CN115269206A - Data processing method and platform based on resource allocation - Google Patents
Data processing method and platform based on resource allocation Download PDFInfo
- Publication number
- CN115269206A CN115269206A CN202211181889.9A CN202211181889A CN115269206A CN 115269206 A CN115269206 A CN 115269206A CN 202211181889 A CN202211181889 A CN 202211181889A CN 115269206 A CN115269206 A CN 115269206A
- Authority
- CN
- China
- Prior art keywords
- data processing
- data
- processing unit
- resource allocation
- unit determines
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
- G06F9/5027—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
- G06F9/5027—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals
- G06F9/5033—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals considering data affinity
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
- G06F9/5027—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals
- G06F9/5044—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals considering hardware capabilities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2209/00—Indexing scheme relating to G06F9/00
- G06F2209/50—Indexing scheme relating to G06F9/50
- G06F2209/5018—Thread allocation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2209/00—Indexing scheme relating to G06F9/00
- G06F2209/50—Indexing scheme relating to G06F9/50
- G06F2209/508—Monitor
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to the technical field of information processing, in particular to a data processing method and a data processing platform based on resource allocation, which comprises a request receiving unit, a data processing unit and a resource allocation unit, wherein the request receiving unit acquires a data processing request of a user in a server; the data processing unit determines a processing mode of the data processing request according to the matching degree of the number of the allocable resources and the number of the pre-allocated resources; when the data processing unit determines that the processing mode is to allocate resources according to the pre-allocated resource quantity, the resource allocation unit allocates resources, and the resource management unit adjusts the allocated resource quantity according to the performance influence coefficient of the data processing request on the server; when the data processing unit determines that the processing mode is to add the data processing request into the to-be-processed data list, the resource management unit releases the enabled process with delay, so that the accuracy of resource allocation during data processing of the server is improved.
Description
Technical Field
The present invention relates to the field of information processing technologies, and in particular, to a data processing method and platform based on resource allocation.
Background
In the prior solution, the allocation and management of system resources always completely depend on a resource allocation mechanism of an operating system, but some abnormal processes and abnormal threads are difficult to be discovered and processed in time by the operating system, so that the service application efficiency of the server is extremely reduced.
Chinese patent publication No.: CN108052396a discloses a resource allocation method and system, the method includes: acquiring a starting instruction input by a user, starting a service program according to the starting instruction, and generating at least one thread; acquiring at least one thread applying for computing resources of the same hardware accelerator card; allocating the service mutual exclusion lock to the target thread according to the time sequence of the thread application; distributing the target thread to a target computing unit with the least number of queuing threads, and releasing a service mutual exclusion lock of the target thread; if the number of the queuing threads before the target thread is zero, processing the service data of the target thread; allocating the service mutual exclusion lock to a target thread; resetting the flag bit of the target thread, pointing the active bit pointer of the queue where the target thread is positioned to the next thread of the service data to be processed, releasing the service mutual exclusion lock of the target thread, and canceling the target thread. Although the invention can obviously improve the utilization rate of the computing resources and the application value of the hardware accelerator card, the influence on the system resources in the resource allocation process is not considered in the resource allocation process, so that the resource allocation method and the resource allocation system have the problem that the resources are not accurately allocated according to the data processing amount when the data processing request is received.
Disclosure of Invention
Therefore, the invention provides a data processing method and a data processing platform based on resource allocation, which are used for solving the problem that in the prior art, when a data processing request is received, resources are not accurately allocated according to the size of data processing capacity.
In order to achieve the above object, an aspect of the present invention provides a data processing method based on resource allocation, including the following steps:
s1, a request receiving unit acquires a data processing request of a user in a server, and a data processing unit determines the quantity of pre-allocated resources according to the data processing request, wherein the quantity of the pre-allocated resources comprises the quantity of processes of the server and the quantity of threads under each process;
s2, the data processing unit determines a processing mode of the data processing request according to the matching degree of the number of the allocable resources and the number of the pre-allocated resources, wherein the processing mode comprises the steps of allocating resources according to the number of the pre-allocated resources and adding data into a to-be-processed data list;
s3, when the data processing unit determines that the processing mode is to allocate resources according to the pre-allocated resource quantity, the resource allocation unit allocates resources, and the resource management unit adjusts the allocated resource quantity according to the performance influence coefficient of the data processing request on the server;
and S4, when the data processing unit determines that the processing mode is adding the data processing request into the to-be-processed data list, the resource management unit releases the enabled process with delay.
