CN106155770B - Method for scheduling task and electronic equipment - Google Patents
Method for scheduling task and electronic equipment Download PDFInfo
- Publication number
- CN106155770B CN106155770B CN201510145555.XA CN201510145555A CN106155770B CN 106155770 B CN106155770 B CN 106155770B CN 201510145555 A CN201510145555 A CN 201510145555A CN 106155770 B CN106155770 B CN 106155770B
- Authority
- CN
- China
- Prior art keywords
- task
- calculate node
- virtualization
- fragment
- node
- 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.)
- Active
Links
Abstract
The present invention provides a kind of method for scheduling task and electronic equipment.It the described method includes: receiving task to be processed, and is multiple tasks fragment by the Task-decomposing；The multiple task fragment is distributed into the respective virtual calculate node in the virtualization computing cluster, by respective virtual calculate node to the task execution calculating operation of distribution；Receive the indication signal returned from the timing of respective virtual calculate node, the indication signal indicate the calculate node whether normal operating；When not receiving indication signal from specific virtualization calculate node, determine that the specific virtualization calculate node is malfunctioning node, and determine whether to meet predetermined condition；And when a predetermined condition is satisfied, the specific virtualization calculate node is waited to restore the calculating operation to continue to execute allocated task fragment.
Description
Technical field
This application involves method for scheduling task and electronic equipment.
Background technique
MapReduce is operated on physical machine cluster at the beginning of design, in view of the unreliability of physical machine,
MapReduce has carried out the design of many fault-tolerances in task scheduling process.And many MapReduce applications are all run at present
On virtual platform, virtual platform can provide better guaranteed reliability compared with traditional physical machine cluster.For
The original method for scheduling task of such case MapReduce is just correspondingly improved.
For this reason, it may be desirable to a kind of method for scheduling task and electronic equipment are provided, it can be more preferable for virtualization computing platform
Ground scheduler task.
Summary of the invention
According to embodiments of the present invention, a kind of method for scheduling task is provided, virtualization computing cluster system is applied to, it is described
Method includes:
Task to be processed is received, and is multiple tasks fragment by the Task-decomposing；
The multiple task fragment is distributed into the respective virtual calculate node in the virtualization computing cluster, by phase
Calculate node should be virtualized to the task execution calculating operation of distribution；
The indication signal that timing returns is received from respective virtual calculate node, the indication signal indicates the calculating section
Point whether normal operating；
When not receiving indication signal from specific virtualization calculate node, determine that the specific virtualization calculate node is
Malfunctioning node, and determine whether to meet predetermined condition；
When a predetermined condition is satisfied, the specific virtualization calculate node is waited to restore to continue to execute allocated task point
The calculating operation of piece.
Preferably, it is determined whether meet predetermined condition further include:
The calculating time needed for estimation re-executes the first task fragment for having distributed to the specific virtualization calculate node；
Estimation is calculated into the time compared with the recovery time of pre-set virtualization calculate node；
If the calculating time of estimation is greater than the recovery time, it is determined that meet predetermined condition.
Preferably, when calculating needed for estimation re-executes the task fragment for having distributed to the specific virtualization calculate node
Between further include:
Obtain the information for distributing to the unfinished portion of task fragment of the specific virtualization calculate node；
Meter needed for re-executing the unfinished portion of the task fragment according to the estimation of the information of the unfinished portion of acquisition
Evaluation time.
Preferably, the method also includes:
When being unsatisfactory for predetermined condition, by not completing in the task fragment for having distributed to the specific virtualization calculate node
Distribute to other virtualization calculate nodes in part.
Preferably, the method also includes:
Sequentially according to distance, from closely not complete into the task fragment that will have far distributed to the specific virtualization calculate node
At partially distributing to other virtualization calculate nodes.
Preferably, the method also includes:
Receive the processing result of the task fragment of each return from the respective virtual calculate node for executing calculating operation；
And
All processing results are assembled to generate the processing result to be exported.
