Low-cost backup and edge caching using unused disk blocks

Patent metadata

Field	Value
Publication number	US-9645950-B2
Application number	US-201313756454-A
Country	US
Kind code	B2
Filing date	Jan 31, 2013
Priority date	Jan 31, 2013
Publication date	May 9, 2017
Grant date	May 9, 2017

Abstract

A designated storage system receives a request to store data in the local storage as a backup copy. The designated storage system requests a file system in the computer system to store the backup copy as a file in the local storage and maintains a record describing storage locations for each of the one or more sets of contiguous available file system data blocks. The storage system may transmit the record to a management computer configured to track which of the computer systems has stored the backup copy. The storage system then requests the file system to delete the file, whereupon the file system removes the file descriptor and frees the one or more file system data blocks in order to satisfy the deletion request but does not delete the data stored in the one or more file system data blocks.

First claim

What is claimed is:

1. A distributed computing system configured to maintain backup copies of data, the distributed computing system comprising a data source computer system communicatively coupled to a plurality of storage computer systems, each computer system comprising a physical processor and a local storage, the processor of the data source computer system configured by software to perform the steps of:
providing a backup copy of the data to a set of two or more storage systems that have available local storage to store the backup copy wherein, in response, the processor of each of the storage system in the set is configured to perform the following steps:
receiving the backup copy of the data from the data source computer;
storing the backup copy as a file in the local storage using a file system, wherein the file system stores the backup copy in one or more sets of available file system data blocks and generates a file descriptor that tracks the one or more sets of file system data blocks used to store the backup copy;
providing, to the data source computer system, a block location record describing storage locations of the one or more sets of file system data blocks in the local storage corresponding to the data of the file, wherein the block location record is different from the file descriptor;
deleting the file using the file system, whereupon, in response, the file system deletes the file by removing the file descriptor without deleting the contents of the corresponding data blocks;
receiving, at the storage system, a request from the data source computer to provide the contents of the deleted file having the deleted file descriptor, wherein the request from the data source computer includes information included in the block location record identifying the data blocks in the local storage of the storage system that correspond to the data of the file;
retrieving the contents of the data blocks for the deleted file identified in the request using the information included in the block location record; and
transmitting the contents of the data blocks to the data source computer.

2. The distributed computing system of claim 1 , wherein each of the storage computer systems performs alternative but primary activities unrelated to storing the data as the backup copy.

3. The distributed computer system of claim 1 , wherein the data source computer system is further configured to transmit the block location record to a management computer configured to track which of the storage computer systems has stored the backup copy.

4. The distributed computing system of claim 3 , wherein each of the set of storage computer systems is further configured to perform the steps of:
receiving from the management computer a request to retrieve the backup copy, wherein the request includes the block location record and a first hash value derived from the backup copy;
calculating a second hash value derived from the data blocks of the deleted file; and
comparing the first hash value to the second hash value to determine whether the data blocks of the deleted file matches the backup copy.

5. The distributed computer system of claim 4 , wherein each of the set of storage computer systems is further configured to perform the steps of (1) providing the data blocks of the deleted file to the management computer if the first hash value matches the second hash value, and (2) transmitting a notification to the management computer that the data blocks of the deleted file does not match the backup copy if the hash value does not match the second hash value.

6. The computer system of claim 1 , wherein the management computer stores a mapping of an identification of the backup copy to the block location record to an identification of the computer system storing the backup copy in the one or more file system data blocks.

7. The distributed computer system of claim 1 , wherein the backup copy is encrypted prior to requesting the file system to store the backup copy as a file in the local storage.

8. The distributed computer system of claim 1 , wherein providing a backup copy of the data the set of storage systems includes providing a backup copy of the data to each storage system of the set such that each storage system of the set has a corresponding backup copy of the data.

9. A method for managing backup copies of data in a distributed computer system comprising:
providing a backup copy of the data from a data source computer, comprising a physical processor and a local storage, to a set of two or more storage systems that have available local storage to store the backup copy wherein, in response, each storage system in the set performs the following steps:
receiving the backup copy of the data from the data source computer;
storing the backup copy as a file in the local storage using a file system, wherein the file system stores the backup copy in one or more sets of available file system data blocks and generates a file descriptor that tracks the one or more sets of file system data blocks used to store the backup copy;
providing, to the data source computer system, a block location record describing storage locations of the one or more sets of file system data blocks in the local storage corresponding to the data of the file, wherein the block location record is different from the file descriptor;
deleting the file using the file system, whereupon, in response, the file system deletes the file by removing the file descriptor and indicating the one or more file system data blocks as free in order to satisfy the deletion request without deleting the contents of the corresponding data blocks;
receiving, at the storage system, a request from the data source computer to provide the contents of the deleted file having the deleted file descriptor, wherein the request from the data source computer includes information included in the block location record identifying the data blocks in the local storage of the storage system that correspond to the data of the file;
retrieving the contents of the data blocks for the deleted file identified in the request using the information included in the block location record; and
transmitting the contents of the data blocks to the data source computer.

10. The method of claim 9 , wherein the data source computer system transmits the block location record to a management computer configured to track which of the storage computer systems has stored the backup copy.

11. The method of claim 10 , wherein each storage system in the set further performs the steps of:
receiving from the management computer a request to retrieve the backup copy, wherein the request includes the block location record and a first hash value derived from the backup copy;
calculating a second hash value derived from the data blocks of the deleted file; and
comparing the first hash value to the second hash value to determine whether the data blocks of the deleted file matches the backup copy.

12. The method of claim 11 , wherein each storage system in the set further performs the steps of (1) providing the data blocks of the deleted file to the management computer if the first hash value matches the second hash value, and (2) transmitting a notification to the management computer that the data blocks of the deleted file does not match the backup copy if the first hash value does not match the second hash value.

13. The method of claim 9 , wherein the management computer stores a mapping of an identification of the backup copy to the block location record an identification of the storage computer system.

14. The method of claim 9 , wherein the

Assignees

• Clark Jonathan
• Vmware Inc

Inventors

• Clark Jonathan

Classifications

• G06F11/1464

  for networked environments · CPC title

• G06F3/0619

  in relation to data integrity, e.g. data losses, bit errors · CPC title

• G06F3/067

  Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS] · CPC title

• G06F12/1408

  by using cryptography (for digital transmission H04L9/00) · CPC title

• G06F12/0864

  using pseudo-associative means, e.g. set-associative or hashing · CPC title