Information
-
Patent Application
-
20030140069
-
Publication Number
20030140069
-
Date Filed
January 23, 200222 years ago
-
Date Published
July 24, 200321 years ago
-
Inventors
-
Original Assignees
-
CPC
-
US Classifications
-
International Classifications
Abstract
A method for using ancillary processors and memory to speed critical data capture, comprising: building a list of memory address ranges associated with a second partition, where the memory address ranges are located in central storage memory and contain the data to be captured; reading the data from the memory address ranges; and writing the data to a portion of memory reserved by a first partition as a capture pool, where the capture pool is also located in central storage memory and the capture pool is not accessible by said secondary partition. A system for implementing the method is also disclosed.
Description
FIELD OF THE INVENTION
[0001] This invention relates to data exchange and more specifically to the use of ancillary processors and storage to speed time critical data capture.
BACKGROUND OF THE INVENTION
[0002] Computer systems are a vital part of almost every business. As a result, the preservation of data and the maintaining of data integrity is critical. Moreover, inaccessibility to computer systems due to system failure, system maintenance, or system delays can result in economic losses to those parties involved in transactions requiring the use of the computer systems.
[0003] Certain operations, such as the capture of diagnostic and error information or the recording of transaction logs, cause other operations to be suspended or delayed. The problem is worsened where the speed of outboard storage devices fail to match the speed of internal storage devices and processors.
[0004] In addition, critical data is at a risk of loss if the capture of such data is not completed prior to an event that precludes data capture. This is exemplified where a system fails or “crashes” prior to the completion of a critical data capture. The chance of such a loss is further heightened where critical data capture is directed to slower outboard storage devices.
[0005] The present invention provides for the use of ancillary storage and processors to speed time critical data capture.
SUMMARY OF THE INVENTION
[0006] A method for using ancillary processors and memory to speed critical data capture, comprising: building a list of memory address ranges associated with a second partition, where the memory address ranges are located in central storage memory and contain the data to be captured; reading the data from the memory address ranges; and writing the data to a portion of memory reserved by a first partition as a capture pool, where the capture pool is also located in central storage memory and the capture pool is not accessible by said secondary partition. A system for implementing the method is also disclosed.
BRIEF DESCRIPTION OF THE DRAWINGS
[0007]
FIG. 1 shows the main elements of a computer capable of being enabled for logical partitioning.
[0008]
FIG. 2 shows a computer system logically partitioned into a primary partition and two secondary partitions.
[0009]
FIG. 3 is a flow chart of a method for using ancillary storage and processors to speed time critical data capture.
DETAILED EMBODIMENT
[0010] Logical partitioning (“LPAR”), first studied by IBM as early as 1976, allows a computer system to be split into multiple independent systems capable of simultaneously running applications in multiple, independent environments. For example, LPAR makes it possible for a user to run a single application using different sets of data on separate partitions, as if it was running independently on separate physical systems. While earlier implementations of LPAR were limited to physical partitioning, later implementations allow partitions to share resources. Thus, LPAR also makes it possible for a user to run multiple applications on separate partitions using the same set of data stored in shared resources.
[0011] LPAR can be used to minimize financial costs and system management requirements. For example, in a production software—test software environment, LPAR would allow production and test systems to be an be located in the same physical hardware. Upon validation of changes to test system applications and the duplication of the changes to the production system applications, resources used by the test system are reallocated to the production system. Without LPAR, separate physical systems would be required for the test system and for the production system. Thus, at least two physical systems would have to be purchased, installed, and maintained. More over, once application changes were completed the test system would no longer be utilized.
[0012] A system enabled for LPAR generally includes of a computer including resources such as processors, central storage memory, and input/output processors. The physical system is then divided into logical systems, known as partitions. A primary partition (“service processor”) owns and manages physical system resources and provides management functions to logical partitions. In addition, the primary partition can function as a hub for external communications.
