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 .
DETAILED ACTION
Claims 1-5, 7-9, 11-12, and 14-21 are pending. Claims 6, 10, and 13 are canceled by Applicant. Claim 21 is newly added by Applicant.
Examiner Notes
Examiner cites particular paragraphs and/or columns and lines in the references as applied to Applicant’s claims 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 apply as well. It is respectfully requested that, in preparing responses, the Applicant fully consider the references in 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. The prompt development of a clear issue requires that the replies of the Applicant meet the objections to and rejections of the claims. Applicant should also specifically point out the support for any amendments made to the disclosure. See MPEP § 2163.06.
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
As per claim 1, the examiner recommends that Applicant amend the claim in ll. 19 from “in response to determining from” to “based on”.
As per claim 7, the examiner recommends that Applicant amend the claim from “in response to determining that the first NUMA node does not meet” to “based on the first NUMA node not meeting”.
As per claim 8, the examiner recommends that Applicant amend the claim to avoid the recitation of “determining that the second NUMA node meets the particular policy of the endpoint application”.
As per claims 20-21, the examiner recommends that Applicant amend the claims in the same fashion as for claim 1.
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, 5-9, 11-12, 14, and 20-21 are rejected under 35 U.S.C. 103 as being unpatentable over
Alexis et al. (US 2021/0320901) (hereinafter Alexis as previously cited) in view of
Krasilnikov et al. (US 11,625,175) (hereinafter Krasilnikov) in view of
Kim et al. (US 2017/0371777) (hereinafter Kim).
As per claim 1, Alexis primarily teaches the invention as claimed including a method for processing data message flows ([0025] flow processing module may control a flow of data packets through the virtual firewall) using a plurality of non-uniform memory access (NUMA) nodes of a processing system ([0030] a quantity of non-uniform memory access (NUMA) nodes that will be associated with the virtual firewall), the method comprising:
at a load balancing application associated with a first NUMA node of the plurality of NUMA nodes ([0030] whether an Irqbalance is enabled/disabled e.g., a process that balances the CPU load generated by interrupts across a set of CPUs),
receiving, at the first NUMA node from a network interface card (NIC) associated with the first NUMA node ([0119] determining that a network interface card port associated with the virtual firewall is associated with a non-uniform memory access (NUMA) node associated with the virtual firewall, wherein the virtual firewall is being to be deployed further based on the network interface card port being associated with the NUMA node associated with the virtual firewall), a data message flow destined for an endpoint application ([0067] endpoint device includes one or more devices capable of receiving and/or providing information over a network, and/or capable of generating, storing, and/or processing information received and/or provided over the network and [0073] application includes one or more software applications that may be provided to or accessed by endpoint device), wherein the first NUMA node is a local NUMA node that first receives the data message flow through the NIC ([0025]-[0027] flow processing module may apply one or more filters/policies to the input and/or the output of a virtual network interface to control the flow of data packets through the virtual firewall); and
directing the data message flow to a second NUMA node through the processor interconnect bridge for performing, by the second NUMA node, a middlebox service operation on the data message flow ([0042] if the resource availability check is not successfully performed e.g., the host platform determines that the computing device does not satisfy the minimum requirements, the host platform may determine to deploy the virtual firewall on a different computing device, output information indicating that the computing device does not satisfy the minimum requirements, prevent the virtual firewall from being deployed on the computing device, and/or the like).
Alexis does not explicitly teach:
using a processor interconnect bridge that connects the set of processors of the NUMA node to another set of processors of another NUMA node;
collecting real-time metrics for the first NUMA node and a second NUMA node, the real- time metrics comprising CPU utilization metrics and latency metrics associated with the first NUMA node and the second NUMA node;
each NUMA node comprising a local memory and a set of processors that can access data from local memories of other NUMA nodes; and
in response to determining from the CPU utilization metrics that a CPU utilization for the first NUMA node exceeds a CPU utilization threshold or from the latency metrics that a latency of the first NUMA node exceeds a latency of the second NUMA node, the second NUMA node performing the middlebox service operation using at least one of (i) data stored at a local memory of the second NUMA node and (ii) data stored at a local memory of another NUMA node accessed through the processor interconnect bridge.
