Method, device, and computer program product for managing storage system

Patent metadata

Field	Value
Publication number	US-2021405904-A1
Application number	US-202017005215-A
Country	US
Kind code	A1
Filing date	Aug 27, 2020
Priority date	Jun 29, 2020
Publication date	Dec 30, 2021
Grant date	—

Abstract

To manage a storage system, data objects are divided to groups according to keyword ranges of the data objects in the storage system. Array sets associated with the groups are respectively generated. An array in the array set includes elements. The elements are set according to a keyword of at least one data object in the group and at least one hash function. At least a part of the arrays in the array sets respectively associated with the groups is loaded into a memory of the storage system. The storage system is managed based on at least the part of the arrays in the memory. Further, a corresponding device and a corresponding computer program product are provided. With the above example implementation, only a part of the arrays is loaded into the memory of the storage system, so that the overhead of memory resources can be reduced.

First claim

1 . A method, comprising:
dividing, by a system comprising a processor, a plurality of data objects to a plurality of groups according to keyword ranges of the plurality of data objects in a storage system; generating array sets associated with groups in the plurality of groups respectively, an array in the array set comprising a plurality of elements, the plurality of elements being set according to a keyword of at least one data object in the group and at least one hash function; loading at least a part of the arrays in the plurality of array sets respectively associated with the plurality of groups into a memory of the storage system; and managing the storage system based on at least the part of the arrays in the memory.

2 . The method according to claim 1 , wherein dividing the plurality of data objects to the plurality of groups comprises:
acquiring indexes corresponding to the plurality of data objects in the storage system; and dividing the plurality of data objects to the plurality of groups based on a hierarchical structure of the indexes.

3 . The method according to claim 1 , wherein loading at least the part of the arrays in the plurality of array sets respectively associated with the plurality of groups into the memory of the storage system comprises: for a given group in the plurality of groups,
determining an access popularity of the at least one data object in the given group; and loading at least a part of the arrays in the array set associated with the given group into the memory based on the access popularity.

4 . The method according to claim 3 , further comprising:
determining numbers of loaded arrays of the plurality of groups respectively based on numbers of arrays loaded into the memory and associated with the plurality of groups; and mapping the plurality of groups to a plurality of queues based on the numbers of loaded arrays of the plurality of groups, the number of loaded arrays of each group in a given queue in the plurality of queues being the same.

5 . The method according to claim 4 , further comprising: sorting, according to a time sequence in which data objects in at least one group in the given queue are accessed, the at least one group in the given queue.

6 . The method according to claim 4 , further comprising at least any one of:
removing the arrays associated with the given group from the memory upon determining that a time period during which data objects in the given group are not accessed exceeds a threshold expiration time; and loading the unloaded arrays associated with the given group into the memory upon determining that the access popularity of the at least one data object in the given group is higher than a threshold popularity.

7 . The method according to claim 6 , further comprising:
moving the given group to another queue corresponding to the changed number upon determining that the number of loaded queues of the given group is changed.

8 . The method according to claim 1 , wherein managing the storage system based on at least the part of the arrays in the memory comprises:
determining, upon determining that a search request to search for a target data object from the storage system is received, a target group corresponding to the target data object in the plurality of groups based on a keyword range of the target data object; determining a plurality of target elements corresponding to the target data object based on the at least one hash function; determining, in response to the determination that the plurality of target elements match at least a part of the arrays in the target group and loaded into the memory, that the storage system comprises the target data object; and determining, in response to the determination that the plurality of target elements do not match at least the part of the arrays in the target group and loaded into the memory, that the storage system does not comprise the target data object.

9 . The method according to claim 1 , wherein managing the storage system based on at least a part of the arrays in the memory comprises:
determining, upon determining that a storage request to store a target data object into the storage system is received, a target group corresponding to the target data object in the plurality of groups based on a keyword range of the target data object; determining a plurality of target elements corresponding to the target data object based on the at least one hash function; and updating the array set of the target group based on the plurality of target elements.

10 . The method according to claim 1 , wherein the array is represented by a bloom filter, and the method further comprises:
determining an original length of an original bloom filter associated with the storage system; and determining a length and a number of the plurality of arrays based on the original length and the number of groups.

11 . An electronic device, comprising:
at least one processor; a volatile memory; and a memory coupled to the at least one processor and having instructions stored therein, wherein the instructions, when executed by the at least one processor, cause the device to perform operations, comprising: dividing a plurality of data objects to a plurality of groups according to keyword ranges of the plurality of data objects in the storage system; generating array sets associated with groups in the plurality of groups respectively, an array in the array set comprising a plurality of elements, and the plurality of elements being set according to a keyword of at least one data object in the group and at least one hash function; loading at least a part of the arrays in the plurality of array sets respectively associated with the plurality of groups into a memory of the storage system; and managing the storage system based on at least a part of the arrays in the memory.

12 . The device according to claim 11 , wherein dividing the plurality of data objects to the plurality of groups comprises:
acquiring indexes corresponding to the plurality of data objects in the storage system; and dividing the plurality of data objects to the plurality of groups based on a hierarchical structure of the indexes.

13 . The device according to claim 11 , wherein loading at least the part of the arrays in the plurality of array sets respectively associated with the plurality of groups into the memory of the storage system comprises: for a given group in the plurality of groups,
determining an access popularity of the at least one data object in the given group; and loading at least the part of the arrays in the array set associated with the given group into the memory based on the access popularity.

14 . The device according to claim 13 , wherein the operations further comprise:
determining numbers of loaded arrays of the plurality of groups respectively based on numbers of arrays loaded into the memory and associated with the plurality of groups; and mapping the plurality of groups to a plurality of queues based on the numbers of loaded arrays of the plurality of groups, the number of loaded arrays of each group in a given queue in the plurality of queues being the same.

15 . The device according to claim 14 , wherein the operations further comprise: sorting, according to a time sequence in which data objects in at least one group in the given queue are accessed, the at least one group in the given queue.

16 . The device according to claim 14 , wherein the operations further comprise at least any one of:
removing the arrays associated with the given group from the memory upon

Assignees

• Emc Ip Holding Co Llc

Inventors

• Zhang Alex Pengbo
• Chen You

Classifications

• G06F16/901

  Indexing; Data structures therefor; Storage structures (for retrieval from the web G06F16/951) · CPC title

• G06F3/0608 Primary

  Saving storage space on storage systems · CPC title

• G06F3/0659

  Command handling arrangements, e.g. command buffers, queues, command scheduling · CPC title

• G06F3/0689 Primary

  Disk arrays, e.g. RAID, JBOD · CPC title

• G06F3/064

  Management of blocks · CPC title