-
公开(公告)号:GB2579754A
公开(公告)日:2020-07-01
申请号:GB202004608
申请日:2018-08-24
Applicant: IBM
Inventor: LOKESH GUPTA , KEVIN JOHN ASH , KYLER ANDERSON , MATTHEW JOSEPH KALOS
Abstract: A cache hit is generated, in response to receiving an input/output (I/O) command over a bus interface. An update for a metadata track is stored in a buffer associated with a central processing unit (CPU) that processes the I/O command, in response to generating the cache hit. The metadata track is asynchronously updated from the buffer with the stored update for the metadata track in the buffer.
-
公开(公告)号:GB2591424B
公开(公告)日:2021-11-10
申请号:GB202106810
申请日:2019-09-30
Applicant: IBM
Inventor: LOKESH GUPTA , KYLER ANDERSON , KEVIN JOHN ASH , MATTHEW BORLICK
Abstract: A machine learning module receives inputs comprising attributes of a storage controller, where the attributes affect performance parameters for performing stages and destages in the storage controller. In response to an event, the machine learning module generates, via forward propagation, an output value that indicates whether to fill holes in a track of a cache by staging data to the cache prior to destage of the track. A margin of error is calculated based on comparing the generated output value to an expected output value, where the expected output value is generated from an indication of whether it is correct to fill holes in a track of the cache by staging data to the cache prior to destage of the track. An adjustment is made of weights of links that interconnect nodes of the plurality of layers via back propagation to reduce the margin of error.
-
3.
公开(公告)号:GB2587314B
公开(公告)日:2021-09-15
申请号:GB202100441
申请日:2019-06-20
Applicant: IBM
Inventor: MATTHEW BORLICK , KARL ALLEN NIELSEN , CLINT HARDY , LOKESH GUPTA
Abstract: 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.
-
公开(公告)号:GB2584064B
公开(公告)日:2021-04-14
申请号:GB202014835
申请日:2019-02-15
Applicant: IBM
Inventor: MATTHEW BORLICK , LOKESH GUPTA , KEVIN JOHN ASH , KARL ALLEN NIELSEN
Abstract: 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.
-
公开(公告)号:GB2588037A
公开(公告)日:2021-04-14
申请号:GB202019055
申请日:2019-05-13
Applicant: IBM
Inventor: LOKESH GUPTA , MATTHEW BORLICK , KYLER ANDERSON , KEVIN JOHN ASH
IPC: G06F12/00
Abstract: A machine learning module selects one of multiple cache eviction algorithms to use to evict a track from the cache. A first cache eviction algorithm determines tracks to evict from the cache. A second cache eviction algorithm determines tracks to evict from the cache, wherein the first and second cache eviction algorithms use different eviction schemes. At least one machine learning module is executed to produce output indicating one of the first cache eviction algorithm and the second cache eviction algorithm to use to select a track to evict from the cache. A track is evicted that is selected by one of the first and second cache eviction algorithms indicated in the output from the at least one machine learning module.
-
公开(公告)号:GB2585320A
公开(公告)日:2021-01-06
申请号:GB202017405
申请日:2019-04-01
Applicant: IBM
Inventor: LOKESH GUPTA , MATTHEW BORLICK , KEVIN JOHN ASH
IPC: G06F12/0866 , G06F3/06 , G06F12/0895
Abstract: Provided are a computer program product, system, and method for using track locks and stride group locks to manage cache operations. A group of tracks from the storage devices are stored in a cache. Exclusive track locks for tracks in the group in the cache are granted for writes to the tracks in the group in the cache, wherein exclusive track locks can be simultaneously held for writes to different tracks in the cache. An exclusive group lock for the group of tracks in the cache is granted to destage the tracks in the group from the cache to the storage devices. The exclusive group lock is released in response to completing the destage of the tracks in the group in the cache to the storage devices.
-
公开(公告)号:GB2579754B
公开(公告)日:2020-12-02
申请号:GB202004608
申请日:2018-08-24
Applicant: IBM
Inventor: LOKESH GUPTA , KEVIN JOHN ASH , KYLER ANDERSON , MATTHEW JOSEPH KALOS
Abstract: A cache hit is generated, in response to receiving an input/output (I/O) command over a bus interface. An update for a metadata track is stored in a buffer associated with a central processing unit (CPU) that processes the I/O command, in response to generating the cache hit. The metadata track is asynchronously updated from the buffer with the stored update for the metadata track in the buffer.
-
公开(公告)号:GB2586409B
公开(公告)日:2021-07-14
申请号:GB202016053
申请日:2019-03-06
Applicant: IBM
Inventor: LOKESH GUPTA , MATTHEW BORLICK , TRUNG N NGUYEN , MICAH ROBISON
Abstract: Provided are a computer program product, system, and method for injecting trap code in an execution path of a process executing a program to generate a trap address range to detect potential malicious code. A specified type of command is processed in application code and, in response, trap code is executed to allocate a trap address range. The specified type of command is executed in the application code. A determination is made as to whether an accessing application accesses the trap address range. At least one of transmitting a notification that the accessing application comprises potentially malicious code, monitoring the execution of the accessing application, and restricting execution of the accessing application is performed in response to determining that the accessing application accessed the trap address range.
-
公开(公告)号:GB2586409A
公开(公告)日:2021-02-17
申请号:GB202016053
申请日:2019-03-06
Applicant: IBM
Inventor: LOKESH GUPTA , MATTHEW BORLICK , TRUNG N NGUYEN , MICAH ROBISON
Abstract: Provided area computer program product, system, and method for injecting trap code in an execution path of a process executing a program to generate a trap address range to detect potential malicious code. A specified type of command is processed in application code and, in response, trap code is executed to allocate a trap address range. The specified type of command is executed in the application code. A determination is made as to whether an accessing application accesses the trap address range. At least one of transmitting a notification that the accessing application comprises potentially malicious code, monitoring the execution of the accessing application, and restricting execution of the accessing application is performed in response to determining that the accessing application accessed the trap address range.
-
公开(公告)号:GB2586398A
公开(公告)日:2021-02-17
申请号:GB202015329
申请日:2019-02-27
Applicant: IBM
Inventor: LOKESH GUPTA , MATTHEW BORLICK , ROGER HATHORN
IPC: G06F17/00
Abstract: In one aspect of the present description, safe data commit scan operations of individual data storage systems of a distributed data storage system may be synchronized to reduce the occurrence of reductions in input/output (I/O) response times. In one embodiment, a set of safe data commit scan operations of the individual data storage systems of a distributed data storage system are synchronously timed to substantially overlap in time within a single synchronized safe data commit scan set interval to reduce or eliminate the occurrences of reductions in input/output response times outside the synchronized safe data commit scan set interval. Other features and aspects may be realized, depending upon the particular application.
-
-
-
-
-
-
-
-
-