Application bundle preloading

• US 10,523,518 B2
• Filed: 06/27/2015
• Issued: 12/31/2019
• Est. Priority Date: 05/21/2015
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Fawcett, Bradley W.
• Primary Examiner(s): Divecha, Kamal B
• Assistant Examiner(s): Kim, Eui H
• Application Number:
  US14/752,851
• Publication Number:
  US 20160342405A1
• Time in Patent Office: 1,648 Days
• CPC Class Codes: H04L 41/14 Network analysis or design
• CPC Class Codes: H04L 67/1095 Replication or mirroring of data, e.g. scheduling or transport for data synchronisation between network nodes
• CPC Class Codes: H04L 67/1097 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 Class Codes: H04L 67/34 involving the movement of software or configuration parameters network booting or remote initial program loading [RIPL] G06F9/4416
• CPC Class Codes: H04L 67/52 specially adapted for the location of the user terminal

Abstract

Disclosed aspects include managing a set of application bundles for processing a stream of tuples. A set of application bundles which are installed on a second compute node is monitored by a first compute node. A candidate application bundle of the set of application bundles is detected by the first compute node. A determination is made to install the candidate application bundle on the first compute node. The determination is made by the first compute node based on a set of anticipation criteria. The candidate application bundle is installed on the first compute node.

Claims

1. A system for managing a set of application bundles, the system comprising:

a memory having a set of computer readable computer instructions, and a processor for executing the set of computer readable instructions, the set of computer readable instructions including;

monitoring, by a first compute node, a set of application bundles which are installed on a second compute node, the second node being one of a set of compute nodes comprising one or more processing elements that executes the set of application bundles;

identifying, by a first compute node, a candidate application bundle that is needed to interpret a particularized subset of information to be found in tuples expected to be received for processing within an approaching temporal period, based on inspecting the set of application data on the second compute node indicating possession of the candidate application bundle by the second compute node, wherein the candidate application bundle contains an executable code that can be executed by a subset of processing elements, wherein the subset of processing elements are capable of executing a stream of tuples expected to be received for processing prior to the first compute node receiving a request to process the stream of tuples, wherein the candidate application bundle requires more bandwidth than is currently available on the second compute node to interpret the stream of tuples, and wherein the first compute node currently has more processing power than the second compute node;

determining, by the first compute node based on the identified candidate application bundle and based on a set of anticipation criteria, to install the candidate application bundle on the first compute node, wherein the set of anticipation criteria anticipates a likelihood that the first compute node will be requested to process the stream of tuples, and wherein the set of anticipation criteria are an expected resource burden that corresponds to a predicted value based on a predicted resource usage, a physical proximity criterion, a failover frequency, an expected candidacy criterion of the first compute node for processing the stream of tuples based on a load of the system and availability of the first compute node, and a temporal benefit criterion;

preloading, based on the identifying and the determining, the candidate application bundle on the first compute node prior to the first compute node receiving the request to process the stream of tuples;

receiving the stream of tuples to be processed by a plurality of processing elements operating on a set of compute nodes; and

processing, using the preloaded candidate application bundle on the first compute node, the stream of tuples in response to installing the candidate application bundle on the first compute node,

wherein the monitoring comprises communicating, by the first compute node, with an application bundle directory which stores the set of application bundle data and which is separate from the second compute node.

2. The system of claim 1, wherein the set of anticipation criteria includes:

the expected resource burden criterion when downloading the application bundle to the first compute node from the second compute node.

3. The system of claim 1, wherein the set of anticipation criteria includes:

a second physical proximity criterion of the second compute node with respect to the first compute node.

4. The system of claim 1, wherein the set of anticipation criteria includes:

a second failover frequency criterion of the second compute node.

5. The system of claim 1, wherein the temporal benefit criterion for processing the stream of tuples is within a threshold temporal period.

6. The system of claim 1, wherein monitoring, by the first compute node, the set of application bundles which are installed on the second compute node includes:

observing the set of application bundles; and

analyzing the set of application bundles.

7. A computer program product for managing a set of application bundles, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, wherein the computer readable storage medium is not a transitory signal per se, the program instructions executable by a processor to cause the processor to perform a method comprising:

monitoring, by a first compute node, a set of application bundles which are installed on a second compute node, the second node being one of a set of compute nodes comprising one or more processing elements that executes the set of application bundles;

identifying, by a first compute node, a candidate application bundle that is needed to interpret a particularized subset of information to be found in tuples expected to be received for processing within an approaching temporal period, based on inspecting the set of application data on the second compute node indicating possession of the candidate application bundle by the second compute node, wherein the candidate application bundle contains an executable code that can by executed by a subset of processing elements, wherein the subset of processing elements are capable of executing a stream of tuples expected to be received for processing prior to the first compute node receiving a request to process the stream of tuples, wherein the candidate application bundle requires more bandwidth than is currently available on the second compute node to interpret the stream of tuples, and wherein the first compute node currently has more processing power than the second compute node;

determining, by the first compute node based on the identified candidate application bundle and based on a set of anticipation criteria, to install the candidate application bundle on the first compute node, wherein the set of anticipation criteria anticipates a likelihood that the first compute node will be requested to process the stream of tuples, and wherein the set of anticipation criteria are an expected resource burden that corresponds to a predicted value based on a predicted resource usage, a physical proximity criterion, a failover frequency, an expected candidacy criterion of the first compute node for processing the stream of tuples based on a load of the system and availability of the first compute node, and a temporal benefit criterion;

preloading, based on the identifying and the determining, the candidate application bundle on the first compute node prior to the first compute node receiving the request to process the stream of tuples;

receiving the stream of tuples to be processed by a plurality of processing elements operating on a set of compute nodes; and

processing, using the preloaded candidate application bundle on the first compute node, the stream of tuples in response to installing the candidate application bundle on the first compute node,

wherein the monitoring comprises communicating, by the first compute node, with an application bundle directory which stores the set of application bundle data and which is separate from the second compute node.

8. The computer program product of claim 7, wherein the program instructions are stored in a computer readable storage medium in a data processing system, wherein the computer readable storage medium is not a transitory signal per se, and wherein the program instructions were downloaded over a network from a remote data processing system.

9. The computer program product of claim 7, wherein the program instructions are stored in a computer readable storage medium in a server data processing system, wherein the computer readable storage medium is not a transitory signal per se, and wherein the program instructions are downloaded over a network to a remote data processing system for use in a computer readable storage medium with the remote data processing system.