Patent US6332200B1 successfully refreshed from Google Patents.
US6332200B1
Expired / Lapsed
US
⏱️ 0.0 years remaining
Capturing and identifying a complete and consistent set of checkpoint files
Assignee: International Business Machines Corp
•
Filing: 1998-10-29
•
Granted: 2001-12-18
•
Expires: 2018-10-29
Abstract
Abstract A complete and consistent set of checkpoint files is captured and identified for use in restarting a parallel program. When each process of a parallel program takes a checkpoint, it creates a checkpoint file. The checkpoint file is named, and a part of that name includes a version number for the checkpoint file. When a parallel program is to be restarted, each process of the parallel program identifies its most current valid checkpoint file. It provides the version number of this file to a coordinating process. The coordinating process then decides which version of the checkpoint files is valid and complete for all of the processes of the parallel program participating in restart. Once this version number is determined, it is forwarded to the processes and the processes restore themselves using its corresponding checkpoint file having that particular version number.
Inventors
- 👤 Kalman Zvi Meth
- 👤 Adnan M. Agbaria
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-11-03 22:50
CPC Classifications
G; G06; G06F; G06F11/00; G06F11/07; G06F11/14; G06F11/1446; G06F11/1458; G06F2201/00; G06F2201/82; Y; Y10; Y10S; Y10S707/00; Y10S707/99951; Y10S707/99952; Y10S707/99953; Y10S707/99954
Claims Analysis
Total Claims: 54
Claim 1
Independent Claim
73 words
A method of identifying a complete and consistent set of checkpoint files for a parallel program, said method comprising: determining, by a plurality of processes of said parallel program, a plurality of version numbers representative of a plurality of current valid checkpoint files corresponding to said plurality of processes; and selecting from said plurality of version numbers a selected version number representative of a consistent set of checkpoint files for said parallel program.
Claim 2
Independent Claim
73 words
A method of identifying a complete and consistent set of checkpoint files for a parallel program, said method comprising: determining, by a plurality of processes of said parallel program, a plurality of version numbers representative of a plurality of current valid checkpoint files corresponding to said plurality of processes; and selecting from said plurality of version numbers a selected version number representative of a consistent set of checkpoint files for said parallel program.
Claim 3
Dependent Claim
31 words
The method of claim 1 , wherein said consistent set of checkpoint files comprises a plurality of checkpoint files corresponding to said plurality of processes and having said selected version number.
Claim 4
Dependent Claim
24 words
The method of claim 2 , further comprising restoring said plurality of processes using said plurality of checkpoint files having said selected version number.
Claim 5
Dependent Claim
33 words
The method of claim 3 , further comprising verifying, by said plurality of processes, prior to restoring, that said plurality of processes have said plurality of checkpoint files with said selected version number.
Claim 6
Dependent Claim
37 words
The method of claim 4 , wherein said selecting is performed by a coordinating process, and wherein said method further comprises said coordinating process informing said plurality of processes, prior to verifying, of said selected version number.
Claim 7
Dependent Claim
33 words
The method of claim 1 , wherein each of said plurality of current valid checkpoint files has a corresponding name, and wherein each corresponding name includes one of said plurality of version numbers.
Claim 8
Dependent Claim
75 words
The method of claim 1 , wherein said determining, for each process of said plurality of processes, comprises: identifying one or more valid checkpoint files corresponding to said each process, wherein each of said one or more valid checkpoint files has a corresponding name with a version number; and selecting from said one or more valid checkpoint files a maximum version number, wherein said plurality of version numbers comprises a plurality of maximum version numbers.
Claim 9
Dependent Claim
24 words
The method of claim 7 , wherein said selected version number is a minimum version number selected from said plurality of maximum version numbers.
Claim 10
Independent Claim
64 words
A method of identifying a set of complete and consistent checkpoint files for a parallel program, said method comprising: selecting, by a plurality of processes of said parallel program, a plurality of current valid checkpoint files corresponding to said plurality of processes; and using said selected plurality of current valid checkpoint files to identify a consistent set of checkpoint files for said parallel program.
Claim 11
Independent Claim
64 words
A method of identifying a set of complete and consistent checkpoint files for a parallel program, said method comprising: selecting, by a plurality of processes of said parallel program, a plurality of current valid checkpoint files corresponding to said plurality of processes; and using said selected plurality of current valid checkpoint files to identify a consistent set of checkpoint files for said parallel program.
Claim 12
Independent Claim
71 words
A method of capturing a set of checkpoint files for a parallel program, said method comprising: providing a plurality of checkpoint files to be used during a taking of a plurality of checkpoints corresponding to a plurality of processes of said parallel program, wherein each of said plurality of checkpoint files has a name, which includes a version number; and taking said plurality of checkpoints using said plurality of checkpoint files.
