CN105022666A - Method, device and system for controlling MapReduce task scheduling - Google Patents
Method, device and system for controlling MapReduce task scheduling Download PDFInfo
- Publication number
- CN105022666A CN105022666A CN201410166552.XA CN201410166552A CN105022666A CN 105022666 A CN105022666 A CN 105022666A CN 201410166552 A CN201410166552 A CN 201410166552A CN 105022666 A CN105022666 A CN 105022666A
- Authority
- CN
- China
- Prior art keywords
- node
- failure
- effective
- task
- monitoring device
- 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.)
- Pending
Links
Landscapes
- Mobile Radio Communication Systems (AREA)
Abstract
The invention discloses a method, device and system for controlling MapReduce task scheduling. The method comprises the following steps of extracting a failure node identification that has a fault from the node failure information when the node failure information transmitted by a monitoring device is received, wherein the monitoring device monitors a task node state associated with a master control node in real time, and after the task node is monitored to be changed into a failure state from a significant state and becomes the failure node, the monitoring device transmits the node failure information when the transmitting condition is satisfied; deleting the failure node identification from the significant node collection, wherein the nodes included in the significant node collection are used for the MapReduce task scheduling; adding the failure node identification to the failure node collection. According to the method for controlling the MapReduce task scheduling provided by the invention, the state of task nodes can be detected more comprehensively, so that the scheduling selection of the MapReduce task nodes can be optimized.
Description
Technical field
The present invention relates to the communications field, particularly a kind of methods, devices and systems of control MapReduce task scheduling.
Background technology
Need multiple node to work in coordination with in MapReduce tasks carrying process, in implementation, Map Reduce main controlled node needs to detect each task node executing state, and certain task node needed to reselect node initiating task after losing efficacy.Nowadays Intel Virtualization Technology more comes more to popularize, and a lot of MapReduce cluster also operates on virtualization layer, and virtualization layer possesses node state monitoring function, and the fault detect of MapReduce and the node failure of virtualization layer detect and can be linked.
But some problems: MapReduce below existing MapReduce node state detects and exists only depends on the heartbeat response in tasks carrying process to the condition adjudgement of node, the state of task node can not be fullyed understand, there is the node making repeated attempts and substantially lost efficacy, cause whole MapReduce task all to be waited for because of the inefficacy of certain node.
Summary of the invention
The embodiment of the present invention provides a kind of methods, devices and systems of control MapReduce task scheduling.By utilizing the empty machine state-detection mechanism of virtualization layer to realize more comprehensively task node state-detection, thus the scheduling optimizing MapReduce task node is selected.
According to an aspect of the present invention, a kind of method of control MapReduce task scheduling is provided, comprises:
When receiving the node failure information that monitoring device sends, the failure node mark broken down is extracted from node failure information, the wherein task node state that is associated with main controlled node of monitoring device Real-Time Monitoring, be converted to failure state from effective status and after becoming failure node, send described node failure information when transmission condition meets monitoring task node;
From effective node set, delete described failure node mark, wherein effectively the node that comprises of node set for MapReduce task scheduling;
Described failure node mark is added in failure node set.
In one embodiment, the step of deleting described failure node mark from effective node set comprises:
Judge that described failure node is current and whether carry task;
If judge, described failure node is current does not carry task, then from effective node set, delete described failure node mark.
In one embodiment, if judge, described failure node is current carries task, then in effective node set, select node node as an alternative;
Described task is carried by described substitute node;
Then the step of deleting described failure node mark from effective node set is performed.
In one embodiment, in effective node set, select the step of node node as an alternative to comprise:
In effective node set, select the node node as an alternative of least-loaded.
In one embodiment, also comprise:
When the node receiving monitoring device transmission comes into force information, effective node identification of fault recovery is extracted from node comes into force information, wherein monitoring device is converted to effective status from failure state and after becoming effective node monitoring task node, sends described node to come into force information when transmission condition meets;
Described effective node identification is deleted from failure node set;
Described effective node identification is added in effective node set.
In one embodiment, also comprise:
Periodically send inquiry request with predetermined time interval to monitoring device, so that monitoring device is when receiving inquiry request, determines that described transmission condition obtains and meeting.
