Настройки

Укажите год
-

Небесная энциклопедия

Космические корабли и станции, автоматические КА и методы их проектирования, бортовые комплексы управления, системы и средства жизнеобеспечения, особенности технологии производства ракетно-космических систем

Подробнее
-

Мониторинг СМИ

Мониторинг СМИ и социальных сетей. Сканирование интернета, новостных сайтов, специализированных контентных площадок на базе мессенджеров. Гибкие настройки фильтров и первоначальных источников.

Подробнее

Форма поиска

Поддерживает ввод нескольких поисковых фраз (по одной на строку). При поиске обеспечивает поддержку морфологии русского и английского языка
Ведите корректный номера.
Ведите корректный номера.
Ведите корректный номера.
Ведите корректный номера.
Укажите год
Укажите год
Применить Всего найдено 144. Отображено 105.
06-12-2016 дата публикации

Determining adjustments of storage device timeout values based on synchronous or asynchronous remote copy state

Номер: US0009513827B1
Автор: Matthew G. Borlick, Karl A. Nielsen, Richard P. Oubre, Jr., Todd C. Sorenson, BORLICK MATTHEW G, NIELSEN KARL A, OUBRE JR RICHARD P, SORENSON TODD C, Borlick Matthew G., Nielsen Karl A., Oubre, Jr. Richard P., Sorenson Todd C.
Принадлежит: INTETRNATIONAL BUSINESS MACHINES CORPORATION, IBM, INTETRNATIONAL BUSINESS MACHINES CORP, INTERNATIONAL BUSINESS MACHINES CORPORATION

A determination is made as to whether a plurality of storage volumes controlled by a processor complex are secondary storage volumes that are in an asynchronous copy relationship with a plurality of primary storage volumes. A storage device timeout value for a storage device that stores the plurality of storage volumes is changed from a predetermined low value to a predetermined high value, wherein the predetermined high value is indicative of a greater duration of time than the predetermined low value, in response to determining that each of the plurality of storage volumes controlled by the processor complex and stored in the storage device are secondary storage volumes that are in the asynchronous copy relationship with the plurality of primary storage volumes.

Подробнее
Номер записи: 1
02-01-2018 дата публикации

Raid data loss prevention

Номер: US0009858148B2
Автор: Matthew G. Borlick, Lokesh M. Gupta, Clint A. Hardy, Karl A. Nielsen, Brian A. Rinaldi, BORLICK MATTHEW G, GUPTA LOKESH M, HARDY CLINT A, NIELSEN KARL A, RINALDI BRIAN A, Borlick Matthew G., Gupta Lokesh M., Hardy Clint A., Nielsen Karl A., Rinaldi Brian A.
Принадлежит: International Business Machines Corporation, IBM

A method for preventing data loss in a RAID includes monitoring the age of storage drives making up a RAID. When a storage drive in the RAID reaches a specified age, the method individually tests the storage drive by subjecting the storage drive to a stress workload test. This stress workload test may be designed to place additional stress on the storage drive while refraining from adding stress to other storage drives in the RAID. In the event the storage drive fails the stress workload test (e.g., the storage drive cannot adequately handle the additional workload or generates errors in response to the additional workload), the method replaces the storage drive with a spare storage drive and rebuilds the RAID. In certain embodiments, the method tests the storage drive with greater frequency as the age of the storage drive increases. A corresponding system and computer program product are also disclosed.

Подробнее
Номер записи: 2
05-01-2017 дата публикации

STATISTIC-BASED ISOLATION OF LETHARGIC DRIVES

Номер: US20170003888A1
Автор: Matthew J. Kalos, Karl A. Nielsen, KALOS MATTHEW J, NIELSEN KARL A, Kalos Matthew J., Nielsen Karl A.
Принадлежит:

A method is provided for identifying a lethargic drive. The method includes executing a command directed to at least two drives in a redundant array of independent disks (RAID) configuration. Each of the drives of the at least two drives is associated with a plurality of timing buckets. The method also includes determining a completion time of the command, and, for each of the at least two drives that the command was directed to, counting the completion time of the command in one of the timing buckets associated with the drive. 1. A method , comprising:executing a command directed to at least two drives in a redundant array of independent disks (RAID) configuration, wherein each of the drives of the at least two drives is associated with a plurality of timing buckets;determining a completion time of the command; andfor each of the at least two drives that the command was directed to, counting the completion time of the command in one of the timing buckets associated with the drive.2. The method of claim 1 , further comprising identifying one of the at least two drives as a lethargic drive.3. The method of claim 2 , wherein the lethargic drive is identified by automated logic that analyzes the timing buckets of the drives.4. The method of claim 3 , wherein the timing buckets of the one of the at least two drives identified as the lethargic drive exceed a threshold.5. The method of claim 4 , wherein the threshold includes a total number of counts in all of the timing buckets of the one of the at least two drives identified as the lethargic drive.6. The method of claim 4 , wherein the threshold includes a total number of counts in at least one of the timing buckets of the one of the at least two drives identified as the lethargic drive.7. The method of claim 4 , wherein the threshold is set with respect to the other drives.8. The method of claim 7 , wherein the threshold includes a total number of counts in all of the timing buckets of the one of the at least two ...

Подробнее
Номер записи: 3
23-02-2017 дата публикации

DETERMINING ADJUSTMENTS OF STORAGE DEVICE TIMEOUT VALUES BASED ON SYNCHRONOUS OR ASYNCHRONOUS REMOTE COPY STATE

Номер: US20170052724A1
Автор: Matthew G. Borlick, Karl A. Nielsen, Richard P. Oubre, JR., Todd C. Sorenson, BORLICK MATTHEW G, NIELSEN KARL A, OUBRE JR RICHARD P, SORENSON TODD C, Borlick Matthew G., Nielsen Karl A., Oubre, JR. Richard P., Sorenson Todd C.
Принадлежит:

A determination is made as to whether a plurality of storage volumes controlled by a processor complex are secondary storage volumes that are in an asynchronous copy relationship with a plurality of primary storage volumes. A storage device timeout value for a storage device that stores the plurality of storage volumes is changed from a predetermined low value to a predetermined high value, wherein the predetermined high value is indicative of a greater duration of time than the predetermined low value, in response to determining that each of the plurality of storage volumes controlled by the processor complex and stored in the storage device are secondary storage volumes that are in the asynchronous copy relationship with the plurality of primary storage volumes. 120-. (canceled)21. A method , comprising:determining that at least one storage volume of a plurality of storage volumes controlled by a processor complex and stored in a storage device is a secondary storage volume that is in a synchronous copy relationship with a primary storage volume of a plurality of primary storage volumes, wherein a storage device timeout value is to be assigned to one of at least two values comprising a predetermined low value and a predetermined high value, wherein the predetermined high value is indicative of a greater duration of time than the predetermined low value; andassigning the storage device timeout value to the predetermined low value.22. The method of claim 21 , wherein a request from a host times out if data corresponding to the request is not retrieved from the storage device within a time indicated by the storage device timeout value.23. A method claim 21 , comprising:determining that at least one storage volume of a plurality of storage volumes controlled by a processor complex and stored in a storage device is a primary storage volume that is in an asynchronous or a synchronous copy relationship with at least one secondary storage volume of a plurality of ...

Подробнее
Номер записи: 4
30-08-2016 дата публикации

Thinly provisioned flash cache with shared storage pool

Номер: US0009430404B2
Автор: Michael T. Benhase, Lokesh M. Gupta, Karl A. Nielsen, BENHASE MICHAEL T, GUPTA LOKESH M, NIELSEN KARL A, Benhase Michael T., Gupta Lokesh M., Nielsen Karl A.
Принадлежит: INTERNATIONAL BUSINESS MACHINES CORPORATION, IBM

For data processing in a computing storage environment by a processor device, the computing storage environment incorporating at least high-speed and lower-speed caches, and managed tiered levels of storage, a Solid State Device (SSD) tier is variably shared between the lower-speed cache and the managed tiered levels of storage such that the managed tiered levels of storage are operational on large data segments, and the lower-speed cache is allocated with the large data segments, yet operates with data segments of a smaller size than the large data segments and within the large data segments, where if selected data segments are cached in the lower-speed cache and are determined to become uniformly hot, the selected group from the lower-speed cache are migrated to the SSD tier.

Подробнее
Номер записи: 5
29-08-2017 дата публикации

Statistic-based isolation of lethargic drives

Номер: US0009747042B2
Автор: Matthew J. Kalos, Karl A. Nielsen, KALOS MATTHEW J, NIELSEN KARL A, Kalos Matthew J., Nielsen Karl A.
Принадлежит: International Business Machines Corporation, IBM

A method is provided for identifying a lethargic drive. The method includes executing a command directed to at least two drives in a redundant array of independent disks (RAID) configuration. Each of the drives of the at least two drives is associated with a plurality of timing buckets. The method also includes determining a completion time of the command, and, for each of the at least two drives that the command was directed to, counting the completion time of the command in one of the timing buckets associated with the drive.

Подробнее
Номер записи: 6
21-09-2017 дата публикации

STATISTIC-BASED ISOLATION OF LETHARGIC DRIVES

Номер: US20170269853A1
Автор: Matthew J. Kalos, Karl A. Nielsen, KALOS MATTHEW J, NIELSEN KARL A, Kalos Matthew J., Nielsen Karl A.
Принадлежит: International Business Machines Corp

A method is provided for identifying a lethargic drive. The method includes identifying a timing bucket unique to a drive located in a redundant array of independent disks (RAID) configuration, computing a delta-count for the timing bucket at a predetermined time, including determining a difference between a counter for the timing bucket at the predetermined time and the counter for the timing bucket at a time when the drive was replaced within the RAID configuration, comparing the delta-count for the timing bucket to a predetermined threshold, and determining whether the drive is lethargic, based on the comparing.

Подробнее
Номер записи: 7
08-06-2017 дата публикации

COMMUNICATIONS TO A PLURALITY OF CLOUD STORAGES VIA A PLURALITY OF COMMUNICATIONS PROTOCOLS THAT CHANGE OVER TIME

Номер: US20170163772A1
Автор: Matthew G. Borlick, Lokesh M. Gupta, Roger G. Hathorn, Karl A. Nielsen, BORLICK MATTHEW G, GUPTA LOKESH M, HATHORN ROGER G, NIELSEN KARL A, Borlick Matthew G., Gupta Lokesh M., Hathorn Roger G., Nielsen Karl A.
Принадлежит:

Provided are a method, a system, and a computer program product in which a computational device transmits, via a first communications protocol, a first set of data to a first cloud storage maintained by a first entity. The computational device transmits, via a second communications protocol, a second set of data to a second cloud storage maintained by a second entity. 1. A method , comprising:maintaining a computational device having an interface to access a heterogeneous cloud storage comprised of a first cloud storage maintained by a first entity and a second cloud storage maintained by a second entity;transmitting, via a first communications protocol over the interface, by a communication protocol management application of the computational device, a first set of data comprising usernames, to the first cloud storage maintained by the first entity;transmitting via a second communications protocol over the interface, by the communication protocol management application of the computational device, a second set of data comprising passwords corresponding to the usernames, to the second cloud storage maintained by the second entity;in response to an elapse of a first predetermined amount of time, changing, by the computational device, the first communications protocol to a third communications protocol, wherein the first communications protocol is also changed to the third communications protocol in response to the first communications protocol being compromised; andin response to an elapse of a second predetermined amount of time, changing, by the computational device, the second communications protocol to a fourth communications protocol, wherein the second communications protocol is also changed to the fourth communications protocol in response to the second communications protocol being compromised.2. The method of claim 1 , wherein the first set of data and the second set of data are both parts of an entire dataset claim 1 , wherein the entire dataset is stored ...

Подробнее
Номер записи: 8
25-05-2017 дата публикации

INTELLIGENT STRESS TESTING AND RAID REBUILD TO PREVENT DATA LOSS

Номер: US20170147437A1
Автор: Matthew G. Borlick, John C. Elliott, Lokesh M. Gupta, Clint A. Hardy, Karl A. Nielsen, BORLICK MATTHEW G, ELLIOTT JOHN C, GUPTA LOKESH M, HARDY CLINT A, NIELSEN KARL A, Borlick Matthew G., Elliott John C., Gupta Lokesh M., Hardy Clint A., Nielsen Karl A.
Принадлежит: International Business Machines Corporation

A method for intelligently rebuilding a RAID includes subjecting a storage drive in an existing RAID to a stress workload test by placing the storage drive in a RAID 1 configuration with a spare storage drive. In the event the storage drive fails the stress workload test but can still be read, the method uses the RAID 1 configuration to copy recoverable data from the failing storage drive to the spare storage drive. The method uses other storage drives in the existing RAID to reconstruct, on the spare storage drive, data that is not recoverable from the failing storage drive. Either before or after all non-recoverable data has been reconstructed on the spare storage drive, the method logically replaces, in the existing RAID, the failing storage drive with the spare storage drive. A corresponding system and computer program product are also disclosed. 1. A method for intelligently rebuilding a RAID , the method comprising:subjecting a storage drive in an existing RAID to a stress workload test by placing the storage drive in a RAID 1 configuration with a spare storage drive;in the event the storage drive (hereinafter “the failing storage drive”) fails the stress workload test but can still be read, using the RAID 1 configuration to copy recoverable data from the failing storage drive to the spare storage drive;using other storage drives in the existing RAID to reconstruct, on the spare storage drive, data not recoverable from the failing storage drive; andlogically replacing, in the existing RAID, the failing storage drive with the spare storage drive.2. The method of claim 1 , wherein subjecting the storage drive to the stress workload test comprises performing the stress workload test when the storage drive reaches a specified age.3. The method of claim 1 , wherein subjecting the storage drive to the stress workload test comprises simultaneously refraining from stressing other storage drives in the RAID during the stress workload test.4. The method of claim 1 , ...

Подробнее
Номер записи: 9
24-11-2016 дата публикации

DETERMINING ADJUSTMENTS OF STORAGE DEVICE TIMEOUT VALUES BASED ON SYNCHRONOUS OR ASYNCHRONOUS REMOTE COPY STATE

Номер: US20160342349A1
Автор: Matthew G. Borlick, Karl A. Nielsen, Richard P. Oubre, JR., Todd C. Sorenson, BORLICK MATTHEW G, NIELSEN KARL A, OUBRE JR RICHARD P, SORENSON TODD C, Borlick Matthew G., Nielsen Karl A., Oubre, JR. Richard P., Sorenson Todd C.
Принадлежит:

A determination is made as to whether a plurality of storage volumes controlled by a processor complex are secondary storage volumes that are in an asynchronous copy relationship with a plurality of primary storage volumes. A storage device timeout value for a storage device that stores the plurality of storage volumes is changed from a predetermined low value to a predetermined high value, wherein the predetermined high value is indicative of a greater duration of time than the predetermined low value, in response to determining that each of the plurality of storage volumes controlled by the processor complex and stored in the storage device are secondary storage volumes that are in the asynchronous copy relationship with the plurality of primary storage volumes. 1. A method , comprising:determining whether a plurality of storage volumes controlled by a processor complex are secondary storage volumes that are in an asynchronous copy relationship with a plurality of primary storage volumes; andchanging a storage device timeout value for a storage device that stores the plurality of storage volumes from a predetermined low value to a predetermined high value, wherein the predetermined high value is indicative of a greater duration of time than the predetermined low value, in response to determining that each of the plurality of storage volumes controlled by the processor complex and stored in the storage device are secondary storage volumes that are in the asynchronous copy relationship with the plurality of primary storage volumes.2. The method of claim 1 , the method further comprising:assigning the storage device timeout value with the predetermined low value, in response to determining that not each of the plurality of storage volumes controlled by the processor complex and stored in the storage device are secondary storage volumes that are in the asynchronous copy relationship with the plurality of primary storage volumes.3. The method of claim 1 , the method ...

Подробнее
Номер записи: 10
25-05-2017 дата публикации

RAID DATA LOSS PREVENTION

Номер: US20170147436A1
Автор: Matthew G. Borlick, Lokesh M. Gupta, Clint A. Hardy, Karl A. Nielsen, Brian A. Rinaldi, BORLICK MATTHEW G, GUPTA LOKESH M, HARDY CLINT A, NIELSEN KARL A, RINALDI BRIAN A, Borlick Matthew G., Gupta Lokesh M., Hardy Clint A., Nielsen Karl A., Rinaldi Brian A.
Принадлежит: International Business Machines Corporation

A method for preventing data loss in a RAID includes monitoring the age of storage drives making up a RAID. When a storage drive in the RAID reaches a specified age, the method individually tests the storage drive by subjecting the storage drive to a stress workload test. This stress workload test may be designed to place additional stress on the storage drive while refraining from adding stress to other storage drives in the RAID. In the event the storage drive fails the stress workload test (e.g., the storage drive cannot adequately handle the additional workload or generates errors in response to the additional workload), the method replaces the storage drive with a spare storage drive and rebuilds the RAID. In certain embodiments, the method tests the storage drive with greater frequency as the age of the storage drive increases. A corresponding system and computer program product are also disclosed. 1. A method for preventing data loss in RAIDs , the method comprising:monitoring the age of storage drives making up a RAID;when a storage drive in the RAID reaches a specified age, individually testing the storage drive by subjecting the storage drive to a stress workload test, wherein the stress workload test isolates the storage drive to not place additional stress on other storage drives making up the RAID;determining whether the storage drive passed or failed the stress workload test; andin the event the storage drive failed the stress workload test, replacing the storage drive with a spare storage drive and rebuilding the RAID.2. The method of claim 1 , wherein monitoring the age of the storage drives comprises monitoring the age relative to a life expectancy published by a vendor of the storage drives.3. The method of claim 1 , wherein testing the storage drive comprises placing the storage drive in a RAID 1 configuration with another storage drive not belonging to the RAID.4. The method of claim 1 , further comprising testing the storage drive with greater ...

Подробнее
Номер записи: 11
30-01-2018 дата публикации

Intelligent stress testing and raid rebuild to prevent data loss

Номер: US0009880903B2
Автор: Matthew G. Borlick, John C. Elliott, Lokesh M. Gupta, Clint A. Hardy, Karl A. Nielsen, BORLICK MATTHEW G, ELLIOTT JOHN C, GUPTA LOKESH M, HARDY CLINT A, NIELSEN KARL A, Borlick Matthew G., Elliott John C., Gupta Lokesh M., Hardy Clint A., Nielsen Karl A.
Принадлежит: International Business Machines Corporation, IBM

A method for intelligently rebuilding a RAID includes subjecting a storage drive in an existing RAID to a stress workload test by placing the storage drive in a RAID 1 configuration with a spare storage drive. In the event the storage drive fails the stress workload test but can still be read, the method uses the RAID 1 configuration to copy recoverable data from the failing storage drive to the spare storage drive. The method uses other storage drives in the existing RAID to reconstruct, on the spare storage drive, data that is not recoverable from the failing storage drive. Either before or after all non-recoverable data has been reconstructed on the spare storage drive, the method logically replaces, in the existing RAID, the failing storage drive with the spare storage drive. A corresponding system and computer program product are also disclosed.

