CN102508738A - Backup method of service information of multi-core processor, inner core and backup inner core - Google Patents

Backup method of service information of multi-core processor, inner core and backup inner core Download PDF

Info

Publication number
CN102508738A
CN102508738A CN201110312607XA CN201110312607A CN102508738A CN 102508738 A CN102508738 A CN 102508738A CN 201110312607X A CN201110312607X A CN 201110312607XA CN 201110312607 A CN201110312607 A CN 201110312607A CN 102508738 A CN102508738 A CN 102508738A
Authority
CN
China
Prior art keywords
kernel
service information
backup
kernels
core
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN201110312607XA
Other languages
Chinese (zh)
Other versions
CN102508738B (en
Inventor
安宏杰
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Huawei Digital Technologies Chengdu Co Ltd
Original Assignee
Huawei Digital Technologies Chengdu Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Huawei Digital Technologies Chengdu Co Ltd filed Critical Huawei Digital Technologies Chengdu Co Ltd
Priority to CN201110312607.XA priority Critical patent/CN102508738B/en
Publication of CN102508738A publication Critical patent/CN102508738A/en
Application granted granted Critical
Publication of CN102508738B publication Critical patent/CN102508738B/en
Expired - Fee Related legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Landscapes

  • Hardware Redundancy (AREA)

Abstract

The invention provides a backup method of service information of a multi-core processor, an inner core and a backup inner core and relates to the technical field of computer application. According to the embodiment of the invention, firstly, a preset inner core receives service information of other inner cores and sends the service information to a backup inner core corresponding to the preset inner core, and then, the backup inner core corresponding to the preset inner core sends the received service information of the other inner cores to backup inner cores corresponding to the other inner cores; or, firstly, the inner core stores the self service information to a shared memory, and then, the preset backup inner core reads the service information of the shared memory and sends the read service information of the inner core to the backup inner core corresponding to the inner core. The method provided by the invention can be used for realizing the service information backup of the inner core and simultaneously ensuring the sequence of the backup service information, thus the problem that inconsistent service information between the charged backup inner cores leads to errors in the service processing can be solved, thus the high availability of the system can be improved.