Claim 13
Independent Claim
71 words
A method of capturing a set of checkpoint files for a parallel program, said method comprising: providing a plurality of checkpoint files to be used during a taking of a plurality of checkpoints corresponding to a plurality of processes of said parallel program, wherein each of said plurality of checkpoint files has a name, which includes a version number; and taking said plurality of checkpoints using said plurality of checkpoint files.
Claim 14
Dependent Claim
16 words
The method of claim 10 , further comprising synchronizing said taking of said plurality of checkpoints.
Claim 15
Dependent Claim
20 words
The method of claim 10 , further comprising synchronizing deletion of any older versions of said plurality of checkpoint files.
Claim 16
Dependent Claim
33 words
The method of claim 10 , further comprising restoring said plurality of processes using a consistent set of checkpoint files, wherein each checkpoint file of said consistent set has a same version number.
Claim 17
Independent Claim
77 words
A system of identifying a complete and consistent set of checkpoint files for a parallel program, said system comprising: means for determining, by a plurality of processes of said parallel program, a plurality of version numbers representative of a plurality of current valid checkpoint files corresponding to said plurality of processes; and means for selecting from said plurality of version numbers a selected version number representative of a consistent set of checkpoint files for said parallel program.
Claim 18
Independent Claim
77 words
A system of identifying a complete and consistent set of checkpoint files for a parallel program, said system comprising: means for determining, by a plurality of processes of said parallel program, a plurality of version numbers representative of a plurality of current valid checkpoint files corresponding to said plurality of processes; and means for selecting from said plurality of version numbers a selected version number representative of a consistent set of checkpoint files for said parallel program.
Claim 19
Dependent Claim
31 words
The system of claim 14 , wherein said consistent set of checkpoint files comprises a plurality of checkpoint files corresponding to said plurality of processes and having said selected version number.
Claim 20
Dependent Claim
26 words
The system of claim 15 , further comprising means for restoring said plurality of processes using said plurality of checkpoint files having said selected version number.
Claim 21
Dependent Claim
35 words
The system of claim 16 , further comprising means for verifying, by said plurality of processes, prior to restoring, that said plurality of processes have said plurality of checkpoint files with said selected version number.
Claim 22
Dependent Claim
37 words
The system of claim 17 , wherein said means for selecting uses a coordinating process, and wherein said system further comprises means for informing, by said coordinating process, said plurality of processes of said selected version number.
Claim 23
Dependent Claim
33 words
The system of claim 14 , wherein each of said plurality of current valid checkpoint files has a corresponding name, and wherein each corresponding name includes one of said plurality of version numbers.
Claim 24
Dependent Claim
81 words
The system of claim 14 , wherein said means for determining, for each process of said plurality of processes, comprises: means for identifying one or more valid checkpoint files corresponding to said each process, wherein each of said one or more valid checkpoint files has a corresponding name with a version number; and means for selecting from said one or more valid checkpoint files a maximum version number, wherein said plurality of version numbers comprises a plurality of maximum version numbers.
Claim 25
Dependent Claim
24 words
The system of claim 20 , wherein said selected version number is a minimum version number selected from said plurality of maximum version numbers.
Claim 26
Independent Claim
68 words
A system of identifying a set of complete and consistent checkpoint files for a parallel program, said system comprising: means for selecting, by a plurality of processes of said parallel program, a plurality of current valid checkpoint files corresponding to said plurality of processes; and means for using said selected plurality of current valid checkpoint files to identify a consistent set of checkpoint files for said parallel program.
Claim 27
Independent Claim
68 words
A system of identifying a set of complete and consistent checkpoint files for a parallel program, said system comprising: means for selecting, by a plurality of processes of said parallel program, a plurality of current valid checkpoint files corresponding to said plurality of processes; and means for using said selected plurality of current valid checkpoint files to identify a consistent set of checkpoint files for said parallel program.
Claim 28
Independent Claim
87 words
A system of identifying a complete and consistent set of checkpoint files for a parallel program, said system comprising: at least one computing unit adapted to determine, by a plurality of processes of said parallel program, a plurality of version numbers representative of a plurality of current valid checkpoint files corresponding to said plurality of processes; and at least one computing unit adapted to select from said plurality of version numbers a selected version number representative of a consistent set of checkpoint files for said parallel program.
Claim 29
Independent Claim
87 words
A system of identifying a complete and consistent set of checkpoint files for a parallel program, said system comprising: at least one computing unit adapted to determine, by a plurality of processes of said parallel program, a plurality of version numbers representative of a plurality of current valid checkpoint files corresponding to said plurality of processes; and at least one computing unit adapted to select from said plurality of version numbers a selected version number representative of a consistent set of checkpoint files for said parallel program.