According to a further aspect in the invention, provide a kind of main controlled node of control MapReduce task scheduling, comprise receiving element, extraction unit, effectively node set administrative unit and invalid node set management unit, wherein:
Receiving element, for receiving the node failure information that monitoring device sends, the wherein task node state that is associated with main controlled node of monitoring device Real-Time Monitoring, be converted to failure state from effective status and after becoming failure node, send described node failure information when transmission condition meets monitoring task node;
Extraction unit, for receive when receiving element monitoring device send node failure information time, extract from node failure information break down failure node mark;
Effective node set administrative unit, for deleting described failure node mark from effective node set, wherein effectively the node that comprises of node set for MapReduce task scheduling;
Invalid node set management unit, for adding to described failure node mark in failure node set.
In one embodiment, effective node set administrative unit specifically judges that described failure node is current and whether carries task; If judge, described failure node is current does not carry task, then from effective node set, delete described failure node mark.
In one embodiment, effective node set administrative unit also for when judging that described failure node is current and carrying task, selects node node as an alternative in effective node set; Described task is carried by described substitute node; Then the operation of deleting described failure node mark from effective node set is performed.
In one embodiment, effective node set administrative unit, specifically in effective node set, selects the node node as an alternative of least-loaded.
In one embodiment, extraction unit also for receive when receiving element monitoring device send node come into force information time, effective node identification of fault recovery is extracted from node comes into force information, wherein monitoring device is converted to effective status from failure state and after becoming effective node monitoring task node, sends described node to come into force information when transmission condition meets;
Invalid node set management unit also for deleting described effective node identification from failure node set;
Effective node set administrative unit is also for adding to described effective node identification in effective node set.
In one embodiment, above-mentioned main controlled node also comprises:
Transmitting element, for periodically sending inquiry request with predetermined time interval to monitoring device, so that monitoring device is when receiving inquiry request, determines that described transmission condition obtains and meeting.
According to a further aspect in the invention, a kind of system of control MapReduce task scheduling is provided, comprises main controlled node and monitoring device, wherein:
Monitoring device, for the task node state that Real-Time Monitoring is associated with main controlled node, failure state is converted to and after becoming failure node monitoring task node from effective status, the sending node fail message when transmission condition meets, wherein node failure information comprises the failure node mark broken down;
Main controlled node is the main controlled node that above-mentioned any embodiment relates to.
In one embodiment, monitoring device is also for being converted to effective status from failure state and after becoming effective node monitoring task node, when transmission condition meets, sending node comes into force information, and its interior joint information of coming into force comprises effective node identification of fault recovery.
In one embodiment, monitoring device, specifically when the state monitoring task node changes, is determined that described transmission condition obtains and is met.
In one embodiment, monitoring device, specifically after the inquiry request receiving main controlled node transmission, is determined that described transmission condition obtains and is met.
The present invention is by when receiving the node failure information that monitoring device sends, the failure node mark broken down is extracted from node failure information, from effective node set, delete described failure node mark, described failure node mark is added in failure node set.Thus the scheduling can optimizing MapReduce task node is selected.
Description of the invention provides in order to example with for the purpose of describing, and is not exhaustively or limit the invention to disclosed form.Many modifications and variations are obvious for the ordinary skill in the art.Selecting and describing embodiment is in order to principle of the present invention and practical application are better described, and enables those of ordinary skill in the art understand the present invention thus design the various embodiments with various amendment being suitable for special-purpose.
Accompanying drawing explanation
In order to be illustrated more clearly in the embodiment of the present invention or technical scheme of the prior art, be briefly described to the accompanying drawing used required in embodiment or description of the prior art below, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, for those of ordinary skill in the art, under the prerequisite not paying creative work, other accompanying drawing can also be obtained according to these accompanying drawings.
Fig. 1 is the schematic diagram of a method embodiment of the present invention's control MapReduce task scheduling.
Fig. 2 is the schematic diagram that the present invention deletes a method embodiment of failure node mark from effective node set.
Fig. 3 is the schematic diagram of another embodiment of method of the present invention's control MapReduce task scheduling.
Fig. 4 is the schematic diagram of a main controlled node of the present invention embodiment.
Fig. 5 is the schematic diagram of another embodiment of main controlled node of the present invention.
Fig. 6 is the schematic diagram of a system embodiment of the present invention's control MapReduce task scheduling.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, be clearly and completely described the technical scheme in the embodiment of the present invention, obviously, described embodiment is only the present invention's part embodiment, instead of whole embodiments.Illustrative to the description only actually of at least one exemplary embodiment below, never as any restriction to the present invention and application or use.Based on the embodiment in the present invention, those of ordinary skill in the art, not making the every other embodiment obtained under creative work prerequisite, belong to the scope of protection of the invention.
