WO2004031955A2 - Verfahren zur regulierung des datenzugriffs bei einem aus mehreren einzelsystemen bestehenden system auf wenigstens eine datenspeichereinrichtung - Google Patents
Verfahren zur regulierung des datenzugriffs bei einem aus mehreren einzelsystemen bestehenden system auf wenigstens eine datenspeichereinrichtung Download PDFInfo
- Publication number
- WO2004031955A2 WO2004031955A2 PCT/EP2003/010794 EP0310794W WO2004031955A2 WO 2004031955 A2 WO2004031955 A2 WO 2004031955A2 EP 0310794 W EP0310794 W EP 0310794W WO 2004031955 A2 WO2004031955 A2 WO 2004031955A2
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- area
- data storage
- storage device
- individual
- areas
- Prior art date
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F12/00—Accessing, addressing or allocating within memory systems or architectures
- G06F12/02—Addressing or allocation; Relocation
- G06F12/0223—User address space allocation, e.g. contiguous or non contiguous base addressing
- G06F12/0284—Multiple user address space allocation, e.g. using different base addresses
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F12/00—Accessing, addressing or allocating within memory systems or architectures
- G06F12/02—Addressing or allocation; Relocation
- G06F12/08—Addressing or allocation; Relocation in hierarchically structured memory systems, e.g. virtual memory systems
- G06F12/10—Address translation
Definitions
- the invention relates to a method for regulating data access in a system consisting of several individual systems to at least one data storage device, the accesses being able to overlap and overlap in terms of time and data area.
- the access and latency times as well as the maximum data rate, which limits throughput represent a major problem.
- This problem also occurs in standalone systems in the form of the so-called memory gap and is a so-called “bottleneck problem”. known for a long time.
- DSM distributed shared memories
- the invention has for its object to provide a method and devices for regulating data access, that enables the fastest possible operations while minimizing unnecessary data traffic.
- This object is achieved according to the invention in that the individual systems reserve free data or address areas of the data source and the reserved areas are then blocked for access by other individual systems, speculatively enlarged areas being reserved compared to the directly required areas.
- the invention is e.g. in connection with Distributed Shared Memories (DSM), with the NUMA architecture (Non-Uniform Memory Addressing), with SMP computers (Symmetrie MultiProcessor) or the like. It has particular advantages with distributed systems.
- DSM Distributed Shared Memories
- NUMA Non-Uniform Memory Addressing
- SMP computers Symmetrie MultiProcessor
- a data storage device and individual systems cooperating with the data storage device are provided to achieve the object.
- the data storage device receives reservation requests from the individual systems with which the individual systems want to reserve free data or address areas with the data storage device.
- Reservation means of the data storage device reserve the speculatively enlarged areas for the individual systems.
- the reservation means can also reserve the required areas. It is particularly preferred that the individual systems specify the areas they need directly using one or more address details. In this embodiment of the invention, it is therefore not only important that the data storage device reserves memory areas for the individual systems at all, which can be arranged in any storage location, but by the individual systems with address details specified memory areas. This also applies to the request for a speculatively enlarged area by a single system, whereby such a request can also be made at the same time as the request for a directly required area, the location of which is defined by the individual systems.
- the individual systems of the data storage device do not provide any information about the directly required areas, but instead request speculatively enlarged areas from the outset. This is because the speculatively enlarged area can also be understood as a superset or an upper area of a directly required storage area.
- the data storage device reserves the individual systems speculatively enlarged areas if possible, but at least the memory area directly required. However, it can happen that a smaller speculatively enlarged memory area is reserved than has been requested, or even areas that are not directly required have been reserved. Subsequent communication enables the data storage device and the respective individual system to solve this problem.
- the extension of the directly required areas can be specified by the individual systems in the respective reservation request.
- the data storage device can speculatively enlarge the directly required areas by extension areas.
- the individual systems can access both the directly required and the speculatively expanded areas without having to make another reservation request. change is required.
- Different variants are possible for the individual systems. For example, they can be databases, operating systems or the like. It is also possible for an individual system to be represented by a computer, for example a personal computer.