However, Krasilnikov teaches:
using a processor interconnect bridge that connects the set of processors of the NUMA node to another set of processors of another NUMA node (col. 12, ll. 37-45 the data that is copied may then be transferred over an interface to the local memory allocated to an empty slot of the NUMA node. The NUMA node may then have the CPU(s) execute the virtual resource(s) that were migrated from the NUMA node. Generally, the interface(s) may be any type of processor interconnect, such as a point-to-point processor interconnect e.g., QuickPath Interconnect, a front-side bus, etc.);
collecting real-time metrics for the first NUMA node and a second NUMA node, the real- time metrics comprising CPU utilization metrics associated with the first NUMA node and the second NUMA node (col. 15, ll. 16-22 the server may determine a utilization metric that indicates utilization of a computing resource associated with the first NUMA node. For instance, the utilization metric may indicate utilization of one or more computing resources (CPU, memory, etc.) of the NUMA node by the virtual resources at a point in time, and/or over a period of time);
each NUMA node comprising a local memory and a set of processors that can access data from local memories of other NUMA nodes (col. 6, ll. 62 to col. 7, ll. 1 the server may have a NUMA architecture that locates various subsets of system memory near subsets of the CPU cores. In a NUMA architecture, the memory access time depends on the memory location relative to the processor. That is, a processor can access its own local memory faster than non-local memory e.g., memory local to another processor and col. 11, ll. 17-21 each of the NUMA nodes may include respective local memory that are controlled by respective memory controllers. The memory controllers may each be digital circuits that manage the flow of data going to and from the respective local memories); and
in response to determining from the CPU utilization metrics that a CPU utilization for the first NUMA node exceeds a CPU utilization threshold of the second NUMA node, the second NUMA node performing the middlebox service operation using at least one of (i) data stored at a local memory of the second NUMA node and (ii) data stored at a local memory of another NUMA node accessed through the processor interconnect bridge (fig. 5, blocks 508-514 and col. 15, ll. 22-47 the server may determine that the utilization metric is greater than or equal to a threshold utilization metric where the threshold utilization metric being associated with degradation in performance of the first NUMA node running the first virtual computing resource. The server may copy data stored in the first memory slot that represents a state of the first virtual computing resource. For instance, the migration component may copy data from the local memory of the NUMA node. The server may transfer, over the interconnect, the data to a third memory slot of the second local memory of the second NUMA node. For instance, the migration component may transfer the copied data to a slot of the NUMA node. The server may cause the first virtual computing resource to run on the second NUMA node using the second CPU and a third memory slot of the second local memory).
Krasilnikov and Alexis are both concerned with NUMA nodes and are therefore combinable/modifiable. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Alexis in view of Krasilnikov because it would provide a way to determine that multiple NUMA nodes are able run a virtual resource, and select the NUMA node that has the greatest availability of computing resources for running the virtual resource. The server may then migrate the virtual resource from the overcommitted NUMA node onto the NUMA node that has availability to run the virtual resource. In this way, the server may reduce resource contention among virtual resources running on a same NUMA node. The NUMA system provides for separate memory allocations for each processor (or group of processors) in a multiprocessor system, which helps avoid the performance degradation when several processors attempt to address the same memory.
Alexis in view of Krasilnikov do not explicitly teach:
collecting real-time metrics for the first NUMA node and a second NUMA node, the real- time metrics comprising latency metrics associated with the first NUMA node and the second NUMA node; and
in response to determining from the latency metrics that a latency for the first NUMA node exceeds a latency of the second NUMA node, the second NUMA node performing the middlebox service operation using at least one of (i) data stored at a local memory of the second NUMA node and (ii) data stored at a local memory of another NUMA node accessed through the processor interconnect bridge.
However, Kim teaches:
collecting real-time metrics for the first NUMA node and a second NUMA node, the real- time metrics comprising latency metrics associated with the first NUMA node and the second NUMA node ([0004] and [0017] probing latencies of local and remote memory accesses by a latency monitor for each NUMA node); and
in response to determining from the latency metrics that a latency for the first NUMA node exceeds a latency of the second NUMA node, the second NUMA node performing the middlebox service operation using at least one of (i) data stored at a local memory of the second NUMA node and (ii) data stored at a local memory of another NUMA node accessed through the processor interconnect bridge (fig. 4; [0022] and [0026] if the latency gap between NUMA nodes is greater than a threshold latency then migrate memory pages between the NUMA nodes).