Further, in the step S1, when the data processing unit determines the amount of pre-allocated resources according to the data processing request, the data processing unit determines the amount of required processes according to the comparison result between the amount W of data types in the data processing request and the amount of preset data types,
wherein the data processing unit is provided with a first preset data type quantity W1, a second preset data type quantity W2, a first process quantity P1, a second process quantity P2 and a third process quantity P3, wherein W1 is more than W2, P1 is more than P2 and more than P3,
when W is less than or equal to W1, the data processing unit determines that the process number is P1;
when W1 is larger than W and smaller than or equal to W2, the data processing unit determines that the process quantity is P2;
when W > W2, the amount of the compound, the data processing unit determines that the number of processes is P3.
Further, when the data processing unit determines that the number of the processes is completed, the data processing unit determines the number of threads pre-allocated to the processes corresponding to each data type according to the comparison result between the data quantity Di to be processed of each data type in the data processing request and the preset data quantity,
the data processing unit is provided with a first preset data volume Db1, a second preset data volume Db2, a first thread quantity T1, a second thread quantity T2 and a third thread quantity T3, wherein Db1 is less than Db2, and T1 is less than T2 and less than T3;
if Di is less than Db1, the data processing unit determines that the number of threads pre-allocated to the ith process is T1;
if Db1 is not more than Di and less than Db2, the server determines the number of threads pre-allocated to the ith process as T2;
if Db2 is less than or equal to Di, the server determines that the number of threads pre-allocated to the ith process is T3;
where i is the ith data type, i =1,2,3, …, and m is a positive integer.
Further, in step S2, when the data processing unit determines the processing mode of the data processing request according to the matching degree between the number of allocable resources and the number of pre-allocated resources, the data obtaining unit obtains the number of remaining processes and the number of remaining threads, and the data processing unit calculates the matching degree G according to the obtained number of remaining processes and the obtained number of remaining threads
Where Pn is the number of processes, P10 represents the number of remaining processes,a coefficient representing the lowest remaining process quantity, alpha representing the influence weight of the thread quantity, tz representing the thread quantity, T10 representing the remaining thread quantity, K2 representing the coefficient of the lowest remaining thread quantity, beta representing the influence weight of the threadValue, n =1,2,3,z =1,2,3.
Further, when the data processing unit finishes calculating the matching degree G, the data processing unit determines the processing mode of the data processing request according to the comparison result of the matching degree G and the preset matching degree G0,
if G is less than or equal to G0, the data processing unit determines that the processing mode of the data processing request is to allocate resources according to the number of pre-allocated resources;
and if G is larger than G0, the data processing unit determines that the data processing request is processed in a mode of adding the data processing request into a to-be-processed data list.
Further, in step S3, when the data processing unit determines that the processing manner of the data processing request is to allocate resources according to the pre-allocated resource quantity, the resource allocation unit allocates Pn processes and allocates the number of threads corresponding to each process to be Tz.
Further, when the resource allocation unit completes resource allocation, the data acquisition unit acquires a processor utilization rate and a memory utilization rate of completing resource allocation, and the data processing unit calculates the performance impact coefficient U according to the acquired processor utilization rate and memory utilization rate
Wherein C1 represents a processor utilization rate, C10 represents a preset processor utilization rate, α 1 represents a processor utilization rate influence weight, R1 represents a memory utilization rate, R10 represents a preset memory utilization rate, and β 1 represents a memory utilization rate influence weight.
Further, when the data processing unit completes the calculation of the performance impact coefficient U, the resource management unit determines whether to adjust the amount of the allocated resources according to a comparison result between the performance impact coefficient U and a preset performance impact coefficient U0,
the resource management unit is provided with a thread number adjusting coefficient Kt, and Kt is more than or equal to 0.5 and less than 0;
if U is larger than or equal to U0, the resource management unit determines to use Kt to adjust the number of threads corresponding to each process in the resource allocation;
and if U is less than U0, the resource management unit determines not to adjust the quantity of the allocated resources.