Подробнее
Номер записи: 12
08-06-2017 дата публикации

METHOD, SYSTEM, AND COMPUTER PROGRAM PRODUCT FOR DISTRIBUTED STORAGE OF DATA IN A HETEROGENEOUS CLOUD

Номер: US20170163731A1
Автор: Matthew G. Borlick, Lokesh M. Gupta, Roger G. Hathorn, Karl A. Nielsen, BORLICK MATTHEW G, GUPTA LOKESH M, HATHORN ROGER G, NIELSEN KARL A, Borlick Matthew G., Gupta Lokesh M., Hathorn Roger G., Nielsen Karl A.
Принадлежит:

Provided are a method, a system, and a computer program product in which a computational device stores a first part of data in a first cloud storage maintained by a first entity. A second part of the data is stored in a second cloud storage maintained by a second entity. 1. A method , comprising:associating, in a computational device, a plurality of identifiers with a plurality of data elements, wherein a first data element and a second data element of the plurality of data elements are both associated with a first identifier of the plurality of identifiers;storing, by the computational device, the first data element with which the first identifier is associated, in a first cloud storage maintained by a first entity; andstoring, by the computational device, the second data element with which the first identifier is associated, in a second cloud storage maintained by a second entity, wherein the first cloud storage is different from the second cloud storage, and wherein data elements that are associated with an identical identifier are stored in cloud storages provided by different entities, wherein a user identifier and a corresponding password are associated with the identical identifier to indicate that the user identifier and the corresponding password are keys to a secure system, and wherein the user identifier is stored in the first cloud storage maintained by the first entity, and the corresponding password is stored in the second cloud storage maintained by the second entity.2. The method of claim 1 , wherein the computational device is a storage controller coupled to a plurality of hosts claim 1 , wherein the first cloud storage is separated at least by 10 kilometers from the second cloud storage claim 1 , and wherein the first entity and the second entity are different vendors that provide cloud computing services to the storage controller for the plurality of hosts.3. The method of claim 1 , wherein a plurality of cloud storages maintained by a plurality ...

Подробнее
Номер записи: 13
08-06-2017 дата публикации

DISTRIBUTED STORAGE OF DATA IN A LOCAL STORAGE AND A HETEROGENEOUS CLOUD

Номер: US20170160951A1
Автор: Matthew G. Borlick, Lokesh M. Gupta, Roger G. Hathorn, Karl A. Nielsen, BORLICK MATTHEW G, GUPTA LOKESH M, HATHORN ROGER G, NIELSEN KARL A, Borlick Matthew G., Gupta Lokesh M., Hathorn Roger G., Nielsen Karl A.
Принадлежит:

Provided are a method, a system, and a computer program product in which a storage controller determines a plurality of parts of a dataset. At least one part of the dataset is stored in a local storage coupled to the storage controller. At least one other part of the dataset in one or more cloud storages coupled to the storage controller. 1. A method comprising:determining, by a storage controller, a plurality of parts of a dataset;storing at least one part of the dataset in local storage coupled to the storage controller; andstoring at least one other part of the dataset in one or more cloud storages coupled to the storage controller, wherein the one or more cloud storages include a first cloud storage and a second cloud storage, the method further comprising:communicating, by the storage controller, via a first communications protocol with the first cloud storage;communicating, by the storage controller, via a second communications protocol that is different from the first communications protocol with the second cloud storage, wherein the first communications protocol provides a relatively higher level of security than the second communications protocol, and wherein the second communication protocol provides a relatively lower level of security than the first communications protocol;changing the first communications protocol that provides a relatively higher level of security than the second communications protocol, to another communications protocol, in response to an elapse of a first predetermined amount of time; andchanging the second communications protocol that provides a relatively lower level of security than the first communications protocol, to a different communications protocol, in response to an elapse of a second predetermined amount of time.2. The method of claim 1 , wherein the at least one part of the dataset stored in the local storage requires greater security than the at least one other part of the dataset that is stored in the one or more ...

Подробнее
Номер записи: 14
13-02-2018 дата публикации

Managing raid parity stripe contention

Номер: US0009891993B2
Автор: Matthew J. Kalos, Karl A. Nielsen, Richard B. Stelmach, KALOS MATTHEW J, NIELSEN KARL A, STELMACH RICHARD B, Kalos Matthew J., Nielsen Karl A., Stelmach Richard B.
Принадлежит: INTERNATIONAL BUSINESS MACHINES CORPORATION, IBM

For managing RAID parity stripe contention using a processor device in a computing environment, delaying one of a multiplicity of operations overlapping a parity sector in a parity stripe with a currently running operation and serializing each one of the multiplicity of operations overlapping the parity sector.

Подробнее
Номер записи: 15
16-08-2016 дата публикации

Promotion of partial data segments in flash cache

Номер: US0009417808B2
Автор: Michael T. Benhase, Stephen L. Blinick, Evangelos S. Eleftheriou, Lokesh M. Gupta, Robert Haas, Xiao-Yu Hu, Matthew J. Kalos, Ioannis Koltsidas, Karl A. Nielsen, Roman A. Pletka, BENHASE MICHAEL T, BLINICK STEPHEN L, ELEFTHERIOU EVANGELOS S, GUPTA LOKESH M, HAAS ROBERT, HU XIAO-YU, KALOS MATTHEW J, KOLTSIDAS IOANNIS, NIELSEN KARL A, PLETKA ROMAN A, Benhase Michael T., Blinick Stephen L., Eleftheriou Evangelos S., Gupta Lokesh M., Haas Robert, Hu Xiao-Yu, Kalos Matthew J., Koltsidas Ioannis, Nielsen Karl A., Pletka Roman A.
Принадлежит: INTERNATIONAL BUSINESS MACHINES CORPORATION, IBM

For efficient track destage in secondary storage in a more effective manner, for temporal bits employed with sequential bits for controlling the timing for destaging the track in a primary storage, if a first bit has at least one of a lower amount of holes and a hotter data heat metric, it is moved to the lower speed cache level. If the first bit has a hotter data heat and greater than a predetermined number of holes, the first bit is discarded.

Подробнее
Номер записи: 16
06-03-2018 дата публикации

Determining adjustments of storage device timeout values based on synchronous or asynchronous remote copy state

Номер: US0009910609B2
Автор: Matthew G. Borlick, Karl A. Nielsen, Richard P. Oubre, Jr., Todd C. Sorenson, BORLICK MATTHEW G, NIELSEN KARL A, OUBRE JR RICHARD P, SORENSON TODD C, Borlick Matthew G., Nielsen Karl A., Oubre, Jr. Richard P., Sorenson Todd C.
Принадлежит: INTERNATIONAL BUSINESS MACHINES CORPORATION, IBM

A determination is made as to whether a plurality of storage volumes controlled by a processor complex are secondary storage volumes that are in an asynchronous copy relationship with a plurality of primary storage volumes. A storage device timeout value for a storage device that stores the plurality of storage volumes is changed from a predetermined low value to a predetermined high value, wherein the predetermined high value is indicative of a greater duration of time than the predetermined low value, in response to determining that each of the plurality of storage volumes controlled by the processor complex and stored in the storage device are secondary storage volumes that are in the asynchronous copy relationship with the plurality of primary storage volumes.

Подробнее
Номер записи: 17
07-06-2012 дата публикации

METHODS FOR PROCESS KEY ROLLOVER/RE-ENCRYPTION AND SYSTEMS THEREOF

Номер: US20120144209A1
Автор: Kahler David R., Moore Roderick G.C., Nielsen Karl A.
Принадлежит: INTERNATIONAL BUSINESS CORPORATION

A method according to one embodiment includes defining a new encryption band with a length that is consistent with a redundant array of inexpensive disks (RAID) parity strip; freeing a working extent in a working stride on the RAID. In an iterative process until each stride in a source band is depleted of data: marking a source extent in a source stride from which to gather data to be re-encrypted; marking parity inconsistent in the working stride in the new encryption band; performing a second iterative process; and freeing the working extent. The second iterative process is performed until each extent in a source stride is depleted of data. Additional systems, methods and computer program products are also presented. 2. The method as recited in claim 1 , wherein the working extent is freed at a starting point.3. The method as recited in claim 2 , wherein the starting point is LBA 0.4. The method as recited in claim 1 , wherein the source extent is a next extent on the RAID.5. The method as recited in claim 1 , wherein marking the source extent in the source stride includes locking the source extent such that operations may not be performed on the source extent during re-encryption.6. A method claim 1 , comprising:staging a parity stride from a source array in a redundant array of inexpensive disks (RAID);storing the parity stride from the source array to a non-volatile memory; defining a new encryption band with a length that is consistent with a RAID parity strip;', 'marking a source extent in the source array from which to gather data to be re-encrypted;', 'marking the RAID parity strip free on the source extent;', 'applying the new encryption band to each array component in the parity strip; and', 'moving each data band from the source extent in the source array to the non-volatile memory;, 'in an iterative process until the source array is depleted of datadeleting the source extent after being depleted of data;destaging the parity stride; andfreeing the non- ...

Подробнее
Номер записи: 18
29-11-2012 дата публикации

WRITING OF NEW DATA OF A FIRST BLOCK SIZE IN A RAID ARRAY THAT STORES BOTH PARITY AND DATA IN A SECOND BLOCK SIZE

Номер: US20120303890A1
Автор: BENHASE Michael T., Judd Ian David, Moertl Daniel F., Nielsen Karl A.
Принадлежит: INTERNATIONAL BUSINESS MACHINES CORPORATION

A Redundant Array of Independent Disks (RAID) controller receives new data that is to be written, wherein the new data is indicated in blocks of a first block size. The RAID controller reads old data, and old parity that corresponds to the old data, stored in blocks of a second block size that is larger in size than the first block size. The RAID controller computes new parity based on the new data, the old data, and the old parity. The RAID controller writes the new data and the new parity aligned to the blocks of the second block size, wherein portions of the old data that are not overwritten by the RAID controller are also written to the blocks of the second block size. 15-. (canceled)6. A system , comprising:a memory; and receiving new data that is to be written, wherein the new data is indicated in blocks of a first block size;', 'reading old data, and old parity that corresponds to the old data, stored in blocks of a second block size that is larger in size than the first block size;', 'computing new parity based on the new data, the old data, and the old parity; and', 'writing the new data and the new parity aligned to the blocks of the second block size, wherein portions of the old data that are not overwritten by the RAID controller are also written to the blocks of the second block size., 'a processor coupled to the memory, wherein the processor performs7. The system of claim 6 , wherein the system is a RAID controller that controls disks that are configured as RAID-5 claim 6 , wherein:the reading is performed via two sets of read operations from the disks, wherein a first set of read operations include reading the old data and a second set of read operations include reading the old parity; andthe writing is performed via two sets of write operations to the disks, wherein a first set of write operations include writing the new data and portions of the old data that are not overwritten, and a second set of write operations include writing the new parity.8. ...

Подробнее
Номер записи: 19
29-11-2012 дата публикации

WRITING OF NEW DATA OF A FIRST BLOCK SIZE IN A RAID ARRAY THAT STORES BOTH PARITY AND DATA IN A SECOND BLOCK SIZE

Номер: US20120303892A1
Автор: BENHASE Michael T., Judd Ian David, Moertl Daniel F., Nielsen Karl A.
Принадлежит: INTERNATIONAL BUSINESS MACHINES CORPORATION

A Redundant Array of Independent Disks (RAID) controller receives new data that is to be written, wherein the new data is indicated in blocks of a first block size. The RAID controller reads old data, and old parity that corresponds to the old data, stored in blocks of a second block size that is larger in size than the first block size. The RAID controller computes new parity based on the new data, the old data, and the old parity. The RAID controller writes the new data and the new parity aligned to the blocks of the second block size, wherein portions of the old data that are not overwritten by the RAID controller are also written to the blocks of the second block size. 1. A method implemented in a device , the method comprising:receiving, by a Redundant Array of Independent Disks (RAID) controller, new data that is to be written, wherein the new data is indicated in blocks of a first block size;reading, by the RAID controller, old data, and old parity that corresponds to the old data, stored in blocks of a second block size that is larger in size than the first block size;computing, by the RAID controller, new parity based on the new data, the old data, and the old parity; andwriting, by the RAID controller, the new data and the new parity aligned to the blocks of the second block size, wherein portions of the old data that are not overwritten by the RAID controller are also written to the blocks of the second block size.2. The method of claim 1 , wherein the RAID controller is implemented in hardware claim 1 , and wherein the RAID controller controls disks that are configured as RAID-5 claim 1 , wherein:the reading is performed via two sets of read operations from the disks, wherein a first set of read operations include reading the old data and a second set of read operations include reading the old parity; andthe writing is performed via two sets of write operations to the disks, wherein a first set of write operations include writing the new data and ...

Подробнее
Номер записи: 20
02-05-2013 дата публикации

PROMOTION OF PARTIAL DATA SEGMENTS IN FLASH CACHE

Номер: US20130111106A1
Автор: BENHASE Michael T., BLINICK Stephen L., Eleftheriou Evangelos S., GUPTA Lokesh M., Haas Robert, Hu Xiao-Yu, KALOS Matthew J., Koltsidas Ioannis, Nielsen Karl A., PLETKA Roman A.
Принадлежит: INTERNATIONAL BUSINESS MACHINES CORPORATION

Exemplary method, system, and computer program product embodiments for efficient track destage in secondary storage in a more effective manner, are provided. In one embodiment, by way of example only, for temporal bits employed with sequential bits for controlling the timing for destaging the track in a primary storage, the temporal bits and sequential bits are transferred from the primary storage to the secondary storage. The temporal bits are allowed to age on the secondary storage. Additional system and computer program product embodiments are disclosed and provide related advantages. 1. A method for promoting partial data segments in a computing storage environment having lower and higher speed levels of cache by a processor , comprising: allowing the partial data segments to remain in the higher speed cache level for a time period longer that at least one whole data segment, and', 'implementing a preference for movement of the partial data segments to the lower speed cache level based on at least one of an amount of holes and a data heat metric, wherein a first of the partial data segments having at least one of a lower amount of holes and a hotter data heat is moved to the lower speed cache level ahead of a second of the partial data segments having at least one of a higher amount of holes and a cooler data heat., 'configuring a data moving mechanism adapted for performing at least one of2. The method of claim 1 , further including claim 1 , pursuant to configuring the data mover mechanism claim 1 , writing one of the partial data segments to the lower speed cache level as a whole data segment.3. The method of claim 1 , further including claim 1 , pursuant to configuring the data mover mechanism claim 1 , densely packing one of the partial data segments into a Cache Flash Element (CFE).4. The method of claim 1 , further including writing fixed portions of the partial data segment to portions of the lower speed cache corresponding to an associated storage ...

Подробнее
Номер записи: 21
23-05-2013 дата публикации

ERROR CHECKING ADDRESSABLE BLOCKS IN STORAGE

Номер: US20130132801A1
Автор: "OCONNOR James A.", Hafner James L., Kahler David R., Kubo Robert A., Mannenbach David F., Nielsen Karl A., Stelmach Richard B., Surugucchi Krishnakumar R.
Принадлежит: INTERNATIONAL BUSINESS MACHINES CORPORATION

Provided are a method, system, and article of manufacture for error checking addressable blocks in storage. Addressable blocks of data are stored in a storage in stripes, wherein each stripe includes a plurality of data blocks for one of the addressable blocks and at least one checksum block including checksum data for the addressable block. A write request is received to modify data in one of the addressable blocks. The write and updating the checksum are performed in the stripe having the modified addressable block. An indication is made to perform an error checking operation on the stripe for the modified addressable block in response to the write request, wherein the error checking operation reads the data blocks and the checksum in the stripe to determine if the checksum data is accurate. An error handling operation is initiated in response to determining that the checksum data is not accurate. 1. An article of manufacture comprising a non-transitory computer readable storage medium having code executed to cause operations with respect to a storage device and a memory and to cause operations comprising:storing addressable blocks of data in the storage device in stripes, wherein each stripe includes a plurality of data blocks for one of the addressable blocks and at least one checksum block including checksum data derived from the data blocks for the addressable block;receiving a write request to modify data in one of the addressable blocks in the storage device;performing the write and updating the checksum in the stripe having the modified addressable block, wherein the modified data and the updated checksum resulting from the write are destaged to the storage device;indicating in a recently modified list in the memory addressable blocks recently modified in response to write requests;after the write is performed, performing an error checking operation on the stripes of the addressable blocks indicated in the recently modified list by reading the data blocks ...

Подробнее
Номер записи: 22
06-06-2013 дата публикации

SPATIAL EXTENT MIGRATION FOR TIERED STORAGE ARCHITECTURE

Номер: US20130145115A1
Автор: Lau Pui Fun, Montgomery David, Nielsen Karl A., Stelmach Richard B.
Принадлежит: INTERNATIONAL BUSINESS MACHINES CORPORATION

Provided are techniques for migrating a first extent, determining a spatial distance between the first extent and a second extent, determining a ratio of a profiling score of the second extent to the spatial distance, and, in response to determining that the ratio exceeds a threshold, migrating the second extent. 1. A method , comprising:migrating, using a computer including a processor, a first extent;determining a spatial distance between the first extent and a second extent;determining a ratio of a profiling score of the second extent to the spatial distance;in response to determining that the ratio exceeds a threshold, migrating the second extent.2. The method of claim 1 , further comprising:dynamically migrating the first extent from a first storage tier to a second storage tier based on a profiling score of the first extent.3. The method of claim 1 , further comprising:migrating the first extent and the second extent to different storage tiers.4. The method of claim 1 , further comprising:migrating the first extent and the second extent to a same storage tier.5. The method of claim 1 , further comprising:identifying a list of extents that reside on a same volume as the first extent; anddetermining whether each of the extents on the list should be migrated.6. The method of claim 1 , further comprising:in response to determining that the ratio does not exceed the threshold, not migrating the second extent.7. A system claim 1 , comprising:a processor; and migrating a first extent;', 'determining a spatial distance between the first extent and a second extent;', 'determining a ratio of a profiling score of the second extent to the spatial distance;', 'in response to determining that the ratio exceeds a threshold, migrating the second extent., 'a migration system coupled to the processor and performing operations, the operations comprising8. The system of claim 7 , wherein the operations further comprise:dynamically migrating the first extent from a first storage ...

Подробнее
Номер записи: 23
18-07-2013 дата публикации

Populating a first stride of tracks from a first cache to write to a second stride in a second cache

Номер: US20130185478A1
Автор: Karl A. Nielsen, Kevin J. Ash, Lokesh M. Gupta, Matthew J. Kalos, Michael T. Benhase
Принадлежит: International Business Machines Corp

Provided are a computer program product, system, and method for managing data in a cache system comprising a first cache, a second cache, and a storage system. A determination is made of tracks stored in the storage system to demote from the first cache. A first stride is formed including the determined tracks to demote. A determination is made of a second stride in the second cache in which to include the tracks in the first stride. The tracks from the first stride are added to the second stride in the second cache. A determination is made of tracks in strides in the second cache to demote from the second cache. The determined tracks to demote from the second cache are demoted.

