CN112783441A - Method and device for adjusting read-write speed limit of virtual machine disk and computing equipment - Google Patents

Method and device for adjusting read-write speed limit of virtual machine disk and computing equipment Download PDF

Info

Publication number
CN112783441A
CN112783441A CN202110024118.8A CN202110024118A CN112783441A CN 112783441 A CN112783441 A CN 112783441A CN 202110024118 A CN202110024118 A CN 202110024118A CN 112783441 A CN112783441 A CN 112783441A
Authority
CN
China
Prior art keywords
read
write
virtual machine
speed limit
value
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
Application number
CN202110024118.8A
Other languages
Chinese (zh)
Other versions
CN112783441B (en
Inventor
李彭
施跃跃
刘震
洪华
董龙
鲁逸丁
谢增强
王辛
裘斌伟
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
China Unionpay Co Ltd
Original Assignee
China Unionpay Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by China Unionpay Co Ltd filed Critical China Unionpay Co Ltd
Priority to CN202110024118.8A priority Critical patent/CN112783441B/en
Publication of CN112783441A publication Critical patent/CN112783441A/en
Application granted granted Critical
Publication of CN112783441B publication Critical patent/CN112783441B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
    • G06F3/0601—Interfaces specially adapted for storage systems
    • G06F3/0602—Interfaces specially adapted for storage systems specifically adapted to achieve a particular effect
    • G06F3/061—Improving I/O performance
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
    • G06F3/0601—Interfaces specially adapted for storage systems
    • G06F3/0628—Interfaces specially adapted for storage systems making use of a particular technique
    • G06F3/0629—Configuration or reconfiguration of storage systems
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
    • G06F3/0601—Interfaces specially adapted for storage systems
    • G06F3/0668—Interfaces specially adapted for storage systems adopting a particular infrastructure
    • G06F3/0671—In-line storage system
    • G06F3/0673—Single storage device
    • G06F3/0674—Disk device
    • G06F3/0676—Magnetic disk device
    • 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
    • G06F9/44—Arrangements for executing specific programs
    • G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
    • G06F9/45533—Hypervisors; Virtual machine monitors
    • G06F9/45558—Hypervisor-specific management and integration aspects
    • 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)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Human Computer Interaction (AREA)
  • Software Systems (AREA)
  • Debugging And Monitoring (AREA)

Abstract

The embodiment of the invention relates to the technical field of computers, in particular to a method and a device for adjusting the read-write speed limit of a virtual machine disk, a computing device and a computer readable storage medium. The method comprises the following steps: acquiring a first read-write rate of each first virtual machine deployed on a computing node; and if the first read-write speed of M first virtual machines in each first virtual machine exceeds a speed threshold and the sum of the first read-write speeds of the first virtual machines does not exceed the read-write performance threshold of the computing node, setting the read-write speed limit of at least one first virtual machine in the M first virtual machines as a first speed limit value. Therefore, the disk performance is used more optimally under the condition of not influencing the read-write performance of other virtual machines of different computing nodes.