Further, in the step S4, when the resource management unit releases the enabled process with delay, the data obtaining unit obtains the processing delay time Qe of each process, the resource management unit determines whether to release the process according to the comparison result between the processing delay time Qe of each process and the preset delay time Q0,
if Qe is larger than or equal to Q0, the resource management unit determines to release the process corresponding to the e-th delay time and sends error information to the user;
and if Qe is less than Q0, the resource management unit determines not to release the process corresponding to the e-th delay time.
Another aspect of the present invention provides a data processing platform based on resource allocation, including:
the request receiving unit is used for receiving a data processing request sent by a user;
a data acquisition unit for acquiring resource utilization data of the server;
the data processing unit is respectively connected with the request receiving unit and the data acquisition unit and is used for determining the quantity of pre-allocated resources according to the data processing request acquired by the request receiving unit and calculating a performance influence coefficient according to the processor utilization rate and the memory utilization rate of the server acquired by the data acquisition unit;
the resource allocation unit is connected with the data processing unit and used for determining the process quantity in the resource allocation quantity and the thread quantity pre-allocated in the process according to the data processing type quantity determined by the data processing unit;
and the resource management unit is respectively connected with the resource allocation unit and the data processing unit and is used for monitoring the consumption of resources in the server and releasing abnormal resources.
Compared with the prior art, the method has the advantages that the request receiving unit obtains the data processing request information of the user in the server, the data processing unit pre-allocates the number of resources according to the data processing request, the data processing unit determines the processing mode of the data processing request according to the matching degree of the number of the allocable resources and the number of the pre-allocated resources, the resource management unit releases the delayed enabled process when the data processing unit determines that the processing mode is adding the data processing request into the data list to be processed, and the resource management unit releases the delayed enabled process when the data processing unit determines that the processing mode is adding the data processing request into the data list to be processed, so that the accuracy of resource allocation in data processing of the server is improved.
Furthermore, the data processing unit determines the number of the required processes according to the comparison result of the number of the data types in the data processing request and the number of the preset data types, and allocates different processes according to different data processing types, so that the accuracy of resource allocation during data processing of the server is improved.
Furthermore, the data processing unit determines the number of threads pre-allocated to the process corresponding to each data type according to the comparison result between the data amount to be processed of each data type in the data processing request and the preset data amount, so that the unnecessary thread resource allocation amount under each process is reduced, and the resource allocation accuracy is improved when the server performs data processing.
Further, the residual process quantity and the residual thread quantity acquired by the data acquisition unit, the matching degree is calculated by the data processing unit according to the acquired residual process quantity and the acquired residual thread quantity, when the matching degree is calculated by the data processing unit, the data processing unit determines the processing mode of the data processing request according to the comparison result of the matching degree and the preset matching degree, the rationality of judgment on the rationality of resource allocation is ensured, and the accuracy of resource allocation is improved when the server performs data processing.
Further, when the data processing unit determines that the processing mode of the data processing request is to allocate resources according to the pre-allocated resource quantity, the resource allocation unit allocates a process and allocates the thread quantity corresponding to each process, so that the rationality of resource allocation is ensured, and the accuracy of resource allocation when the server performs data processing is improved.
Further, when the resource allocation unit completes resource allocation, the data acquisition unit acquires a processor utilization rate and a memory utilization rate for completing resource allocation, the data processing unit calculates a performance impact coefficient according to the acquired processor utilization rate and memory utilization rate, and when the data processing unit calculates the performance impact coefficient, the resource management unit determines whether to adjust the number of allocated resources according to a comparison result of the performance impact coefficient and a preset performance impact coefficient after the resource allocation unit completes resource allocation, so that the influence of resource allocation on the system resource utilization rate is reduced, and the accuracy of resource allocation when the server performs data processing is improved.
Further, when the resource management unit releases the started processes with delay, the data acquisition unit acquires the processing delay time of each process, the resource management unit determines whether to release the processes according to the comparison result of the processing delay time of each process and the preset delay time, and abnormal resource consumption caused by zombie processes and zombie threads is prevented by releasing the high-delay processes, so that the accuracy of resource allocation during data processing of the server is improved.
Drawings
FIG. 1 is a logic diagram of a data processing method based on resource allocation according to the present invention;
fig. 2 is a connection relationship block diagram of a data processing platform based on resource allocation according to the present invention.