Description

Backup method, kernel and backup kernel of multi-core processor service information
Technical Field
The invention relates to the technical field of computer application, in particular to a backup method, a kernel and a backup kernel for multi-core processor service information.
Background
A multi-core processor refers to a processor that integrates two or more complete computational cores, and by dividing tasks among two or more computational cores, the multi-core processor can execute more tasks in a specific clock cycle, and each computational core can run at a lower speed without increasing heat.
At present, in order to realize high availability of a multi-core processor, a master-slave mode or a service sharing mode is generally adopted to back up service information of the multi-core processor. When the service information is backed up, the kernel needs to send the service information of the kernel to a corresponding backup kernel, but when at least two kernels need to be backed up and the sequence of the service information exists between the kernels, for example, the two kernels are respectively kernel 1 and kernel 2, the service of the kernel 1 can be realized based on the service of the kernel 2, the backup kernel of the kernel 1 is kernel 3, and the backup kernel of the kernel 2 is kernel 4, because the service backups are mutually independent, if the service of the kernel 1 is backed up to the kernel 3, but the service of the kernel 2 is not completely backed up to the kernel 4, and at the moment, when the kernel 3 and the kernel 4 take over the service of the kernel 1 and the kernel 2 respectively, because the service information between the kernel 4 and the kernel 3 is not completely corresponding, an error occurs when the kernel 3 and the kernel 4 process the service.
Disclosure of Invention
The embodiment of the invention provides a backup method, an inner core and a backup inner core of multi-core processor service information, which solves the problem that when the sequence of the service information exists among the prior inner cores, the service backup operation of the backup inner cores of all the takeover services is mutually independent, so that the service information backed up among the backup inner cores cannot be completely consistent, and the backup inner cores are wrong when processing the service.
The embodiment of the invention provides a backup method of service information of a multi-core processor, which comprises the following steps:
the preset kernel receives the service information of other kernels and sends the service information to a backup kernel corresponding to the preset kernel; the backup kernel corresponding to the preset kernel sends the received service information of other kernels to the backup kernels corresponding to the other kernels; or,
the kernel stores the service information of the kernel to a shared memory, the preset backup kernel reads the service information of the shared memory, and the read service information of the kernel is sent to the backup kernel corresponding to the kernel.
An embodiment of the present invention provides an inner core, including:
the receiving unit is used for receiving the service information of other kernels;
and the sending unit is used for sending the service information of the other kernels received by the receiving unit to the corresponding backup kernels.
The embodiment of the invention provides a backup kernel, which is characterized by comprising the following steps:
the receiving and reading module is used for receiving the service information of other kernels sent by the corresponding kernel needing to be backed up; or, the method is used for reading the service information of the kernel stored in the shared memory;
the sending module is used for sending the service information of other kernels received by the receiving and reading module to the backup kernels corresponding to the other kernels; or, the core processing module is configured to send the service information of the core read by the receiving and reading module to the backup core corresponding to the core.
The technical scheme provided by the embodiment of the invention can be seen that the sequence of the backed-up service information is ensured while the kernel service information is backed-up, and the problem that errors occur when the service is processed due to inconsistency of the service information between the taken-over backup kernels is avoided, so that the high availability of the system is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive labor.
Fig. 1 is a flowchart of a method for backing up service information of a multi-core processor according to an embodiment of the present invention;
fig. 2 is a schematic flowchart of a method for backing up service information of a multi-core processor according to another embodiment of the present invention;
fig. 3 is a schematic structural diagram of a multi-core processor according to an embodiment of the present invention;
FIG. 4 is a schematic structural diagram of yet another multi-core processor according to an embodiment of the present invention;
FIG. 5 is a schematic structural diagram of a kernel according to an embodiment of the present invention;
fig. 6 is a schematic structural diagram of a backup kernel according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The service information of the multi-core processor comprises internal control information and external data information, all the cores mentioned in the embodiment of the invention can be positioned in the same multi-core processor, and the service information is transmitted between the cores through a data bus among the cores or a shared memory; all the cores can also be positioned in different multi-core processors, and service information is transmitted among the cores through a data bus or a shared memory among the multi-core processors; all cores may also be located on different circuit boards, with the cores passing traffic information between them via data buses between the circuit boards.
An embodiment of the present invention provides a method for backing up service information of a multi-core processor, where the multi-core processor includes multiple cores, and as shown in fig. 1, the method includes:
11. and the preset kernel receives the service information of other kernels and sends the service information to the backup kernel corresponding to the preset kernel.
Specifically, for example, the preset kernel is kernel 1, the other kernels are kernel 2 and kernel 3, the backup kernel of kernel 1 is kernel 4, the backup kernels of kernel 2 and kernel 3 are kernel 5 and kernel 6, respectively, and kernel 1 receives the service information of kernel 2 and kernel 3 and sends the service information to kernel 4.
Optionally, the preset kernel may further send its own service information to a backup kernel corresponding to the preset kernel.
12. And the backup kernel corresponding to the preset kernel sends the received service information of the other kernels to the backup kernels corresponding to the other kernels.
Specifically, for example, the core 4 receives the service information of the core 2 and the core 3, the core 4 sends the service information of the core 2 to the core 5, and sends the service information of the core 3 to the core 6.
Further, for example, if the service information of the core 2 is based on the service information of the core 3, since all the service information of the cores that need to be backed up can only be backed up through the core 1 and the core 4, the service information generated first must be backed up through the core 1 and the core 4, and therefore the service information generated by the core 3 is prior to the corresponding service information generated by the core 2, the service information generated by the core 3 must be backed up to the core 6 through the core 1 and the core 4, thereby avoiding the situation that the corresponding service information generated by the core 2 is backed up first, and the service information generated by the core 3 is not backed up yet, and ensuring the requirement of the sequence of the backed-up service information between the cores.
In the method, a preset kernel can receive the service information transmitted to other kernels from the outside simultaneously with other kernels, and the preset kernel transmits the received service information transmitted to other kernels from the outside to a backup kernel corresponding to the preset kernel; and the backup kernel corresponding to the preset kernel transmits the received service information which is externally transmitted to other kernels to the backup kernel corresponding to the other kernels. For example, if the service information is transmitted from the outside to the core 2, the preset core 1 and the preset core 2 simultaneously receive the service information transmitted from the outside to the core 2, the core 2 sends the received service information transmitted from the outside to the core 2 to the core 4 (the backup core corresponding to the core 1), and the core 4 sends the service information transmitted from the outside to the core 2 to the core 5 (the backup core corresponding to the core 2). Therefore, the step that the kernel 2 retransmits the externally transmitted service data to the kernel 1 is omitted, and the backup time of the service information is shortened.
An embodiment of the present invention provides another method for backing up service information of a multi-core processor, as shown in fig. 2, including:
21. and the kernel stores the service information of the kernel to a shared memory.
Specifically, the kernel applies for a corresponding storage space from the shared memory according to the size of its own service information, and stores its own service information into the applied storage space by using the identity information of the backup kernel corresponding to the kernel as an identifier of the applied storage space. For example, the backup kernel of the kernel 1 is the kernel 4, the backup kernel of the kernel 2 is the kernel 5, and the size of the service information of the kernel 1 is 15k, the kernel 1 applies a storage space larger than or equal to 15k to the shared memory, stores the service information of 15k into the storage space, and uses the identity information of the kernel 4 as an identifier of the storage space, where the identity information of the kernel 4 may be its own number 4 or other information for distinguishing the kernel from other kernels. Optionally, if the shared memory is a shared buffer queue, the memory spaces applied by the cores are sequentially allocated from the high order to the low order.
Optionally, the identifier of the storage space applied by the kernel may also be the identity information of the kernel itself, and when the preset backup kernel reads the identifier of the storage space, the service information in the storage space is sent to the corresponding backup kernel according to the identity information of the kernel.
22. And reading the service information of the shared memory by a preset backup kernel, and sending the read service information of the kernel to the backup kernel corresponding to the kernel.
Specifically, a preset backup kernel reads the service information of the shared memory, and sends the service information in the storage space corresponding to the application to the backup kernel corresponding to the identifier of the storage space according to the identifier of the storage space corresponding to the application. For example, if the identifier of the storage space applied by the kernel 1 is the number 4 of the kernel 4 (i.e. the backup kernel of the kernel 1), the preset backup kernel sends the service information in the storage space to the kernel 4 according to the identifier (number 4) of the storage space.
Further, if the predetermined backup kernel is the backup kernel (kernel 4) of the kernel 1, and the service information of the kernel 1 is based on the service information of the kernel 2, as all the service information of the cores needing to be backed up is sequentially stored in the shared memory and the stored service information needing to be backed up is sequentially distributed to the backup cores corresponding to the cores through the cores 4, therefore, the service information generated first is always stored in the shared memory first, so that the service information generated by the kernel 2 is prior to the corresponding service information generated by the kernel 1, therefore, the service information generated by the kernel 2 is certainly stored in the shared memory firstly and then backed up to the kernel 5 through the kernel 4, so that the corresponding service information generated by the kernel 1 is prevented from being backed up firstly, and the service information generated by the kernel 2 is not backed up, thereby ensuring the sequence requirement of the backup service information between kernels.
