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 .
Response to Amendment
Applicant’s Remarks/Arguments filed on May 7th, 2026, have been carefully considered.
Claims 1, 9, and 15-17 have been amended.
No claims have been added or canceled.
Claims 1-20 are currently pending in the instant application.
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.
Claims 1-20 are rejected under 35 U.S.C. 103 as being unpatentable over Goel et al. [US7,958,304] in view of Ellard et al. [US8,825,938]. Goel teaches dynamically adapting the fault tolerance and performance characteristics of a RAID-based storage system by merging and splitting RAID groups. Ellard teaches use of write allocation decisions to achieve desired levels of wear across a set of redundant solid-state memory devices.
Regarding claims 1, 9, and 17, Goel teaches a method comprising:
detecting a change of failure characteristics for a storage device within a storage system [Goel column 3, lines 13-21 “…The dynamic reconfiguration of RAID groups is performed to adapt the RAID groups to changes in data and system characteristics. The dynamic reconfiguration includes merging and splitting RAID groups without incurring system downtime. Merging or splitting RAID groups changes fault tolerance and performance characteristics of the RAID groups, and, therefore, adapts the RAID groups to the changes in data and system characteristics…”]; and
in response to the detection, changing a number of copies of metadata stored in different physical storage units within the storage device [Goel column 8, lines 4-8 “…two RAID-4 groups may be merged to form a RAID-TP group (referring to "RAID Triple Protection," which offers triple disk failure protection). In this scenario, adding a new parity disk becomes necessary, as every merged stripe needs three parity blocks…”(The examiner has determined that parity reads on the applicant’s use of the word metadata for recovery means.)],
wherein the metadata is used to recover data from within the storage system [Goel column 1, lines 42-45 “…RAID-DP adds a second parity disk to each RAID group in order to provide data protection against the failure of two disks in the same RAID group…”], and
Goel fails to explicitly teach wherein at least two copies of the metadata are stored within the storage device.
However, Ellard does teach wherein at least two copies of the metadata are stored within the storage device [Ellard column 6, lines 16-29 “…computes the fingerprint of the data block (using, e.g., a hash function, CRC, etc.). The storage manager 21 then identifies the SSMs 7 to which the data block is to be written at 303. As noted above, in one embodiment an attempt is made to write the data block to all of the SSMs 7. In other embodiments, as described further below, an attempt is made to write the data block to more than one, but not all, of the SSMs 7, in order to accomplish wear skewing. The storage manager 21 then attempts at 304 to write the data block and its fingerprint to each of the SSMs that were identified at 303. Next, the storage manager 21 determines whether at least a quorum of the SSMs report that they have written the data block successfully 305…” and column 2, lines 53-55 “…where "devices" here can mean flash chips, DIMMs, solid-state drives (SSDs), etc…”(Examiner points to the embodiment can be on the chip level within a device) and column 4, lines 9-10 “…each individual SSM 7 is a flash memory chip…” and column 5, lines 18-20, “…The SSMs 7 can be arranged in a RAID-like manner to tolerate a fail-stop failure (a failure in which a device fails by stopping or shutting down) of one or more of the SSMs 7…” and column 4, last lines “… The storage access layer 24 implements a higher-level disk storage protocol, such as RAID-4, RAID-5 or RAID-DP…” and column 6, lines 47-52 “…It should also be noted that the system can be designed to tolerate the loss of more than one flash memory device. For example, instead of simple mirroring, a redundancy scheme such as RAID-DP, RAID-TP, or any other arbitrary coding scheme that enables arbitrary numbers of failures to be tolerated, could be used….”].
Goel and Ellard are analogous arts in that they both deal with improving data protection with storage systems.
It would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to combine Goel’s detection of failure characteristics with Ellard’s storing of metadata to multiple flash memory modules for the benefit of reducing the likelihood of concurrent memory device failure and thus improve the storage lifetime [Ellard column 2, lines 55-57 “…the techniques introduced here also include a way to reduce the likelihood that substantially concurrent failures of two or more solid-state memory devices will occur…”].