Detailed Description
In order that the objects and advantages of the invention will be more clearly understood, the invention is further described in conjunction with the following examples; it should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only for explaining the technical principle of the present invention, and do not limit the scope of the present invention.
Referring to fig. 1, fig. 1 is a logic block diagram of a data processing method based on resource allocation according to an embodiment of the present invention.
The data processing method based on resource allocation comprises the following steps:
s1, a request receiving unit acquires a data processing request of a user in a server, and a data processing unit determines the quantity of pre-allocated resources according to the data processing request, wherein the quantity of the pre-allocated resources comprises the quantity of processes of the server and the quantity of threads under each process;
s2, the data processing unit determines a processing mode of the data processing request according to the matching degree of the number of the allocable resources and the number of the pre-allocated resources, wherein the processing mode comprises the steps of allocating resources according to the number of the pre-allocated resources and adding data into a to-be-processed data list;
s3, when the data processing unit determines that the processing mode is to allocate resources according to the pre-allocated resource quantity, the resource allocation unit allocates resources, and the resource management unit adjusts the allocated resource quantity according to the performance influence coefficient of the data processing request on the server;
and S4, when the data processing unit determines that the processing mode is to add the data processing request into the to-be-processed data list, the resource management unit releases the delayed enabled process.
Specifically, in step S1, when the data processing unit determines the amount of pre-allocated resources according to the data processing request, the data processing unit determines the required number of processes according to the comparison result of the number W of data types in the data processing request and the preset number of data types,
wherein the data processing unit is provided with a first preset data type quantity W1, a second preset data type quantity W2, a first process quantity P1, a second process quantity P2 and a third process quantity P3, wherein W1 is more than W2, P1 is more than P2 and more than P3,
when W is less than or equal to W1, the data processing unit determines the process number to be P1;
when W1 is larger than W and is not larger than W2, the data processing unit determines that the process quantity is P2;
when W > W2, the data processing unit determines the number of processes to be P3.
Specifically, when the data processing unit determines that the number of processes is completed, the data processing unit determines the number of threads pre-allocated to the process corresponding to each data type according to the comparison result between the data amount Di to be processed of each data type in the data processing request and the preset data amount,
the data processing unit is provided with a first preset data volume Db1, a second preset data volume Db2, a first thread quantity T1, a second thread quantity T2 and a third thread quantity T3, wherein Db1 is less than Db2, and T1 is less than T2 and less than T3;
if Di is less than Db1, the data processing unit determines that the number of threads pre-allocated to the ith process is T1;
if Db1 is less than or equal to Di and less than Db2, the server determines the number of threads pre-allocated to the ith process to be T2;
if Db2 is less than or equal to Di, the server determines that the number of threads pre-allocated to the ith process is T3;
where i is the ith data type, i =1,2,3, …, and m is a positive integer.
Specifically, in step S2, when the data processing unit determines the processing mode of the data processing request according to the matching degree between the number of allocable resources and the number of pre-allocated resources, the data obtaining unit obtains the number of remaining processes and the number of remaining threads, and the data processing unit calculates the matching degree G according to the obtained number of remaining processes and the obtained number of remaining threads
Where Pn is the number of processes, P10 represents the number of remaining processes,a coefficient representing the lowest residual process number, alpha representing the influence weight of the thread number, tz representing the thread number, and T10 representing the residual thread numberAmount, K2 represents the lowest remaining thread amount coefficient, β represents the thread impact weight, n =1,2,3,z =1,2,3.
Specifically, when the data processing unit completes the calculation of the matching degree G, the data processing unit determines the processing mode of the data processing request according to the comparison result of the matching degree G and the preset matching degree G0,
if G is less than or equal to G0, the data processing unit determines that the processing mode of the data processing request is to allocate resources according to the pre-allocation resource quantity;
if G is larger than G0, the data processing unit determines that the data processing request is processed in a mode of adding the data processing request into the to-be-processed data list.
Specifically, in step S3, when the data processing unit determines that the data processing request is processed in a manner that resources are allocated according to the pre-allocated resource amount, the resource allocation unit allocates Pn processes and allocates the number of threads corresponding to each process to Tz.