Kim and Alexis are both concerned with NUMA nodes and are therefore combinable/modifiable. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Alexis in view of Krasilnikov in view of Kim because it would provide a way to evaluate contention at NUMA nodes for process and memory placement, so that better process and memory scheduling decisions can be made in NUMA systems. Latencies of local and remote memory access are probed at each NUMA node. When there is no contention, the local memory access latency will be less than the remote memory access latency. If the contention at the local NUMA node increases, the local memory access latency may become large enough so that it becomes beneficial to allocate/rebalance memory to a remote NUMA node. The benefits of using the latency probing technique are its simplicity and accuracy.
As per claim 5, Alexis further teaches wherein the policies ([0023] routing policies) are received from a set of endpoint applications including the endpoint application ([0067] endpoint device includes one or more devices capable of receiving and/or providing information over a network, and/or capable of generating, storing, and/or processing information received and/or provided over the network and [0073] application includes one or more software applications that may be provided to or accessed by endpoint device).
As per claim 7, Alexis further teaches directing the data message flow to the second NUMA node through the processor interconnect bridge for performing, by the second NUMA node, a middlebox service operation on the data message flow in response to determining that the first NUMA node does not meet a particular policy of the endpoint application ([0023] routing policies and [0042] if the resource availability check is not successfully performed e.g., the host platform determines that the computing device does not satisfy the minimum requirements, the host platform may determine to deploy the virtual firewall on a different computing device, output information indicating that the computing device does not satisfy the minimum requirements, prevent the virtual firewall from being deployed on the computing device, and/or the like).
As per claim 8, Alexis further teaches further comprising, before directing the data message flow to the second NUMA node, determining that the second NUMA node meets the particular policy of the endpoint application ([0023] routing policies and [0042] if the resource availability check is not successfully performed e.g., the host platform determines that the computing device does not satisfy the minimum requirements, the host platform may determine to deploy the virtual firewall on a different computing device, output information indicating that the computing device does not satisfy the minimum requirements, prevent the virtual firewall from being deployed on the computing device, and/or the like).
As per claim 9, Alexis further teaches wherein the middlebox service operation is one of a firewall operation, a load balancing operation, and a network address translation service operation ([0042] resource availability check may be performed to determine that the computing device on which the virtual firewall is to be implemented satisfies certain minimum requirements for implementing the virtual firewall. For example, the resource availability check may determine whether NUMA socket/hyper-threading is enabled/disabled, whether the virtual firewall is to be implemented on a NUMA associated with a NIC port, and/or the like).
As per claim 11, Krasilnikov teaches wherein the processor interconnect bridge is one of a QuickPath Interconnect bridge or an Ultra Path Interconnect Bridge (col. 12, ll. 37-45 the data that is copied may then be transferred over an interface to the local memory allocated to an empty slot of the NUMA node. The NUMA node may then have the CPU(s) execute the virtual resource(s) that were migrated from the NUMA node. Generally, the interface(s) may be any type of processor interconnect, such as a point-to-point processor interconnect e.g., QuickPath Interconnect, a front-side bus, etc.).
As per claim 12, Alexis further teaches wherein the data message flow is directed to the second NUMA node for performing the middlebox service operation and for forwarding the data message flow to the endpoint application ([0026] packet forwarding module may control the forwarding of data packets to a destination device. For example, the packet forwarding module may apply one or more routing policies to the input and/or the output of a virtual network interface to forward data packets processed by the virtual firewall toward a destination device).
As per claim 14, Krasilnikov teaches wherein the local memory of the other NUMA node is a local memory of the first NUMA node (col. 6, ll. 62 to col. 7, ll. 1 the server may have a NUMA architecture that locates various subsets of system memory near subsets of the CPU cores. In a NUMA architecture, the memory access time depends on the memory location relative to the processor. That is, a processor can access its own local memory faster than non-local memory e.g., memory local to another processor and col. 11, ll. 17-21 each of the NUMA nodes may include respective local memory that are controlled by respective memory controllers. The memory controllers may each be digital circuits that manage the flow of data going to and from the respective local memories).
As per claim 19, Alexis further teaches wherein the load balancing application is a first instance of a distributed load balancing application implemented by a plurality of instances operating on the plurality of NUMA nodes ([0030] whether an Irqbalance is enabled/disabled e.g., a process that balances the CPU load generated by interrupts across a set of CPUs and [0078] two or more devices may be implemented as multiple, distributed devices).
As per claim 20, it has similar limitations as claim 1 and is therefore rejected using the same rationale.
As per claim 21, it has similar limitations as claim 1 and is therefore rejected using the same rationale.