Подробнее
Номер записи: 24
18-07-2013 дата публикации

POPULATING A FIRST STRIDE OF TRACKS FROM A FIRST CACHE TO WRITE TO A SECOND STRIDE IN A SECOND CACHE

Номер: US20130185494A1
Автор: Ash Kevin J., BENHASE Michael T., GUPTA Lokesh M., KALOS Matthew J., Nielsen Karl A.
Принадлежит: INTERNATIONAL BUSINESS MACHINES CORPORATION

Provided are a computer program product, system, and method for managing data in a cache system comprising a first cache, a second cache, and a storage system. A determination is made of tracks stored in the storage system to demote from the first cache. A first stride is formed including the determined tracks to demote. A determination is made of a second stride in the second cache in which to include the tracks in the first stride. The tracks from the first stride are added to the second stride in the second cache. A determination is made of tracks in strides in the second cache to demote from the second cache. The determined tracks to demote from the second cache are demoted. 1. A computer program product for managing data in a cache system comprising a first cache , a second cache , and a storage system , the computer program product comprising a computer readable storage medium having computer readable program code embodied therein that executes to perform operations , the operations comprising:determining tracks stored in the storage system to demote from the first cache;forming a first stride including the determined tracks to demote;determining a second stride in the second cache in which to include the tracks in the first stride;adding the tracks from the first stride to the second stride in the second cache;determining tracks in strides in the second cache to demote from the second cache; anddemoting the determined tracks to demote from the second cache.2. The computer program product of claim 1 , wherein the first cache is a faster access device than the second cache and wherein the second cache is a faster access device than the storage system.3. The computer program product of claim 1 , wherein the first cache comprises a Dynamic Random Access Memory (RAM) claim 1 , the second cache comprises a plurality of flash devices claim 1 , and the storage system is comprised of a plurality of slower access devices than the flash devices.4. The computer program ...

Подробнее
Номер записи: 25
08-08-2013 дата публикации

PROMOTION OF PARTIAL DATA SEGMENTS IN FLASH CACHE

Номер: US20130205077A1
Автор: BENHASE Michael T., BLINICK Stephen L., Eleftheriou Evangelos S., GUPTA Lokesh M., Haas Robert, Hu Xiao-Yu, KALOS Matthew J., Koltsidas Ioannis, Nielsen Karl A., PLETKA Roman A.
Принадлежит: INTERNATIONAL BUSINESS MACHINES CORPORATION

For efficient track destage in secondary storage in a more effective manner, for temporal bits employed with sequential bits for controlling the timing for destaging the track in a primary storage, the temporal bits and sequential bits are transferred from the primary storage to the secondary storage. The temporal bits are allowed to age on the secondary storage. 1. A method for promoting partial data segments in a computing storage environment having lower and higher speed levels of cache by a processor , comprising: allowing the partial data segments to remain in the higher speed cache level for a time period longer that at least one whole data segment, and', 'implementing a preference for movement of the partial data segments to the lower speed cache level based on at least one of an amount of holes and a data heat metric, wherein a first of the partial data segments having at least one of a lower amount of holes and a hotter data heat is moved to the lower speed cache level ahead of a second of the partial data segments having at least one of a higher amount of holes and a cooler data heat., 'configuring a data moving mechanism adapted for performing at least one of2. The method of claim 1 , further including claim 1 , pursuant to configuring the data mover mechanism claim 1 , writing one of the partial data segments to the lower speed cache level as a whole data segment.3. The method of claim 1 , further including claim 1 , pursuant to configuring the data mover mechanism claim 1 , densely packing one of the partial data segments into a Cache Flash Element (CFE).4. The method of claim 1 , further including writing fixed portions of the partial data segment to portions of the lower speed cache corresponding to an associated storage device claim 1 , wherein the fixed portions are located using pointers in an affiliated Cache Flash Control Block (CFCB).5. The method of claim 2 , further including claim 2 , if the first of the partial data segments has a hotter ...

Подробнее
Номер записи: 26
06-03-2014 дата публикации

METHOD TO INCREASE PERFORMANCE OF NON-CONTIGUOUSLY WRITTEN SECTORS

Номер: US20140068195A1
Автор: Mannenbach David F., Nielsen Karl A.
Принадлежит: INTERNATIONAL BUSINESS MACHINES CORPORATION

A method of managing data in a cache upon a cache write operation includes determining a number of non-contiguously written sectors on a track in the cache and comparing the number with a threshold number. If the number exceeds the threshold number, a full background stage operation is issued to fill the non-contiguously written sectors with unmodified data from a storage medium and the full track is then destaged. A corresponding system includes a cache manager module operating on the storage subsystem. Upon a determination that a cache write operation on a track has taken place, the cache manager module determines a number of non-contiguously written sectors on the track, compares the number with a predetermined threshold number, issues a background stage operation to fill the non-contiguously written sectors with unmodified data from a storage medium if the number exceeds the threshold number, and then destages the full track. 1. A method for managing data in a cache , the method comprising:identifying one or more non-contiguously written sectors in a partially filled track;performing a full background stage operation to fill the one or more non-contiguously written sectors with unmodified data from a storage medium to create a full track anddestaging the full track to the storage medium.2. The method of claim 1 , wherein identifying the one or more non-contiguously written sectors comprises:receiving, by the cache, a write operation;determining a number of non-contiguously written sectors on a track in the cache; andcomparing the number of non-contiguously written sectors with a predetermined threshold number of non-contiguously written sectors.3. The method of claim 2 , further including claim 2 , prior to determining the number of non-contiguously written sectors claim 2 , detecting that the write operation has taken place.4. The method of claim 2 , wherein determining the number of non-contiguously written sectors is performed using a cache bit map that is ...

Подробнее
Номер записи: 27
20-03-2014 дата публикации

Apparatus and Method for Sharing Resources between Storage Devices

Номер: US20140082318A1
Автор: BENHASE Michael T., KALOS Matthew J., Nielsen Karl A.
Принадлежит: INTERNATIONAL BUSINESS MACHINES CORPORATION

A method for allocating resources of a storage system including at least a first and second group of storage devices. The method identifies a first set of resources to be reserved for use by the first group of storage devices, identifies a second set of resources to be reserved for use by the second group of storage devices, and identifies a third set of resources The method then allocates resources from the third set of resources to the first group of storage devices or the second group of storage device according to an allocation algorithm, and restricts use of the first set of resources to the first group of devices and use of the second set of resources to the second group of devices. 1. A method for allocating resources of a storage system including at least a first and second group of storage devices , comprising:identifying a first set of resources to be reserved for use by the first group of storage devices;identifying a second set of resources to be reserved for use by the second group of storage devices;identifying a third set of resources;allocating resources from the third set of resources to the first group of storage devices or the second group of storage device according to an allocation algorithm; andrestricting use of the first set of resources to the first group of devices and use of the second set of resources to the second group of devices.2. The method of claim 1 , wherein said resources comprise available command structures.3. The method of claim 1 , wherein said resources comprise PCI address space.4. The method of claim 1 , wherein the first group of storage devices includes a plurality of solid state disks.5. The method of claim 1 , wherein the second group of storage devices include a plurality of spinning disk drives.6. The method of claim 1 , wherein the allocation algorithm includes a first-come claim 1 , first-serve allocation algorithm.7. The method of claim 1 , including dynamically adjusting an allocation of resources from the third ...

Подробнее
Номер записи: 28
10-04-2014 дата публикации

IMPLEMENTING DYNAMIC BANDING OF SELF ENCRYPTING DRIVE

Номер: US20140101455A1
Автор: Anderson Michael J., Bauman Scott A., Edwards Joseph R., Faunce Michael S., Galbraith Robert E., Kahler David R., Nielsen Karl A., Roble Michael T., Yadlosky Mark
Принадлежит: INTERNATIONAL BUSINESS MACHINES CORPORATION

A method and controller for implementing dynamic banding of a storage device, such as a Self Encrypting Device (SED) in a data storage array, and a design structure on which the subject controller circuit resides are provided. The controller dynamically identifies band boundaries for the storage device at the time a data storage array is created, when one or more devices are added into an existing data storage array, and when a replacement device is rebuilt into an exposed array, or an array with a failed device. A storage device band definition is provided based upon the dynamically identified band boundaries for the storage device. 1. A data storage system comprising:a controller for implementing dynamic banding of a storage device in a data storage array;said controller dynamically identifying band boundaries for the storage device at the time of a data storage array being created, andsaid controller providing a storage device band definition for the storage device based upon the dynamically identified band boundaries for the storage device.2. The data storage system as recited in includes said controller dynamically identifying band boundaries for a storage device at the time a storage device is added into the data storage array.3. The data storage system as recited in includes said controller dynamically identifying band boundaries for a storage device at the time a replacement device is rebuilt into the data storage array including a failed device.4. The data storage system as recited in wherein said controller dynamically identifies band boundaries for the storage device based upon user selected values for secure area and a non-secure area.5. The data storage system as recited in wherein said data storage array includes a redundant array of independent drives (RAID) and wherein said controller dynamically identifies band boundaries for the storage device based upon a number of drives in said RAID and a RAID level value.6. The data storage system as recited in ...

Подробнее
Номер записи: 29
02-01-2020 дата публикации

Determining when to replace a storage device using a machine learning module

Номер: US20200004434A1
Автор: Clint A. Hardy, Karl A. Nielsen, Lokesh M. Gupta, Matthew G. Borlick
Принадлежит: International Business Machines Corp

Provided are a computer program product, system, and method for using a machine learning module to determine when to replace a storage device. Input on attributes of the storage device is provided to a machine learning module to produce an output value. A determination is made whether the output value indicates to replace the storage device. Indication is made to replace the storage device in response to determining that the output value indicates to replace the storage device.

Подробнее
Номер записи: 30
02-01-2020 дата публикации

DETERMINING WHEN TO REPLACE A STORAGE DEVICE BY TRAINING A MACHINE LEARNING MODULE

Номер: US20200004435A1
Автор: Borlick Matthew G., GUPTA Lokesh M., Hardy Clint A., Nielsen Karl A.
Принадлежит:

Provided are a computer program product, system, and method for using a machine learning module to determine when to replace a storage device. Input on attributes of the storage device is provided to a machine learning module to produce an output value. A determination is made whether the output value indicates to replace the storage device. Indication is made to replace the storage device in response to determining that the output value indicates to replace the storage device. 18-.9. A computer program product for determining when to replace a storage device deployed within a computing environment , the computer program product comprising a computer readable storage medium storing computer readable program code that when executed performs operations , the operations comprising:updating dynamic attributes for the storage device in response to access requests to the storage device;detecting a failure of the storage device; determining input comprising the dynamic attributes of the storage device that failed; and', 'using the input to train a machine learning module to produce an output value indicating no expected remaining life of the storage device; and', 'after training the machine learning module for the storage device that failed, executing the machine learning module to produce an output value based on dynamic storage attributes of an operational storage device to determine an expected remaining life of the operational storage device., 'in response to detecting the failure of the storage device, performing10. The computer program product of claim 9 , wherein to train the machine learning module comprises:executing the machine learning module with the input to produce a current output value of the storage device that failed;determining a margin of error of the current output value and an output value indicating no expected remaining life of the storage device that failed; andusing the margin of error and the input to train weights and biases of nodes in the ...

Подробнее
Номер записи: 31
02-01-2020 дата публикации

DETERMINING WHEN TO PERFORM A DATA INTEGRITY CHECK OF COPIES OF A DATA SET USING A MACHINE LEARNING MODULE

Номер: US20200004437A1
Автор: Borlick Matthew G., GUPTA Lokesh M., Hardy Clint A., Nielsen Karl A.
Принадлежит:

Provided are a computer program product, system, and method for using a machine learning module to determine when to perform a data integrity check of copies of a data set. Input on storage attributes of a plurality of storage units, each storage unit of the storage units storing a copy of a data set, is provided to a machine learning module to produce an output value. A determination is made as to whether the output value indicates to perform a data integrity check of the copies of the data set. A determination is made as to whether the copies of the data set on different storage units are inconsistent in response to determining to perform the data integrity check. At least one of the copies of the data set is corrected to synchronize all the copies of the data set. 1. A computer program product for checking data integrity of copies of a data set , the computer program product comprising a computer readable storage medium storing computer readable program code that when executed performs operations , the operations comprising:providing input on storage attributes of a plurality of storage units, each storage unit of the storage units storing a copy of a data set, to a machine learning module to produce an output value;determining whether the output value indicates to perform a data integrity check of the copies of the data set;determining whether the copies of the data set on different storage units are inconsistent in response to determining to perform the data integrity check; andcorrecting at least one of the copies of the data set to synchronize all the copies of the data set.2. The computer program product of claim 1 , wherein the correcting the at least one of the copies of the data set to synchronize all the copies of the data set comprises performing one of:using parity information for each copy of the data set of the copies of the data set to perform a parity check of the copy of the data set and if the copy of the data set has errors, using the parity ...

Подробнее
Номер записи: 32
02-01-2020 дата публикации

Determining when to perform a data integrity check of copies of a data set by training a machine learning module

Номер: US20200004439A1
Автор: Clint A. Hardy, Karl A. Nielsen, Lokesh M. Gupta, Matthew G. Borlick
Принадлежит: International Business Machines Corp

Provided are a computer program product, system, and method for using a machine learning module to determine when to perform a data integrity check of copies of a data set. Input on storage attributes of a plurality of storage units, each storage unit of the storage units storing a copy of a data set, is provided to a machine learning module to produce an output value. A determination is made as to whether the output value indicates to perform a data integrity check of the copies of the data set. A determination is made as to whether the copies of the data set on different storage units are inconsistent in response to determining to perform the data integrity check. At least one of the copies of the data set is corrected to synchronize all the copies of the data set.

Подробнее
Номер записи: 33
02-01-2020 дата публикации

Determining when to perform error checking of a storage unit by using a machine learning module

Номер: US20200004623A1
Автор: Clint A. Hardy, Karl A. Nielsen, Lokesh M. Gupta, Matthew G. Borlick
Принадлежит: International Business Machines Corp

Provided are a computer program product, system, and method for using a machine learning module to determine when to perform error checking of a storage unit. Input on attributes of at least one storage device comprising the storage unit are provided to a machine learning module to produce an output value. An error check frequency is determined from the output value. A determination is made as to whether the error check frequency indicates to perform an error checking operation with respect to the storage unit. The error checking operation is performed in response to determining that the error checking frequency indicates to perform the error checking operation.

Подробнее
Номер записи: 34
02-01-2020 дата публикации

DETERMINING WHEN TO PERFORM ERROR CHECKING OF A STORAGE UNIT BY TRAINING A MACHINE LEARNING MODULE

Номер: US20200004625A1
Автор: Borlick Matthew G., GUPTA Lokesh M., Hardy Clint A., Nielsen Karl A.
Принадлежит:

Provided are a computer program product, system, and method for using a machine learning module to determine when to perform error checking of a storage unit. Input on attributes of at least one storage device comprising the storage unit are provided to a machine learning module to produce an output value. An error check frequency is determined from the output value. A determination is made as to whether the error check frequency indicates to perform an error checking operation with respect to the storage unit. The error checking operation is performed in response to determining that the error checking frequency indicates to perform the error checking operation. 19-. (canceled)10. A computer program product for error checking data in a storage unit , the computer program product comprising a computer readable storage medium storing computer readable program code that when executed performs operations , the operations comprising:determining to train a machine learning module; determining inputs comprising attributes of at least one storage device of the storage unit; and', 'training the machine learning module to produce a desired output value indicating to perform an error checking operation of the storage unit from the determined inputs in response to detecting the error; and', 'executing the machine learning module to produce an output value used to determine whether to perform an error checking operation with respect to the storage unit., 'in response to determining to train the machine learning module, performing11. The computer program product of claim 10 , wherein the operations further comprise:detecting an error while performing the error checking operation, wherein the determining to train the machine learning module occurs in response to detecting the error; andsetting the desired output value to an output value indicating to perform error checking to use to train the machine learning module in response to detecting the error.12. The computer program ...

Подробнее
Номер записи: 35
02-01-2020 дата публикации

USING ALTERNATE RECOVERY ACTIONS FOR INITIAL RECOVERY ACTIONS IN A COMPUTING SYSTEM

Номер: US20200004634A1
Автор: Borlick Matthew G., GUPTA Lokesh M., Nielsen Karl A.
Принадлежит:

Provided are a computer program product, system, and method for using alternate recovery actions for initial recovery actions in a computing system. An initial recovery table provides initial recovery actions to perform for errors detected in the computing system. An alternate recovery table is received including at least one alternate recovery action for at least one of the initial recovery actions. An alternative recovery action provided for an initial recovery action specifies a different recovery path involving at least one of a different action and a different component in the computing system than involved in the initial recovery action. A determination is made as to whether to use the initial recovery action in the initial recovery table for a detected error or the alternate recovery action in the alternate recovery table. The determined initial recovery action or alternate recovery action determined is used to address the detected error. 123-. (canceled)24. A computer program product for performing a recovery action upon detecting an error in a computing system , the computer program product comprising a computer readable storage medium having computer readable program code embodied therein that is executable to perform operations , the operations comprising:detecting an error in the computing system;determining whether to use an initial recovery action for the detected error or an alternate recovery action for the initial recovery action, wherein an alternative recovery action provided for an initial recovery action specifies a different recovery path involving at least one of a different action and a different component in the computing system than involved in the initial recovery action for which the alternative recovery action is provided; andusing the initial recovery action or the alternate recovery action determined to use to address the detected error.25. The computer program product of claim 24 , wherein the operations further comprise:maintaining a ...

Подробнее
Номер записи: 36
03-01-2019 дата публикации

PREVENTING UNEXPECTED POWER-UP FAILURES OF HARDWARE COMPONENTS

Номер: US20190004581A1
Автор: Borlick Matthew G., Cagno Brian J., GUPTA Lokesh M., Nielsen Karl A., Sorenson Todd C.
Принадлежит:

In one embodiment, a method includes determining a plurality of hardware components of a system. The method also includes power cycling a first hardware component of the plurality of hardware components of the system according to a dynamic schedule. Also, the method includes determining whether the first hardware component experienced a power-up failure resulting from the power cycling. Moreover, the method includes outputting an indication to replace and/or repair the first hardware component in response to a determination that the first hardware component experienced the power-up failure resulting from the power cycling. Other systems, methods, ad computer program products for preventing unexpected power-up failures of individual hardware components are described in accordance with more embodiments. 1. A method , comprising:determining a plurality of hardware components of a system;power cycling a first hardware component of the plurality of hardware components of the system according to a dynamic schedule;determining whether the first hardware component experienced a power-up failure resulting from the power cycling; andoutputting an indication to replace and/or repair the first hardware component in response to a determination that the first hardware component experienced the power-up failure resulting from the power cycling.2. The method as recited in claim 1 , further comprising:routing input and/or output (I/O) requests that are destined for the first hardware component to a first redundant hardware component for processing thereof prior to and during the power cycling of the first hardware component, wherein the first redundant hardware component is configured to provide full back-up redundancy for the first hardware component within the system; andresuming sending I/O requests to the first hardware component in response to a determination that the first hardware component did not experience the power-up failure after the power cycling.3. The method as ...

Подробнее
Номер записи: 37
21-01-2016 дата публикации

PROMOTION OF PARTIAL DATA SEGMENTS IN FLASH CACHE

Номер: US20160019000A1
Автор: BENHASE Michael T., BLINICK Stephen L., Eleftheriou Evangelos S., GUPTA Lokesh M., Haas Robert, Hu Xiao-Yu, KALOS Matthew J., Koltsidas Ioannis, Nielsen Karl A., PLETKA Roman A.
Принадлежит: INTERNATIONAL BUSINESS MACHINES CORPORATION

For efficient track destage in secondary storage in a more effective manner, for temporal bits employed with sequential bits for controlling the timing for destaging the track in a primary storage, if a first bit has at least one of a lower amount of holes and a hotter data heat metric, it is moved to the lower speed cache level. If the first bit has a hotter data heat and greater than a predetermined number of holes, the first bit is discarded.

Подробнее
Номер записи: 38
21-01-2016 дата публикации

VALIDATION OF STORAGE ARRAYS BASED ON INFORMATION STORED IN GLOBAL METADATA

Номер: US20160019003A1
Автор: GRUSY Ellen J., LOVRIEN Kurt A., Nielsen Karl A., Sheppard Jacob L.
Принадлежит:

A director node of a plurality of nodes determines a plurality of data arrays, where the plurality of data arrays have been discovered at boot time. The director node determines global metadata information, based on reading boot sectors of at least one of the plurality of data arrays discovered at boot time. A determination is made from the global metadata information as to how many data arrays had been previously configured. In response to determining that the plurality of data arrays discovered at boot time is not equal in number to the previously configured data arrays, the director node determines that all configured data arrays have not been discovered.

Подробнее
Номер записи: 39
17-04-2014 дата публикации

PREVENTING ACCESS LOSS WHEN DEVICE ADAPTER AFFINITY TO A NODE CHANGES

Номер: US20140108724A1
Автор: Mathur Anjul, Nielsen Karl A.
Принадлежит: INTERNATIONAL BUSINESS MACHINES CORPORATION

Provided are a computer implemented method, computer program product, and system for maintaining state information. An available node affiliated with an unavailable device adapter and an unavailable node affiliated with an available device adapter are identified, wherein the available node is assigned a first subset of disk arrays, and wherein the unavailable node is assigned a second subset of disk arrays. The available device adapter is affiliated with the available node. First state information of the first node that describes a state of the first subset of disk arrays is updated with second state information of the second node that describes a state of the second subset of disk arrays. Access to the first subset of disk arrays and the second subset of disk arrays is provided through the available node and the available device adapter using the updated first state information. 1. A method for maintaining state information , comprising:identifying, with a processor of a computer, an available node affiliated with an unavailable device adapter and an unavailable node affiliated with an available device adapter, wherein the available node is assigned a first subset of disk arrays, and wherein the unavailable node is assigned a second subset of disk arrays;affiliating the available device adapter with the available node;updating first state information of the first node that describes a state of the first subset of disk arrays with second state information of the second node that describes a state of the second subset of disk arrays; andproviding access to the first subset of disk arrays and the second subset of disk arrays through the available node and the available device adapter using the updated first state information.2. The method of claim 1 , wherein the second state information includes information on a state of the available device adapter.3. The method of claim 1 , further comprising:detecting a change in affiliation of the available device adapter from ...

Подробнее
Номер записи: 40
24-01-2019 дата публикации

CONCURRENT DATA ERASURE AND REPLACEMENT OF PROCESSORS

Номер: US20190026229A1
Автор: Borlick Matthew G., GUPTA Lokesh M., Hardy Clint A., Nielsen Karl A.
Принадлежит: INTERNATIONAL BUSINESS MACHINES CORPORATION

A method for concurrently erasing data on a processor and preparing the processor for removal from a computing system is disclosed. In one embodiment, such a method includes determining tasks queued to be executed on a processor and reassigning the tasks to a different processor, such as to a different processor in the same cluster as the processor. The method further prevents new tasks from being assigned to the processor. The method waits for currently executing tasks on the processor to complete. Once the currently executing tasks are complete, the method initiates a cache-hostile job on the processor to evict entries in cache of the processor. Once the cache-hostile job is complete, the method enables the processor to be removed from a computing system such as a storage system controller. A corresponding system and computer program product are also disclosed. 1. A method for concurrently erasing data on a processor and preparing the processor for removal from a computing system , the method comprising:determining tasks queued to be executed on an identified processor belonging to a cluster of processors;reassigning the tasks to a different processor within the cluster;preventing new tasks from being assigned to the identified processor;waiting for currently executing tasks on the identified processor to complete prior to initiating a cache-hostile job on the identified processor to replace entries in cache of the identified processor;once the currently executing tasks are complete, initiating the cache-hostile job on the identified processor; andonce the cache-hostile job is complete, removing the identified processor from the cluster.2. (canceled)3. (canceled)4. The method of claim 1 , wherein the cluster is implemented within a storage controller.5. The method of claim 1 , wherein the cache-hostile job allocates an amount of memory at least as large as the cache.6. The method of claim 1 , wherein the cache-hostile job performs at least one of: randomly writing ...

Подробнее
Номер записи: 41
24-04-2014 дата публикации

GLOBAL DATA ESTABLISHMENT FOR STORAGE ARRAYS CONTROLLED BY A PLURALITY OF NODES

Номер: US20140115253A1
Автор: GRUSY Ellen J., LOVRIEN Kurt A., Nielsen Karl A., Sheppard Jacob L.
Принадлежит: INTERNATIONAL BUSINESS MACHINES CORPORATION

A plurality of data arrays are coupled to a plurality of nodes via a plurality of adapters. The plurality of adapters discover the plurality of data arrays during startup, and information about the plurality of data arrays are communicated to corresponding local nodes of the plurality of nodes, wherein the local nodes broadcast the information to other nodes of plurality of nodes. A director node of the plurality of nodes determines which data arrays of the plurality of data arrays are a current set of global metadata arrays, based on the broadcasted information. 1. A method , comprising:maintaining a plurality of data arrays coupled to a plurality of nodes via a plurality of adapters;discovering, via the plurality of adapters, the plurality of data arrays during startup, and communicating information about the plurality of data arrays to corresponding local nodes of the plurality of nodes, wherein the local nodes broadcast the information to other nodes of plurality of nodes; anddetermining based on the broadcasted information, by a director node of the plurality of nodes, which data arrays of the plurality of data arrays are a current set of global metadata arrays.2. The method of claim 1 , wherein the global metadata arrays store global metadata that includes metadata for system configuration.3. The method of claim 2 , wherein the global metadata data arrays are a primary claim 2 , a secondary claim 2 , and a tertiary data array claim 2 , the method further comprising:maintaining, in a boot sector of each of the primary, secondary, and tertiary data arrays, a pointer record that stores indicators indicating the primary, secondary, and tertiary data array and a corresponding reconfiguration count.4. The method of claim 3 , the method further comprising:maintaining the global metadata in each of the primary, secondary, and tertiary data arrays.5. The method of claim 1 , the method further comprising:determining a node of the plurality of nodes to be the director ...

Подробнее
Номер записи: 42
24-04-2014 дата публикации

Validation of storage arrays based on information stored in global metadata

Номер: US20140115309A1
Автор: Ellen J. GRUSY, Jacob L. SHEPPARD, Karl A. Nielsen, Kurt A. Lovrien
Принадлежит: International Business Machines Corp

A director node of a plurality of nodes determines a plurality of data arrays, where the plurality of data arrays have been discovered at boot time. The director node determines global metadata information, based on reading boot sectors of at least one of the plurality of data arrays discovered at boot time. A determination is made from the global metadata information as to how many data arrays had been previously configured. In response to determining that the plurality of data arrays discovered at boot time is not equal in number to the previously configured data arrays, the director node determines that all configured data arrays have not been discovered.

Подробнее
Номер записи: 43
29-01-2015 дата публикации

SEMICONDUCTOR MEMORY GARBAGE COLLECTION

Номер: US20150032939A1
Автор: Gao Xue Dong, Long Min, Nielsen Karl A., Qian Hai Bo, Steffan Jeffrey R.
Принадлежит: INTERNATIONAL BUSINESS MACHINES CORPORATION

For semiconductor memory garbage collection, an identification module identifies a garbage collection time window for at least one block of a flash memory array. A garbage collection module garbage collects a first block of the flash memory array with a highest garbage collection level and an open garbage collection time window. 1. An apparatus comprising:an identification module identifying a garbage collection time window for at least one block of a flash memory array;a garbage collection module garbage collecting a first block of the flash memory array with a highest garbage collection level and an open garbage collection time window; andwherein at least a portion of the identification module and the garbage collection module comprise one or more of hardware and program code, the program code stored on one or more computer readable storage media.2. The apparatus of claim 1 , the identification module further determining a garbage collection level for the at least one block.3. The apparatus of claim 2 , wherein the garbage collection level is determined from at least one of a free pages number and a partial pages number for each block.4. The apparatus of claim 3 , wherein the garbage collection level is a critical level in response to at least one of the free pages number being less than a critical free pages threshold and the partial pages number being less than a critical partial pages threshold claim 3 , the garbage collection level is a middle level in response to at least one of the free pages number being less than a middle free pages threshold and not less than the critical free pages threshold claim 3 , and the partial pages number being less than a middle partial pages threshold and not less than the critical partial pages threshold claim 3 , and the garbage collection level is a warning level in response to at least one of the free pages number being less than a warning free pages threshold and not less than the middle free pages number claim 3 , and the ...

Подробнее
Номер записи: 44
04-02-2016 дата публикации

GLOBAL DATA ESTABLISHMENT FOR STORAGE ARRAYS CONTROLLED BY A PLURALITY OF NODES

Номер: US20160034283A1
Автор: GRUSY Ellen J., LOVRIEN Kurt A., Nielsen Karl A., Sheppard Jacob L.
Принадлежит:

A plurality of data arrays are coupled to a plurality of nodes via a plurality of adapters. The plurality of adapters discover the plurality of data arrays during startup, and information about the plurality of data arrays are communicated to corresponding local nodes of the plurality of nodes, wherein the local nodes broadcast the information to other nodes of plurality of nodes. A director node of the plurality of nodes determines which data arrays of the plurality of data arrays are a current set of global metadata arrays, based on the broadcasted information. 1. A method , comprising:maintaining a plurality of data arrays coupled to a plurality of nodes;broadcasting, by local nodes corresponding to the plurality of nodes, information about the plurality of data arrays to other nodes of plurality of nodes; anddetermining based on the broadcasted information, by a director node of the plurality of nodes, which data arrays of the plurality of data arrays are a current set of global metadata arrays comprising a primary, a secondary, and a tertiary data arrays, wherein the director node synchronizes global metadata between the primary, the secondary, and the tertiary data arrays, wherein each of the primary, the secondary, and the tertiary data arrays have a boot sector that stores pointer records pointing to the current set of global metadata arrays, and wherein boot sectors of other data arrays besides the global metadata arrays do not store pointer records pointing to the current set of global metadata arrays.2. The method of claim 1 , the global metadata includes metadata for system configuration.3. The method of claim 1 , the method further comprising:maintaining, in the boot sector of each of the primary, secondary, and tertiary data arrays a reconfiguration count.4. The method of claim 1 , the method further comprising:determining a node of the plurality of nodes to be the director node;collecting the information about each of the data arrays by the director ...

Подробнее
Номер записи: 45
06-02-2020 дата публикации

COPY SOURCE TO TARGET MANAGEMENT IN A DATA STORAGE SYSTEM

Номер: US20200042206A1
Автор: Ash Kevin J., GUPTA Lokesh M., Hardy Clint A., Nielsen Karl A.
Принадлежит:

Copy source to target operations may be selectively and preemptively undertaken in advance of source destage operations. In another aspect, logic detects sequential writes including large block writes to point-in-time copy sources. In response, destage tasks on the associated point-in-time copy targets are started which include in one embodiment, stride-aligned copy source to target operations which copy unmodified data from the point-in-time copy sources to the point-in-time copy targets in alignment with the strides of the target. As a result, when write data of write operations is destaged to the point-in-time copy sources, such source destages do not need to wait for copy source to target operations since they have already been performed. In addition, the copy source to target operations may be stride-aligned with respect to the stride boundaries of the point-in-time copy targets. Other features and aspects may be realized, depending upon the particular application. 1. A method , comprising:writing a modified set of data for a point-in-time copy source to a cache wherein the modified set of data is modified with respect to an unmodified set of data in the point-in-time copy source; andprior to initiation of a safe data commit scan of the cache to identify tracks of modified data in the cache to destage to storage, in preemptively and selectively initiating a copy source to target operation which includes:reading the point-in-time copy source to obtain read data including the unmodified set of data; andwriting the unmodified set of data to a point-in-time copy target; andinitiating a scan of the cache to identify tracks of modified data in the cache to destage to storage.2. The method of further comprising determining whether conditions for preemptive copy source to target operations are present for modified data in the cache including determining that conditions for preemptive copy source to target operation are present an interval of time prior to initiation of ...

Подробнее
Номер записи: 46
14-02-2019 дата публикации

TRANSFERRING DATA BETWEEN BLOCK AND FILE STORAGE SYSTEMS

Номер: US20190052698A1
Автор: Gao Xue Dong, Nielsen Karl A., Peng Yao, Rinaldi Brian A., Yao Tang Ren
Принадлежит:

Provided is a method, computer program product, and system for transferring data between block and file storage systems. A remote server may receive, from a host device, a request to restore data to the host device. The remote server may store the data as one or more objects, with each object corresponding to an extent of a logical volume on the host device. A set of strides on the host device that correspond to the one or more objects may be determined using metadata for the one or more objects. Each of the one or more objects may be split into a set of data pieces using the metadata. Each data piece may then be transmitted from the remote server to the host device. 1. A method comprising:receiving, by a remote server and from a host device, a request to restore data to the host device, wherein the data is stored by the remote server as one or more objects, each respective object corresponding to a respective extent of a logical volume that includes the data on the host device;determining, using metadata for the one or more objects, a set of strides on the host device that corresponds to the one or more objects;splitting each of the one or more objects into a set of data pieces using the metadata for the one or more objects, each data piece corresponding to a stride in the set of strides; andtransmitting each data piece from the remote server to the host device.2. The method of claim 1 , wherein transmitting each data piece from the remote server to the host device comprises transmitting each data piece to a stride buffer that is communicatively coupled to the host device.3. The method of claim 1 , wherein determining the set of strides on the host device that corresponds to the one or more objects comprises retrieving the metadata from a master volumes table file (MVTF) claim 1 , the MVTF being a node that stores information for each volume of the host device that has been transferred to the remote server.4. The method of claim 3 , the method further comprising: ...

Подробнее
Номер записи: 47
28-02-2019 дата публикации

REBALANCING OF THE FIRST EXTENTS OF LOGICAL VOLUMES AMONG A PLURALITY OF RANKS

Номер: US20190065068A1
Автор: Hardy Clint A., Nielsen Karl A., Xie Qiang, ZHANG Hui
Принадлежит:

A plurality of extents of a plurality of logical volumes are stored in a plurality of ranks, where each logical volume of the plurality of logical volumes is comprised of a plurality of extents including a first extent. In response to determining that first extents stored in each rank of the plurality of ranks have become unbalanced in number in the plurality of ranks, a balancing of the first extents in the plurality of ranks is performed by redistributing the first extents in the plurality of ranks. 1. A method , comprising:storing a plurality of extents of a plurality of logical volumes in a plurality of ranks, wherein each logical volume of the plurality of logical volumes is comprised of a plurality of extents including a first extent; andin response to determining that first extents stored in each rank of the plurality of ranks have become unbalanced in number in the plurality of ranks, performing a balancing of the first extents in the plurality of ranks by redistributing the first extents in the plurality of ranks, wherein on an average a greater number of I/O operations are performed on the first extent of a logical volume than on other extents of the logical volume, and wherein the first extent of the logical volume stores a directory information of the logical volume.23-. (canceled)4. The method of claim 1 , wherein the redistributing further comprises:moving a first extent of a first logical volume from a first rank to a second rank of the plurality or ranks, in response to determining that the second rank has a fewer number of first extents than the first rank.5. The method of claim 1 , the method further comprising:in response to a request to add a new logical volume to the plurality of extents, placing a first extent of the new logical volume in a rank of the plurality of ranks that has fewer first extents than other ranks of the plurality of ranks.6. The method of claim 1 , wherein the redistributing is performed in response to determining that an ...

Подробнее
Номер записи: 48
08-03-2018 дата публикации

Raid data loss prevention

Номер: US20180067809A1
Автор: Brian A. Rinaldi, Clint A. Hardy, Karl A. Nielsen, Lokesh M. Gupta, Matthew G. Borlick
Принадлежит: International Business Machines Corp

A method for preventing data loss in a RAID includes monitoring storage drives making up a RAID. The method individually tests a storage drive of the RAID by subjecting the storage drive to a stress workload test. This stress workload test may be designed to place additional stress on the storage drive while refraining from adding stress to other storage drives in the RAID. In the event the storage drive fails the stress workload test (e.g., the storage drive cannot adequately handle the additional workload or generates errors in response to the additional workload), the method replaces the storage drive with a spare storage drive and rebuilds the RAID. In certain embodiments, the method tests the storage drive with greater frequency as the age of the storage drive increases. A corresponding system and computer program product are also disclosed.

Подробнее
Номер записи: 49
05-03-2020 дата публикации

MIGRATING DATA FROM A SMALL EXTENT POOL TO A LARGE EXTENT POOL

Номер: US20200073955A1
Автор: Hardy Clint A., KALOS Matthew J., Nielsen Karl A., Xie Qiang, ZHANG Hui
Принадлежит:

A computer-implemented method according to one embodiment includes identifying a request to migrate data associated with a volume from a source storage pool that has a first rank extent size to a destination storage pool that has a second rank extent size greater than the first rank extent size. Additionally, the method includes creating a correspondence between logical volume extents of the volume and physical offset locations within rank extents of the destination storage pool. Further, the method includes migrating data from one or more ranks of the source storage pool to one or more ranks of the destination storage pool, according to the correspondence between the logical volume extents of the volume and the physical offset locations within the rank extents of the destination storage pool. 1. A computer-implemented method , comprising:identifying a request to migrate data associated with a volume from a source storage pool having a first rank extent size to a destination storage pool having a second rank extent size greater than the first rank extent size;creating a correspondence between logical volume extents of the volume and physical offset locations within rank extents of the destination storage pool; andmigrating data from one or more ranks of the source storage pool to one or more ranks of the destination storage pool, according to the correspondence between the logical volume extents of the volume and the physical offset locations within the rank extents of the destination storage pool.2. The computer-implemented method of claim 1 , wherein creating the correspondence includes allocating one or more rank extents within the destination storage pool.3. The computer-implemented method of claim 1 , wherein creating the correspondence includes populating empty volume extents of the volume with corresponding offset locations within one or more allocated rank extents within the destination storage pool.4. The computer-implemented method of claim 1 , wherein ...

Подробнее
Номер записи: 50
22-03-2018 дата публикации

MANAGING RAID PARITY STRIPE CONTENTION

Номер: US20180081760A1
Автор: KALOS Matthew J., Nielsen Karl A., Stelmach Richard B.
Принадлежит: INTERNATIONAL BUSINESS MACHINES CORPORATION

For managing RAID parity stripe contention using a processor device in a computing environment, delaying, by a host being separate to the RAID, one of a plurality of operations overlapping a parity sector in a parity stripe with a currently running operation and serializing each one of the multiplicity of operations overlapping the parity sector. The host further serializes each one of the plurality of operations overlapping the parity sector. The delaying is performed when the host determines whether a new write written through a hardware performance path comprising the one of the plurality of operations will overlap the parity stripe of a previous write comprising the currently running operation at the RAID controller. 1. A method for managing RAID parity stripe contention using a processor device in a computing environment , the method comprising:delaying, by a host being separate to the RAID, one of a plurality of operations sent to a RAID controller having an overlapping of a parity sector in a parity stripe with a currently running operation and serializing, by the host, each one of the plurality of operations overlapping the parity sector; wherein the delaying further includes the host determining whether a new write written through a hardware performance path comprising the one of the plurality of operations will overlap the parity stripe of a previous write comprising the currently running operation at the RAID controller, and wherein the hardware performance path comprises a hardware optimization mode for handling write operations and updates controlled by the RAID controller.2. The method of claim 1 , further including using the hard performance path for each one of the plurality of operations by the RAID controller.3. The method of claim 1 , further including determining if each one of the plurality of operations overlaps with the currently running operation in the parity sector in the parity stripe.4. The method of claim 1 , further including allowing ...

Подробнее
Номер записи: 51
12-03-2020 дата публикации

Aggregation of updated tracks to be copied to a backup volume for physically contiguous storage on a raid stride

Номер: US20200081808A1
Автор: Clint A. Hardy, Dave FEI, Gail Spear, Karl A. Nielsen, Kevin Lin, Theresa M. BROWN
Принадлежит: International Business Machines Corp

A plurality of tracks that are to be copied to a backup volume are aggregated in a container data structure. The plurality of tracks are stored physically contiguously in a single Redundant Array of Independent Disks (RAID) stride. Mapping metadata is updated in the backup volume to indicate how logical tracks of the backup volume correspond to physical tracks stored in the RAID stride.

Подробнее
Номер записи: 52
02-04-2015 дата публикации

PROMOTION OF PARTIAL DATA SEGMENTS IN FLASH CACHE

Номер: US20150095561A1
Автор: BENHASE Michael T., BLINICK Stephen L., Eleftheriou Evangelos S., GUPTA Lokesh M., Haas Robert, Hu Xiao-Yu, KALOS Matthew J., Koltsidas Ioannis, Nielsen Karl A., PLETKA Roman A.
Принадлежит: INTERNATIONAL BUSINESS MACHINES CORPORATION

For efficient track destage in secondary storage in a more effective manner, for temporal bits employed with sequential bits for controlling the timing for destaging the track in a primary storage, a preference of movement to lower speed cache level is implemented based on at least one of an amount of holes and a data heat metric. If a first bit has at least one of a lower amount of holes and a hotter data heat metric, it is moved to the lower speed cache level ahead of a second bit that has at least one of a higher amount of holes and a cooler data heat. If the first bit has a hotter data heat and greater than a predetermined number of holes, the first bit is discarded. 1. A method for promoting partial data segments in a computing storage environment having lower and higher speed levels of cache by a processor , comprising: a first of the partial data segments having at least one of a lower amount of holes and a hotter data heat metric is moved to the lower speed cache level ahead of a second of the partial data segments having at least one of a higher amount of holes and a cooler data heat; and', 'if the first of the partial data segments has a hotter data heat and greater than a predetermined number of holes, the first of the partial data segments is discarded., 'implementing a preference for movement of the partial data segments to the lower speed cache level based on at least one of an amount of holes and a data heat metric, wherein, 'configuring a data moving mechanism adapted for performing2. The method of claim 1 , further including claim 1 , pursuant to configuring the data mover mechanism claim 1 , allowing the partial data segments to remain in the higher speed cache level for a time period longer that at least one whole data segment.3. The method of claim 1 , further including claim 1 , pursuant to configuring the data mover mechanism claim 1 , writing one of the partial data segments to the lower speed cache level as a whole data segment.4. The method ...

Подробнее
Номер записи: 53
07-04-2016 дата публикации

TASK POOLING AND WORK AFFINITY IN DATA PROCESSING

Номер: US20160098296A1
Автор: Ash Kevin J., Burke Seamus J., GUPTA Lokesh M., Hardy Clint A., KALOS Matthew J., NGUYEN Trung N., Nielsen Karl A., Rasor Louis A., Whitworth David B.
Принадлежит: INTERNATIONAL BUSINESS MACHINES CORPORATION

Mechanisms for improving computing system performance by a processor device. System resources are organized into a plurality of groups. Each of the plurality of groups is assigned one of a plurality of predetermined task pools. Each of the predetermined task pools has a plurality of tasks. Each of the plurality of groups corresponds to at least one physical boundary of the system resources such that a speed of an execution of those of the plurality of tasks for a particular one of the plurality of predetermined task pools is optimized by a placement of an association with the at least one physical boundary and the plurality of groups. 1. A method for improving computing system performance by a processor device , comprising: 'wherein each of the plurality of groups corresponds to at least one physical boundary of the system resources such that a speed of an execution of those of the plurality of tasks for a particular one of the plurality of predetermined task pools is optimized by a placement of an association with the at least one physical boundary and the plurality of groups.', 'organizing system resources into a plurality of groups, each of the plurality of groups assigned one of a plurality of predetermined task pools, each of the predetermined task pools having a plurality of tasks;'}2. The method of claim 1 , wherein organizing system resources into a plurality of groups includes organizing a plurality of Central Processing Units (CPUs) into a plurality of CPU groups claim 1 , each of the plurality of CPU groups assigned one of the plurality of predetermined task pools claim 1 , wherein each of the plurality of CPU groups are selected in part based on the at least one physical boundary for optimizing the execution speed.3. The method of claim 2 , further including organizing a plurality of Task Control Blocks (TCBs) into TCB task pools of the plurality of predetermined task pools.4. The method of claim 3 , further including assigning particular ones of the ...

Подробнее
Номер записи: 54
09-04-2020 дата публикации

I/O RESPONSE TIMES IN DATA REPLICATION ENVIRONMENTS

Номер: US20200110541A1
Автор: Juarez Larry, Nielsen Karl A., Riley Sean P., Sheppard Jacob L., Sorenson Todd C.
Принадлежит: INTERNATIONAL BUSINESS MACHINES CORPORATION

A method for improving I/O response times in a data replication environment is disclosed. In one embodiment, such a method includes receiving, at a primary storage system, a request to read data on the primary storage system. The method starts a timer upon receiving the request. In the event the data cannot be retrieved from the primary storage system by the time the timer expires, the method requests the data from a secondary storage system. In the event the primary storage system returns the data before the secondary storage system, the method returns data retrieved from the primary storage system to a host system. In the event the secondary storage system returns the data before the primary storage system, the method returns the data retrieved from the secondary storage system to the host system. A corresponding system and computer program product are also disclosed. 1. A method for improving I/O response times in a data replication environment , the method comprising:receiving, at a primary storage system from a host system, a request to read data on the primary storage system;starting a timer upon receiving the request;in the event the data cannot be retrieved from the primary storage system by the time the timer expires, requesting, by the primary storage system, the data from a secondary storage system;in the event the primary storage system returns the data before the secondary storage system, returning the data retrieved from the primary storage system to the host system; andin the event the secondary storage system returns the data before the primary storage system, returning the data retrieved from the secondary storage system to the host system.2. The method of claim 1 , further comprising claim 1 , in the event the primary storage system returns the data before the secondary storage system claim 1 , incrementing the timer.3. The method of claim 2 , wherein incrementing the timer comprises incrementing the timer until a maximum value is reached.4. The ...

Подробнее
Номер записи: 55
13-05-2021 дата публикации

USING A MACHINE LEARNING MODULE TO DETERMINE WHEN TO PERFORM ERROR CHECKING OF A STORAGE UNIT

Номер: US20210141688A1
Автор: Borlick Matthew G., GUPTA Lokesh M., Hardy Clint A., Nielsen Karl A.
Принадлежит:

Provided are a computer program product, system, and method for using a machine learning module to determine when to perform error checking of a storage unit. Input on attributes of at least one storage device comprising the storage unit are provided to a machine learning module to produce an output value. An error check frequency is determined from the output value. A determination is made as to whether the error check frequency indicates to perform an error checking operation with respect to the storage unit. The error checking operation is performed in response to determining that the error checking frequency indicates to perform the error checking operation. 126-. (canceled)27. A computer program product for error checking data in a storage , the computer program product comprising a computer readable storage medium storing computer readable program code that when executed performs operations , the operations comprising:providing input on attributes of a storage to a machine learning module to produce an output value indicating a likelihood that the storage is experiencing an error;performing an error checking operation in response to determining that the output value indicates to perform the error checking operation; andusing the output value to adjust an error check frequency in response to the output value indicating to adjust the error check frequency, wherein the error check frequency indicates a number of writes that occur before an error checking operation is performed at the storage.28. The computer program product of claim 27 , wherein the output value comprises a number from zero to 1 claim 27 , not performing the error checking operation in response to the output value being less than a lower bound; and', 'performing the error checking operation in response to the output value being greater than an upper bound., 'wherein the determining whether the error check frequency indicates to perform the error checking operation comprises29. The computer ...

Подробнее
Номер записи: 56
03-05-2018 дата публикации

TRANSFERRING DATA BETWEEN BLOCK AND FILE STORAGE SYSTEMS

Номер: US20180124152A1
Автор: Gao Xue Dong, Nielsen Karl A., Peng Yao, Rinaldi Brian A., Yao Tang Ren
Принадлежит:

A processor may receive a request to transmit a logical volume to a cloud-based server. The logical volume may be stored in a data storage subsystem that includes one or more ranks. Each rank may include one or more extents, which may include one or more stride. The processor may determine an extent of the one or more extents that includes data of the logical volume. The processor may determine a set of strides associated with the extent. The processor may copy the set of strides into a stride buffer and combine the set of strides into a block extent file. The processor may transmit the block extent file to the cloud server. 1. A method comprising:receiving a request to transmit a logical volume stored on a host server to a remote server, the logical volume being stored in a data storage system that includes one or more ranks, each rank having one or more extents, each extent having one or more strides;determining an extent of the one or more extents that includes data of the logical volume;determining a set of strides associated with the extent;copying the set of strides for the extent into a stride buffer;combining the set of strides for the extent into a block extent file; andtransmitting the block extent file to the remote server.2. The method of claim 1 , the method further comprising determining whether the logical volume is stored using block-level storage claim 1 , wherein the determining the extent is performed in response to determining that the logical volume is stored using block-level storage claim 1 , wherein the data storage system is a storage attached network (SAN) device claim 1 , and wherein each rank of the one or more ranks is a redundant array of independent disks (RAID) array.3. The method of claim 2 , wherein the determining an extent of the one or more extents that includes data of the logical volume includes:determining one or more logical block address (LBAs) associated with the logical volume;determining, using the LBAs and a rank segment ...

Подробнее
Номер записи: 57
03-05-2018 дата публикации

TRANSFERRING DATA BETWEEN BLOCK AND FILE STORAGE SYSTEMS

Номер: US20180124157A1
Автор: Gao Xue Dong, Nielsen Karl A., Peng Yao, Rinaldi Brian A., Yao Tang Ren
Принадлежит:

A processor may receive a request to transmit a logical volume to a cloud-based server. The logical volume may be stored in a data storage subsystem that includes one or more ranks. Each rank may include one or more extents, which may include one or more stride. The processor may determine an extent of the one or more extents that includes data of the logical volume. The processor may determine a set of strides associated with the extent. The processor may copy the set of strides into a stride buffer and combine the set of strides into a block extent file. The processor may transmit the block extent file to the cloud server. 1receiving a request to transmit a logical volume stored on a host server to a remote server, the logical volume being stored in a data storage system that includes one or more ranks, each rank having one or more extents, each extent having one or more strides,wherein the logical volume includes one or more distinct logical volumes,wherein the data storage system is a Network-attached Storage (NAS) device that includes a storage processor, wherein each rank of the one or more ranks is a redundant array of independent disks (RAID) array;determining that the logical volume is stored using block-level storage; determining one or more logical block address (LBAs) associated with the logical volume;', 'determining, using the LBAs and a rank segment table, one or more ranks that are associated with the LBAs; and', 'mapping the one or more LBAs associated with the logical volume to one or more extent ranges using a logic configuration volume segment table;, 'determining, in response to determining that the logical volume is stored using block-level storage, an extent of the one or more extents that includes data of the logical volume bydetermining a set of strides associated with the extent;copying the set of strides for the extent into a stride buffer;combining the set of strides for the extent into a block extent file;transmitting the block extent ...

Подробнее
Номер записи: 58
24-07-2014 дата публикации

Thinly provisioned flash cache with shared storage pool

Номер: US20140208017A1
Автор: Karl A. Nielsen, Lokesh M. Gupta, Michael T. Benhase
Принадлежит: International Business Machines Corp

For data processing in a computing storage environment by a processor device, the computing storage environment incorporating at least high-speed and lower-speed caches, and managed tiered levels of storage, a Solid State Device (SSD) tier is variably shared between the lower-speed cache and the managed tiered levels of storage such that the managed tiered levels of storage are operational on large data segments, and the lower-speed cache is allocated with the large data segments, yet operates with data segments of a smaller size than the large data segments and within the large data segments.

Подробнее
Номер записи: 59
24-07-2014 дата публикации

THINLY PROVISIONED FLASH CACHE WITH SHARED STORAGE POOL

Номер: US20140208021A1
Автор: BENHASE Michael T., GUPTA Lokesh M., Nielsen Karl A.
Принадлежит: INTERNATIONAL BUSINESS MACHINES CORPORATION

For data processing in a computing storage environment by a processor device, the computing storage environment incorporating at least high-speed and lower-speed caches, and managed tiered levels of storage, a Solid State Device (SSD) tier is variably shared between the lower-speed cache and the managed tiered levels of storage such that the managed tiered levels of storage are operational on large data segments, and the lower-speed cache is allocated with the large data segments, yet operates with data segments of a smaller size than the large data segments and within the large data segments. 1. A method for data processing in a computing storage environment by a processor device , the computing storage environment incorporating at least high-speed and lower-speed caches , and managed tiered levels of storage , the method comprising:variably sharing a Solid State Device (SSD) tier between the lower-speed cache and the managed tiered levels of storage such that the managed tiered levels of storage are operational on large data segments, and the lower-speed cache is allocated with the large data segments, yet operates with data segments of a smaller size than the large data segments and within the large data segments.2. The method of claim 1 , further including configuring the SSD tier for caching those of the large data segments determined to be uniformly hot.3. The method of claim 1 , further including configuring the lower-speed cache for caching the data segments of the smaller size determined to be sparsely hot.4. The method of claim 2 , further including determining the uniformly hot data segments by determining that a heat map is hotter than a predetermined threshold.5. The method of claim 4 , wherein determining the heat map is hotter than the predetermined threshold includes determining that at least a predetermined number of granular portions of the heat map is hotter than the predetermined threshold.6. The method of claim 3 , further including determining ...

Подробнее
Номер записи: 60
23-04-2020 дата публикации

RECLAIMING STORAGE SPACE IN RAIDS MADE UP OF HETEROGENEOUS STORAGE DRIVES

Номер: US20200125284A1
Автор: Ash Kevin J., Borlick Matthew G., GUPTA Lokesh M., Nielsen Karl A.
Принадлежит: INTERNATIONAL BUSINESS MACHINES CORPORATION

A method for reclaiming storage space in RAID arrays made up of heterogeneous storage drives is disclosed. In one embodiment, such a method includes determining a most common storage capacity for a set of storage drives utilized in a storage system. The method further identifies physical storage drives from the set that contain unused storage space. The method pools the unused storage space of the physical storage drives to create virtual storage drives with storage capacities substantially equal to the most common storage capacity. The method then utilizes the virtual storage drives in existing or new RAID arrays. A corresponding system and computer program product are also disclosed. 1. A method for reclaiming storage space in RAID arrays made up of heterogeneous storage drives:determining a most common storage capacity for a plurality of physical storage drives in a storage system;identifying physical storage drives from the plurality that contain unused storage space;pooling the unused storage space to create virtual storage drives with storage capacities substantially equal to the most common storage capacity; andutilizing the virtual storage drives in the storage system to create RAID arrays.2. The method of claim 1 , wherein pooling the unused storage space to create virtual storage drives comprises creating a single virtual storage drive by using the storage space from multiple physical storage drives.3. The method of claim 1 , wherein utilizing the virtual storage drives in the storage system comprises mixing virtual storage drives with physical storage drives to create selected RAID arrays.4. The method of claim 1 , wherein utilizing the virtual storage drives in the storage system comprises not mixing virtual storage drives with physical storage drives to create selected RAID arrays.5. The method of claim 1 , wherein utilizing the virtual storage drives in the storage system comprises ensuring that performance and/or redundancy requirements associated ...

Подробнее
Номер записи: 61
07-05-2020 дата публикации

USING A MACHINE LEARNING MODULE TO SELECT A PRIORITY QUEUE FROM WHICH TO PROCESS AN INPUT/OUTPUT (I/O) REQUEST

Номер: US20200142846A1
Автор: Borlick Matthew G., GUPTA Lokesh M., Hardy Clint A., Nielsen Karl A.
Принадлежит:

Provided are a computer program product, system, and method for using at least one machine learning module to select a priority queue from which to process an Input/Output (I/O) request. Input I/O statistics are provided on processing of I/O requests at the queues to at least one machine learning module. Output is received from the at least one machine learning module for each of the queues. The output for each queue indicates a likelihood that selection of an I/O request from the queue will maintain desired response time ratios between the queues. The received output for each of the queues is used to select a queue of the queues. An I/O request from the selected queue is processed. 127-. (canceled)28. A computer program product for selecting one of a plurality queues having Input/Output (I/O) requests for a storage to process , comprising a computer readable storage medium having computer readable program code embodied therein that when executed performs operations , the operations comprising:providing at least one machine learning module that receives as input I/O statistics for the queues based on I/O activity at the queues and produces output indicating which queue to select;providing the output to use to select a queue of the queues from which to service an I/O request from the selected queue;determining an adjusted output for at least one of the queues based on a desired ratio of response times between queues;retraining the at least one machine learning module with the input I/O statistics to produce the adjusted output for the at least one of the queues; andusing the retrained at least one machine learning module to select one of the queues from which to process an I/O request.29. The computer program product of claim 28 , wherein the output for each queue indicates a likelihood that selection of an I/O request from the queue will maintain expected response time ratios between the queues.30. The computer program product of claim 28 , wherein the determining ...

Подробнее
Номер записи: 62
07-06-2018 дата публикации

Management of foreground and background processes in a storage controller

Номер: US20180157498A1
Автор: Karl A. Nielsen, Lokesh M. Gupta, Matthew G. Borlick, Trung N. NGUYEN
Принадлежит: International Business Machines Corp

A background process is configured to periodically scrub a boot storage of a storage controller to ensure operational correctness of the boot storage. One or more foreground processes store a system configuration data of the storage controller in the boot storage of the storage controller. The background process and the one or more foreground processes are executed to meet predetermined performance requirements for the background process and the one or more foreground processes.

Подробнее
Номер записи: 63
23-05-2019 дата публикации

Processing of a set of pending operations for a switchover from a first storage resource to a second storage resource

Номер: US20190155509A1
Автор: Clint A. Hardy, HUI Zhang, Karl A. Nielsen, Matthew G. Borlick, Matthew J. Kalos, Richard B. Stelmach
Принадлежит: International Business Machines Corp

A determination is made that data stored in an extent of a first storage resource is to be moved to an extent of a second storage resource. Operations that are still awaiting to start execution in the first storage resource after the data stored in the extent of the first storage resource has been moved to the extent of the second storage resource, are configured for execution in the second storage resource.

Подробнее
Номер записи: 64
24-06-2021 дата публикации

Migrating data from a large extent pool to a small extent pool

Номер: US20210191643A1
Автор: Clint A. Hardy, HUI Zhang, Karl A. Nielsen, Matthew J. Kalos, Qiang Xie
Принадлежит: International Business Machines Corp

A computer-implemented method according to one embodiment includes identifying a request to migrate data associated with a volume from a source storage pool having a first rank extent size to a destination storage pool having a second rank extent size smaller than the first rank extent size, creating a correspondence between logical volume extents of the volume and physical offset locations within rank extents of the source storage pool, and migrating data from one or more ranks of the source storage pool to one or more ranks of the destination storage pool, utilizing the correspondence between the logical volume extents of the volume and the physical offset locations within the rank extents of the source storage pool.

Подробнее
Номер записи: 65
20-06-2019 дата публикации

COPY SOURCE TO TARGET MANAGEMENT IN A DATA STORAGE SYSTEM

Номер: US20190187920A1
Автор: Ash Kevin J., GUPTA Lokesh M., Hardy Clint A., Nielsen Karl A.
Принадлежит:

Copy source to target operations may be selectively and preemptively undertaken in advance of source destage operations. In another aspect, logic detects sequential writes including large block writes to point-in-time copy sources. In response, destage tasks on the associated point-in-time copy targets are started which include in one embodiment, stride-aligned copy source to target operations which copy unmodified data from the point-in-time copy sources to the point-in-time copy targets in alignment with the strides of the target. As a result, when write data of write operations is destaged to the point-in-time copy sources, such source destages do not need to wait for copy source to target operations since they have already been performed. In addition, the copy source to target operations may be stride-aligned with respect to the stride boundaries of the point-in-time copy targets. Other features and aspects may be realized, depending upon the particular application. 1. A method , comprising:detecting a sequential write operation to modify a set of data in a point-in-time copy source; andinitiating a copy source to target operation which includes:directing a stride-aligned read operation to a point-in-time copy target of the point-in-time copy source to force a redirected operation to the point-in-time copy source to obtain read data including the set of data; andwriting stride-aligned data to point-in-time copy target including the read set of data.2. The method of further comprising generating a task control block data structure for controlling the copy source to target operation claim 1 , the task control block having at least two input values including a starting track value and a number of tracks value wherein the stride-aligned read operation is directed to one or more strides of tracks which include a track identified by the starting track value followed a number of tracks identified by the number of tracks value.3. The method of wherein the point-in-time ...

Подробнее
Номер записи: 66
20-06-2019 дата публикации

COPY SOURCE TO TARGET MANAGEMENT IN A DATA STORAGE SYSTEM

Номер: US20190187921A1
Автор: Ash Kevin J., GUPTA Lokesh M., Hardy Clint A., Nielsen Karl A.
Принадлежит:

Copy source to target operations may be selectively and preemptively undertaken in advance of source destage operations. In another aspect, logic detects sequential writes including large block writes to point-in-time copy sources. In response, destage tasks on the associated point-in-time copy targets are started which include in one embodiment, stride-aligned copy source to target operations which copy unmodified data from the point-in-time copy sources to the point-in-time copy targets in alignment with the strides of the target. As a result, when write data of write operations is destaged to the point-in-time copy sources, such source destages do not need to wait for copy source to target operations since they have already been performed. In addition, the copy source to target operations may be stride-aligned with respect to the stride boundaries of the point-in-time copy targets. Other features and aspects may be realized, depending upon the particular application. 1. A method , comprising:writing a modified set of data for a point-in-time copy source to cache wherein the modified set of data is modified with respect to an unmodified set of data in the point-in-time copy source;determining whether conditions for preemptive copy source to target operations are present for modified data in cache; andin response to a determination that conditions for preemptive copy source to target operations are present, preemptively and selectively initiating a copy source to target operation which includes:reading the point-in-time copy source to obtain read data including the unmodified set of data; andwriting the unmodified set of data to a point-in-time copy target; andinitiating a scan of cache to identify tracks of modified data in cache to destage to storage.2. The method of wherein determining whether conditions for preemptive copy source to target operations are present for modified data in cache includes determining that conditions for preemptive copy source to target ...

Подробнее
Номер записи: 67
09-08-2018 дата публикации

LEGACY PROGRAM CODE ANALYSIS AND OPTIMIZATION

Номер: US20180225110A1
Автор: Borlick Matthew G., GUPTA Lokesh M., Hardy Clint A., Nielsen Karl A.
Принадлежит: INTERNATIONAL BUSINESS MACHINES CORPORATION

A method for analyzing and optimizing legacy program code is disclosed. In one embodiment, such a method includes logically dividing legacy program code into multiple sections and possibly subsections. The method then instruments each section with a counter that increments a value each time the respective section is executed. The legacy program code is then executed over a specified period of time on a specified number of test systems. The values are then gathered from the counters and analyzed to determine relative importance of the sections. In certain embodiments, this analysis generates a list of sections that are dead. The method then removes, from the legacy program code, sections that are dead. A corresponding system and computer program product are also disclosed. 1. A method for analyzing and optimizing legacy program code , the method comprising:logically dividing legacy program code into a plurality of sections;instrumenting each section with a counter that increments a value each time the respective section is executed;executing, on at least one test system, the legacy program code over a specified period of time;gathering the values from the counters;analyzing the values to determine a relative importance of the sections; andidentifying for removal, from the legacy program code, sections having a counter value of zero.2. The method of claim 1 , wherein analyzing the values to determine a relative importance of the sections comprises generating a list of sections that are dead.3. The method of claim 1 , wherein the at least one test system comprises at least one of a production system and a dedicated test system.4. The method of claim 1 , wherein the counters are maintained on the at least one test system.5. The method of claim 1 , wherein the counters are maintained on a system external to the at least one test system.6. The method of claim 1 , further comprising optimizing the legacy program code based on the values from the counters claim 1 , wherein ...

Подробнее
Номер записи: 68
23-08-2018 дата публикации

SUPPLEMENTAL POWER DISTRIBUTION VOLTAGE STABILIZATION

Номер: US20180239414A1
Автор: Borlick Matthew G., Cagno Brian J., Elliott John C., GUPTA Lokesh M., Nielsen Karl A.
Принадлежит: INTERNATIONAL BUSINESS MACHINES CORPORATION

A method for providing stable and reliable power to electronic devices is disclosed. In one embodiment, such a method includes providing a backplane having several power supplies coupled thereto. The method further provides connectors to connect multiple power-consuming devices, such as storage drives, expansion cards, memory expansion cards, or the like, to the backplane. In certain embodiments, the backplane provides a data transfer path and shared power distribution to the power-consuming devices. In the event a power supply is electrically decoupled from the backplane, the method enables a supplemental power-supplying device to supply power to the backplane by way of one of the connectors. A corresponding system is also disclosed. 1. A method for providing stable and reliable power to electronic devices , the method comprising:providing a backplane having a plurality of power supplies coupled thereto;providing connectors to connect a plurality of power-consuming devices to the backplane; andin the event a power supply is electrically decoupled from the backplane, enabling a supplemental power-supplying device to supply power to the backplane by way of one of the connectors.2. The method of claim 1 , wherein the backplane provides a data transfer path and shared power distribution to the plurality of power-consuming devices.3. The method of claim 2 , wherein the power-consuming devices are data storage drives.4. The method of claim 3 , wherein the data storage drives comprise at least one hard disk drive.5. The method of claim 3 , wherein the data storage drives comprise at least one solid-state drive.6. The method of claim 1 , wherein the connectors are expansion slots for receiving adapter cards.7. The method of claim 1 , wherein the connectors are expansion slots on a PCI bus.8. The method of claim 1 , wherein the power supplies are device adapters and the power-consuming devices are data storage drives.9. The method of claim 1 , wherein the power-consuming ...

Подробнее
Номер записи: 69
30-07-2020 дата публикации

INCREASING STORAGE CAPACITY IN HETEROGENEOUS STORAGE ARRAYS

Номер: US20200241762A1
Автор: Ash Kevin J., Borlick Matthew G., GUPTA Lokesh M., Nielsen Karl A.
Принадлежит: INTERNATIONAL BUSINESS MACHINES CORPORATION

A method for increasing effective storage capacity in a heterogeneous storage array is disclosed. In one embodiment, such a method determines a number of smaller-capacity storage drives and a number of larger-capacity storage drives in a storage array. The method further determines which RAID arrays in the storage array may be composed exclusively of the larger-capacity storage drives. Using this information, the method establishes a first set of RAID arrays in the storage array that will be composed exclusively of the larger-capacity storage drives and a second set of RAID arrays that may contain the smaller-capacity storage drives. The method then initiates a process to swap the smaller-capacity storage drives in the first set with the larger-capacity storage drives in the second set until the first set of RAID arrays is composed exclusively of the larger-capacity storage drives. A corresponding system and computer program product are also disclosed. 1. A method for increasing effective storage capacity in a heterogeneous storage array , the method comprising:determining a number of larger-capacity storage drives that are utilized in a storage array, the storage array containing the larger-capacity storage drives and a quantity of smaller-capacity storage drives;taking into account the number, determining which RAID arrays in the storage array may be composed exclusively of the larger-capacity storage drives;establishing a first set of RAID arrays in the storage array that will be composed exclusively of the larger-capacity storage drives and a second set of RAID arrays that may contain the smaller-capacity storage drives; andinitiating a process to swap the smaller-capacity storage drives in the first set with the larger-capacity storage drives in the second set until the first set of RAID arrays is composed exclusively of the larger-capacity storage drives.2. The method of claim 1 , wherein initiating the process comprises initiating the process at designated ...

Подробнее
Номер записи: 70
30-07-2020 дата публикации

Migrating data from a large extent pool to a small extent pool

Номер: US20200241787A1
Автор: Clint A. Hardy, HUI Zhang, Karl A. Nielsen, Matthew J. Kalos, Qiang Xie
Принадлежит: International Business Machines Corp

A computer-implemented method according to one embodiment includes identifying a request to migrate data associated with a volume from a source storage pool having a first rank extent size to a destination storage pool having a second rank extent size smaller than the first rank extent size, creating a correspondence between logical volume extents of the volume and physical offset locations within rank extents of the source storage pool, and migrating data from one or more ranks of the source storage pool to one or more ranks of the destination storage pool, utilizing the correspondence between the logical volume extents of the volume and the physical offset locations within the rank extents of the source storage pool.

Подробнее
Номер записи: 71
06-09-2018 дата публикации

PROCESSING OF A SET OF PENDING OPERATIONS FOR A SWITCHOVER FROM A FIRST STORAGE RESOURCE TO A SECOND STORAGE RESOURCE

Номер: US20180253237A1
Автор: Borlick Matthew G., Hardy Clint A., KALOS Matthew J., Nielsen Karl A., Stelmach Richard B., ZHANG Hui
Принадлежит:

A determination is made that data stored in an extent of a first storage resource is to be moved to an extent of a second storage resource. Operations that are still awaiting to start execution in the first storage resource after the data stored in the extent of the first storage resource has been moved to the extent of the second storage resource, are configured for execution in the second storage resource. 1. A method , comprising:determining that data stored in an extent of a first storage resource is to be moved to an extent of a second storage resource; andconfiguring operations that are still awaiting to start execution in the first storage resource after the data stored in the extent of the first storage resource has been moved to the extent of the second storage resource, for execution in the second storage resource.2. The method of claim 1 , wherein the operations comprise input/output (I/O) requests claim 1 , the method further comprising:storing a plurality of pending I/O requests on the extent of the first storage resource while the data stored in the extent of the first storage resource is being copied to the extent of the second storage resource, wherein the plurality of pending I/O requests have not been transmitted to the first storage resource for execution at least at some instant of time prior to completion of copying of data stored in the extent of the first storage resource to the extent of the second storage resource; andin response to completion of copying of data stored in the extent of the first storage resource to the extent of the second storage resource, indicating that those I/O requests of the plurality of pending I/O requests that have not been transmitted to the first storage resource for execution, are to be executed in the second storage resource and not in the first storage resource.3. The method of claim 2 , wherein a higher priority is indicated for those I/O requests of the plurality of pending I/O requests that have not been ...

Подробнее
Номер записи: 72
22-08-2019 дата публикации

REBALANCING OF THE FIRST EXTENTS OF LOGICAL VOLUMES AMONG A PLURALITY OF RANKS

Номер: US20190258408A1
Автор: Hardy Clint A., Nielsen Karl A., Xie Qiang, ZHANG Hui
Принадлежит:

A plurality of extents of a plurality of logical volumes are stored in a plurality of ranks, where each logical volume of the plurality of logical volumes is comprised of a plurality of extents including a first extent. In response to determining that first extents stored in each rank of the plurality of ranks have become unbalanced in number in the plurality of ranks, a balancing of the first extents in the plurality of ranks is performed by redistributing the first extents in the plurality of ranks. 125-. (canceled)26. A method , comprising:storing a plurality of extents of a plurality of logical volumes in a plurality of ranks, wherein each logical volume of the plurality of logical volumes is comprised of a plurality of extents including a first extent;determining that first extents stored in each rank of the plurality of ranks have become unbalanced in number in the plurality of ranks by determining that a number of first extents differs by more than a predetermined percentage between any two ranks of the plurality of ranks; andin response to determining that first extents stored in each rank of the plurality of ranks have become unbalanced in number in the plurality of ranks, performing a balancing of the first extents in the plurality of ranks by redistributing the first extents in the plurality of ranks, wherein the redistributing is performed by moving the first extent of a first logical volume from a first rank to a second rank of the plurality or ranks, in response to determining that the second rank has a fewer number of first extents than the first rank.27. The method of claim 26 , the method further comprising:in response to a request to add a new logical volume to the plurality of extents, placing a first extent of the new logical volume in a rank of the plurality of ranks that has fewer first extents than other ranks of the plurality of ranks.28. The method of claim 26 , wherein the redistributing is performed in response to determining that an ...

Подробнее
Номер записи: 73
22-08-2019 дата публикации

USING A DELAY TIMER TO DELAY CODE LOAD OPERATIONS TO PROCESS QUEUED WRITE REQUESTS

Номер: US20190258424A1
Автор: Ash Kevin J., Hardy Clint A., KALOS Matthew J., Nielsen Karl A., Rinaldi Brian A., Utter Samantha A.
Принадлежит:

Provided are a computer program product, system, and method for using a delay timer to delay code load operations to process queued write requests. A code load is performed to a selected storage device in a storage array comprised of a plurality of the storage devices. Writes are queued to the storage array in a non-volatile storage while performing the code load. A determination is made as to whether the queued writes to the storage array exceed a threshold. A delay timer is started in response to determining that the queued writes to the storage array exceed the threshold. An additional code load is initiated to an additional selected storage device in the storage array in response to determining that the delay timer has expired. The additional code load is initiated to the additional selected storage device in response to determining that the queued writes are less than the threshold. 1. A computer program product for loading code into storage devices in a storage system , the computer program product comprising a computer readable storage medium having computer readable program code embodied therein that is executable to perform operations , the operations comprising:performing a code load to a selected storage device in a storage array comprised of a plurality of the storage devices;queuing writes to the storage array in a non-volatile storage while performing the code load;determining whether the queued writes to the storage array exceed a threshold;starting a delay timer in response to determining that the queued writes to the storage array exceed the threshold;initiating an additional code load to an additional selected storage device in the storage array in response to determining that the delay timer has expired; andinitiating the additional code load to the additional selected storage device in response to determining that the queued writes are less than the threshold.2. The computer program product of claim 1 , wherein the operations further comprise: ...

Подробнее
Номер записи: 74
29-08-2019 дата публикации

Virtual storage drive management in a data storage system

Номер: US20190266062A1
Автор: Karl A. Nielsen, Kevin J. Ash, Lokesh M. Gupta, Matthew G. Borlick
Принадлежит: International Business Machines Corp

In one embodiment, virtual storage drives are allocated to RAID arrays so that no two virtual storage drives of a RAID array are mapped to the same physical storage drive. In another aspect, error handling routines are limited to virtual storage drives impacted by an error in a physical storage drive so that virtual storage drives of the physical storage drive not impacted by the error are bypassed. In yet another aspect, cache operations to a target virtual storage drive may be throttled as a function of both a limit imposed on cache operations directed to the RAID array to which the virtual storage drive is allocated, and a separate limit on cache operations directed to a group of virtual storage drives which are mapped to the same physical storage drive as the target virtual storage drive. Other features and aspects may be realized, depending upon the particular application.

Подробнее
Номер записи: 75
19-10-2017 дата публикации

STORAGE AND APPLICATION CONTROLLER FOR MIRRORING AND SWITCHOVER OF APPLICATIONS IN A PLURALITY OF CLOUD LOCATIONS VIA A PLURALITY OF CONFIGURABLE SECURITY PROTOCOLS

Номер: US20170302733A1
Автор: Borlick Matthew G., GUPTA Lokesh M., Hathorn Roger G., Nielsen Karl A.
Принадлежит:

A storage and application controller that is coupled to a plurality of storage and application execution clouds is maintained. The storage and application controller transmits, via a first communications protocol, an application to a first storage and application execution cloud. The storage and application controller transmits, via a second communications protocol, a copy of the application to a second storage and application execution cloud. In response to a compromise of the first communications protocol, execution of the application is stopped and replaced via execution of the copy of the application. 1. A method , comprising:maintaining a storage and application controller coupled to a plurality of storage and application execution clouds;transmitting via a first communications protocol, by the storage and application controller, an application to a first storage and application execution cloud;transmitting via a second communications protocol, by the storage and application controller, a copy of the application to a second storage and application execution cloud; andin response to a compromise of the first communications protocol, stopping execution of the application and replacing the execution of the application via execution of the copy of the application.2. The method of claim 1 , wherein the first storage and application execution cloud is maintained by a first entity claim 1 , and wherein the second storage and application execution cloud is maintained by a second entity claim 1 , the method further comprising:in response to a failure in execution of the application in the first storage and application execution cloud, returning results to a host by executing the copy of the application in the second storage and application execution cloud.3. The method of claim 2 , the method further comprising:changing the first communications protocol to a different communications protocol after an elapse of a first predetermined amount of time, to transmit additional ...