- the individual systems are, for example, also individual processes or modules that are operated under the management of an operating system or distributed operating system.
- the same applies in principle to the data storage device which can be, for example, a data storage module of a database, an operating system or the like.
- the data storage module manages memory of the system, which is represented, for example, by a computer.
- Reservations also called locks, always lead to a waiting time due to the communication latencies. If each time you only occupied the currently required data or address area with a lock that is currently required, there would be a waiting time each time a new lock is required.
- By reserving a speculatively enlarged area you do not need to make a time-consuming new access every time, but can use the already received speculatively enlarged area without waiting, e.g. pass it on to other individual systems as sub-tenants as soon as corresponding requirements are made. If the speculatively enlarged area is not required, it can be returned to other individual systems that need it at any time. Overall, this significantly reduces data access time.
- the procedure according to the invention causes a speculative distribution of the available data areas in advance, which are subsequently corrected by current requirements can. Various strategies can then be used to return speculatively requested or reserved areas.
- the data storage device preferably serves as a communication platform for the individual systems.
- two or more individual systems use a common area of the data storage device.
- the individual systems enter and / or read out information in such a data area.
- the precautionary speculative reservation of expansion areas then also makes it possible for the individual systems not only to read and / or change the information in the directly required area, but also to be able to change the information contained in the expansion area or areas.
- the invention is based on the knowledge that usually initially only the information contained in directly required areas is relevant for a single system. Often, a single system will later need information that is located next to the area that was originally required.
- the return of speculatively reserved areas can be at least partially released if a corresponding reservation request is made by another individual system or a data storage device.
- the data storage device can return without inquiry to a single system whose expansion area (s) are to be reduced. However, it is expedient for the data storage device to have an individual system. If possible, be informed about these measures before reducing or returning an expansion area.
- the data storage device beforehand e.g. asks for his consent to return an extension area by means of a so-called retract message.
- the individual system can then return all or just part of the extension area to be returned, e.g. agree by means of a so-called retract grant message.
- extension area is only released for a reservation request if it is requested by the requesting individual system as a directly required area.
- the extension area can also be released, in particular also completely released, when a reservation request is made by another individual system, even if it is only requested as an extension area by this other individual system.
- areas that are directly required are not released in favor of requirements for expansion areas.
- Intermediate strategies are also possible, that is, in the case of a reservation request by another individual system, the extension area is only released to a certain extent if it also only affects the extension area in this other individual system. For example, half of the requested expansion area or the expansion area reserved for the first individual system can be released.
- the individual systems forming the system are, for example, databases and / or operating systems.
- the individual systems and the at least one data storage device are expediently used by means of a buffer cache. Units decoupled from each other. Buffer modules of this type ensure that activities, for example between inputs and outputs, are decoupled and are suitable for adapting the time access behavior between slow and fast module instances.
- the release of the directly required area in the event of a reservation request from another individual system expediently depends on the urgency of the respective reservation.
- urgency priorities can be introduced so that, for example, access by a single system with very high priority can force the release of an area reserved by another single system with very low urgency.
- the reservations can relate to read access, write access or both.
- exclusive read access multiple reservations of a directly required area and / or an expansion area are possible, e.g. so-called read or shared locks, while exclusive reservations are useful for write access, so-called write or exclusive locks.
- Figure 1 is a schematic representation of a first embodiment of the invention with a system consisting of three individual systems and a data storage device.
- FIG. 2 shows a schematic illustration to explain the reservation of address areas
- FIG. 3 shows a schematic illustration of a second exemplary embodiment of the invention with a system constructed in a modular manner and consisting of two individual systems and a data storage device
- Figure 4 is a schematic representation of a reservation request
- Figure 5 is a schematic representation of a release message.
- the distributed system 9 shown in FIG. 1 consists of three individual systems 10 - 12 and 10 ', which can be databases and / or operating systems, and a data storage device 13, which can be any data source.
- the individual systems 10-12 and the data storage device 13 are connected to one another via buffer modules 14-17, which can be buffer cache units. Buffer modules of this type are used for decoupling and for adapting the time access behavior between slow and fast modules and can also be designed in the manner of individual systems according to the invention.
