CN116339989A - Mixed part server, resource management method and device of mixed part server - Google Patents
Mixed part server, resource management method and device of mixed part server Download PDFInfo
- Publication number
- CN116339989A CN116339989A CN202310303098.7A CN202310303098A CN116339989A CN 116339989 A CN116339989 A CN 116339989A CN 202310303098 A CN202310303098 A CN 202310303098A CN 116339989 A CN116339989 A CN 116339989A
- Authority
- CN
- China
- Prior art keywords
- partition
- service
- risk
- server
- resource utilization
- 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
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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Hardware Redundancy (AREA)
Abstract
The application relates to a mixed part server, a resource management method and a resource management device of the mixed part server, wherein a plurality of partitions are arranged in the server to deploy a plurality of types of services, so that the mixed part of the services is realized; the hardware resources of each partition are set according to the hardware configuration constraint of the corresponding service type, and different hardware resources of a plurality of partitions are reasonably deployed in the server, so that the resource allocation rate and the utilization rate of the server are improved. In addition, the resource utilization rate of the server is checked at regular time, and when the resource utilization rate of the server exceeds the limit, the partition in the server is subjected to service eviction, so that the normal operation of main services in the server is ensured.
Description
Technical Field
The present invention relates to the field of operation and maintenance, and in particular, to a hybrid server, and a method and an apparatus for resource management of the hybrid server.
Background
Services deployed in a server may be generally classified into various types, such as a computing type service, a storage type service, and an equilibrium type service, according to different business attributes and scenarios. For different types of services, the existing deployment manner generally uses each server to deploy the same type of service, for example, only compute type services are deployed in some servers, and only storage type services are deployed in some servers.
However, in the above solution, the proportion of the multiple hardware resources of the server is not necessarily matched with the hardware resource requirement of the corresponding service, so that deploying a single type of service may cause waste of a certain hardware resource in the corresponding server.
Disclosure of Invention
One of the purposes of the present application is to provide a hybrid server, and a method and an apparatus for managing resources of the hybrid server, so as to solve the technical problem of server resource waste in the prior art.
According to an aspect of the present application, there is provided a hybrid server including:
a plurality of partitions for deploying multiple types of services;
the plurality of partitions are obtained by dividing hardware resources of the server, the hardware resources of the plurality of partitions are isolated from each other, and the hardware resources of each partition are set according to hardware configuration constraint of a corresponding service type.
In one embodiment of the present application, the hardware configuration constraint includes a ratio between a plurality of hardware resources, wherein the hardware resources include a processor, a disk, and a memory.
In an embodiment of the present application, the plurality of partitions is obtained by dividing hardware resources of the server based on a control group.
In another aspect of the present application, there is further provided a resource management method of a hybrid server, including:
determining the resource utilization rate of the hybrid server according to the first preset period;
and when the resource utilization rate of the hybrid server exceeds a first threshold, performing service eviction based on the resource utilization rate of each partition in the hybrid server.
In an embodiment of the present application, the eviction service based on the resource utilization of each partition in the hybrid server includes:
for each partition, when the resource utilization rate of the partition is greater than a second threshold value, taking the partition as a risk partition;
service eviction is performed on at least one of the risk partitions.
In an embodiment of the present application, further includes:
determining the resource utilization rate of each partition in each partition according to a second preset period, wherein the first preset period is the same as or different from the second preset period;
and for each partition, when the resource utilization rate of the partition is larger than a second threshold value, taking the partition as a risk partition, and performing service eviction on the risk partition.
In an embodiment of the present application, performing service eviction on the risk partition includes:
expelling a service of the risk partition based at least on service priority;
determining the resource utilization rate of the risk partition;
returning to said step of evicting one of said risk partitions based at least on service priority if there are evictable services in said risk partition when the resource utilization of said risk partition exceeds a second threshold; if the eviction service does not exist in the risk zone, ending the service eviction of the risk zone and sending an alarm event;
and ending the service eviction of the risk zone when the resource utilization rate of the risk zone does not exceed the second threshold value.
In an embodiment of the present application, after performing service eviction on all the risk partitions, the method further includes:
if the resource utilization rate of the hybrid server exceeds the first threshold, sending a machine alarm; or alternatively
And if the resource utilization rate of the hybrid server does not exceed the first threshold, recording a self-healing event.
