Computing system, host system and method for managing data

• US 9,489,388 B2
• Filed: 09/27/2013
• Issued: 11/08/2016
• Est. Priority Date: 09/28/2012
• Status: Active Grant

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: Lee, Chang-Man, Kim, Jae-Geuk, Lee, Chul, Hwang, Joo-Young
• Primary Examiner(s): Ruiz, Angelica
• Application Number:
  US14/038,938
• Publication Number:
  US 20140095556A1
• Time in Patent Office: 1,138 Days
• Field of Search: 707600-831, 707/899, 707999001-999206
• US Class Current: 1/1
• CPC Class Codes: G06F 16/13 File access structures, e.g. distributed indices arrangements of input from, or output to, record carriers G06F3/06

Abstract

A computing system includes a storage device in which file data is stored through data blocks and metadata is stored through a node block, and a file system configured to manage the file data and the metadata stored in the storage device. The node block includes data pointers respectively pointing to the data blocks, and one or more extents each indicative of data block groups which include data blocks having continuous physical addresses among the data blocks.

Claims

1. A computing system comprising:

a storage device in which file data is stored through data blocks and metadata is stored through node blocks; and

a file system configured to manage the file data and the metadata stored in the storage device,

wherein the node blocks include data pointers respectively pointing to the data blocks, and one or more extents each indicative of data block groups which include data blocks having continuous physical addresses among the data blocks, and

wherein a number of extents included in the node blocks is a predetermined number N that is less than or equal to half of a number of the data pointers.

2. The computing system of claim 1, wherein each of the one or more extents includes offset information indicative of a first block of a corresponding data block group among the data blocks of the file data, a block pointer pointing to the corresponding data block group, and length information of the corresponding data block group.

3. The computing system of claim 1, wherein the node blocks include direct node blocks pointing to the data blocks, indirect node blocks pointing to the direct node blocks, and an inode block pointing to the direct node blocks and the indirect node blocks, and

wherein the one or more extents are included in the inode block or the direct node blocks.

4. The computing system of claim 1, wherein when the file data is read from the storage device, the file system reads the file data by referencing the one or more extents first among the data pointers and the one or more extents.

5. The computing system of claim 1, wherein the storage device includes a first area written by a random access method, and a second area written by a sequential access method, and

wherein the data blocks and the node blocks are stored in the second area.

6. The computing system of claim 5, wherein in the storage device, a physical address of the first area precedes a physical address of the second area.

7. The computing system of claim 5, wherein a node address table is stored in the first area, the node address table including a node identifier corresponding to the node blocks and a physical address corresponding to the node identifier.

8. The computing system of claim 1, wherein the storage device includes a solid state drive (SSD).

9. The computing system of claim 1, wherein the storage device includes a memory controller and a non-volatile memory, and wherein the file system is contained in a host device communicating with the memory controller.

10. The computing system of claim 9, wherein the non-volatile memory includes a plurality of memory chips communicating with the memory controller over respective channels.

11. A host device, comprising:

a storage interface configured to communicate with a storage device; and

a file system configured to control the storage device, via the storage interface, to store a file data through data blocks in the storage device and to store metadata through node blocks in the storage device,

wherein the node blocks include data pointers respectively pointing to the data blocks, and one or more extents each indicative of data block groups which include data blocks having continuous physical addresses among the data blocks,

wherein the file system is further configured to read the file data by referencing the one or more extents first among the data pointers and the one or more extents, and

wherein a number of extents included in the node blocks is a predetermined number N or less, where N is a natural number smaller than a number of the data pointers.

12. The host device of claim 11, wherein each of the one or more extents includes offset information indicative of a first block of a corresponding data block group among the data blocks of the file data, a block pointer pointing to the corresponding data block group, and length information of the corresponding data block group.

13. A method for managing data in a computing system, the method comprising:

creating data blocks storing a file data; and

creating a node block including data pointers respectively pointing to the data blocks, and one or more extents each indicative of data block groups which include data blocks having continuous physical addresses among the data blocks,

wherein a number of extents included in the node block is maintained to be a predetermined number N or less, where N is a natural number smaller than or equal to half of a the number of the data pointers.

14. The method of claim 13, wherein the creating of the one or more extents comprises, when a first data block among the data blocks has physical addresses arranged to be continuous to a second data block among the data blocks, allowing the one or more extents included in the node block and pointing to the second data block to group and point to the first data block and the second data block.

15. The method of claim 13, wherein the creating of the one or more extents comprises, when a first data block among the data blocks has physical addresses discontinuous to a second data block among the data blocks and the second data block has physical addresses arranged to be continuous to a third data block among the data blocks, merging a first extent included in the node block and pointing to the second data block with a second extent included in the node block and pointing to the third data block;

and

newly creating an extent pointing to the first data block.

16. The method of claim 13, wherein the creating of the one or more extents comprises, when a first data block among the data blocks has physical addresses discontinuous to a second data block among the data blocks and the second data block has physical addresses discontinuous to a third data block among the data blocks, removing one of a first extent and a second extent, the first extent included in the node block and pointing to the second data block and the second extent included in the node block and pointing to the third data block;

and

newly creating an extent pointing out the first data block.