- the individual systems 10-12 and the data storage device 13 can also be connected to one another via other coupling elements or types of connection.
- the number of individual systems 10-12 is practically arbitrary, with several data storage devices also being provided can. Not only the individual systems 10-12 can access the data storage device 13, but also - in the case of a plurality of data storage devices 13 - such data storage devices can also access one another, for example recursively. Such data storage devices 13 can also be components of individual systems 10-12 or form such.
- the data accesses can in principle be write accesses and / or read accesses.
- an individual system 10-12 wants to access data from the data storage device 13, it requires not only the directly required address area 18 (shown with a thick line) for the action to be performed by it, but also an area 20 speculatively enlarged by extension areas 19, 19 ' on.
- the request for such a lock can usually only take effect when the corresponding areas are free.
- other individual systems can no longer easily access the reserved area, that is to say the speculatively enlarged area 20.
- the speculatively enlarged area 20 is immediately available for subsequent actions of the respective individual system 10 - 12, that is, if, for example, addresses in the extension areas 19, 19 'are required, this can be done in a time-saving manner without further lock requests.
- the individual system 10 had the area 20 speculatively enlarged by extension areas 19, 19 " 'reserved for the data storage device.
- Cell system 10 can now not only access the information b and c stored in the directly required area 18, if necessary also change it, but also the information a, d, e and f stored in the extension areas 19, 19 '.
- the individual system 10 can access the extension areas 19, 19 'without a further reservation request and read and / or modify the information a, d, e and f.
- the buffer module 14 functions in the manner of an individual system according to the invention and requests extended memory areas from the data storage device 13.
- the individual system 10 could only request directly required areas from the buffer module 14, and the buffer module 14 could manage speculatively expanded areas which it e.g. has itself requested or received from the data storage device 13 without any special request. If the individual system 10 or another individual system 10 'connected to the buffer module 14' requests further memory areas from the buffer module 14, the buffer module 14 reserves these memory areas from the extended areas if possible. A further time-consuming reservation with the data storage device 13 is generally not necessary for this.
- FIG. 2 now shows that another individual system wants to access addresses of the data storage device 13 in such a way that overlaps would result.
- a lock request from another system with a directly required area 21 (shown in thick lines) and extension areas 22 and 24 is shown, that is to say that the other individual system requests a speculatively enlarged area 23, which deals with the already reserved area.
- fourth speculatively enlarged area 20 of the first individual system overlaps.
- the first individual system releases the entire expansion area 19 '.
- the first individual system only releases the expansion area 19 'to the extent that it is overlapped by the speculatively enlarged area 22 of the second individual system.
- the first individual system only releases the extension area 19 'to the extent that it is overlapped by the directly required address area 21 of the second individual system.
- the first individual system releases the expansion area 19 'to the extent that it is overlapped by the directly required address area 21 of the second individual system, and in addition a part of the area overlapped by the expansion area 22 of the second system is released.
- the area occupied by both extension areas 19 'and 22 can be divided in half or divided according to an urgency key if the locks are assigned to different urgency levels. These urgency levels can also determine which alternatives are used.
- the address area 18 of the first individual system directly required is generally not released or returned, not even partially.
- directly required address areas 18 or 21 overlap there is generally no release or return. would be the area reserved first, although here, too, other return criteria can be introduced depending on the urgency levels of the locks, statistical analyzes of previous lock operations and / or memory accesses or other criteria.
- a scenario is described below in which the individual systems 10 and 11 communicate with one another by writing and reading information to common areas within the data storage device 13.
- the starting situation is, for example, the above scenario, in which the individual system 10 requested the enlarged area 20 from the data storage device 13.
- the individual system 10 has, for example, written the information e and f in the expansion area 19 '.
- the individual system 11 now requests the directly required area 21, which is preferably to be speculatively enlarged to the area 23, from the data storage device. It is possible for the individual system 10 to register the request for enlarging the directly required area 21 with the data storage device 13. It is also possible for the data storage device 13 to enlarge the directly required area 21 by the extension areas 22 and 24.