Unless specifically stated otherwise, otherwise positioned opposite, the numerical expression of the parts of setting forth in these embodiments and step and numerical value do not limit the scope of the invention.
Meanwhile, it should be understood that for convenience of description, the size of the various piece shown in accompanying drawing is not draw according to the proportionate relationship of reality.
May not discuss in detail for the known technology of person of ordinary skill in the relevant, method and apparatus, but in the appropriate case, described technology, method and apparatus should be regarded as a part of authorizing instructions.
In all examples with discussing shown here, any occurrence should be construed as merely exemplary, instead of as restriction.Therefore, other example of exemplary embodiment can have different values.
It should be noted that: represent similar terms in similar label and letter accompanying drawing below, therefore, once be defined in an a certain Xiang Yi accompanying drawing, then do not need to be further discussed it in accompanying drawing subsequently.
Fig. 1 is the schematic diagram of a method embodiment of the present invention's control MapReduce task scheduling.Preferably, the method step of the present embodiment can be performed by main controlled node.
Step 101, when receiving the node failure information that monitoring device sends, extracts the failure node mark broken down from node failure information.
Wherein task node (Slave (the TaskTracker)) state that is associated with main controlled node (Master (JobTracker)) of monitoring device Real-Time Monitoring, be converted to failure state from effective status and after becoming failure node, send described node failure information when transmission condition meets monitoring task node.
Preferably, monitoring device can utilize the virtual state monitoring mechanism of virtualization layer (Hyper-V) to detect nodes for state.Because monitoring technology itself is that those skilled in the art understood, therefore do not launch here to describe.
Step 102, deletes described failure node mark from effective node set, wherein effectively the node that comprises of node set for MapReduce task scheduling.
Step 103, adds to described failure node mark in failure node set.
Based on the method for the control MapReduce task scheduling that the above embodiment of the present invention provides, when receiving the node failure information that monitoring device sends, the failure node mark broken down is extracted from node failure information, from effective node set, delete described failure node mark, described failure node mark is added in failure node set.Thus the scheduling can optimizing MapReduce task node is selected.
Fig. 2 is the schematic diagram that the present invention deletes a method embodiment of failure node mark from effective node set.As shown in Figure 2, above-mentioned steps 102 can comprise:
Step 201, judges that described failure node is current and whether carries task.If judge, described failure node is current does not carry task, then perform step 204; If judge, described failure node is current carries task, then perform step 202.
Step 202, selects node node as an alternative in effective node set.
Preferably, in effective node set, select the node node as an alternative of least-loaded.
Step 203, carries described task by described substitute node.
Step 204, deletes described failure node mark from effective node set.
Thus, can effectively avoid when node switches the impact of executing the task.
Fig. 3 is the schematic diagram of another embodiment of method of the present invention's control MapReduce task scheduling.Preferably, the method step of the present embodiment can be performed by main controlled node.
Step 301, when the node receiving monitoring device transmission comes into force information, extracts effective node identification of fault recovery from node comes into force information.
Wherein monitoring device is converted to effective status from failure state and after becoming effective node monitoring task node, sends described node to come into force information when transmission condition meets.
Step 302, deletes described effective node identification from failure node set.
Step 303, adds to described effective node identification in effective node set.
Thus, when node state is recovered, can come back in effective node set, thus improve resource utilization ratio.
Preferably, predetermined time interval periodically can send inquiry request to monitoring device, so that monitoring device is when receiving inquiry request, determines that described transmission condition obtains and meeting, now can send relevant information.Or monitoring device, when monitoring node state and changing, just sends relevant information.
Fig. 4 is the schematic diagram of a main controlled node of the present invention embodiment.As shown in Figure 4, main controlled node comprises receiving element 401, extraction unit 402, effectively node set administrative unit 403 and invalid node set management unit 404.Wherein:
Receiving element 401, for receiving the node failure information that monitoring device sends.
The wherein task node state that is associated with main controlled node of monitoring device Real-Time Monitoring, is converted to failure state from effective status and after becoming failure node, sends described node failure information when transmission condition meets monitoring task node.
Extraction unit 402, for receive when receiving element 401 monitoring device send node failure information time, extract from node failure information break down failure node mark.
Effective node set administrative unit 403, for deleting described failure node mark from effective node set, wherein effectively the node that comprises of node set for MapReduce task scheduling.
Invalid node set management unit 404, for adding to described failure node mark in failure node set.
