DETAILED ACTION
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
The text of those sections of Title 35, U.S. Code not included in this action can be found in a prior Office action.
This Action is in response to communications filed 05/04/2026.
Claims 1, 11-12, and 19-20 have been amended.
Claims 1-20 are pending.
Claims 1-20 are rejected.
Response to Amendment
In the Remarks filed 05/04/2026, Applicant has amended:
The language of claims 1, 12, and 19 to address the claim objections regarding the use of the acronym “I/O” while potentially expected to be understood in the field of art and to clarify the term with the full description. The Examiner therefore withdraws the corresponding objections made in the Office action dated 02/04/2026.
The language of claims 11 and 20 to address the claim objections regarding the use of the acronym “LRU” and “MFU” while potentially expected to be understood in the field of art and to clarify the term with the full description. The Examiner therefore withdraws the corresponding objections made in the Office action dated 02/04/2026.
Response to Arguments
In Remarks filed on 05/04/2026, Applicant substantially argues:
On Pages 7-8, the amended language of the independent claims 1, 12, and 19 recite limitations which integrate the claimed steps into a practical application which improve the performance of the cache operation. Applicant’s arguments filed have been fully considered and are found to be persuasive. The Examiner therefore withdraws the 35 U.S.C. 101 rejections made in the Office action dated 02/04/2026.
On Pages 8-10, the prior art references of record including Alshawabkeh and Douglis fail to disclose the amended limitations of claims 1, 12, and 19 including using write-operation information of a data block as in input to the predictive model to determine an eviction event for the data block based on a forecasted read-after-write interval. In particular, Alshawabkeh teaches predictive workload modeling without addressing cache evictions and Douglis discloses cache evictions without addressing the prediction model. Applicant’s arguments filed have been fully considered but are moot in view of the current rejections made in response to Applicant’s amendments.
All arguments by the applicant are believed to be covered in the body of the office action; thus, this action constitutes a complete response to the issues raised in the remarks dated May 4, 2026.
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.
Claims 4, 8-10, 14, and 18 are 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 4 recites “predictive model includes writing a data block to cache to generate…” Herein both recitations of “data block” and “cache” lack proper antecedent basis with respect to the recitations of the terms currently present in claim 1, from which claim 4 depends. Claim 14 recites the same issue with respect to claim 12.
Claim 8 recites “retaining a data block in cache.” Herein both recitations of “data block” and “cache” lack proper antecedent basis with respect to the recitations of the terms currently present in claim 1, from which claim 8 depends. Claim 18 recites the same issue with respect to claim 12.
Claim 9 depends from claim 8 and does not resolve the above issue.
Claim 10 recites “marking a data block for eviction.” Herein recitation of “data block” lacks proper antecedent basis with respect to the recitation of the term currently present in claim 1, from which claim 10 depends.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102 of this title, 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 set forth in Graham v. John Deere Co., 383 U.S. 1, 148 USPQ 459 (1966), that are applied for establishing a background for determining obviousness under 35 U.S.C. 103(a) 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.
Claims 1-6, 8-16, and 18-20 are rejected under 35 U.S.C. 103 as being unpatentable over Alshawabkeh et al. (US 9,703,664) in view of Frachtenberg (US 2014/0136792) and further in view of Zuraski et al. (US 2015/0193334).