Another embodiment according to the present invention, provides a kind of electronic equipment, comprising:
Task-decomposing module is configured to receive task to be processed, and is multiple tasks fragment by the Task-decomposing；
Task allocating module is configured to distributing to the multiple task fragment into the respective virtual in virtualization computing cluster
Change calculate node, by respective virtual calculate node to the task execution calculating operation of distribution；
Control module is configured to receive the indication signal that timing returns from respective virtual calculate node, the instruction letter
Number instruction calculate node whether normal operating,
Wherein, when not receiving indication signal from specific virtualization calculate node, the control module determines the spy
Surely virtualization calculate node is malfunctioning node, and determines whether to meet predetermined condition；And
When a predetermined condition is satisfied, the control module waits the specific virtualization calculate node to restore to continue to execute
The calculating operation of the task fragment of distribution.
Preferably, the control module is further configured to:
The calculating time needed for estimation re-executes the first task fragment for having distributed to the specific virtualization calculate node；
Estimation is calculated into the time compared with the recovery time of pre-set virtualization calculate node；
If the calculating time of estimation is greater than the recovery time, it is determined that meet predetermined condition.
Preferably, the control module is further configured to:
Obtain the information for distributing to the unfinished portion of task fragment of the specific virtualization calculate node；
Meter needed for re-executing the unfinished portion of the task fragment according to the estimation of the information of the unfinished portion of acquisition
Evaluation time.
Preferably, the task allocating module is further configured to
When being unsatisfactory for predetermined condition, by not completing in the task fragment for having distributed to the specific virtualization calculate node
Distribute to other virtualization calculate nodes in part.
Preferably, the task allocating module is further configured to:
Sequentially according to distance, from closely not complete into the task fragment that will have far distributed to the specific virtualization calculate node
At partially distributing to other virtualization calculate nodes.
Preferably, the control module is further configured to
Receive the processing result of the task fragment of each return from the respective virtual calculate node for executing calculating operation；
And
All processing results are assembled to generate the processing result to be exported.
Therefore, method for scheduling task and electronic equipment according to an embodiment of the present invention, can be for virtualization computing platform
Preferably scheduler task.
Detailed description of the invention
Fig. 1 is the flow chart of diagram method for scheduling task according to a first embodiment of the present invention；
Fig. 2 is the flow chart for illustrating method for scheduling task according to a second embodiment of the present invention；And
Fig. 3 is the functional configuration block diagram for illustrating electronic equipment according to a third embodiment of the present invention.
Specific embodiment
In the following, method for scheduling task and electronic equipment according to an embodiment of the present invention will be described in detail with reference to the attached drawings.
<first embodiment>
In the following, reference Fig. 1 to be described in detail to method for scheduling task according to a first embodiment of the present invention.
Method for scheduling task according to embodiments of the present invention is applied to virtualization computing cluster system.
The method 100 includes:
Step S101: receiving task to be processed, and is multiple tasks fragment by the Task-decomposing；
Step S102: the multiple task fragment is distributed into the respective virtualization in the virtualization computing cluster and is calculated
Node, by respective virtual calculate node to the task execution calculating operation of distribution；
Step S103: receiving the indication signal that timing returns, and the indication signal indicates whether the calculate node is normal
Operation；
Step S104: when not receiving indication signal from specific virtualization calculate node, the specific virtualization is determined
Calculate node is malfunctioning node, and determines whether to meet predetermined condition；
Step S105: when a predetermined condition is satisfied, the specific virtualization calculate node recovery is waited to divide to continue to execute
The calculating operation for the task fragment matched.
Specifically, in step s101, such as by task management node (JobTracker) task to be processed is received
It (Job), is then, multiple tasks fragment (Task) by the Task-decomposing.For example, long data block to be processed is received, by this
Long data block is divided into multiple small data blocks, that is to say, that each task fragment corresponds to a small data block.
Then, in step s 102, the multiple task fragment is distributed to corresponding in the virtualization computing cluster
Virtualize calculate node (TaskTracker), by respective virtual calculate node to the task execution calculating operation of distribution (that is,
Mpa/Reduce task).