Specifically, when the resource allocation unit completes resource allocation, the data acquisition unit acquires a processor utilization rate and a memory utilization rate for completing resource allocation, and the data processing unit calculates the performance impact coefficient U according to the acquired processor utilization rate and memory utilization rate
Wherein C1 represents a processor utilization rate, C10 represents a preset processor utilization rate, α 1 represents a processor utilization rate influence weight, R1 represents a memory utilization rate, R10 represents a preset memory utilization rate, and β 1 represents a memory utilization rate influence weight.
Specifically, when the data processing unit completes the calculation of the performance impact coefficient U, the resource management unit determines whether to adjust the amount of the allocated resources according to the comparison result of the performance impact coefficient U and the preset performance impact coefficient U0,
wherein the resource management unit is provided with a thread number adjusting coefficient Kt, and Kt is more than or equal to 0.5 and less than 0;
if U is larger than or equal to U0, the resource management unit determines to use Kt to adjust the number of threads corresponding to each process in the resource allocation;
and if U is less than U0, the resource management unit determines not to adjust the quantity of the allocated resources.
Specifically, in step S4, when the resource management unit releases the enabled process with delay, the data acquisition unit acquires the processing delay time Qe of each process, the resource management unit determines whether to release the process by comparing the processing delay time Qe of each process with the preset delay time Q0,
if Qe is larger than or equal to Q0, the resource management unit determines to release the process corresponding to the e-th delay time and sends error information to the user;
and if Qe is less than Q0, the resource management unit determines not to release the process corresponding to the e-th delay time.
Referring to fig. 2, fig. 2 is a block diagram of a connection relationship between data processing platforms based on resource allocation according to an embodiment of the present invention.
The data processing platform based on resource allocation of the embodiment of the invention comprises:
the request receiving unit is used for receiving a data processing request sent by a user;
a data acquisition unit for acquiring resource utilization data of the server;
the data processing unit is respectively connected with the request receiving unit and the data acquisition unit and used for determining the pre-allocation resource quantity according to the data processing request acquired by the request receiving unit and calculating the performance influence coefficient according to the processor utilization rate and the memory utilization rate of the server acquired by the data acquisition unit;
the resource allocation unit is connected with the data processing unit and used for determining the process quantity in the resource allocation quantity and the thread quantity pre-allocated in the process according to the data processing type quantity determined by the data processing unit;
and the resource management unit is respectively connected with the resource allocation unit and the data processing unit and is used for monitoring the consumption of resources in the server and releasing abnormal resources.
So far, the technical solutions of the present invention have been described in connection with the preferred embodiments shown in the drawings, but it is easily understood by those skilled in the art that the scope of the present invention is obviously not limited to these specific embodiments. Equivalent changes or substitutions of related technical features can be made by those skilled in the art without departing from the principle of the invention, and the technical scheme after the changes or substitutions can be within the protection scope of the invention.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention; various modifications and alterations to this invention will become apparent to those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A data processing method based on resource allocation, comprising the steps of:
s1, a request receiving unit acquires a data processing request of a user in a server, and a data processing unit determines the quantity of pre-allocated resources according to the data processing request, wherein the quantity of the pre-allocated resources comprises the quantity of processes of the server and the quantity of threads under each process;
s2, the data processing unit determines a processing mode of the data processing request according to the matching degree of the number of the allocable resources and the number of the pre-allocated resources, wherein the processing mode comprises the steps of allocating resources according to the number of the pre-allocated resources and adding data into a to-be-processed data list;
s3, when the data processing unit determines that the processing mode is to allocate resources according to the pre-allocated resource quantity, the resource allocation unit allocates resources, and the resource management unit adjusts the allocated resource quantity according to the performance influence coefficient of the data processing request on the server;
and S4, when the data processing unit determines that the processing mode is adding the data processing request into the to-be-processed data list, the resource management unit releases the enabled process with delay.
2. The data processing method based on resource allocation according to claim 1, wherein in step S1, when the data processing unit determines the amount of pre-allocated resources according to the data processing request, the data processing unit determines the required number of processes according to the comparison result between the amount of data types W in the data processing request and the preset amount of data types,
wherein the data processing unit is provided with a first preset data type quantity W1, a second preset data type quantity W2, a first process quantity P1, a second process quantity P2 and a third process quantity P3, wherein W1 is more than W2, P1 is more than P2 and more than P3,
when W is less than or equal to W1, the data processing unit determines that the process number is P1;
when W1 is larger than W and is smaller than or equal to W2, the data processing unit determines that the process quantity is P2;
when W > W2, the data processing unit determines that the number of processes is P3.