In an embodiment of the present application, a resource management device of a hybrid server includes:
a determining module, configured to determine, according to a first preset period, a resource utilization rate of the hybrid server as described above;
and the service eviction module is used for performing service eviction based on the resource utilization rate of each partition in the hybrid server when the resource utilization rate of the hybrid server exceeds a first threshold.
In another aspect of the present application, there is also provided a server, including:
a processor; and
a memory in which a program is stored,
wherein the program comprises instructions which, when executed by the processor, cause the processor to perform the method of any of the above.
In another aspect of the present application, there is also provided a non-transitory computer readable storage medium storing computer instructions for causing a computer to perform the method of any one of the above.
The beneficial effects of this application are:
the server is provided with a plurality of partitions to deploy various types of services, so that a service mixing part is realized; the hardware resources of each partition are set according to the hardware configuration constraint of the corresponding service type, so that the hardware resources of each partition are matched with the requirements of the corresponding service type, and the resource allocation rate and the utilization rate of each partition are improved. The different hardware resources of the multiple partitions are reasonably deployed in the server, so that the resource allocation rate and the utilization rate of the server are improved. In addition, the resource utilization rate of the server is checked at regular time, and when the resource utilization rate of the server exceeds the limit, the partition in the server is subjected to service eviction, so that the normal operation of main services in the server is ensured.
Drawings
Fig. 1 is a schematic structural diagram of a hybrid server according to an exemplary embodiment of the present application;
FIG. 2 is a schematic diagram of a service deployment of a hybrid server according to an exemplary embodiment of the present application;
FIG. 3 is a flowchart illustrating a method of resource management for a hybrid server according to an exemplary embodiment of the present application;
FIG. 4 is a flow chart of a method of resource management of a hybrid server as illustrated in another exemplary embodiment of the present application;
FIG. 5 is a flow chart of a method of resource management of a hybrid server as illustrated in another exemplary embodiment of the present application;
FIG. 6 is a block diagram of a resource management device of a hybrid server according to an exemplary embodiment of the present application;
fig. 7 shows a schematic diagram of a computer system suitable for use in implementing the electronic device of the embodiments of the present application.
Detailed Description
Further advantages and effects of the present application will be readily apparent to those skilled in the art from the disclosure in the present specification, by describing embodiments of the present application with reference to the accompanying drawings and preferred examples. The present application may be embodied or carried out in other specific embodiments, and the details of the present application may be modified or changed from various points of view and applications without departing from the spirit of the present application. It should be understood that the preferred embodiments are presented by way of illustration only and not by way of limitation to the scope of the present application.
It should be noted that, the illustrations provided in the following embodiments merely illustrate the basic concepts of the application by way of illustration, and only the components related to the application are shown in the drawings and are not drawn according to the number, shape and size of the components in actual implementation, and the form, number and proportion of the components in actual implementation may be arbitrarily changed, and the layout of the components may be more complex.
Fig. 1 is a schematic structural diagram of a hybrid server according to an exemplary embodiment of the present application, as shown in fig. 1, where the hybrid server in the present embodiment includes: a plurality of partitions 110, the plurality of partitions 110 for deploying multiple types of services; the plurality of partitions 110 are obtained by dividing the hardware resources of the server 120, the hardware resources of the plurality of partitions 110 are isolated from each other, and the hardware resources of each partition 110 are set according to the hardware configuration constraint of the corresponding service type.
The hardware configuration constraint includes a ratio between various hardware resources, and different service types may require the ratio between various hardware resources, so when partitioning, the ratio of various hardware resources of the partition needs to be set according to the service type, so that the hardware resources of the partition are matched with the characteristics of the corresponding service type.
In one embodiment, the plurality of partitions 110 are obtained by dividing the hardware resources of the server based on a control group (Cgroup). The control group is used to limit, control and separate hardware resources (e.g., CPU, memory, disk input/output, etc.) of a process group.
Fig. 2 is a schematic service deployment diagram of a hybrid server according to an exemplary embodiment of the present application, as shown in fig. 2: in this example, the service types may include a computing type service, a storage type service, and an equilibrium type service. The computing service mainly consumes a CPU and a memory, and is commonly used in off-line computing and batch running scenes; the storage type service mainly consumes a disk, and is commonly used for various databases such as mysql, gfs, SFTP and the like and storage type services; balanced services are relatively average in CPU, memory, disk usage and are common to online business services.
In this example, the hardware resources of the server include a central processing unit (Central Processing Unit, abbreviated as CPU), a memory MEM, a DISK, and the like. The internal resources of a server include: the CPU of 24 physical cores, 256G memory and two 4T Solid State disks (Solid State Drive, SSD for short), and the CPU can start the hyper-threading, so that the actually available logic cores are 48 cores. Therefore, the actual machine package is two blocks of 48-core CPU, 256G memory and 4T SSD hard disk.
In an actual use scenario, taking the characteristic of the balanced service as an example, the hardware resource ratio suitable for the balanced service is CPU (1): MEM (4): DISK (80). Therefore, if the partition is not performed, 48 balanced services are directly deployed, and the corresponding hardware resource occupation condition is that the CPU:48 threads, memory: 196G, hard disk: 3840G. Therefore, when the allocation of the CPU is completed, the memory remains 64G, and the hard disk of the second block 4T cannot be allocated.
Therefore, in this embodiment, the type partition is performed on the hardware resource of the server by the Cgroup, which may be divided into a computing/balancing area and a storage area, where the storage area monopolizes a 4T hard disk, and in cooperation with an 8-core CPU and a 96G memory, may store a Mysql instance, and the remaining computing/balancing area uses 40 cores: 160G memory and another disk, thereby realizing a balanced/computational and storage type service mixing part and improving the resource allocation rate.
Different partitions are created based on the same Cgroup, the Cgroup limits the available CPU, MEM, DISK of each partition, the hardware resources of each partition are isolated from each other, and the inter-partition service is ensured not to be affected. Services within the same Cgroup partition inherit the Cgroup group restrictions. In order to ensure that services in the same partition cannot be affected mutually, resource isolation is also used when the services are started, and the services are started directly through a cgroup or are deployed through technologies such as a docker container, a k8s and the like.
In another embodiment of the present application, for servers with a greater number of hard disks, one hard disk may be reserved as an equalization partition/compute partition, deploying an equalization-type service (e.g., online service), or a compute task (offline task, run-in task). In addition to the balanced/compute partition, the remaining disks are available as storage partitions for deployment of storage type services such as mysql, sftp, bos, gfs. The storage partition still complies with the cgroup partition rules.
In the embodiment shown in fig. 2, a resource scheduling system is also built based on the hybrid server. The resource scheduling system comprises a request unit and a resource scheduling unit except for the mixed part server, wherein the request unit faces to a user, and the user can apply for corresponding resource types and resource amounts on a resource application initiating interface according to actual demands; the resource scheduling unit is responsible for analyzing the user resource demand and the resource screening condition, scoring and sorting the mixed servers in the schedulable range, and selecting the optimal mixed server for resource allocation. The optimal mixed part server is used as a resource entity and is used for carrying out actual resource allocation as a carrier of user service.
Therefore, the mixed part server disclosed by the application reasonably divides hardware resources, so that resources such as a CPU, a memory, a disk and the like in the server can be distributed maximally, and different service types cannot interfere with each other. Specifically, the CPU and the memory of the machine are divided into different partitions through the cgroup, and the hardware resources such as the CPU, the memory and the disk among the different partitions are mutually independent and limited in useful quantity by combining a plurality of disks. In the same partition, different services of the same partition are isolated from each other through a cgroup (or a dock container, the bottom layer is still a cgroup mechanism), and finally, different services in the unified partition are independent from each other, and the total amount of resources of all services in the same partition can be ensured not to exceed the upper limit value of the partition.
During the actual operation of the services within the hybrid server, certain types of services may experience a steep increase in resource consumption due to external factors, thereby affecting other services as well as the server. For example: if online services exist inside the hybrid server, the sudden increase of the traffic may cause the resource consumption of the online services to increase instantaneously, and in severe cases, the machine may hang up, so that all the services in the machine are affected. The above problems also exist with servers that deploy a single type of service during operation. Therefore, the application also provides a resource management method of the hybrid server, so as to solve the problems.
Fig. 3 is a flowchart illustrating a method for managing resources of a hybrid server according to an exemplary embodiment of the present application, and as shown in fig. 3, the method for managing resources of a hybrid server includes steps S310 to S320.
Step S310, determining the resource utilization rate of the hybrid server according to the first preset period.