Regarding claim 1, Alshawabkeh discloses, in the italicized portions, a method comprising: receiving a collection of I/O operations; analyzing the collection of input/output (I/O) operations for one or more access patterns; generating a predictive model based on the one or more access patterns, the predictive model configured to forecast a future I/O operation ([Col. 80, lines 9-23] As described in more detail elsewhere herein, the I/O statistics collected at a sub-LUN level in an embodiment in accordance with techniques herein may be analyzed to facilitate determining an I/O workload pattern and which may be used to predict future I/O workload directed to each sub-LUN based on its previous I/O workload or activity. It may be desirable to use a forecasting technique such as described herein based on the ARIMA models to provide for accurate I/O workload predictions for use in modeling data storage system workload performance used, for example, in determining data movements. For example, for a current time period for a first extent having a current I/O workload, modeling techniques described herein based on the ARIMA models may be used to accurately predict a future I/O workload for the first extent in the next time period.); and in response to writing a data block to a cache, inputting write-operation information for the data block to the predictive model to determine, based on a forecasted read-after-write interval for the data block, an eviction event for the data block, wherein the eviction event control retention of the data block in the cache. Herein Alshawabkeh explicitly discloses monitoring a collection of I/O statistics related to operations in order to determine a workload pattern which is then used to predict a future I/O workload via a forecasting technique. It is further noted that the workload pattern includes determining data movements between storage locations. Alshawabkeh does not explicitly address using the forecast model to generate a read-after-write interval to determine an eviction event for the data block written to the cache. Regarding forecasting the read-after-write interval for the written data block, Zuraski discloses in Paragraphs [0010-11] and [0021-29] dynamically predicting read-after-write (RAW) hazards in response to execution of an instruction. Herein the system utilizes the predicted RAW events, under broadest reasonable interpretation to be analogous to the RAW interval as claimed for when the RAW event happens, to optimize instruction execution and data handling. In this manner, it would be obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to view of RAWs as a form of workload in order to improve storage management of limited memory allocations (Zuraski [0075]) as Alshawabkeh is concerned with future data migration operations and data evictions (Alshawabkeh Column 79, lines 27-53). Zuraski does not explicitly address using the predictive model to determine an eviction event for the data block based on the forecasted RAW interval. Regarding this aspect of the limitation Frachtenberg discloses in Paragraph [0056] “Prediction operation 330 predicts future access patterns of current data within a cache based on the current version of the model. For example, prediction operation 330 can return a score or probability of future access over one or more time periods (e.g., one hour, two hours, and anytime in the future). Using this information, eviction operation 340 determines which data is least likely to be accessed and should be evicted from the cache.” Herein Frachtenberg explicitly identifies that through predicting future access patterns of data within cache based on a current model, an eviction event for data within a cache is determined. In view of Alshawabkeh wherein workload model based data handling is disclosed and Zuraski wherein determined RAW workloads are discussed, it would be obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to control cache eviction policies according to modeled access patterns to improve memory performance (Frachtenberg [0026]). Alshawabkeh, Zuraski, and Frachtenberg are analogous art because they are from the same field of endeavor of managing storage migration.
Regarding claim 2, Alshawabkeh further discloses the method of claim 1 wherein the predictive model is a time-series forecasting model (Col. 79, line 63 – Col. 80 ln. 4] To address this, described herein is are techniques based on mathematical models of autocorrelation in a time series analysis, called auto-regressive integrated moving average (ARIMA) models, which are capable of capturing periodic patterns and trends of workload I/O access to predict the future load demand, and thus, attempt to migrate the data across different storage tiers and also guarantee multiple SLO requirements for applications under dynamic workloads.). Herein Alshawabkeh explicitly discloses using time-series analysis for calculating future accesses.
Regarding claim 3, Alshawabkeh further discloses the method of claim 2 wherein the time-series forecasting model is an autoregressive integrated moving average (ARIMA) model (Col. 79, line 63 – Col. 80 ln. 4]). Herein Alshawabkeh explicitly discloses using ARIMA models for time-series analysis to predict future accesses.
Regarding claim 4, Alshawabkeh further discloses the method of claim 1, wherein inputting the I/O operation to predictive model includes writing a data block to cache to generate a forecasted interval for a future read operation (Alshawabkeh [Col. 82 ln. 44-53] The collected information may include counts of the number of observed I/O operations occurring during that particular time period or data collection period for each particular I/O statistic as in FIG. 41. Using such collected I/O statistics based on observed values during the collection time period as well as possibly other observed values for I/O statistics from prior time periods and also associated error values of prior predictions, an ARIMA model described herein may be used to predict values for the I/O statistics for the next time period.). Herein Alshawabkeh discloses monitoring operations to memory to collect information for the forecast model. As identified by the I/O operations, one of ordinary skill in the art would recognize these to include both read and write operations and subsequent read or write access.
Regarding claim 5, Alshawabkeh, Zuraski, and Frachtenberg in combination further disclose the method of claim 1 wherein the one or more access patterns include a read-after-write pattern (Zuraski [0010-11]). Herein Zuraski addresses predicting a RAW event and in view of both Alshawabkeh and Frachtenberg, the RAW event would be obvious to one of ordinary skill in the art as a form of access pattern.
Regarding claim 6, Alshawabkeh further discloses the method of claim 1 wherein the one or more access patterns are based on a contiguous sequence of data (Alshawabkeh [Col. 76 ln. 1-5] In one embodiment in accordance with techniques herein, the I/O density range may be divided into 4 non-overlapping contiguous subranges which may or may not be the same size. The size of each subrange may vary, for example, with the storage capacity of each media type.). Herein Alshawabkeh identifies managing and access contiguous memory locations in part based on sequentially stored data.
Regarding claim 8, Alshawabkeh and Frachtenberg in combination further disclose the method of claim 1, wherein the eviction event includes retaining a data block in cache (Frachtenberg [0057]). Herein Frachtenberg identifies maintaining data in cache based on the access prediction.
Regarding claim 9, Alshawabkeh and Frachtenberg in combination further disclose the method of claim 8 wherein the future I/O operation includes a probability of a read occurring within a specified time window (Frachtenberg [0056]). Herein Frachtenberg identifies performing the steps to determine the likelihood of access, or similarly read, of data with a particular time interval.
Regarding claim 10, Alshawabkeh and Frachtenberg in combination further disclose the method of claim 1, wherein the eviction event includes marking a data block for eviction (Frachtenberg [0054-56]). Herein Frachtenberg identifies and manages data as candidates for eviction based on predicted future access.
Regarding claim 11, Alshawabkeh and Frachtenberg in combination further disclose the method of claim 10 wherein the eviction event comprises one of a least recently used (LRU) operation, a most frequently used (MFU) operation or a tag-based eviction operation (Frachtenberg [0025]). Herein Frachtenberg identifies that LRU as known in the art can be used to evict data.
Regarding claim 12, Alshawabkeh discloses, in the italicized portions, a system comprising: a memory; and at least one processor that is operatively coupled to the memory, the at least one processor being configured to perform the operations of (Figure 1, service processor 22a, data storage system 12): receiving a collection of input/output (I/O) operations; analyzing the collection of I/O operations for one or more access patterns; generating a predictive model based on the one or more access patterns, the predictive model configured to forecast a future I/O operation ([Col. 80, lines 9-23]); and in response to writing a data block to a cache, inputting write-operation information for the data block to the predictive model to determine, based on a forecasted read-after-write interval for the data block, an eviction event for the data block, wherein the eviction event control retention of the data block in the cache. Herein Alshawabkeh explicitly discloses monitoring a collection of I/O statistics related to operations in order to determine a workload pattern which is then used to predict a future I/O workload via a forecasting technique. It is further noted that the workload pattern includes determining data movements between storage locations. Alshawabkeh does not explicitly address using the forecast model to generate a read-after-write interval to determine an eviction event for the data block written to the cache. Regarding forecasting the read-after-write interval for the written data block, Zuraski discloses in Paragraphs [0010-11] and [0021-29] dynamically predicting read-after-write (RAW) hazards in response to execution of an instruction. Zuraski does not explicitly address using the predictive model to determine an eviction event for the data block based on the forecasted RAW interval. Regarding this aspect of the limitation Frachtenberg discloses in Paragraph [0056] that through predicting future access patterns of data within cache based on a current model, an eviction event for data within a cache is determined. Claim 12 is rejected on a similar basis as claim 1.
Regarding claim 13, Alshawabkeh further discloses the system of claim 12 wherein the predictive model is an autoregressive integrated moving average (ARIMA) time-series forecasting model (Col. 79, line 63 – Col. 80 ln. 4]). Claim 13 is rejected on a similar basis as claim 3.
Regarding claim 14, Alshawabkeh further discloses the system of claim 12, wherein inputting the I/O operation to predictive model includes writing a data block to cache to generate a forecasted interval for a future read operation (Alshawabkeh [Col. 82 ln. 44-53]). Claim 14 is rejected on a similar basis as claim 4.
Regarding claim 15, Alshawabkeh, Zuraski, and Frachtenberg in combination further disclose the system of claim 12 wherein the one or more access patterns include a read-after- write pattern (Zuraski [0010-11]). Claim 15 is rejected on a similar basis as claim 5.
Regarding claim 16, Alshawabkeh further discloses the system of claim 12 wherein the one or more access patterns are based on a contiguous sequence of data (Alshawabkeh [Col. 76 ln. 1-5]). Claim 16 is rejected on a similar basis as claim 6.
Regarding claim 18, Alshawabkeh and Frachtenberg in combination further disclose the system of claim 12, wherein the future I/O operation includes a probability of a read occurring within a specified time window (Frachtenberg [0056]) and the eviction event includes retaining a data block in cache (Frachtenberg [0057]). Claim 18 is rejected on a similar basis as claims 8 and 9.
Regarding claim 19, Alshawabkeh and Frachtenberg in combination further disclose the system of claim 12, wherein the eviction event includes marking a data block for eviction using one of a least recently used (LRU) operation, a most frequently used (MFU) operation and a tag-based eviction operation (Frachtenberg [0025]). Claim 19 is rejected on a similar basis as claim 11.
Regarding claim 20 Alshawabkeh discloses, in the italicized portions, a non-transitory computer-readable medium storing one or more processor-executable instructions, which when executed by at least one processor cause the at least one processor to perform the operations of (Column 3, lines 35-58]): receiving a collection of input/output (I/O) operations; analyzing the collection of I/O operations for one or more access patterns; generating a predictive model based on the one or more access patterns, the predictive model configured to forecast a future I/O operation ([Col. 80, lines 9-23]); and in response to writing a data block to a cache, inputting write-operation information for the data block to the predictive model to determine, based on a forecasted read-after-write interval for the data block, an eviction event for the data block, wherein the eviction event control retention of the data block in the cache. Herein Alshawabkeh explicitly discloses monitoring a collection of I/O statistics related to operations in order to determine a workload pattern which is then used to predict a future I/O workload via a forecasting technique. It is further noted that the workload pattern includes determining data movements between storage locations. Alshawabkeh does not explicitly address using the forecast model to generate a read-after-write interval to determine an eviction event for the data block written to the cache. Regarding forecasting the read-after-write interval for the written data block, Zuraski discloses in Paragraphs [0010-11] and [0021-29] dynamically predicting read-after-write (RAW) hazards in response to execution of an instruction. Zuraski does not explicitly address using the predictive model to determine an eviction event for the data block based on the forecasted RAW interval. Regarding this aspect of the limitation Frachtenberg discloses in Paragraph [0056] that through predicting future access patterns of data within cache based on a current model, an eviction event for data within a cache is determined. Claim 20 is rejected on a similar basis as claim 1.
Claims 7 and 17 are rejected under 35 U.S.C. 103 as being unpatentable over Alshawabkeh in view of Zuraski and further in view of Frachtenberg and still in further view of Navon et al. (US 2023/0376227).
Regarding claim 7, Alshawabkeh, Zuraski, and Frachtenberg do not explicitly disclose the method of claim 1 wherein the future I/O operation includes a probability and a timing of a future read-after-write pattern. Zuraski addresses predicting RAW events. Regarding the claim limitation, Navon discloses in Paragraph [0055] “determine a temperature for the data, wherein the temperature is an indication of how soon the data is to be re-written or read after writing; and write the data to the memory device, wherein the writing occurs after the determining. The temperature is classified as cold, hot, or super-hot, wherein super-hot is expected to be read sooner than hot, and wherein hot is expected to be read sooner than cold. The determining comprises using traces of data previously written to predict how soon the data is to be re-written or read after the writing.” As part of the cache access pattern determination, read-after-write (RAW) patterns may be identified before evicting data. In view of Zuraski, it would be obvious to one of ordinary skill in the art before the effective filing date of the claimed invention that the RAW determinations as noted in Navon may be made as part of the access timings as performed in Zuraski in order to determine likelihood of access at a particular point in time before evicting data. Alshawabkeh, Zuraski, Frachtenberg and Navon are analogous art because they are from the same field of endeavor of managing cache storage.
Regarding claim 17, Alshawabkeh, Zuraski, and Frachtenberg do not explicitly disclose the system of claim 12 wherein the future I/O operation includes a probability and a timing of a future read-after-write pattern. Zuraski addresses predicting RAW events. Regarding the claim limitation, Navon discloses in Paragraph [0055] as part of the cache access pattern determination, read-after-write (RAW) patterns may be identified before evicting data. Claim 17 is rejected on a similar basis as claim 7.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ALEXANDER J YOON whose telephone number is (408)918-7629. The examiner can normally be reached on Monday-Friday 8am-3pm ET. The examiner’s email is alexander.yoon2@uspto.gov.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Jared Rutz can be reached on 571-272-5535. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/ALEXANDER YOON/
Examiner, Art Unit 2135
/JARED I RUTZ/Supervisory Patent Examiner, Art Unit 2135
Prosecution Insights