In the method, a kernel and a shared memory simultaneously receive service information transmitted to the kernel from the outside, and the shared memory stores the service information transmitted to the kernel from the outside; and the preset backup kernel reads the service information which is stored in the shared memory and is transmitted to the kernel from the outside, and sends the read service information which is transmitted to the kernel from the outside to the backup kernel corresponding to the kernel. For example, the external service information is transmitted to the kernel 1, at this time, the shared memory and the kernel 1 simultaneously receive the service information transmitted to the kernel 1 from the external, the shared memory stores the service information transmitted to the kernel 1 from the external, and the preset kernel 4 (backup kernel of the kernel 1) reads and backs up the service information transmitted to the kernel 1 from the external, which is stored in the shared memory. Therefore, the step that the kernel 1 stores the externally transmitted service data into the shared memory is omitted, and the backup time of the service information is shortened.
As shown in fig. 3, the master cores are 301, 302, and 303, the corresponding backup cores are 311, 312, and 313, respectively, and the core 320 is responsible for receiving external data and transmitting the external data to the corresponding master core.
Presetting that the service information of the kernel 302 and the kernel 303 needs to be sent to the kernel 301 for backup, and sending the service data of the kernel 301 to the kernel 311 to complete the backup; the kernel 302 sends the service information to be backed up to the kernel 301, and distributes the service information to the kernel 312 via the kernel 311 to complete the backup; the kernel 303 sends the service information to be backed up to the kernel 301, and distributes the service information to the kernel 313 via the kernel 311 to complete the backup. If the service information of the core 302 is based on the service information of the core 303, it is inevitable that the core 303 generates the service information to be backed up first, at this time, the service information to be backed up generated by the core 303 is sent to the core 301 for backup, and is simultaneously sent to the core 302 for subsequent processing of the service information, further, the core 301 sends the service information of the core 303 to the core 311, and is sent to the core 313 by the core 311 for completing backup, and the core 302 sends the service information to be backed up to the core 301 after performing the subsequent processing on the service information of the core 303, and distributes the service information to be backed up to the core 312 through the core 311 for completing backup. Therefore, the sequence requirement of the service information backed up between the kernels is ensured. Meanwhile, optionally, when the kernel 320 receives the service information transmitted to the kernel 302 from the outside, the service information is simultaneously sent to the kernel 301 and the kernel 302, the kernel 301 directly sends the service information to the kernel 311, and the kernel 311 sends the service information to the kernel 312 to complete the backup, so that the step of sending the service information to the kernel 301 by the kernel 302 is omitted, and the time for backing up the service information is shortened.
In the above method, if fig. 3 adopts a method for backing up service information of a multi-core processor in a service sharing manner, the service information responsible for the kernel 301, the kernel 302, and the kernel 303 is backed up to the kernel 311, the kernel 312, and the kernel 313, respectively, and the service information responsible for the kernel 311, the kernel 312, and the kernel 313 is backed up to the kernel 301, the kernel 302, and the kernel 303, respectively. The method comprises the steps that service information responsible for the kernel 302 and the kernel 303 is preset to be sent to the kernel 301 and sent to the corresponding kernels 312 and 313 through the kernel 311 to complete backup, the service information responsible for the kernel 312 and the kernel 313 is sent to the kernel 311 and sent to the corresponding kernel 302 and the corresponding kernel 303 through the kernel 301 to complete backup, the kernel 301 sends the service information responsible for the kernel 301 to the kernel 311 to complete backup, and the kernel 311 sends the service information responsible for the kernel 301 to complete backup.
As shown in fig. 4, the active cores are 401, 402, and 403, the corresponding backup cores are 411, 412, and 413, respectively, the core 420 is responsible for receiving external data and transmitting the external data to the corresponding active core, the shared memory 430 is responsible for receiving the service information sent by the active cores 401, 402, and 403, and it is noted that when the shared memory stores the service information sent by the active cores from high order to low order, the service information is read from high order to low order.
The kernel 401, the kernel 402 or the kernel 403 applies for a corresponding storage space from the shared memory according to the size of its own service information, and numbers of the kernel 411, the kernel 412 or the kernel 413 are respectively used as identifiers of the applied corresponding storage space, the kernel 411 is preset to read the service information of the shared memory, and when the identifier of the storage space is read to be 411, the service information in the storage space is backed up to its own kernel; when the identifier of the storage space is read as 412, sending the service information in the storage space to the kernel 412 for backup; when the identifier 413 of the storage space is read, the service information in the storage space is sent to the kernel 413 for backup. If the service information of the kernel 402 is based on the service information of the kernel 403, it is inevitable that the kernel 403 generates the service information to be backed up and stores the service information to be backed up in the shared memory, the kernel 411 reads the service information to be backed up stored in the shared memory 403 and sends the service information to the kernel 413 to complete the backup, the kernel 402 stores the service information to be backed up in the shared memory after performing subsequent processing on the service information of the kernel 403, and the kernel 411 reads the service information to be backed up stored in the shared memory 402 and sends the service information to the kernel 412 to complete the backup. Since the kernel 411 reads the shared memory according to the stored sequence when reading the shared memory, the sequence requirement of the service information backed up between the kernels is ensured. Meanwhile, optionally, when the kernel 420 receives the service information transmitted to the kernel 402 from the outside, the service information is simultaneously sent to the shared memory and the kernel 402, the shared memory directly stores the service information, and the kernel 411 reads the stored service information and sends the service information to the kernel 412 to complete the backup, so that the step of sending the service information to the shared memory by the kernel 402 is omitted, and the time for backing up the service information is shortened.
In the method, if fig. 4 adopts a method for backing up service information of a multi-core processor in a service sharing manner, it is further preset that one of the cores 401, 402 and 403 reads the service information of the core 411, 412 and 413 stored in the shared memory. Other steps are similar to the master-slave mode, and are not described again.
An embodiment of the present invention further provides an inner core, as shown in fig. 5, including:
and the receiving unit 51 is configured to receive service information of other cores.
Furthermore, the method can also be used for receiving the service information transmitted to other cores from the outside.
A sending unit 52, configured to send the service information of the other cores received by the receiving unit 51 to the backup cores corresponding to the sending unit.
Furthermore, the method can also be used for sending the self service information to the corresponding backup kernel; and/or, the receiving unit 51 may be further configured to send the service information, which is received by the receiving unit 51 and is externally transmitted to other cores, to a backup core corresponding to the receiving unit.
An embodiment of the present invention further provides a backup kernel, as shown in fig. 6, including:
the receiving and reading module 61 is configured to receive service information of other cores sent by a core which needs to be backed up and corresponds to the receiving and reading module; or, the method is used for reading the service information of the kernel stored in the shared memory;
a sending module 62, configured to send the service information of the other cores received by the receiving and reading module to the backup cores corresponding to the other cores; or, the core processing module is configured to send the service information of the core read by the receiving and reading module to the backup core corresponding to the core.
Specifically, the method and the device are used for sending the service information stored in the storage space to the backup kernel corresponding to the identifier of the storage space according to the identifier of the storage space in the shared memory, where the storage space in the shared memory is applied to the shared memory by the kernel needing to be backed up according to the size of the service information of the kernel, and the identifier of the storage space is the identity information of the backup kernel corresponding to the kernel needing to be backed up.
The specific implementation of the processing functions of the units or modules included in the above-described apparatus has been described in the previous method embodiments, and the description is not repeated here.
It should be noted that, in the embodiment of the kernel or the backup kernel, each unit or module included in the kernel or the backup kernel is only divided according to functional logic, but is not limited to the above division, as long as the corresponding function can be implemented; in addition, specific names of the functional units or modules are only for convenience of distinguishing from each other and are not used for limiting the protection scope of the present invention.
In addition, it is understood by those skilled in the art that all or part of the steps in the above method embodiments may be implemented by related hardware, and the corresponding program may be stored in a computer readable storage medium, where the above mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk.
The embodiment of the invention uniformly completes the backup of the service information of the kernel and other kernels through the preset kernel and the backup kernel of the preset kernel or the shared memory and the preset backup kernel, realizes the backup of the kernel service information, simultaneously ensures the sequence of the backup service information, avoids the problem of errors in service processing caused by inconsistency of the service information between the taken over backup kernels, and thus, the high availability of the system is improved. Meanwhile, the preset kernel or the shared memory finishes the backup by directly reading the service information externally transmitted to the kernel or other kernels, so that the step that other kernels store the service data externally transmitted to the shared memory or send the service data to the preset kernel is omitted, and the backup time of the service information is shortened.
The above description is only a preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the embodiments of the present invention are included in the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims (10)

1. A backup method for business information of a multi-core processor is characterized by comprising the following steps:
the preset kernel receives the service information of other kernels and sends the service information to a backup kernel corresponding to the preset kernel; the backup kernel corresponding to the preset kernel sends the received service information of other kernels to the backup kernels corresponding to the other kernels; or,
the kernel stores the service information of the kernel to a shared memory, the preset backup kernel reads the service information of the shared memory, and the read service information of the kernel is sent to the backup kernel corresponding to the kernel.
2. The method of claim 1, wherein the service information comprises internal control information and external data information; the preset kernel, the other kernels, the backup kernels corresponding to the preset kernel, the backup kernels corresponding to the other kernels, the preset backup kernels and/or the backup kernels corresponding to the kernels are/is located in the same multi-core processor, or located in different multi-core processors, or located in different circuit boards.
3. The method according to claim 1 or 2, wherein the preset kernel sends its own service information to a backup kernel corresponding to the preset kernel.
4. The method according to claim 1 or 2, characterized in that the kernel sends its own service information to the shared memory; the preset backup kernel reads the service information of the shared memory and sends the read service information of the kernel to the backup kernel corresponding to the kernel, and the method comprises the following steps:
the kernel applies for a corresponding storage space to a shared memory according to the size of the business information of the kernel, takes the identity information of a backup kernel corresponding to the kernel as an identifier of the applied corresponding storage space, and stores the business information of the kernel into the applied corresponding storage space; and reading the service information of the shared memory by a preset backup kernel, and sending the service information in the corresponding storage space to the backup kernel corresponding to the identifier of the storage space according to the identifier of the corresponding storage space.
5. The method of claim 1 or 2, further comprising:
the preset kernel and other kernels simultaneously receive the service information transmitted to other kernels from the outside, and the preset kernel transmits the received service information transmitted to other kernels from the outside to the backup kernels corresponding to the preset kernel; the backup kernel corresponding to the preset kernel transmits the received service information which is externally transmitted to other kernels to the backup kernel corresponding to the other kernels; or,
the method comprises the steps that a kernel and a shared memory simultaneously receive service information transmitted to the kernel from the outside, and the shared memory stores the service information transmitted to the kernel from the outside; and the preset backup kernel reads the service information which is stored in the shared memory and is transmitted to the kernel from the outside, and sends the read service information which is transmitted to the kernel from the outside to the backup kernel corresponding to the kernel.
6. A core, comprising:
the receiving unit is used for receiving the service information of other kernels;
and the sending unit is used for sending the service information of the other kernels received by the receiving unit to the corresponding backup kernels.
7. The kernel according to claim 6, wherein the sending unit is further configured to send its service information to its corresponding backup kernel.
8. The core of claim 6,
the receiving unit is also used for receiving the service information transmitted to other inner cores from the outside;
the sending unit is further configured to send the service information, which is received by the receiving unit and transmitted to other kernels from the outside, to the corresponding backup kernel.
9. A backup kernel, comprising:
the receiving and reading module is used for receiving the service information of other kernels sent by the corresponding kernel needing to be backed up; or, the method is used for reading the service information of the kernel stored in the shared memory;
the sending module is used for sending the service information of other kernels received by the receiving and reading module to the backup kernels corresponding to the other kernels; or, the core processing module is configured to send the service information of the core read by the receiving and reading module to the backup core corresponding to the core.
10. The backup kernel of claim 9,
the sending module is used for sending the service information stored in the storage space to the backup kernel corresponding to the identifier of the storage space according to the identifier of the storage space in the shared memory, the storage space in the shared memory is applied to the shared memory by the kernel needing to be backed up according to the size of the service information of the kernel, and the identifier of the storage space is the identity information of the backup kernel corresponding to the kernel needing to be backed up.
CN201110312607.XA 2011-10-14 2011-10-14 Backup method of service information of multi-core processor, inner core and backup inner core Expired - Fee Related CN102508738B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201110312607.XA CN102508738B (en) 2011-10-14 2011-10-14 Backup method of service information of multi-core processor, inner core and backup inner core

