IP Library Granted Patent US 8,655,931
Granted Patent B2
US 8,655,931 · App. 13/493,701 · Granted Feb 18, 2014

Media aware distributed data layout

Inventor: Michael L. Kazar (Pittsburgh, PA)
Assignee: Avere Systems, Inc.
G06F12/1036G06F12/109G06F12/145Y10S707/956
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 8,655,931
App. No.
13/493,701
Granted
Feb 18, 2014
Kind
B2
Abstract

A storage system includes a plurality of vdisks, with each vdisk containing a plurality of storage segments, and each segment providing a specific class of service (CoS) for storage. Each vdisk stores files with data and meta data distributed among its storage segments. A storage system includes a memory having multiple classes of service. The system includes an interface for storing a file as blocks of data associated with a class of service in the memory. The interface chooses the class of service for a block on a block by block basis for storage. A file system for storing a file. A file system for storing includes a plurality of vdisks. A method for storing a file.

Claims (45)

1. A storage system comprising:

an interface for receiving files;

a plurality of processors; and

a memory having a plurality of vdisks with each vdisk served by one of the plurality of processors, and with at least two vdisks served by different processors, with each vdisk storing one or more directories, each vdisk containing a plurality of storage segments, each segment providing a specific class of service (CoS) for storage different from the CoS for storage of the other segments with a desired different CoS for portions of a file, each vdisk storing one or more files with data and meta data distributed among its storage segments, each file's meta data including a search tree indexed by logical block number, each file described by a single inode, a directory updating operation requires at least two vdisks and at least two processors.

2. A storage system as described in claim 1 , wherein at least one file's data is stored in one segment, and at least one other file's data is stored in a second segment.

3. A storage system as described in claim 2 , including a plurality of vdisks, and where a vdisk to hold a newly created file or directory is chosen from the plurality of vdisks based on a predetermined mapping into the plurality of vdisks.

4. A storage system as described in claim 3 , where the predetermined mapping is a round robin assignment algorithm.

5. A storage system as described in claim 3 , where the predetermined mapping chooses the vdisk with a largest available space, or a largest percentage of available space.

6. A storage system as described in claim 3 , including a plurality of processors and wherein the predetermined mapping chooses the vdisk served by a least loaded processor.

7. A storage system as described in claim 2 , wherein each vdisk contains an arbitrary collection of directories and files, and at least two vdisks hold at least one file.

8. A storage system as described in claim 2 , wherein each vdisk contains meta data disk block pointers only to blocks within the same vdisk.

9. A storage system as described in claim 8 , including an interface to initiate a file system consistency check on an individual vdisk, triggered by an indication of an inconsistency in a specific vdisk.

10. A storage system as described in claim 1 where at least one file stores at least one block in a segment with one CoS, and at least one other block in a segment with a second CoS.

11. A storage system as described in claim 10 where a persistent operations table implements directory modifying operations atomically.

12. A storage system as described in claim 3 , wherein a first portion of a file's data is stored in a first segment, and a second portion of the file is stored in either the first segment or a second segment.

13. A storage system as described in claim 12 wherein a vdisk to hold a newly created file or directory is chosen from the plurality of vdisks based on a predetermined mapping into the plurality of vdisks.

14. A storage system as described in claim 13 , where the predetermined mapping is a round robin assignment algorithm.

15. A storage system as described in claim 13 , where the predetermined mapping chooses the vdisk with a largest available space, or a largest percentage of available space.

16. A storage system as described in claim 13 , wherein the predetermined mapping chooses the vdisk served by a least loaded processor.

17. A system as described in claim 13 wherein each segment consists of a plurality of chunks.

18. A storage system as described in claim 12 , wherein each vdisk contains an arbitrary collection of directories and files, and at least two vdisks hold at least one file.

19. A storage system as described in claim 12 , wherein each vdisk contains meta data disk block pointers only to blocks within a same vdisk.

20. A storage system as described in claim 19 , including an interface to initiate a file system consistency check on an individual vdisk, triggered by an indication of an inconsistency in a specific vdisk.

21. A storage system as described in claim 12 , wherein each vdisk is an arbitrary collection of directories and files, and at least one file is stored in at least two segments.