- the individual system 11 can read out the information f after at least the directly required area 21 has been reserved for it. This is possible, for example, if the data storage device 13 realizes the third variant explained above. If the data storage device 13 explains the second realized variant, in which it also reserves the expansion area 22 for the individual system 11, the individual system 11 can also read the information e. The part of the expansion areas 19 ′ and 22 containing the information e then forms a common area via which the individual systems 10 and 11 communicate. In any case, the data storage device 13 serves as a communication platform for the individual systems 10 and 11 in both scenarios. It goes without saying that further data and address areas of the data storage device can also serve for communication of the individual systems 10, 11 and 12.
- the data storage module manages the memory 31 of a computer 40 and at least partially makes this memory 31 available to the individual modules 41, 42, which are individual systems according to the invention.
- the modules 41 to 43 are, for example, program modules whose program code is executed by one or more processors 30 of the computer 40.
- the modules 41 to 43 are operated under the control of an operating system 32.
- the data storage module 43 may e.g. form part of the operating system 32 or a database.
- the individual modules 41, 42 are, for example, application programs.
- the computer 40 is shown very schematically and can have further means, not shown, for example input / output means, network interfaces or the like.
- the computer 40 have a monitor, loudspeaker, keyboard or the like.
- the individual modules 41, 42 reserve data and address areas in the data storage module 43. In some cases, the reserved data and address areas serve for inter-process communication of the individual modules 41, 42.
- a reservation of memory area can proceed as follows:
- communication means 45 instruct requesting means 44 to request a directly required address area 49 of a storage means 47 of the memory 31.
- the storage means 47 is, for example, RAM (Random Access Memory) and / or hard disk memory.
- the communication means 45 for example, want to write information directed to the individual module 42 into an area of the storage means 47 that can be addressed via the address area 49.
- the reservation means 44 send a reservation request 50 to the data storage module 43.
- the reservation request 50 is, for example, a function call, an interprocess message or the like and can have the name “Lock_Address” or “Get_Address”, for example.
- the reservation request 50 has the following contents, for example: An address specification 51, which defines the first address within the address area 49, for example.
- the address area 49 is preferably linear.
- Reservation request 50 also contains information 52 about the minimum length of the desired address area to be reserved, as well as information about the maximum length of the address area that begins with address information 51.
- the data 51, 52 thus define the directly required address area 49, the data 53 one or more speculatively expanded areas.
- the specification 53 can, for example, be one or more length specifications and / or contain address details.
- the information 51, 52 could also indicate the first and the last address of the area 49.
- the reservation means 44 request a larger address area from the data storage device 43 than is required directly.
- the reservation request 50 can optionally also contain an indication 54 which, for example, indicates whether writing and / or reading is planned in the address area to be reserved, whether the address area is to be initialized, for example, by writing start values or the like.
- An optional blocking information 55 of the reservation request 50 specifies whether the address area to be reserved should be blocked against write and / or read access by other individual modules.
- the reservation request 50 can also contain sender and recipient identifiers or the like.
- reservation means 46 of the data storage module 43 reserve both the directly required address area 49 and the extension address area 48, which adjoins the address area 49, for the individual module 41.
- the individual module 41 can then write information into the address areas 48, 49 , Read out information there or the like.
- the interactive accesses of the individual module 41 to the address areas 48, 49 are shown schematically by an arrow 70 in the drawing.
- the data storage module 43 confirms to the individual module 41 that the address area 48, 49 has been reserved for the individual module 41.
- the confirmation message 65 contains, for example, an address 66 and a length 67 which indicate the start and the length of the actually reserved area, which in the present case comprises the address areas 48, 49. In principle, a smaller area could also have been reserved, for example, only the directly required address area 49. 65 can also contain further information, not shown, for example in analogy to the reservation request 50.
- the release message 60 contains, for example an address 61 which in the present case corresponds to address 51.
- the address information 61 could also be another address within the ranges 48, 49.
- the address 61 defines the location of the data or address area to be released.
- the address information 61 contains, for example, the first address to be released.
- the release message also contains a length specification of the area to be released, for example the total length of the address areas 48, 49. It is also possible for the release message 60 to release only part of the address area 48, 49.
- the release message 60 can also contain sender and recipient identifiers.
- the individual module 42 can then reserve the address areas 48 and / or 49 or a part thereof by means of a reservation request 50 ′ and read and / or modify information stored there by the individual module 41.
- the individual module 42 releases the reserved memory areas.
- the data storage module 43 can carry out the variants 1 to 4 explained in connection with FIG. 2 in the event of competing reservation requests for the individual modules 41, 42 or other individual modules (not shown).
- the reservation means 46 can, in the case of reservation requests, the address ranges which have already been reserved elsewhere. Before they concern, also send a request for reclamation (eg with the name ⁇ Notify_Lock "or ⁇ Retract_Address n ) to a single system for which an address area is already reserved if part of this address area is to be reserved for another single system
- the address area is preferably an extension area, but it can also be a directly required area.
- the individual system can then agree to return the reserved area in whole or in part. For example, a speculatively expanded area is released in full, in half or in another fraction.
- the confirmation of Address area release can be sent to the data storage device and / or to the individual system competing for the address area.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Memory System Of A Hierarchy Structure (AREA)
Abstract
Description
Claims
Priority Applications (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
AU2003270288A AU2003270288A1 (en) | 2002-09-30 | 2003-09-29 | Method for regulating access to data in at least one data storage device in a system consisting of several individual systems |
DE10393434T DE10393434D2 (de) | 2002-09-30 | 2003-09-29 | Verfahren zur Regulierung des Datenzugriffs bei einemaus mehreren Einzelsystemen bestehenden System auf wenigstens eine Datenspeichereinrichtung |
US10/529,435 US20060168413A1 (en) | 2002-09-30 | 2003-09-29 | Method for regulating access to data in at least one data storage device in a system consisting of several individual systems |
Applications Claiming Priority (4)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
DE10246369A DE10246369A1 (de) | 2002-09-30 | 2002-09-30 | Verfahren zur Regelung des Datenzugriffs auf Daten wenigstens einer Datenspeichereinrichtung |
DE2002146367 DE10246367A1 (de) | 2002-09-30 | 2002-09-30 | Verfahren zur Regulierung des Datenzugriffs bei einem aus mehreren Einzelsystemen bestehenden System auf wenigstens eine Datenspeichereinrichtung |
DE10246367.0 | 2002-09-30 | ||
DE10246369.7 | 2002-09-30 |
Publications (2)
Publication Number | Publication Date |
---|---|
WO2004031955A2 true WO2004031955A2 (de) | 2004-04-15 |
WO2004031955A3 WO2004031955A3 (de) | 2004-10-14 |
Family
ID=32070712
Family Applications (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/EP2003/010792 WO2004031954A2 (de) | 2002-09-30 | 2003-09-29 | Verfahren und vorrichtungen zum zugriff eines einzelsystems auf einen speicherbereich einer datenspeichereinrichtung |
PCT/EP2003/010794 WO2004031955A2 (de) | 2002-09-30 | 2003-09-29 | Verfahren zur regulierung des datenzugriffs bei einem aus mehreren einzelsystemen bestehenden system auf wenigstens eine datenspeichereinrichtung |
Family Applications Before (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/EP2003/010792 WO2004031954A2 (de) | 2002-09-30 | 2003-09-29 | Verfahren und vorrichtungen zum zugriff eines einzelsystems auf einen speicherbereich einer datenspeichereinrichtung |
Country Status (4)
Country | Link |
---|---|
US (1) | US20060168413A1 (de) |
AU (1) | AU2003270288A1 (de) |
DE (1) | DE10393434D2 (de) |
WO (2) | WO2004031954A2 (de) |
Families Citing this family (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8103642B2 (en) * | 2006-02-03 | 2012-01-24 | Oracle International Corporation | Adaptive region locking |
US7786903B2 (en) | 2008-10-06 | 2010-08-31 | Donald Martin Monro | Combinatorial coding/decoding with specified occurrences for electrical computers and digital data processing systems |
US7786907B2 (en) | 2008-10-06 | 2010-08-31 | Donald Martin Monro | Combinatorial coding/decoding with specified occurrences for electrical computers and digital data processing systems |
US7864086B2 (en) | 2008-10-06 | 2011-01-04 | Donald Martin Monro | Mode switched adaptive combinatorial coding/decoding for electrical computers and digital data processing systems |
US7791513B2 (en) | 2008-10-06 | 2010-09-07 | Donald Martin Monro | Adaptive combinatorial coding/decoding with specified occurrences for electrical computers and digital data processing systems |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP0817044A2 (de) * | 1996-06-28 | 1998-01-07 | Sun Microsystems, Inc. | Speicherzuordnung in einer Mehrfachfädenumgebung |
EP0817041A2 (de) * | 1996-07-01 | 1998-01-07 | Sun Microsystems, Inc. | Methode zum Reservieren von Betriebsmitteln |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE69428881T2 (de) * | 1994-01-12 | 2002-07-18 | Sun Microsystems Inc | Logisch adressierbarer physikalischer Speicher für ein Rechnersystem mit virtuellem Speicher, das mehrere Seitengrössen unterstützt |
-
2003
- 2003-09-29 AU AU2003270288A patent/AU2003270288A1/en not_active Abandoned
- 2003-09-29 WO PCT/EP2003/010792 patent/WO2004031954A2/de not_active Application Discontinuation
- 2003-09-29 WO PCT/EP2003/010794 patent/WO2004031955A2/de not_active Application Discontinuation
- 2003-09-29 US US10/529,435 patent/US20060168413A1/en not_active Abandoned
- 2003-09-29 DE DE10393434T patent/DE10393434D2/de not_active Withdrawn - After Issue
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP0817044A2 (de) * | 1996-06-28 | 1998-01-07 | Sun Microsystems, Inc. | Speicherzuordnung in einer Mehrfachfädenumgebung |
EP0817041A2 (de) * | 1996-07-01 | 1998-01-07 | Sun Microsystems, Inc. | Methode zum Reservieren von Betriebsmitteln |
Non-Patent Citations (1)
Title |
---|
POUL-HENNING KAMP: " Malloc(3) in modern Virtual Memory environments." 4.4BSD DOCUMENTATION, [Online] 5. April 1996 (1996-04-05), Seiten 1-7, XP002283869 Gefunden im Internet: <URL:http://docs.freebsd.org/44doc/papers/malloc.pdf> [gefunden am 2004-06-08] * |
Also Published As
Publication number | Publication date |
---|---|
US20060168413A1 (en) | 2006-07-27 |
DE10393434D2 (de) | 2005-10-06 |
AU2003270288A1 (en) | 2004-04-23 |
WO2004031954A2 (de) | 2004-04-15 |
AU2003270288A8 (en) | 2004-04-23 |
WO2004031954A3 (de) | 2004-08-19 |
WO2004031955A3 (de) | 2004-10-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
EP0762274B1 (de) | Einrichtung und Verfahren zur Echtzeit-Verarbeitung einer Mehrzahl von Tasks | |
DE69822541T2 (de) | Verfahren zum Verwalten eines geteilten Speichers | |
DE69819686T2 (de) | Objekt und verfahren zum bereitstellen eines effizienten mehrbenutzerzugriff auf verteilten betriebssystemkernkode durch instanzierung | |
DE69834739T2 (de) | Ausgleichen von daten die zwischen verschiedenen leitern fliessen die auf unterschiedlichen frequenzen operieren | |
DE3621321A1 (de) | Cache-speicher- bzw. multiprozessor-system und betriebsverfahren | |
DE10219623A1 (de) | System und Verfahren zur Speicherentscheidung unter Verwendung von mehreren Warteschlangen | |
DE69936257T2 (de) | Erzeugen und uberprüfen von referenz-adresszeigern | |
EP1731999B1 (de) | Mechanismus zum dynamischen Registrieren von Dateien in einer stapelverarbeitungsorientierten Umgebung | |
DE4207158A1 (de) | Speicher-zugriffssteuerung | |
DE3046912C2 (de) | Schaltungsanordnung zum selektiven Löschen von Cachespeichern in einer Multiprozessor-Datenverarbeitungsanlage | |
DE2641722A1 (de) | Hierarchisch geordnetes speichersystem fuer eine datenverarbeitende anlage mit virtueller adressierung | |
DE112010005609T5 (de) | Speichern von Daten in einem einer Mehrzahl von Puffern in einer Speichersteuerung | |
DE69726795T2 (de) | Kodierungsverfahren des Verzeichnisstatus in einem gemeinsamen, verteilten Speichersystem mit koherenten Pufferspeichern | |
DE60009817T2 (de) | Gemeinsamen Speicher verteilende Multiprozessorvorrichtung | |
DE602004008712T2 (de) | Speicherbandbreiten-Steuereinrichtung | |
WO2004031955A2 (de) | Verfahren zur regulierung des datenzugriffs bei einem aus mehreren einzelsystemen bestehenden system auf wenigstens eine datenspeichereinrichtung | |
EP2283402B1 (de) | Verfahren zum steuern eines zugriffs auf bereiche eines speichers aus mehreren prozessen heraus und kommunikations-modul mit einem nachrichten-speicher zur realisierung des verfahrens | |
DE2507405A1 (de) | Verfahren und anordnung zum synchronisieren der tasks in peripheriegeraeten in einer datenverarbeitungsanlage | |
EP0970426B1 (de) | Abhängigkeitssteuerung für überlappende speicherzugriffe | |
EP0556430B1 (de) | Verfahren zur Steuerung eines Peripheriesystems | |
DE102009061066A1 (de) | Kommunikationsmedium für ein Mehrprozessor-Computersystem | |
DE102022003674A1 (de) | Verfahren zum statischen Allozieren von lnformationen zu Speicherbereichen, informationstechnisches System und Fahrzeug | |
DE102019118757B4 (de) | Verfahren zur Herstellung der Cachekohärenz in Mehrkernprozessoren | |
EP0651897B1 (de) | Verfahren zur dynamischen verwaltung eines freien speichers einer rechenanlage, des freispeichers, für den eine unterteilung in wenigstens zwei logische speicherbereiche, die sich in ihren zugriffseigenschaften unterscheiden, vorgesehen ist | |
DE102022214054A1 (de) | Verfahren zum Betrieb eines Datenverarbeitungssystems |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AK | Designated states |
Kind code of ref document: A2 Designated state(s): AE AG AL AM AT AU AZ BA BB BG BR BY BZ CA CH CN CO CR CU CZ DE DK DM DZ EC EE ES FI GB GD GE GH GM HR HU ID IL IN IS JP KE KG KP KR KZ LC LK LR LS LT LU LV MA MD MG MK MN MW MX MZ NI NO NZ OM PG PH PL PT RO RU SC SD SE SG SK SL SY TJ TM TN TR TT TZ UA UG US UZ VC VN YU ZA ZM ZW |
|
AL | Designated countries for regional patents |
Kind code of ref document: A2 Designated state(s): GH GM KE LS MW MZ SD SL SZ TZ UG ZM ZW AM AZ BY KG KZ MD RU TJ TM AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HU IE IT LU MC NL PT RO SE SI SK TR BF BJ CF CG CI CM GA GN GQ GW ML MR NE SN TD TG |
|
121 | Ep: the epo has been informed by wipo that ep was designated in this application | ||
ENP | Entry into the national phase |
Ref document number: 2006168413 Country of ref document: US Kind code of ref document: A1 |
|
WWE | Wipo information: entry into national phase |
Ref document number: 10529435 Country of ref document: US |
|
REF | Corresponds to |
Ref document number: 10393434 Country of ref document: DE Date of ref document: 20051006 Kind code of ref document: P |
|
WWE | Wipo information: entry into national phase |
Ref document number: 10393434 Country of ref document: DE |
|
122 | Ep: pct application non-entry in european phase | ||
WWP | Wipo information: published in national office |
Ref document number: 10529435 Country of ref document: US |
|
NENP | Non-entry into the national phase |
Ref country code: JP |
|
WWW | Wipo information: withdrawn in national office |
Ref document number: JP |