Based on the main controlled node of the control MapReduce task scheduling that the above embodiment of the present invention provides, when receiving the node failure information that monitoring device sends, the failure node mark broken down is extracted from node failure information, from effective node set, delete described failure node mark, described failure node mark is added in failure node set.Thus the scheduling can optimizing MapReduce task node is selected.
Preferably, whether specifically judge that described failure node is current carries task to effective node set administrative unit 403; If judge, described failure node is current does not carry task, then from effective node set, delete described failure node mark.
Preferably, effective node set administrative unit 403 also for when judging that described failure node is current and carrying task, selects node node as an alternative in effective node set; Described task is carried by described substitute node; Then the operation of deleting described failure node mark from effective node set is performed.
In one embodiment, effective node set administrative unit, specifically in effective node set, selects the node node as an alternative of least-loaded.
Preferably, extraction unit 402 also for receive when receiving element 401 monitoring device send node come into force information time, from node comes into force information, extract effective node identification of fault recovery.
Wherein monitoring device is converted to effective status from failure state and after becoming effective node monitoring task node, sends described node to come into force information when transmission condition meets.
Invalid node set management unit 404 also for deleting described effective node identification from failure node set.
Effective node set administrative unit 403 is also for adding to described effective node identification in effective node set.
Fig. 5 is the schematic diagram of another embodiment of main controlled node of the present invention.Compared with embodiment illustrated in fig. 4, in the embodiment shown in fig. 5, main controlled node also comprises transmitting element 501, for periodically sending inquiry request with predetermined time interval to monitoring device, so that monitoring device is when receiving inquiry request, determines that described transmission condition obtains and meeting.
Fig. 6 is the schematic diagram of a system embodiment of the present invention's control MapReduce task scheduling.As shown in Figure 6, this system comprises main controlled node 601 and monitoring device 602, wherein:
Monitoring device 602, for the task node state that Real-Time Monitoring is associated with main controlled node, failure state is converted to and after becoming failure node monitoring task node from effective status, the sending node fail message when transmission condition meets, wherein node failure information comprises the failure node mark broken down.
Main controlled node 601 is the main controlled node that any embodiment in Fig. 4 or Fig. 5 relates to.
Based on the system of the control MapReduce task scheduling that the above embodiment of the present invention provides,
When main controlled node receives the node failure information of monitoring device transmission, the failure node mark broken down is extracted from node failure information, from effective node set, delete described failure node mark, described failure node mark is added in failure node set.Thus the scheduling can optimizing MapReduce task node is selected.
Preferably, monitoring device 602 is also for being converted to effective status from failure state and after becoming effective node monitoring task node, when transmission condition meets, sending node comes into force information, and its interior joint information of coming into force comprises effective node identification of fault recovery.
Preferably, monitoring device 602, specifically when the state monitoring task node changes, is determined that described transmission condition obtains and is met.
Preferably, monitoring device 602, specifically after the inquiry request receiving main controlled node transmission, is determined that described transmission condition obtains and is met.
By implementing the present invention, node information more comprehensively and accurately can be obtained, can more reasonably arrange task in the task of internodal distribution and Pre-handoff failure node where necessary.The method makes MapReduce node state data more comprehensive, and node switches more initiatively.
One of ordinary skill in the art will appreciate that all or part of step realizing above-described embodiment can have been come by hardware, the hardware that also can carry out instruction relevant by program completes, described program can be stored in a kind of computer-readable recording medium, the above-mentioned storage medium mentioned can be ROM (read-only memory), disk or CD etc.
Claims (16)
1. a method for control MapReduce task scheduling, is characterized in that, comprising:
When receiving the node failure information that monitoring device sends, the failure node mark broken down is extracted from node failure information, the wherein task node state that is associated with main controlled node of monitoring device Real-Time Monitoring, be converted to failure state from effective status and after becoming failure node, send described node failure information when transmission condition meets monitoring task node;
From effective node set, delete described failure node mark, wherein effectively the node that comprises of node set for MapReduce task scheduling;
Described failure node mark is added in failure node set.
2. method according to claim 1, is characterized in that,
The step of deleting described failure node mark from effective node set comprises:
Judge that described failure node is current and whether carry task;
If judge, described failure node is current does not carry task, then from effective node set, delete described failure node mark.
3. method according to claim 2, is characterized in that,
If judge, described failure node is current carries task, then in effective node set, select node node as an alternative;
Described task is carried by described substitute node;
Then the step of deleting described failure node mark from effective node set is performed.
4. method according to claim 3, is characterized in that,
In effective node set, select the step of node node as an alternative to comprise:
In effective node set, select the node node as an alternative of least-loaded.
5. method according to claim 1, is characterized in that, also comprises:
When the node receiving monitoring device transmission comes into force information, effective node identification of fault recovery is extracted from node comes into force information, wherein monitoring device is converted to effective status from failure state and after becoming effective node monitoring task node, sends described node to come into force information when transmission condition meets;
Described effective node identification is deleted from failure node set;
Described effective node identification is added in effective node set.
6. method according to claim 1, is characterized in that, also comprises:
Periodically send inquiry request with predetermined time interval to monitoring device, so that monitoring device is when receiving inquiry request, determines that described transmission condition obtains and meeting.
7. a main controlled node for control MapReduce task scheduling, is characterized in that, comprises receiving element, extraction unit, effectively node set administrative unit and invalid node set management unit, wherein:
Receiving element, for receiving the node failure information that monitoring device sends, the wherein task node state that is associated with main controlled node of monitoring device Real-Time Monitoring, be converted to failure state from effective status and after becoming failure node, send described node failure information when transmission condition meets monitoring task node;
Extraction unit, for receive when receiving element monitoring device send node failure information time, extract from node failure information break down failure node mark;
Effective node set administrative unit, for deleting described failure node mark from effective node set, wherein effectively the node that comprises of node set for MapReduce task scheduling;
Invalid node set management unit, for adding to described failure node mark in failure node set.
8. main controlled node according to claim 7, is characterized in that,
Effective node set administrative unit specifically judges that described failure node is current and whether carries task; If judge, described failure node is current does not carry task, then from effective node set, delete described failure node mark.
9. main controlled node according to claim 8, is characterized in that,
Effective node set administrative unit also for when judging that described failure node is current and carrying task, selects node node as an alternative in effective node set; Described task is carried by described substitute node; Then the operation of deleting described failure node mark from effective node set is performed.
10. main controlled node according to claim 9, is characterized in that,
Effective node set administrative unit, specifically in effective node set, selects the node node as an alternative of least-loaded.
11. main controlled nodes according to claim 7, is characterized in that,
Extraction unit also for receive when receiving element monitoring device send node come into force information time, effective node identification of fault recovery is extracted from node comes into force information, wherein monitoring device is converted to effective status from failure state and after becoming effective node monitoring task node, sends described node to come into force information when transmission condition meets;
Invalid node set management unit also for deleting described effective node identification from failure node set;
Effective node set administrative unit is also for adding to described effective node identification in effective node set.
12. main controlled nodes according to claim 7, is characterized in that, also comprise:
Transmitting element, for periodically sending inquiry request with predetermined time interval to monitoring device, so that monitoring device is when receiving inquiry request, determines that described transmission condition obtains and meeting.
The system of 13. 1 kinds of control MapReduce task schedulings, is characterized in that, comprises main controlled node and monitoring device, wherein:
Monitoring device, for the task node state that Real-Time Monitoring is associated with main controlled node, failure state is converted to and after becoming failure node monitoring task node from effective status, the sending node fail message when transmission condition meets, wherein node failure information comprises the failure node mark broken down;
Main controlled node, the main controlled node related to any one of claim 7-12.
14. systems according to claim 13, is characterized in that,
Monitoring device is also for being converted to effective status from failure state and after becoming effective node monitoring task node, and when transmission condition meets, sending node comes into force information, and its interior joint information of coming into force comprises effective node identification of fault recovery.
15. systems according to claim 13, is characterized in that,
Monitoring device, specifically when the state monitoring task node changes, is determined that described transmission condition obtains and is met.