Description

Method and device for adjusting read-write speed limit of virtual machine disk and computing equipment
Technical Field
The embodiment of the invention relates to the technical field of computers, in particular to a method and a device for adjusting the read-write speed limit of a virtual machine disk, a computing device and a computer readable storage medium.
Background
At present, the cloud system technical framework based on Openstack is more and more widely used in the industry, the disk read-write performance of a virtual machine in a cloud system is very important for daily use of tenants, and particularly, when the cloud system is used in scenes such as big data operation or file batch generation, the disk read-write performance directly affects the application performance. Meanwhile, in the cloud system, there is generally no special priority difference between virtual machines of different tenants.
The cloud system is designed based on a sharing concept, and virtual machines of multiple tenants run on a common computing node infrastructure and share underlying computing resources. However, if a plurality of virtual machines with higher requirements for disk read-write performance are operated on one computing node, there is a flow contention for disk read-write between the plurality of virtual machines, which often results in unstable disk performance of a single virtual machine. And according to the actual test result, the more virtual machines run on a single computing node, the worse the read-write stability of the disk.
One currently adopted method is to divide the read-write rate of a cloud hard disk by a fixed value. If a fixed speed limit threshold scheme is adopted, partial disk reading and writing of the virtual machines on the same computing node can reach a bottleneck, but the disk reading and writing quantity of other virtual machines is very small, and resource waste is brought.
In summary, there is a need for a method for adjusting the read-write speed limit of a virtual machine disk, so as to solve the problem of resource waste caused by the fact that the read-write speed limit of the virtual machine disk cannot be dynamically adjusted.
Disclosure of Invention
The embodiment of the invention provides a method for adjusting the read-write speed limit of a virtual machine disk, which is used for solving the problem of resource waste caused by the fact that the read-write speed limit of the virtual machine disk cannot be dynamically adjusted.
The embodiment of the invention provides a method for adjusting the read-write speed limit of a virtual machine disk, which comprises the following steps:
acquiring a first read-write rate of each first virtual machine deployed on a computing node;
if the first read-write speed of M first virtual machines in each first virtual machine exceeds a speed threshold and the sum of the first read-write speeds of the first virtual machines does not exceed the read-write performance threshold of the computing node, setting the read-write speed limit of at least one first virtual machine in the M first virtual machines as a first speed limit value; the first speed limit value is higher than the initial read-write speed limit of each first virtual machine; the speed threshold is determined according to the read-write speed limit; m is a positive integer.
If the first read-write speed of M first virtual machines in each first virtual machine exceeds a speed threshold, indicating that high-disk read-write requirements of the M first virtual machines exist; and meanwhile, the sum of the first read-write rates of the first virtual machines does not exceed the read-write performance threshold of the computing node, which indicates that the high read-write requirements do not exist in the read-write of the disk of the whole computing node server. Therefore, dynamic disk speed limit adjustment can be carried out on the disk of each first virtual machine deployed on the computing node, so that the read-write speed limit of at least one first virtual machine in the M first virtual machines is higher than the initial read-write speed limit. Therefore, the disk performance is used more optimally under the condition of not influencing the read-write performance of other virtual machines of different computing nodes.
Optionally, the initial read-write speed limit is determined by the following method, including:
acquiring historical operating conditions of each second virtual machine in a cloud system where the computing node is located;
establishing a simulated operation environment of each first virtual machine according to the historical operation condition of each second virtual machine;
determining the read-write rate fluctuation value of each first virtual machine under a second speed limit value in the simulated operation environment;
and if the read-write speed fluctuation value of each first virtual machine accords with a fluctuation threshold value, determining the second speed limit value as the initial read-write speed limit.
And establishing a simulated operation environment of each first virtual machine, so that the first virtual machines can be simulated to operate in the simulated operation environment to obtain a read-write speed fluctuation value under the second speed limit value, and determining the initial read-write speed limit according to the relation between the fluctuation value and a fluctuation threshold value. The initial read-write speed limit obtained in the way is objectively determined through the operation condition of each first virtual machine, so that the influence of other factors such as the capacity of a cloud hard disk of a tenant and the like is avoided; meanwhile, performance stability when high disk read-write requests simultaneously occur to each first virtual machine on the same computing node can be guaranteed within a range allowed by the read-write performance of the physical machine total disk of the computing node.
Optionally, constructing a simulated operating environment of each first virtual machine according to the historical operating conditions of each second virtual machine, including:
determining the proportion values of different read-write states in the second virtual machines according to the historical operating conditions of the second virtual machines;
establishing simulated operating environments of the first virtual machines in different reading and writing states; and the read-write state of each first virtual machine in each simulated operation environment accords with the proportion value of each second virtual machine in the read-write state.
By enabling the read-write state of each first virtual machine in each simulated operation environment to accord with the proportion value of each second virtual machine in the read-write state, the proportion value can be ensured to more objectively and accurately reflect the proportion of the first virtual machine in different read-write states, and the subsequent calculation of the read-write rate fluctuation value of each first virtual machine in the simulated operation environment is more accurate.
Optionally, determining that the read-write rate fluctuation value of each first virtual machine meets a fluctuation threshold by:
determining the read-write rate fluctuation value of the computing node according to the read-write rate fluctuation value of each first virtual machine in each simulated operation environment and the proportional value in the read-write state corresponding to each simulated operation environment;
and determining that the read-write rate fluctuation value of each first virtual machine meets the fluctuation threshold value.
Therefore, the accuracy and the objectivity of the calculation of the read-write rate fluctuation value of the calculation node are improved.
Optionally, the method further comprises:
if the read-write rate fluctuation value of each first virtual machine does not accord with the fluctuation threshold value, acquiring a second read-write rate of each first virtual machine in each simulated operation environment;
and updating the second speed limit value according to the second read-write rate of each first virtual machine in each simulated operation environment and the proportional value of each first virtual machine in the read-write state corresponding to each simulated operation environment, returning to the simulated operation environment, and determining the read-write rate fluctuation value of each first virtual machine in the second speed limit value until the read-write rate fluctuation value of each first virtual machine meets the fluctuation threshold value.
Under the condition that the fluctuation value of the read-write speed does not accord with the fluctuation threshold value, adjusting the second speed limit value according to the proportion value of the second read-write speed and the corresponding proportion value under the simulated operation environment; and circularly adjusting the second speed limit value according to whether the read-write speed fluctuation value meets the fluctuation threshold value. Therefore, the read-write speed fluctuation value of each first virtual machine running under the limitation of the initial read-write speed limit is ensured to accord with the fluctuation threshold value, and the stable performance can be ensured.