Specifically, virtualization computing cluster includes the virtualization calculate node (that is, virtual machine) of multiple dispersions.In step
In S102, each task fragment divided in step s101 is distributed to a virtualization in virtualization computing cluster
Calculate node, by virtualizing calculate node accordingly to the task execution calculating operation of distribution.It should be noted that distribution task
Any virtualization calculate node that can be in virtualization computing cluster of fragment.
Then, in step s 103, the indication signal returned from respective virtual calculate node timing, the instruction are received
Calculate node described in signal designation whether normal operating.
For example, the virtualization calculate node timing for executing calculating operation sends the heart to the virtualization calculate node of distribution task
Jump signal.The heartbeat signal indicates that the virtualization calculate node operation of the execution calculating operation is normal.
Then, in step S104, when not receiving indication signal from specific virtualization calculate node, the spy is determined
Surely virtualization calculate node is malfunctioning node.That is, if not receiving heartbeat signal from specific virtualization calculate node,
It can then determine the specific virtualization node current failure, that is, without heartbeat.Then, it is determined that the virtualization calculate node is
It is no to meet predetermined condition.
Then, in step s105, when a predetermined condition is satisfied, the specific virtualization calculate node is waited to restore to continue
Execute the calculating operation of allocated task fragment.
Because virtual machine can be fully returned in a short period of time when running on virtualizing computing cluster system
State (including the data on memory and network) before delay machine, all Task run before in virtual machine at this time can continue to hold
Row, without being re-executed on other machines.
That is, the scheme from the prior art is different, when the virtualization calculate node for determining that execution calculating is thought occurs
When failure, the distributing to the calculate node of the task is not deleted not instead of immediately, first judges whether to meet predetermined condition, and when full
When sufficient predetermined condition, the distributing to the calculate node of the task is not deleted.On the contrary, when a predetermined condition is satisfied, waiting the specific void
Quasi-ization calculate node is restored to continue to execute the calculating operation of allocated task fragment.
Therefore, method for scheduling task according to an embodiment of the present invention goes out in the virtualization calculate node for executing calculating task
It when existing failure, can judge to meet according to oneself state predetermined, judge to wait the calculate node to restart rather than by calculating task
Other nodes are distributed to, so as to greatly improve computational efficiency for virtualization computing platform preferably scheduler task.
<second embodiment>
In the following, the method for scheduling task by reference Fig. 2 detailed description according to a second embodiment of the present invention.
The method 200 includes:
Step S201: receiving task to be processed, and is multiple tasks fragment by the Task-decomposing；
Step S202: the multiple task fragment is distributed into the respective virtualization in the virtualization computing cluster and is calculated
Node, by respective virtual calculate node to the task execution calculating operation of distribution；
Step S203: receiving the indication signal that timing returns, and the indication signal indicates whether the calculate node is normal
Operation；
Step S204: when not receiving indication signal from specific virtualization calculate node, the specific virtualization is determined
Calculate node is malfunctioning node；
Step S205: estimation re-executes needed for the first task fragment for having distributed to the specific virtualization calculate node
The time is calculated, estimation is calculated into the time compared with the recovery time of pre-set virtualization calculate node；
Step S206: when the calculating time of estimation being greater than the recovery time, the specific virtualization calculate node is waited
Restore to continue to execute the calculating operation of allocated task fragment.
Specifically, in step s 201, task to be processed (Job) is received, is multiple by the Task-decomposing then
It is engaged in fragment (Task).For example, receiving long data block to be processed, which is divided into multiple small data blocks, that is,
It says, each task fragment corresponds to a small data block.
Then, in step S202, the multiple task fragment is distributed to corresponding in the virtualization computing cluster
Calculate node is virtualized, by respective virtual calculate node to the task execution calculating operation of distribution.