Claim 30
Independent Claim
75 words
A system of capturing a set of checkpoint files for a parallel program, said system comprising: means for providing a plurality of checkpoint files to be used during a taking of a plurality of checkpoints corresponding to a plurality of processes of said parallel program, wherein each of said plurality of checkpoint files has a name, which includes a version number; and means for taking said plurality of checkpoints using said plurality of checkpoint files.
Claim 31
Independent Claim
75 words
A system of capturing a set of checkpoint files for a parallel program, said system comprising: means for providing a plurality of checkpoint files to be used during a taking of a plurality of checkpoints corresponding to a plurality of processes of said parallel program, wherein each of said plurality of checkpoint files has a name, which includes a version number; and means for taking said plurality of checkpoints using said plurality of checkpoint files.
Claim 32
Dependent Claim
18 words
The system of claim 24 , further comprising means for synchronizing said taking of said plurality of checkpoints.
Claim 33
Dependent Claim
22 words
The system of claim 24 , further comprising means for synchronizing deletion of any older versions of said plurality of checkpoint files.
Claim 34
Dependent Claim
35 words
The system of claim 24 , further comprising means for restoring said plurality of processes using a consistent set of checkpoint files, wherein each checkpoint file of said consistent set has a same version number.
Claim 35
Dependent Claim
122 words
An article of manufacture, comprising: at least one computer usable medium having computer readable program code means embodied therein for causing the identifying of a complete and consistent set of checkpoint files for a parallel program, said computer readable program code means in said article of manufacture comprising: computer readable program code means for causing a computer to determine, by a plurality of processes of said parallel program, a plurality of version numbers representative of a plurality of current valid checkpoint files corresponding to said plurality of processes; and computer readable program code means for causing a computer to select from said plurality of version numbers a selected version number representative of a consistent set of checkpoint files for said parallel program.
Claim 36
Dependent Claim
122 words
An article of manufacture, comprising: at least one computer usable medium having computer readable program code means embodied therein for causing the identifying of a complete and consistent set of checkpoint files for a parallel program, said computer readable program code means in said article of manufacture comprising: computer readable program code means for causing a computer to determine, by a plurality of processes of said parallel program, a plurality of version numbers representative of a plurality of current valid checkpoint files corresponding to said plurality of processes; and computer readable program code means for causing a computer to select from said plurality of version numbers a selected version number representative of a consistent set of checkpoint files for said parallel program.
Claim 37
Dependent Claim
33 words
The article of manufacture of claim 28 , wherein said consistent set of checkpoint files comprises a plurality of checkpoint files corresponding to said plurality of processes and having said selected version number.
Claim 38
Dependent Claim
36 words
The article of manufacture of claim 29 , further comprising computer readable program code means for causing a computer to restore said plurality of processes using said plurality of checkpoint files having said selected version number.
Claim 39
Dependent Claim
45 words
The article of manufacture of claim 30 , further comprising computer readable program code means for causing a computer to verify, by said plurality of processes, prior to restoring, that said plurality of processes have said plurality of checkpoint files with said selected version number.
Claim 40
Dependent Claim
60 words
The article of manufacture of claim 31 , wherein said computer readable program code means for causing a computer to select uses a coordinating process, and wherein said article of manufacture further comprises computer readable program code means for causing a computer to inform, by said coordinating process, said plurality of processes, prior to verifying, of said selected version number.
Claim 41
Dependent Claim
35 words
The article of manufacture of claim 28 , wherein each of said plurality of current valid checkpoint files has a corresponding name, and wherein each corresponding name includes one of said plurality of version numbers.
Claim 42
Dependent Claim
107 words
The article of manufacture of claim 28 , wherein said computer readable program code means for causing a computer to determine, for each process of said plurality of processes, comprises: computer readable program code means for causing a computer to identify one or more valid checkpoint files corresponding to said each process, wherein each of said one or more valid checkpoint files has a corresponding name with a version number; and computer readable program code means for causing a computer to select from said one or more valid checkpoint files a maximum version number, wherein said plurality of version numbers comprises a plurality of maximum version numbers.
Claim 43
Dependent Claim
26 words
The article of manufacture of claim 34 , wherein said selected version number is a minimum version number selected from said plurality of maximum version numbers.
Claim 44
Dependent Claim
88 words
At least one program storage device readable by a machine, tangibly embodying at least one program of instructions executable by the machine to perform a method of identifying a set of complete and consistent checkpoint files for a parallel program, said method comprising: selecting, by a plurality of processes of said parallel program, a plurality of current valid checkpoint files corresponding to said plurality of processes; and using said selected plurality of current valid checkpoint files to identify a consistent set of checkpoint files for said parallel program.