Optionally, after setting the read-write speed limit of at least one first virtual machine of the M first virtual machines to be the first speed limit value, the method further includes:
and after the adjustment period is finished, adjusting the read-write speed limit of each virtual machine to the initial read-write speed limit.
The initial read-write speed limit determined by the method can ensure that the first virtual machines do not generate excessive traffic contention during operation, so that the virtual machines are ensured to have stable performance. Therefore, the read-write speed limit of the M first virtual machines is adjusted and limited in the adjustment period, the initial read-write speed limit is recovered after the period is finished, excessive disk resources cannot be continuously occupied even after the high disk read-write requirements of the M first virtual machines are finished, the adjustment dynamics is guaranteed, and meanwhile the stable operation of each first virtual machine in the computing node is guaranteed.
Optionally, setting the read-write speed limit of at least one first virtual machine of the M first virtual machines to be a first speed limit value includes:
Se＝Sbase+[SPmax*P-(S1+......+SN)]/M；
wherein S iseIs a first speed limit value; sbaseIs the initial speed limit value; SPmaxCalculating the peak value performance of the whole disk read-write of the node server; p is the acceptable percentage of the total disk read-write rate of the bottom-layer computing node physical machine set based on experience; SPmaxP is a read-write performance threshold of the computing node; s1To SNThe average value of the disk speed in the adjustment period on the N virtual machines is obtained; m is the number of the virtual machines of which the first read-write speed exceeds the speed threshold value.
In this way, the part of each first virtual machine where the sum of the first read-write rates does not exceed the performance threshold of the compute node can be averagely allocated to the M first virtual machines where the first read-write rates exceed the rate threshold. The speed limit values of the M first virtual machines are improved, and the disk performance is guaranteed to be used more optimally under the condition that other tenant virtual machines of different computing nodes are not affected.
Optionally, if the first read-write rates of M first virtual machines in each first virtual machine exceed a rate threshold, and the sum of the first read-write rates of each first virtual machine exceeds the read-write performance threshold of the computing node, setting the read-write speed limit of at least one first virtual machine in each first virtual machine to be a third speed limit value; and the third speed limit value is lower than the initial read-write speed limit.
If the first read-write rates of the M first virtual machines exceed the rate threshold value and the sum of the first read-write rates of the first virtual machines exceeds the read-write performance threshold value of the computing node, it is indicated that most of the first virtual machines in the computing node are in the read-write requirement of the high disk. At this time, the situation of traffic robbery of each first virtual machine needs to be prevented, so that the third speed limit value needs to be set lower than the initial speed limit value to avoid the problem of unstable performance of each virtual machine.
The embodiment of the invention also provides a device for adjusting the read-write speed limit of the virtual machine disk, which comprises the following steps:
the acquisition unit is used for acquiring a first read-write rate of each first virtual machine deployed on the computing node;
the processing unit is used for setting the read-write speed limit of at least one first virtual machine in the M first virtual machines as a first speed limit value if the first read-write speed of the M first virtual machines exceeds a speed threshold value and the sum of the first read-write speed of the M first virtual machines does not exceed the read-write performance threshold value of the computing node; the first speed limit value is higher than the initial read-write speed limit of each first virtual machine; the speed threshold is determined according to the read-write speed limit; m is a positive integer.
An embodiment of the present invention further provides a computing device, including:
a memory for storing a computer program;
a processor for calling the computer program stored in the memory and executing the method according to the obtained program.
An embodiment of the present invention further provides a computer-readable storage medium, where a computer-executable program is stored, where the computer-executable program is used to enable a computer to execute any one of the methods described above.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a schematic diagram illustrating an application scenario provided by an embodiment of the present invention;
FIG. 2 illustrates schematically one possible method of determining the initial read-write speed limit for a virtual machine;
FIG. 3 is a diagram illustrating an exemplary possible method for adjusting the read/write speed limit of a virtual machine disk;
FIG. 4 is a schematic diagram of an overall flow involved in an embodiment of the present invention;
fig. 5 is a diagram illustrating a possible apparatus 500 for adjusting a read/write speed limit of a virtual machine disk according to an embodiment of the present invention.
Detailed Description
To make the objects, embodiments and advantages of the present application clearer, the following description of exemplary embodiments of the present application will clearly and completely describe the exemplary embodiments of the present application with reference to the accompanying drawings in the exemplary embodiments of the present application, and it is to be understood that the described exemplary embodiments are only a part of the embodiments of the present application, and not all of the embodiments.
All other embodiments, which can be derived by a person skilled in the art from the exemplary embodiments described herein without inventive step, are intended to be within the scope of the claims appended hereto. In addition, while the disclosure herein has been presented in terms of one or more exemplary examples, it should be appreciated that aspects of the disclosure may be implemented solely as a complete embodiment.
It should be noted that the brief descriptions of the terms in the present application are only for the convenience of understanding the embodiments described below, and are not intended to limit the embodiments of the present application. These terms should be understood in their ordinary and customary meaning unless otherwise indicated.
The terms "first," "second," "third," and the like in the description and claims of this application and in the above-described drawings are used for distinguishing between similar or analogous objects or entities and are not necessarily intended to limit the order or sequence of any particular one, Unless otherwise indicated. It is to be understood that the terms so used are interchangeable under appropriate circumstances such that the embodiments described herein are, for example, capable of operation in sequences other than those illustrated or otherwise described herein.
Furthermore, the terms "comprises" and "comprising," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a product or device that comprises a list of elements is not necessarily limited to those elements explicitly listed, but may include other elements not expressly listed or inherent to such product or device.
Fig. 1 is a schematic diagram illustrating an application scenario provided by an embodiment of the present invention. As shown in fig. 1, a plurality of compute nodes 201, 202, and 203 are distributed in cloud system 100; multiple virtual machines are deployed on each compute node for running disk read-write tasks using the disk read-write performance of the compute node, such as virtual machines 301, 302, 303, and 304 deployed on compute node 201.
If the speed limit of the disk is not carried out, the disk read-write performance of the virtual machine is superior because the number of the virtual machines on the cloud is small at the initial stage of external service of the cloud system; however, as the number of virtual machines increases, the disk performance of the virtual machines may be significantly reduced, and when a plurality of virtual machines send high read/write requests, the speed stability may be very poor.