Specifically, virtualization computing cluster includes the virtualization calculate node (that is, virtual machine) of multiple dispersions.In step
In S202, each task fragment divided in step s 201 is distributed to a virtualization in virtualization computing cluster
Calculate node, by virtualizing calculate node accordingly to the task execution calculating operation of distribution.It should be noted that distribution task
Any virtualization calculate node that can be in virtualization computing cluster of fragment.
Then, in step S203, the indication signal returned from respective virtual calculate node timing, the instruction are received
Calculate node described in signal designation whether normal operating.
For example, the virtualization calculate node timing for executing calculating operation sends the heart to the virtualization calculate node of distribution task
Jump signal.The heartbeat signal indicates that the virtualization calculate node operation of the execution calculating operation is normal.
Then, in step S204, when not receiving indication signal from specific virtualization calculate node, the spy is determined
Surely virtualization calculate node is malfunctioning node.That is, if not receiving heartbeat signal from specific virtualization calculate node,
It can then determine the specific virtualization node current failure, that is, without heartbeat.
Then, in step S205, estimation re-executes the first task for having distributed to the specific virtualization calculate node
Estimation is calculated the time compared with the recovery time of pre-set virtualization calculate node by the calculating time needed for fragment.
Specifically, in one embodiment, it is determined whether meet predetermined condition further include:
The calculating time needed for estimation re-executes the first task fragment for having distributed to the specific virtualization calculate node；
Estimation is calculated into the time compared with the recovery time of pre-set virtualization calculate node；If the calculating time of estimation is big
In the recovery time, it is determined that meet predetermined condition.
That is, estimation re-executes the first task fragment institute for having distributed to the specific virtualization calculate node first
The calculating time needed, for example, it is assumed that calculating meter needed for calculate node re-executes the first task fragment as another virtualization
Evaluation time is 5 minutes.
Then, the recovery time for reading pre-set virtualization calculate node, for example, it is assumed that each virtualization calculates section
The recovery time of point is set as 1 minute.By the recovery time for calculating time and pre-set virtualization calculate node of estimation
Compare, can determine that the calculating time (5 minutes) of estimation are greater than recovery time (1 minute).Make a reservation at this point it is possible to determine and meet this
Condition.
Then, in step S206, when the calculating time of estimation being greater than the recovery time, the specific virtualization is waited
Calculate node is restored to continue to execute the calculating operation of allocated task fragment.
That is, the scheme from the prior art is different, when the virtualization calculate node for determining execution calculating task occurs
When failure, the distributing to the calculate node of the task is not deleted not instead of immediately, first judges whether to meet predetermined condition, and when full
When sufficient predetermined condition, the distributing to the calculate node of the task is not deleted.On the contrary, when a predetermined condition is satisfied, waiting the specific void
Quasi-ization calculate node is restored to continue to execute the calculating operation of allocated task fragment.
On the other hand, when being unsatisfactory for predetermined condition, that is to say, that be less than the recovery time when the calculating time of estimation
When, the unfinished portion in the task fragment for having distributed to the specific virtualization calculate node can be distributed into other virtualizations
Calculate node.
In one embodiment, estimation re-executes needed for the task fragment for having distributed to the specific virtualization calculate node
The calculating time further include:
Obtain the information for distributing to the unfinished portion of task fragment of the specific virtualization calculate node；
Meter needed for re-executing the unfinished portion of the task fragment according to the estimation of the information of the unfinished portion of acquisition
Evaluation time.
That is, needed for re-executing the first task fragment for having distributed to the specific virtualization calculate node in estimation
The calculating time when, do not need the time needed for estimation re-executes whole first task fragments, but can first obtain point
The information of the unfinished portion of the task fragment of the dispensing specific virtualization calculate node.
For example, the journey for the task fragment completed according to the virtualization calculate node cached in virtualized computing system
It spends (for example, 40%), can determine that unfinished portion is 60%.
Then, needed for re-executing the unfinished portion of the task fragment according to the estimation of the information of the unfinished portion of acquisition
The calculating time.It is 3 minutes that is, determining that the time needed for the calculating for completing the unfinished portion is 5 minutes * 60%.
