Key-Value data storage system

Patent metadata

Field	Value
Publication number	US-9659048-B2
Application number	US-201414491337-A
Country	US
Kind code	B2
Filing date	Sep 19, 2014
Priority date	Nov 6, 2013
Publication date	May 23, 2017
Grant date	May 23, 2017

Abstract

According to an aspect, a key-value store (KVS) system includes a data management unit that stores a data KVS storing a pair of a data KVS key including information on a storage location of application data to be an access target object and the application data; and a key KVS storing a pair of an application key and the data KVS key. The data KVS includes a normal partition in which a size of a record for storing one pair is a predetermined specific size; and a special partition in which the size of the record for storing one pair is a size set according to a data size of the pair to be stored. A data relocation unit relocates a pair of a relocation target object to the special partition having the record size suitable for the data size of the pair.

First claim

What is claimed is:

1. A system of managing data, comprising:
a memory having computer readable instructions; and
a processor for executing the computer readable instructions, the computer readable instructions including instructions for:
storing and managing a set of data and a key uniquely associated with the data; and
an access management unit for receiving an access request for accessing the data associated with the key, the access request being made by specifying the key,
wherein the data management unit includes:
a first storage unit storing a set of data and a first key, the first key serving as a key uniquely associated with the data, the first key including information on a storage location of the data to be accessed,
a second storage unit storing a set of the first key and a second key, the first key serving as data, the second key serving as a key uniquely associated with the first key, the second key being specified in the access request when accessing the data associated with the first key,
a relocation unit for relocating the set of the data and the first key in the first storage unit in a different area of the first storage unit, when a predetermined execution condition is satisfied,
the first storage unit includes:
a first area where a size of a record for storing one of the sets of the data and the first key is a predetermined specific size, and
a second area where the size of the record for storing one of the sets of the data and the first key is a size set according to the data size of the set, and
the relocation unit relocates the set of the data and the first key, which is a relocation target object, in the second area having the record size suitable for the data size of the set.

2. The system according to claim 1 , wherein, when there is no second area having the record size suitable for the data size of the set of the data and the first key to be relocated, the relocation unit adds the second area having the record size and stores the set in the record in the added second area.

3. The system according to claim 1 , wherein, when, as the execution condition, the data size of the set among the sets of the data and the key stored in the first area or the second area of the first storage unit is larger than a threshold determined for the first area or the second area in which the set is stored, the relocation unit relocates the set in another second area.

4. The system according to claim 1 , wherein, when, as the execution condition, a degree of collisions of a hash value identifying the storage location of the set of the data and the key in the first area of the first storage unit is greater than a predetermined threshold, the relocation unit relocates the set in the second area.

5. The system according to claim 1 , further comprising
a storage control unit for acquiring the data and the second key that are new on the basis of the access request, specifying the storage location of the data in the first area of the first storage unit, generating the first key including the information on the storage location, storing the set of the first key and the data at the specified storage location, creating the set of the acquired second key and the created first key, and storing the set in the second storage unit.

6. The system according to claim 5 , wherein, when the set of the data and the first key is relocated, the relocation unit updates the first key by replacing the information on the storage location of the set, which is included in the first key, with the information on the storage location after relocation, and replaces the first key in the set of the second key and the first key associated with the relocated data, which is stored in the second storage unit, with contents updated on the basis of the storage location after the relocation.

Assignees

• IBM

Inventors

• Ding Jie
• Shiomi Tatsuyuki
• Yaegashi Yoshiko
• Yoshifuji Nobuyuki

Classifications

• G06F17/30628

  Physics · mapped topic

• G06F17/30587

  Physics · mapped topic

• G06F17/30336 Primary

  Physics · mapped topic

• G06F16/28 Primary

  Databases characterised by their database models, e.g. relational or object models · CPC title

• G06F16/2255 Primary

  Hash tables · CPC title