If a fixed speed limit threshold scheme is adopted, as shown in table 1, the corresponding read-write speed is finally determined according to the capacity and the upper limit of different cloud hard disks, that is: obtaining a speed limit value based on the guaranteed base of 100MB/s and the multiplication of the size of the actual cloud hard disk by a fixed coefficient; and setting an upper limit value, and taking the minimum value from the speed limit value and the upper limit value to limit the current so as to ensure the read-write isolation of the disks among different virtual machines. However, this may cause that some of the disk reads and writes of the virtual machines on the same computing node have reached a bottleneck, but the disk read and write amounts of other virtual machines are very small, which causes resource waste. Meanwhile, the method for determining the speed limit value greatly depends on the capacity of the cloud hard disk to a certain extent, namely, a tenant needs to configure the cloud hard disk with larger capacity to improve the read-write speed.
Read-write rate MB/s
Cloud hard disk 1 min {100+ volume (GB) × 0.15,150}
Cloud hard disk 2 min {100+ volume (GB) × 0.15,140}
Cloud hard disk 3 min {100+ volume (GB) × 0.15,140}
Cloud hard disk 4 min {128+ volume (GB) × 0.5,320}
Cloud hard disk 5 MAX 150
TABLE 1
If the charging guidance mode is adopted to guide the tenant to select the cloud hard disks with different charging levels, and the hard disks with high charging levels are adopted for the service system with high magnetic disk read-write performance requirements, on one hand, the tenant is required to definitely distinguish the service systems with different levels from each other in resource purchasing to select the cloud hard disks with different charging standards, certain requirements are required for tenant resource planning, and the method is not suitable for a scene that the service systems of different tenants in the cloud system have no obvious priority difference; on the other hand, a certain hysteresis may be caused, that is, if the service system has a sudden disk read-write performance requirement, a high-performance cloud hard disk needs to be purchased again or additional payment is needed to upgrade the disk performance, and the time and response are slow.
The embodiment of the invention provides a method for adjusting the read-write speed limit of a virtual machine disk, which is used for solving the problems that the read-write speed limit of the virtual machine disk cannot be dynamically adjusted, so that resource waste is caused, and the determination of the speed limit value greatly depends on the capacity of a cloud hard disk.
In a cloud system, disk read and write tasks are executed in multiple virtual machines running on the same compute node, as shown in fig. 1. If the disk read-write speed limit is not performed on each virtual machine, when the virtual machine 301 has a high disk read-write requirement, the disk read-write performance of the virtual machines 302, 303, and 304 can be seized to the maximum extent, so that the disk read-write tasks of the virtual machines 302, 303, and 304 cannot be performed normally. Fig. 2 exemplarily shows a possible method for determining an initial read-write speed limit of a virtual machine, which includes:
step 201, obtaining historical operating conditions of each second virtual machine in a cloud system where the computing node is located;
step 202, establishing a simulated operation environment of each first virtual machine according to the historical operation condition of each second virtual machine;
step 203, determining the read-write rate fluctuation value of each first virtual machine under the second speed limit value in the simulated operation environment;
and 204, if the read-write speed fluctuation value of each first virtual machine meets a fluctuation threshold, determining that the second speed limit value is the initial read-write speed limit.
If the first read-write speed of M first virtual machines in each first virtual machine exceeds a speed threshold, indicating that high-disk read-write requirements of the M first virtual machines exist; and meanwhile, the sum of the first read-write rates of the first virtual machines does not exceed the read-write performance threshold of the computing node, which indicates that the high read-write requirements do not exist in the read-write of the disk of the whole computing node server. Therefore, dynamic disk speed limit adjustment can be carried out on the disk of each first virtual machine deployed on the computing node, so that the read-write speed limit of at least one first virtual machine in the M first virtual machines is higher than the initial read-write speed limit. Therefore, the disk performance is used more optimally under the condition of not influencing the read-write performance of other virtual machines of different computing nodes.
Optionally, the method may be performed before a new computing node, such as the computing node 201, is deployed in the cloud system 100 for use, or may be performed after the new computing node is deployed in the cloud system 100 for use, which is not limited in this embodiment of the present invention. The cloud system 100 automatically creates a plurality of disk performance test special virtual machines on the computing nodes 201; simulating and initiating a calculation task and a disk read-write task inside each virtual machine, and transmitting disk read-write information such as a Central Processing Unit (CPU) and disk read-write speed to a baseline disk performance index calculation module through a monitoring data acquisition module in each virtual machine; the baseline disk performance index calculation module analyzes and confirms an initial read-write speed limit through an algorithm, and the initial read-write speed limit can become an initial read-write speed limit of each virtual machine delivered to a tenant for use; the cloud system 100 automatically reclaims each virtual machine, and then marks the new computing node 201 as an online state, which may formally provide computing resources for tenants on the cloud system.
Optionally, in step 202, constructing a simulated operating environment of the first virtual machine based on the historical disk read-write data of the second virtual machine in the cloud system, where the method includes:
determining the proportion values of different read-write states in the second virtual machines according to the historical operating conditions of the second virtual machines;
establishing simulated operating environments of the first virtual machines in different reading and writing states; and the read-write state of each first virtual machine in each simulated operation environment accords with the proportion value of each second virtual machine in the read-write state.
For example, the proportion of time slices for which the CPU is used for disk reading and writing is divided into arbitrary intervals or values. Such as division into 4 intervals: 0-25%, 25-50%, 50-75% and 75-100%. If the proportion of the time slices used by 10% of the virtual machines for reading and writing the CPU to the disk is 0-25%, the proportion of the time slices used by 20% of the virtual machines for reading and writing the CPU to the disk is 25-50%, the proportion of the time slices used by 30% of the virtual machines for reading and writing the CPU to the disk is 50-75%, and the proportion of the time slices used by 40% of the virtual machines for reading and writing the CPU to the disk is 75-100% in the whole cloud system according to the historical operating conditions. Based on the principle of statistics, it can be considered that in the computing node 201, 10% of the time slices used by the virtual machines to read and write the CPU to the disk account for 0-25%, 20% of the time slices used by the virtual machines to read and write the CPU to the disk account for 25-50%, 30% of the time slices used by the virtual machines to read and write the CPU to the disk account for 50-75%, and 40% of the time slices used by the virtual machines to read and write the CPU to the disk account for 75-100%. The above numbers are merely examples, and embodiments of the present invention are not limited thereto.
Thus, based on the above example, a simulated execution environment of the first virtual machine can be constructed as follows. For convenience of description, the cloud system 100 is illustrated as creating 4 virtual machines on the computing node 201.
Simulating a first operating environment: 4 virtual machines (100%) are enabled to operate a large amount of disk read-write tasks;
simulating an operation environment II: enabling 3 virtual machines (75%) to completely run a large number of disk read-write tasks, and enabling 1 virtual machine not to run the disk read-write tasks;
simulating a running environment III: enabling 2 virtual machines (50%) to completely run a large number of disk read-write tasks, and enabling 2 virtual machines not to run the disk read-write tasks;