3. The data processing method based on resource allocation according to claim 2, wherein when the data processing unit determines that the number of processes is completed, the data processing unit determines the number of threads pre-allocated to the process corresponding to each data type according to the comparison result between the data amount Di to be processed of each data type in the data processing request and the preset data amount,
the data processing unit is provided with a first preset data volume Db1, a second preset data volume Db2, a first thread quantity T1, a second thread quantity T2 and a third thread quantity T3, wherein Db1 is less than Db2, and T1 is less than T2 and less than T3;
if Di is less than Db1, the data processing unit determines that the number of threads pre-allocated to the ith process is T1;
if Db1 is not more than Di and less than Db2, the server determines the number of threads pre-allocated to the ith process as T2;
if Db2 is less than or equal to Di, the server determines that the number of threads pre-allocated to the ith process is T3;
where i is the ith data type, i =1,2,3, …, and m is a positive integer.
4. The data processing method based on resource allocation according to claim 3, wherein in step S2, when the data processing unit determines the processing mode of the data processing request according to the matching degree between the number of allocable resources and the number of pre-allocated resources, the data processing unit obtains the number of remaining processes and the number of remaining threads, and the data processing unit calculates the matching degree G according to the obtained number of remaining processes and the obtained number of remaining threads
Where Pn is the number of processes, P10 represents the number of remaining processes,represents the lowest remaining process number coefficient, α represents the thread number influence weight, tz is the thread number, T10 represents the remaining thread number, K2 represents the lowest remaining thread number coefficient, β represents the thread influence weight, n =1,2,3, z =1,2,3.
5. The data processing method based on resource allocation according to claim 4, wherein when the data processing unit completes calculating the matching degree G, the data processing unit determines the processing mode of the data processing request according to the comparison result of the matching degree G and a preset matching degree G0,
if G is less than or equal to G0, the data processing unit determines that the processing mode of the data processing request is to allocate resources according to the number of pre-allocated resources;
and if G is larger than G0, the data processing unit determines that the data processing request is processed in a mode of adding the data processing request into a to-be-processed data list.
6. The method according to claim 5, wherein in step S3, when the data processing unit determines that the data processing request is processed by allocating resources according to the pre-allocated resource amount, the resource allocation unit allocates Pn processes and allocates the number of threads corresponding to each process to be Tz.
7. The data processing method based on resource allocation according to claim 6, wherein when the resource allocation unit completes resource allocation, the data obtaining unit obtains a processor utilization rate and a memory utilization rate for completing resource allocation, and the data processing unit calculates the performance impact coefficient U according to the obtained processor utilization rate and memory utilization rate
Wherein C1 represents a processor utilization rate, C10 represents a preset processor utilization rate, α 1 represents a processor utilization rate influence weight, R1 represents a memory utilization rate, R10 represents a preset memory utilization rate, and β 1 represents a memory utilization rate influence weight.
8. The data processing method based on resource allocation according to claim 7, wherein when the data processing unit completes calculating the performance impact coefficient U, the resource management unit determines whether to adjust the amount of allocated resources according to a comparison result between the performance impact coefficient U and a preset performance impact coefficient U0, wherein the resource management unit is provided with a thread amount adjustment coefficient Kt, kt is greater than or equal to 0.5 and is less than 0;
if U is larger than or equal to U0, the resource management unit determines to use Kt to adjust the number of threads corresponding to each process in the resource allocation;
and if U is less than U0, the resource management unit determines not to adjust the quantity of the allocated resources.
9. The data processing method based on resource allocation according to claim 8, wherein in said step S4, when said resource management unit releases the enabled processes with delay, said data obtaining unit obtains the processing delay time Qe of each process, said resource management unit determines whether to release the processes according to the comparison result between the processing delay time Qe of each process and the preset delay time Q0,
if Qe is more than or equal to Q0, the resource management unit determines to release the process corresponding to the e-th delay time and sends error information to the user;
and if Qe is less than Q0, the resource management unit determines not to release the process corresponding to the e-th delay time.