It therefore, the calculating time needed for re-executing the unfinished portion of the task fragment by estimation, can be more accurate
Ground determination is that the calculate node is waited to restore or the first task fragment is distributed to other calculate nodes.In the embodiment
In, because the time needed for completing remainder is 3 minutes, the time needed for restarting the calculate node is still greater than, that is,
1 minute.
Therefore, calculate node recovery is continued waiting for.
On the other hand, virtual management platform can be migrated when detecting that specific virtualization calculate node breaks down
The state and data of the specific virtualization calculate node, and start to restore the virtualization calculate node.
After the virtualization calculate node is successfully recovered, specific virtualization when breaking down can be calculated into section
The state and Data Migration of point are returned, and are executed since state of the virtualization calculate node break down when continued
It calculates, and sends heartbeat signal to host node.
For host node after receiving heartbeat signal, redefining the calculate node is normal condition.
In one embodiment, the method also includes:
Sequentially according to distance, from closely not complete into the task fragment that will have far distributed to the specific virtualization calculate node
At partially distributing to other virtualization calculate nodes.
Specifically, when the unfinished portion of task fragment is distributed to other virtualization calculate nodes, according to from backward
The unfinished portion of the task fragment is distributed to other virtualization calculate nodes by preceding sequence.
In one embodiment, the method also includes:
Receive the processing result of the task fragment of each return from the respective virtual calculate node for executing calculating operation；
And
All processing results are assembled to generate the processing result to be exported.
That is, each virtualization calculate node returns to the calculated result of oneself after completing calculating task
Then the host node of distribution task assembles all processing results by host node to generate the processing result to be exported, that is, be directed to
The calculated result of the task of distribution.
Therefore, method for scheduling task according to an embodiment of the present invention goes out in the virtualization calculate node for executing calculating task
When existing failure, can judge it is that the calculate node is waited to restart or by distribution of computation tasks to other nodes according to oneself state,
So as to greatly improve computational efficiency for virtualization computing platform preferably scheduler task.
<3rd embodiment>
In the following, the electronic equipment by reference Fig. 3 description according to a third embodiment of the present invention.
Electronic equipment 300 according to a third embodiment of the present invention includes:
Task-decomposing module 301 is configured to receive task to be processed, and is multiple tasks point by the Task-decomposing
Piece；
Task allocating module 302 is configured to distribute to the multiple task fragment corresponding in virtualization computing cluster
Calculate node is virtualized, by respective virtual calculate node to the task execution calculating operation of distribution；
Control module 303 is configured to receive the indication signal that timing returns, and the indication signal indicates the calculate node
Whether normal operating,
Wherein, when not receiving indication signal from specific virtualization calculate node, the control module 303 determines should
Specific virtualization calculate node is malfunctioning node, and determines whether to meet predetermined condition；And
When a predetermined condition is satisfied, the control module 303 waits the specific virtualization calculate node to restore to continue to hold
The calculating operation of the allocated task fragment of row.
Preferably, the control module 303 is further configured to:
The calculating time needed for estimation re-executes the first task fragment for having distributed to the specific virtualization calculate node；
Estimation is calculated into the time compared with the recovery time of pre-set virtualization calculate node；
If the calculating time of estimation is greater than the recovery time, it is determined that meet predetermined condition.
Preferably, the control module 303 is further configured to:
Obtain the information for distributing to the unfinished portion of task fragment of the specific virtualization calculate node；
Meter needed for re-executing the unfinished portion of the task fragment according to the estimation of the information of the unfinished portion of acquisition
Evaluation time.
Preferably, the task allocating module 302 is further configured to
When being unsatisfactory for predetermined condition, by not completing in the task fragment for having distributed to the specific virtualization calculate node
Distribute to other virtualization calculate nodes in part.
Preferably, the task allocating module 302 is further configured to:
Sequentially according to distance, from closely not complete into the task fragment that will have far distributed to the specific virtualization calculate node
At partially distributing to other virtualization calculate nodes.