[0013] Secondary partitions are created and managed by the service processor, but function as independent systems within the entire partitioned system. They may be assigned their own resources including processors, central storage memory, system buses, system values, time-of-day, operating systems, applications, files and user profiles.
[0014]
FIG. 1 shows a conceptual overview of the main elements of an IBM system 390 (“s/390”) computer. Although this preferred embodiment describes the s/390, it is understood to one of ordinary skill in the art that any computer system capable of being enabled for logical partitioning may be used. The s/390 may be configured with one or more processors (“CPUs”) 5, 7, 9, 11, 13, 15, central storage memory 3, and input/output processors 17, 19, 20 (“IOP”). Central storage memory is analogous to random access memory (“RAM”) commonly found in personal computers. An IOP is a piece of hardware that allows devices such as disk drives, tape drives, and communication devices to be attached to the computer system. It is understood that a computer system used with the present invention may be configured with any number of CPUs, IOPs, and central storage memories. Read/write operations to and from central storage memory is generally much faster than similar operations to and from outboard storage memory via IOPs, and thus the capture of data to central storage memory is used for the preferred embodiment of this invention.
[0015]
FIG. 2 shows the main elements of an s/390 configured for LPAR operation. The s/390 of FIG. 2 has been defined to have three partitions including a primary partition including service processor 51 and two secondary partitions 53, 55. A first secondary partition 53 has been assigned three CPUs 57, 59, 61, one IOP 73, and a portion of central storage memory 79. A second secondary partition 55 has been assigned two CPUs 65, 67, one IOP 77 and a portion of central storage memory 81. The service processor 51 has reserved a portion of central storage memory 69 as a capture pool for storing captured data. In the preferred embodiment, the capture pool is not accessible by secondary partitions. However, in an alternative embodiment secondary partitions could access the capture pool as necessary. One CPU 63, an IOP 75, and a portion of central memory 71 have not been assigned to either secondary partition 53, 55 and have not been reserved by the primary partition 51 for other uses. It is understood that the number and type of resources assigned to secondary partitions or reserved for use by the primary partition may be varied without exceeding the scope of the present invention.
[0016] Partitions may communicate in a manner similar to that of separate physical systems. For example, if two partitions are each assigned an Ethernet or token ring adapter, the two partitions may carry on network communications as if they were separate physical systems. However, in order to take advantage of the speed potential inherent in intra-system communications, partitions may also utilize alternative communication mechanisms. For example, IBM AS/400 partitions may communicate via virtual Opticonnect/400. Virtual Opticonnect/400 is a software-only adaptation of Opticonnect/400. Opticonnect/400 is a combination of hardware and software that allows physically separate AS/400 computers systems to communicate via high speed fiber optic links. Virtual Opticonnect/400 allows partitions to communicate via high speed fiber optic links. It is understood that the present invention allows for the utilization of any inter-partition communications mechanism known to one of ordinary skill in the art.
[0017] In addition to inter-partition communications, partitions may exchange data by reading and writing to commonly accessible storage memory. For example, where a first and second partition both have access to storage memory, both partitions may read and write data to that storage memory. This method of data exchange is highly efficient because it occurs at the speed at which the partitions read and write to the storage memory. In particular, where the storage memory is central storage memory, the exchange of data takes place at speeds faster than could be achieved through inter-partition communications or where the storage memory is outboard storage memory.
[0018] In one embodiment, the system provides for the suspension of a partition while the service processor captures data in accordance with a request by the partition. FIG. 3 is a flowchart of processing performed to capture data from a partition. The service processor reserves a portion of central storage memory to be used as a capture pool for storing captured data.
[0019] When a partition determines that the capture of critical data is necessary, the partition generates and issues a service call to the service processor requesting a data capture. The service call includes a list of memory address ranges containing data to be captured by the service processor as shown at step 103. The service processor receives the request for the data capture along with the accompanying memory address ranges at 105. The request for a data capture can be made using any conventional inter-partition communication mechanism. Moreover, in an alternative embodiment, the request for a data capture could be made without using an inter-partition communication method by defining an address within central storage memory and accessible by a secondary partition that the service processor would regularly poll for a “capture data” indicator. In such an embodiment, the defined memory location could also contain the memory address ranges of data to be captured.
