Preemptive extraction of data from long latency storage in a cloud computing environment

Patent metadata

Field	Value
Publication number	US-10057332-B2
Application number	US-201414567441-A
Country	US
Kind code	B2
Filing date	Dec 11, 2014
Priority date	Dec 11, 2014
Publication date	Aug 21, 2018
Grant date	Aug 21, 2018

Abstract

A resource utilization mechanism (RUM) preemptively extracts data from long latency storage in a cloud computing environment to economically and quickly provide data that is infrequently accessed by customers. The RUM identifies periods of low resource utilization where capacity can be efficiently utilized, identifies data to be retrieved, and retrieves the data from long latency storage to make it available to the customer. The RUM may notify a customer that the data is available and allow the customer to accept terms of use for the data or opt out of using the data.

First claim

The invention claimed is:

1. A computer-implemented method executed by at least one processor for preemptively extracting data from long latency storage and placing the preemptively extracted data in low latency storage to provide infrequently accessed data to a customer application, the method comprises:
identifying periods of low utilization of cloud resources where excess capacity can be efficiently utilized;
identifying data of a customer's data stored on cloud resources to be preemptively retrieved from the long latency storage; and
retrieving the data from the long latency storage located in offline storage in a service provider's data center and moving it prior to a request for the data from the customer application to the low latency storage in online disk storage also located in the service provider's data center;
providing the data moved to low latency storage to the customer application located on the cloud resources.

2. The method of claim 1 wherein the low utilization of cloud resources includes central processor utilization, disk utilization and network utilization.

3. The method of claim 1 wherein identifying periods of low utilization of cloud resources further comprises:
tracking and recording resource usage;
analyzing resource usage; and
predicting periods of low utilization of resources.

4. The method of claim 1 wherein identifying data to be preemptively retrieved from long latency storage further comprises considering data requests from the customer application for future needs.

5. The method of claim 1 wherein identifying data to be preemptively retrieved further comprises analyzing access patterns by the customer application to long latency data and cross referencing history of usage of the overall cloud to find an optimal time to fit the user's periodic usage into the overall cloud usage.

6. The method of claim 1 wherein making the long latency data available to the customer further comprises:
notifying the customer application of availability of the data;
giving the customer application terms of access to the data; and
allowing a user of the customer application to either accept the terms or opt out of using the data.

7. The method of claim 4 further comprising receiving a data pre-order message from the customer application that indicates what data items are needed, a priority and a time frame when the data is needed.

8. The method of claim 7 wherein the data pre-order message is manually provided by a user of the customer application.

9. A computer-implemented method executed by at least one processor for preemptively extracting data from long latency storage and placing the preemptively extracted data in low latency storage to provide infrequently accessed data to a customer application comprises:
identifying periods of low utilization of cloud resources where excess capacity can be efficiently utilized by:
tracking and recording resource usage;
analyzing resource usage;
predicting periods of low utilization of resources;

identifying data of a customer's data stored on cloud resources to be preemptively retrieved from long latency storage in response to a data pre-order message from the customer application that indicates what data in long latency storage will likely be needed at a future time;
retrieving the data from long latency storage located in offline storage in a service provider's data center and moving it to the low latency storage in online disk storage also located in the service provider's data center and making it available to the customer application prior to a request for the data from the customer application by:
notifying the customer application of availability of the data;
giving the customer application terms of access to the data; and
allowing a user of the customer application to either accept the terms or opt out of using the data;
providing the data moved to low latency storage to the customer application located on the cloud resources;

wherein the low utilization of cloud resources includes central processor utilization, disk utilization and network utilization; and
wherein identifying data to be preemptively retrieved further comprises analyzing access patterns by the customer application to long latency data and cross-referencing history of usage of the overall cloud to find an optimal time to fit the user's periodic usage into the overall cloud usage.

10. The method of claim 9 wherein considering data requests from the customer application for future needs further comprises receiving a data pre-order message from a customer application that is manually provided by a user of the customer application.

11. The method of claim 9 wherein identifying data to be preemptively retrieved further comprises analyzing customer access patterns to long latency data.

12. The method of claim 9 wherein the pre-order message indicates what data items are needed, a priority and a time frame when the data is needed.

Assignees

• IBM

Inventors

• Bragstad Lance
• Fork Michael J
• Odden Mathew R
• Reznechek Adam D

Classifications

• H04L67/10 Primary

  in which an application is distributed across nodes in the network (software deployment G06F8/60; multiprogramming arrangements G06F9/46) · 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

• H04L47/78

  Architectures of resource allocation · CPC title

• G06F5/00

  Methods or arrangements for data conversion without changing the order or content of the data handled · CPC title

• H04L47/83

  based on usage prediction · CPC title