16. systems according to claim 13, is characterized in that,
Monitoring device, specifically after the inquiry request receiving main controlled node transmission, is determined that described transmission condition obtains and is met.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410166552.XA CN105022666A (en) | 2014-04-24 | 2014-04-24 | Method, device and system for controlling MapReduce task scheduling |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410166552.XA CN105022666A (en) | 2014-04-24 | 2014-04-24 | Method, device and system for controlling MapReduce task scheduling |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105022666A true CN105022666A (en) | 2015-11-04 |
Family
ID=54412655
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410166552.XA Pending CN105022666A (en) | 2014-04-24 | 2014-04-24 | Method, device and system for controlling MapReduce task scheduling |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105022666A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106406990A (en) * | 2016-08-26 | 2017-02-15 | 李逸博 | Batch job-resource matching method and system with security constraint |
| CN106649555A (en) * | 2016-11-08 | 2017-05-10 | 深圳市中博睿存科技有限公司 | Memory unit state marking method and distributed memory system |
| CN107885549A (en) * | 2017-11-16 | 2018-04-06 | 信阳师范学院 | Remove the method and system that process is remained in TORQUE computing cluster calculate nodes |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030204509A1 (en) * | 2002-04-29 | 2003-10-30 | Darpan Dinker | System and method dynamic cluster membership in a distributed data system |
| CN102521044A (en) * | 2011-12-30 | 2012-06-27 | 北京拓明科技有限公司 | Distributed task scheduling method and system based on messaging middleware |
| CN102769673A (en) * | 2012-07-25 | 2012-11-07 | 楚云汉智武汉网络存储系统有限公司 | Failure detection method suitable to large-scale storage cluster |
| US20140059154A1 (en) * | 2012-08-23 | 2014-02-27 | Metaswitch Networks Ltd | Leader Node Appointment |
| CN103677967A (en) * | 2012-09-03 | 2014-03-26 | 阿里巴巴集团控股有限公司 | Remote data service system of data base and task scheduling method |
-
2014
- 2014-04-24 CN CN201410166552.XA patent/CN105022666A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030204509A1 (en) * | 2002-04-29 | 2003-10-30 | Darpan Dinker | System and method dynamic cluster membership in a distributed data system |
| CN102521044A (en) * | 2011-12-30 | 2012-06-27 | 北京拓明科技有限公司 | Distributed task scheduling method and system based on messaging middleware |
| CN102769673A (en) * | 2012-07-25 | 2012-11-07 | 楚云汉智武汉网络存储系统有限公司 | Failure detection method suitable to large-scale storage cluster |
| US20140059154A1 (en) * | 2012-08-23 | 2014-02-27 | Metaswitch Networks Ltd | Leader Node Appointment |
| CN103677967A (en) * | 2012-09-03 | 2014-03-26 | 阿里巴巴集团控股有限公司 | Remote data service system of data base and task scheduling method |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106406990A (en) * | 2016-08-26 | 2017-02-15 | 李逸博 | Batch job-resource matching method and system with security constraint |
| CN106649555A (en) * | 2016-11-08 | 2017-05-10 | 深圳市中博睿存科技有限公司 | Memory unit state marking method and distributed memory system |
| CN107885549A (en) * | 2017-11-16 | 2018-04-06 | 信阳师范学院 | Remove the method and system that process is remained in TORQUE computing cluster calculate nodes |
| CN107885549B (en) * | 2017-11-16 | 2020-10-23 | 信阳师范学院 | Method and system for clearing residual process in TORQUE computing cluster computing node |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11184216B2 (en) | State control method and apparatus | |
| CN108040108B (en) | Communication switching method, device, coordination server and readable storage medium | |
| CN106331098B (en) | Server cluster system | |
| EP3142011B9 (en) | Anomaly recovery method for virtual machine in distributed environment | |
| US11256539B2 (en) | Task processing method, apparatus, and system based on distributed system | |
| CN104092719B (en) | Document transmission method, device and distributed cluster file system | |
| CN103345422B (en) | A kind of multithreading hard real-time control method based on Linux | |
| US10541862B2 (en) | VNF processing policy determining method, apparatus, and system | |
| CN104601366B (en) | It is a kind of control, service node configuration service method and device | |
| CN105354108A (en) | Data backup method and node | |
| CN104468521A (en) | Online migration method, device and system | |
| CN106790092B (en) | Remote procedure call server control system and method | |
| CN104219288A (en) | Multi-thread based distributed data synchronism method and system thereof | |
| KR20170118165A (en) | Method and apparatus for updating a network service technician | |
| CN105426271A (en) | Lock management method and device for distributed storage system | |
| CN103870362A (en) | Data recovery method, data recovery device and backup system | |
| CN104158707A (en) | Method and device of detecting and processing brain split in cluster | |
| CN104301140A (en) | Service request responding method, device and system | |
| CN102420820A (en) | Fence method in cluster system and apparatus thereof | |
| CN110768840A (en) | Control method, device, equipment and storage medium of communication equipment | |
| CN105022666A (en) | Method, device and system for controlling MapReduce task scheduling | |
| KR20180122593A (en) | How to delete a cloud host in a cloud computing environment, devices, servers, and storage media | |
| CN104125089A (en) | Network transaction control method and execution method, and network controller and forwarding equipment | |
| CN106462448A (en) | Multi-operating system device, notification device and methods thereof | |
| CN105262604A (en) | Virtual machine migration method and equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20151104 |