DETAILED ACTION
This office action is in response to the amendments filed on 11/19/2025.
Claims 3, 5, 11, 13, 18-20 are cancelled.
Claims 1-2, 4, 8-10, 12, 16-17 are amended
Claims 1-2, 4, 6-10, 12, 14-17 are presented for examination.
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 .
Claim Interpretation
Regarding Claims 9-16, they recite in part “A computer program product comprising a computer-readable storage medium having program instructions embodied therewith, the program instructions executable by one or more processors to cause the one or more processors to perform operations comprising:…”. While these claims recite a computer readable storage medium without excluding transitory signals per se, para.0057 of the originally filed specification states “A computer-readable storage medium, as that term is used in the present disclosure, is not to be construed as storage in the form of transitory signals per se,”. Therefore these claims are not interpreted to comprise a signal per se.
Response to Arguments
Applicant’s arguments with respect to the 35 USC 103 rejections to the claims filed on 11/19/2025 in Remarks pg 8-9 have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
Applicant argues further in essence:
[a] “Applicant respectfully asserts that the cited references, alone or in combination, fail to
teach or suggest at least "identifying volumes identified by one or more hosts as data that can be migrated to cloud storage when the volumes were created and identifying volumes based on read/write activity" as recited in independent claims 1, 9, and 17. For at least this reason, Applicant respectfully requests that the rejections of claims 1, 9, and 17, and their dependent claims, be withdrawn.”
In response to [a], while examiner relies upon a new prior art to the limitation of “identifying volumes identified by one or more hosts as data that can be migrated to cloud storage when the volumes were created”, the concept of “identifying volumes based on read/write activity” is still taught by Martin in at least para.0058 and para.0070 wherein the coldest extents identified by the lowest amount of read or write activity are selected for migration, and Perneti in para.0071 and para.0073 wherein cold data is migrated to cloud storage. Therefore, while examiner relies upon a new combination of references for each independent claim, Martin-Perneti is still relied upon for the concept of using read/write activity to identify data to be migrated to cloud storage.
Martin: para.0058 “The extent with the lowest rank is the least busy (e.g., having the lowest amount associated I/O operations) and the highest rank is the busiest (e.g., having the greatest amount of associated I/O operations)…. Additionally, the optimizer 138 maintains an MA data structure identifying a moving average (MA_ of each extent stored in a fast media storage. The extent with a lowest MA is considered a “coldest” extent.”
para.0070 “Referring to step 705, if it is determined that the fast storage media has reached or is above the threshold capacity, the method 700 can include determining and obtaining an extent from the fast storage media that has a coldest moving average. At 715, the method 700 can include migrating the extent with the coldest moving average to a slow storage media (e.g., NAND).”
Perneti: para.0071 “When the forecasted storage consumption value for the given storage system reaches TH.sub.2=90%, the decision engine 420 may perform one or both of: (1) identifying and migrating “unique cold data” from an active tier to a cloud tier; and (2) overriding garbage collection policies and running a garbage collection process.”
para.0073 “Additional details regarding proactive measures for identifying and migrating “unique cold data” from an active tier to a cloud tier will now be described. Cold data may be classified into two types, cold data that is never accessed and cold data that is infrequently accessed.”
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claim(s) 1, 4, 8-9, 12, 16 is/are rejected under 35 U.S.C. 103 as being unpatentable over Martin et al. (hereinafter Martin, US 2021/0117336 A1) in view of Perneti et al. (hereinafter Perneti, Us 2022/0091763 A1) in view of Luo (US 2015/0007183 A1).
Regarding Claim 1, Martin discloses A method migrating data to slow storage (Martin: para.0022 “Some embodiments for memory management include migrating tracks of data units between different types of storage media (e.g., fast and slow) based on how frequently tracks of data units are accessed.” Data is moved from one storage to another based on frequency of access), the method comprising:
identifying, by a storage control unit (Martin: Fig. 3 22a memory management processor), data to be migrated to slow storage (Martin: para.0058 “For each extent associated with an incoming I/O stream, the memory optimizer 138 adds the extent or updates an existing extent in a “hot” ranking data structure 305. The data structure 305 and all other data structures described herein can be searchable structures such as an index, hash table, a linked list, amongst other known searchable structures. In the embodiment depicted by FIG. 3, the “hot” ranking data structure 305 is a list that ranks extents 310 a-n generated from the incoming I/O stream from lowest 310 a to highest 310 n. The extent with the lowest rank is the least busy (e.g., having the lowest amount associated I/O operations) and the highest rank is the busiest (e.g., having the greatest amount of associated I/O operations)…. Additionally, the optimizer 138 maintains an MA data structure identifying a moving average (MA_ of each extent stored in a fast media storage. The extent with a lowest MA is considered a “coldest” extent.” the system, via the memory management processer 22a comprising the memory optimizer 138 in fig. 3, maintains a ranking of extents based on how hot they are based on the number of i/o operations, and further maintains a moving average of each extent, para.0054 “The processor 22 a can also monitor input/output (I/O) streams that include operations (e.g., events) such as read/write operations) through the connection 132 with HA 21.” Such as read and write operations. This ranking list determines data to be migrated as the coldest extents are migrated, in para.0070)