Regarding claims 2, 10, and 18, as per claim 1, Goel teaches a degree of redundancy defines a number of copies of the metadata stored in the storage system [Goel column 3, lines 25-27 “…The term "fault tolerance level" herein refers to the number of parity disks used by a RAID group, as well as the data-to-parity ratio in the RAID group…”].
Regarding claims 3, 11, and 19, as per claim 1, Ellard teaches a number of copies is fewer than a number of storage devices in the storage system [Ellard column 5, lines 36-38 “…to accomplish wear skewing, the data item and fingerprint are written to some, but not all, of the SSMs 7…”].
Regarding claims 4, 12, and 20, as per claim 1, Goel teaches the failure characteristics comprise a failure rate for a plurality of storage devices [Goel column 1, lines 37 – column 2, line 2 “…high mean-time-to-failure (MTTF) and high bit error rate…a system administrator may determine the fault tolerance level based on the mean-time-to-data-loss (MTTDL) requirement in the system specification… the data-to-parity ratio needs to be rebalanced to ensure that the Mean Time to Data Loss (MTTDL) is within acceptable bounds…”].
Regarding claims 6 and 14, as per claim 1, Goel teaches the failure characteristics comprise a Redundant Array of Independent Disks (RAID) configuration for the storage system [Goel column 1, lines 40-45 “…The widespread acceptance of the SATA drives has resulted in the development and use of double-parity RAID (RAID-DP). RAID-DP adds a second parity disk to each RAID group in order to provide data protection against the failure of two disks in the same RAID group…”].
Regarding claims 7 and 15, as per claim 1, Both Goel and Ellard teach determining a degree of redundancy for the metadata comprises determining the degree of redundancy for the metadata based on a metadata type of the metadata [Goel column 12, lines 31-35 “…the first RAID I/O operation corresponds to stripes 3 and 4, which belong to the merged RAID-DP stripe group 810. I/O processing for this stripe group involves the computation of both the row (R) parity and the diagonal (D) parity, as defined by the RAID-DP protocol…”(Where the examiner has determined the row parity or the diagonal parity reads on the type of metadata)] and [Ellard column 5, lines 27-30 “…The fingerprint can be, for example, a cryptographic hash of the data represented by the item, although a simpler method, such as cyclic redundancy check (CRC), may be sufficient….”]..
Regarding claims 8 and 16, as per claim 1, Goel teaches wherein changing a number of copies of the metadata stored in different physical storage units within the storage device [Goel column 10, lines 7-8 “…if a RAID group is upgraded from RAID-4 to RAID-DP by simply adding an extra parity drive to the RAID group…”] comprises storing, in different dies within the storage device, additional copies of the metadata on different dies [Ellard column 6, lines 20-29 “…the storage manager 21 then identifies the SSMs 7 to which the data block is to be written at 303. As noted above, in one embodiment an attempt is made to write the data block to all of the SSMs 7. In other embodiments, as described further below, an attempt is made to write the data block to more than one, but not all, of the SSMs 7, in order to accomplish wear skewing. The storage manager 21 then attempts at 304 to write the data block and its fingerprint to each of the SSMs that were identified at 303. Next, the storage manager 21 determines whether at least a quorum of the SSMs report that they have written the data block successfully 305…” and lines 47-52 “...It should also be noted that the system can be designed to tolerate the loss of more than one flash memory device. For example, instead of simple mirroring, a redundancy scheme such as RAID-DP, RAID-TP, or any other arbitrary coding scheme that enables arbitrary numbers of failures to be tolerated, could be used…” column 2, lines 53-55 “…where "devices" here can mean flash chips, DIMMs, solid-state drives (SSDs), etc…”(Examiner points to the embodiment can be on the chip level within a device) and column 4, lines 9-10 “…each individual SSM 7 is a flash memory chip…” and column 5, lines 18-20, “…The SSMs 7 can be arranged in a RAID-like manner to tolerate a fail-stop failure (a failure in which a device fails by stopping or shutting down) of one or more of the SSMs 7…” and column 4, last lines “… The storage access layer 24 implements a higher-level disk storage protocol, such as RAID-4, RAID-5 or RAID-DP…” and column 6, lines 47-52 “…It should also be noted that the system can be designed to tolerate the loss of more than one flash memory device. For example, instead of simple mirroring, a redundancy scheme such as RAID-DP, RAID-TP, or any other arbitrary coding scheme that enables arbitrary numbers of failures to be tolerated, could be used….” (The examiner has determined there is at least one embodiment where a flash memory device can be the flash memory chip and as such reads on the claims as the multiple chips within the device will have multiple fingerprints)].
Claims 5 and 13 are rejected under 35 U.S.C. 103 as being unpatentable over Goel et al. [US7,958,304] in view of Ellard et al. [US8,825,938] further in view of Matosevich et al. [US2021/0373796]. Goel teaches dynamically adapting the fault tolerance and performance characteristics of a RAID-based storage system by merging and splitting RAID groups. Ellard teaches use of write allocation decisions to achieve desired levels of wear across a set of redundant solid-state memory devices. Matosevich teaches balancing resiliency and performance by selective use of degraded writes and spare capacity in storage system.
Regarding claims 5 and 13, Goel and Ellard fail to explicitly teach the failure characteristics comprise an estimated rebuild time.
However, Matosevich does teach the failure characteristics comprise an estimated rebuild time [Matosevich paragraph 0073, most lines “…mean time to repair (MTTR), etc…”]
Goel, Ellard, and Matosevich are analogous arts in that they all deal with improving data protection with storage systems.
It would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings of Goel and Ellard with Matosevich’s repair time for the benefit of increasing the user I/O performance by throttling the rebuild process in a RAID system [Matosevich paragraph 0050, last lines “…Applying rebuild throttling will increase the time it takes to complete a rebuild operation and keep the RAID system in a degraded mode of operation, while reducing the impact on user I/O performance…”].
Response to Arguments
Applicant's arguments filed May 7th, 2026, have been fully considered but they are not persuasive.
The applicant argues on page 8, 2nd paragraph, middle lines, that Ellard fails to teach “storing multiple copies of metadata within a single storage device”. The examiner has provided evidence that the prior art does teach embodiments that would reflect a teaching of storing multiple copies of metadata within a single storage device. The examiner has determined, as cited in the above rejection, that Ellard first teaches that the “devices” can mean flash chips and as such the invention can be applied to work at the flash chip level. As can be seen in column 4, lines 9-10 “…each individual SSM 7 is a flash memory chip…”. It is well known that most SSD’s contain multiple flash chips and therefore the method being applied to the multiple flash chips within a single SSD storage device would read on the claim language in question.
Secondly, Ellard teaches another embodiment where multiple SSM 7 can be arranged to form a RAID storage device of various RAID implementations. The examiner has determined that when SSDs are used in a RAID and data is striped across multiple SSDs the RAID device is the actual device, since the RAID device is the one being accessed and not the individual SSDs. The fingerprints are written to multiple SSM 7 within the RAID device. The RAID device then therefore reads on the claim limitation of a single storage device storing multiple copies of the metadata.
Thirdly, Ellard teaches yet another embodiment in column 6, lines 47-52 that “...It should also be noted that the system can be designed to tolerate the loss of more than one flash memory device. For example, instead of simple mirroring, a redundancy scheme such as RAID-DP, RAID-TP, or any other arbitrary coding scheme that enables arbitrary numbers of failures to be tolerated, could be used…”. The examiner interprets this to mean the RAID storage device can implement RAID Double Parity or RAID Triple Parity. The examiner believes this would be in addition to the fingerprints stored in the SSM 7s. But that the SSM 7s would be striped in such a way across the drives as to have double parity bits or triple parity bits also striped across the drives. This means that by having double or triple parity the single RAID device now has multiple copies of metadata (since parity data reads on metadata) within the one single RAID storage device. And as such, it reads on the claims as currently presented. Thus the examiner as provided 3 different embodiments that provide rationales as to how the prior art can be interpreted to read on the current claim language.
Conclusion
THIS ACTION IS MADE FINAL. 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 ERIC CARDWELL whose telephone number is (571)270-1379. The examiner can normally be reached on Monday - Friday 10-6pm EST.
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, Reginald Bragdon can be reached on (571) 272-4204. 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.
/ERIC CARDWELL/Primary Examiner, Art Unit 2139
Prosecution Insights