and simulating a running environment IV: 1 virtual machine (25%) is enabled to operate a large amount of disk read-write tasks, and 3 virtual machines are not enabled to operate the disk read-write tasks;
by enabling the read-write state of each first virtual machine in each simulated operation environment to accord with the proportion value of each second virtual machine in the read-write state, the proportion value can be ensured to more objectively and accurately reflect the proportion of the first virtual machine in different read-write states, and the subsequent calculation of the read-write rate fluctuation value of each first virtual machine in the simulated operation environment is more accurate.
Optionally, in step 203, in the simulated operation environment, determining a read-write rate fluctuation value of each first virtual machine under a second speed limit value;
for example, in each simulated operating environment, the average value of the disk read-write speed of the virtual machine is recorded S11NAnd average value T1 of fluctuation degree of disk speed1N. For example, in a simulated operating environment one, the average values of the read-write rates of the disks of 4 virtual machines in a period of time are recorded as S1To S4And recording the disk read-write speed fluctuation values of 4 virtual machines in a period of time as T1To T4. Disk read-write rate mean S for 4 virtual machines1To S4Then averaging to obtain S114Averaging the disk read-write rate fluctuation values of the 4 virtual machines to obtain T114. By analogy, disk read-write rate mean values S2 of the virtual machines in the simulated operation environment II are obtained respectively14And average value T2 of fluctuation degree of disk speed14Disk read-write rate mean S3 for virtual machines in simulated runtime Environment three14And average value T3 of fluctuation degree of disk speed14Disk read-write rate mean value of virtual machines in simulated operating environment four S414And average value T4 of fluctuation degree of disk speed14。
Optionally, in step 204, if the read-write speed fluctuation value of each first virtual machine meets a fluctuation threshold, it is determined that the second speed limit value is the initial read-write speed limit.
Optionally, determining that the read-write rate fluctuation value of each first virtual machine meets a fluctuation threshold by:
determining the read-write rate fluctuation value of the computing node according to the read-write rate fluctuation value of each first virtual machine in each simulated operation environment and the proportional value in the read-write state corresponding to each simulated operation environment;
and determining that the read-write rate fluctuation value of each first virtual machine meets the fluctuation threshold value.
For example, the read-write rate fluctuation value T of each first virtual machinebaseCan be calculated by the following formula:
Tbase＝WS1*T11N+WS2*T21N+WS3*T31N+WS4*T41N；
wherein, in the four simulation operation environments enumerated above, WS140% of, WS230% of, WS320% of, WS410 percent; the above are merely examples, and embodiments of the present invention are not limited thereto.
And if the read-write speed fluctuation value of each first virtual machine accords with a fluctuation threshold value, determining the second speed limit value as the initial read-write speed limit. Wherein, the fluctuation threshold is the fluctuation degree which can be accepted by the read-write speed of the magnetic disk based on experience setting. The second speed limit value may be 0, or may be determined according to the second read/write rate of each first virtual machine in each simulated operating environment and the proportional value in the read/write state corresponding to each simulated operating environment, which is not limited in this embodiment of the present invention. Optionally, the second speed limit value is 0 at the initial time, that is, each virtual machine is enabled to read and write without speed limit. And when the subsequent obtained read-write rate fluctuation value does not accord with the fluctuation threshold value, determining according to the second read-write rate of each first virtual machine in each simulated operation environment and the proportional value in the read-write state corresponding to each simulated operation environment.
Therefore, the accuracy and the objectivity of the calculation of the read-write rate fluctuation value of the calculation node are improved.
Optionally, if the read-write rate fluctuation value of each first virtual machine does not meet the fluctuation threshold, obtaining a second read-write rate of each first virtual machine in each simulated operation environment;
and updating the second speed limit value according to the second read-write rate of each first virtual machine in each simulated operation environment and the proportional value of each first virtual machine in the read-write state corresponding to each simulated operation environment, returning to the simulated operation environment, and determining the read-write rate fluctuation value of each first virtual machine in the second speed limit value until the read-write rate fluctuation value of each first virtual machine meets the fluctuation threshold value.
Second read/write Rate, that is, average disk read/write Rate of virtual machine recorded in each simulated operating Environment S114、S214、S314、S414。
Optionally, the second speed limit is updated by the following formula:
Sbase＝WS1*S114+WS2*S214+WS3*S314+WS4*S414
wherein, in the four simulation operation environments enumerated above, WS140% of, WS230% of, WS320% of, WS410 percent; the above are merely examples, and embodiments of the present invention are not limited thereto.
Under the condition that the fluctuation value of the read-write speed does not accord with the fluctuation threshold value, adjusting the second speed limit value according to the proportion value of the second read-write speed and the corresponding proportion value under the simulated operation environment; and circularly adjusting the second speed limit value according to whether the read-write speed fluctuation value meets the fluctuation threshold value. Therefore, the read-write speed fluctuation value of each first virtual machine running under the limitation of the initial read-write speed limit is ensured to accord with the fluctuation threshold value, and the stable performance can be ensured.
And after the second speed limit value is obtained, returning to the step 203 again until the read-write rate fluctuation value of each first virtual machine is converged within the fluctuation threshold value. The second speed limit value can be set as the initial read-write speed limit.
And establishing a simulated operation environment of each first virtual machine, so that the first virtual machines can be simulated to operate in the simulated operation environment to obtain a read-write speed fluctuation value under the second speed limit value, and determining the initial read-write speed limit according to the relation between the fluctuation value and a fluctuation threshold value. The initial read-write speed limit obtained in the way is objectively determined through the operation condition of each first virtual machine, so that the influence of other factors such as the capacity of a cloud hard disk of a tenant and the like is avoided; meanwhile, performance stability when high disk read-write requests simultaneously occur to each first virtual machine on the same computing node can be guaranteed within a range allowed by the read-write performance of the physical machine total disk of the computing node.
In the cloud system, the virtual machines operate under the read-write speed limit value, so that the virtual machines can be prevented from contending for flow, and the performance stability of the virtual machines is improved. However, problems arise: on the same computing node, the read-write quantity of a disk of a part of virtual machines is very large, for example, in virtual machines 301 and 302 in fig. 1, the disk read-write tasks run by the virtual machines already prompt the disk performance of the virtual machines to reach a bottleneck. However, the amount of read and write of the disk of the other virtual machine is very small, such as the virtual machines 303 and 304 in fig. 1, the running tasks of which have prompted that the read and write requirements of the disk of the virtual machine are very small. The intelligent speed limit module in the computing node 201 is started at this time, and the disk speed limit values of the virtual machines 301 and 302 are appropriately and temporarily adjusted on the premise that the disk read-write quantity of the bottom computing node is controllable, so that the tasks in the virtual machines 301 and 302 can be guaranteed to run more quickly.
Fig. 3 exemplarily shows a possible method for adjusting the read-write speed limit of a virtual machine disk, which includes:
301, acquiring a first read-write rate of each first virtual machine deployed on a computing node;
step 302, if the first read-write speed of M first virtual machines in each first virtual machine exceeds a speed threshold and the sum of the first read-write speeds of the first virtual machines does not exceed the read-write performance threshold of the computing node, setting the read-write speed limit of at least one first virtual machine in the M first virtual machines as a first speed limit value; the first speed limit value is higher than the initial read-write speed limit of each first virtual machine; the speed threshold is determined according to the read-write speed limit; m is a positive integer.
Alternatively, the initial read-write rate may be determined by a method as shown in fig. 2, which is not limited by the embodiment of the present invention.
Optionally, the adjusting method may be performed in one adjusting period, and after the adjusting period is finished, the read-write speed limit of each virtual machine is adjusted to the initial read-write speed limit. And when the first read-write rates of some virtual machines exceed the rate threshold value and the sum of the first read-write rates of all the first virtual machines does not exceed the read-write performance threshold value of the computing node, adjusting again.
Optionally, the above adjustment method may be performed once or multiple times in one adjustment period, and may also be performed with a custom setting depending on the adjustment condition. The first speed limit value after each adjustment is the read-write speed limit, and the speed threshold value of the next adjustment is determined on the basis of the read-write speed limit. Alternatively, the rate threshold may be less than or equal to the read-write speed limit. For example, the initial read-write speed limit is 50MB/s, in an adjustment period, the first speed limit value obtained after the first adjustment is 60MB/s, and the speed threshold value is determined to be 58MB/s on the basis of 60 MB/s; and then, when the first read-write speed of M first virtual machines in each first virtual machine exceeds the speed threshold value 58MB/s and the sum of the first read-write speeds of the first virtual machines does not exceed the read-write performance threshold value of the computing node next time, adjusting the first speed limit value again.
The initial read-write speed limit determined by the method can ensure that the first virtual machines do not generate excessive traffic contention during operation, so that the virtual machines are ensured to have stable performance. Therefore, the read-write speed limit of the M first virtual machines is adjusted and limited in the adjustment period, the initial read-write speed limit is recovered after the period is finished, excessive disk resources cannot be continuously occupied even after the high disk read-write requirements of the M first virtual machines are finished, the adjustment dynamics is guaranteed, and meanwhile the stable operation of each first virtual machine in the computing node is guaranteed.
Optionally, the read-write speed limit of at least one first virtual machine in the M first virtual machines is set as a first speed limit value SeThe method comprises the following steps:
Se＝Sbase+[SPmax*P-(S1+......+SN)]/M
wherein S isbaseIs the initial speed limit value; SPmaxCalculating the peak value performance of the whole disk read-write of the node server; p is the acceptable percentage of the total disk read-write rate of the bottom-layer computing node physical machine set based on experience; SPmaxP is a read-write performance threshold of the computing node; s1To SNThe average value of the disk speed in the adjustment period on the N virtual machines is obtained; m is the number of the virtual machines of which the first read-write speed exceeds the speed threshold value.
In this way, the part of each first virtual machine where the sum of the first read-write rates does not exceed the performance threshold of the compute node can be averagely allocated to the M first virtual machines where the first read-write rates exceed the rate threshold. The speed limit values of the M first virtual machines are improved, and the disk performance is guaranteed to be used more optimally under the condition that other tenant virtual machines of different computing nodes are not affected.
Optionally, the method further comprises:
if the first read-write rates of M first virtual machines in each first virtual machine exceed a rate threshold value and the sum of the first read-write rates of each first virtual machine exceeds the read-write performance threshold value of the computing node, setting the read-write speed limit of at least one first virtual machine in each first virtual machine to be a third speed limit value; and the third speed limit value is lower than the initial read-write speed limit.
If the first read-write rates of the M first virtual machines exceed the rate threshold value and the sum of the first read-write rates of the first virtual machines exceeds the read-write performance threshold value of the computing node, it is indicated that most of the first virtual machines in the computing node are in the read-write requirement of the high disk. At this time, the situation of traffic robbery of each first virtual machine needs to be prevented, so that the third speed limit value needs to be set lower than the initial speed limit value to avoid the problem of unstable performance of each virtual machine.
Optionally, setting the read-write speed limit of at least one of the first virtual machines to be a third speed limit value includes:
Se＝SPmax*P/N
wherein, SPmaxCalculating the peak value performance of the whole disk read-write of the node server; p is the acceptable percentage of the total disk read-write rate of the bottom-layer computing node physical machine set based on experience; SPmaxP is a read-write performance threshold of the computing node; n is the number of first virtual machines in the compute node.
In order to more clearly describe the method for adjusting the read-write speed limit of the virtual machine disk, the following describes the process involved in the embodiment of the present invention in an overall manner with reference to fig. 4. As shown in fig. 4, the following steps may be included:
step 401, start;
step 402, tenants apply for virtual machine resources;
step 403, the cloud system enters a virtual machine creation process;
step 404, generating an initial read-write speed limit by a baseline disk performance index calculation module;
step 405, the cloud system initializes the initial read-write speed limit of the virtual machine according to the performance index;
step 406, after the virtual machine is created, the tenant deploys and uses the application;
step 407, judging whether the high magnetic disk read-write performance requirement exists, if so, entering step 408; if not, go to step 4011;
step 408, the intelligent speed limit module calculates a first speed limit value of the virtual machine in the current period and takes effect;
step 409, ending the speed adjusting period;
step 4010, determining whether the high disk read-write performance still exists, if yes, returning to step 408; if not, go to step 4011;
step 4011, maintaining the initial read-write speed limit of the virtual machine;
step 4012, end;
the embodiment of the present invention further provides a device 500 for adjusting the read-write speed limit of the virtual machine disk, as shown in fig. 5. The method comprises the following steps:
an obtaining unit 501, configured to obtain a first read-write rate of each first virtual machine deployed on a compute node;
a processing unit 502, configured to set a read-write speed limit of at least one first virtual machine of the M first virtual machines to a first speed limit value if the first read-write speed of the M first virtual machines exceeds a speed threshold and a sum of the first read-write speeds of the M first virtual machines does not exceed the read-write performance threshold of the computing node; the first speed limit value is higher than the initial read-write speed limit of each first virtual machine; the speed threshold is determined according to the read-write speed limit; m is a positive integer.
An embodiment of the present invention further provides a computing device, including:
a memory for storing a computer program;
a processor for calling the computer program stored in the memory and executing the method according to the obtained program.
An embodiment of the present invention further provides a computer-readable storage medium, where a computer-executable program is stored, where the computer-executable program is used to enable a computer to execute any one of the methods described above.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present application without departing from the spirit and scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is intended to include such modifications and variations as well.

Claims (11)

1. A method for adjusting the read-write speed limit of a virtual machine disk is characterized by comprising the following steps:
acquiring a first read-write rate of each first virtual machine deployed on a computing node;
if the first read-write speed of M first virtual machines in each first virtual machine exceeds a speed threshold and the sum of the first read-write speeds of the first virtual machines does not exceed the read-write performance threshold of the computing node, setting the read-write speed limit of at least one first virtual machine in the M first virtual machines as a first speed limit value; the first speed limit value is higher than the initial read-write speed limit of each first virtual machine; the speed threshold is determined according to the read-write speed limit; m is a positive integer.
2. The method of claim 1,
the initial read-write speed limit is determined by the following method, including:
acquiring historical operating conditions of each second virtual machine in a cloud system where the computing node is located;
establishing a simulated operation environment of each first virtual machine according to the historical operation condition of each second virtual machine;
determining the read-write rate fluctuation value of each first virtual machine under a second speed limit value in the simulated operation environment;
and if the read-write speed fluctuation value of each first virtual machine accords with a fluctuation threshold value, determining the second speed limit value as the initial read-write speed limit.
3. The method of claim 2,
according to the historical operating conditions of the second virtual machines, establishing a simulated operating environment of the first virtual machines, wherein the simulated operating environment comprises the following steps:
determining the proportion values of different read-write states in the second virtual machines according to the historical operating conditions of the second virtual machines;
establishing simulated operating environments of the first virtual machines in different reading and writing states; and the read-write state of each first virtual machine in each simulated operation environment accords with the proportion value of each second virtual machine in the read-write state.
4. The method of claim 3,
determining that the read-write rate fluctuation value of each first virtual machine meets a fluctuation threshold value in the following way, including:
determining the read-write rate fluctuation value of the computing node according to the read-write rate fluctuation value of each first virtual machine in each simulated operation environment and the proportional value in the read-write state corresponding to each simulated operation environment;
and determining that the read-write rate fluctuation value of each first virtual machine meets the fluctuation threshold value.
5. The method of claim 3, further comprising:
if the read-write rate fluctuation value of each first virtual machine does not accord with the fluctuation threshold value, acquiring a second read-write rate of each first virtual machine in each simulated operation environment;
and updating the second speed limit value according to the second read-write rate of each first virtual machine in each simulated operation environment and the proportional value of each first virtual machine in the read-write state corresponding to each simulated operation environment, returning to the simulated operation environment, and determining the read-write rate fluctuation value of each first virtual machine in the second speed limit value until the read-write rate fluctuation value of each first virtual machine meets the fluctuation threshold value.
6. The method of any one of claims 1-5,
after setting the read-write speed limit of at least one first virtual machine in the M first virtual machines to be the first speed limit value, the method further includes:
and after the adjustment period is finished, adjusting the read-write speed limit of each virtual machine to the initial read-write speed limit.
7. The method of any one of claims 1-5,
setting the read-write speed limit of at least one first virtual machine in the M first virtual machines as a first speed limit value, and the method comprises the following steps:
Se＝Sbase+[SPmax*P-(S1+......+SN)]/M；
wherein S iseIs a first speed limit value; sbaseIs the initial speed limit value; SPmaxCalculating the peak value performance of the whole disk read-write of the node server; p is the acceptable percentage of the total disk read-write rate of the bottom-layer computing node physical machine set based on experience; SPmaxP is a read-write performance threshold of the computing node; s1To SNThe average value of the disk speed in the adjustment period on the N virtual machines is obtained; m is the number of the virtual machines of which the first read-write speed exceeds the speed threshold value.
8. The method of any one of claims 1-5, further comprising:
if the first read-write rates of M first virtual machines in each first virtual machine exceed a rate threshold value and the sum of the first read-write rates of each first virtual machine exceeds the read-write performance threshold value of the computing node, setting the read-write speed limit of at least one first virtual machine in each first virtual machine to be a third speed limit value; and the third speed limit value is lower than the initial read-write speed limit.
9. A device for adjusting the read-write speed limit of a virtual machine disk is characterized by comprising:
the acquisition unit is used for acquiring a first read-write rate of each first virtual machine deployed on the computing node;
the processing unit is used for setting the read-write speed limit of at least one first virtual machine in the M first virtual machines as a first speed limit value if the first read-write speed of the M first virtual machines exceeds a speed threshold value and the sum of the first read-write speed of the M first virtual machines does not exceed the read-write performance threshold value of the computing node; the first speed limit value is higher than the initial read-write speed limit of each first virtual machine; the speed threshold is determined according to the read-write speed limit; m is a positive integer.
10. A computing device, comprising:
a memory for storing a computer program;
a processor for calling a computer program stored in said memory and executing the method of any one of claims 1 to 8 in accordance with the obtained program.
11. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer-executable program for causing a computer to execute the method of any one of claims 1 to 8.
CN202110024118.8A 2021-01-08 2021-01-08 Method and device for adjusting read-write speed limit of virtual machine disk and computing equipment Active CN112783441B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110024118.8A CN112783441B (en) 2021-01-08 2021-01-08 Method and device for adjusting read-write speed limit of virtual machine disk and computing equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110024118.8A CN112783441B (en) 2021-01-08 2021-01-08 Method and device for adjusting read-write speed limit of virtual machine disk and computing equipment