Claim 45
Dependent Claim
88 words
At least one program storage device readable by a machine, tangibly embodying at least one program of instructions executable by the machine to perform a method of identifying a set of complete and consistent checkpoint files for a parallel program, said method comprising: selecting, by a plurality of processes of said parallel program, a plurality of current valid checkpoint files corresponding to said plurality of processes; and using said selected plurality of current valid checkpoint files to identify a consistent set of checkpoint files for said parallel program.
Claim 46
Dependent Claim
120 words
An article of manufacture comprising: at least one computer usable medium having computer readable program code means embodied therein for causing the capturing of a set of checkpoint files for a parallel program, said computer readable program code means in said article of manufacture comprising: computer readable program code means for causing a computer to provide a plurality of checkpoint files to be used during a taking of a plurality of checkpoints corresponding to a plurality of processes of said parallel program, wherein each of said plurality of checkpoint files has a name, which includes a version number; and computer readable program code means for causing a computer to take said plurality of checkpoints using said plurality of checkpoint files.
Claim 47
Dependent Claim
120 words
An article of manufacture comprising: at least one computer usable medium having computer readable program code means embodied therein for causing the capturing of a set of checkpoint files for a parallel program, said computer readable program code means in said article of manufacture comprising: computer readable program code means for causing a computer to provide a plurality of checkpoint files to be used during a taking of a plurality of checkpoints corresponding to a plurality of processes of said parallel program, wherein each of said plurality of checkpoint files has a name, which includes a version number; and computer readable program code means for causing a computer to take said plurality of checkpoints using said plurality of checkpoint files.
Claim 48
Dependent Claim
28 words
The article of manufacture of claim 37 , further comprising computer readable program code means for causing a computer to synchronize said taking of said plurality of checkpoints.
Claim 49
Dependent Claim
32 words
The article of manufacture of claim 37 , further comprising computer readable program code means for causing a computer to synchronize deletion of any older versions of said plurality of checkpoint files.
Claim 50
Dependent Claim
45 words
The article of manufacture of claim 37 , further comprising computer readable program code means for causing a computer to restore said plurality of processes using a consistent set of checkpoint files, wherein each checkpoint file of said consistent set has a same version number.
Claim 51
Independent Claim
71 words
A system of identifying a set of complete and consistent checkpoint files for a parallel program, said system comprising: a plurality of processes of said parallel program to select a plurality of current valid checkpoint files corresponding to said plurality of processes; and at least one computing unit adapted to use said selected plurality of current valid checkpoint files to identify a consistent set of checkpoint files for said parallel program.
Claim 52
Independent Claim
71 words
A system of identifying a set of complete and consistent checkpoint files for a parallel program, said system comprising: a plurality of processes of said parallel program to select a plurality of current valid checkpoint files corresponding to said plurality of processes; and at least one computing unit adapted to use said selected plurality of current valid checkpoint files to identify a consistent set of checkpoint files for said parallel program.
Claim 53
Independent Claim
76 words
A system of capturing a set of checkpoint files for a parallel program, said system comprising: a plurality of checkpoint files to be used during a taking of a plurality of checkpoints corresponding to a plurality of processes of said parallel program, wherein each of said plurality of checkpoint files has a name, which includes a version number; and at least one computing unit to take said plurality of checkpoints using said plurality of checkpoint files.
Claim 54
Independent Claim
76 words
A system of capturing a set of checkpoint files for a parallel program, said system comprising: a plurality of checkpoint files to be used during a taking of a plurality of checkpoints corresponding to a plurality of processes of said parallel program, wherein each of said plurality of checkpoint files has a name, which includes a version number; and at least one computing unit to take said plurality of checkpoints using said plurality of checkpoint files.
References Cited (Backward Citations)
JPS582936A
Cited
US4703481A
Cited
US5008786A
Cited
US4823261A
Cited
US5301309A
Cited
US5710929A
Cited
US5495590A
Cited
JPH05119995A
Cited
KR930009859A
Cited
JPH0652031A
Cited
JPH0713805A
Cited
US5455929A
Cited
US5590277A
Cited
JPH0869404A
Cited
US5551043A
Cited
US5634096A
Cited
US5644742A
Cited
US5659721A
Cited
US5621885A
Cited
US5630047A
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 2004-12-17 | 2005-06-18 | 2005-12-18 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2008-12-17 | 2009-06-18 | 2009-12-18 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2012-12-17 | 2013-06-18 | 2013-12-18 | $7700.00 | Window Closed / Lapsed |