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and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114.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 March 3rd, 2026 has been entered.
Claim Status
Claims 1, 10, 13 and 17 have been amended. Claims 19-20 remain cancelled. No new claims have been added. Claims 1-18 remain pending and are ready for examination.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claim 1 rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Claim 1 recites the limitation “performing a tuning for Quality-of-Service conformity with the first storage device”. However, later in the claim the newly added claim limitation recites “wherein the QoS specification is based on a performance metric of the first storage device which is not a storage device where the tuning is performed.” These two claim limitations appear to contradict each other, and make it unclear whether the first storage device has a tuning performed on it, or does not have a tuning performed on it. The examiner will interpret the original claim limitation (performing a tuning … with the first storage device), and interpret the newly added claim limitation as merely requiring a performance metric of the first storage device. Appropriate correction is required.
Claim Rejections - 35 USC § 103
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 (i.e., changing from AIA to pre-AIA ) 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.
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.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claim(s) 1 is/are rejected under 35 U.S.C. 103 as being unpatentable over Karia et al. (US Publication No. 2018/0329626 – “Karia”) in view of Zinger et al. (US Publication No. 2025/0036286 – “Zinger”) in further view of Lee et al. (US Publication No. 2011/0149775 – “Lee”) and further in view of Tomlin et al. (US Publication No. 2017/0139823 – “Tomlin”).
Regarding claim 1, Karia teaches A storage device connected with a host, a first storage, the storage device comprising: at least one nonvolatile memory device configured to store or read data; (Karia paragraph [0028], Auxiliary connections may be provided to the data storage arrangement to allow additional options for inputting data directly to the data storage arrangement without interfacing with the host. The non-volatile memory device may be a NAND flash memory, see Karia paragraph [0076], the arrangement may be configured wherein the flash memory is a vertical NAND flash memory) and at least one controller configured to: control the at least one nonvolatile memory device, (Karia paragraph [0030], a controller is provided to control actions of the data storage arrangement as required by the host. The controller may also be configured to perform maintenance activities for the data storage arrangement to allow efficient use) perform at least one workload of a plurality of workloads, based on at least one parameter, (Karia paragraph [0011], In one non-limiting embodiment, an arrangement to perform supervised learning with a closed loop feedback for a solid state drive is disclosed comprising a workload detection engine configured to receive an input command from a host, a command dispatcher configured to receive the input command from the host, a flash memory with a connection for receiving and sending data, a command processor connected to the command dispatcher, the command processor configured to perform commands provided by the command dispatcher, the command processor connected to the flash memory through the connection, an engine configured to receive a set of data from the workload detection engine, the engine configured to calculate throttling latencies for the solid state drive and a host responder connected to the command dispatcher and the engine, the host responder configured to respond to the host with completed commands. A workload may be performed based on a given parameter, such as a latency) perform a tuning for improvement of a performance and a Quality-of-Service (QoS) conformity with a first storage device associated with the workload, (Karia paragraph [0011], the command processor configured to perform commands provided by the command dispatcher, the command processor connected to the flash memory through the connection, an engine configured to receive a set of data from the workload detection engine, the engine configured to calculate throttling latencies for the solid state drive and a host responder connected to the command dispatcher and the engine, the host responder configured to respond to the host with completed commands. The workloads for a storage device (i.e., SSD) may be adjusted based on a throttling latency, also see Karia paragraph [0027], Aspects of the present disclosure relate to computer operations and computer storage and specifically, performing supervised learning with closed loop feedback to improve IO consistency of solid state drives. In the embodiments described, a data storage arrangement is connected to the host system. The function of the data storage arrangement is to accept data and store the data until needed again by a user or the host. The data storage arrangement may be configured to accept bursts of data, depending on the computer process performed, therefore the data storage arrangement is configured with multiple memory units that provide various states of usage) and wherein the at least one controller is further configured to individually perform the tuning for each of the plurality of workloads that are different kinds (Karia paragraph [0077], a method for improving an input and an output consistency of a solid state drive is disclosed comprising: calculating a minimum system imposed read and write latency for the solid state drive; calculating an expected read latency and an expected write latency for the solid state drive based on the minimum system imposed read and write latency; calculating an amplification coefficient for write operations and an amplification coefficient for read operations based upon a model, calculating a final read latency and a final write latency for the solid state drive based upon the calculated expected read latency and the calculated expected write latency and the amplification coefficient for write operations and the amplification coefficient for read operations and operating the solid state drive according to the final read latency and the write latency. The tuning adjustment for the memory workloads may be different based on workload type, such as reading and writing operations).
Karia does not teach A storage device connected with a host, a first storage device, perform a tuning for… a Quality-of-Service (QoS) conformity, wherein the storage device supports a first specification and the first storage device supports a second specification that is different from the first specification, and wherein the tuning for improvement of the performance and the QoS conformity is performed to maintain performance metrics of the storage device and the first storage device within a preset range based on the QoS specification from the host, wherein the first specification and the second specification are hardware or software specifications that are different from the QoS conformity and the QoS specification, and wherein the QoS specification is based on a performance metric of the first storage device which is not a storage device where the tuning is performed.
However, Zinger teaches A storage device connected with a host, a first storage device (Zinger paragraph [0002], Data storage systems are arrangements of hardware and software that are coupled to non-volatile data storage drives, such as solid state drives and/or magnetic disk drives. The data storage system services host I/O commands received from physical and/or virtual host machines (“hosts”). The host I/O commands received by the data storage system specify host data that is written and/or read by the hosts. The data storage system executes software that processes the host I/O commands by performing various data processing tasks to efficiently organize and persistently store the host data in the non-volatile data storage drives of the data storage system. A host may be connected to a plurality of storage drives also connected to each other) perform a tuning for… a Quality-of-Service (QoS) conformity (Zinger paragraph [0006], the command descriptor for the command is subsequently dequeued from the QoS wait queue at a time when the command can be completed in conformance with the QoS policy. Zinger teaches adjusting the workload commands to conform with QoS standards).
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to combine the teachings of Karia with those of Zinger. Zinger teaches adjusting a workload command to satisfy a QoS standard, which is a common method of more efficiently operating a data storage system (see Zinger paragraph [0002], Data storage systems are arrangements of hardware and software that are coupled to non-volatile data storage drives, such as solid state drives and/or magnetic disk drives. The data storage system services host I/O commands received from physical and/or virtual host machines (“hosts”). The host I/O commands received by the data storage system specify host data that is written and/or read by the hosts. The data storage system executes software that processes the host I/O commands by performing various data processing tasks to efficiently organize and persistently store the host data in the non-volatile data storage drives of the data storage system).
Karia in view of Zinger does not teach wherein the storage device supports a first specification and the first storage device supports a second specification that is different from the first specification, and wherein the tuning for improvement of the performance and the QoS conformity is performed to maintain performance metrics of the storage device and the first storage device within a preset range based on the QoS specification from the host, wherein the first specification and the second specification are hardware or software specifications that are different from the QoS conformity and the QoS specification, and wherein the QoS specification is based on a performance metric of the first storage device which is not a storage device where the tuning is performed.
However, Lee teaches wherein the tuning for improvement of the performance and the QoS conformity is performed to maintain performance metrics of the storage device and the first storage device within a preset range based on the QoS specification (Lee paragraphs [0047-0048], The media quality comparing/analyzing module 240 may obtain a QoS parameter associated with a quality deterioration by comparing and analyzing the QoE measured by the MQMS 120 with the QoE predicted by the media quality evaluating module 230, and may calculate a QoS parameter adjustment value. In this example, when a quality deterioration in the QoE measured by the MQMS 120 is within a predetermined range of a quality deterioration in the QoE predicted by the media quality evaluating module 230, the media quality comparing/analyzing module 240 may calculate a QoS parameter associated with a media quality item where a quality deterioration is detected, a relative contribution level, and the QoS parameter adjustment value. The tuning for the performance may be maintained within a preset range based on determined performance metrics).
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to combine the teachings of Karia and Zinger with those of Lee. Lee teaches performing adjustments/tuning for improvement of performance based on QoS specifications, which allows the memory system to upkeep a static/consistent level of quality and prevent declines in user experience (i.e., see Lee paragraphs [0064-0065], According to example embodiments, the service QoE predicting and managing system may predict a change in a user's QoE based on a change in a QoS index, may determine a cause of the quality deterioration by comparing and analyzing the predicted QoE with a QoE measured in a user terminal, and may dynamically control, based on the obtained cause, a sub-transmission network and a service. According to example embodiments, the service QoE predicting and managing system may dynamically control a sub-transmission network and a service and thus, may further enhance a QoE and may prevent unnecessary costs expended for establishing a network and maintaining the network).
Karia in view of Zinger in further view of Lee does not teach wherein the storage device supports a first specification and the first storage device supports a second specification that is different from the first specification, wherein the first specification and the second specification are hardware or software specifications that are different from the QoS conformity and the QoS specification, and wherein the QoS specification is based on a performance metric of the first storage device which is not a storage device where the tuning is performed.
