CN102096602A - Task scheduling method, and system and equipment thereof - Google Patents
Task scheduling method, and system and equipment thereof Download PDFInfo
- Publication number
- CN102096602A CN102096602A CN2009102424854A CN200910242485A CN102096602A CN 102096602 A CN102096602 A CN 102096602A CN 2009102424854 A CN2009102424854 A CN 2009102424854A CN 200910242485 A CN200910242485 A CN 200910242485A CN 102096602 A CN102096602 A CN 102096602A
- Authority
- CN
- China
- Prior art keywords
- task
- node
- working node
- working
- resources
- 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
Images
Landscapes
- Multi Processors (AREA)
Abstract
The invention discloses a task scheduling method, and a system and equipment thereof. The method provided by the invention is applied to a data processing system which is provided with a main node and a plurality of working nodes, wherein the main node is used for scheduling tasks, and the working nodes are used for executing the tasks. The method comprises the following steps that: each working node transmits a request for acquiring a task to the main node, wherein the request carries available resources of the working node and the used resources of each task executed on the working node; and the main node determines resource demand of each type of tasks on the main node according to the used resource of each task which is transmitted by each working node and executed on each node and schedules the tasks for the working nodes according to the determined resource demand of each type of tasks and the available resources of the working node which transmits the request. By the method, the system and the equipment, overload of the working node can be avoided and the resource utilization ratio of the working node can be improved so as to improve the operating efficiency of the data processing system, particularly a MapReduce system.
Description
Technical field
The present invention relates to the data processing technique of the communications field, relate in particular to a kind of method for scheduling task and system thereof and equipment.
Background technology
MapReduce is a kind of distributed multiple programming system that is used to handle the mass data collection, can automatically the MapReduce data processing task be walked abreast and turn to a plurality of subtasks, and be dispatched to one by concurrent execution on the cluster of ordinary node (as PC) structure; Simultaneously, system solves automatically to problems such as exchanges data between node failure, task inefficacy and node, make MapReduce use and to be concerned about this problem, and can realize the function of distributed data processing by definition corresponding M ap (mapping) and Reduce (abbreviation) function.
The MapReduce system mainly is made up of three modules, and its system architecture as shown in Figure 1.Client (Client) is used for the parallel processing operation (Job) that the user arranges is committed to host node (Master); The Job that Master submits client to automatically is decomposed into a plurality of Map tasks and a plurality of Reduce tasks with same treatment function (but the data of handling may be different) with same treatment function (but the input data may be different), wherein, the output data of Map task is as the input data of Reduce task, and with task scheduling to working node (Worker); Worker is to Master request task and carry out the task of asking.
Because the MapReduce system generally is structured in (as the network system of thousand level node scales) on the large-scale calculations resource, Master can't obtain the load information of all Worker and carry out the scheduling of task, so, in the MapReduce system, according to the configuration file of disposing in advance, initiatively ask task by Worker to Master.Master carries out to Worker according to Information Selection tasks such as formation configuration and job priority and scheduling.Its concrete scheduling flow can comprise as shown in Figure 2:
Step 201, Worker trigger the heartbeat message transmission flow, and trigger condition can be periodically to set or Event triggered, as when there is vacant resource in certain task system of being finished, can initiatively trigger the transmission heartbeat message;
Step 202, Worker check the configuration file of disposing in advance, record the maximum number of tasks quota that Worker can carry out in advance in the configuration file of Bu Shuing;
Step 203, Worker be according to configuration file, judges whether the task of please looking for novelty, and when the number of tasks of carrying out as Worker does not reach quota, will carry out new task to the Master request;
Step 204, Worker send heartbeat message according to judged result to Master, wherein have the mark of " whether asking task ".When new task was carried out in the Worker request, this mark was set to true; Otherwise this mark is set to false.
After step 205, Master receive the heartbeat message of Worker transmission, check the mark of " whether asking task ", when this was labeled as true, Master selected to give this Worker with certain task scheduling.Scheduler task on the Master tactful configurable, as possess with task scheduling to its redundancy scheduling or the like of the rescheduling of the nearer node of the data of handling, failed tasks, bottleneck task.
Step 206, Master return the heartbeat response to Worker, and when Worker request task, return task to Worker.
The inventor finds that there is following problem in the existing task scheduling mechanism of MapReduce system in realizing process of the present invention:
(1) Worker carries out new task according to the configuration request of disposing in advance fully, along with the continuous increase of node scale and the update of equipment, and the isomerism of different MapReduce operation resource requirements, only rely on the configuration file of disposing in advance to carry out task scheduling and can cause following problem:
When the hardware configuration of Worker task lower or operation on it takies more resource, when having taken a large amount of system resource (CPU is or/and internal memory etc.) as moving of task, if Worker does not reach its pre-configured maximum task quota as yet, it still can carry out new task to the Master request, in this case, new task not only may appear because the situation that low memory can not normally be carried out, but also can have influence on carrying out of task, even can cause Worker to break down;
When task higher or operation on it takies less resource when the hardware configuration of Worker, if Worker has reached its pre-configured maximum task quota, it will no longer carry out new task to the Master request, in this case, can cause the waste of Worker resource.
(2), when Master receives task requests from Worker, give this Worker with certain task scheduling according to self strategy for Master.Because the job behavior difference in the MapReduce system, its task is handled required stock number to be had than big-difference, what the required by task stock number that causes Master to distribute to Worker easily exceeded this Worker can stock number, cause task to carry out failure, can influence other tasks of on this Worker, moving simultaneously.
Generally speaking, in the task scheduling mechanism of current MapReduce system, on the one hand, Worker only relies on the configuration information of disposing in advance and dispatches, thereby does not cause the overload of Worker or underloading to cause the wasting of resources simultaneously in node configuration and task type; On the other hand, Master can't be with task scheduling to the suitable Worker of load, thereby causes overload or the underloading of Worker, has reduced the operational efficiency of MapReduce system.
Summary of the invention
The embodiment of the invention provides a kind of method for scheduling task and system and equipment, in order to working node overload or the low problem of resource utilization because of not considering that the working node load is caused in the task scheduling mechanism that solves the available data disposal system.
The method for scheduling task that the embodiment of the invention provides is applied to be provided with the data handling system of host node and a plurality of working nodes, and wherein, host node is used for task scheduling, and working node is used to execute the task, and this method comprises the steps:
Working node sends the request obtain task to host node, wherein carries each task resource use amount separately of carrying out on the available volume of resources of this working node and this working node;
Each task resource use amount separately of carrying out on the node separately of described host node according to each working node transmission, determine the resources requirement of each generic task on this host node, and according to the resources requirement of each generic task of determining and the available volume of resources that sends the working node of described request, for described working node carries out task scheduling.
The data handling system that the embodiment of the invention provides comprises host node equipment and a plurality of working node equipment;
Described working node equipment is used for sending the request obtain task to host node, wherein carries each task resource use amount information separately of carrying out on the available volume of resources of this working node and this working node;
Described host node equipment, each task resource use amount separately of carrying out on the node separately that is used for sending according to each working node, determine the resources requirement of each generic task on this host node, and according to the resources requirement of each generic task of determining and the available volume of resources that sends the working node of described request, for described working node carries out task scheduling.
The host node equipment that the embodiment of the invention provides is applied to be provided with the data handling system of host node equipment and a plurality of working node equipment, and wherein, working node equipment is used to carry out the task of host node devices allocation, and described host node equipment comprises:
The mission bit stream statistical module is used for after the request that receives the task of obtaining that working node sends, and each task resource use amount separately of carrying out on the node separately that sends according to each working node is determined the resources requirement of each generic task on this host node;
Task scheduling modules is used for the resources requirement of each generic task of determining according to described mission bit stream statistical module, and the available volume of resources of entrained described working node in the request that receives, for described working node carries out task scheduling.
In the above embodiment of the present invention, working node sends the available volume of resources of self and each task resource use amount separately of carrying out on it to host node, make host node when carrying out task scheduling for this working node, each task resource use amount separately of carrying out on the node separately that can send according to each working node, calculate the resources requirement of each generic task on this host node in advance, thereby can be according to the resources requirement of each generic task and the available volume of resources that sends the working node of request, for working node carries out task scheduling.Owing to when task scheduling, introduced working node load and mission requirements amount as the task scheduling foundation, therefore task of can come the Resources allocation demand to adapt according to the working node actual loading, thereby can avoid the situation of working node overload on the one hand, can improve the resource utilization of working node on the other hand, thereby improve the operational efficiency of whole data handling system.
The embodiment of the invention also provides a kind of working node equipment, to realize sending each task resource use amount separately of carrying out on the available volume of resources of working node and this working node to host node equipment, carries out the foundation of task scheduling as host node equipment.
The working node equipment that the embodiment of the invention provides, be applied to be provided with the data handling system of host node equipment and a plurality of working node equipment, wherein, host node equipment is used for task scheduling, working node equipment comprises task execution module, be used to carry out the task that host node distributes, described working node equipment also comprises:
The monitoring resource module is used to monitor each task resource use amount separately of carrying out on the available volume of resources of working node and this working node;
Sending module is used for sending the request obtain task to host node, wherein carry described monitoring resource module monitors to the available volume of resources of this working node and this working node on each task resource use amount separately of carrying out.
The above embodiment of the present invention, by sending to host node when obtaining the request of task, each task resource use amount separately of carrying out on the available volume of resources of working node and this working node is sent to host node equipment, for host node equipment adopts the available volume of resources of the resources requirement of task and working node for providing assurance according to carrying out task scheduling.
Description of drawings
Fig. 1 is the configuration diagram of existing MapReduce system;
Fig. 2 is existing MapReduce system task scheduling flow synoptic diagram;
Worker in the MapReduce system that Fig. 3 provides for the embodiment of the invention and the structural representation of Master;
The MapReduce system task scheduling flow synoptic diagram that Fig. 4 provides for the embodiment of the invention.
Embodiment
At the problems referred to above that the task scheduling mechanism of existing MepReduce system exists, the embodiment of the invention has proposed a kind of MapReduce of being applicable to system and based on the task scheduling scheme of Worker actual loading.
Described task scheduling scheme may be implemented as a kind of method for scheduling task, also may be implemented as a kind of MapReduce system, and relevant equipment; And, may be implemented as hardware, also may be implemented as software, perhaps be implemented as the combination of software and hardware.Describe the present invention below in conjunction with accompanying drawing and specific embodiment.
The framework of the MapReduce system that the embodiment of the invention provided but improves respectively Worker and Master wherein as shown in Figure 1.
For Worker, increased following function:
Worker can be according to self loading condition or resource operating position, whether decision carries out new task to the Master request, thereby when the Worker load is higher, even it does not reach the maximum task quota of configuration file defined, still do not ask to carry out new task, and when the Worker load was low, even it has reached maximum task quota, still new task was carried out in request;
Worker reports the available volume of resources of self simultaneously to Master when Master request task, with and go up the resource use amount statistical information of each task of operation, carry out the foundation of task scheduling as Master.
For Master, increased following function:
The task that Master reports according to Worker is carried out the information of used resource, and the every generic task of statistical study is carried out required stock number.Because in the Mapreduce system, the same generic task of all of same Job, may be different but treatment scheme is identical as the input data of all Map tasks and all Reduce tasks, therefore a plurality of Map tasks and a plurality of Reduce task of same operation have similar resources requirement, so required stock number when used stock number can reflect this generic task execution when certain Map task or Reduce task are carried out on certain Worker.Report on it information of the used stock number of carrying out of task by Worker to Master, Master can progressively accurately grasp such task resource demand, thereby provides foundation for task scheduling;
Master receives Worker when obtaining the request of new task, the available volume of resources of this Worker self that reports according to this Worker, and each generic task that Master counts is carried out required resource use amount, for this Worker distributes suitable task, can not surpass the load tolerance range of this Worker so that distribute to the resources requirement of the task of this Worker as far as possible, and make full use of the load capacity of this Worker as far as possible.
According to the above-mentioned functions that Worker and Master realized, internal module structure and the annexation of Worker and Master can be as shown in Figure 3, and Fig. 3 only shows the structure of a Master and a Worker and the annexation between each module.
As shown in Figure 3, among the Worker except comprising that (this module is used for the reception of signal and send handles transceiver module 301, as the transmission of heartbeat signal and the reception of heartbeat response signal), beyond the task execution module 302 conventional modules such as (this module are used to carry out the task of asking from Master), also comprise monitoring resource module 303 and task requests decision-making module 304, wherein, monitoring resource module 303 is newly-increased modules, and task requests decision-making module 304 can improve on the basis of original task requests decision-making module and obtain.
Monitoring resource module 303: on the one hand, the load of monitoring Worker itself, the stock number operating position that comprises CPU, Mem (internal memory) or Disk (disk) etc. as stock number and the spendable stock number of having used of residue, and can offer monitored results task requests decision-making module 304; On the other hand, monitoring Worker goes up the employed stock number of each task, the resource operating position that can comprise CPU, Mem (internal memory) or Disk (disk) etc., and the stock number that each task can be used and the available volume of resources of this Worker send to Master by transceiver module 301.For each task on the Worker, can monitor and add up employed stock number when task is carried out in a period of time, employed maximum resource amount was carried out employed stock number as this task and is reported when preferably this task that statistics in this section period can be obtained was carried out, and can avoid like this owing to task being carried out Master that employed stock number statistics inaccurate (being lower than the required maximum resource amount of this task actual motion as statistics) causes with the situation of task scheduling to the Worker of surplus resources deficiency as far as possible.
Task requests decision-making module 304: the task requests decision rule of getting rid of original task quota based on pre-configured file defined, judge whether the task of please looking for novelty and be improved to the node load situation that is monitored according to monitoring resource module 303, and the result of decision can be sent to transceiver module 301 and send to Master so that it generates heartbeat signal.Concrete, if specified conditions are satisfied in judgement, promptly the node load amount is no more than the charge capacity threshold value of setting, then carries out new task to the Master request, otherwise will not ask new task; These specified conditions can be expressed as:
(LCPU＜TCPU)&&(LMEM＜TMEM)&&(LDISK＜TDISK)
Wherein, L
*Be the current load of Worker, T
*It is the threshold value that system budget is provided with; This condition shows: the CPU use amount threshold value that is no more than default when the CPU of Worker use amount, and the internal memory use amount of Worker is no more than the internal memory use amount threshold value of default, and the disk use amount of Worker then can ask to carry out new task when being no more than the disk use amount threshold value of default.
Above conditional expression only is an example; in fact; can be out of shape this expression formula; as reducing the judgement factor (as the disk use amount not being judged) wherein; perhaps increase other and judge the factor; as long as can whether surpass the charge capacity threshold value of default by the charge capacity that expression formula is judged Worker, all should be within protection scope of the present invention.
As shown in Figure 3, among the Master except comprising that (this module is used for the reception of signal and send handles transceiver module 310, as the reception of heartbeat signal and the transmission of heartbeat response signal) etc. beyond the conventional module, also comprise: mission bit stream statistical module 311 and task scheduling modules 312, wherein, mission bit stream statistical module 311 is newly-increased modules, and task scheduling modules 312 can be improved on the basis of original task scheduling modules and obtain.
Mission bit stream statistical module 311: be mainly used in receive that each Worker sends carry out the information of used resource about task, and carry out statistical study, thereby obtain every generic task and carry out required stock number, carry out the foundation of task scheduling as task scheduling modules 312;
Task scheduling modules 312: when carrying out task scheduling with existing task scheduling modules, do not consider that each task carries out required stock number and compare, task scheduling modules 312 after the improvement, after the available volume of resources of its node that the request and the Worker of the task of obtaining that receives the Worker transmission send, carry out required stock number according to every generic task that mission bit stream statistical module 311 is counted, select the resource requirement amount to give this Worker less than the Task Distribution of this Worker available volume of resources.
Need to prove; the Module Division mode of above Worker and Master only is a kind of in the various possible Module Division modes; those skilled in the art should be understood that; as long as make Worker and Master possess above-mentioned functions; whether it is divided into different modules or how divides module, can not be construed as limiting protection scope of the present invention.
Structure with Worker shown in Figure 3 and Master is an example below, and in conjunction with flow process shown in Figure 4, the task scheduling process is described in detail.As shown in Figure 4, this flow process comprises:
Step 401, Worker trigger the heartbeat message transmission flow.It can be the transmission of periodic triggers heartbeat message, also can be based on the transmission of Event triggered heartbeat message, as when there is vacant resource in certain task system of being finished or node surplus yield (as DISK) when not enough, can initiatively trigger the transmission heartbeat message.
Task requests decision-making module 304 among step 402, the Worker from monitoring resource module 303 read current self charge capacity (as CPU/MEM/DISK etc.) with and each task of operation take the statistical information of stock number.
Wherein, monitoring resource module 303 can use the methods such as mean value of certain class resource (as CPU) to calculate on node by each process of statistics task.Monitoring resource module 303 can be monitored and add up according to the measurement period of setting.
Task requests decision-making module 304 among step 403, the Worker judges whether request execution new task according to the node load component analysis that gets access to from monitoring resource module 303.If the node load amount does not surpass the charge capacity threshold value of system's regulation, then new task is carried out in request, otherwise does not ask to carry out new task.
The transceiver module 301 of step 404, Worker sends heartbeat message to Master, have in the heartbeat message Worker node available volume of resources that " whether asking task " mark, monitoring resource module 303 monitor and count on and go up the stock number information that each task of moving takies.When the task requests decision-making module 304 of Worker was determined to carry out new task, this mark was set to true; Otherwise this mark is set to false.
The transceiver module 310 of step 405, Master receives the heartbeat message that Worker sends, the stock number that each task that mission bit stream statistical module 311 upward moves according to this Worker that carries in the heartbeat message takies, and the stock number that takies of its each task moved on node separately that sends with reference to other Worker, calculate every generic task and carry out required stock number.
" whether asking task " mark in the task scheduling modules 312 inspection heartbeat message of step 406, Master and the node available volume of resources of Worker.When " whether asking task " when mark value is true, Master carries out required stock number according to every generic task that mission bit stream statistical module 311 calculates, choose the task-set that resources requirement is no more than Worker node available volume of resources, and the selection task is dispatched to this Worker also from this task-set.
Step 407, Master return the heartbeat response to Worker, have distributed task if Master is Worker, then will return to Worker for the task that this Worker distributes.
After Worker received the task that Master returns, task execution module 302 was carried out receiving of task.
In the above-mentioned flow process, if current task of not having resources requirement to be no more than Worker node available volume of resources among the Master in the step 406 then can be returned the information of task scheduling failure to Worker, and finish this flow process.
According to above description as can be seen, compare with existing scheme, on the one hand, Worker determines whether to ask to carry out new task according to the actual loading situation, eliminated to a certain extent in the existing scheme and only judged Worker node overload or the underloaded problem of being brought, thereby can better guarantee normal, the efficient execution of Worker based on the configuration file of disposing in advance; On the other hand, the information that Master sends according to Worker about each task use stock number, the employed stock number of the every generic task of statistical study, thereby can be more accurately give Worker, avoided Worker to a certain extent because surplus resources is not enough and carry out the overload phenomenon that new task causes with suitable task scheduling.
In the another embodiment of the present invention, the task requests decision-making module of Worker still adopts existing mode to judge whether to ask to carry out new task, promptly, when if the task quantity on the Worker does not reach the task amount quota then ask to carry out new task, but unlike the prior art be also to send the resource use amount of carrying out on the available volume of resources of this node that the monitoring resource module monitored and this node of task with heartbeat message; Master is after the request of the execution new task that receives the Worker transmission, the resource use amount of carrying out on the node separately that the mission bit stream statistical module reports according to each Worker of task, determine that Master goes up the resources requirement of each task, the resources requirement of each task of being determined according to the mission bit stream statistical module by task scheduling modules and the available volume of resources of this Worker are carried out task scheduling then, concrete, give this Worker with resources requirement less than the Task Distribution of Worker current available resource amount, if there is not such task to distribute, then Master can return the response of Task Distribution failure.
This embodiment at Worker in request during task, the situation that its load is bigger, Task Distribution that can resources requirement is less is relatively given this Worker, perhaps do not distribute new task to give this Worker, thereby compare the load pressure that to alleviate Worker to a certain extent with existing task scheduling mechanism; At Worker in request during task, the situation that its load is less, Task Distribution that can resources requirement is relatively large is given this Worker, thereby compares the resource utilization that can improve Worker to a certain extent with existing task scheduling mechanism.
The above embodiment of the present invention is not only applicable to the MapReduce system, also applicable to the data handling system of similar structures, as be provided with the data handling system of host node and a plurality of working nodes, wherein, host node is used for task scheduling, and working node is used to execute the task.
Obviously, those skilled in the art can carry out various changes and modification to the present invention and not break away from the spirit and scope of the present invention.Like this, if of the present invention these are revised and modification belongs within the scope of claim of the present invention and equivalent technologies thereof, then the present invention also is intended to comprise these changes and modification interior.
Claims (17)
1. method for scheduling task is applied to be provided with the data handling system of host node and a plurality of working nodes, and wherein, host node is used for task scheduling, and working node is used to execute the task, and it is characterized in that, comprises the steps:
Working node sends the request obtain task to host node, wherein carries each task resource use amount separately of carrying out on the available volume of resources of this working node and this working node;
Each task resource use amount separately of carrying out on the node separately of described host node according to each working node transmission, determine the resources requirement of each generic task on this host node, and according to the resources requirement of each generic task of determining and the available volume of resources that sends the working node of described request, for described working node carries out task scheduling.
2. the method for claim 1 is characterized in that, described host node is a described working node when carrying out task scheduling, and the Task Distribution that resources requirement is no more than the available volume of resources of this working node is given this working node.
3. the method for claim 1 is characterized in that, the resource use amount that working node sends to the task of host node is the maximum resource use amount of this task in setting duration.
4. the method for claim 1 is characterized in that, working node sends the request of obtaining task by heartbeat message when triggering the transmission heartbeat message;
Each node in each working node sends to host node with each task resource use amount separately of carrying out on it by heartbeat message when triggering the transmission heartbeat message.
5. as each described method of claim 1 to 4, it is characterized in that, when working node is no more than the charge capacity threshold value of setting in the charge capacity of judging himself, send the request of obtaining task to host node.
6. as each described method of claim 1 to 4, it is characterized in that described data handling system is the MapReduce system.
7. working node equipment, be applied to be provided with the data handling system of host node equipment and a plurality of working node equipment, wherein, host node equipment is used for task scheduling, working node equipment comprises task execution module, be used to carry out the task that host node distributes, it is characterized in that described working node equipment also comprises:
The monitoring resource module is used to monitor each task resource use amount separately of carrying out on the available volume of resources of working node and this working node;
Sending module is used for sending the request obtain task to host node, wherein carry described monitoring resource module monitors to the available volume of resources of this working node and this working node on each task resource use amount separately of carrying out.
8. working node equipment as claimed in claim 7 is characterized in that, described sending module specifically is used for: with described monitoring resource module monitors to the maximum resource use amount of task in setting duration send.
9. working node equipment as claimed in claim 7 is characterized in that, described sending module specifically is used for: when triggering the transmission heartbeat message, send the request of obtaining task by heartbeat message.
10. as each described working node equipment of claim 7 to 9, it is characterized in that, also comprise:
The task requests decision-making module is used for the available volume of resources at the working node that arrives according to described monitoring resource module monitors, when the charge capacity of judging this working node is no more than the charge capacity threshold value of setting, indicates described sending module to send the request of obtaining task;
Described sending module is further used for, and sends the request of obtaining task according to the indication of described task requests decision-making module.
11. a host node equipment is applied to be provided with the data handling system of host node equipment and a plurality of working node equipment, wherein, working node equipment is used to carry out the task of host node devices allocation, it is characterized in that, described host node equipment comprises:
The mission bit stream statistical module is used for after the request that receives the task of obtaining that working node sends, and each task resource use amount separately of carrying out on the node separately that sends according to each working node is determined the resources requirement of each generic task on this host node;
Task scheduling modules is used for the resources requirement of each generic task of determining according to described mission bit stream statistical module, and the available volume of resources of entrained described working node in the request that receives, for described working node carries out task scheduling.
12. host node equipment as claimed in claim 11 is characterized in that, described task scheduling modules specifically is used for: the Task Distribution that resources requirement is no more than the available volume of resources of this working node is given this working node.
13. host node equipment as claimed in claim 11, it is characterized in that, described mission bit stream statistical module specifically is used for: receive each working node when triggering the transmission heartbeat message, parse each task resource use amount separately that working node is carried out from heartbeat message.
14. a data handling system is characterized in that, comprises host node equipment and a plurality of working node equipment;
Described working node equipment is used for sending the request obtain task to host node, wherein carries each task resource use amount information separately of carrying out on the available volume of resources of this working node and this working node;
Described host node equipment, each task resource use amount separately of carrying out on the node separately that is used for sending according to each working node, determine the resources requirement of each generic task on this host node, and according to the resources requirement of each generic task of determining and the available volume of resources that sends the working node of described request, for described working node carries out task scheduling.
15. data handling system as claimed in claim 14 is characterized in that, described host node is a described working node when carrying out task scheduling, and the Task Distribution that resources requirement is no more than the available volume of resources of this working node is given this working node.
16. data handling system as claimed in claim 14 is characterized in that, when described working node is no more than the charge capacity threshold value of setting in the charge capacity of judging himself, sends the request of obtaining task to host node.
17., it is characterized in that described data handling system is the MapReduce system as each described data handling system of claim 14 to 16.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2009102424854A CN102096602A (en) | 2009-12-15 | 2009-12-15 | Task scheduling method, and system and equipment thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2009102424854A CN102096602A (en) | 2009-12-15 | 2009-12-15 | Task scheduling method, and system and equipment thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN102096602A true CN102096602A (en) | 2011-06-15 |
Family
ID=44129709
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2009102424854A Pending CN102096602A (en) | 2009-12-15 | 2009-12-15 | Task scheduling method, and system and equipment thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102096602A (en) |
Cited By (51)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102541640A (en) * | 2011-12-28 | 2012-07-04 | 厦门市美亚柏科信息股份有限公司 | Cluster GPU (graphic processing unit) resource scheduling system and method |
| CN102638456A (en) * | 2012-03-19 | 2012-08-15 | 杭州海康威视系统技术有限公司 | Intelligent analysis method for mass real-time video code stream based on cloud computation and system thereof |
| CN102866918A (en) * | 2012-07-26 | 2013-01-09 | 中国科学院信息工程研究所 | Resource management system for distributed programming framework |
| CN103019853A (en) * | 2012-11-19 | 2013-04-03 | 北京亿赞普网络技术有限公司 | Method and device for dispatching job task |
| CN103246550A (en) * | 2012-02-09 | 2013-08-14 | 深圳市腾讯计算机系统有限公司 | Multitask dispatching method and system based on capacity |
| CN103279351A (en) * | 2013-05-31 | 2013-09-04 | 北京高森明晨信息科技有限公司 | Method and device for task scheduling |
| CN103279386A (en) * | 2013-06-09 | 2013-09-04 | 浪潮电子信息产业股份有限公司 | Method for achieving high availability of computer operation scheduling system |
| CN103500119A (en) * | 2013-09-06 | 2014-01-08 | 西安交通大学 | Task allocation method based on pre-dispatch |
| CN103763373A (en) * | 2014-01-23 | 2014-04-30 | 浪潮(北京)电子信息产业有限公司 | Method for dispatching based on cloud computing and dispatcher |
| CN103793272A (en) * | 2013-12-27 | 2014-05-14 | 北京天融信软件有限公司 | Periodical task scheduling method and periodical task scheduling system |
| CN103885832A (en) * | 2012-12-20 | 2014-06-25 | 华为技术有限公司 | Resource allocating method, equipment and system |
| CN104050042A (en) * | 2014-05-30 | 2014-09-17 | 北京先进数通信息技术股份公司 | Resource allocation method and resource allocation device for ETL (Extraction-Transformation-Loading) jobs |
| CN104077188A (en) * | 2013-03-29 | 2014-10-01 | 西门子公司 | Method and device for scheduling tasks |
| CN104102949A (en) * | 2014-06-27 | 2014-10-15 | 北京奇艺世纪科技有限公司 | Distributed workflow device and method for processing workflow by distributed workflow device |
| CN104317650A (en) * | 2014-10-10 | 2015-01-28 | 北京工业大学 | Map/Reduce type mass data processing platform-orientated job scheduling method |
| CN104407923A (en) * | 2014-10-31 | 2015-03-11 | 百度在线网络技术（北京）有限公司 | Cluster task balancing method and device based on single node triggering |
| CN104424189A (en) * | 2013-08-20 | 2015-03-18 | 中国电信集团公司 | Positioning resolving method and positioning resolving system based on cloud platform |
| CN104520815A (en) * | 2014-03-17 | 2015-04-15 | 华为技术有限公司 | Method, device and equipment for task scheduling |
| CN104536767A (en) * | 2015-01-14 | 2015-04-22 | 国家电网公司 | Task processing method and device for bay level of intelligent substation |
| WO2015180340A1 (en) * | 2014-05-30 | 2015-12-03 | 华为技术有限公司 | Data mining method and device |
| CN105159769A (en) * | 2015-09-11 | 2015-12-16 | 国电南瑞科技股份有限公司 | Distributed job scheduling method suitable for heterogeneous computational capability cluster |
| CN106484524A (en) * | 2015-08-28 | 2017-03-08 | 阿里巴巴集团控股有限公司 | A kind of task processing method and device |
| WO2017045576A1 (en) * | 2015-09-18 | 2017-03-23 | Huawei Technologies Co., Ltd. | System and method for resource management |
| CN103761148B (en) * | 2014-01-26 | 2017-04-05 | 北京京东尚科信息技术有限公司 | The control method of cluster timer-triggered scheduler task |
| CN106600220A (en) * | 2016-11-29 | 2017-04-26 | 叶飞 | Distributed calculation method |
| CN106598735A (en) * | 2016-12-13 | 2017-04-26 | 广东金赋科技股份有限公司 | Distributive calculation method, main control node, calculation node and system |
| CN106776025A (en) * | 2016-12-16 | 2017-05-31 | 郑州云海信息技术有限公司 | A kind of computer cluster job scheduling method and its device |
| CN106878356A (en) * | 2015-12-11 | 2017-06-20 | 中国移动通信集团公司 | A kind of dispatching method and calculate node |
| CN106940656A (en) * | 2016-01-04 | 2017-07-11 | 阿里巴巴集团控股有限公司 | A kind of method for scheduling task and device |
| CN107066332A (en) * | 2017-01-25 | 2017-08-18 | 广东神马搜索科技有限公司 | Distributed system and its dispatching method and dispatching device |
| CN107423122A (en) * | 2017-07-25 | 2017-12-01 | 苏州博纳讯动软件有限公司 | A kind of complicated O＆M operation layout and scheduling system and method |
| CN107580023A (en) * | 2017-08-04 | 2018-01-12 | 山东大学 | A kind of the stream process job scheduling method and system of dynamic adjustment task distribution |
| CN107688496A (en) * | 2017-07-24 | 2018-02-13 | 上海壹账通金融科技有限公司 | Task distribution formula processing method, device, storage medium and server |
| CN107977257A (en) * | 2016-10-25 | 2018-05-01 | 杭州海康威视数字技术股份有限公司 | A kind of method for scheduling task and device |
| CN104951372B (en) * | 2015-06-16 | 2018-07-31 | 北京工业大学 | A kind of Map/Reduce data processing platform (DPP) memory source dynamic allocation methods based on prediction |
| WO2018176998A1 (en) * | 2017-03-29 | 2018-10-04 | 华为技术有限公司 | Data storage method and device |
| CN109408236A (en) * | 2018-10-22 | 2019-03-01 | 福建南威软件有限公司 | A kind of task load equalization methods of ETL on cluster |
| CN109710391A (en) * | 2018-12-20 | 2019-05-03 | 西安四叶草信息技术有限公司 | Method for scheduling task and equipment |
| CN110069329A (en) * | 2019-04-15 | 2019-07-30 | 北京达佳互联信息技术有限公司 | A kind of task processing method, device, server and storage medium |
| CN110502800A (en) * | 2019-07-25 | 2019-11-26 | 上海理工大学 | A kind of product data model modeling method based on parallel computation |
| CN110928679A (en) * | 2019-10-16 | 2020-03-27 | 华为技术有限公司 | Resource allocation method and device |
| CN111026527A (en) * | 2019-11-18 | 2020-04-17 | 江苏艾佳家居用品有限公司 | Distribution execution system for processing mass timing tasks |
| WO2020186781A1 (en) * | 2019-03-18 | 2020-09-24 | 平安普惠企业管理有限公司 | Test code handover control method and apparatus, electronic device, and computer non-volatile readable storage medium |
| CN111783102A (en) * | 2020-06-30 | 2020-10-16 | 福建健康之路信息技术有限公司 | Method for safely expelling nodes in Kubernetes cluster and storage device |
| CN112148462A (en) * | 2020-10-20 | 2020-12-29 | 上海新炬网络信息技术股份有限公司 | Jenkins-based CICD process processing method |
| CN112817721A (en) * | 2021-01-29 | 2021-05-18 | 中国平安财产保险股份有限公司 | Task scheduling method and device based on artificial intelligence, computer equipment and medium |
| CN112887407A (en) * | 2021-01-26 | 2021-06-01 | 北京百度网讯科技有限公司 | Job flow control method and device for distributed cluster |
| US11032858B2 (en) | 2017-03-28 | 2021-06-08 | Huawei Technologies Co., Ltd. | Network access method, terminal, access network, and core network |
| CN113608878A (en) * | 2021-08-18 | 2021-11-05 | 上海德拓信息技术股份有限公司 | Task distributed scheduling method and system based on resource weight calculation |
| CN113760549A (en) * | 2021-08-30 | 2021-12-07 | 聚好看科技股份有限公司 | Pod deployment method and device |
| CN114840343A (en) * | 2022-05-16 | 2022-08-02 | 江苏安超云软件有限公司 | Task scheduling method and system based on distributed system |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101013386A (en) * | 2007-02-06 | 2007-08-08 | 华中科技大学 | Grid task scheduling method based on feedback mechanism |
| US20080209434A1 (en) * | 2007-02-28 | 2008-08-28 | Tobias Queck | Distribution of data and task instances in grid environments |
-
2009
- 2009-12-15 CN CN2009102424854A patent/CN102096602A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101013386A (en) * | 2007-02-06 | 2007-08-08 | 华中科技大学 | Grid task scheduling method based on feedback mechanism |
| US20080209434A1 (en) * | 2007-02-28 | 2008-08-28 | Tobias Queck | Distribution of data and task instances in grid environments |
Non-Patent Citations (1)
| Title |
|---|
| 万至臻: "基于MapReduce模型的并行计算平台的设计与实现", 《中国优秀硕士学位论文全文数据库》 * |
Cited By (81)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102541640A (en) * | 2011-12-28 | 2012-07-04 | 厦门市美亚柏科信息股份有限公司 | Cluster GPU (graphic processing unit) resource scheduling system and method |
| CN102541640B (en) * | 2011-12-28 | 2014-10-29 | 厦门市美亚柏科信息股份有限公司 | Cluster GPU (graphic processing unit) resource scheduling system and method |
| WO2013117136A1 (en) * | 2012-02-09 | 2013-08-15 | 腾讯科技（深圳）有限公司 | Capacity-based multi-task scheduling method, device and system |
| CN103246550A (en) * | 2012-02-09 | 2013-08-14 | 深圳市腾讯计算机系统有限公司 | Multitask dispatching method and system based on capacity |
| CN102638456B (en) * | 2012-03-19 | 2015-09-23 | 杭州海康威视数字技术股份有限公司 | Based on magnanimity real-time video code stream intelligent analysis method and the system thereof of cloud computing |
| CN102638456A (en) * | 2012-03-19 | 2012-08-15 | 杭州海康威视系统技术有限公司 | Intelligent analysis method for mass real-time video code stream based on cloud computation and system thereof |
| CN102866918B (en) * | 2012-07-26 | 2016-02-24 | 中国科学院信息工程研究所 | The resource management system of Based on Distributed programming framework |
| CN102866918A (en) * | 2012-07-26 | 2013-01-09 | 中国科学院信息工程研究所 | Resource management system for distributed programming framework |
| CN103019853A (en) * | 2012-11-19 | 2013-04-03 | 北京亿赞普网络技术有限公司 | Method and device for dispatching job task |
| CN103885832A (en) * | 2012-12-20 | 2014-06-25 | 华为技术有限公司 | Resource allocating method, equipment and system |
| CN104077188A (en) * | 2013-03-29 | 2014-10-01 | 西门子公司 | Method and device for scheduling tasks |
| CN103279351B (en) * | 2013-05-31 | 2016-06-29 | 北京高森明晨信息科技有限公司 | A kind of method of task scheduling and device |
| CN103279351A (en) * | 2013-05-31 | 2013-09-04 | 北京高森明晨信息科技有限公司 | Method and device for task scheduling |
| CN103279386A (en) * | 2013-06-09 | 2013-09-04 | 浪潮电子信息产业股份有限公司 | Method for achieving high availability of computer operation scheduling system |
| CN104424189A (en) * | 2013-08-20 | 2015-03-18 | 中国电信集团公司 | Positioning resolving method and positioning resolving system based on cloud platform |
| CN103500119A (en) * | 2013-09-06 | 2014-01-08 | 西安交通大学 | Task allocation method based on pre-dispatch |
| CN103500119B (en) * | 2013-09-06 | 2017-01-04 | 西安交通大学 | A kind of method for allocating tasks based on pre-scheduling |
| CN103793272A (en) * | 2013-12-27 | 2014-05-14 | 北京天融信软件有限公司 | Periodical task scheduling method and periodical task scheduling system |
| CN103793272B (en) * | 2013-12-27 | 2017-05-24 | 北京天融信软件有限公司 | Periodical task scheduling method and periodical task scheduling system |
| CN103763373A (en) * | 2014-01-23 | 2014-04-30 | 浪潮(北京)电子信息产业有限公司 | Method for dispatching based on cloud computing and dispatcher |
| CN103761148B (en) * | 2014-01-26 | 2017-04-05 | 北京京东尚科信息技术有限公司 | The control method of cluster timer-triggered scheduler task |
| CN104520815B (en) * | 2014-03-17 | 2019-03-01 | 华为技术有限公司 | A kind of method and device of task schedule |
| WO2015139164A1 (en) * | 2014-03-17 | 2015-09-24 | 华为技术有限公司 | Task scheduling method, apparatus and device |
| CN104520815A (en) * | 2014-03-17 | 2015-04-15 | 华为技术有限公司 | Method, device and equipment for task scheduling |
| US10216542B2 (en) | 2014-03-17 | 2019-02-26 | Huawei Technologies Co., Ltd. | Resource comparison based task scheduling method, apparatus, and device |
| WO2015180340A1 (en) * | 2014-05-30 | 2015-12-03 | 华为技术有限公司 | Data mining method and device |
| US10606867B2 (en) | 2014-05-30 | 2020-03-31 | Huawei Technologies Co., Ltd. | Data mining method and apparatus |
| CN105205052B (en) * | 2014-05-30 | 2019-01-25 | 华为技术有限公司 | A kind of data digging method and device |
| CN104050042A (en) * | 2014-05-30 | 2014-09-17 | 北京先进数通信息技术股份公司 | Resource allocation method and resource allocation device for ETL (Extraction-Transformation-Loading) jobs |
| CN104050042B (en) * | 2014-05-30 | 2017-06-13 | 北京先进数通信息技术股份公司 | The resource allocation methods and device of ETL operations |
| CN104102949B (en) * | 2014-06-27 | 2018-01-26 | 北京奇艺世纪科技有限公司 | A kind of distributed work flow device and its method for handling workflow |
| CN104102949A (en) * | 2014-06-27 | 2014-10-15 | 北京奇艺世纪科技有限公司 | Distributed workflow device and method for processing workflow by distributed workflow device |
| CN104317650B (en) * | 2014-10-10 | 2018-05-01 | 北京工业大学 | A kind of job scheduling method towards Map/Reduce type mass data processing platforms |
| CN104317650A (en) * | 2014-10-10 | 2015-01-28 | 北京工业大学 | Map/Reduce type mass data processing platform-orientated job scheduling method |
| CN104407923A (en) * | 2014-10-31 | 2015-03-11 | 百度在线网络技术（北京）有限公司 | Cluster task balancing method and device based on single node triggering |
| CN104536767A (en) * | 2015-01-14 | 2015-04-22 | 国家电网公司 | Task processing method and device for bay level of intelligent substation |
| CN104951372B (en) * | 2015-06-16 | 2018-07-31 | 北京工业大学 | A kind of Map/Reduce data processing platform (DPP) memory source dynamic allocation methods based on prediction |
| CN106484524A (en) * | 2015-08-28 | 2017-03-08 | 阿里巴巴集团控股有限公司 | A kind of task processing method and device |
| CN105159769B (en) * | 2015-09-11 | 2018-06-29 | 国电南瑞科技股份有限公司 | A kind of Distributed Job Scheduling method suitable for computing capability isomeric group |
| CN105159769A (en) * | 2015-09-11 | 2015-12-16 | 国电南瑞科技股份有限公司 | Distributed job scheduling method suitable for heterogeneous computational capability cluster |
| WO2017045576A1 (en) * | 2015-09-18 | 2017-03-23 | Huawei Technologies Co., Ltd. | System and method for resource management |
| US10191771B2 (en) | 2015-09-18 | 2019-01-29 | Huawei Technologies Co., Ltd. | System and method for resource management |
| CN106878356B (en) * | 2015-12-11 | 2020-08-04 | 中国移动通信集团公司 | Scheduling method and computing node |
| CN106878356A (en) * | 2015-12-11 | 2017-06-20 | 中国移动通信集团公司 | A kind of dispatching method and calculate node |
| CN106940656A (en) * | 2016-01-04 | 2017-07-11 | 阿里巴巴集团控股有限公司 | A kind of method for scheduling task and device |
| CN107977257A (en) * | 2016-10-25 | 2018-05-01 | 杭州海康威视数字技术股份有限公司 | A kind of method for scheduling task and device |
| CN106600220A (en) * | 2016-11-29 | 2017-04-26 | 叶飞 | Distributed calculation method |
| CN106598735A (en) * | 2016-12-13 | 2017-04-26 | 广东金赋科技股份有限公司 | Distributive calculation method, main control node, calculation node and system |
| CN106776025A (en) * | 2016-12-16 | 2017-05-31 | 郑州云海信息技术有限公司 | A kind of computer cluster job scheduling method and its device |
| CN107066332A (en) * | 2017-01-25 | 2017-08-18 | 广东神马搜索科技有限公司 | Distributed system and its dispatching method and dispatching device |
| CN107066332B (en) * | 2017-01-25 | 2020-03-13 | 广东神马搜索科技有限公司 | Distributed system and scheduling method and scheduling device thereof |
| US11032858B2 (en) | 2017-03-28 | 2021-06-08 | Huawei Technologies Co., Ltd. | Network access method, terminal, access network, and core network |
| WO2018176998A1 (en) * | 2017-03-29 | 2018-10-04 | 华为技术有限公司 | Data storage method and device |
| US11575748B2 (en) | 2017-03-29 | 2023-02-07 | Huawei Technologies Co., Ltd. | Data storage method and apparatus for combining different data distribution policies |
| US10972542B2 (en) | 2017-03-29 | 2021-04-06 | Huawei Technologies Co., Ltd. | Data storage method and apparatus |
| US20200028911A1 (en) * | 2017-03-29 | 2020-01-23 | Huawei Technologies Co., Ltd. | Data Storage Method and Apparatus |
| CN107688496B (en) * | 2017-07-24 | 2020-12-04 | 深圳壹账通智能科技有限公司 | Task distributed processing method and device, storage medium and server |
| CN107688496A (en) * | 2017-07-24 | 2018-02-13 | 上海壹账通金融科技有限公司 | Task distribution formula processing method, device, storage medium and server |
| CN107423122A (en) * | 2017-07-25 | 2017-12-01 | 苏州博纳讯动软件有限公司 | A kind of complicated O＆M operation layout and scheduling system and method |
| CN107423122B (en) * | 2017-07-25 | 2020-08-18 | 苏州博纳讯动软件有限公司 | Complex operation and maintenance operation arranging and scheduling system and method thereof |
| CN107580023B (en) * | 2017-08-04 | 2020-05-12 | 山东大学 | Stream processing job scheduling method and system for dynamically adjusting task allocation |
| CN107580023A (en) * | 2017-08-04 | 2018-01-12 | 山东大学 | A kind of the stream process job scheduling method and system of dynamic adjustment task distribution |
| CN109408236A (en) * | 2018-10-22 | 2019-03-01 | 福建南威软件有限公司 | A kind of task load equalization methods of ETL on cluster |
| CN109710391A (en) * | 2018-12-20 | 2019-05-03 | 西安四叶草信息技术有限公司 | Method for scheduling task and equipment |
| WO2020186781A1 (en) * | 2019-03-18 | 2020-09-24 | 平安普惠企业管理有限公司 | Test code handover control method and apparatus, electronic device, and computer non-volatile readable storage medium |
| CN110069329A (en) * | 2019-04-15 | 2019-07-30 | 北京达佳互联信息技术有限公司 | A kind of task processing method, device, server and storage medium |
| CN110502800A (en) * | 2019-07-25 | 2019-11-26 | 上海理工大学 | A kind of product data model modeling method based on parallel computation |
| CN110928679A (en) * | 2019-10-16 | 2020-03-27 | 华为技术有限公司 | Resource allocation method and device |
| CN111026527A (en) * | 2019-11-18 | 2020-04-17 | 江苏艾佳家居用品有限公司 | Distribution execution system for processing mass timing tasks |
| CN111026527B (en) * | 2019-11-18 | 2022-07-08 | 江苏艾佳家居用品有限公司 | Distribution execution system for processing mass timing tasks |
| CN111783102B (en) * | 2020-06-30 | 2022-06-14 | 福建健康之路信息技术有限公司 | Method for safely expelling nodes in Kubernetes cluster and storage device |
| CN111783102A (en) * | 2020-06-30 | 2020-10-16 | 福建健康之路信息技术有限公司 | Method for safely expelling nodes in Kubernetes cluster and storage device |
| CN112148462A (en) * | 2020-10-20 | 2020-12-29 | 上海新炬网络信息技术股份有限公司 | Jenkins-based CICD process processing method |
| CN112148462B (en) * | 2020-10-20 | 2023-03-28 | 上海新炬网络信息技术股份有限公司 | Jenkins-based CICD process processing method |
| CN112887407A (en) * | 2021-01-26 | 2021-06-01 | 北京百度网讯科技有限公司 | Job flow control method and device for distributed cluster |
| CN112817721A (en) * | 2021-01-29 | 2021-05-18 | 中国平安财产保险股份有限公司 | Task scheduling method and device based on artificial intelligence, computer equipment and medium |
| CN112817721B (en) * | 2021-01-29 | 2022-08-09 | 中国平安财产保险股份有限公司 | Task scheduling method and device based on artificial intelligence, computer equipment and medium |
| CN113608878A (en) * | 2021-08-18 | 2021-11-05 | 上海德拓信息技术股份有限公司 | Task distributed scheduling method and system based on resource weight calculation |
| CN113760549A (en) * | 2021-08-30 | 2021-12-07 | 聚好看科技股份有限公司 | Pod deployment method and device |
| CN113760549B (en) * | 2021-08-30 | 2024-03-15 | 聚好看科技股份有限公司 | Pod deployment method and device |
| CN114840343A (en) * | 2022-05-16 | 2022-08-02 | 江苏安超云软件有限公司 | Task scheduling method and system based on distributed system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102096602A (en) | Task scheduling method, and system and equipment thereof | |
| JP2008527514A5 (en) | ||
| US10474504B2 (en) | Distributed node intra-group task scheduling method and system | |
| CN105718479B (en) | Execution strategy generation method and device under cross-IDC big data processing architecture | |
| CN102567086B (en) | Task scheduling method, equipment and system | |
| JP5609868B2 (en) | Workflow monitoring control system, monitoring control method and monitoring control program | |
| US6349325B1 (en) | Prioritized agent-based hierarchy structure for handling performance metrics data in a telecommunication management system | |
| US9189272B2 (en) | Information processing apparatus, computer program, and method for controlling execution of jobs | |
| CN101719082A (en) | Method and system for dispatching application requests in virtual calculation platform | |
| EP3932025B1 (en) | Computing resource scheduling method, scheduler, internet of things system, and computer readable medium | |
| CN102096599A (en) | Multi-queue task scheduling method and related system and equipment | |
| JP2008519322A (en) | Method for managing resources in a platform for telecommunications services and / or network management, supported platforms, and computer program products thereof | |
| CN102193832A (en) | Cloud computing resource scheduling method and applied system | |
| US11972301B2 (en) | Allocating computing resources for deferrable virtual machines | |
| US10606650B2 (en) | Methods and nodes for scheduling data processing | |
| CN102868573A (en) | Method and device for Web service load cloud test | |
| CN103631650A (en) | Collection scheduling method used for IT operation and maintenance system | |
| CN103634132A (en) | High-efficiency acquisition system for IT operation and maintenance platform | |
| CN110914805A (en) | Computing system for hierarchical task scheduling | |
| KR20100118357A (en) | Semantic computing-based dynamic job scheduling system for distributed processing | |
| CN116010064A (en) | DAG job scheduling and cluster management method, system and device | |
| CN110955516A (en) | Batch task processing method and device, computer equipment and storage medium | |
| JP5670290B2 (en) | Method, system and computer program for managing resources for execution of processes for communication services | |
| CN112948229A (en) | Method and device for determining performance of scheduling cluster, computer equipment and storage medium | |
| Lili et al. | A Markov chain based resource prediction in computational grid |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C12 | Rejection of a patent application after its publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20110615 |