10. A data processing platform to which the data processing method of resource allocation of claims 1-9 is applied, comprising:
the request receiving unit is used for receiving a data processing request sent by a user;
a data acquisition unit for acquiring resource utilization data of the server;
the data processing unit is respectively connected with the request receiving unit and the data acquisition unit and is used for determining the quantity of pre-allocated resources according to the data processing request acquired by the request receiving unit and calculating a performance influence coefficient according to the processor utilization rate and the memory utilization rate of the server acquired by the data acquisition unit;
the resource allocation unit is connected with the data processing unit and used for determining the process quantity in the resource allocation quantity and the thread quantity pre-allocated in the process according to the data processing type quantity determined by the data processing unit;
and the resource management unit is respectively connected with the resource allocation unit and the data processing unit and is used for monitoring the consumption of resources in the server and releasing abnormal resources.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211181889.9A CN115269206B (en) | 2022-09-27 | 2022-09-27 | Data processing method and platform based on resource allocation |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211181889.9A CN115269206B (en) | 2022-09-27 | 2022-09-27 | Data processing method and platform based on resource allocation |
Publications (2)
Publication Number | Publication Date |
---|---|
CN115269206A true CN115269206A (en) | 2022-11-01 |
CN115269206B CN115269206B (en) | 2023-01-10 |
Family
ID=83757268
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211181889.9A Active CN115269206B (en) | 2022-09-27 | 2022-09-27 | Data processing method and platform based on resource allocation |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115269206B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116700999A (en) * | 2023-08-07 | 2023-09-05 | 上海观安信息技术股份有限公司 | Data processing method, device, computer equipment and storage medium |
Citations (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20110231513A1 (en) * | 2000-09-25 | 2011-09-22 | Yevgeny Korsunsky | Application distribution control network apparatus |
CN103336722A (en) * | 2013-07-16 | 2013-10-02 | 上海大学 | Virtual machine CPU source monitoring and dynamic distributing method |
CN103458525A (en) * | 2012-06-01 | 2013-12-18 | 北京邮电大学 | Method and device for scheduling policy selection in heterogeneous network |
CN104079503A (en) * | 2013-03-27 | 2014-10-01 | 华为技术有限公司 | Method and device of distributing resources |
CN104537008A (en) * | 2014-12-16 | 2015-04-22 | 语联网(武汉)信息技术有限公司 | Item set capacity value extracting method and device based on matching degree |
CN105700948A (en) * | 2014-11-24 | 2016-06-22 | 阿里巴巴集团控股有限公司 | Method and device for scheduling calculation task in cluster |
CN108121601A (en) * | 2017-11-08 | 2018-06-05 | 上海格蒂电力科技有限公司 | A kind of application resource dispatching device and method based on weight |
CN109992366A (en) * | 2017-12-29 | 2019-07-09 | 华为技术有限公司 | Method for scheduling task and dispatching device |
CN110275777A (en) * | 2019-06-10 | 2019-09-24 | 广州市九重天信息科技有限公司 | Resource scheduling system |
US20190303308A1 (en) * | 2018-04-03 | 2019-10-03 | Vmware, Inc. | Distributed storage system and method for managing storage access bandwidth for multiple clients |
CN111625331A (en) * | 2020-05-20 | 2020-09-04 | 拉扎斯网络科技(上海)有限公司 | Task scheduling method, device, platform, server and storage medium |
CN112131004A (en) * | 2020-04-29 | 2020-12-25 | 章稳建 | Data processing method based on communication of Internet of things and cloud computing server |
CN113469423A (en) * | 2021-06-18 | 2021-10-01 | 北京明略软件系统有限公司 | Resource allocation method, device, storage medium and electronic equipment |
US20210392087A1 (en) * | 2020-06-16 | 2021-12-16 | Hitachi, Ltd. | Computer system and operation management method for computer system |
US20220058060A1 (en) * | 2020-08-18 | 2022-02-24 | Core Scientific, Inc. | Ranking computing resources |
-
2022
- 2022-09-27 CN CN202211181889.9A patent/CN115269206B/en active Active
Patent Citations (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20110231513A1 (en) * | 2000-09-25 | 2011-09-22 | Yevgeny Korsunsky | Application distribution control network apparatus |
