Computing system and control method

• US 7,293,092 B2
• Filed: 01/14/2003
• Issued: 11/06/2007
• Est. Priority Date: 07/23/2002
• Status: Expired due to Fees

• Current Assignee: Hitachi, Ltd.
• Original Assignee: Hitachi, Ltd.
• Inventors: Sukegawa, Naonobu
• Primary Examiner(s): Nguyen; Phuoc
• Application Number:
  US10/341,505
• Publication Number:
  US 20040019624A1
• Time in Patent Office: 1,757 Days
• Field of Search: 718/101, 718/102, 718/103, 718/105, 709/202, 709/226, 709/238, 709/245
• US Class Current: 709/226
• CPC Class Codes: G06F 9/4843 by program, e.g. task dispatcher, supervisor, operating system

Abstract

A parallel or grid computing system that having a plurality of nodes and achieves job scheduling for the nodes with a view toward system efficiency optimization. The parallel or grid computing system has a plurality of nodes for transmitting and receiving data and a communication path for exchanging data among the nodes, which are either a transmitting node for transmitting data or a receiving node for processing a job dependent on transmitted data, and further has a time measuring means for measuring the time interval between the instant at which data is called for by a job and the instant at which the data is transmitted from a transmitting node to a receiving node, a time counting means for adding up the measured wait time data about each job, and a job scheduling means for determining the priority of jobs in accordance with the counted wait time and for scheduling jobs.

Claims

1. A computing system comprising:

a plurality of nodes for transmitting and receiving data and a communication path for exchanging data among said nodes, each of said nodes being either a transmitting node for transmitting data or a receiving node for processing a job dependent on transmitted data;

time measuring means for measuring the time interval between the instant at which data is called for by said job and the instant at which the data is transmitted from said transmitting node to said receiving node;

time counting means for adding up said measured time data on an individual job basis;

job scheduling means for scheduling jobs determining in accordance with the counted time,

wherein the time measuring means comprises a counter that starts counting in response to said job calling for data and stopping counting in response to the transmitted data reaching a reception buffer in a receiving node, and

wherein said transmitting node comprises load balance measuring means for adding up said time data measured at various nodes on an individual job basis, and said scheduling means determines the priority of jobs in accordance with the time count of each job and schedules the jobs, and the load balance measuring means comprises a load balance calculation circuit that adds waiting time at each node measured by the counter.

2. The computing system according to claim 1, wherein said time measuring means calculates the cumulative time per unit time at a node receiving said time data and notifies said load balance measuring means of the calculated cumulative time per said unit time.

3. The computing system according to claim 2, wherein said load balance measuring means is notified of said calculated cumulative time per said unit time in synchronism with signals generated at fixed intervals by said wait time measuring means.

4. The computing system according to claim 2, wherein said load balance measuring means retains weight information according to the load on job processes performed at nodes, calculates the product of said wait time data and weight information, and determines the total accumulated value of calculated values.

5. The computing system according to claim 1 wherein said load balance measuring means retains weight information according to the load on job processes performed at nodes, calculates the product of said wait time data and weight information, and determines the total accumulated value of calculated values.

6. The computing system according to claim 1 wherein said transmitting node comprises load balance measuring means for adding up said time data measured at various nodes on an individual job basis, and said scheduling means determines the priority of jobs in accordance with the time count of each job and schedules the jobs.

7. The computing system according to claim 1 wherein said load wherein said transmitting node comprises load balance measuring means for adding up balance measuring means retains weight information according to the load on job processes performed at nodes, calculates the product of said wait time data and weight information, and determines the total accumulated value of calculated values.