Job protection within a distributed processing system having subsystem downtime

• US 6,625,636 B1
• Filed: 05/13/1999
• Issued: 09/23/2003
• Est. Priority Date: 05/13/1999
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: International Business Machines Corporation
• Inventors: Skovira, Joseph Francis
• Primary Examiner(s): Wiley, David
• Assistant Examiner(s): Avellino, Joseph E
• Application Number:
  US09/311,778
• Time in Patent Office: 1,594 Days
• Field of Search: 709/100, 709/102, 709/103, 709/105, 709/223, 711/158, 700/100
• US Class Current: 718/102
• CPC Class Codes: G06F 15/161 Computing infrastructure, e.g. computer clusters, blade chassis or hardware partitioning casings, cabinets, racks or drawers for data centers H05K5/00
• CPC Class Codes: G06F 9/4843 by program, e.g. task dispatcher, supervisor, operating system

Abstract

A job scheduler module for a distributed processing system is provided with capability to protect jobs from planned or unplanned subsystem downtimes. The approach includes determining a downtime for a subsystem of the distributed processing system, determining at least one of a start time and an end time of a job to be executed using the subsystem, determining whether the start time or the end time of the job is within the downtime, and if not, placing the job in an eligible job list. The scheduler then makes a decision whether to start the job using the eligible job list. A downtime protection flag can be associated with each job, thereby allowing a user to indicate whether the job is to receive subsystem downtime protection. If not, then the job is placed directly in the eligible job list for scheduler execution irrespective of subsystem downtime.

Claims

1. A method for processing computer jobs within a distributed processing computer system, said method comprising:

(i) automatically determining a downtime for a subsystem of said distributed processing computer system, wherein during said downtime, said subsystem is unavailable;

(ii) determining at least one of a start time and an end time of a computer job to be executed at least in part using said subsystem;

(iii) determining whether said start time or said end time of said computer job is within said downtime, and if not, placing said computer job in an eligible job list;

(iv) making a decision whether to start said computer job using said eligible job list; and

(v) further comprising indicating whether said computer job is to receive downtime protection, and if so, performing said determining (ii) and said determining (iii) for said computer job.

2. The method of claim 1, further comprising implementing said method from an external parallel job scheduler.

3. The method of claim 1, wherein said indicating comprises setting a flag associated with said job when said job is to receive subsystem downtime protection by performing said determining (ii) and said determining (iii) for said job.

4. The method of claim 1, wherein said automatically determining (i) comprises reading a downtime file identifying said subsystem with a downtime entry, and wherein said method comprises for each job of a plurality of jobs to be processed within said distributed processing system, repeating said determining (ii), said determining (iii) and said making (iv).

5. The method of claim 1, wherein said determining (ii) comprises assuming that said job has an immediate start time and computing an end time therefor from said immediate start time.

6. The method of claim 1, wherein said subsystem comprises at least one of a batch scheduling system, a parallel file system, and a mass storage system.

7. The method of claim 1, wherein the determining (i) occurs without suspending operation of said distributed processing computer system.

8. The method of claim 1, wherein the determining (i) comprises dynamically determining the downtime for the subsystem while processing computer jobs within the distributed processing computer system.

9. A system for processing jobs within a distributed processing computer system, said system comprising:

a scheduler module for controlling scheduling of a computer job for execution within said distributed processing computer system, said scheduler module comprising computer code for;

(i) automatically determining a downtime for a subsystem of said distributed processing computer system, wherein during said downtime, said subsystem is unavailable;

(ii) determining at least one of a start time and an end time of a computer job to be executed at least in part using said subsystem;

(iii) determining whether said start time or said end time of said computer job is within said downtime, and if not, placing said computer job in an eligible job list; and

(iv) making a decision whether to start said computer job using said eligible job list; and

wherein said scheduler module is further adapted to indicate whether said computer job is to receive downtime protection, and if so, to perform said determining (ii) and said determining (iii) for said computer job.

10. The system of claim 9, wherein said scheduler module comprises an external parallel job scheduler coupled to said distributed processing system.

11. The system of claim 9, wherein said indicating of said scheduler module comprises setting a flag associated with said job when said job is to receive subsystem downtime protection by performing said determining (ii) and said determining (iii) for said job.

12. The system of claim 9, wherein said automatically determining (i) comprises reading a downtime file identifying said subsystem with a downtime entry, and wherein said scheduler module of said system comprises for each job of a plurality of jobs to be processed within said distributed processing system, computer code for repeating said determining (ii), said determining (iii) and said making (iv).

13. The system of claim 9, wherein said determining (ii) comprises assuming that said job has an immediate start time and computing an end time therefor from said immediate start time.

14. The system of claim 9, wherein said subsystem comprises at least one of a batch scheduling system, a parallel file system, and a mass storage system.

15. A system for processing computer jobs within a distributed processing computer system, said system comprising:

(i) means for automatically determining a downtime for a subsystem of said distributed processing computer system, wherein during said downtime, said subsystem is unavailable;

(ii) means for determining at least one of a start time and an end time of a computer job to be executed using said subsystem;

(iii) means for determining whether said start time or said end time of said computer job is within said downtime, and if not, for placing said computer job in an eligible job list;

(iv) means for making a decision whether to start said computer job using said eligible job list; and

(v) means for indicating whether said computer job is to receive downtime protection, and if so, for performing said means for determining (ii) and said means for determining (iii) for said computer job.

16. An article of manufacture comprising:

a computer program product comprising computer usable medium having computer readable program code means therein for use in processing computer jobs within a distributed processing computer system, said computer readable program code means in said computer program product comprising;

computer readable program code means for causing a computer to automatically effect determining a downtime for a subsystem of said distributed processing computer system, wherein during said downtime, said subsystem is unavailable;

computer readable program code means for causing a computer to effect determining at least one of a start time and an end time for a computer job to be executed using said subsystem;

computer readable program code means for causing a computer to effect determining whether said start time or said end time of said computer job is within said downtime, and if not, placing said computer job in an eligible job list;

computer readable program code means for causing a computer to effect making a decision whether to start said computer job using said eligible job; and

computer readable program code means for causing a computer to effect indicating whether said computer job is to receive downtime protection, and if so, performing said determining at least one of said start time and end time for said computer job and said determining whether said start time or end time of said computer job is within said downtime.

17. The article of manufacture of claim 16, wherein said article of manufacture resides within an external parallel job scheduler coupled to said distributed processing system.

18. The article of manufacture of claim 16, wherein said computer readable program code means for causing a computer to effect indicating comprises computer readable program code means for causing a computer to effect setting a flag associated with said job when said job is to receive subsystem downtime protection via said determining at least one of the start time and the end time for said job and said determining whether said start time or said end time of said job is within said downtime.

19. The article of manufacture of claim 16, wherein said computer readable program code means for causing a computer to effect determining at least one of a start time and an end time for said job comprises computer readable program code means for causing a computer to effect assuming that said job has an immediate start time and computing an end time therefor from said immediate start time.