Preferably, the control module 303 is further configured to
Receive the processing result of the task fragment of each return from the respective virtual calculate node for executing calculating operation；
And
All processing results are assembled to generate the processing result to be exported.
Therefore, method for scheduling task and electronic equipment according to an embodiment of the present invention, can be for virtualization computing platform
Preferably scheduler task.
Therefore, there is event in the virtualization calculate node for executing calculating task in electronic equipment according to an embodiment of the present invention
When barrier, can be judged according to oneself state be wait the calculate node to restart or by distribution of computation tasks to other nodes, thus
Computational efficiency can be greatly improved for virtualization computing platform preferably scheduler task.
It should be noted that above embodiment is intended merely as example, the present invention is not limited to such examples, but can
To carry out various change.
For example, the electronic equipment can be including multiple physical machine clusters with computing capability.
It should be noted that in the present specification, the terms "include", "comprise" or its any other variant are intended to
Non-exclusive inclusion, so that the process, method, article or equipment including a series of elements is not only wanted including those
Element, but also including other elements that are not explicitly listed, or further include for this process, method, article or equipment
Intrinsic element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that
There is also other identical elements in process, method, article or equipment including the element.
Finally, it is to be noted that, it is above-mentioned it is a series of processing not only include with sequence described here in temporal sequence
The processing of execution, and the processing including executing parallel or respectively rather than in chronological order.
Through the above description of the embodiments, those skilled in the art can be understood that the present invention can be by
Software adds the mode of required hardware platform to realize, naturally it is also possible to all be implemented by hardware.Based on this understanding,
Technical solution of the present invention can be embodied in the form of software products in whole or in part to what background technique contributed,
The computer software product can store in storage medium, such as ROM (read-only memory)/RAM (random access memory), magnetic
Dish, CD etc., including some instructions are used so that a computer equipment (can be personal computer, server or network
Equipment etc.) execute method described in certain parts of each embodiment of the present invention or embodiment.
The present invention is described in detail above, specific case used herein is to the principle of the present invention and embodiment party
Formula is expounded, and the above description of the embodiment is only used to help understand the method for the present invention and its core ideas；Meanwhile it is right
In those of ordinary skill in the art, according to the thought of the present invention, change is had in specific embodiments and applications
Place, in conclusion the contents of this specification are not to be construed as limiting the invention.
Claims (10)
1. a kind of method for scheduling task is applied to virtualization computing cluster system, which comprises
Task to be processed is received, and is multiple tasks fragment by the Task-decomposing；
The multiple task fragment is distributed into the respective virtual calculate node in the virtualization computing cluster, by corresponding empty
Task execution calculating operation of the quasi-ization calculate node to distribution；
The indication signal returned from respective virtual calculate node timing is received, the indication signal indicates that the calculate node is
No normal operating；
When not receiving indication signal from specific virtualization calculate node, determine that the specific virtualization calculate node is failure
Node, and determine whether to meet predetermined condition；And
When a predetermined condition is satisfied, the specific virtualization calculate node is waited to restore to continue to execute allocated task fragment
Calculating operation,
Where it is determined whether meeting predetermined condition further include:
The calculating time needed for estimation re-executes the task fragment for having distributed to the specific virtualization calculate node；
Estimation is calculated into the time compared with the recovery time of pre-set virtualization calculate node；
If the calculating time of estimation is greater than the recovery time, it is determined that meet predetermined condition.
2. the method for claim 1, wherein estimation, which re-executes, has distributed to appointing for the specific virtualization calculate node
It is engaged in the calculating time needed for fragment further include:
Obtain the information for distributing to the unfinished portion of task fragment of the specific virtualization calculate node；
When calculating needed for re-executing the unfinished portion of the task fragment according to the estimation of the information of the unfinished portion of acquisition
Between.
3. the method as described in claim 1, further includes:
When being unsatisfactory for predetermined condition, by the unfinished portion in the task fragment for having distributed to the specific virtualization calculate node
Distribute to other virtualization calculate nodes.
4. method as claimed in claim 3, further includes:
According to distance sequence, from closely to far by the unfinished portion in the task fragment for having distributed to the specific virtualization calculate node
Distribute to other virtualization calculate nodes.
5. the method as described in claim 1, further includes:
Receive the processing result of the task fragment of each return from the respective virtual calculate node for executing calculating operation；And
All processing results are assembled to generate the processing result to be exported.
6. a kind of electronic equipment, comprising:
Task-decomposing module is configured to receive task to be processed, and is multiple tasks fragment by the Task-decomposing；
Task allocating module is configured to distributing to the multiple task fragment into the respective virtual meter in virtualization computing cluster
Operator node, by respective virtual calculate node to the task execution calculating operation of distribution；
Control module is configured to receive the indication signal that timing returns from respective virtual calculate node, and the indication signal refers to
Show the calculate node whether normal operating,
Wherein, when not receiving indication signal from specific virtualization calculate node, the control module determines the specific void
Quasi-ization calculate node is malfunctioning node, and determines whether to meet predetermined condition；And
When a predetermined condition is satisfied, the control module waits the specific virtualization calculate node recovery to distribute to continue to execute
Task fragment calculating operation,
Wherein, the control module is further configured to:
The calculating time needed for estimation re-executes the task fragment for having distributed to the specific virtualization calculate node；
Estimation is calculated into the time compared with the recovery time of pre-set virtualization calculate node；
If the calculating time of estimation is greater than the recovery time, it is determined that meet predetermined condition.
7. method as claimed in claim 6, wherein the control module is further configured to:
Obtain the information for distributing to the unfinished portion of task fragment of the specific virtualization calculate node；
When calculating needed for re-executing the unfinished portion of the task fragment according to the estimation of the information of the unfinished portion of acquisition
Between.
8. electronic equipment as claimed in claim 7, wherein the task allocating module is further configured to
When being unsatisfactory for predetermined condition, by the unfinished portion in the task fragment for having distributed to the specific virtualization calculate node
Distribute to other virtualization calculate nodes.
9. electronic equipment as claimed in claim 8, wherein the task allocating module is further configured to:
According to distance sequence, from closely to far by the unfinished portion in the task fragment for having distributed to the specific virtualization calculate node
Distribute to other virtualization calculate nodes.
10. electronic equipment as claimed in claim 6, wherein the control module is further configured to receive from executing calculating
The processing result of the task fragment of each return of the respective virtual calculate node of operation；And
All processing results are assembled to generate the processing result to be exported.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510145555.XA CN106155770B (en) | 2015-03-30 | 2015-03-30 | Method for scheduling task and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510145555.XA CN106155770B (en) | 2015-03-30 | 2015-03-30 | Method for scheduling task and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106155770A CN106155770A (en) | 2016-11-23 |
| CN106155770B true CN106155770B (en) | 2019-11-26 |
Family
ID=57340307
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510145555.XA Active CN106155770B (en) | 2015-03-30 | 2015-03-30 | Method for scheduling task and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106155770B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106850354A (en) * | 2017-02-22 | 2017-06-13 | 郑州云海信息技术有限公司 | A kind of processing method and processing device of Single Point of Faliure |
| CN111818159B (en) * | 2020-07-08 | 2024-04-05 | 腾讯科技（深圳）有限公司 | Management method, device, equipment and storage medium of data processing node |
| CN114691241B (en) * | 2022-04-19 | 2024-01-19 | 中煤航测遥感集团有限公司 | Task execution method, device, electronic equipment and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6041425A (en) * | 1996-09-03 | 2000-03-21 | Hitachi, Ltd. | Error recovery method and apparatus in a computer system |