Publications (2)

Publication Number Publication Date
CN112783441A true CN112783441A (en) 2021-05-11
CN112783441B CN112783441B (en) 2023-08-01

Family

ID=75756920

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110024118.8A Active CN112783441B (en) 2021-01-08 2021-01-08 Method and device for adjusting read-write speed limit of virtual machine disk and computing equipment

Country Status (1)

Country Link
CN (1) CN112783441B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116610266A (en) * 2023-07-18 2023-08-18 中移(苏州)软件技术有限公司 Method and device for adjusting read-write performance of virtual machine disk and related equipment

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2007148371A1 (en) * 2006-06-19 2007-12-27 Nec Corporation Performance management system and performance management method for virtual machine
US20150236971A1 (en) * 2013-12-24 2015-08-20 Hill-Rom Services, Inc. Cloud compute scheduling using a heuristic contention model
CN107544755A (en) * 2017-08-02 2018-01-05 新华三云计算技术有限公司 The control method and device of a kind of reading and writing data
WO2018199415A1 (en) * 2017-04-26 2018-11-01 (주) 글루시스 Method for limiting input and output performance for virtual machine
CN110018781A (en) * 2018-01-09 2019-07-16 阿里巴巴集团控股有限公司 Disk flow control method, device and electronic equipment
CN111352592A (en) * 2020-02-27 2020-06-30 腾讯科技（深圳）有限公司 Disk read-write control method, device, equipment and computer readable storage medium

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2007148371A1 (en) * 2006-06-19 2007-12-27 Nec Corporation Performance management system and performance management method for virtual machine
US20150236971A1 (en) * 2013-12-24 2015-08-20 Hill-Rom Services, Inc. Cloud compute scheduling using a heuristic contention model
WO2018199415A1 (en) * 2017-04-26 2018-11-01 (주) 글루시스 Method for limiting input and output performance for virtual machine
CN107544755A (en) * 2017-08-02 2018-01-05 新华三云计算技术有限公司 The control method and device of a kind of reading and writing data
CN110018781A (en) * 2018-01-09 2019-07-16 阿里巴巴集团控股有限公司 Disk flow control method, device and electronic equipment
CN111352592A (en) * 2020-02-27 2020-06-30 腾讯科技（深圳）有限公司 Disk read-write control method, device, equipment and computer readable storage medium

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116610266A (en) * 2023-07-18 2023-08-18 中移(苏州)软件技术有限公司 Method and device for adjusting read-write performance of virtual machine disk and related equipment
CN116610266B (en) * 2023-07-18 2023-10-10 中移(苏州)软件技术有限公司 Method and device for adjusting read-write performance of virtual machine disk and related equipment

Also Published As

Publication number Publication date
CN112783441B (en) 2023-08-01

Similar Documents

Publication Publication Date Title
CN107229518B (en) Distributed cluster training method and device
CN110287197B (en) Data storage method, migration method and device
CN109408590B (en) Method, device and equipment for expanding distributed database and storage medium
CN110413412B (en) GPU (graphics processing Unit) cluster resource allocation method and device
US20140059559A1 (en) Intellegent tiering
CN115129782A (en) Partition level connection method and device for distributed database
JP2018515844A (en) Data processing method and system
EP4088185A1 (en) Automated local scaling of compute instances
CN113177050A (en) Data balancing method, device, query system and storage medium
CN109960579A (en) A kind of method and device of adjustment business container
CN112783441A (en) Method and device for adjusting read-write speed limit of virtual machine disk and computing equipment
EP4006725A1 (en) Virtual machine migration processing and strategy generation method, apparatus and device, and storage medium
JP2011192049A (en) Virtual machine system, automatic migration method, and automatic migration program
CN104657216A (en) Resource allocation method and device for resource pool
CN110413393B (en) Cluster resource management method and device, computer cluster and readable storage medium
US10387578B1 (en) Utilization limiting for nested object queries
CN115269118A (en) Scheduling method, device and equipment of virtual machine
CN106909472B (en) Input/output load adjusting method and device of distributed file system
CN114817209A (en) Monitoring rule processing method and device, processor and electronic equipment
CN110083438B (en) Transaction distribution method, device, equipment and storage medium
CN110286949A (en) Process based on the read-write of physical host storage device hangs up method and relevant device
CN107122303B (en) Test method and device
CN106775854B (en) Method and device for generating configuration file
CN107045457A (en) A kind of method and device of multi-tenant resource-sharing
CN111796934A (en) Task issuing method and device, storage medium and electronic equipment

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