Step S320, when the resource utilization of the hybrid server exceeds the first threshold, performing service eviction based on the resource utilization of each partition in the hybrid server.
In this embodiment, the polling is initiated at regular time, first, the resource utilization rate of hardware including CPU, memory, disk, etc. is checked, and if the resource utilization rate exceeds a first threshold, it is determined that the current hybrid server has a risk.
Since the plurality of partitions are divided in advance inside the hybrid server, and the sum of the hardware resources of all the partitions is smaller than or equal to the hardware resources of the hybrid server, when the hybrid server is at risk, there is necessarily a risk that one or more partitions are at risk. It is therefore necessary to perform service eviction on the hybrid server to eliminate the risk.
In an embodiment of the present application, the process of expelling services based on the resource utilization of each partition in the hybrid server may include:
for each partition, when the resource utilization rate of the partition is greater than a second threshold value, taking the partition as a risk partition;
service eviction is performed on at least one of the risk partitions.
Whether the partition has risks is judged based on the current resource utilization rate of the partition, and the risk of the risk partition is eliminated by performing service eviction on the risk partition, so that the resource utilization rate of the hybrid server is reduced until the risk of the hybrid service is eliminated. The ways of service eviction of risk include, but are not limited to, the following three:
(1) And performing service eviction on all risk partitions, so that risks of all risk partitions are eliminated, and risks of the hybrid servers are correspondingly eliminated.
(2) Selecting one or more risk partitions for service eviction, and then re-determining the resource utilization rate of the hybrid server; if the resource utilization rate of the hybrid server is still greater than the first threshold, returning to selecting one or more risk partitions for service eviction until the risk of the hybrid server is eliminated; if the resource utilization of the hybrid non-server does not exceed the first threshold, ending the service eviction.
(3) In the method (2), when one or more risk partitions are selected, one or more partitions having the highest resource utilization are selected, and the other steps are the same as in the method (2).
By the three modes, the resource utilization rate of the hybrid server can be effectively enabled to not exceed the first threshold value. In addition, the three service eviction manners described above are only used to illustrate the manner in which the service is evicted, and other service eviction manners are not excluded.
In an embodiment of the present application, in order to ensure that each partition can normally operate, it is also possible to perform inspection on all partitions at regular time, and directly perform service eviction on an inspected risk partition, so as to ensure that each risk partition normally operates, including:
determining the resource utilization rate of each partition in each partition according to a second preset period;
and for each partition, when the resource utilization rate of the partition is larger than a second threshold value, taking the partition as a risk partition, and performing service eviction on the risk partition, wherein the first preset period is the same as or different from the second preset period.
In this embodiment, firstly, the resource utilization rates of all the partitions are queried at regular time to obtain the resource utilization rates of all the partitions at the query time, and then the partition with the resource utilization rate greater than the second threshold is used as the risk partition. And then performing service eviction on all risk partitions, and after the risk of each risk partition is eliminated, correspondingly eliminating the risk of the server.
It should be noted that the second preset period of traversing all the partitions may be the same as the first preset period, and when determining the resource utilization rate of the server, the server is inspected while inspecting the resource utilization rate of each partition. That is, in this embodiment, when the server has a risk, service eviction may be performed in a plurality of ways to ensure that the resource utilization rate of the server does not exceed the first threshold; when the server does not have risk, all the partitions can be traversed, and then the risk partitions are evicted, so that the resource utilization rate of each partition is ensured not to exceed a second threshold value.
In an embodiment of the present application, the process after service eviction for all the risk partitions further includes:
if the resource utilization rate of the hybrid server exceeds the first threshold, sending a machine alarm; or if the resource utilization rate of the hybrid server does not exceed the first threshold, recording a self-healing event.
In general, after service eviction of all risk partitions, the resource utilization of each risk partition does not exceed the second threshold. Correspondingly, the resource utilization of the server returns to below the first threshold, and the risk disappears. Therefore, in order to verify whether the risk of the server is eliminated, the resource utilization rate of the hybrid server is re-determined after service eviction is performed on all the risk partitions. And if the resource utilization rate of the hybrid server does not exceed the first threshold value at the moment, indicating that the hybrid server returns to a normal state, and recording a self-healing event at the moment. If the resource utilization of the hybrid server exceeds the first threshold at this time, it is indicated that the hybrid server is not restored after service eviction for all the risk partitions. At the moment, the mixed part server cannot realize self-healing, machine alarm needs to be sent, and related personnel are reminded to carry out manual inspection through the machine alarm.
In the above embodiment, whether the service eviction is performed on the partitions one by one or on all the risk partitions, the service within the partitions needs to be evicted. In an embodiment of the present application, the process of performing service eviction on the risk partition may include:
expelling a service of the risk partition based at least on service priority;
there is an explicit class of service (based on the cpu share parameter settings) between different services within the same partition, e.g. the priority of online services is to be rated according to the importance of the service. The service priority of the service in the same partition is predefined, for example, the service priority of the online service is classified according to the importance degree of the service, and the service priority of the whole online service is higher than that of the offline service; when the partition is at risk, expelling the service according to the service priority; for example, one service with the lowest priority may be evicted.
Determining the resource utilization rate of the risk partition;
after one service is evicted, the resource utilization of the risk partition needs to be redetermined, and the resource utilization determines whether the risk partition returns to normal after one service is evicted.
Returning to said step of evicting one of said risk partitions based at least on service priority if there are evictable services in said risk partition when the resource utilization of said risk partition exceeds a second threshold; if the eviction service does not exist in the risk zone, ending the service eviction of the risk zone and sending an alarm event;
if the resource utilization of the risk partition still exceeds the second threshold after evicting one service, it is stated that evicting only one service does not eliminate the risk of the risk partition. Thus, it is necessary to continue to evict the next service in accordance with the service priority, for example, evicting the service with the lowest service priority among the remaining services; and then the resource utilization rate of the partition is queried again until the resource utilization rate of the risk partition does not exceed a second threshold.
In addition, the services that can be evicted are all evictable services, and the services within the partition also need to define in advance whether they are evictable, for example: the online service is defined as non-evictable, then when the service is evicted according to the priority, the online service is excluded in advance, and does not participate in the prioritization, so that it is ensured that the online service is not evicted.
In some cases, if there is no evictable service within the partition after one or more evictions have passed, but the partition's resource utilization still exceeds a second threshold, this indicates that the partition is not self-healing. And under the condition that the subareas cannot be self-healed, sending an alarm event to related personnel, so as to perform manual investigation.
And ending the service eviction of the risk zone when the resource utilization rate of the risk zone does not exceed the second threshold value.
After one or more evictions, if the resource utilization rate of the risk partition does not exceed the second threshold, the risk elimination of the risk partition is indicated, and the service eviction of the risk partition is directly ended at the moment.
In this embodiment, services are evicted one by one based on whether they are evictable, and the attributes of the service priority. Important non-eviction services within the partition are guaranteed not to be evicted, maintaining the main functionality of the partition. And simultaneously, performing one-by-one eviction in the secondary service, and then inquiring the resource utilization rate of the partition once every eviction until the partition resource utilization rate does not exceed a second threshold value, so that the service is reserved as much as possible. Under the condition that most of services in the partition can work normally, the full utilization of partition resources is guaranteed.
Fig. 4 is a flowchart of a resource management method of a hybrid server according to another exemplary embodiment of the present application, as shown in fig. 4, where the resource management method of a hybrid server according to another embodiment includes:
(1) Initiating resource inspection at regular time, checking the resource (CPU, MEM, DISK) utilization rate of the hybrid server, and if the resource utilization rate of the hybrid server exceeds a configured first threshold value, recording an alarm event;
(2) Traversing the cgroup partitions in the mixed part server, and checking whether each cgroup partition has a risk of resource overrun (when the resource utilization rate of the partition exceeds a second threshold, the risk of resource overrun exists);
(3) If the partition has risks, traversing all the services in the risk partition, and sorting the rest of the evictable services according to the service priority after excluding the non-evictable services in the risk partition; if there is no evictable service, the partition is proved to be unable to self-heal at this time, and an alarm event needs to be sent to wait for manual processing.
(4) And expelling the expelling service with the lowest service priority, releasing resources, re-inquiring the resource utilization rate of the risk partition after releasing, judging whether the risk partition after expelling has risks, and if the risk still exists, returning to expelling the expelling service with the lowest service priority until the resource risk in the partition is relieved.
(5) After service eviction is carried out on all risk partitions, whether the machine index exceeds the limit is queried again, and if the machine index exceeds the limit, a machine alarm needs to be sent; if the risk is contacted at this time, the fault self-healing is proved to be finished, the self-healing event is recorded, and the inspection is finished.
Fig. 5 is a flowchart of a method for managing resources of a hybrid server according to another exemplary embodiment of the present application, as shown in fig. 4, where the method for managing resources of a hybrid server according to another embodiment includes:
(1) Initiating resource inspection at regular time, checking the resource (CPU, MEM, DISK) utilization rate of the hybrid server, and recording an alarm event if the resource utilization rate of the hybrid server exceeds a configured first threshold;
(2) Determining the resource utilization rate of the current partition in the hybrid server;
(3) When the current partition is a risk partition with the resource utilization rate exceeding a preset second threshold value, executing service eviction on the risk partition so that the resource utilization rate of the risk partition does not exceed the preset second threshold value;
(4) When the resource utilization rate of the current partition does not exceed a preset second threshold value, taking the next partition as the current partition, and determining the resource utilization rate of the current partition; or after performing service eviction on the risk partition, determining the resource utilization rate of the hybrid server, and when the resource utilization rate of the hybrid server exceeds a preset first threshold, taking the next partition as the current partition, and determining the resource utilization rate of the current partition;
(5) Returning to executing service eviction on the risk partition when the current partition is the risk partition with the resource utilization rate exceeding a preset second threshold value; and (3) until the resource utilization rate of the mixed part server does not exceed a preset first threshold value, or until service eviction is executed for all risk partitions, and the inspection is completed.
The process of performing service eviction on the risk partition comprises the following steps: traversing all services in the risk partition, and sorting the rest of the evictable services according to the service priority after excluding the non-evictable services in the risk partition; if there is no evictable service, the partition is proved to be unable to self-heal at this time, and an alarm event needs to be sent to wait for manual processing. And expelling the expelling service with the lowest service priority, releasing resources, re-inquiring the resource utilization rate of the risk partition after releasing, judging whether the risk partition after expelling has risks, and if the risk still exists, returning to expelling the expelling service with the lowest service priority until the resource risk in the partition is relieved.
According to the resource management method of the mixed part server, multiple types of services are deployed by arranging multiple partitions in the server, so that mixed parts of the services are realized; the hardware resources of each partition are set according to the hardware configuration constraint of the corresponding service type, so that the hardware resources of each partition are matched with the requirements of the corresponding service type, and the resource allocation rate and the utilization rate of each partition are improved. The different hardware resources of the multiple partitions are reasonably deployed in the server, so that the resource allocation rate and the utilization rate of the server are improved. In addition, the corresponding services are isolated by setting the partitions, so that the situation that the services of different partitions find resources to preempt is avoided; and the resource utilization rate of the server is checked at regular time, and when the resource utilization rate of the server exceeds the limit, the partition in the server is subjected to service eviction, so that the normal operation of main services in the server is ensured.
Fig. 6 is a block diagram of a resource management device of a hybrid server according to an exemplary embodiment of the present application, and as shown in fig. 6, the resource management device of a hybrid server includes:
a determining module 610, configured to determine, according to a first preset period, a resource utilization of the hybrid server as described above;
and a service eviction module 620, configured to perform service eviction based on the resource utilization of each partition in the hybrid server when the resource utilization of the hybrid server exceeds a first threshold.
According to the resource management device of the mixed part server, a plurality of partitions are arranged in the server to deploy a plurality of types of services, so that mixed parts of the services are realized; the hardware resources of each partition are set according to the hardware configuration constraint of the corresponding service type, so that the hardware resources of each partition are matched with the requirements of the corresponding service type, and the resource allocation rate and the utilization rate of each partition are improved. The different hardware resources of the multiple partitions are reasonably deployed in the server, so that the resource allocation rate and the utilization rate of the server are improved. In addition, the corresponding services are isolated by setting the partitions, so that the situation that the services of different partitions find resources to preempt is avoided; and the resource utilization rate of the server is checked at regular time, and when the resource utilization rate of the server exceeds the limit, the partition in the server is subjected to service eviction, so that the normal operation of main services in the server is ensured.
Fig. 7 shows a schematic diagram of a computer system suitable for use in implementing the electronic device of the embodiments of the present application. It should be noted that, the computer system 700 of the electronic device shown in fig. 7 is only an example, and should not impose any limitation on the functions and the application scope of the embodiments of the present application.
As shown in fig. 7, the computer system 700 includes a central processing unit (Central Processing Unit, CPU) 701 that can perform various appropriate actions and processes, such as performing the methods in the above-described embodiments, according to a program stored in a Read-Only Memory (ROM) 702 or a program loaded from a storage section 708 into a random access Memory (Random Access Memory, RAM) 703. In the RAM 703, various programs and data required for the system operation are also stored. The CPU 701, ROM 702, and RAM 703 are connected to each other through a bus 704. An Input/Output (I/O) interface 705 is also connected to bus 704.
The following components are connected to the I/O interface 705: an input section 706 including a keyboard, a mouse, and the like; an output section 707 including a Cathode Ray Tube (CRT), a liquid crystal display (Liquid Crystal Display, LCD), and the like, a speaker, and the like; a storage section 708 including a hard disk or the like; and a communication section 709 including a network interface card such as a LAN (Local Area Network ) card, a modem, or the like. The communication section 709 performs communication processing via a network such as the internet. The drive 710 is also connected to the I/O interface 705 as needed. A removable medium 711 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is installed on the drive 710 as needed, so that a computer program read out therefrom is installed into the storage section 708 as needed.
In particular, according to embodiments of the present application, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, embodiments of the present application include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising a computer program for performing the method shown in the flowchart. In such an embodiment, the computer program may be downloaded and installed from a network via the communication portion 709, and/or installed from the removable medium 711. When executed by a Central Processing Unit (CPU) 701, performs the various functions defined in the system of the present application.
It should be noted that, the computer readable medium shown in the embodiments of the present application may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium may be, for example, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-Only Memory (ROM), an erasable programmable read-Only Memory (Erasable Programmable Read Only Memory, EPROM), flash Memory, an optical fiber, a portable compact disc read-Only Memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, with a computer-readable computer program embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. A computer program embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the foregoing.
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. Where each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units involved in the embodiments of the present application may be implemented by means of software, or may be implemented by means of hardware, and the described units may also be provided in a processor. Wherein the names of the units do not constitute a limitation of the units themselves in some cases.
Another aspect of the present application also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor of a computer, causes the computer to perform a method as before. The computer-readable storage medium may be included in the electronic device described in the above embodiment or may exist alone without being incorporated in the electronic device.
Another aspect of the present application also provides a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs the service mix and forecast method provided in the above embodiments.
The above embodiments are merely preferred embodiments for the purpose of fully explaining the present application, and the scope of the present application is not limited thereto. Equivalent substitutions and modifications will occur to those skilled in the art based on the present application, and are intended to be within the scope of the present application.
Claims (11)
1. A hybrid server, comprising:
a plurality of partitions for deploying multiple types of services;
the plurality of partitions are obtained by dividing hardware resources of the server, the hardware resources of the plurality of partitions are isolated from each other, and the hardware resources of each partition are set according to hardware configuration constraint of a corresponding service type.
2. The hybrid server of claim 1, wherein the hardware configuration constraints comprise proportions between a plurality of hardware resources, wherein the hardware resources comprise processors, disks, and memory.
3. The hybrid server of claim 1, wherein the plurality of partitions are partitioned into hardware resources of the server based on a control population.
4. A method for resource management of a hybrid server, comprising:
determining the resource utilization of the hybrid server according to any one of claims 1 to 3 according to a first preset period;
and when the resource utilization rate of the hybrid server exceeds a first threshold, performing service eviction based on the resource utilization rate of each partition in the hybrid server.
5. The method for resource management of a hybrid server according to claim 4, wherein the eviction service based on the resource utilization of each partition in the hybrid server comprises:
for each partition, when the resource utilization rate of the partition is greater than a second threshold value, taking the partition as a risk partition;
service eviction is performed on at least one of the risk partitions.
6. The method for resource management of a hybrid server according to claim 4, further comprising:
determining the resource utilization rate of each partition in each partition according to a second preset period, wherein the first preset period is the same as or different from the second preset period;
and for each partition, when the resource utilization rate of the partition is larger than a second threshold value, taking the partition as a risk partition, and performing service eviction on the risk partition.
7. The method of resource management of a hybrid server according to claim 5 or 6, wherein service eviction of the risk partition comprises:
expelling a service of the risk partition based at least on service priority;
determining the resource utilization rate of the risk partition;
returning to said step of evicting one of said risk partitions based at least on service priority if there are evictable services in said risk partition when the resource utilization of said risk partition exceeds a second threshold; if the eviction service does not exist in the risk zone, ending the service eviction of the risk zone and sending an alarm event;
and ending the service eviction of the risk zone when the resource utilization rate of the risk zone does not exceed the second threshold value.
8. The method for resource management of a hybrid server according to claim 7, further comprising, after service eviction for all the risk zones:
if the resource utilization rate of the hybrid server exceeds the first threshold, sending a machine alarm; or alternatively
And if the resource utilization rate of the hybrid server does not exceed the first threshold, recording a self-healing event.
9. A resource management device of a hybrid server, comprising:
a determining module, configured to determine, according to a first preset period, a resource utilization rate of the hybrid server according to any one of claims 1 to 3;
and the service eviction module is used for performing service eviction based on the resource utilization rate of each partition in the hybrid server when the resource utilization rate of the hybrid server exceeds a first threshold.
10. A server, comprising:
a processor; and
a memory in which a program is stored,
wherein the program comprises instructions which, when executed by the processor, cause the processor to perform the method according to any of claims 4-8.
11. A non-transitory computer readable storage medium storing computer instructions for causing a computer to perform the method of any one of claims 4-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310303098.7A CN116339989A (en) | 2023-03-23 | 2023-03-23 | Mixed part server, resource management method and device of mixed part server |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310303098.7A CN116339989A (en) | 2023-03-23 | 2023-03-23 | Mixed part server, resource management method and device of mixed part server |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116339989A true CN116339989A (en) | 2023-06-27 |
Family
ID=86880185
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310303098.7A Pending CN116339989A (en) | 2023-03-23 | 2023-03-23 | Mixed part server, resource management method and device of mixed part server |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116339989A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116501478A (en) * | 2023-06-28 | 2023-07-28 | 中国电信股份有限公司 | Task allocation method, device, equipment, medium and digital twin system |
-
2023
- 2023-03-23 CN CN202310303098.7A patent/CN116339989A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116501478A (en) * | 2023-06-28 | 2023-07-28 | 中国电信股份有限公司 | Task allocation method, device, equipment, medium and digital twin system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111966500B (en) | Resource scheduling method and device, electronic equipment and storage medium | |
| CN108701059B (en) | Multi-tenant resource allocation method and system | |
| US8751657B2 (en) | Multi-client storage system and storage system management method | |
| US8463908B2 (en) | Method and apparatus for hierarchical management of system resources | |
| CN109936604B (en) | Resource scheduling method, device and system | |
| US8131855B2 (en) | Management computer, resource management method, resource management computer program, recording medium, and information processing system | |
| US11138049B1 (en) | Generating narratives for optimized compute platforms | |
| US20050108714A1 (en) | Dynamic resource management system and method for multiprocessor systems | |
| US20110231853A1 (en) | Method and apparatus for managing reallocation of system resources | |
| CN103763346B (en) | A kind of distributed resource scheduling method and device | |
| CN113641457A (en) | Container creation method, device, apparatus, medium, and program product | |
| WO2022105659A1 (en) | Application container management method and apparatus, and device. | |
| CN112905342B (en) | Resource scheduling method, device, equipment and computer readable storage medium | |
| CN111866054A (en) | Cloud host building method and device, electronic equipment and readable storage medium | |
| CN113742114A (en) | System current limiting method and device | |
| US9547576B2 (en) | Multi-core processor system and control method | |
| CN116339989A (en) | Mixed part server, resource management method and device of mixed part server | |
| CN112749002A (en) | Method and device for dynamically managing cluster resources | |
| CN114116173A (en) | Method, device and system for dynamically adjusting task allocation | |
| CN114153549A (en) | Virtual machine creation method and related equipment | |
| CN112527490B (en) | Node resource management and control method and device, electronic equipment and storage medium | |
| CN115658311A (en) | Resource scheduling method, device, equipment and medium | |
| CN116360994A (en) | Scheduling method, device, server and storage medium of distributed heterogeneous resource pool | |
| EP4206915A1 (en) | Container creation method and apparatus, electronic device, and storage medium | |
| CN111694670B (en) | Resource allocation method, apparatus, device and computer readable 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 |