Leveraging NAS protocol for efficient file transfer

Patent metadata

Field	Value
Publication number	US-11153385-B2
Application number	US-201916547768-A
Country	US
Kind code	B2
Filing date	Aug 22, 2019
Priority date	Aug 22, 2019
Publication date	Oct 19, 2021
Grant date	Oct 19, 2021

Abstract

A technique for transferring data over a network leverages a standard NAS (Network Attached Storage) protocol to augment its inherent file-copying ability with fingerprint matching, enabling the NAS protocol to limit its data copying over the network to unique data segments while avoiding copying of redundant data segments.

First claim

What is claimed is:

1. A method of transferring data between computing machines over a network, the method comprising:
in response to a first computing machine receiving a request to transfer file data to a second computing machine, sending, via a NAS (Network Attached Storage) protocol configured to perform fingerprint-enabled data transfer, a first transmission to the second computing machine over the network, the first transmission including multiple fingerprints that identify respective data segments of the file data;
receiving, via the NAS protocol responsive to fingerprint matching performed by commands of the NAS protocol, reply data from the second computing machine, the reply data specifying missing data segments, the missing data segments being data segments, identified by the fingerprints in the first transmission, which are unavailable on the second computing machine; and
in response to receiving the reply data, sending, via the NAS protocol, a second transmission to the second computing machine, the second transmission providing the missing data segments to the second computing machine,
wherein the file data includes data for a particular file on the second computing machine, wherein the NAS protocol supports extended attributes of files, wherein sending the first transmission includes providing the fingerprints as at least a first extended attribute associated with the particular file using at least one SET XATTR command, and wherein receiving the reply data is responsive to sending at least one GET XATTR command to the second computing machine.

2. The method of claim 1 , wherein the first computing machine operates as a NAS client and the second computing machine operates as a NAS server.

3. The method of claim 2 , wherein the NAS protocol is one of NFS (Network File System) and CIFS (Common Internet File System).

4. The method of claim 3 , wherein the NAS protocol is NFSv4 or greater.

5. The method of claim 3 , wherein the NAS protocol supports RPC (Remote Procedure Call), and wherein sending the first transmission includes providing the fingerprints in at least one RPC command.

6. The method of claim 3 , further comprising generating the fingerprints as cryptographically secure hashes of the respective data segments of the file data, wherein generating the fingerprints is performed prior to receiving the request to transfer the file data and as part of a deduplication facility operating on the first computing machine.

7. The method of claim 3 , further comprising generating the fingerprints as cryptographically secure hashes of the respective data segments of the file data, wherein generating the fingerprints includes generating at least some of the fingerprints in response to receiving the request to transfer the file data.

8. The method of claim 3 , further comprising generating the fingerprints by the first computing machine as non-cryptographically secure identifiers according to a predetermined methodology shared between the first computing machine and the second computing machine.

9. The method of claim 3 , wherein the method further comprises compressing the missing data segments prior to sending the second transmission.

10. The method of claim 1 , further comprising, prior to receiving the reply data, sending a command to the second computing machine requesting at least a second extended attribute associated with the particular file.

11. A computer program product, including a set of non-transitory, computer-readable media having instructions which, when executed by a controller of a computerized apparatus, cause the computerized apparatus to perform a method of transferring data over a network, the method comprising:
operating a NAS (Network Attached Storage) server configured to share or export files over the network;
receiving, via a NAS protocol of the NAS server, a first transmission from a computing machine that operates a NAS client, the first transmission including multiple fingerprints that identify respective data segments of file data, the NAS protocol configured to perform fingerprint-enabled data transfer;
transmitting, via the NAS protocol responsive to fingerprint matching performed by commands of the NAS protocol, reply data to the computing machine, the reply data specifying missing data segments, the missing data segments being data segments, identified by the fingerprints in the first transmission, which are unavailable on the computerized apparatus; and
after transmitting the reply data, receiving, via the NAS protocol, a second transmission from the computing machine, the second transmission providing the missing data segments,
wherein the file data includes data of a particular file, wherein the NAS protocol is NFSv4 or greater and supports extended attributes of files, and wherein the method further comprises, in response to receiving the first transmission, storing the fingerprints in at least a first extended attribute of the particular file, wherein the first transmission is received as part of at least one SET XATTR command, and wherein the reply data is transmitted in response to at least one GET XATTR command.

12. The computer program product of claim 11 , wherein the method further comprises:
generating a list of missing fingerprints as fingerprints received in the first transmission that do not match any local fingerprints generated for data segments stored in the computerized apparatus,
wherein transmitting the reply data includes providing indicators of data segments identified by the list of missing fingerprints.

13. The computer program product of claim 12 , wherein the method further comprises performing a handshaking procedure with the NAS client during a mount or map operation, the handshaking procedure establishing attributes to be used in supporting fingerprint-enabled data transfer between the NAS client and the NAS server.

14. The computer program product of claim 12 , wherein the computerized apparatus employs a deduplication facility, and wherein the method further comprises, after receiving the first transmission that includes the fingerprints:
identifying a plurality of found fingerprints as fingerprints received in the first transmission that match fingerprints generated for data segments stored in the computerized apparatus; and
for each of the plurality of found fingerprints, storing the respective data segment by configuring pointer metadata and without persistently storing a new copy of the respective data segment.

15. The computer program product of claim 12 , wherein the computerized apparatus supports multiple tenants, wherein the computing machine belongs to a particular tenant, and wherein, when generating the list of missing fingerprints, the method comprises limiting a scope of fingerprints searched to a plurality of fingerprints specific to the particular tenant.

16. A computerized system, comprising a first computing machine operatively connected to a second computing machine over a network, the computerized system constructed and arranged to:
receive, by the first computing machine, a request to transfer file data to the second computing machine,
send, by the first computing machine via a NAS (Network Attached Storage) protocol configured to perform fingerprint-enabled data transfer, a first transmission to the second computing machine, the first transmission including multiple fingerprints that identify respective data segments of the file data;
transmit, by the second computing machine via the NAS protocol responsive to fingerprint matching performed by commands of the NAS protocol, reply data to the first

Assignees

• Emc Ip Holding Co Llc

Inventors

• Faibish Sorin
• Shilane Philip

Classifications

• H04L67/133

  Protocols for remote procedure calls [RPC] · CPC title

• H04L69/04

  Protocols for data compression, e.g. ROHC · CPC title

• H04L67/1097 Primary

  for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS] · CPC title

• H04L9/0643

  Hash functions, e.g. MD5, SHA, HMAC or f9 MAC · CPC title

• H04L67/06

  specially adapted for file transfer, e.g. file transfer protocol [FTP] · CPC title