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201110312607.XA CN102508738B (en) 2011-10-14 2011-10-14 Backup method of service information of multi-core processor, inner core and backup inner core

Publications (2)

Publication Number Publication Date
CN102508738A true CN102508738A (en) 2012-06-20
CN102508738B CN102508738B (en) 2014-02-19

Family

ID=46220830

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201110312607.XA Expired - Fee Related CN102508738B (en) 2011-10-14 2011-10-14 Backup method of service information of multi-core processor, inner core and backup inner core

Country Status (1)

Country Link
CN (1) CN102508738B (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109190378A (en) * 2018-09-19 2019-01-11 郑州云海信息技术有限公司 A kind of kernel restoration methods and device
CN110262993A (en) * 2019-06-11 2019-09-20 浙江华创视讯科技有限公司 Input the read method and circuit, storage medium, electronic device of information
CN114020529A (en) * 2021-10-29 2022-02-08 恒安嘉新(北京)科技股份公司 Backup method and device of flow table data, network equipment and storage medium

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1916858A (en) * 2006-09-19 2007-02-21 杭州华为三康技术有限公司 Monitoring methd, monitoring equipment in system with multiple cores, and multiple cores system
CN101059768A (en) * 2006-04-17 2007-10-24 北京软通科技有限责任公司 System and method for implementing operating system standby
CN101246466A (en) * 2007-11-29 2008-08-20 华为技术有限公司 Management method and device for sharing internal memory in multi-core system
WO2011021318A1 (en) * 2009-08-19 2011-02-24 日本電気株式会社 Multi-core system, control method of multi-core system, and multiprocessor

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101059768A (en) * 2006-04-17 2007-10-24 北京软通科技有限责任公司 System and method for implementing operating system standby
CN1916858A (en) * 2006-09-19 2007-02-21 杭州华为三康技术有限公司 Monitoring methd, monitoring equipment in system with multiple cores, and multiple cores system
CN101246466A (en) * 2007-11-29 2008-08-20 华为技术有限公司 Management method and device for sharing internal memory in multi-core system
WO2011021318A1 (en) * 2009-08-19 2011-02-24 日本電気株式会社 Multi-core system, control method of multi-core system, and multiprocessor

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
郭惠芳 等: "多核处理器片上Cache的选择性复制策略", 《计算机工程》 *

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109190378A (en) * 2018-09-19 2019-01-11 郑州云海信息技术有限公司 A kind of kernel restoration methods and device
CN110262993A (en) * 2019-06-11 2019-09-20 浙江华创视讯科技有限公司 Input the read method and circuit, storage medium, electronic device of information
CN114020529A (en) * 2021-10-29 2022-02-08 恒安嘉新(北京)科技股份公司 Backup method and device of flow table data, network equipment and storage medium

Also Published As

Publication number Publication date
CN102508738B (en) 2014-02-19

Similar Documents

Publication Publication Date Title
CN109951331B (en) Method, device and computing cluster for sending information
JP6921107B2 (en) Service processing methods, devices, and systems
US20210011817A1 (en) Virtual Machine Recovery Method and Virtual Machine Management Device
US9389976B2 (en) Distributed persistent memory using asynchronous streaming of log records
CN107544871B (en) Virtual machine disk backup method and device
US20170168756A1 (en) Storage transactions
US9152491B2 (en) Job continuation management apparatus, job continuation management method and job continuation management program
CN110753084B (en) Uplink data reading method, cache server and computer readable storage medium
EP3713195B1 (en) Log processing method, related device, and system
WO2016078529A1 (en) Service processing method, device and system
CN105653345A (en) Method and device supporting data nonvolatile random access
CN112953757B (en) Data distribution method, system and computer equipment
JPH086910A (en) Cluster type computer system
CN106815094B (en) Method and equipment for realizing transaction submission in master-slave synchronization mode
CN105808374A (en) Snapshot processing method and associated equipment
CN102508738B (en) Backup method of service information of multi-core processor, inner core and backup inner core
CN111338834B (en) Data storage method and device
CN111400086B (en) Method and system for realizing fault tolerance of virtual machine
CN105373563B (en) Database switching method and device
US9830263B1 (en) Cache consistency
CN116088950A (en) System starting method and device and electronic equipment
US10949203B2 (en) Technologies for ensuring functional safety of an electronic device
US20170235600A1 (en) System and method for running application processes
KR102053849B1 (en) Airplane system and control method thereof
CN109933547B (en) RAID passive acceleration device and method in SSD master control

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
C53 Correction of patent of invention or patent application
CB02 Change of applicant information

Address after: 100085 Beijing, Haidian District on the road, No. 3

Applicant after: Beijing Huawei Digital Technology Co.,Ltd.

Address before: 100085 Beijing, Haidian District on the road, No. 3

Applicant before: Huawei Digit Technology Co., Ltd.

COR Change of bibliographic data

Free format text: CORRECT: APPLICANT; FROM: HUAWEI DIGIT TECHNOLOGY CO., LTD. TO: BEIJING HUAWEI DIGITAL TECHNOLOGY CO., LTD.

C14 Grant of patent or utility model
GR01 Patent grant
CF01 Termination of patent right due to non-payment of annual fee
CF01 Termination of patent right due to non-payment of annual fee

Granted publication date: 20140219

Termination date: 20191014