[0020] The service processor suspends the execution of the requesting partition at 106. The service processor captures the requested data by reading said data directly from the portion of central storage memory assigned to the requesting partition and writing said data directly to the service processor's capture pool, which is also located in the central storage memory, at 107. Such a data capture, may be completed quickly and efficiently as it requires no inter-partition communication. Upon completion of the data capture, the service processor restarts execution of the requesting partition at 109. In an alternative embodiment, the service processor could also notify the requesting partition of the completion of the data capture as shown at 111.
[0021] In another embodiment, the service processor would not suspend or restart execution of the requesting partition as shown at step 106 and 109. Such an embodiment would be advantageous under many circumstances including those where the requesting partition must remain engaged in critical operations.
[0022] The requesting partition may request information regarding the captured data from the service processor at 113. If such a request is made, the service processor provides such information to the requesting partition at 115. Whether to make such a request could depend upon the purpose of the data capture.
[0023] In addition, the requesting partition may request that all or a portion of the data captured be copied back to the memory address ranges the data was originally captured from at 117. In response to such a copy-back request, the service processor would read captured data from the capture pool and write captured data to the memory address ranges it was originally captured from at 119. In an alternative embodiment, the copy back could be automated such that no copy back request (step 117) is needed. In such an embodiment, the automated copy back could occur for every data capture or could occur selectively based upon pre-determined criteria.
[0024] One aspect of an embodiment of the invention is that the capture of critical data is accelerated because the captured data is read from and written to central storage memory. As a result, data capture is more likely to be completed prior to an event that would preclude data capture.
[0025] Another aspect of an embodiment of the invention is that the time required for the capture of critical data, where execution of the requesting partition is suspended during data capture, is minimized. Thus, execution of the requesting partition is resumed earlier than would otherwise be possible. As a result, the requesting partition remains online and available for operations for periods exceeding what would be possible on a similar system not fitted with the present invention.
[0026] Another aspect of an embodiment of the invention is that delays to a requesting partition's non-data-capture operations, which are the result of the partition's participation in critical data capture operations, are minimized due to the shortened duration of the critical data capture.
[0027] The description applying the above embodiments is merely illustrative. As described above, embodiments in the form of computer-implemented processes and apparatuses for practicing those processes may be included. Also included may be embodiments in the form of computer program code containing instructions embodied in tangible media, such as floppy diskettes, CD-ROMs, hard drives, or any other computer-readable storage medium, wherein, when the computer program code is loaded into and executed by a computer, the computer becomes an apparatus for practicing the invention. Also included may be embodiments in the form of computer program code, for example, whether stored in a storage medium, loaded into and/or executed by a computer, or as a data signal transmitted, whether a modulated carrier wave or not, over some transmission medium, such as over electrical wiring or cabling, through fiber optics, or via electromagnetic radiation, wherein, when the computer program code is loaded into and executed by a computer, the computer becomes an apparatus for practicing the invention. When implemented on a general-purpose microprocessor, the computer program code segments configure the microprocessor to create specific logic circuits.
[0028] While the invention has been described with reference to exemplary embodiments, it will be understood by those skilled in the art that various changes may be made and equivalents may be substituted for elements thereof without departing from the scope of the invention. In addition, many modifications may be made to adapt a particular situation or material to the teachings of the invention without departing from the essential scope thereof. Therefore, it is intended that the invention not be limited to the particular embodiments disclosed for carrying out this invention, but that the invention will include all embodiments falling within the scope of the appended claims.