Claim 2 is rejected under 35 U.S.C. 103 as being unpatentable over Alexis in view of Krasilnikov in view of Kim in view of Saripalli (US 2012/0331227) (as previously cited).
As per claim 2, Alexis in view of Krasilnikov in view of Kim do not explicitly teach applying policies to data message flows, such that a first set of higher priority flow types is assigned to the first NUMA node and a second set of lower priority flow types is assigned to the second NUMA node.
However, Saripalli teaches applying policies to data message flows, such that a first set of higher priority flow types is assigned to the first NUMA node and a second set of lower priority flow types is assigned to the second NUMA node ([0002] employ data center bridging protocols to control and prioritize different types and/or flows of network traffic among the nodes).
Saripalli and Alexis are both concerned with computer node management and are therefore combinable/modifiable. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Alexis in view of Krasilnikov in view of Kim in view of Saripalli because it would provide a way of appropriately selecting and/or adjusting the criteria and/or values thereof upon which one or more policies may be based to reflect and/or implement the respective priorities and/or the relative priorities established among the network traffic. Accordingly, and advantageously, one or more policies may result in, at least in part, a relatively lower cache miss probability occurring in connection with respective information associated with relatively higher priority network traffic compared to a relatively higher cache miss probability that may occur in connection with other respective information that may be associated with relatively lower priority network traffic. This may result, for example, from appropriate reduction in latencies in processing higher priority traffic compared to lower priority traffic.
Claim 3-4 are rejected under 35 U.S.C. 103 as being unpatentable over Alexis in view of Krasilnikov in view of Kim in view of Saripalli in view of Das et al. (US 2007/0149129) (hereinafter Das as previously cited).
As per claim 3, Alexis in view of Krasilnikov in view of Kim in view of Saripalli do not explicitly teach wherein the policies specify latency requirements of different flows, and the first set of higher priority flow types comprise flows requiring a low latency while the second set of lower priority flow types comprise flows that do not require a low latency.
However, Das teaches wherein the policies specify latency requirements of different flows, and the first set of higher priority flow types comprise flows requiring a low latency while the second set of lower priority flow types comprise flows that do not require a low latency (fig. 40 different data flow types are associated with different latencies).
Das and Alexis are both concerned with computer node management and are therefore combinable/modifiable. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Alexis in view of Krasilnikov in view of Kim in view of Saripalli in view of Das because it would provide a way to efficiently communicate the varying needs of individual wireless terminals for uplink traffic channel resources. This can achieve reporting diversity while accommodating small information report size and would facilitate a wide range of quantization schemes such that a particular quantization scheme well suited to a wireless terminal at a particular time can be selected and used by the wireless terminal to communicate backlog information. It would also provide for efficient reporting to make use of available information already being communicated between the wireless terminal and base station such as quality information, thus expanding reporting options while retaining a small report bit size.
As per claim 4, Alexis in view of Krasilnikov in view of Kim in view of Saripalli do not explicitly teach wherein the policies specify bandwidth requirements of different flows, and the first set of higher priority flow types comprise flows requiring a high bandwidth, while the second set of lower priority flow types comprise flows that do not require a high bandwidth.
However, Das teaches wherein the policies specify bandwidth requirements of different flows, and the first set of higher priority flow types comprise flows requiring a high bandwidth, while the second set of lower priority flow types comprise flows that do not require a high bandwidth (fig. 40 different data flow types are associated with different bandwidths).
Das and Alexis are both concerned with computer node management and are therefore combinable/modifiable. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Alexis in view of Krasilnikov in view of Kim in view of Saripalli in view of Das because it would provide a way to customize and/or optimize request queue mapping to match the different types of data being communicated via uplink traffic channel segments at any time.
Claim 15 is rejected under 35 U.S.C. 103 as being unpatentable over Alexis in view of Krasilnikov in view of Kim in view of Kancherla et al. (US 2019/0036819) (hereinafter Kancherla as previously cited).
As per claim 15, Alexis in view of Krasilnikov in view of Kim do not explicitly teach creating a record associating the data message flow with the second NUMA node.
However, Kancherla teaches creating a record associating the data message flow with the second NUMA node ([0036] each forwarding table entry of forwarding table records an association between a particular data message flow and a particular set of service nodes).
Kancherla and Alexis are both concerned with computing node management and are therefore combinable/modifiable. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Alexis in view of Krasilnikov in view of Kim in view of Kancherla because it would provide for a set of service nodes in an active-active service node cluster in conjunction with a host computer hosting a destination data compute node to improve the efficiency of directing a reverse-flow data message to a service node storing state information for the flow to which the data message belongs.