the identifying comprising identifying volumes based on read/write activity (Martin: para.0058 “The extent with the lowest rank is the least busy (e.g., having the lowest amount associated I/O operations) and the highest rank is the busiest (e.g., having the greatest amount of associated I/O operations)…. Additionally, the optimizer 138 maintains an MA data structure identifying a moving average (MA_ of each extent stored in a fast media storage. The extent with a lowest MA is considered a “coldest” extent.” para.0070 “Referring to step 705, if it is determined that the fast storage media has reached or is above the threshold capacity, the method 700 can include determining and obtaining an extent from the fast storage media that has a coldest moving average. At 715, the method 700 can include migrating the extent with the coldest moving average to a slow storage media (e.g., NAND).” The coldest extents, i.e. the lowest amount of read/write operations, is determined to be migrated.);
determining, by the storage control unit, that local storage space has reached a threshold (Martin: para.0070 “The method 700, at 705, can include determining if a fast storage media (e.g., storage class media (SCM)) reached or is above a threshold capacity level (e.g., at or above 98% capacity) using any known or yet to be known embodiment for monitoring storage media capacity. “ it is determines that the fast storage media is at or above a threshold capacity); and
in response to determining that the local storage space has reached the threshold, migrating, by the storage control unit, data from local storage to slow storage (Martin: para.0070 “Referring to step 705, if it is determined that the fast storage media has reached or is above the threshold capacity, the method 700 can include determining and obtaining an extent from the fast storage media that has a coldest moving average. At 715, the method 700 can include migrating the extent with the coldest moving average to a slow storage media (e.g., NAND).” in response to determining that the fast storage media is above a threshold, the coldest extent is migrated to the slow storage media).
However Martin does not explicitly disclose migrating data to cloud storage, the identifying comprising identifying volumes identified by one or more hosts as data that can be migrated to cloud storage when the volumes were created; identifying, by a storage control unit, data to be migrated to cloud storage; migrating, by the storage control unit, data selected from the identified data from local storage to cloud storage.
Perneti discloses migrating data to cloud storage (Perneti: para.0060 “The selected one or more remedial actions may comprise identifying portions of data stored in the at least one storage system that meet one or more usage-based selection criteria, and step 206 may comprise migrating the identified portions of data from the at least one storage system in the active tier of the storage environment to a cloud tier of the storage environment.” Based on usage based criteria, data can be migrated from local storage, such as active tier of a storage array, para.0027 “the storage arrays 106 may themselves provide both an active and an inactive tier of the storage backup system.”);
identifying, by a storage control unit, data to be migrated to cloud storage (Perneti: para.0071 “When the forecasted storage consumption value for the given storage system reaches TH.sub.2=90%, the decision engine 420 may perform one or both of: (1) identifying and migrating “unique cold data” from an active tier to a cloud tier; and (2) overriding garbage collection policies and running a garbage collection process.” Based on a threshold capacity of the storage system, cold data, i.e. data that is less frequently accessed, can be identified to be migrated to cloud storage. Para.0073 “ Cold data may be classified into two types, cold data that is never accessed and cold data that is infrequently accessed. “);
migrating, by the storage control unit, data selected from the identified data from local storage to cloud storage (Perneti: para.0071 “When the forecasted storage consumption value for the given storage system reaches TH.sub.2=90%, the decision engine 420 may perform one or both of: (1) identifying and migrating “unique cold data” from an active tier to a cloud tier; and (2) overriding garbage collection policies and running a garbage collection process.” The identified unique cold data selected from the set of cold data is moved to cloud storage).
Therefore it would have been obvious to one of ordinary skill in the art before the effective filing date to combine Martin with Perneti in order to incorporate migrating data to cloud storage; identifying, by a storage control unit, data to be migrated to cloud storage; migrating, by the storage control unit, data selected from the identified data from local storage to cloud storage.
One of ordinary skill in the art would have been motivated to combine because of the expected benefits of cloud storage that brings additional storage for inactive data (Perneti: para.0018, para.0027).
However Martin-Perneti does not explicitly disclose the identifying comprising identifying volumes identified by one or more hosts as data that can be migrated to cloud storage when the volumes were created.
Luo discloses the identifying comprising identifying volumes identified by one or more hosts as data that can be migrated when the volumes were created (Luo: para.0042 “Each partition may have data integrity information, and this information may be recorded in the controller. The data integrity information is used to mark whether data of a partition is complete. A partition in a complete state indicates that this partition can be migrated, a node to which the partition belongs may serve as a source node of a partition balancing subtask, and data of all partitions may be set to complete by default; a partition in an incomplete state indicates that data on the partition is incomplete and cannot be migrated. For example, the partition is being generated and this partition may be marked as complete after the generation is complete.” When the partition is generated it is marked as incomplete, indicating it cannot be migrated, however after completing generation after the partitions creation, it is indicated as complete, and able to be migrated. Or alternatively, when the volumes become a completed state, they are generated and are marked as complete and therefore able to be migrated.).
Therefore it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Martin-Perneti with that of Luo in order to incorporate the identifying comprising identifying volumes identified by one or more hosts as data that can be migrated when the volumes were created, such that only completed data may be migrated, and apply this concept to the migration to cloud storage in that of Martin-Perneti.
One of ordinary skill in the art would have been motivated to combine because of the expected benefit of data integrity during migration (Luo: para.0041).
Regarding Claim 4, Martin-Perneti-Luo discloses claim 1 as set forth above.
Martin further discloses wherein the identifying volumes based on read/write activity comprises ranking a plurality of volumes based on read/write activity, and wherein the data for migrating is based on the ranking. (Martin: para.0058 “. The extent with the lowest rank is the least busy (e.g., having the lowest amount associated I/O operations) and the highest rank is the busiest (e.g., having the greatest amount of associated I/O operations)…. Additionally, the optimizer 138 maintains an MA data structure identifying a moving average (MA_ of each extent stored in a fast media storage. The extent with a lowest MA is considered a “coldest” extent.” the system maintains a ranking of extents based on how hot they are based on the number of i/o operations, and further maintains a moving average of each extent, para.0054 “The processor 22 a can also monitor input/output (I/O) streams that include operations (e.g., events) such as read/write operations) through the connection 132 with HA 21.” Such as read and write operations. This ranking list determines data to be migrated as the coldest extents are migrated, in para.0070 “ the method 700 can include determining and obtaining an extent from the fast storage media that has a coldest moving average. At 715, the method 700 can include migrating the extent with the coldest moving average to a slow storage media (e.g., NAND).”).
However Martin does not explicitly disclose wherein the data selected from the identified data for migrating is based on the ranking.
Perneti discloses wherein the data selected from the identified data for migrating is based on the ranking (Perneti: para.0071 “When the forecasted storage consumption value for the given storage system reaches TH.sub.2=90%, the decision engine 420 may perform one or both of: (1) identifying and migrating “unique cold data” from an active tier to a cloud tier; and (2) overriding garbage collection policies and running a garbage collection process.” The identified unique cold data selected from the set of cold data that is ranked as cold or not cold similar to that of Martin, is moved to cloud storage).
Therefore it would have been obvious to one of ordinary skill in the art before the effective filing date to combine Martin with Perneti in order to incorporate wherein the data selected from the identified data for migrating is based on the ranking, and apply this concept to the ranked hot to cold data in Martin, such that unique cold data from the ranked set of hot and cold data is identified to be migrated.
One of ordinary skill in the art would have been motivated to combine because of the expected benefits of cloud storage that brings additional storage for inactive data (Perneti: para.0018, para.0027).
Regarding Claim 8, Martin-Perneti-Luo discloses claim 1 as set forth above.
Martin further discloses wherein the local data is assigned to a plurality of classifications based on read/write activity and wherein the data comprises selecting data in a classification associated with low read/write activity (Martin: para.0022 “Tracks of data units that are frequency accessed (e.g., having accesses above an access threshold) are considered “hot” tracks. The embodiments can move hot tracks to fast storage media to ensure fast response times, while tracks that are not hot can be moved to slow storage media.” Para.0058 “In the embodiment depicted by FIG. 3, the “hot” ranking data structure 305 is a list that ranks extents 310 a-n generated from the incoming I/O stream from lowest 310 a to highest 310 n. The extent with the lowest rank is the least busy (e.g., having the lowest amount associated I/O operations) and the highest rank is the busiest (e.g., having the greatest amount of associated I/O operations). The memory optimizer 138 can calculate a ranking based on one or more of amounts I/O operations (i.e., I/O count) associated with each extent, a duration that each extent is maintained in the “hot” ranking data structure 305, a frequency of I/O counts for each extent over a period, amongst other parameters. In embodiments, the memory optimizer 138 can rank records stored in the “hot” ranking data structure 305 as a function of ‘n’ (e.g., 2) exponential moving averages of I/O operations (e.g., events) over time. Additionally, the optimizer 138 maintains an MA data structure identifying a moving average (MA_ of each extent stored in a fast media storage. The extent with a lowest MA is considered a “coldest” extent.” The extents are ranked based on how hot or cold they are. For example, the highest rank item is considered to be the hottest extent, and the lowest rank is considered to be the coldest extent, based on the number of i/o operations including read and write.).
However Martin does not explicitly disclose wherein the data selected from the identified data comprises selecting data in a classification associated with low read/write activity.
Perneti discloses wherein the data selected from the identified data comprises selecting data in a classification associated with low read/write activity (Perneti: para.0071 “When the forecasted storage consumption value for the given storage system reaches TH.sub.2=90%, the decision engine 420 may perform one or both of: (1) identifying and migrating “unique cold data” from an active tier to a cloud tier; and (2) overriding garbage collection policies and running a garbage collection process.” The identified unique cold data selected from the set of cold data that is ranked as cold or not cold similar to that of Martin, is moved to cloud storage. The cold data is identified as data that is infrequently accessed, i.e. via read and writer operations. Para.0024 “The host devices 102 interact with the storage array 106-1 utilizing read and write commands as well as other types of commands that are transmitted over the network 104.” Para.0073 “Cold data may be classified into two types, cold data that is never accessed and cold data that is infrequently accessed. Here, the case of “never accessed” data is considered.”).
Therefore it would have been obvious to one of ordinary skill in the art before the effective filing date to combine Martin with Perneti in order to incorporate wherein the data selected from the identified data comprises selecting data in a classification associated with low read/write activity, and apply this concept to the ranked hot to cold data in Martin, such that unique cold data from the ranked set of hot and cold data is identified to be migrated.
One of ordinary skill in the art would have been motivated to combine because of the expected benefits of cloud storage that brings additional storage for inactive data (Perneti: para.0018, para.0027).
Regarding Claims 9, 12 and 16 they recite all of the same steps as claims 1, 4, and 8, but in A computer program product comprising a computer-readable storage medium having program instructions embodied therewith, the program instructions executable by one or more processors to cause the one or more processors to perform operations comprising: (Martin: para.0051-0054). Therefore claims 9, 12 and 16 are rejected under the same rationale as claims 1, 4, and 8.
Claim(s) 2, 10 is/are rejected under 35 U.S.C. 103 as being unpatentable over Martin et al. (hereinafter Martin, US 2021/0117336 A1) in view of Perneti et al. (hereinafter Perneti, Us 2022/0091763 A1) in view of Luo (US 2015/0007183 A1) further in view of Brenner et al. (hereinafter US 2021/0303515 A1).
Regarding Claim 2, Martin-Perneti-Luo discloses claim 1 as set forth above.
However Matin-Perneti-Luo does not explicitly disclose wherein the one or more hosts are preconfigured to include an indication that a volume can be migrated to cloud storage based on a type of data of the volume.
Brenner discloses wherein the one or more hosts are preconfigured to include an indication that a volume can be migrated to cloud storage based on a type of data of the volume (Brenner: para.0038 “The backup software would communicate with the DLRE. While the backup operation is in progress, and the DLRE would respond with a rule such as: for all highly restrictive files, those files must be retained forever (never deleted) and cannot be stored on publicly accessible storage, such as a Cloud tier. It is up to the backup software to enforce and follow this rule. The DLRE only provides the rules that the backup software should respect.” para.0042 “Thus for the example of FIG. 6, default data has a rule that is unrestricted, and thus this data can be stored locally or cloud tiered, and can be replicated and retained at will. Other types of data, such as highly restricted data, is subject to stricter rules, such as it cannot be cloud tiered, and it cannot be deleted, i.e., retained forever.” The server that comprises the back up software is the host, and obtains rules for migration based on labels of data type. In this case, restrictive data type may not be migrated to cloud storage.).
Therefore it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Martin-Perneti-Luo with that of Brenner in order to incorporate wherein the one or more hosts are preconfigured to include an indication that a volume can be migrated to cloud storage based on a type of data of the volume.
One of ordinary skill in the art would have been motivated to combine because of the expected benefit of improved security of the system by not moving restrictive data to cloud storage (Brenner: para.0003, para.0038).
Regarding Claim 10, it does not teach nor further define over the limitations of claim 2, therefore the supporting rationale for the rejection to claim 2 applies equally as well to that of claim 10.
Claim(s) 6, 14 is/are rejected under 35 U.S.C. 103 as being unpatentable over Martin et al. (hereinafter Martin, US 2021/0117336 A1) in view of Perneti et al. (hereinafter Perneti, Us 2022/0091763 A1) in view of Luo (US 2015/0007183 A1) in view of Belluomini et al. (hereinafter Bell, US 2012/0102350 A1).
Regarding Claim 6, Martin-Perneti-Luo discloses claim 1 as set forth above.
Martin further discloses determining, by the storage control unit, that available storage space is below the threshold (Martin: Fig. 7 705, 735, para.0070 “ The method 700, at 705, can include determining if a fast storage media (e.g., storage class media (SCM)) reached or is above a threshold capacity level (e.g., at or above 98% capacity) using any known or yet to be known embodiment for monitoring storage media capacity…. If so, the method 700 returns to step 725. If not, the method 700 can include migrating a track associated with the record to the fast storage media. ” based on the same threshold for migration, instead the storage is below the threshold is determined and moves on to step 725.); and
in response to determining that available storage space is below the threshold, migrating data from slow storage to local storage (Martin: Fig. 7 705, 735, para.0070 “ The method 700, at 705, can include determining if a fast storage media (e.g., storage class media (SCM)) reached or is above a threshold capacity level (e.g., at or above 98% capacity) using any known or yet to be known embodiment for monitoring storage media capacity…. If so, the method 700 returns to step 725. If not, the method 700 can include migrating a track associated with the record to the fast storage media. ” In response to the capacity being below the threshold, i.e. there is sufficient storage, data from the slow storage can be moved to the fast storage, i.e. local. Para.0057 “ For example, IB learning can directly analyze an I/O stream to evaluate the data units that are candidates for promotion from slow storage media (NOT-AND (“NAND”) memory to fast storage media (e.g., storage class memory (“SCM”)).” For example via a promotion process).
However Martin does not explicitly disclose determining, by the storage control unit, that available storage space is above a second threshold, in response to determining that available storage space is above the second threshold, migrating data from cloud storage to local storage.
Perneti discloses cloud storage (Perneti: para.0071 “When the forecasted storage consumption value for the given storage system reaches TH.sub.2=90%, the decision engine 420 may perform one or both of: (1) identifying and migrating “unique cold data” from an active tier to a cloud tier; and (2) overriding garbage collection policies and running a garbage collection process.” Based on a threshold capacity of the storage system, cold data can be identified to be migrated to cloud storage, the cold data being identified based on frequency of access in para.0073 “Additional details regarding proactive measures for identifying and migrating “unique cold data” from an active tier to a cloud tier will now be described. Cold data may be classified into two types, cold data that is never accessed and cold data that is infrequently accessed.”);
Therefore it would have been obvious to one of ordinary skill in the art before the effective filing date to combine Martin with Perneti in order to incorporate cloud storage, and apply the process of Martin to the cloud storage migration process of Perneti.
One of ordinary skill in the art would have been motivated to combine because of the expected benefits of cloud storage that brings additional storage for inactive data (Perneti: para.0018, para.0027).
However Martin-Perneti-Luo does not explicitly disclose determining, by the storage control unit, that available storage space is above a second threshold, in response to determining that available storage space is above the second threshold, migrating data from cloud storage to local storage.
Bell discloses determining, by the storage control unit, that available storage space is above a second threshold, in response to determining that available storage space is above the second threshold, migrating data from one storage to another storage (Bell: para.0045 “In step 408, the placement module 130 determines at least one storage device (among the plurality of storage devices) in the one selected storage tier (selected by the placement module 130 to migrate the storage extent to) that has available storage resources that would satisfy the storage extent's performance and capacity requirements (see step 208). In step 410, the placement module 130 migrates the storage extent (from the storage tier it was allocated) to the one selected storage tier (selected by the placement module 130 to migrate the storage extent to) and to the one storage device (among the at least one storage device) that has the least amount of available storage capacity (see step 210).” When migrating data, it is determined that the destination storage device contains enough space for migrating the data, i.e. above a second threshold of available storage, and if so, the data is migrated to the storage that has available storage above a threshold).
Therefore it would be obvious to one of ordinary skill in the art before the effective filing date to combine Martin-Perneti-Luo with Bell in order to incorporate determining, by the storage control unit, that available storage space is above a second threshold, in response to determining that available storage space is above the second threshold, migrating data from cloud storage to local storage, and apply this concept to Martin that only considered if the used storage is not above a threshold capacity when promoting data back to the local storage.
One of ordinary skill in the art would have been motivated to combine because of the expected benefit of considering there is enough space to accommodate the particular piece of data being moved to the storage (Bell: para.0045).
Regarding claim 14, it does not teach nor further define over the limitations of claim 6, therefore the supporting rationale for the rejection of claim 6 applies equally as well to that of claim 14.
Claim(s) 7, 15 is/are rejected under 35 U.S.C. 103 as being unpatentable over Martin et al. (hereinafter Martin, US 2021/0117336 A1) in view of Perneti et al. (hereinafter Perneti, Us 2022/0091763 A1) in view of Luo (US 2015/0007183 A1) in view of Dantkale et al. (hereinafter Dant, US 10,264,064 B1).
Regarding Claim 7, Martin-Perneti-Luo discloses claim 1 as set forth above.
However, while Perneti discloses the concept of increasing the speed of the data movement operation based on urgency for the node in para.0077, Martin-Perneti-Luo does not explicitly disclose determining that storage space is below a second threshold; and in response to determining that the storage space is below the second threshold, increasing a rate of the migrating the data from local storage to cloud storage.
Dant discloses determining that storage space is below a second threshold (Dant: col. 11 lines 50-67 “In some examples, a data replication process may be elevated and/or increased to achieve data replication more aggressively and/or rapidly. In one example, a data replication process may be elevated and/or increased to an aggressive data replication job in the event that the storage-utilization total for a virtual machine reaches and/or exceeds a certain threshold.” It can be determined that the storage utilization for a VM is above a threshold, therefore the available storage space is below a threshold.); and
in response to determining that the storage space is below the second threshold, increasing a rate of the migrating the data from local storage to remote storage (Dant: col. 11 lines 50-67 “In some examples, a data replication process may be elevated and/or increased to achieve data replication more aggressively and/or rapidly. In one example, a data replication process may be elevated and/or increased to an aggressive data replication job in the event that the storage-utilization total for a virtual machine reaches and/or exceeds a certain threshold.” Col. 11 lines 22-38 “ In some examples, scheduling module 108 may direct compute nodes 202(1)-(N) to initiate data replication processes as scheduled in order of highest storage-utilization total to lowest storage-utilization total. For example, scheduling module 108 may direct compute node 202(1)) to initiate a data replication process with data node 206 in connection with virtual machine 210. In response to this directive, compute node 202(1)) may initiate and/or perform the data replication process by moving and/or copying a log, layer, and/or version of virtual disk 220 to data node 206. Once compute node 202(1)) has moved and/or copied this log, layer, and/or version of virtual disk 220 to data node 206 in this way, compute node 202(1)) may reclaim the storage space previously occupied by this log, layer, and/or version of virtual disk 220 by way of a garbage collection process.” It can be determined that the storage utilization for a VM is above a threshold, therefore the available storage space is below a threshold, and in response, the speed of data replication may be increased, such that the data replication is achieved more rapidly. The local storage space may then be reclaimed via garbage collection operation.).
Therefore it would have been obvious to one of ordinary skill in the art before the effective filing date to combine Martin-Perneti-Luo with Dant in order to incorporate determining that storage space is below a second threshold and in response to determining that the storage space is below the second threshold, increasing a rate of the migrating the data from local storage to remote storage, and apply this concept to the migration of data to the cloud storage of Martin-Perneti-Luo.
One of ordinary skill in the art would have been motivated to combine because of the expected benefit of prioritizing higher priority nodes that have a higher utilization when freeing up data (Dant: col. 11 lines 50-67, Col. 11 lines 22-38).
Regarding claim 15, it does not teach nor further define over the limitations of claim 7, therefore the supporting rationale for the rejection of claim 7 applies equally as well to that of claim 15.
Claim(s) 17 is/are rejected under 35 U.S.C. 103 as being unpatentable over Martin et al. (hereinafter Martin, US 2021/0117336 A1) in view of Perneti et al. (hereinafter Perneti, Us 2022/0091763 A1) in view of Luo (US 2015/0007183 A1) in view of Dantkale et al. (hereinafter Dant, US 10,264,064 B1) in view of Belluomini et al. (hereinafter Bell, US 2012/0102350 A1).
Regarding Claim 17, Martin discloses A system comprising (Martin: Fig. 1 including data storage system 12 and hosts 14a-n), a storage control unit having one or more processors communicatively coupled to one or more memories, the one or more processors configured to perform operations (Martin: Fig. 1, para.0041, para.0045-0046 memory and processor) comprising:
identifying data to be migrated to slow storage (Martin: para.0058 “For each extent associated with an incoming I/O stream, the memory optimizer 138 adds the extent or updates an existing extent in a “hot” ranking data structure 305. The data structure 305 and all other data structures described herein can be searchable structures such as an index, hash table, a linked list, amongst other known searchable structures. In the embodiment depicted by FIG. 3, the “hot” ranking data structure 305 is a list that ranks extents 310 a-n generated from the incoming I/O stream from lowest 310 a to highest 310 n. The extent with the lowest rank is the least busy (e.g., having the lowest amount associated I/O operations) and the highest rank is the busiest (e.g., having the greatest amount of associated I/O operations)…. Additionally, the optimizer 138 maintains an MA data structure identifying a moving average (MA_ of each extent stored in a fast media storage. The extent with a lowest MA is considered a “coldest” extent.” the system, via the memory management processer 22a comprising the memory optimizer 138 in fig. 3, maintains a ranking of extents based on how hot they are based on the number of i/o operations, and further maintains a moving average of each extent, para.0054 “The processor 22 a can also monitor input/output (I/O) streams that include operations (e.g., events) such as read/write operations) through the connection 132 with HA 21.” Such as read and write operations. This ranking list determines data to be migrated as the coldest extents are migrated, in para.0070),
the identifying comprising identifying volumes based on read/write activity (Martin: para.0058 “The extent with the lowest rank is the least busy (e.g., having the lowest amount associated I/O operations) and the highest rank is the busiest (e.g., having the greatest amount of associated I/O operations)…. Additionally, the optimizer 138 maintains an MA data structure identifying a moving average (MA_ of each extent stored in a fast media storage. The extent with a lowest MA is considered a “coldest” extent.” para.0070 “Referring to step 705, if it is determined that the fast storage media has reached or is above the threshold capacity, the method 700 can include determining and obtaining an extent from the fast storage media that has a coldest moving average. At 715, the method 700 can include migrating the extent with the coldest moving average to a slow storage media (e.g., NAND).” The coldest extents, i.e. the lowest amount of read/write operations, is determined to be migrated.);
determining that local storage space has reached a first threshold (Martin: para.0070 “The method 700, at 705, can include determining if a fast storage media (e.g., storage class media (SCM)) reached or is above a threshold capacity level (e.g., at or above 98% capacity) using any known or yet to be known embodiment for monitoring storage media capacity. “ it is determines that the fast storage media is at or above a threshold capacity);
in response to determining that the local storage space has reached the first threshold, migrating data from local storage to slow storage (Martin: para.0070 “Referring to step 705, if it is determined that the fast storage media has reached or is above the threshold capacity, the method 700 can include determining and obtaining an extent from the fast storage media that has a coldest moving average. At 715, the method 700 can include migrating the extent with the coldest moving average to a slow storage media (e.g., NAND).” in response to determining that the fast storage media is above a threshold, the coldest extent is migrated to the slow storage media),
determining, by the storage control unit, that available storage space is below a third threshold (Martin: Fig. 7 705, 735, para.0070 “ The method 700, at 705, can include determining if a fast storage media (e.g., storage class media (SCM)) reached or is above a threshold capacity level (e.g., at or above 98% capacity) using any known or yet to be known embodiment for monitoring storage media capacity…. If so, the method 700 returns to step 725. If not, the method 700 can include migrating a track associated with the record to the fast storage media. ” when the available storage space falls below a threshold, method moves on to step 725.); and
in response to determining that the available storage space is below the third threshold, migrating data from slow storage to local storage (Martin: Fig. 7 705, 735, para.0070 “ The method 700, at 705, can include determining if a fast storage media (e.g., storage class media (SCM)) reached or is above a threshold capacity level (e.g., at or above 98% capacity) using any known or yet to be known embodiment for monitoring storage media capacity…. If so, the method 700 returns to step 725. If not, the method 700 can include migrating a track associated with the record to the fast storage media. ” In response to the capacity being below the threshold, i.e. there is sufficient storage, data from the slow storage can be moved to the fast storage, i.e. local. Para.0057 “ For example, IB learning can directly analyze an I/O stream to evaluate the data units that are candidates for promotion from slow storage media (NOT-AND (“NAND”) memory to fast storage media (e.g., storage class memory (“SCM”)).” For example via a promotion process).
However Martin does not explicitly disclose identifying data to be migrated to cloud storage; the identifying comprising identifying volumes identified by one or more hosts as data that can be migrated to cloud storage when the volumes were created; migrating data selected from the identified data from local storage to cloud storage, wherein less that all of the identified data is selected for migrating, wherein the volumes identified by one or more host as data that can be migrated to cloud storage is selected over volumes identified based on read/write activity; determining that local storage space has reached a second threshold while migrating data; in response to determining that the local storage space has reached the second threshold, increasing a rate of migrating data; determining that available storage space is above a third threshold; and in response to determining that available storage space is above the third threshold, migrating data from cloud storage to local storage.
Perneti discloses identifying data to be migrated to cloud storage (Perneti: para.0071 “When the forecasted storage consumption value for the given storage system reaches TH.sub.2=90%, the decision engine 420 may perform one or both of: (1) identifying and migrating “unique cold data” from an active tier to a cloud tier; and (2) overriding garbage collection policies and running a garbage collection process.” Based on a threshold capacity of the storage system, cold data, i.e. data that is less frequently accessed, can be identified to be migrated to cloud storage. Para.0073 “ Cold data may be classified into two types, cold data that is never accessed and cold data that is infrequently accessed. “);
migrating data selected from the identified data from local storage to cloud storage, wherein less that all of the identified data is selected for migrating, (Perneti: para.0071 “When the forecasted storage consumption value for the given storage system reaches TH.sub.2=90%, the decision engine 420 may perform one or both of: (1) identifying and migrating “unique cold data” from an active tier to a cloud tier; and (2) overriding garbage collection policies and running a garbage collection process.” The identified unique cold data selected from the set of cold data is moved to cloud storage).
Therefore it would have been obvious to one of ordinary skill in the art before the effective filing date to combine Martin with Perneti in order to incorporate identifying data to be migrated to cloud storage; migrating data selected from the identified data from local storage to cloud storage wherein less that all of the identified data is selected for migrating,.
One of ordinary skill in the art would have been motivated to combine because of the expected benefits of cloud storage that brings additional storage for inactive data (Perneti: para.0018, para.0027).
However Martin-Perneti does not explicitly disclose the identifying comprising identifying volumes identified by one or more hosts as data that can be migrated to cloud storage when the volumes were created; wherein the volumes identified by one or more host as data that can be migrated to cloud storage is selected over volumes identified based on read/write activity; determining that local storage space has reached a second threshold while migrating data; in response to determining that the local storage space has reached the second threshold, increasing a rate of migrating data; determining that available storage space is above a third threshold; and in response to determining that available storage space is above the third threshold, migrating data from cloud storage to local storage.
Luo discloses the identifying comprising identifying volumes identified by one or more hosts as data that can be migrated when the volumes were created (Luo: para.0042 “Each partition may have data integrity information, and this information may be recorded in the controller. The data integrity information is used to mark whether data of a partition is complete. A partition in a complete state indicates that this partition can be migrated, a node to which the partition belongs may serve as a source node of a partition balancing subtask, and data of all partitions may be set to complete by default; a partition in an incomplete state indicates that data on the partition is incomplete and cannot be migrated. For example, the partition is being generated and this partition may be marked as complete after the generation is complete.” When the partition is generated it is marked as incomplete, indicating it cannot be migrated, however after completing generation after the partitions creation, it is indicated as complete, and able to be migrated. Or alternatively, when the volumes become a completed state, they are generated and are marked as complete and therefore able to be migrated.).
Therefore it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Martin-Perneti with that of Luo in order to incorporate the identifying comprising identifying volumes identified by one or more hosts as data that can be migrated when the volumes were created, such that only completed data may be migrated, and apply this concept to the migration to cloud storage as disclosed in Martin-Perneti.
One of ordinary skill in the art would have been motivated to combine because of the expected benefit of data integrity during migration (Luo: para.0041).
However Martin-Perneti-Luo does not explicitly disclose wherein the volumes identified by one or more host as data that can be migrated to cloud storage is selected over volumes identified based on read/write activity; determining that local storage space has reached a second threshold while migrating data; in response to determining that the local storage space has reached the second threshold, increasing a rate of migrating data; determining that available storage space is above a third threshold; and in response to determining that available storage space is above the third threshold, migrating data from cloud storage to local storage.
Dant discloses wherein the volumes identified by one or more host as data that can be migrated is selected over other identified volumes (Dant: col. 6 lines 39-59 “(3) identify, based at least in part on the storage-utilization totals, which of virtual machines 210 and 212 has the highest storage-utilization total, (4) prioritize the virtual machine with the highest storage-utilization total and then in response to the prioritization” volumes of data identified to be migrated can be prioritized over one another based on its utilization needs, therefore one volume of data that is indicated to be migrated may be migrated prior to another.);
determining that local storage space has reached a second threshold while migrating data (Dant: col. 11 lines 50-67 “In some examples, a data replication process may be elevated and/or increased to achieve data replication more aggressively and/or rapidly. In one example, a data replication process may be elevated and/or increased to an aggressive data replication job in the event that the storage-utilization total for a virtual machine reaches and/or exceeds a certain threshold. Additionally or alternatively, a data replication process may be elevated and/or increased to an aggressive data replication job in the event that a transfer-rate total exceeds a certain threshold. The transfer-rate total may represent the sum of all the transfer rates of data replication processes being performed on the data node at any point in time, and the certain threshold may represent the maximum write speed of the data node. As an example, scheduling module 108 may direct compute node 202(1)) to elevate and/or increase a data replication process in progress to an aggressive data replication job.” It can be determined that the storage utilization for a VM is above a threshold for a data replication that is in progress, therefore the available storage space is below a threshold.);
in response to determining that the local storage space has reached the second threshold, increasing a rate of migrating data (Dant: col. 11 lines 50-67 “In some examples, a data replication process may be elevated and/or increased to achieve data replication more aggressively and/or rapidly. In one example, a data replication process may be elevated and/or increased to an aggressive data replication job in the event that the storage-utilization total for a virtual machine reaches and/or exceeds a certain threshold…. As an example, scheduling module 108 may direct compute node 202(1)) to elevate and/or increase a data replication process in progress to an aggressive data replication job” Col. 11 lines 22-38 “ In some examples, scheduling module 108 may direct compute nodes 202(1)-(N) to initiate data replication processes as scheduled in order of highest storage-utilization total to lowest storage-utilization total. For example, scheduling module 108 may direct compute node 202(1)) to initiate a data replication process with data node 206 in connection with virtual machine 210. In response to this directive, compute node 202(1)) may initiate and/or perform the data replication process by moving and/or copying a log, layer, and/or version of virtual disk 220 to data node 206. Once compute node 202(1)) has moved and/or copied this log, layer, and/or version of virtual disk 220 to data node 206 in this way, compute node 202(1)) may reclaim the storage space previously occupied by this log, layer, and/or version of virtual disk 220 by way of a garbage collection process.” It can be determined that the storage utilization for a VM is above a threshold, therefore the available storage space is below a threshold, and in response, the speed of data replication that is in progress may be increased, such that the data replication is achieved more rapidly. The local storage space may then be reclaimed via garbage collection operation.).
Therefore it would have been obvious to one of ordinary skill in the art before the effective filing date to combine Martin-Perneti-Luo with Dant in order to incorporate wherein the volumes identified by one or more host as data that can be migrated is selected over other identified volumes, determining that local storage space has reached a second threshold while migrating data, in response to determining that the local storage space has reached the second threshold, increasing a rate of migrating data, and apply the concept of migrating one data over another to that of the volumes identified by one or more host as data that can be migrated to cloud storage and volumes identified based on read/write activity as described in Martin-Perneti-Luo.
One of ordinary skill in the art would have been motivated to combine because of the expected benefit of prioritizing higher priority nodes that have a higher utilization when freeing up data (Dant: col. 11 lines 50-67, Col. 11 lines 22-38).
However Martin-Perneti-Luo-Dant does not explicitly disclose determining that available storage space is above a third threshold; and in response to determining that available storage space is above the third threshold, migrating data from cloud storage to local storage.
Bell discloses determining that available storage space is above a third threshold; and in response to determining that available storage space is above the third threshold, migrating data from one storage to another storage (Bell: para.0045 “In step 408, the placement module 130 determines at least one storage device (among the plurality of storage devices) in the one selected storage tier (selected by the placement module 130 to migrate the storage extent to) that has available storage resources that would satisfy the storage extent's performance and capacity requirements (see step 208). In step 410, the placement module 130 migrates the storage extent (from the storage tier it was allocated) to the one selected storage tier (selected by the placement module 130 to migrate the storage extent to) and to the one storage device (among the at least one storage device) that has the least amount of available storage capacity (see step 210).” When migrating data, it is determined that the destination storage device contains enough space for migrating the data, i.e. above a second threshold of available storage, and if so, the data is migrated to the storage that has available storage above a threshold).
Therefore it would be obvious to one of ordinary skill in the art before the effective filing date to combine Martin-Perneti-Luo-Dant with Bell in order to incorporate determining that available storage space is above a third threshold; and in response to determining that available storage space is above the third threshold, migrating data from one storage to another storage, and apply this concept to Martin that only considered if the used storage is not above a threshold capacity when promoting data back to the local storage, and to the cloud storage that is used for slow data as described in Perneti.
One of ordinary skill in the art would have been motivated to combine because of the expected benefit of considering there is enough space to accommodate the particular piece of data being moved to the storage (Bell: para.0045).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. Lin et al. US 2021/0303170 A1 see para.0025, 0033 showing migration of cold data to cloud storage
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 EUI H KIM whose telephone number is (571)272-8133. The examiner can normally be reached 7:30-5 M-R, M-F alternating.
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, Kamal B Divecha can be reached at 5712725863. 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.
/EUI H KIM/ Examiner, Art Unit 2453
/KAMAL B DIVECHA/ Supervisory Patent Examiner, Art Unit 2453