22. A method for storing a file comprising the steps of:

receiving the file at an interface;

storing a first portion of the file in a first segment of a memory in communication with the interface and a second portion of the file in a second segment of the memory having a different class of service for storage than the first segment's class of service, with a desired different class of service for portions of the file, the memory having a plurality of vdisks with each vdisk served by one of the plurality of processors, and with at least two vdisks served by different processors;

retrieving the file by reading the first portion and the second portion from the first and second segment, respectively, each file's meta data including a search tree indexed by logical block number, each file described by a single inode; and

updating a directory using at least two vdisks and at least two processors.

23. A storage system comprising:

an interface for receiving files;

a plurality of processors; and

a memory having a plurality of vdisks with each vdisk served by one of the plurality of processors, and with at least two vdisks served by different processors, each vdisk storing one or more directories, each vdisk containing a plurality of storage segments, each segment providing a specific class of service (CoS) for storage different from the CoS for storage of the other segments, with a desired different CoS for portions of a file, each vdisk storing one or more files with data and meta data distributed among its storage segments and a persistent operations table that implements directory modifying operations atomically, the meta data in at least one segment describes file data stored in any other segment, each file described by a single inode, a directory updating operation requires at least two vdisks and at least two processors.

24. A storage system comprising:

an interface for receiving files;

a plurality of processors; and

a memory having a plurality of vdisks with each vdisk served by one of the plurality of processors, and with at least two vdisks served by different processors, each vdisk storing one or more directories, each vdisk containing a plurality of storage segments, each segment providing a specific class of service (CoS) for storage different from the CoS for storage of the other segments, with a desired different CoS for portions of a file, each vdisk storing one or more files with data and meta data distributed among its storage segments, each segment having disk blocks, the disk blocks being allocated to files and being marked as in use by a corresponding bit being set in the bitmap allocation table, indexed by physical block address, each file described by a single inode, a directory updating operation requires at least two vdisks and at least two processors.

25. A storage system comprising:

an interface for receiving files;

a plurality of processors; and

a memory having a plurality of vdisks with each vdisk served by one of the plurality of processors, and with at least two vdisks served by different processors, each vdisk containing a plurality of storage segments, each segment providing a specific class of service (CoS) for storage different from the CoS for storage of the other segments, with a desired different CoS for portions of a file, each vdisk storing one or more files with data and meta data distributed among its storage segments, each file's meta data including a search tree indexed by logical block number, each file described by a single inode, a first portion of a file's data is stored in a first segment, and a second portion of the file is stored in either the first segment or a second segment, wherein a vdisk to hold a newly created file or directory is chosen from the plurality of vdisks based on a predetermined mapping into the plurality of vdisks, the predetermined mapping is a round robin assignment algorithm, a directory updating operation requires at least two vdisks and at least two processors.

26. A storage system comprising:

an interface for receiving files;

a plurality of processors; and

a memory having a plurality of vdisks with each vdisk served by one of the plurality of processors, and with at least two vdisks served by different processors, each vdisk containing a plurality of storage segments, each segment providing a specific class of service (CoS) for storage different from the CoS for storage of the other segments, with a desired different CoS for portions of a file, each vdisk storing one or more files with data and meta data distributed among its storage segments, each file's meta data including a search tree indexed by logical block number, each file described by a single inode, at least one file's data is stored in one segment, and at least one other file's data is stored in a second segment, a plurality of vdisks, and where a vdisk to hold a newly created file or directory is chosen from the plurality of vdisks based on a predetermined mapping into the plurality of vdisks, the predetermined mapping is a round robin assignment algorithm, a directory updating operation requires at least two vdisks and at least two processors.

Assignments (3)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jul 31, 2020
From: AVERE SYSTEMS, INC.
To: MICROSOFT TECHNOLOGY LICENSING, LLC
Reel/Frame 053373/0574 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Mar 8, 2018
From: KAZAR, MICHAEL L.
To: ARRIAD, INC.
Reel/Frame 045141/0856 →
CHANGE OF NAME Recorded Mar 8, 2018
From: ARRIAD, INC.
To: AVERE SYSTEMS, INC.
Reel/Frame 045529/0384 →
Continuity (2)
Continuation 12218085 · Jul 11, 2008
Related Publication 20120271858A1 · Oct 25, 2012