Подробнее
Номер записи: 76
26-11-2015 дата публикации

MANAGING RAID PARITY STRIPE CONTENTION

Номер: US20150339194A1
Автор: KALOS Matthew J., Nielsen Karl A., Stelmach Richard B.
Принадлежит: INTERNATIONAL BUSINESS MACHINES CORPORATION

For managing RAID parity stripe contention using a processor device in a computing environment, delaying one of a multiplicity of operations overlapping a parity sector in a parity stripe with a currently running operation and serializing each one of the multiplicity of operations overlapping the parity sector. 1. A method for managing RAID parity stripe contention using a processor device in a computing environment , the method comprising:delaying one of a plurality of operations overlapping a parity sector in a parity stripe with a currently running operation and serializing each one of the plurality of operations overlapping the parity sector.2. The method of claim 1 , further including using a hard performance path for each one of the plurality of operations by a RAID controller.3. The method of claim 1 , further including determining if each one of the plurality of operations overlaps with the currently running operation in the parity sector in the parity stripe.4. The method of claim 1 , further including allowing those of the plurality of operations claim 1 , which are not overlapping with the currently running operation in the parity sector in the parity stripe claim 1 , to continue on a hardware performance path without being delayed.5. The method of claim 1 , further including maintaining a parity bitmap indicating those of a plurality of parity sectors in a plurality of parity stripes are affected by the plurality of operations.6. The method of claim 5 , further including setting a bit in the parity bitmap for the parity sector in the parity stripe for the currently running operation.7. The method of claim 6 , further including clearing the bit in the parity bitmap for the parity sector in the parity stripe upon completion of the currently running operation.8. A system for managing RAID parity stripe contention in a computing environment claim 6 , the system comprising:a RAID controller; and 'delays one of a plurality of operations overlapping a parity ...

Подробнее
Номер записи: 77
03-12-2015 дата публикации

Thinly provisioned flash cache with shared storage pool

Номер: US20150347318A1
Автор: Karl A. Nielsen, Lokesh M. Gupta, Michael T. Benhase
Принадлежит: International Business Machines Corp

For data processing in a computing storage environment by a processor device, the computing storage environment incorporating at least high-speed and lower-speed caches, and managed tiered levels of storage, a Solid State Device (SSD) tier is variably shared between the lower-speed cache and the managed tiered levels of storage such that the managed tiered levels of storage are operational on large data segments, and the lower-speed cache is allocated with the large data segments, yet operates with data segments of a smaller size than the large data segments and within the large data segments, where if selected data segments are cached in the lower-speed cache and are determined to become uniformly hot, the selected group from the lower-speed cache are migrated to the SSD tier.

Подробнее
Номер записи: 78
15-11-2018 дата публикации

STORAGE AND APPLICATION CONTROLLER FOR MIRRORING AND SWITCHOVER OF APPLICATIONS IN A PLURALITY OF CLOUD LOCATIONS VIA A PLURALITY OF CONFIGURABLE SECURITY PROTOCOLS

Номер: US20180332111A1
Автор: Borlick Matthew G., GUPTA Lokesh M., Hathorn Roger G., Nielsen Karl A.
Принадлежит:

A storage and application controller that is coupled to a plurality of storage and application execution clouds is maintained. The storage and application controller transmits, via a first communications protocol, an application to a first storage and application execution cloud. The storage and application controller transmits, via a second communications protocol, a copy of the application to a second storage and application execution cloud. In response to a compromise of the first communications protocol, execution of the application is stopped and replaced via execution of the copy of the application. 120-. (canceled)21. A method , comprising:transmitting via a first communications protocol, an application to a first storage and application execution cloud;transmitting via a second communications protocol, a copy of the application to a second storage and application execution cloud; andin response to a compromise of the first communications protocol, stopping execution of the application and replacing the execution of the application via execution of the copy of the application.22. The method of claim 21 , wherein the first storage and application execution cloud is maintained by a first entity claim 21 , and wherein the second storage and application execution cloud is maintained by a second entity claim 21 , the method further comprising:in response to a failure in execution of the application in the first storage and application execution cloud, returning results to a host by executing the copy of the application in the second storage and application execution cloud.23. The method of claim 22 , the method further comprising:changing the first communications protocol to a different communications protocol after an elapse of a first predetermined amount of time, to transmit additional applications from a storage and application controller to the first storage and application execution cloud.24. The method of claim 23 , the method further comprising:changing ...

Подробнее
Номер записи: 79
24-10-2019 дата публикации

Management of foreground and background processes in a storage controller

Номер: US20190324845A1
Автор: Karl A. Nielsen, Lokesh M. Gupta, Matthew G. Borlick, Trung N. NGUYEN
Принадлежит: International Business Machines Corp

A background process is configured to periodically scrub a boot storage of a storage controller to ensure operational correctness of the boot storage. One or more foreground processes store a system configuration data of the storage controller in the boot storage of the storage controller. The background process and the one or more foreground processes are executed to meet predetermined performance requirements for the background process and the one or more foreground processes.

Подробнее
Номер записи: 80
30-11-2017 дата публикации

TARGETED SECURE DATA OVERWRITE

Номер: US20170344280A1
Автор: Borlick Matthew G., LOVRIEN Kurt A., Nielsen Karl A.
Принадлежит:

Provided are a computer program product, system, and method in accordance with one embodiment of the present description, in which selected memory resources targeted for secure data cleaning. For example, memory resources which may be targeted for secure data cleaning may include a specific volume (or portion of a volume) of data storage which has been selected for secure erasure of any residual data which may remain on the targeted storage volume before the volume is released for use by others. Other examples of memory resources which may be targeted for secure data cleaning in accordance with the present description may include one or more buffers located in switches or other storage area network components which provide data paths between hosts and storage controllers or storage control units. Other aspects of targeted secure data overwriting in accordance with the present description are described. 1. A method , comprising: determining whether a secure data overwrite target metadata attribute of the first volume of data storage has been set; and', 'in response to a determination that the secure data overwrite target metadata attribute of the first volume of data storage has been set, performing a multi-pass secure data overwriting of the first memory location., 'data cleaning a first memory location of a first volume of data storage to erase residual data stored in the first memory location, said data cleaning including2. The method of wherein the data cleaning further includes in response to a determination that the secure data overwrite target metadata attribute of the first volume of data storage has been set claim 1 , setting a data structure indicating a status of memory locations of the first volume to indicate a status of the first memory location as pending a multi-pass secure data overwriting of the first memory location.3. The method of wherein the data cleaning further includes determining a status of the first memory location as pending a multi-pass ...

Подробнее
Номер записи: 81
07-12-2017 дата публикации

DATA LOSS RECOVERY IN A SECONDARY STORAGE CONTROLLER FROM A PRIMARY STORAGE CONTROLLER

Номер: US20170351440A1
Автор: Carson Matthew D., Mellgren Carol S., Nielsen Karl A., SANCHEZ Matthew, Sorenson Todd C.
Принадлежит:

A secondary storage controller determines one or more tracks of one or more volumes in which data loss has occurred in the secondary storage controller. The secondary storage controller suspends a peer to peer remote copy operation between the secondary storage controller and a primary storage controller. Information on the one or more tracks of the one or more volumes in which the data loss has occurred is transmitted to the primary storage controller. 1. A method comprising ,determining, by a secondary storage controller, one or more tracks of one or more volumes in which data loss has occurred in the secondary storage controller;suspending, by the secondary storage controller, a peer to peer remote copy operation between the secondary storage controller and a primary storage controller; andtransmitting information on the one or more tracks of the one or more volumes in which the data loss has occurred to the primary storage controller.2. The method of claim 1 , the method further comprising:accumulating over a period of time, by the secondary storage controller, the information on the one or more tracks of the one or more volumes in which the data loss has occurred, prior to transmitting of any part of the information to the primary storage controller.3. The method of claim 1 , the method further comprising:in response to an unsuspension of the peer to peer remote copy operation, receiving by the secondary storage controller, via the peer to peer remote copy operation, data stored in the primary storage controller to restore data that was lost in the one or more tracks of the one or more volumes of the secondary storage controller.4. The method of claim 1 , wherein the one or more tracks comprise a first track and a second track of a volume claim 1 , the method further comprising:in response to an unsuspension of the peer to peer remote copy operation, receiving by the secondary storage controller, data stored in the primary storage controller to restore data in ...

Подробнее
Номер записи: 82
07-11-2019 дата публикации

LOAD BALANCING BETWEEN VIRTUAL STORAGE DRIVES

Номер: US20190339897A1
Автор: Ash Kevin J., Borlick Matthew G., GUPTA Lokesh M., Nielsen Karl A.
Принадлежит: INTERNATIONAL BUSINESS MACHINES CORPORATION

A method for balancing load among virtual storage drives is disclosed. In one embodiment, such a method includes providing multiple storage drives and dividing each storage drive into multiple virtual storage drives. The method further creates RAID arrays from the virtual storage drives. Each RAID array is made up of extents that are striped across its virtual storage drives. The method tracks I/O to each virtual storage drive to determine which virtual storage drives have high I/O traffic and which virtual storage drives have low I/O traffic. The virtual storage drives are correlated to their respective RAID arrays. The method migrates extents from RAID arrays having virtual storage drives with high I/O traffic to RAID arrays having virtual storage drives with low I/O traffic. A corresponding system and computer program product are also disclosed. 1. A method for balancing load among virtual storage drives , the method comprising:providing a plurality of physical storage drives;dividing each physical storage drive into a plurality of virtual storage drives;creating redundant array of independent disks (RAID) arrays from the virtual storage drives such that virtual storage drives on the same physical storage drive may be utilized in different RAID arrays, wherein each RAID array is made up of extents that are striped across its virtual storage drives;tracking input/output (I/O) to each virtual storage drive to determine which virtual storage drives have high I/O traffic and which virtual storage drives have low I/O traffic;correlating the virtual storage drives to their respective RAID arrays; andmigrating extents from RAID arrays having virtual storage drives with high I/O traffic to RAID arrays having virtual storage drives with low I/O traffic.2. The method of claim 1 , wherein tracking I/O to each virtual storage drive comprises tracking average I/O to each virtual storage drive over a specified period of time.3. The method of claim 2 , wherein tracking I/O to ...

Подробнее
Номер записи: 83
14-11-2019 дата публикации

POWER LEVEL MANAGEMENT IN A DATA STORAGE SYSTEM

Номер: US20190346904A1
Автор: Bernhardt Bradley, Fleischman Thomas J., Hutzler Richard, Montanez Mitchell, Morse William K., Nielsen Karl A., Tannenberger Hans-Joachim
Принадлежит:

In one embodiment, power level management in accordance with the present description, is provided in a storage unit having both a disk storage drive, and another non-volatile, non-disk memory or storage such as a solid state drive, for storing metadata. The metadata storage provides direct access to the metadata stored in the non-disk storage even though the disk storage drive may be in a low power mode in which the data storage media disk of the disk storage drive is stopped or spinning at a reduced rate of rotation. As a result, power consumption and cooling requirements associated with disk storage drives, may be reduced in a low power level mode of storage unit operation for input/output operations limited to metadata stored in the metadata storage. Other features and aspects may be realized, depending upon the particular application. 1. A system , comprising:a data storage system having a storage controller and at least one storage unit controlled by the storage controller and configured to store data, wherein the storage controller has a processor and a cache, and wherein the storage unit has an input, a metadata storage configured to store metadata and a disk storage drive having a data storage media disk configured to store data; and transferring metadata between a storage unit input and a metadata storage of the storage unit in a first power level mode in which reading data from and writing data to a data storage media disk of a disk storage drive of the storage unit is disabled; and', 'transferring data between the storage unit input and the data storage media disk of the disk storage drive in a second power level mode in which reading data from and writing data to the data storage media disk of the disk storage drive is enabled; and', 'wherein the first power level mode has a reduced level of power expenditure as compared to the second power level mode., 'a computer program product comprising a computer readable storage medium having program instructions ...

Подробнее
Номер записи: 84
13-12-2018 дата публикации

USING ALTERNATE RECOVERY ACTIONS FOR INITIAL RECOVERY ACTIONS IN A COMPUTING SYSTEM

Номер: US20180357120A1
Автор: Borlick Matthew G., GUPTA Lokesh M., Nielsen Karl A.
Принадлежит:

Provided are a computer program product, system, and method for using alternate recovery actions for initial recovery actions in a computing system. An initial recovery table provides initial recovery actions to perform for errors detected in the computing system. An alternate recovery table is received including at least one alternate recovery action for at least one of the initial recovery actions. An alternative recovery action provided for an initial recovery action specifies a different recovery path involving at least one of a different action and a different component in the computing system than involved in the initial recovery action. A determination is made as to whether to use the initial recovery action in the initial recovery table for a detected error or the alternate recovery action in the alternate recovery table. The determined initial recovery action or alternate recovery action determined is used to address the detected error. 1. A computer program product for performing a recovery action upon detecting an error in a computing system , the computer program product comprising a computer readable storage medium having computer readable program code embodied therein that is executable to perform operations , the operations comprising:maintaining an initial recovery table providing initial recovery actions to perform for errors detected in the computing system;receiving an alternate recovery table including at least one alternate recovery action for at least one of the initial recovery actions, wherein an alternative recovery action provided for an initial recovery action specifies a different recovery path involving at least one of a different action and a different component in the computing system than involved in the initial recovery action;detecting an error in the computing system;determining whether to use the initial recovery action in the initial recovery table for the detected error or the alternate recovery action in the alternate recovery ...

Подробнее
Номер записи: 85
21-11-2019 дата публикации

PREVENTING UNEXPECTED POWER-UP FAILURES OF HARDWARE COMPONENTS

Номер: US20190354158A1
Автор: Borlick Matthew G., Cagno Brian J., GUPTA Lokesh M., Nielsen Karl A., Sorenson Todd C.
Принадлежит:

In one embodiment, a method includes determining a plurality of hardware components of a system. The method also includes power cycling a first hardware component of the plurality of hardware components of the system according to a dynamic schedule. A period of time in which power cycling of the first hardware component takes place is shortened as the age of the first hardware component approaches the expected lifespan of the first hardware component. Also, the method includes determining whether the first hardware component experienced a power-up failure resulting from the power cycling. Moreover, the method includes outputting an indication to replace and/or repair the first hardware component in response to a determination that the first hardware component experienced the power-up failure resulting from the power cycling. Other systems, methods, ad computer program products for preventing unexpected power-up failures of individual hardware components are described in accordance with more embodiments. 1. A method , comprising:determining a plurality of hardware components of a system;power cycling a first hardware component of the plurality of hardware components of the system according to a dynamic schedule, wherein a period of time in which power cycling of the first hardware component takes place is shortened as the age of the first hardware component approaches the expected lifespan of the first hardware component;determining whether the first hardware component experienced a power-up failure resulting from the power cycling; andoutputting an indication to replace and/or repair the first hardware component in response to a determination that the first hardware component experienced the power-up failure resulting from the power cycling.2. The method as recited in claim 1 , further comprising:routing input and/or output (I/O) requests that are destined for the first hardware component to a first redundant hardware component for processing thereof prior to and ...

Подробнее
Номер записи: 86
21-11-2019 дата публикации

SELECTING A PRIORITY QUEUE FROM WHICH TO PROCESS AN INPUT/OUTPUT (I/O) REQUEST USING A MACHINE LEARNING MODULE

Номер: US20190354496A1
Автор: Borlick Matthew G., GUPTA Lokesh M., Hardy Clint A., Nielsen Karl A.
Принадлежит:

Provided are a computer program product, system, and method for using at least one machine learning module to select a priority queue from which to process an Input/Output (I/O) request. Input I/O statistics are provided on processing of I/O requests at the queues to at least one machine learning module. Output is received from the at least one machine learning module for each of the queues. The output for each queue indicates a likelihood that selection of an I/O request from the queue will maintain desired response time ratios between the queues. The received output for each of the queues is used to select a queue of the queues. An I/O request from the selected queue is processed. 1. A computer program product for selecting one of a plurality of queues having Input/Output (I/O) requests for a storage to process , comprising a computer readable storage medium having computer readable program code embodied therein that when executed performs operations , the operations comprising:providing Input I/O statistics on processing of I/O requests at the queues to at least one machine learning module;receiving, from the at least one machine learning module, output for each of the queues, wherein the output for each queue indicates a likelihood that selection of an I/O request from the queue will maintain desired response time ratios between the queues;using the received output for each of the queues to select a queue of the queues; andprocessing an I/O request from the selected queue.2. The computer program product of claim 1 , wherein the output for each queue of the queues comprises a value from zero to one indicating a likelihood that selection of an I/O request from the queue will maintain the desired response time ratios between the queues claim 1 , wherein using the received output to select a queue comprises selecting one of the queues having a highest output value.3. The computer program product of claim 1 , wherein the plurality of queues includes a low priority ...

Подробнее
Номер записи: 87
21-11-2019 дата публикации

Selecting a priority queue from which to process an input/output (I/O) request by training a machine learning module

Номер: US20190354497A1
Автор: Borlick Matthew G., GUPTA Lokesh M., Hardy Clint A., Nielsen Karl A.
Принадлежит:

Provided are a computer program product, system, and method for using at least one machine learning module to select a priority queue from which to process an Input/Output (I/O) request. Input I/O statistics are provided on processing of I/O requests at the queues to at least one machine learning module. Output is received from the at least one machine learning module for each of the queues. The output for each queue indicates a likelihood that selection of an I/O request from the queue will maintain desired response time ratios between the queues. The received output for each of the queues is used to select a queue of the queues. An I/O request from the selected queue is processed. 16-. (canceled)7. A computer program product for selecting one of a plurality queues having Input/Output (I/O) requests for a storage to process , comprising a computer readable storage medium having computer readable program code embodied therein that when executed performs operations , the operations comprising:providing at least one machine learning module that receives as input I/O statistics for the queues based on I/O activity at the queues and produces output for each of the queues, wherein the output for each queue indicates a likelihood that selection of an I/O request from the queue will maintain expected response time ratios between the queues;determining an adjusted output for at least one of the queues;retraining the at least one machine learning module with the input I/O statistics to produce the adjusted output for the at least one of the queues; andusing the retrained at least one machine learning module to select one of the queues from which to process an I/O request.8. The computer program product of claim 7 , wherein the determining the adjusted output and retraining the machine learning module are performed after processing at least one I/O request from one of the queues.9. The computer program product of claim 7 , wherein the adjusted output is determined for less ...

Подробнее
Номер записи: 88
17-12-2020 дата публикации

CONVERTING A RAID TO A MORE ROBUST RAID LEVEL

Номер: US20200393983A1
Автор: Borlick Matthew G., GUPTA Lokesh M., Hardy Clint A., Nielsen Karl A., Rinaldi Brian A.
Принадлежит: INTERNATIONAL BUSINESS MACHINES CORPORATION

A method for converting a redundant array of independent disks (RAID) to a more robust RAID level is disclosed. Such a method identifies, in a data storage environment, higher risk storage drives having a failure risk above a first threshold. The method determines a number of the higher risk storage drives that are contained within a RAID array of the data storage environment. The method determines whether the number exceeds a second threshold. The method also determines whether a destage rate associated with the RAID array is below a third threshold. In the event the number exceeds the second threshold and the destage rate is below the third threshold, the method converts the RAID array to a more robust RAID level. A corresponding system and computer program product are also disclosed. 1. A method for converting a redundant array of independent disks (RAID) to a more robust RAID level , the method comprising:identifying, in a data storage environment, higher risk storage drives having a failure risk above a first threshold;determining a number of the higher risk storage drives that are contained within a RAID array of the data storage environment;determining whether the number exceeds a second threshold;determining whether a destage rate associated with the RAID array is below a third threshold, the destage rate indicating a rate at which data is destaged from a cache to the RAID array; andupon determining that the number exceeds the second threshold and the destage rate is below the third threshold, converting the RAID array to a more robust RAID level.2. The method of claim 1 , wherein the RAID array is a RAID-5 array.3. The method of claim 2 , wherein converting the RAID array to a more robust RAID level comprises converting the RAID-5 array to a RAID-6 array.4. The method of claim 1 , further comprising determining whether the RAID array is associated with a high performance class.5. The method of claim 4 , further comprising only converting the RAID array to ...

Подробнее
Номер записи: 89
17-12-2020 дата публикации

REPORTING INCIDENTS OF DATA LOSS IN RAID ARRAYS

Номер: US20200394096A1
Автор: Borlick Matthew G., GUPTA Lokesh M., Hardy Clint A., Nielsen Karl A., Rinaldi Brian A.
Принадлежит: INTERNATIONAL BUSINESS MACHINES CORPORATION

A method for reporting incidents of data loss in a storage environment comprising redundant arrays of independent disks (RAIDs) is disclosed. In one embodiment, such a method monitors storage drive failures in a storage environment. For a storage drive failure detected in the storage environment, the method reports the RAID type in which the storage drive failure occurred and whether data loss occurred in the RAID as a result of the storage drive failure. In certain embodiments, the method reports whether the data loss could have been prevented had the RAID type been converted to a more robust RAID type. In other or the same embodiments, the method reports whether the data loss was prevented by the RAID type. A corresponding system and computer program product are also disclosed. 1. A method for reporting incidents of data loss in a storage environment comprising redundant arrays of independent disks (RAIDs) , the method comprising:monitoring storage drive failures in a storage environment; andfor a storage drive failure detected in the storage environment, reporting the RAID type in which the storage drive failure occurred and whether data loss occurred in the RAID as a result of the storage drive failure.2. The method of claim 1 , wherein reporting further comprises reporting whether the data loss could have been prevented had the RAID type been converted to a more robust RAID type.3. The method of claim 1 , wherein reporting further comprises reporting whether the data loss was prevented by the RAID type.4. The method of claim 1 , wherein reporting further comprises reporting an age of a storage drive associated with the storage drive failure.5. The method of claim 1 , wherein reporting further comprises reporting a number of storage drives that failed in association with the storage drive failure.6. The method of claim 1 , wherein reporting further comprises reporting a type of storage drive that failed in association with the storage drive failure.7. The method ...

Подробнее
Номер записи: 90
17-12-2020 дата публикации

REDUCING INCIDENTS OF DATA LOSS IN RAID ARRAYS OF DIFFERING RAID LEVELS

Номер: US20200394112A1
Автор: Borlick Matthew G., GUPTA Lokesh M., Hardy Clint A., Nielsen Karl A., Rinaldi Brian A.
Принадлежит: INTERNATIONAL BUSINESS MACHINES CORPORATION

A method for reducing incidents of data loss in RAIDs of differing RAID levels is disclosed. Such a method identifies, in a data storage environment, first and second sets of RAIDs. The first set contains RAIDs providing more robust data protection (e.g., RAID-6 arrays), and the second set contains RAIDs providing less robust data protection (e.g., RAID-5 arrays). The method identifies, in the data storage environment, higher risk storage drives having a failure risk above a threshold and lower risk storage drives having a failure risk below the threshold. The method swaps higher risk storage drives from RAIDs of the second set with lower risk storage drives from RAIDs of the first set. In certain embodiments, the swapping may be performed such that no RAID of the second set includes more than a selected number of higher risk storage drives. A corresponding system and computer program product are also disclosed. 1. A method for reducing incidents of data loss in redundant arrays of independent disks (RAIDs) of differing RAID levels , the method comprising:identifying, in a data storage environment, first and second sets of RAIDs, the first set comprising RAIDs providing more robust data protection, and the second set comprising RAIDs providing less robust data protection;identifying, in the data storage environment, higher risk storage drives having a failure risk above a threshold and lower risk storage drives having a failure risk below the threshold; andswapping higher risk storage drives from RAIDs of the second set with lower risk storage drives from RAIDs of the first set in order to reduce a risk of data loss in the data storage environment.2. The method of claim 1 , wherein swapping comprises swapping using a smart rebuild process that enables a storage drive to be used as a spare even as data is being copied to the storage drive.3. The method of claim 1 , wherein swapping comprises swapping such that no RAID of the second set includes more than a selected ...

Подробнее
Номер записи: 91
17-12-2020 дата публикации

REDUCING INCIDENTS OF DATA LOSS IN RAID ARRAYS HAVING THE SAME RAID LEVEL

Номер: US20200394113A1
Автор: Borlick Matthew G., GUPTA Lokesh M., Hardy Clint A., Nielsen Karl A., Rinaldi Brian A.
Принадлежит: INTERNATIONAL BUSINESS MACHINES CORPORATION

A method for reducing incidents of data loss in redundant arrays of independent disks (RAIDs) having the same RAID level is disclosed. In one embodiment, such a method identifies, in a data storage environment, a set of RAIDs having a common RAID level. The method also identifies, in the set of RAIDs, higher risk storage drives having a failure risk above a threshold and lower risk storage drives having a failure risk below the threshold. The method swaps, within the RAIDs, higher risk storage drives with lower risk storage drives to more evenly distribute higher risk storage drives across the RAIDs. A corresponding system and computer program product are also disclosed. 1. A method for reducing incidents of data loss in redundant arrays of independent disks (RAIDs) having the same RAID level , the method comprising:identifying, in a data storage environment, a set of RAIDs having a common RAID level;identifying, in the set of RAIDs, higher risk storage drives having a failure risk above a threshold and lower risk storage drives having a failure risk below the threshold; andswapping, within the RAIDs, higher risk storage drives with lower risk storage drives to more evenly distribute higher risk storage drives across the RAIDs.2. The method of claim 1 , wherein identifying the higher risk storage drives comprises gathering statistics to identify storage drives having a higher risk of failure.3. The method of claim 2 , wherein the statistics include at least one of storage drive age and storage drive type.4. The method of claim 1 , wherein swapping comprises swapping using a smart rebuild process that enables a storage drive to be used as a spare even as data is being copied to the storage drive.5. The method of claim 1 , wherein the failure risk is represented as a percentage chance a storage drive will fail within a specified time period.6. The method of claim 1 , wherein the RAID level is selected from the group consisting of RAID-5 claim 1 , RAID-6 claim 1 , and ...

Подробнее
Номер записи: 92
31-12-2020 дата публикации

DYNAMIC LOGICAL STORAGE CAPACITY ADJUSTMENT FOR STORAGE DRIVES

Номер: US20200409568A1
Автор: Borlick Matthew G., GUPTA Lokesh M., Nielsen Karl A., ROBISON Micah
Принадлежит: INTERNATIONAL BUSINESS MACHINES CORPORATION

A method for dynamically altering logical storage capacity within multiple storage drives is disclosed. In one embodiment, such a method monitors, within a storage environment, characteristics (e.g., age, wear, etc.) of multiple storage drives. Each storage drive has an amount of overprovisioning associated therewith. Based on the characteristics, the method periodically modifies a logical storage capacity of the storage drives in order to alter the amount of overprovisioning. The method then reorganizes the storage drives within various storage groups (e.g., RAID arrays, storage tiers, workloads, etc.) based on their logical storage capacity. For example, the method may place, as much as possible, storage drives of the same logical storage capacity within the same storage groups. A corresponding system and computer program product are also disclosed. 1. A method for dynamically altering logical storage capacity within a plurality of storage drives , the method comprising:monitoring, within a storage environment, characteristics of a plurality of storage drives, each storage drive having an amount of overprovisioning associated therewith; based on the characteristics, modifying a logical storage capacity of the storage drives in order to alter the amount of overprovisioning, wherein modifying the logical storage capacity comprises migrating data out of the storage drives in order to increase the amount of overprovisioning; and', 'reorganizing the storage drives within various storage groups based on the logical storage capacity., 'periodically performing the following2. The method of claim 1 , wherein the storage groups are RAID arrays.3. The method of claim 1 , wherein the storage groups are storage tiers in a tiered storage environment.4. The method of claim 1 , wherein the storage groups are groups of storage drives configured to support a certain I/O workload.5. The method of claim 1 , wherein monitoring characteristics comprises monitoring an age of the storage ...

Подробнее
Номер записи: 93
31-12-2020 дата публикации

DYNAMIC PERFORMANCE-CLASS ADJUSTMENT FOR STORAGE DRIVES

Номер: US20200409590A1
Автор: Borlick Matthew G., GUPTA Lokesh M., Nielsen Karl A., ROBISON Micah
Принадлежит: INTERNATIONAL BUSINESS MACHINES CORPORATION

A method for dynamically altering the performance class of multiple storage drives is disclosed. In one embodiment, such a method monitors, within a storage environment, characteristics (e.g., age, wear, etc.) of multiple storage drives. Each storage drive has a performance class associated therewith. Based on the characteristics, the method periodically modifies the performance class of the storage drives. The method then reorganizes the storage drives within various storage groups (e.g., RAID arrays, storage tiers, workloads, etc.) based on their performance class. For example, the method may place, as much as possible, storage drives of the same performance class within the same storage groups. A corresponding system and computer program product are also disclosed. 1. A method for dynamically altering the performance class of a plurality of storage drives , the method comprising:monitoring, within a storage environment, characteristics of a plurality of storage drives, each storage drive having a performance class associated therewith; identifying selected storage drives of the plurality where an amount of overprovisioning has fallen below a specified level;', 'modifying a logical storage capacity of the selected storage drives to increase the amount of overprovisioning in the selected storage drives, thereby modifying the characteristics of the selected storage drives;', 'based on the characteristics, modifying the performance class of the storage drives; and', 'reorganizing the storage drives within various storage groups based on their performance class., 'periodically performing the following2. The method of claim 1 , wherein the storage groups are RAID (redundant array of inexpensive disks) arrays.3. The method of claim 1 , wherein the storage groups are storage tiers in a tiered storage environment.4. The method of claim 1 , wherein the storage groups are groups of storage drives configured to support a certain I/O workload.5. The method of claim 1 , ...

Подробнее
Номер записи: 94
31-12-2020 дата публикации

Dynamic writes-per-day adjustment for storage drives

Номер: US20200411111A1
Автор: Karl A. Nielsen, Lokesh M. Gupta, Matthew G. Borlick, Micah Robison
Принадлежит: International Business Machines Corp

A method for dynamically altering a writes-per-day classification of multiple storage drives is disclosed. In one embodiment, such a method monitors, within a storage environment, an amount of overprovisioning utilized by multiple storage drives. Each storage drive has a writes-per-day classification associated therewith. Based on the amount of overprovisioning, the method periodically modifies the writes-per-day classification of the storage drives. The method then reorganizes the storage drives within various storage groups (e.g., RAID arrays, storage tiers, workloads, etc.) based on their writes-per-day classification. For example, the method may place, as much as possible, storage drives of the same writes-per-day classification within the same storage groups. A corresponding system and computer program product are also disclosed.

Подробнее
Номер записи: 95
23-02-2021 дата публикации

Converting a RAID to a more robust RAID level

Номер: US10929037B2
Автор: Brian A. Rinaldi, Clint A. Hardy, Karl A. Nielsen, Lokesh M. Gupta, Matthew G. Borlick
Принадлежит: International Business Machines Corp

A method for converting a redundant array of independent disks (RAID) to a more robust RAID level is disclosed. Such a method identifies, in a data storage environment, higher risk storage drives having a failure risk above a first threshold. The method determines a number of the higher risk storage drives that are contained within a RAID array of the data storage environment. The method determines whether the number exceeds a second threshold. The method also determines whether a destage rate associated with the RAID array is below a third threshold. In the event the number exceeds the second threshold and the destage rate is below the third threshold, the method converts the RAID array to a more robust RAID level. A corresponding system and computer program product are also disclosed.

Подробнее
Номер записи: 96
23-06-2020 дата публикации

Concurrent data erasure and replacement of processors

Номер: US10691609B2
Автор: Clint A. Hardy, Karl A. Nielsen, Lokesh M. Gupta, Matthew G. Borlick
Принадлежит: International Business Machines Corp

A method for concurrently erasing data on a processor and preparing the processor for removal from a computing system is disclosed. In one embodiment, such a method includes determining tasks queued to be executed on a processor and reassigning the tasks to a different processor, such as to a different processor in the same cluster as the processor. The method further prevents new tasks from being assigned to the processor. The method waits for currently executing tasks on the processor to complete. Once the currently executing tasks are complete, the method initiates a cache-hostile job on the processor to evict entries in cache of the processor. Once the cache-hostile job is complete, the method enables the processor to be removed from a computing system such as a storage system controller. A corresponding system and computer program product are also disclosed.

Подробнее
Номер записи: 97
06-11-2018 дата публикации

Communications of usernames and passwords to a plurality of cloud storages via a plurality of communications protocols that change over time

Номер: US10122832B2
Автор: Karl A. Nielsen, Lokesh M. Gupta, Matthew G. Borlick, Roger G. Hathorn
Принадлежит: International Business Machines Corp

A computational device has an interface to access a heterogeneous cloud storage comprised of a first cloud storage maintained by a first entity and a second cloud storage maintained by a second entity. The computational device transmits, via a first communications protocol over the interface, a first set of data comprising usernames to a first cloud storage maintained by a first entity. The computational device transmits, via a second communications protocol, a second set of data comprising passwords corresponding to the usernames to a second cloud storage maintained by a second entity. On elapse of a first predetermined amount of time or the first communications protocol being compromised, the first communications protocol is changed to a third communications protocol. On elapse of a second predetermined amount of time or the second communications protocol being compromised, the second communications protocol is changed to a fourth communications protocol.

Подробнее
Номер записи: 98
21-07-2020 дата публикации

Power level management in a data storage system

Номер: US10719118B2
Автор: Bradley Bernhardt, Hans-Joachim Tannenberger, Karl A. Nielsen, Mitchell Montanez, Richard Hutzler, Thomas J. Fleischman, William K. Morse
Принадлежит: International Business Machines Corp

In one embodiment, power level management in accordance with the present description, is provided in a storage unit having both a disk storage drive, and another non-volatile, non-disk memory or storage such as a solid state drive, for storing metadata. The metadata storage provides direct access to the metadata stored in the non-disk storage even though the disk storage drive may be in a low power mode in which the data storage media disk of the disk storage drive is stopped or spinning at a reduced rate of rotation. As a result, power consumption and cooling requirements associated with disk storage drives, may be reduced in a low power level mode of storage unit operation for input/output operations limited to metadata stored in the metadata storage. Other features and aspects may be realized, depending upon the particular application.

Подробнее
Номер записи: 99
22-09-2020 дата публикации

Virtual storage drive management in a data storage system

Номер: US10783049B2
Автор: Karl A. Nielsen, Kevin J. Ash, Lokesh M. Gupta, Matthew G. Borlick
Принадлежит: International Business Machines Corp

In one embodiment, virtual storage drives are allocated to RAID arrays so that no two virtual storage drives of a RAID array are mapped to the same physical storage drive. In another aspect, error handling routines are limited to virtual storage drives impacted by an error in a physical storage drive so that virtual storage drives of the physical storage drive not impacted by the error are bypassed. In yet another aspect, cache operations to a target virtual storage drive may be throttled as a function of both a limit imposed on cache operations directed to the RAID array to which the virtual storage drive is allocated, and a separate limit on cache operations directed to a group of virtual storage drives which are mapped to the same physical storage drive as the target virtual storage drive. Other features and aspects may be realized, depending upon the particular application.

Подробнее
Номер записи: 100
17-02-2015 дата публикации

Populating a first stride of tracks from a first cache to write to a second stride in a second cache

Номер: US8959279B2
Автор: Karl A. Nielsen, Kevin J. Ash, Lokesh M. Gupta, Matthew J. Kalos, Michael T. Benhase
Принадлежит: International Business Machines Corp

Provided are a computer program product, system, and method for managing data in a cache system comprising a first cache, a second cache, and a storage system. A determination is made of tracks stored in the storage system to demote from the first cache. A first stride is formed including the determined tracks to demote. A determination is made of a second stride in the second cache in which to include the tracks in the first stride. The tracks from the first stride are added to the second stride in the second cache. A determination is made of tracks in strides in the second cache to demote from the second cache. The determined tracks to demote from the second cache are demoted.

Подробнее
Номер записи: 101
21-12-2021 дата публикации

Using a machine learning module to determine when to perform error checking of a storage unit

Номер: US11204827B2
Автор: Clint A. Hardy, Karl A. Nielsen, Lokesh M. Gupta, Matthew G. Borlick
Принадлежит: International Business Machines Corp

Provided are a computer program product, system, and method for using a machine learning module to determine when to perform error checking of a storage unit. Input on attributes of at least one storage device comprising the storage unit are provided to a machine learning module to produce an output value. An error check frequency is determined from the output value. A determination is made as to whether the error check frequency indicates to perform an error checking operation with respect to the storage unit. The error checking operation is performed in response to determining that the error checking frequency indicates to perform the error checking operation.

Подробнее
Номер записи: 102
13-01-2015 дата публикации

Promotion of partial data segments in flash cache

Номер: US8935462B2
Автор: Evangelos S. Eleftheriou, Ioannis Koltsidas, Karl A. Nielsen, Lokesh M. Gupta, Matthew J. Kalos, Michael T. Benhase, Robert Haas, Roman A. Pletka, Stephen L. Blinick, Xiao-yu HU
Принадлежит: International Business Machines Corp

For efficient track destage in secondary storage in a more effective manner, for temporal bits employed with sequential bits for controlling the timing for destaging the track in a primary storage, the temporal bits and sequential bits are transferred from the primary storage to the secondary storage. The temporal bits are allowed to age on the secondary storage.

Подробнее
Номер записи: 103
15-04-2021 дата публикации

Migrating data from a large extent pool to a small extent pool

Номер: US20210109670A1
Автор: Clint A. Hardy, HUI Zhang, Karl A. Nielsen, Matthew J. Kalos, Qiang Xie
Принадлежит: International Business Machines Corp

A method according to one embodiment includes identifying a request to migrate data associated with a volume from a source storage pool to a destination storage pool, identifying volume segment table (VST) entries corresponding to rank extents within the source storage pool containing the data, allocating and synchronizing small VSTs for the identified VST entries within the volume, allocating one or more rank extents within the destination storage pool, transferring the data associated with the volume from the rank extents within the source storage pool containing the data to the one or more rank extents in the one or more ranks of the destination storage pool, updating the small VSTs to correspond to the transferred data in the one or more rank extents in the one or more ranks of the destination storage pool, and freeing the data from the one or more rank extents within the source storage pool.

Подробнее
Номер записи: 104
03-11-2022 дата публикации

Migrating data from a large extent pool to a small extent pool

Номер: US20220350519A1
Автор: Clint A. Hardy, HUI Zhang, Karl A. Nielsen, Matthew J. Kalos, Qiang Xie
Принадлежит: International Business Machines Corp

A computer-implemented method according to one embodiment includes identifying a request to migrate data associated with a volume from a first storage pool to a second storage pool; identifying entries in a first table corresponding to rank extents in the first storage pool containing the data; allocating and synchronizing a plurality of second tables for the identified entries of the first table that are located in the volume; transferring the data associated with the volume from the rank extents in the first storage pool containing the data to one or more rank extents in the one or more ranks of the second storage pool; and updating the second tables to correspond to the transferred data in the one or more rank extents in the one or more ranks of the second storage pool.

Подробнее
Номер записи: 105