However, Tomlin teaches wherein the storage device supports a first specification and the first storage device supports a second specification that is different from the first specification, wherein the first specification and the second specification are hardware or software specifications that are different from the QoS conformity and the QoS specification (Tomlin paragraph [0008], Efficient and effective multimode storage devices that can include multiple different types of address spaces that enable different storage space activities are described. A multimode selective underlying exposure storage device can enable selective exposure of underlying aspects of the storage device. In one embodiment, a distributed storage system comprises: a plurality of appliances, a distributed multimode storage management coordinator, and a communication mechanism for communicating messages between the plurality of multimode storage management systems, including distributed multimode storage management messages. A first one of the plurality of appliances can include: a plurality of storage devices (SSD) that have a first storage partition including a first type of interface and a first information storage region configured to store a first type of information and a second storage partition including a selective underlying exposure (SUE) interface and a second information storage region that stores a second type of information, wherein the SUE interface exposes an aspect of the second information storage region. The storage devices can include different specifications regarding address spaces and different management systems, as well as different hardware configurations, independent of the QoS factors) and wherein the QoS specification is based on a performance metric of the first storage device which is not a storage device where the tuning is performed (Tomlin paragraph [0181], The quality of service manager (QoS) 2116 defines quality of service policies based on system resource provisioning levels and latency measurements. The quality of service manager 2116 implements multiple queues to service different quality of service policy pools. With regard to latency-based policies, the quality of service manager 2116 implements timestamps on queue entries. The quality of service manager 2116 monitors various queue parameters and selects requests to ensure the policies are not violated. At the request of the flow control manager 2114, the quality of service manager 2116 throttles down traffic on provisioning-based policy queues. Tomlin may use a QoS manager to set a particular QoS policy dependent on performance metrics such as latency).
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to combine the teachings of Karia, Zinger and Lee with those of Tomlin. Tomlin teaches having distinct specifications for hardware/software configurations independent of QoS factors, which can allow for additional flexibility regarding storage management/function multimode design (i.e., see Tomlin paragraphs [0065], Efficient and effective multimode storage approaches that can include multiple different types of address spaces and address space activities are described. In one embodiment, a multimode selective underlying exposure (SUE) storage device enables selective exposure of some underlying aspects of the storage device while not exposing other underlying aspects. A multimode storage and SUE approach can facilitate both improved performance while limiting complexity to a manageable scope. In one exemplary implementation, an underlying aspect of a physical address space is selectively exposed. An overall storage hierarchical approach can be implemented and underlying aspects from one hierarchical level are selectively exposed to another hierarchical level. The selective exposure can occur through address space configurations and mapping between address spaces).
Claim(s) 2-8 is/are rejected under 35 U.S.C. 103 as being unpatentable over Karia in view of Zinger in further view of Lee in further view of Tomlin as applied to claim 1 above, and further in view of Gerhart et al. (US Publication No. 2019/0227920 – “Gerhart”).
Regarding claim 2, Karia in view of Zinger in further view of Lee in view of Tomlin in further view of Gerhart teaches The storage device of claim 1, wherein the at least one controller is further configured to: perform a machine learning-based tuning about the at least one parameter for the each of the plurality of workloads that are the different kinds, (Karia paragraph [0077], a method for improving an input and an output consistency of a solid state drive is disclosed comprising: calculating a minimum system imposed read and write latency for the solid state drive; calculating an expected read latency and an expected write latency for the solid state drive based on the minimum system imposed read and write latency; calculating an amplification coefficient for write operations and an amplification coefficient for read operations based upon a model, calculating a final read latency and a final write latency for the solid state drive based upon the calculated expected read latency and the calculated expected write latency and the amplification coefficient for write operations and the amplification coefficient for read operations and operating the solid state drive according to the final read latency and the write latency. The tuning adjustment for the memory workloads may be different based on workload type, such as reading and writing operations, the tuning can be done by machine learning based methods, see Karia paragraph [0008], There is a further need to provide methods that will automatically limit performance losses, as above, that may be based upon machine learning techniques, to limit the overall variations in performance capabilities) and perform the tuning until a first difference between the performance measured in a first process of performing the at least one workload and a target performance reaches a first preset range or until a second difference between a QoS measured in a second process of performing the at least one workload and a target QoS reaches a second preset range (Gerhart paragraph [0012], means for detecting a workload to be accomplished by the solid state drive, means for loading initial starting values for an automatic performance tuning algorithm, means for configuring a command performance statistics monitor to measure workload input and output performance, means for measuring performance of the solid state drive with the command performance statistics monitor, means for comparing the performance measurement of the solid state drive with the at least one performance profile target and means for adjusting performance of the solid state drive through the automatic performance tuning algorithm when the comparing of the performance measurement of the solid state drive with the at least one performance profile target indicates that the performance of the solid state drive is less than the at least one performance profile target. The tuning of a workload may continue until the measured performance is at least a preset level as compared to an ideal target performance).
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to combine the teachings of Karia, Zinger, Lee and Tomlin with those of Gerhart. Gerhart teaches performing tuning until a measured performance of a workload has reached a preset level, which allows for automatic tuning to a certain level to optimize performance efficiency (see Gerhart paragraph [0005], Conventional computers, while they are dynamic devices, do not provide the ability to fine tune specific components of the computer for maximum efficiency. There is a need, therefore, to provide a memory arrangement or device that minimizes the latency that a user will experience).
Regarding claim 3, Karia in view of Zinger in further view of Lee in further view of Tomlin and further in view of Gerhart teaches The storage device of claim 2, wherein the at least one controller is further configured to: receive, from a host device, a learning log generated through the tuning performed in a second storage device based on machine learning; (Gerhart paragraph [0039], Performance tuning log data may be returned as part of telemetry data or standard log dumps. In some embodiments, large number of logs from healthy field drives would provide good data sources for deep learning on automatic performance tuning points. Deep learning assessments may provide data-based refinement to the automatic performance tuning algorithm and initial performance tuning parameter starting points. Log data may be generated and used for the tuning performance information, which can be from the host, see Gerhart paragraph [0044], such as captured command statistics to measure performance. Workload detector 110 may monitor command reception from the host to characterize workloads and detect workload change. The performance adjustment can be targeted towards any one of a number of storage devices coupled to a host, see Gerhart paragraph [0022], Aspects of the present disclosure relate to computer operations and computer storage and specifically, performing automatic performance tuning of storage devices that are connected to a computer host) and perform the machine learning-based tuning by using the learning log for the improvement of the performance and the QoS conformity (see Zinger for QoS conformity) with the first storage device (Gerhart paragraph [0045], In embodiments, the automatic performance tuning algorithm 102 may use machine learning capabilities to provide for tuning capabilities for help in tuning over time and to help with differing computer installations. The device may assess the latest convergence results of previous algorithm runs and make automatic performance tuning algorithm parameter adjustments to improve future iterations. The automatic performance tuning algorithm parameters may include sequences and an amount of performance tuning parameter adjustments 114. The machine learning based tuning may be applied based on the learning log information).
Regarding claim 4, Karia in view of Zinger in further view of Lee in further view of Tomlin and further in view of Gerhart teaches The storage device of claim 3, wherein the at least one controller is further configured to: determine a parameter value to be used in the tuning based on performance information, QoS information, (see Zinger above for QoS information/conformity) and determine a value of the at least one parameter included in the learning log (Gerhart paragraph [0049], A queue depth value extends along bytes 1 and 2. The queue depth value described is equal to the number of outstanding commands on the drive. A transfer length is also provided for the workload performance profile descriptor. The transfer length is located along bytes 3 and 4 and is defined as the number of blocks transferred for each command. A target IOPs value is further provided in the workload performance profile mode page format along bytes 5 to 7. The target IOPs value relates to host specified I/O per second that are provided and that the device should attempt to match for that workload. The data in the workload performance profile descriptor, therefore, may be read by the algorithm with the algorithm subsequently modifying the drive parameters. The tuning can be done based on performance information associated with a particular parameter value, such as I/O per second, also see Gerhart Figs. 3 and 4).
Regarding claim 5, Karia in view of Zinger in further view of Lee in further view of Tomlin and further in view of Gerhart teaches The storage device of claim 2, wherein the target performance is set based on a second performance measured when the first storage device performs the at least one workload (Gerhart paragraph [0011], means for selecting at least one performance profile target, means for detecting a workload to be accomplished by the solid state drive, means for loading initial starting values for an automatic performance tuning algorithm, means for configuring a command performance statistics monitor to measure workload input and output performance, means for measuring performance of the solid state drive with the command performance statistics monitor, means for comparing the performance measurement of the solid state drive with the at least one performance profile target and means for adjusting performance of the solid state drive through the automatic performance tuning algorithm when the comparing of the performance measurement of the solid state drive with the at least one performance profile target indicates that the performance of the solid state drive is less than the at least one performance profile target. The target performance can be set and/or adjusted based on a measured performance of a given workload).
Regarding claim 6, Karia in view of Zinger in further view of Lee in further view of Tomlin and further in view of Gerhart teaches The storage device of claim 1, wherein the at least one controller is further configured to: receive, from a host device, a first parameter table for the performance and the QoS conformity (see Zinger above for QoS conformity) with the first storage device; and (Gerhart paragraph [0033], The data that is provided includes details regarding what types of operations are needed to be accomplished, (e.g. write or read commands), how long those commands need to be accomplished, and what types of workloads are necessary to be accomplished. The controller may be configured to determine total elapsed time between any timestamps and record information about the operating characteristics of the drive. The drive may also be configured to review operations that have occurred and fine tune operations to provide the best operational modes needed for the user. Parameters that may affect the overall characteristics of the drive may be needed latency, available power, etc. The data for parameters may be stored in a table, also see Gerhart Fig. 5) perform the tuning by changing a value of the at least one parameter based on the first parameter table (Gerhart paragraph [0033], The drive may also be configured to review operations that have occurred and fine tune operations to provide the best operational modes needed for the user. Parameters that may affect the overall characteristics of the drive may be needed latency, available power, etc. The techniques of this disclosure allow for an automatic performance tuning of the drive based upon an algorithm. The algorithm may review data that is placed in various configurations, thereby instructing the future operations of the drive. Data may be inserted into mode page format for reading by the algorithm. The mode pages may be modified, for example by a host, to allow automatic performance tuning to be accomplished and to what degree and extent the operations will be performed. The parameters in the table can be changed to tune the performance).
Regarding claim 7, Karia in view of Zinger in further view of Lee in further view of Tomlin and further in view of Gerhart teaches The storage device of claim 1, wherein the at least one controller is further configured to store a first result of performing the tuning for the performance and the QoS conformity (see Zinger for QoS conformity) with the first storage device (Gerhart paragraph [0049], A queue depth value extends along bytes 1 and 2. The queue depth value described is equal to the number of outstanding commands on the drive. A transfer length is also provided for the workload performance profile descriptor. The transfer length is located along bytes 3 and 4 and is defined as the number of blocks transferred for each command. A target IOPs value is further provided in the workload performance profile mode page format along bytes 5 to 7. The target IOPs value relates to host specified I/O per second that are provided and that the device should attempt to match for that workload. The data in the workload performance profile descriptor, therefore, may be read by the algorithm with the algorithm subsequently modifying the drive parameters. The tuning can be done based on performance information associated with a particular parameter value, such as I/O per second, also see Gerhart Figs. 3 and 4) and a second result of performing the tuning for the performance and the QoS conformity (see Zinger for QoS conformity) with a second storage device, respectively, in independent parameter tables (Gerhart paragraph [0039], Performance tuning log data may be returned as part of telemetry data or standard log dumps. In some embodiments, large number of logs from healthy field drives would provide good data sources for deep learning on automatic performance tuning points. Deep learning assessments may provide data-based refinement to the automatic performance tuning algorithm and initial performance tuning parameter starting points. Log data may be generated and used for the tuning performance information, which can be from the host, see Gerhart paragraph [0044], such as captured command statistics to measure performance. Workload detector 110 may monitor command reception from the host to characterize workloads and detect workload change. The performance adjustment can be targeted towards any one of a number of storage devices coupled to a host, see Gerhart paragraph [0022], Aspects of the present disclosure relate to computer operations and computer storage and specifically, performing automatic performance tuning of storage devices that are connected to a computer host).
Regarding claim 8, Karia in view of Zinger in further view of Lee in further view of Tomlin and further in view of Gerhart teaches The storage device of claim 7, wherein the at least one controller is further configured to store information of the first storage device or environment information of the tuning, which is associated with each of the parameter tables, as parameter metadata (Gerhart paragraph [0033], A controller included with the data storage device may be configured to control functions of the drive and record timestamps associated with events while executing commands. The controller may include circuitry that is configured to record data, in various forms, to allow the drive to alter performance based upon the data recorded. The data that is provided includes details regarding what types of operations are needed to be accomplished, (e.g. write or read commands), how long those commands need to be accomplished, and what types of workloads are necessary to be accomplished. The controller may be configured to determine total elapsed time between any timestamps and record information about the operating characteristics of the drive. The drive may also be configured to review operations that have occurred and fine tune operations to provide the best operational modes needed for the user. Parameters that may affect the overall characteristics of the drive may be needed latency, available power, etc. Timestamps and other record information can be stored regarding the workload operations, corresponding to the parameters).
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to combine the teachings of Karia, Zinger, Lee and Tomlin with those of Gerhart. Gerhart teaches performing tuning until a measured performance of a workload has reached a preset level, which allows for automatic tuning to a certain level to optimize performance efficiency (see Gerhart paragraph [0005], Conventional computers, while they are dynamic devices, do not provide the ability to fine tune specific components of the computer for maximum efficiency. There is a need, therefore, to provide a memory arrangement or device that minimizes the latency that a user will experience).
Claim(s) 9 is/are rejected under 35 U.S.C. 103 as being unpatentable over Karia in view of Zinger in further view of Lee in further view of Tomlin in further view of Gerhart as applied to claim 8 above, and further in view of Espeseth et al. (US Publication No. 2018/0067890 – “Espeseth”).
Regarding claim 9, Karia in view of Zinger in further view of Lee in further view of Tomlin in further view of Gerhart and further in view of Espeseth teaches The storage device of claim 8, wherein the at least one controller is further configured to: receive, from a host device, a request indicating transmission of a first parameter table based on the parameter metadata; (Espeseth paragraph [0039], In some examples, the threshold value may include a number of commands transferred between host device 4 and storage device 6. For example, PMM 28 may determine the number of commands transferred between host device 4 and storage device 6 since either host device 4 or storage device 6 most recently transferred the set of protocol parameters. In response to determining that the number of commands transferred since the protocol parameters were last transferred is greater than or equal to a threshold number of commands, PMM 28 may resend the set of protocol parameters. The parameter table may be sent based on parameter metadata, such as time since last transmitted) and in response to the request, send the first parameter table to the host device (Espeseth paragraph [0043], read module 26 may send the requested data to the host memory address indicated by the host device. By sending the set of protocol parameters to the host memory address indicated by the host device and then overwriting with the actual data requested by host device 4, controller 8 may inject the set of protocol parameters into the data stream while still sending the requested data to host device 4. Thus, analyzer 30 may intercept the set of protocol parameters and host device 4 may receive the requested data. The set of parameters may be transmitted to the host device).
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to combine the teachings of Karia, Zinger, Lee, Tomlin and Gerhart with those of Espeseth. Espeseth teaches transmitting the parameter set of values to the host device in response to parameter metadata, such as time since last transmitted, which can provide consistent updated parameter values to the host for further operations and reduce unnecessary transmissions (see Espeseth paragraph [0012], Rather than sending the protocol parameters only upon the initialization of the storage device, the host device or the data storage device may periodically retransmit the protocol parameters. By periodically resending the protocol parameters, the host device or the data storage device may enable the analyzer to intercept the protocol parameters in order to decode the low level PCIe data to higher level NVMe data as the data is exchanged between the host device and the storage device).
Claim(s) 10-12 is/are rejected under 35 U.S.C. 103 as being unpatentable over Karia et al. (US Publication No. 2018/0329626 – “Karia”) in view of Gerhart et al. (US Publication No. 2019/0227920 – “Gerhart”) in further view of Zinger et al. (US Publication No. 2025/0036286 – “Zinger”) and further in view of Tomlin et al. (US Publication No. 2017/0139823 – “Tomlin”).
Regarding claim 10, Karia teaches A storage device connected with a host device with a first storage device, the storage device comprising: at least one nonvolatile memory device; (Karia paragraph [0028], Auxiliary connections may be provided to the data storage arrangement to allow additional options for inputting data directly to the data storage arrangement without interfacing with the host. The non-volatile memory device may be a NAND flash memory, see Karia paragraph [0076], the arrangement may be configured wherein the flash memory is a vertical NAND flash memory) and at least one controller configured to control the at least one nonvolatile memory device (Karia paragraph [0030], a controller is provided to control actions of the data storage arrangement as required by the host. The controller may also be configured to perform maintenance activities for the data storage arrangement to allow efficient use) and to perform a workload based on at least one parameter, (Karia paragraph [0011], In one non-limiting embodiment, an arrangement to perform supervised learning with a closed loop feedback for a solid state drive is disclosed comprising a workload detection engine configured to receive an input command from a host, a command dispatcher configured to receive the input command from the host, a flash memory with a connection for receiving and sending data, a command processor connected to the command dispatcher, the command processor configured to perform commands provided by the command dispatcher, the command processor connected to the flash memory through the connection, an engine configured to receive a set of data from the workload detection engine, the engine configured to calculate throttling latencies for the solid state drive and a host responder connected to the command dispatcher and the engine, the host responder configured to respond to the host with completed commands. A workload may be performed based on a given parameter, such as a latency) and wherein, based on the first similarity and the second similarity, the at least one parameter is set individually for each workload of a plurality of workloads (Karia paragraph [0077], a method for improving an input and an output consistency of a solid state drive is disclosed comprising: calculating a minimum system imposed read and write latency for the solid state drive; calculating an expected read latency and an expected write latency for the solid state drive based on the minimum system imposed read and write latency; calculating an amplification coefficient for write operations and an amplification coefficient for read operations based upon a model, calculating a final read latency and a final write latency for the solid state drive based upon the calculated expected read latency and the calculated expected write latency and the amplification coefficient for write operations and the amplification coefficient for read operations and operating the solid state drive according to the final read latency and the write latency. The tuning adjustment for the memory workloads may be different based on workload type, such as reading and writing operations).
Karia does not teach A storage device connected with a host device with a first storage device; wherein a value of the at least one parameter is set such that: a first similarity between a first performance measured when the first storage device performs the workload and a second performance measured when the first storage device performs the workload is maximized, and a second similarity between a quality of service (QoS) index of the first storage device and a QoS index of the first storage device is maximized, wherein the storage device supports a first specification and the first storage device supports a second specification that is different from the first specification, and wherein the first specification and the second specification are hardware or software specifications that are different from the QoS conformity and the QoS specification, and wherein the QoS specification is based on a performance metric of the first storage device which is not a storage device where the tuning is performed.
However, Gerhart teaches wherein a value of the at least one parameter is set such that: a first similarity between a first performance measured when the storage device performs the workload and a second performance measured when a second storage device performs the workload is maximized, (Gerhart paragraph [0012], means for detecting a workload to be accomplished by the solid state drive, means for loading initial starting values for an automatic performance tuning algorithm, means for configuring a command performance statistics monitor to measure workload input and output performance, means for measuring performance of the solid state drive with the command performance statistics monitor, means for comparing the performance measurement of the solid state drive with the at least one performance profile target and means for adjusting performance of the solid state drive through the automatic performance tuning algorithm when the comparing of the performance measurement of the solid state drive with the at least one performance profile target indicates that the performance of the solid state drive is less than the at least one performance profile target. The tuning of a workload may continue until the measured performance is at least a preset level as compared to an ideal target performance).
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to combine the teachings of Karia with those of Gerhart. Gerhart teaches performing tuning until a measured performance of a workload has reached a preset level, which allows for automatic tuning to a certain level to optimize performance efficiency (see Gerhart paragraph [0005], Conventional computers, while they are dynamic devices, do not provide the ability to fine tune specific components of the computer for maximum efficiency. There is a need, therefore, to provide a memory arrangement or device that minimizes the latency that a user will experience).
Karia in view of Gerhart does not teach a second similarity between a quality of service (QoS) index of the storage device and a QoS index of the second storage device is maximized; wherein the storage device supports a first specification and the first storage device supports a second specification that is different from the first specification, and wherein the first specification and the second specification are hardware or software specifications that are different from the QoS conformity and the QoS specification, and wherein the QoS specification is based on a performance metric of the first storage device which is not a storage device where the tuning is performed.
However, Zinger teaches a second similarity between a quality of service (QoS) index of the storage device and a QoS index of the second storage device is maximized, (Zinger paragraph [0006], the command descriptor for the command is subsequently dequeued from the QoS wait queue at a time when the command can be completed in conformance with the QoS policy. Zinger teaches adjusting the workload commands to conform with QoS standards, which can be targeted to maximize a given QoS standard for a given storage device, see Zinger paragraph [0003], Data storage systems may enforce QoS policies provided by the hosts. In this regard, the data storage system may operate as a traffic limiter with regard to host I/O commands it receives that are directed to objects with which the QoS policies are associated. Examples of the per-object QoS policies that may be enforced by a data storage system include Maximum Bandwidth (e.g. megabytes or gigabytes per second), which defines an upper limit on the rate at which data may be transferred to and/or from an object, and Maximum I/O Rate (e.g. I/O operations per second), which defines an upper limit on the rate at which host I/O commands directed to an object may be processed).
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to combine the teachings of Karia and Gerhart with those of Zinger. Zinger teaches adjusting a workload command to satisfy a QoS standard, which is a common method of more efficiently operating a data storage system (see Zinger paragraph [0002], Data storage systems are arrangements of hardware and software that are coupled to non-volatile data storage drives, such as solid state drives and/or magnetic disk drives. The data storage system services host I/O commands received from physical and/or virtual host machines (“hosts”). The host I/O commands received by the data storage system specify host data that is written and/or read by the hosts. The data storage system executes software that processes the host I/O commands by performing various data processing tasks to efficiently organize and persistently store the host data in the non-volatile data storage drives of the data storage system).
Karia in view of Gerhart in further view of Zinger does not teach wherein the storage device supports a first specification and the first storage device supports a second specification that is different from the first specification, and wherein the first specification and the second specification are hardware or software specifications that are different from the QoS conformity and the QoS specification, and wherein the QoS specification is based on a performance metric of the first storage device which is not a storage device where the tuning is performed.
However, Tomlin teaches wherein the storage device supports a first specification and the first storage device supports a second specification that is different from the first specification, wherein the first specification and the second specification are hardware or software specifications that are different from the QoS conformity and the QoS specification (Tomlin paragraph [0008], Efficient and effective multimode storage devices that can include multiple different types of address spaces that enable different storage space activities are described. A multimode selective underlying exposure storage device can enable selective exposure of underlying aspects of the storage device. In one embodiment, a distributed storage system comprises: a plurality of appliances, a distributed multimode storage management coordinator, and a communication mechanism for communicating messages between the plurality of multimode storage management systems, including distributed multimode storage management messages. A first one of the plurality of appliances can include: a plurality of storage devices (SSD) that have a first storage partition including a first type of interface and a first information storage region configured to store a first type of information and a second storage partition including a selective underlying exposure (SUE) interface and a second information storage region that stores a second type of information, wherein the SUE interface exposes an aspect of the second information storage region. The storage devices can include different specifications regarding address spaces and different management systems, as well as different hardware configurations, independent of the QoS factors) and wherein the QoS specification is based on a performance metric of the first storage device which is not a storage device where the tuning is performed (Tomlin paragraph [0181], The quality of service manager (QoS) 2116 defines quality of service policies based on system resource provisioning levels and latency measurements. The quality of service manager 2116 implements multiple queues to service different quality of service policy pools. With regard to latency-based policies, the quality of service manager 2116 implements timestamps on queue entries. The quality of service manager 2116 monitors various queue parameters and selects requests to ensure the policies are not violated. At the request of the flow control manager 2114, the quality of service manager 2116 throttles down traffic on provisioning-based policy queues. Tomlin may use a QoS manager to set a particular QoS policy dependent on performance metrics such as latency).
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to combine the teachings of Karia, Gerhart, and Zinger with those of Tomlin. Tomlin teaches having distinct specifications for hardware/software configurations independent of QoS factors, which can allow for additional flexibility regarding storage management/function multimode design (i.e., see Tomlin paragraphs [0065], Efficient and effective multimode storage approaches that can include multiple different types of address spaces and address space activities are described. In one embodiment, a multimode selective underlying exposure (SUE) storage device enables selective exposure of some underlying aspects of the storage device while not exposing other underlying aspects. A multimode storage and SUE approach can facilitate both improved performance while limiting complexity to a manageable scope. In one exemplary implementation, an underlying aspect of a physical address space is selectively exposed. An overall storage hierarchical approach can be implemented and underlying aspects from one hierarchical level are selectively exposed to another hierarchical level. The selective exposure can occur through address space configurations and mapping between address spaces).
Regarding claim 11, Karia in view of Gerhart in further view of Zinger in further view of Tomlin teaches The storage device of claim 10, wherein the at least one nonvolatile memory device is configured to store a plurality of parameter tables, at which different values are recorded with regard to the at least one parameter, (Gerhart paragraph [0033], The data that is provided includes details regarding what types of operations are needed to be accomplished, (e.g. write or read commands), how long those commands need to be accomplished, and what types of workloads are necessary to be accomplished. The controller may be configured to determine total elapsed time between any timestamps and record information about the operating characteristics of the drive. The drive may also be configured to review operations that have occurred and fine tune operations to provide the best operational modes needed for the user. Parameters that may affect the overall characteristics of the drive may be needed latency, available power, etc. The data for parameters may be stored in a table, also see Gerhart Fig. 5) in one region of the at least one nonvolatile memory device, and wherein the at least one controller is configured to: in response to a command of the host device, activate one parameter table among the plurality of parameter tables; (Gerhart paragraph [0039], Performance tuning log data may be returned as part of telemetry data or standard log dumps. In some embodiments, large number of logs from healthy field drives would provide good data sources for deep learning on automatic performance tuning points. Deep learning assessments may provide data-based refinement to the automatic performance tuning algorithm and initial performance tuning parameter starting points. Log data may be generated and used for the tuning performance information, which can be from the host, see Gerhart paragraph [0044], such as captured command statistics to measure performance. Workload detector 110 may monitor command reception from the host to characterize workloads and detect workload change. The performance adjustment can be targeted towards any one of a number of storage devices coupled to a host, and activated to be used, see Gerhart paragraph [0022], Aspects of the present disclosure relate to computer operations and computer storage and specifically, performing automatic performance tuning of storage devices that are connected to a computer host) and perform the workload based on the value of the at least one parameter (Gerhart paragraph [0011], means for selecting at least one performance profile target, means for detecting a workload to be accomplished by the solid state drive, means for loading initial starting values for an automatic performance tuning algorithm, means for configuring a command performance statistics monitor to measure workload input and output performance, means for measuring performance of the solid state drive with the command performance statistics monitor, means for comparing the performance measurement of the solid state drive with the at least one performance profile target and means for adjusting performance of the solid state drive through the automatic performance tuning algorithm when the comparing of the performance measurement of the solid state drive with the at least one performance profile target indicates that the performance of the solid state drive is less than the at least one performance profile target. The target performance can be set and/or adjusted based on a measured performance of a given workload).
Regarding claim 12, Karia in view of Gerhart in further view of Zinger in further view of Tomlin teaches The storage device of claim 10, wherein the at least one parameter comprises a plurality of parameters, wherein the at least one nonvolatile memory device is configured to store a parameter table, at which values of the plurality of parameters maximizing the first similarity and the second similarity associated with the workload are recorded, (Gerhart paragraph [0012], means for detecting a workload to be accomplished by the solid state drive, means for loading initial starting values for an automatic performance tuning algorithm, means for configuring a command performance statistics monitor to measure workload input and output performance, means for measuring performance of the solid state drive with the command performance statistics monitor, means for comparing the performance measurement of the solid state drive with the at least one performance profile target and means for adjusting performance of the solid state drive through the automatic performance tuning algorithm when the comparing of the performance measurement of the solid state drive with the at least one performance profile target indicates that the performance of the solid state drive is less than the at least one performance profile target. The tuning of a workload may continue until the measured performance is at least a preset level as compared to an ideal target performance) in one region of the at least one nonvolatile memory device, and wherein, in response to a tuning command of the host device, the parameter table is generated by a machine learning-tuning (Karia paragraph [0077], a method for improving an input and an output consistency of a solid state drive is disclosed comprising: calculating a minimum system imposed read and write latency for the solid state drive; calculating an expected read latency and an expected write latency for the solid state drive based on the minimum system imposed read and write latency; calculating an amplification coefficient for write operations and an amplification coefficient for read operations based upon a model, calculating a final read latency and a final write latency for the solid state drive based upon the calculated expected read latency and the calculated expected write latency and the amplification coefficient for write operations and the amplification coefficient for read operations and operating the solid state drive according to the final read latency and the write latency. The tuning adjustment for the memory workloads may be different based on workload type, such as reading and writing operations, the tuning can be done by machine learning based methods, see Karia paragraph [0008], There is a further need to provide methods that will automatically limit performance losses, as above, that may be based upon machine learning techniques, to limit the overall variations in performance capabilities).
Claim(s) 13 is/are rejected under 35 U.S.C. 103 as being unpatentable over Karia et al. (US Publication No. 2018/0329626 – “Karia”) in view of Cady (US Publication No. 2022/0342592 – “Cady”) in further view of Tomlin et al. (US Publication No. 2017/0139823 – “Tomlin”).
Regarding claim 13, Karia teaches An operating method of a storage device, the operating method comprising: receiving a tuning request from a host device; receiving, from the host device, at least one of a target performance specification (Karia paragraph [0011], the command processor configured to perform commands provided by the command dispatcher, the command processor connected to the flash memory through the connection, an engine configured to receive a set of data from the workload detection engine, the engine configured to calculate throttling latencies for the solid state drive and a host responder connected to the command dispatcher and the engine, the host responder configured to respond to the host with completed commands. The workloads for a storage device (i.e., SSD) may be adjusted based on a throttling latency, also see Karia paragraph [0027], Aspects of the present disclosure relate to computer operations and computer storage and specifically, performing supervised learning with closed loop feedback to improve IO consistency of solid state drives. In the embodiments described, a data storage arrangement is connected to the host system. The function of the data storage arrangement is to accept data and store the data until needed again by a user or the host. The data storage arrangement may be configured to accept bursts of data, depending on the computer process performed, therefore the data storage arrangement is configured with multiple memory units that provide various states of usage) receiving a workload from the host device; (Karia paragraph [0011], In one non-limiting embodiment, an arrangement to perform supervised learning with a closed loop feedback for a solid state drive is disclosed comprising a workload detection engine configured to receive an input command from a host, a command dispatcher configured to receive the input command from the host, a flash memory with a connection for receiving and sending data, a command processor connected to the command dispatcher, the command processor configured to perform commands provided by the command dispatcher, the command processor connected to the flash memory through the connection, an engine configured to receive a set of data from the workload detection engine, the engine configured to calculate throttling latencies for the solid state drive and a host responder connected to the command dispatcher and the engine, the host responder configured to respond to the host with completed commands. A workload may be performed based on a given parameter, such as a latency) controlling a nonvolatile memory to perform the workload based on a parameter (Karia paragraph [0011], In one non-limiting embodiment, an arrangement to perform supervised learning with a closed loop feedback for a solid state drive is disclosed comprising a workload detection engine configured to receive an input command from a host, a command dispatcher configured to receive the input command from the host, a flash memory with a connection for receiving and sending data, a command processor connected to the command dispatcher, the command processor configured to perform commands provided by the command dispatcher, the command processor connected to the flash memory through the connection, an engine configured to receive a set of data from the workload detection engine, the engine configured to calculate throttling latencies for the solid state drive and a host responder connected to the command dispatcher and the engine, the host responder configured to respond to the host with completed commands. A workload may be performed based on a given parameter, such as a latency) and changing a value of the parameter; (Karia paragraph [0011], the command processor configured to perform commands provided by the command dispatcher, the command processor connected to the flash memory through the connection, an engine configured to receive a set of data from the workload detection engine, the engine configured to calculate throttling latencies for the solid state drive and a host responder connected to the command dispatcher and the engine, the host responder configured to respond to the host with completed commands. The workloads for a storage device (i.e., SSD) may be adjusted based on a throttling latency, also see Karia paragraph [0027], Aspects of the present disclosure relate to computer operations and computer storage and specifically, performing supervised learning with closed loop feedback to improve IO consistency of solid state drives. In the embodiments described, a data storage arrangement is connected to the host system. The function of the data storage arrangement is to accept data and store the data until needed again by a user or the host. The data storage arrangement may be configured to accept bursts of data, depending on the computer process performed, therefore the data storage arrangement is configured with multiple memory units that provide various states of usage) and individually determining the value of the parameter for each workload of a plurality of workloads that are different kinds (Karia paragraph [0077], a method for improving an input and an output consistency of a solid state drive is disclosed comprising: calculating a minimum system imposed read and write latency for the solid state drive; calculating an expected read latency and an expected write latency for the solid state drive based on the minimum system imposed read and write latency; calculating an amplification coefficient for write operations and an amplification coefficient for read operations based upon a model, calculating a final read latency and a final write latency for the solid state drive based upon the calculated expected read latency and the calculated expected write latency and the amplification coefficient for write operations and the amplification coefficient for read operations and operating the solid state drive according to the final read latency and the write latency. The tuning adjustment for the memory workloads may be different based on workload type, such as reading and writing operations).
Karia does not teach a target Quality-of-Service (QoS) specification; monitoring a performance and a QoS of the workload for each of the changed value of the parameter; and determining the value of the parameter for the workload based on the performance and the QoS of the workload, wherein the determining of the value of the parameter includes: determining the value of the parameter such that the performance and a QoS conformity with a first storage device associated with the workload is maximized, wherein the storage device and the first storage device are connected to the host device, wherein the storage device supports a first specification and the first storage device supports a second specification that is different from the first specification, wherein the first specification and the second specification are hardware or software specifications that are different from the QoS conformity and the QoS specification, and wherein the QoS specification is based on a performance metric of the first storage device which is not a storage device where the tuning is performed.
However, Cady teaches a target Quality-of-Service (QoS) specification; monitoring a performance and a QoS of the workload for each of the changed value of the parameter; (Cady paragraph [0036], In one embodiment, API calls may be used to obtain information regarding a custom, proprietary, or standardized measure of the overall load (e.g., SS load) or overall performance (e.g., IOPS) of a particular storage node 136 or to obtain information regarding the overall load or performance of multiple storage nodes 136. As those skilled in the art will appreciate various other types of telemetry data, including, but not limited to measures of latency, utilization, load, and/or performance at various levels (e.g., the cluster level, the storage node level, or the storage node component level), may be made available via the API 137 and/or used internally by various monitoring modules. Cady paragraph [0004], One way of attempting to provide a better user experience is by providing a Quality of Service feature that allows users to set a QoS that guarantees a particular level of performance for volumes. For example, QoS may guarantee a particular level of performance by provisioning minimum, maximum, and/or burst levels of input/output operations per second (IOPS) to volumes. QoS settings may be monitored for performance for various workload operations, as well as for updated QoS settings, as seen in paragraph [0020]). and determining the value of the parameter for the workload based on the performance and the QoS of the workload, wherein the determining of the value of the parameter includes: (Cady paragraph [0006], According to another embodiment, a DRL agent running within a distributed storage system (DSS) is iteratively trained for each state of multiple of states of the DSS. For each state of a multiple states of the DSS, the DRL agent is caused to determine whether to update a set of QoS parameters representing a level of performance being provided by the DS S to a client, during a current iteration of the training based on the state. The state may include (i) the set of QoS parameters, (ii) information indicative of a type of workload to which the DSS is exposed, and (iii) a system metric indicative of a load on the DSS. Responsive to an affirmative determination by the DRL agent, an updated set of QoS parameters is determined, the updated set of QoS parameters is applied to the DSS, and when application of the updated set of QoS parameters lessens the system metric, the DRL agent is rewarded. The QoS settings and parameters may be determined and adjusted based on workload performance) determining the value of the parameter such that the performance and a QoS conformity with a first storage device associated with the workload is maximized; (Cady paragraph [0020], According to one embodiment, a DRL agent may be trained in a simulated environment replicating cluster performance and a target production environment with respect to latency and QoS. The trained DRL agent may then be deployed to one or more clusters to constantly update QoS settings in an optimal manner so as to minimize a selected measure of load on the cluster. In this manner, the DRL agent is expected to learn and adapt to new trends in volume utilization and make adjustments to QoS settings on the fly accordingly. The value of the parameters may be adjusted such that the workload demands are minimized, resulting in maximized performance).
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to combine the teachings of Karia with those of Cady. Cady teaches performing QoS setting adjustments to various parameters to improve the performance of a memory system, which can provide clear improvements to standard functions for memory devices such as reads and writes (see Cady paragraph [0018], While proper settings for various QoS parameters enhance overall performance of a distributed storage system, provisioning of QoS parameters (e.g., minimum, maximum, and burst levels of IOPS) to volumes is highly dynamic and complex, thereby resulting in misconfiguration by users. Over or under provisioning of QoS settings may lead to suboptimal utilization of the QoS feature and degrade volume and overall system performance).
Karia in view of Cady does not teach wherein the storage device supports a first specification and the first storage device supports a second specification that is different from the first specification, wherein the first specification and the second specification are hardware or software specifications that are different from the QoS conformity and the QoS specification, and wherein the QoS specification is based on a performance metric of the first storage device which is not a storage device where the tuning is performed.
However, Tomlin teaches wherein the storage device supports a first specification and the first storage device supports a second specification that is different from the first specification, wherein the first specification and the second specification are hardware or software specifications that are different from the QoS conformity and the QoS specification (Tomlin paragraph [0008], Efficient and effective multimode storage devices that can include multiple different types of address spaces that enable different storage space activities are described. A multimode selective underlying exposure storage device can enable selective exposure of underlying aspects of the storage device. In one embodiment, a distributed storage system comprises: a plurality of appliances, a distributed multimode storage management coordinator, and a communication mechanism for communicating messages between the plurality of multimode storage management systems, including distributed multimode storage management messages. A first one of the plurality of appliances can include: a plurality of storage devices (SSD) that have a first storage partition including a first type of interface and a first information storage region configured to store a first type of information and a second storage partition including a selective underlying exposure (SUE) interface and a second information storage region that stores a second type of information, wherein the SUE interface exposes an aspect of the second information storage region. The storage devices can include different specifications regarding address spaces and different management systems, as well as different hardware configurations, independent of the QoS factors) and wherein the QoS specification is based on a performance metric of the first storage device which is not a storage device where the tuning is performed (Tomlin paragraph [0181], The quality of service manager (QoS) 2116 defines quality of service policies based on system resource provisioning levels and latency measurements. The quality of service manager 2116 implements multiple queues to service different quality of service policy pools. With regard to latency-based policies, the quality of service manager 2116 implements timestamps on queue entries. The quality of service manager 2116 monitors various queue parameters and selects requests to ensure the policies are not violated. At the request of the flow control manager 2114, the quality of service manager 2116 throttles down traffic on provisioning-based policy queues. Tomlin may use a QoS manager to set a particular QoS policy dependent on performance metrics such as latency).
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to combine the teachings of Karia and Cady with those of Tomlin. Tomlin teaches having distinct specifications for hardware/software configurations independent of QoS factors, which can allow for additional flexibility regarding storage management/function multimode design (i.e., see Tomlin paragraphs [0065], Efficient and effective multimode storage approaches that can include multiple different types of address spaces and address space activities are described. In one embodiment, a multimode selective underlying exposure (SUE) storage device enables selective exposure of some underlying aspects of the storage device while not exposing other underlying aspects. A multimode storage and SUE approach can facilitate both improved performance while limiting complexity to a manageable scope. In one exemplary implementation, an underlying aspect of a physical address space is selectively exposed. An overall storage hierarchical approach can be implemented and underlying aspects from one hierarchical level are selectively exposed to another hierarchical level. The selective exposure can occur through address space configurations and mapping between address spaces).
Claim(s) 14-16 is/are rejected under 35 U.S.C. 103 as being unpatentable over Karia in view of Cady in further view of Tomlin as applied to claim 13 above, and further in view of Gerhart.
Regarding claim 14, Karia in view of Cady in further view of Tomlin and further in view of Gerhart teaches The method of claim 13, wherein the determining of the value of the parameter further includes: receiving, from the host device, a learning log generated through a tuning performed in a second storage device based on machine learning; (Gerhart paragraph [0039], Performance tuning log data may be returned as part of telemetry data or standard log dumps. In some embodiments, large number of logs from healthy field drives would provide good data sources for deep learning on automatic performance tuning points. Deep learning assessments may provide data-based refinement to the automatic performance tuning algorithm and initial performance tuning parameter starting points. Log data may be generated and used for the tuning performance information, which can be from the host, see Gerhart paragraph [0044], such as captured command statistics to measure performance. Workload detector 110 may monitor command reception from the host to characterize workloads and detect workload change. The performance adjustment can be targeted towards any one of a number of storage devices coupled to a host, see Gerhart paragraph [0022], Aspects of the present disclosure relate to computer operations and computer storage and specifically, performing automatic performance tuning of storage devices that are connected to a computer host) and performing a machine learning-based tuning by using the learning log for improvement of the performance and the QoS conformity (see Cady above for QoS conformity) with the first storage device (Gerhart paragraph [0045], In embodiments, the automatic performance tuning algorithm 102 may use machine learning capabilities to provide for tuning capabilities for help in tuning over time and to help with differing computer installations. The device may assess the latest convergence results of previous algorithm runs and make automatic performance tuning algorithm parameter adjustments to improve future iterations. The automatic performance tuning algorithm parameters may include sequences and an amount of performance tuning parameter adjustments 114. The machine learning based tuning may be applied based on the learning log information).
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to combine the teachings of Karia and Cady and Tomlin with those of Gerhart. Gerhart teaches performing tuning until a measured performance of a workload has reached a preset level, which allows for automatic tuning to a certain level to optimize performance efficiency (see Gerhart paragraph [0005], Conventional computers, while they are dynamic devices, do not provide the ability to fine tune specific components of the computer for maximum efficiency. There is a need, therefore, to provide a memory arrangement or device that minimizes the latency that a user will experience).
Regarding claim 15, Karia in view of Cady in further view of Tomlin and further in view of Gerhart teaches The method of claim 13, wherein the determining of the value of the parameter further includes: receiving, from the host device, a learning log generated through a tuning performed in a second storage device based on machine learning; (Gerhart paragraph [0045], In embodiments, the automatic performance tuning algorithm 102 may use machine learning capabilities to provide for tuning capabilities for help in tuning over time and to help with differing computer installations. The device may assess the latest convergence results of previous algorithm runs and make automatic performance tuning algorithm parameter adjustments to improve future iterations. The automatic performance tuning algorithm parameters may include sequences and an amount of performance tuning parameter adjustments 114. The machine learning based tuning may be applied based on the learning log information) and determining the value of the parameter to be used in the tuning based on a value of performing performance and at least one parameter included in the learning log (Gerhart paragraph [0049], A queue depth value extends along bytes 1 and 2. The queue depth value described is equal to the number of outstanding commands on the drive. A transfer length is also provided for the workload performance profile descriptor. The transfer length is located along bytes 3 and 4 and is defined as the number of blocks transferred for each command. A target IOPs value is further provided in the workload performance profile mode page format along bytes 5 to 7. The target IOPs value relates to host specified I/O per second that are provided and that the device should attempt to match for that workload. The data in the workload performance profile descriptor, therefore, may be read by the algorithm with the algorithm subsequently modifying the drive parameters. The tuning can be done based on performance information associated with a particular parameter value, such as I/O per second, also see Gerhart Figs. 3 and 4).
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to combine the teachings of Karia and Cady and Tomlin with those of Gerhart. Gerhart teaches performing tuning until a measured performance of a workload has reached a preset level, which allows for automatic tuning to a certain level to optimize performance efficiency (see Gerhart paragraph [0005], Conventional computers, while they are dynamic devices, do not provide the ability to fine tune specific components of the computer for maximum efficiency. There is a need, therefore, to provide a memory arrangement or device that minimizes the latency that a user will experience).
Regarding claim 16, Karia in view of Cady in further view of Tomlin and further in view of Gerhart teaches The method of claim 13, wherein the determining of the value of the parameter further includes: receiving, from the host device, a first parameter table for the performance and the QoS conformity (see Cady above for QoS conformity) with the first storage device; (Gerhart paragraph [0033], A controller included with the data storage device may be configured to control functions of the drive and record timestamps associated with events while executing commands. The controller may include circuitry that is configured to record data, in various forms, to allow the drive to alter performance based upon the data recorded. The data that is provided includes details regarding what types of operations are needed to be accomplished, (e.g. write or read commands), how long those commands need to be accomplished, and what types of workloads are necessary to be accomplished. The controller may be configured to determine total elapsed time between any timestamps and record information about the operating characteristics of the drive. The drive may also be configured to review operations that have occurred and fine tune operations to provide the best operational modes needed for the user. Parameters that may affect the overall characteristics of the drive may be needed latency, available power, etc. Timestamps and other record information can be stored regarding the workload operations, corresponding to the parameters) and performing the tuning by determining the value of the parameter based on the first parameter table (Gerhart paragraph [0033], The drive may also be configured to review operations that have occurred and fine tune operations to provide the best operational modes needed for the user. Parameters that may affect the overall characteristics of the drive may be needed latency, available power, etc. The techniques of this disclosure allow for an automatic performance tuning of the drive based upon an algorithm. The algorithm may review data that is placed in various configurations, thereby instructing the future operations of the drive. Data may be inserted into mode page format for reading by the algorithm. The mode pages may be modified, for example by a host, to allow automatic performance tuning to be accomplished and to what degree and extent the operations will be performed. The parameters in the table can be changed to tune the performance).
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to combine the teachings of Karia and Cady and Tomlin with those of Gerhart. Gerhart teaches performing tuning until a measured performance of a workload has reached a preset level, which allows for automatic tuning to a certain level to optimize performance efficiency (see Gerhart paragraph [0005], Conventional computers, while they are dynamic devices, do not provide the ability to fine tune specific components of the computer for maximum efficiency. There is a need, therefore, to provide a memory arrangement or device that minimizes the latency that a user will experience).
Claim(s) 17-18 is/are rejected under 35 U.S.C. 103 as being unpatentable over Gerhart et al. (US Publication No. 2019/0227920 – “Gerhart”) in view of Cady (US Publication No. 2022/0342592 – “Cady”) in further view of DeSanti et al. (US Publication No. 2024/0281172 – “DeSanti”) in further view of Tomlin et al. (US Publication No. 2017/0139823 – “Tomlin”).
Regarding claim 17, Gerhart teaches An operating method of a storage device, the operating method comprising: receiving, from a host device, a transmission request for a parameter metadata; (Gerhart paragraph [0033], A controller included with the data storage device may be configured to control functions of the drive and record timestamps associated with events while executing commands. The controller may include circuitry that is configured to record data, in various forms, to allow the drive to alter performance based upon the data recorded. The data that is provided includes details regarding what types of operations are needed to be accomplished, (e.g. write or read commands), how long those commands need to be accomplished, and what types of workloads are necessary to be accomplished. The controller may be configured to determine total elapsed time between any timestamps and record information about the operating characteristics of the drive. The drive may also be configured to review operations that have occurred and fine tune operations to provide the best operational modes needed for the user. Parameters that may affect the overall characteristics of the drive may be needed latency, available power, etc. Timestamps and other record information can be stored regarding the workload operations, corresponding to the parameters) in response to the request, sending the parameter metadata to the host device; (Gerhart paragraph [0033], A controller included with the data storage device may be configured to control functions of the drive and record timestamps associated with events while executing commands. The controller may include circuitry that is configured to record data, in various forms, to allow the drive to alter performance based upon the data recorded. The data that is provided includes details regarding what types of operations are needed to be accomplished, (e.g. write or read commands), how long those commands need to be accomplished, and what types of workloads are necessary to be accomplished. The controller may be configured to determine total elapsed time between any timestamps and record information about the operating characteristics of the drive. The drive may also be configured to review operations that have occurred and fine tune operations to provide the best operational modes needed for the user. Parameters that may affect the overall characteristics of the drive may be needed latency, available power, etc. Timestamps and other record information can be stored regarding the workload operations, corresponding to the parameters, and can be transmitted to the host, see Gerhart paragraph [0010], In one non-limiting embodiment, an arrangement is disclosed comprising a memory arrangement configured to store and retrieve data; an interface to allow data to be received and transmitted by the arrangement from a host and a processor configured to dynamically conduct automatic performance tuning for the memory arrangement) receiving a request indicating an activation of a parameter table included in the parameter metadata, wherein the parameter table is associated with one of pieces of information of the parameter table; (Gerhart paragraph [0039], Performance tuning log data may be returned as part of telemetry data or standard log dumps. In some embodiments, large number of logs from healthy field drives would provide good data sources for deep learning on automatic performance tuning points. Deep learning assessments may provide data-based refinement to the automatic performance tuning algorithm and initial performance tuning parameter starting points. Log data may be generated and used for the tuning performance information, which can be from the host, see Gerhart paragraph [0044], such as captured command statistics to measure performance. Workload detector 110 may monitor command reception from the host to characterize workloads and detect workload change. The performance adjustment can be targeted towards any one of a number of storage devices coupled to a host, and activated to be used, see Gerhart paragraph [0022], Aspects of the present disclosure relate to computer operations and computer storage and specifically, performing automatic performance tuning of storage devices that are connected to a computer host) activating the parameter table designated by the host device; (Gerhart paragraph [0039], Performance tuning log data may be returned as part of telemetry data or standard log dumps. In some embodiments, large number of logs from healthy field drives would provide good data sources for deep learning on automatic performance tuning points. Deep learning assessments may provide data-based refinement to the automatic performance tuning algorithm and initial performance tuning parameter starting points. Log data may be generated and used for the tuning performance information, which can be from the host, see Gerhart paragraph [0044], such as captured command statistics to measure performance. Workload detector 110 may monitor command reception from the host to characterize workloads and detect workload change. The performance adjustment can be targeted towards any one of a number of storage devices coupled to a host, and activated to be used, see Gerhart paragraph [0022], Aspects of the present disclosure relate to computer operations and computer storage and specifically, performing automatic performance tuning of storage devices that are connected to a computer host) detecting a workload assigned by the host device; (Gerhart paragraph [0011], In another non-limiting embodiment, a method for altering a performance of a solid state drive is disclosed comprising: selecting at least one performance profile target; detecting a workload to be accomplished by the solid state drive, loading initial starting values for an automatic performance tuning algorithm, configuring a command performance statistics monitor to measure workload input and output performance. A workload may be assigned from a host); wherein the parameter metadata comprises a plurality of parameter tables, (Gerhart paragraph [0039], Performance tuning log data may be returned as part of telemetry data or standard log dumps. In some embodiments, large number of logs from healthy field drives would provide good data sources for deep learning on automatic performance tuning points. Deep learning assessments may provide data-based refinement to the automatic performance tuning algorithm and initial performance tuning parameter starting points. Log data may include a plurality of metadata generated and stored as files/tables and used for the tuning performance information, which can be from the host, see Gerhart paragraph [0044], such as captured command statistics to measure performance. Workload detector 110 may monitor command reception from the host to characterize workloads and detect workload change).
Gerhart does not teach based on the detected workload that is associated with the parameter table, performing the detected workload based on the parameter table; wherein each of the plurality of parameter tables is a tuning result of Quality-of-Service (QoS) conformity for each of a plurality of storage devices, and wherein each of the plurality of storage devices supports a different specification.
However, Cady teaches and based on the detected workload that is associated with the parameter table, performing the detected workload based on the parameter table (Cady paragraph [0039], Those skilled in the art will appreciate DRL agents may be trained specifically for states of a cluster expected to operate within a particular target production environment having specific workload characteristics. For example, the DRL agent may be trained for operation within a transactional environment (e.g., latency-sensitive transactional workloads, large streaming workloads in which the dominant performance attribute is throughput, transactional workloads involving frequent read/write operations with small I/O size in which the dominant performance attribute is IOPS, small datasets in which data is accessed infrequently and performance is not of primary importance, write-heavy database workloads, workloads that require sustained IOPS performance, workloads that require sub-millisecond latency and sustained IOPS performance, etc.). The workload may be performed based on a detected workload associated with various detected workload parameters).
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to combine the teachings of Gerhart with those of Cady. Cady teaches performing QoS setting adjustments to various parameters to improve the performance of a memory system, which can provide clear improvements to standard functions for memory devices such as reads and writes (see Cady paragraph [0018], While proper settings for various QoS parameters enhance overall performance of a distributed storage system, provisioning of QoS parameters (e.g., minimum, maximum, and burst levels of IOPS) to volumes is highly dynamic and complex, thereby resulting in misconfiguration by users. Over or under provisioning of QoS settings may lead to suboptimal utilization of the QoS feature and degrade volume and overall system performance).
Gerhart in view of Cady does not teach wherein each of the plurality of parameter tables is a tuning result of Quality-of-Service (QoS) conformity for each of a plurality of storage devices, and wherein each of the plurality of storage devices supports a different specification.
However, DeSanti teaches a tuning result of Quality-of-Service (QoS) conformity for each of a plurality of storage devices, (DeSanti paragraph [0003], SANS are typically designed to provide “any-to-any” connectivity between hosts and storage systems (e.g., such that any host in the SAN may potentially be allowed to connect to and communicate with one or more of the storage device included in any storage system in the SAN), and zoning techniques are then often used to allow connectivity between particular hosts and particular storage devices/storage systems (e.g., a first zone may allow first hosts to connecting to and communicating with first storage devices/a first storage system in the SAN, a second zone may allow second hosts to connecting to and communicating with second storage devices/a second storage system in the SAN, etc.) in order to, for example, provide security, define Quality of Service (QOS), constrain discovery operations, and/or provide other zoning benefits known in the art. The QoS specifications can be defined individually for each of the storage devices within the storage system, also see DeSanti paragraph [0033], As also discussed above, zones are then provided in the conventional SAN 200 in order to, for example, provide security (e.g., to ensure particular host devices cannot access particular storage subsystems), define Quality of Service (QOS) (e.g., ensure the network provides adequate bandwidth between host devices and storage subsystems), constrain discovery operations (e.g., limit host devices to discovering and logging into storage subsystems they will actually use), and/or provide other zoning benefits known in the art. For example, with reference to FIGS. 3A and 3B, a zone 300 may be provided that includes the host device(s) 206a and the storage subsystem(s) 202a in order to restrict connectivity 300a for the host device(s) 206a to the storage subsystem(s) 202a, a zone 302 may be provided that includes the host device(s) 206b and the storage subsystem(s) 202b in order to restrict connectivity 302a for the host device(s) 206b to the storage subsystem(s) 202b, and a zone 304 may be provided that includes the host device(s) 206c and the storage subsystem(s) 202c in order to restrict connectivity 304a for the host device(s) 206c to the storage subsystem(s) 202c).
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to combine the teachings of Gerhart and Cady with those of DeSanti. DeSanti teaches a plurality of storage devices, wherein each storage device can have unique targeted specifications, such as those corresponding to quality-of-service, in order to optimize the performance between the host and each distinct storage system (i.e., see DeSanti paragraph [0033], As also discussed above, zones are then provided in the conventional SAN 200 in order to, for example, provide security (e.g., to ensure particular host devices cannot access particular storage subsystems), define Quality of Service (QOS) (e.g., ensure the network provides adequate bandwidth between host devices and storage subsystems), constrain discovery operations (e.g., limit host devices to discovering and logging into storage subsystems they will actually use), and/or provide other zoning benefits known in the art. For example, with reference to FIGS. 3A and 3B, a zone 300 may be provided that includes the host device(s) 206a and the storage subsystem(s) 202a in order to restrict connectivity 300a for the host device(s) 206a to the storage subsystem(s) 202a, a zone 302 may be provided that includes the host device(s) 206b and the storage subsystem(s) 202b in order to restrict connectivity 302a for the host device(s) 206b to the storage subsystem(s) 202b, and a zone 304 may be provided that includes the host device(s) 206c and the storage subsystem(s) 202c in order to restrict connectivity 304a for the host device(s) 206c to the storage subsystem(s) 202c).
Gerhart in view of Cady in further view of DeSanti does not teach wherein each of the plurality of storage devices supports a respectively different hardware or software specification that is different from the QoS conformity and a QoS specification, and wherein the QoS specification is based on a performance metric of the first storage device which is not a storage device where the tuning is performed.
However, Tomlin teaches wherein each of the plurality of storage devices supports a respectively different hardware or software specification that is different from the QoS conformity and a QoS specification (Tomlin paragraph [0008], Efficient and effective multimode storage devices that can include multiple different types of address spaces that enable different storage space activities are described. A multimode selective underlying exposure storage device can enable selective exposure of underlying aspects of the storage device. In one embodiment, a distributed storage system comprises: a plurality of appliances, a distributed multimode storage management coordinator, and a communication mechanism for communicating messages between the plurality of multimode storage management systems, including distributed multimode storage management messages. A first one of the plurality of appliances can include: a plurality of storage devices (SSD) that have a first storage partition including a first type of interface and a first information storage region configured to store a first type of information and a second storage partition including a selective underlying exposure (SUE) interface and a second information storage region that stores a second type of information, wherein the SUE interface exposes an aspect of the second information storage region. The storage devices can include different specifications regarding address spaces and different management systems, as well as different hardware configurations, independent of the QoS factors) and wherein the QoS specification is based on a performance metric of the first storage device which is not a storage device where the tuning is performed (Tomlin paragraph [0181], The quality of service manager (QoS) 2116 defines quality of service policies based on system resource provisioning levels and latency measurements. The quality of service manager 2116 implements multiple queues to service different quality of service policy pools. With regard to latency-based policies, the quality of service manager 2116 implements timestamps on queue entries. The quality of service manager 2116 monitors various queue parameters and selects requests to ensure the policies are not violated. At the request of the flow control manager 2114, the quality of service manager 2116 throttles down traffic on provisioning-based policy queues. Tomlin may use a QoS manager to set a particular QoS policy dependent on performance metrics such as latency).
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to combine the teachings of Gerhart, Cady and DeSanti with those of Tomlin. Tomlin teaches having distinct specifications for hardware/software configurations independent of QoS factors, which can allow for additional flexibility regarding storage management/function multimode design (i.e., see Tomlin paragraphs [0065], Efficient and effective multimode storage approaches that can include multiple different types of address spaces and address space activities are described. In one embodiment, a multimode selective underlying exposure (SUE) storage device enables selective exposure of some underlying aspects of the storage device while not exposing other underlying aspects. A multimode storage and SUE approach can facilitate both improved performance while limiting complexity to a manageable scope. In one exemplary implementation, an underlying aspect of a physical address space is selectively exposed. An overall storage hierarchical approach can be implemented and underlying aspects from one hierarchical level are selectively exposed to another hierarchical level. The selective exposure can occur through address space configurations and mapping between address spaces).
Regarding claim 18, Gerhart in view of Cady in further view of DeSanti in further view of Tomlin teaches The operating method of claim 17, further comprising: receiving a second transmission request for the parameter table included in the parameter metadata; and sending the parameter table to the host device (Gerhart paragraph [0033], A controller included with the data storage device may be configured to control functions of the drive and record timestamps associated with events while executing commands. The controller may include circuitry that is configured to record data, in various forms, to allow the drive to alter performance based upon the data recorded. The data that is provided includes details regarding what types of operations are needed to be accomplished, (e.g. write or read commands), how long those commands need to be accomplished, and what types of workloads are necessary to be accomplished. The controller may be configured to determine total elapsed time between any timestamps and record information about the operating characteristics of the drive. The drive may also be configured to review operations that have occurred and fine tune operations to provide the best operational modes needed for the user. Parameters that may affect the overall characteristics of the drive may be needed latency, available power, etc. Timestamps and other record information can be stored regarding the workload operations, corresponding to the parameters).
Response to Arguments
Applicant’s arguments, see pages 1-9 (numbered pages 11-19), filed February 2nd, 2026 with respect to the rejection(s) of claim(s) Claims 1-18 under 35 U.S.C. 103 have been fully considered and are persuasive. Therefore, the rejection has been withdrawn. However, upon further consideration, a new ground(s) of rejection is made in view of Karia et al. (US Publication No. 2018/0329626 – “Karia”) in view of Zinger et al. (US Publication No. 2025/0036286 – “Zinger”) in further view of Lee et al. (US Publication No. 2011/0149775 – “Lee”) and further in view of Tomlin et al. (US Publication No. 2017/0139823 – “Tomlin”).
In response to the newly added claim limitations to independent claims 1, 10, 13 and 17, new references have been added. Specifically, the Lee reference has been added to disclose the specific concept of maintaining performance metrics through QoS specifications within a preset range. Additionally, the Tomlin reference has been added to disclose the limitations regarding different specification configurations (hardware or software) different from the QoS conformity and specification values, as well as specific tuning information for performance, described in further detail in the rejection above. In light of the above references and rationale, the corresponding 35 U.S.C. 103 Rejection is maintained.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JONAH C KRIEGER whose telephone number is (571)272-3627. The examiner can normally be reached Monday - Friday 8 AM - 5 PM.
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, Rocio Del Mar Perez-Velez can be reached at (571)-270-5935. 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.
/J.C.K./Examiner, Art Unit 2133
/ROCIO DEL MAR PEREZ-VELEZ/Supervisory Patent Examiner, Art Unit 2133
Prosecution Insights