Claims
- 1. A system for using ancillary processors and storage to speed critical data capture, comprising:
a computer; at least two processors associated with said computer; a central storage memory associated with said computer; a first partition; at least one second partition; a portion of said central storage memory reserved by said first partition as a capture pool, said capture pool not being accessible by said secondary partition; computer program code for building a list of memory address ranges associated with said second partition containing data to be captured; computer program code for enabling said first partition to read said data defined by said list from said memory address ranges; and computer program code for enabling said first partition to write said read data to said capture pool.
- 2. The system of claim 1 further comprising computer program code enabling said first partition to receive a request for a data capture from said second partition, said request including a list of memory address ranges associated with said second partition, said memory address ranges containing data to be captured.
- 3. The system of claim 1 further comprising computer program code enabling said first partition to suspend execution of said second partition upon receipt of said request for a data capture and enabling said first partition to resume execution of said second partition upon completion of said data capture.
- 4. The system of claim 1 further comprising computer program code for enabling said first partition to copy at least a portion of said captured data to said memory address ranges.
- 5. The system of claim 4 further comprising computer program code for enabling said first partition to receive a request for copying at least a portion of said captured data to said memory address ranges.
- 6. The system of claim 1 further comprising computer program code for enabling said first partition to provide information regarding said data capture to said second partition.
- 7. The system of claim 6 further comprising computer program code for enabling said first partition to receive a request for providing said information regarding said data capture to said second partition.
- 8. A method for using ancillary processors and memory to speed critical data capture, comprising:
building a list of memory address ranges associated with a second partition, said memory address ranges containing data to be captured, said memory addresses being located in central storage memory; reading said data located at said memory address ranges; and writing said read data to a portion of memory reserved by a first partition as a capture pool, said capture pool being located in central storage memory, said capture pool not being accessible by said secondary partition.
- 9. The method of claim 8 further comprising said first partition receiving a request for a data capture from said second partition, said request including a list of memory address ranges associated with said second partition, said memory address ranges containing data to be captured.
- 10. The method of claim 8 further comprising said first partition suspending execution of said second partition upon receipt of said request for a data capture and said first partition resuming execution of said second partition upon completion of said data capture.
- 11. The method of claim 8 further comprising said first partition copying at least a portion of said captured data to said memory address ranges.
- 12. The method of claim 11 further comprising said first partition receiving a request for copying at least a portion of said captured data to said memory address ranges.
- 13. The method of claim 8 further comprising said first partition providing information regarding said data capture to said second partition.
- 14. The system of claim 13 further comprising said first partition receiving a request for providing said information regarding said data capture to said second partition.
- 15. An article of manufacture comprising:
a computer useable medium having computer readable program code embodied therein for using ancillary processors and memory to speed critical data capture, the computer readable program in said article of manufacture comprising:
computer readable program code for building a list of memory address ranges associated with a second partition containing data to be captured, said memory addresses being located in central storage memory; computer readable program code for enabling a first partition to read said data defined by said list from said memory address ranges; and computer readable program code for enabling said first partition to write said read data to said capture pool, said capture pool being located in central storage memory, said capture pool not being accessible by said secondary partition.
- 16. The article of manufacture of claim 15 further comprising computer readable program code enabling said first partition to receive a request for a data capture from said second partition, said request including a list of memory address ranges associated with said second partition, said memory address ranges containing data to be captured.
- 17. The article of manufacture of claim 15 further comprising computer readable program code enabling said first partition to suspend execution of said second partition upon receipt of said request for a data capture and enabling said first partition to resume execution of said second partition upon completion of said data capture.
- 18. The article of manufacture of claim 15 further comprising computer readable program code for enabling said first partition to copy at least a portion of said captured data to said memory address ranges.
- 19. The article of manufacture of claim 18 further comprising computer readable program code for enabling said first partition to receive a request for copying at least a portion of said captured data to said memory address ranges.
- 20. The article of manufacture of claim 15 further comprising computer readable program code for enabling said first partition to provide information regarding said data capture to said second partition.
- 21. The article of manufacture of claim 20 further comprising computer readable program code for enabling said first partition to receive a request for providing said information regarding said data capture to said second partition.