Claims 16-17 are rejected under 35 U.S.C. 103 as being unpatentable over Alexis in view of Krasilnikov in view of Kim in view of Kancherla in view of Maloy (US 2019/0014025) (as previously cited).
As per claim 16, Alexis in view of Krasilnikov in view of Kim in view of Kancherla do not explicitly teach storing the record in the local memory of the second NUMA node.
However, Maloy teaches storing the record in the local memory of the second NUMA node ([0041] each node maintains and stores a domain record of its local domain in its local memory. Each domain record contains the identifiers of all member nodes of its local domain).
Maloy and Alexis are both concerned with computing node management and are therefore combinable/modifiable. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Alexis in view of Krasilnikov in view of Kim in view of Kancherla in view of Maloy because it would provide a network node monitoring method performed by each node. The nodes can be partitioned into domains according to a sorted order. The domains include a local domain in which the node is located and one or more remote domains. Each remote domain has a domain head designated to monitor member nodes in the remote domain. The node sends probes at a given frequency to actively monitored nodes that include all other member nodes in the local domain and domain heads in the remote domains. The node then determines whether each of the actively monitored nodes is up based on replies received from the actively monitored nodes in response to the probes.
As per claim 17, Maloy teaches storing the record in each of the plurality of NUMA nodes ([0041] each node maintains and stores a domain record of its local domain in its local memory. Each domain record contains the identifiers of all member nodes of its local domain).
Claim 18 is rejected under 35 U.S.C. 103 as being unpatentable over Alexis in view of Krasilnikov in view of Kim in view of Kancherla in view of Maloy in view of Bas et al. (US 11,134,032) (hereinafter Bas as previously cited).
As per claim 18, Maloy teaches wherein the record specifies a NUMA node ID identifying the second NUMA node ([0041] each node maintains and stores a domain record of its local domain in its local memory. Each domain record contains the identifiers of all member nodes of its local domain).
Alexis in view of Krasilnikov in view of Kim in view of Kancherla in view of Maloy do not explicitly teach wherein the record specifies a flow identifier (ID) identifying the data message flow.
However, Bas teaches wherein the record specifies a flow identifier (ID) identifying the data message flow (col. 8, ll. 38-39 different records identify the different data message flows that should be stored).
Bas and Alexis are both concerned with computing node management and are therefore combinable/modifiable. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Alexis in view of Krasilnikov in view of Kim in view of Kancherla in view of Maloy in view of Bas because it would provide a way for tuning a virtual firewall so that a host platform may deploy the virtual firewall on the computing device. In this way, the host platform optimizes a performance and/or a latency of the virtual firewall by automatically tuning the virtual firewall prior to the virtual firewall being deployed. Also, by automatically tuning the virtual firewall, the host platform may conserve computing resources that would have otherwise been used to troubleshoot an improperly tuned virtual firewall in an attempt to improve performance.
Response to Arguments
Applicant's arguments have been considered but are moot in view of the new grounds of rejection necessitated by Applicant’s amendments because the new grounds of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
Citation of Relevant Prior Art
The prior art made of record and not relied upon is considered pertinent to Applicant's disclosure:
U (US 2015/0281276) disclose monitoring compliance with security policies for computer networks.
Sze et al. (US 2020/0236043) disclose receiving data message flows at endpoint applications.
McGrath et al. (US 2014/0068611) disclose a distributed load balancing application among nodes.
Masputra et al. (US 2022/0094763) disclose receiving policies among endpoint applications.
Luo (US 2020/0228451) disclose enhanced network stacking.
Filsfils et al. (US 2018/0109450) disclose creating and maintaining segment routed traffic engineering policies via border gateway protocols.
Curewitz et al. (US 2021/0081326) disclose mapping non-typed memory accesses to typed memory accesses.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Adam Lee whose telephone number is (571) 270-3369. The examiner can normally be reached on M-TH 8AM-5PM.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Pierre Vital can be reached on 571-272-4215. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from Patent Center. Status information for published applications may be obtained from Patent Center. Status information for unpublished applications is available through Patent Center for authorized users only. Should you have questions about access to Patent Center, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free).
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) Form at https://www.uspto.gov/patents/uspto-automated-interview-request-air-form.
/Adam Lee/Primary Examiner, Art Unit 2198 June 5, 2026
Prosecution Insights