| US7900206B1 (en) * | 2004-03-31 | 2011-03-01 | Symantec Operating Corporation | Information technology process workflow for data centers |
| CN103019889A (en) * | 2012-12-21 | 2013-04-03 | 曙光信息产业(北京)有限公司 | Distributed file system and failure processing method thereof |
| CN103051691A (en) * | 2012-12-12 | 2013-04-17 | 华为技术有限公司 | Subarea distribution method, device and distributed type storage system |
| CN103259832A (en) * | 2012-12-24 | 2013-08-21 | 中国科学院沈阳自动化研究所 | Cluster resource control method for achieving dynamic load balance, fault diagnosis and failover |
| CN103440160A (en) * | 2013-08-15 | 2013-12-11 | 华为技术有限公司 | Virtual machine recovering method and virtual machine migration method , device and system |
| CN104461752A (en) * | 2014-11-21 | 2015-03-25 | 浙江宇视科技有限公司 | Two-level fault-tolerant multimedia distributed task processing method |
-
2015
- 2015-03-30 CN CN201510145555.XA patent/CN106155770B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6041425A (en) * | 1996-09-03 | 2000-03-21 | Hitachi, Ltd. | Error recovery method and apparatus in a computer system |
| US7900206B1 (en) * | 2004-03-31 | 2011-03-01 | Symantec Operating Corporation | Information technology process workflow for data centers |
| CN103051691A (en) * | 2012-12-12 | 2013-04-17 | 华为技术有限公司 | Subarea distribution method, device and distributed type storage system |
| CN103019889A (en) * | 2012-12-21 | 2013-04-03 | 曙光信息产业(北京)有限公司 | Distributed file system and failure processing method thereof |
| CN103259832A (en) * | 2012-12-24 | 2013-08-21 | 中国科学院沈阳自动化研究所 | Cluster resource control method for achieving dynamic load balance, fault diagnosis and failover |
| CN103440160A (en) * | 2013-08-15 | 2013-12-11 | 华为技术有限公司 | Virtual machine recovering method and virtual machine migration method , device and system |
| CN104461752A (en) * | 2014-11-21 | 2015-03-25 | 浙江宇视科技有限公司 | Two-level fault-tolerant multimedia distributed task processing method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106155770A (en) | 2016-11-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8635493B2 (en) | High availability system allowing conditionally reserved computing resource use and reclamation upon a failover | |
| EP3036625B1 (en) | Virtual hadoop manager | |
| CN108334396B (en) | Data processing method and device, and resource group creation method and device | |
| US9727358B2 (en) | Failover detection and treatment in checkpoint systems | |
| CN106326002B (en) | Resource scheduling method, device and equipment | |
| US9189381B2 (en) | Managing CPU resources for high availability micro-partitions | |
| US20080295095A1 (en) | Method of monitoring performance of virtual computer and apparatus using the method | |
| US9558082B2 (en) | VM availability during migration and VM network failures in host computing systems | |
| CN103201724A (en) | Providing application high availability in highly-available virtual machine environments | |
| US20120096205A1 (en) | Inter-virtual machine profiling | |
| KR20140080434A (en) | Device and method for optimization of data processing in a mapreduce framework | |
| WO2012166106A1 (en) | Estimating a performance parameter of a job having map and reduce tasks after a failure | |
| US9244825B2 (en) | Managing CPU resources for high availability micro-partitions | |
| CN106155770B (en) | Method for scheduling task and electronic equipment | |
| US20150378782A1 (en) | Scheduling of tasks on idle processors without context switching | |
| CN110609749B (en) | Distributed task operation method, system and equipment | |
| US9043575B2 (en) | Managing CPU resources for high availability micro-partitions | |
| US10310890B2 (en) | Control method for virtual machine system, and virtual machine system | |
| CN104239120A (en) | State information synchronization method, state information synchronization device and state information synchronization system for virtual machine | |
| CN106874103B (en) | Heartbeat implementation method and device | |
| CN107506293B (en) | Software performance data acquisition method and device | |
| US9612907B2 (en) | Power efficient distribution and execution of tasks upon hardware fault with multiple processors | |
| CN109753338A (en) | The detection method and device of virtual GPU utilization rate | |
| CN115277398A (en) | Cluster network configuration method and device | |
| JP5905412B2 (en) | Virtual computer system and processor performance measurement method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |