Smoothing peak system load via behavior prediction in collaborative systems with temporal data access patterns

• US 9,942,289 B2
• Filed: 01/08/2016
• Issued: 04/10/2018
• Est. Priority Date: 06/29/2010
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Holden, Russell L.
• Primary Examiner(s): Nguyen, Dustin
• Assistant Examiner(s): Mesa, Joel
• Application Number:
  US14/991,600
• Publication Number:
  US 20160127431A1
• Time in Patent Office: 823 Days
• Field of Search: 709206, 709204
• CPC Class Codes: G06F 9/5083 Techniques for rebalancing the load in a distributed system
• CPC Class Codes: H04L 47/823 Prediction of resource usage
• CPC Class Codes: H04L 47/83 based on usage prediction
• CPC Class Codes: H04L 51/42 Mailbox-related aspects, e.g. synchronisation of mailboxes
• CPC Class Codes: H04L 65/403 Arrangements for multi-party communication, e.g. for conferences data switching systems for conference H04L12/18; arrangements for connecting several subscribers to a common circuit, i.e. affording conference facilities H04M3/56; television conferencing systems H04N7/15
• CPC Class Codes: H04L 67/10 in which an application is distributed across nodes in the network software deployment G06F8/60; multiprogramming arrangements G06F9/46
• CPC Class Codes: H04L 67/568 Storing data temporarily at an intermediate stage, e.g. caching
• CPC Class Codes: H04L 67/5681 Pre-fetching or pre-delivering data based on network characteristics
• CPC Class Codes: H04L 67/61 taking into account QoS or priority requirements

Abstract

Techniques are described above for smoothing peak load in collaborative systems. One embodiment includes, prior to a predicted peak load period, pre-staging user-data associated with one or more users of the collaborative system. During the predicted peak load period, a request from a first one of the users for access to the pre-staged user-data associated with the first user is received. And in response to the request, the pre-staged user-data is provided to the first user.

Claims

1. A computer-implemented method of smoothing system loads in a collaborative system, the method comprising:

recording a plurality of times at which a first user first accesses a resource relative to a predefined time criteria;

determining, based on the recorded times, an average first access time for the resource;

accessing, based on the determined average first access time and a use of the resource being less than a predetermined threshold, the resource on behalf of the first user without an explicit access request from the first user;

caching first data based on the access; and

providing the first user with access to the cached first data.

2. The method of claim 1, wherein the resource is an email client, and the first data comprises one or more email messages.

3. The method of claim 1, further comprising:

accessing the resource on behalf of a second user without an explicit access request from the second user;

caching second data based on the access on behalf of the second user;

determining an amount of time that has elapsed following the caching of the second data; and

determining, based on the determined amount of time and whether the second user has accessed the cached second data during the amount of time, whether to discard the cached second data.

4. The method of claim 1, wherein the first data comprises one or more documents composed by users of the collaborative system.

5. The method of claim 1, wherein caching the first data comprises retrieving the first data from a disk-based storage system and caching the retrieved first data in a memory.

6. The method of claim 1, further comprising discarding the first data after the first user has accessed the cached first data.

7. The method of claim 1, further comprising:

determining, for each of a plurality of users of the collaborative system including the first user, a respective average first access time;

generating, based on the determined plurality of average first access times, a schedule of accesses for each of the plurality of users; and

performing the accesses on behalf of the first user according to the generated schedule.

8. The method of claim 7, further comprising:

predicting a peak load period based on the determined plurality of average first access times,

wherein generating the schedule of accesses is based on the predicted peak load period.

9. A computer program product for smoothing system loads in a collaborative system, the computer program product comprising:

a computer-readable device having computer-readable program code embodied therewith, the computer-readable program code executable by one or more computer processors to;

record a plurality of times at which a first user first accesses a resource relative to a predefined time criteria;

determine, based on the recorded times, an average first access time for the resource;

access, based on the determined average first access time and a use of the resource being less than a predetermined threshold, the resource on behalf of the first user without an explicit access request from the first user;

cache first data based on the access; and

provide the first user with access to the cached first data.

10. The computer program product of claim 9, wherein the resource is an email client, and the first data comprises one or more email messages.

11. The computer program product of claim 9, wherein the first data comprises one or more documents composed by users of the collaborative system.

12. The computer program product of claim 9, wherein caching first data comprises retrieving the first data from a disk-based storage system and caching the retrieved first data in a memory.

13. The computer program product of claim 9, wherein the computer-readable program code is further executable to discard the first data after the first user has accessed the cached first data.

14. The computer program product of claim 9, wherein the computer-readable program code is further executable to:

determine, for each of a plurality of users of the collaborative system including the first user, a respective average first access time;

generate, based on the determined plurality of average first access times, a schedule of accesses for each of the plurality of users; and

perform the accesses on behalf of the first user according to the generated schedule.

15. The computer program product of claim 14, wherein the computer-readable program code is further executable to:

predict a peak load period based on the determined plurality of average first access times,

wherein generating the schedule of accesses is based on the predicted peak load period.

16. A system to smooth system loads in a collaborative system, the system comprising:

one or more computer processors;

a memory containing a program which, when executed by the one or more computer processors, performs an operation comprising;

recording a plurality of times at which a first user first accesses a resource relative to a predefined time criteria;

determining, based on the recorded times, an average first access time for the resource;

accessing, based on the determined average first access time and a use of the resource being less than a predetermined threshold, the resource on behalf of the first user without an explicit access request from the first user;

caching first data based on the access; and

providing the first user with access to the cached first data.

17. The system of claim 16, wherein the first data comprises one of:

one or more email messages, and

one or more documents composed by users of the collaborative system.

18. The system of claim 16, the operation further comprising discarding the first data after the first user has accessed the cached first data.

19. The system of claim 16, the operation further comprising:

determining, for each of a plurality of users of the collaborative system including the first user, a respective average first access time;

generating, based on the determined plurality of average first access times, a schedule of accesses for each of the plurality of users; and

performing the accesses on behalf of the first user and on behalf of the second user according to the generated schedule.

20. The system of claim 19, the operation further comprising:

predicting a peak load period based on the determined plurality of average first access times,

wherein generating the schedule of accesses is based on the predicted peak load period.