CN103458525A (en) * | 2012-06-01 | 2013-12-18 | 北京邮电大学 | Method and device for scheduling policy selection in heterogeneous network |
CN104079503A (en) * | 2013-03-27 | 2014-10-01 | 华为技术有限公司 | Method and device of distributing resources |
CN103336722A (en) * | 2013-07-16 | 2013-10-02 | 上海大学 | Virtual machine CPU source monitoring and dynamic distributing method |
CN105700948A (en) * | 2014-11-24 | 2016-06-22 | 阿里巴巴集团控股有限公司 | Method and device for scheduling calculation task in cluster |
CN104537008A (en) * | 2014-12-16 | 2015-04-22 | 语联网(武汉)信息技术有限公司 | Item set capacity value extracting method and device based on matching degree |
CN108121601A (en) * | 2017-11-08 | 2018-06-05 | 上海格蒂电力科技有限公司 | A kind of application resource dispatching device and method based on weight |
CN109992366A (en) * | 2017-12-29 | 2019-07-09 | 华为技术有限公司 | Method for scheduling task and dispatching device |
US20190303308A1 (en) * | 2018-04-03 | 2019-10-03 | Vmware, Inc. | Distributed storage system and method for managing storage access bandwidth for multiple clients |
CN110275777A (en) * | 2019-06-10 | 2019-09-24 | 广州市九重天信息科技有限公司 | Resource scheduling system |
CN112131004A (en) * | 2020-04-29 | 2020-12-25 | 章稳建 | Data processing method based on communication of Internet of things and cloud computing server |
CN111625331A (en) * | 2020-05-20 | 2020-09-04 | 拉扎斯网络科技(上海)有限公司 | Task scheduling method, device, platform, server and storage medium |
US20210392087A1 (en) * | 2020-06-16 | 2021-12-16 | Hitachi, Ltd. | Computer system and operation management method for computer system |
US20220058060A1 (en) * | 2020-08-18 | 2022-02-24 | Core Scientific, Inc. | Ranking computing resources |
CN113469423A (en) * | 2021-06-18 | 2021-10-01 | 北京明略软件系统有限公司 | Resource allocation method, device, storage medium and electronic equipment |
Non-Patent Citations (1)
Title |
---|
李丽娜: "面向大规模流数据处理的弹性资源调度研究", 《中国博士学位论文全文数据库 (基信息科技辑)》 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116700999A (en) * | 2023-08-07 | 2023-09-05 | 上海观安信息技术股份有限公司 | Data processing method, device, computer equipment and storage medium |
CN116700999B (en) * | 2023-08-07 | 2023-10-03 | 上海观安信息技术股份有限公司 | Data processing method, device, computer equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN115269206B (en) | 2023-01-10 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US8812639B2 (en) | Job managing device, job managing method and job managing program | |
US7206890B2 (en) | System and method for reducing accounting overhead during memory allocation | |
US8108874B2 (en) | Minimizing variations of waiting times of requests for services handled by a processor | |
US8078674B2 (en) | Server device operating in response to received request | |
US20060195845A1 (en) | System and method for scheduling executables | |
US20070053381A1 (en) | Method, apparatus and computer program product for sharing resources | |
CN115269206B (en) | Data processing method and platform based on resource allocation | |
US20200104177A1 (en) | Resource allocation system, management device, method, and program | |
CN104850505B (en) | The EMS memory management process and system stacked based on chain type | |
US20180314435A1 (en) | Deduplication processing method, and storage device | |
WO2019205370A1 (en) | Electronic device, task distribution method and storage medium | |
WO2019024235A1 (en) | Electronic device, server allocation control method and computer readable storage medium | |
CN107704322B (en) | Request distribution method and device | |
CN114155026A (en) | Resource allocation method, device, server and storage medium | |
CN113327053A (en) | Task processing method and device | |
CN111858014A (en) | Resource allocation method and device | |
CN115640113A (en) | Multi-plane flexible scheduling method | |
KR20160139082A (en) | Method and System for Allocation of Resource and Reverse Auction Resource Allocation in hybrid Cloud Server | |
CN108845860B (en) | Method and device for managing quota and electronic equipment | |
CN110073321B (en) | Storage controller and IO request processing method | |
CN111813564B (en) | Cluster resource management method and device and container cluster management system | |
CN112948501B (en) | Data analysis method, device and system | |
CN114528109A (en) | Resource request method, device and system | |
CN114157717A (en) | Micro-service dynamic current limiting system and method | |
WO2021017310A1 (en) | Electronic voucher generation method and apparatus, computer device, and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |