each of the partitions 108(0)-108(P). By interpolating the different allocation indicators 114(0)-114(C), 114′(0)-114′(C), a higher allocation resolution may be attained, thus enabling a smaller portion of the partitioned resource 104 to be allocated to each of the resource clients 106(0)-106(C) if desired.”).
Guim Bernat in view of Ooi, further in view of Hower does not teach provide, in response to identifying the first resource device that is performing the first resource device functionality that is not satisfying the first SLA for the first system, the first system using a second resource device that performs second resource device functionality that satisfies the first SLA for the first system in place of the first resource device that was performing the first resource device functionality that was not satisfying the first SLA for the first system.
However, Sun teaches:
wherein the orchestrator device is configured to:
provide, in response to identifying the first resource device that is performing the first resource device functionality that is not satisfying the first SLA for the first system, the first system using a second resource device that performs second resource device functionality that satisfies the first SLA for the first system in place of the first resource device that was performing the first resource device functionality that was not satisfying the first SLA for the first system (Paragraph 143; “After all pod groups have been deployed, the system monitors the network to determine if the networking SLA is met at step 564. If the SLA is not met, the system attempts to relocate pods at step 566 in an effort to comply with the networking SLA specifications”. In response to identifying that the pods are not meeting SLA specifications, the pod(s) is/are replaced with pod(s) that do satisfy the SLA specifications. Sun further explicitly discloses “replacement” of instances in Paragraph 148).
Guim Bernat, Ooi, Hower, and Sun are considered to be analogous to the claimed invention because they are in the same field of resource orchestration. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Guim Bernat in view of Ooi, further in view of Hower to incorporate the teachings of Sun and redirect workloads from a first resource device portion to a second capable of satisfying the SLA in response to identifying that the first portion of the first resource device is incapable of satisfying the SLA for the LCS. A person of ordinary skill in the art would have recognized the use of redirecting functionality in response to underperforming resources to be a known method in the art yielding the predictable result of continuing to provide the system while maintaining SLA compliance.
Claim 12 recites similar limitations as those of claim 6, directed towards a system. Claim 12 is rejected for similar reasons as those of claim 6.
Claim 19 recites similar limitation as those of claim 6, directed towards a method. Claim 19 is rejected for similar reasons as those of claim 6.
Claims 4, 10, and 17 are rejected under 35 U.S.C. 103 as being unpatentable over Guim Bernat in view of Ooi, further in view of Hower, further in view of Zhao et al. (US 20200174840 A1) hereafter Zhao.
Regarding claim 4, Guim Bernat in view of Ooi, further in view of Hower teach the system of claim 1. Hower teaches:
allocation of portions of resource devices (Paragraph 25; “each of the allocation indicators 114(0)-114(C), 114′(0)-114′(C) for a given one of the resource clients 106(0)-106(C) may vary across different partitions 108(0)-108(P). As a result, a resource client such as the resource client 106(0) may be allocated different portions of each of the partitions 108(0)-108(P). By interpolating the different allocation indicators 114(0)-114(C), 114′(0)-114′(C), a higher allocation resolution may be attained, thus enabling a smaller portion of the partitioned resource 104 to be allocated to each of the resource clients 106(0)-106(C) if desired.”).
Guim Bernat in view of Ooi, further in view of Hower does not teach wherein the first resource device is a processing system, and wherein the first portion of the first resource device is a first core of the processing system, and the second portion of the first resource device is a second core of the processing system.
However, Zhao teaches:
wherein the first resource device is a processing system, and wherein the first portion of the first resource device is a first core of the processing system, and the second portion of the first resource device is a second core of the processing system (Paragraph 82; where the GPU device corresponds to the first resource device which may have a task be concurrently executed on the given GPU device using different regions (threads, cores) of the given GPU device).
Guim Bernat, Ooi, Hower, and Zhao are considered to be analogous to the claimed invention because they are in the same field of resource orchestration. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Guim Bernat in view of Ooi, further in view of Hower to incorporate the teachings of Zhao and have the first resource device be a processing system split into different portions. A person of ordinary skill in the art would have been motivated to make this combination by the need to split resources with particularly high computational power for purposes of resource optimization.
Claim 10 recites similar limitations as those of claim 4, directed towards a system. Claim 10 is rejected for similar reasons as those of claim 4.
Claim 17 recites similar limitation as those of claim 4, directed towards a method. Claim 17 is rejected for similar reasons as those of claim 4.
Claims 13 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Guim Bernat in view of Ooi, further in view of Hower, further in view of Saxena et al. (US 20160117498 A1) hereafter Saxena.
Regarding claim 13, Guim Bernat in view of Ooi, further in view of Hower teach the IHS of claim 7. Guim Bernat teaches:
A LCS (Paragraphs 92-96; “example computing device includes the example pooled accelerators platform 1014 with pooled accelerator resources”, and may include “pooled memory platform with pooled memory resources”, in which “the pooled QoS controller 1012... interfaces with the pooled memory platform” and can provide “pooled memory information for servicing a service request”. Pooled accelerator and memory resources are monitored and allocated by the pooled QoS controller for servicing requests. The system forms a computing configuration based on logically selected pooled resources, thereby corresponding to a logically composed system.).
Hower teaches:
allocation of portions of resource devices (Paragraph 25; “each of the allocation indicators 114(0)-114(C), 114′(0)-114′(C) for a given one of the resource clients 106(0)-106(C) may vary across different partitions 108(0)-108(P). As a result, a resource client such as the resource client 106(0) may be allocated different portions of each of the partitions 108(0)-108(P). By interpolating the different allocation indicators 114(0)-114(C), 114′(0)-114′(C), a higher allocation resolution may be attained, thus enabling a smaller portion of the partitioned resource 104 to be allocated to each of the resource clients 106(0)-106(C) if desired.”).
Guim Bernat in view of Ooi, further in view of Hower does not teach monitoring access to the first portion of the first resource device and, in response, detect that a second LCS is attempting to access the first portion of the resource device; and generate, in response to detecting that the second LCS is attempting to access the first portion of the first resource device, and unauthorized access attempt report.
However, Saxena teaches:
monitor access to the first portion of the first resource device and, in response, detect that the second system is attempting to access the first resource device (Paragraph 140; the isolated region of memory 136 corresponds to the first portion of the first resource device in which the memory monitor 800 continuously monitors access attempts. Saxena further discloses “unauthorized access” attempts, corresponding to the detection of the second system access attempts);
and generate, in response to detecting that the second system is attempting to access the first portion of the first resource device, an unauthorized access attempt report (Paragraph 140; example reporter generating an alert in response to an attempt to access unauthorized resources corresponds to the applicant’s unauthorized access report).
Guim Bernat, Ooi, Hower, and Saxena are considered to be analogous to the claimed invention because they are in the same field of resource orchestration. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Guim Bernat in view of Ooi, further in view of Hower to incorporate the teachings of Saxena and monitor access to resource devices, sending unauthorized access attempt reports if any such actions occur. A person of ordinary skill in the art would be motivated by wanting to adhere to standard computer security practices to detect threats, ensure compliance, and protect sensitive data as disclosed in Saxena.
Claim 20 recites similar limitation as those of claim 13, directed towards a method. Claim 20 is rejected for similar reasons as those of claim 13.
Response to Arguments
Applicant's arguments filed 11/17/2025 have been fully considered but some are not persuasive.
Applicant’s arguments are summarized below:
The references, alone or in any combination, do not teach the limitations of amended claims 1, 7, and 14.
The combination of Ooi and Stone does not appear to teach the LCSes of the claims provided by a BMS system that use different portions of the same resource in the BMS simultaneously.
Allocations of portions of a storage unit to different tasks does not teach the allocation of different portions of a resource in a BMS system to different LCSes provided by that BMS system.
The monitoring of pods to determine whether they meet a networking SLA in Sun cannot be characterized as teaching receiving telemetry and analytics data from a resource device during the use of different portions of that resource device by different LCSes, and the use of that data to determine whether the different portions satisfy different SLAs for different LCSes.
Dependent claims are submitted as allowable for at least the above reasons.
The Examiner respectfully disagrees with B, D, and E.
The Examiner agrees that the previous prior art of record does not teach the limitations of amended independent claims 1, 7, and 14. Therefore, the previous rejections under 35 U.S.C. 103 have been withdrawn. However, upon further consideration, a new ground(s) of rejection is applied in view of Guim Bernat, Ooi, and Hower.
Applicant’s arguments with respect to Ooi and Stone not teaching the LCSes of the claims provided by a BMS system that use different portions of the same resource in the BMS simultaneously have been considered. Upon review, the limitation is adequately disclosed when Ooi and Stone are considered in combination. However, for clarity and completeness, the Examiner has remapped the claim elements to Guim Bernat (LCS), Ooi (BMS system), and Hower (simultaneously providing portions of the same resource device) to explicitly show where each limitation is found in the newly applied references in light of the amendments.
Applicant’s arguments with respect to King have been considered. Upon review, the Examiner agrees that the mapping of King’s allocation of portions of storage devices is problematic due to the BMS-native resource devices presenting issues that are fundamentally different from those of storage devices. For clarity, the Examiner has remapped the particular limitation to Hower (explicitly teaching simultaneous allocations of portions of a cache).
Applicant’s arguments with respect to claim 5 have been considered but are moot because the new ground of rejection does not rely on Sun applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
Independent claims 1, 7, and 14 remain rejected for the reasons stated above. Therefore, contrary to Applicant's arguments, because the dependent claims depend from an unpatentable claim and does not add limitations that overcome the rejection, it likewise remains rejected.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. Jackson (US 20120179824 A1) teaches a system and method of allocating cloud computing resources across multiple users utilizing an associated SLA.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to KENNETH P TRAN whose telephone number is (571)272-6926. The examiner can normally be reached M-TH 4:30 a.m. - 12:30 p.m. PT, F 4:30 a.m. - 8:30 a.m. PT, or at Kenneth.Tran@uspto.gov.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, April Blair can be reached at (571) 270-1014. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/KENNETH P TRAN/ Examiner, Art Unit 2196
/APRIL Y BLAIR/ Supervisory Patent Examiner, Art Unit 2196