# US 2003/0084154 A1 · Energy-induced process migration

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2003/0084154 A1
- Document ID: US20030084154A1
- Status: Published application
- Kind: A1
- Application number: 10/001,742
- Filed: 2001-10-31
- Published: 2003-05-01
- Earliest claimed: 2001-10-31
- Assignees: International Business Machines Corporation
- Inventors: Patrick J. Bohrer; Elmootazbellah N. Elnozahy; Thomas W. Keller; Michael D. Kistler; Freeman L. Rawson III
- Web page: https://patentgrep.com/patent/US20030084154A1

## CPC

- G06F 9/5061: {Partitioning or combining of resources}
- G06F 9/5094: {where the allocation takes into account power or heat criteria (power management in computers in general G06F1/3203; thermal management in computers in general G06F1/206)}
- H04L 9/40: Network security protocols
- G06F 2209/5014: Reservation
- Y02D 10/00: Energy efficient computing, e.g. low power processors, power management or thermal management
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)
- Y02D: CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE

## Abstract

Cluster systems having central processor units (CPUs) with multiple processors (MPs) are configured as high density servers. Power density is managed within the cluster systems by assigning a utilization to persistent states and connections within the cluster systems. If a request to reduce overall power consumption within the cluster system is received, persistent states and connections are moved (migrated) within the multiple processors based on their utilization to balance power dissipation within the cluster systems. If persistent connections and states, that must be maintained have a low rate of reference, they may be maintained in processors that are set to a standby mode where memory states are maintained. In this way the requirement to maintain persistent connections and states does not interfere with an overall strategy of managing power within the cluster systems.

## Claims

### Claim 1

A method for managing workload distribution in a multiple processor cluster system to conserve energy, comprising the steps of:
classifying persistent states and connections within said cluster system according to an activity referencing said persistent states and connections;
receiving a request to modify a workload of said cluster system;
determining a minimum number of processors in said cluster system for executing said modified workload while maintaining said persistent states and connections;
determining a workload distribution within said minimum number of processors that satisfies said modified workload while maintaining said persistent states and connections; and
modifying an operation mode of a selected processor in said processors of said cluster system to conserve energy while satisfying said modified workload while maintaining said persistent states and connections.

### Claim 2 (depends on 1)

The method of claim 1, further comprising the step of migrating persistent states and connections within said cluster system to effect said workload distribution.

### Claim 3 (depends on 1)

The method of claim 1, wherein said operation mode of said selected processor is modified by setting said selected processor to an off mode.

### Claim 4 (depends on 1)

The method of claim 1, wherein said operation mode of said selected processor is modified by setting said selected processor to a stand-by mode.

### Claim 5 (depends on 1)

The method of claim 1, wherein said operation mode of said selected processor is modified by setting said selected processor to an active full power mode from an off or a stand-by mode.

### Claim 6 (depends on 1)

The method of claim 1, wherein said step of determining said workload distribution for said minimum number of processors uses a constraint based bin packing algorithm.

### Claim 7 (depends on 5)

The method of claim 5, wherein a particular constraint of said bin packing algorithm comprises minimizing a number of processes and states migrated to effect said workload distribution.

### Claim 8

A cluster system comprising;
a multiple processor central processing unit (CPU) having circuitry for classifying persistent states and connections within said cluster system according to an activity referencing said persistent states and connections, circuitry for receiving a request to modify a workload of said cluster system, circuitry for determining a minimum number of processors in said cluster system for executing said modified workload while maintaining said persistent states and connections, circuitry for determining a workload distribution within said minimum number of processors that satisfies said modified workload while maintaining said persistent states and connections, and circuitry for modifying an operation mode of a selected processor in said processors of said cluster system to conserve energy while satisfying said modified workload while maintaining said persistent states and connections;
a random access memory (RAM);
a communications adapter coupled to a communication network; and
a bus system coupling said CPUs to said communications adapter and said RAM.

### Claim 9 (depends on 9)

The cluster system of claim 9, further comprising the step of migrating persistent states and connections within said cluster system to effect said workload distribution.

### Claim 10 (depends on 9)

The cluster system of claim 9, wherein said operation mode of said selected processor is modified by setting said selected processor to an off mode.

### Claim 11 (depends on 9)

The cluster system of claim 9, wherein said operation mode of said selected processor is modified by setting said selected processor to a stand-by mode.

### Claim 12 (depends on 9)

The cluster system of claim 9, wherein said operation mode of said selected processor is modified by setting said selected processor to an active full power mode from an off or a stand-by mode.

### Claim 13 (depends on 9)

The cluster system of claim 9, wherein said step of determining said workload distribution for said minimum number of processors uses a constraint based bin packing algorithm.

### Claim 14 (depends on 13)

The cluster system of claim 13, wherein a particular constraint of said bin packing algorithm comprises minimizing a number of processes and states migrated to effect said workload distribution.

### Claim 15

A computer program product for managing workload distribution in a multiple processor cluster system to conserve energy, said computer program product embodied in a machine readable medium for energy management in a computer system having a plurality of computation nodes, including programming for a processor, said computer program comprising a program of instructions for performing the program steps of:
classifying persistent states and connections within said cluster system according to an activity referencing said persistent states and connections;
receiving a request to modify a workload of said cluster system;
determining a minimum number of processors in said cluster system for executing said modified workload while maintaining said persistent states and connections;
determining a workload distribution within said minimum number of processors that satisfies said modified workload while maintaining said persistent states and connections; and
modifying an operation mode of a selected processor in said processors of said cluster system to conserve energy while satisfying said modified workload while maintaining said persistent states and connections.

### Claim 16 (depends on 15)

The computer program product of claim 15, further comprising the step of migrating persistent states and connections within said cluster system to effect said workload distribution.

### Claim 17 (depends on 15)

The computer program product of claim 15, wherein said operation mode of said selected processor is modified by setting said selected processor to an off mode.

### Claim 18 (depends on 15)

The computer program product of claim 15, wherein said operation mode of said selected processor is modified by setting said selected processor to a stand-by mode.

### Claim 19 (depends on 15)

The computer program product of claim 15, wherein said operation mode of said selected processor is modified by setting said selected processor to an active full power mode from an off or a stand-by mode.

### Claim 20 (depends on 15)

The computer program product of claim 15, wherein said step of determining said workload distribution for said minimum number of processors uses a constraint based bin packing algorithm.

### Claim 21 (depends on 20)

The computer program product of claim 20, wherein a particular constraint of said bin packing algorithm comprises minimizing a number of processes and states migrated to effect said workload distribution.
