JP7447186B2 - Construction control method of computer system and virtualization infrastructure - Google Patents

Description

The present invention relates to a technology for constructing a virtualization infrastructure.

One of the virtualization infrastructures is HCI (Hyper Converged Infrastructure). In constructing an HCI, hardware that constitutes a base is prepared, a hypervisor is installed on the base, and a virtual machine (VM) that executes various applications is installed.

As a VM introduction technique, for example, the technique described in Patent Document 1 is known. Patent Document 1 states, ``A management node is a processor, a memory, and a storage device by arranging a virtual computer and a volume through which the virtual computer inputs and outputs data in one of a plurality of nodes. If the virtual computer and volume can be operated by allocating predetermined resources among the drive resources to the virtual computer and volume, and the virtual computer and volume can be placed on the same node among multiple nodes, the virtual computer and volume can be The same node is determined from among a plurality of nodes based on the difference in the ratio of the lease amount allocated to the resource among the plurality of resources.''

JP 2021-149299 Publication

There is a desire to shorten HCI construction time. On the other hand, a method can be considered to shorten the construction time by introducing a large number of VMs in parallel. However, when a large number of VMs are introduced in parallel, a bottleneck may occur in computer resources, and the construction time may become longer.

An object of the present invention is to realize a system and method that automatically sets the number of VMs to be installed in parallel (the number of tasks to be executed in parallel) that can suppress the occurrence of bottlenecks and shorten construction time.

A typical example of the invention disclosed in this application is as follows. That is, a computer system including at least one computer, connected to a construction execution system that executes a virtualization infrastructure construction process, wherein the virtualization infrastructure construction process includes a task of introducing a virtual machine, and the computer system The system obtains a progress rate of the virtual machine installed by the task and a performance value of computer resources of the virtual machine when a predetermined number of the tasks are executed by the construction execution system. , based on the progress rate and the performance value of the computer resource, calculate the number of parallel installations of the virtual machines that can build the virtualization infrastructure without bottlenecks and within the specified request time; .

According to the present invention, it is possible to automatically set the number of VMs to be introduced in parallel (the number of tasks to be executed in parallel) that can suppress the occurrence of bottlenecks and shorten the construction time. Problems, configurations, and effects other than those described above will be made clear by the description of the following examples.

1 is a diagram showing an example of the configuration of a system according to a first embodiment; FIG. 1 is a diagram showing an example of the hardware configuration of a computer included in the construction control system of Example 1. FIG. FIG. 3 is a diagram showing an example of a data structure of threshold information according to the first embodiment. 3 is a diagram showing an example of a data structure of a performance history database according to the first embodiment. FIG. 3 is a diagram showing an example of a data structure of a performance history database according to the first embodiment. FIG. 3 is a diagram showing an example of a data structure of a performance history database according to the first embodiment. FIG. 3 is a diagram showing an example of a data structure of a performance history database according to the first embodiment. FIG. 3 is a flowchart illustrating an example of processing executed by the construction control system of the first embodiment. 3 is a flowchart illustrating an example of processing executed by the construction control system of the first embodiment.

Embodiments of the present invention will be described below with reference to the drawings. However, the present invention should not be construed as being limited to the contents described in the Examples shown below. Those skilled in the art will readily understand that the specific configuration can be changed without departing from the spirit or spirit of the present invention.

In the configuration of the invention described below, the same or similar configurations or functions are denoted by the same reference numerals, and redundant explanations will be omitted.

In this specification, etc., expressions such as "first," "second," and "third" are used to identify constituent elements, and do not necessarily limit the number or order.

The position, size, shape, range, etc. of each component shown in the drawings etc. may not represent the actual position, size, shape, range, etc. in order to facilitate understanding of the invention. Therefore, the present invention is not limited to the position, size, shape, range, etc. disclosed in the drawings and the like.

FIG. 1 is a diagram illustrating an example of the configuration of a system according to a first embodiment. FIG. 2 is a diagram showing an example of the hardware configuration of a computer included in the construction control system of the first embodiment.

The system includes a construction control system 100, a construction execution system 101, a platform 102, and a management terminal 103. The construction control system 100, the construction execution system 101, the infrastructure 102, and the management terminal 103 are connected to each other via a network 104 such as a WAN (Wide Area Network) and a LAN (Local Area Network). The connection method of the network 104 may be either wired or wireless.

The infrastructure 102 is a foundation for constructing HCI (virtualization infrastructure). Infrastructure 102 includes multiple servers 130. Note that the base 102 may include a switch (not shown) or the like.

The construction control system 100 controls the number of VMs 133 to be installed in parallel during HCI construction. Note that hereinafter, the installation of the VM 133 may be expressed as a task, and the number of parallel installations of the VM 133 may be expressed as the number of parallel executions of tasks.

The construction execution system 101 constructs HCI using the infrastructure 102. Specifically, the construction execution system 101 installs a hypervisor 131 in each server 130, and installs a VM 133 and an OS 134 on SDS (Software Defined Storage) 132 generated from the storage device of each server 130 by the hypervisor 131.

The management terminal 103 is a terminal for operating the construction control system 100 and the construction execution system 101.

The construction control system 100 and the construction execution system 101 are comprised of, for example, a computer 200 as shown in FIG. The computer 200 has a processor 201, a main storage device 202, a secondary storage device 203, and a network interface 204. Each hardware element is connected to each other via a bus. Note that the computer 200 may have an input device such as a keyboard, a mouse, and a touch panel, and may also have an output device such as a display and a printer.

Processor 201 executes a program stored in main storage device 202 . By executing processing according to a program, the processor 201 operates as a functional unit (module) that implements a specific function. In the following description, when a process is described using a functional unit as a subject, it is indicated that the processor 201 executes a program that implements the functional unit.

The main storage device 202 is a storage device such as a DRAM (Dynamic Random Access Memory), and stores programs executed by the processor 201 and data used by the programs. The main storage device 202 is also used as a work area.

The secondary storage device 203 is a storage device such as an HDD (Hard Disk Drive) or an SSD (Solid State Drive), and permanently stores data. Note that the programs and data stored in the main storage device 202 may be stored in the secondary storage device 203. In this case, the processor 201 reads the program and data from the secondary storage device 203 and loads them into the main storage device 202.

The construction execution system 101 includes a construction section 120 and a progress monitoring section 121. The construction unit 120 executes HCI construction processing. The progress monitoring unit 121 monitors the progress of HCI construction. For example, the progress monitoring unit 121 monitors the progress rate of installing the hypervisor 131 and VM 133.

The construction control system 100 includes a performance monitoring section 110, a construction time prediction section 111, and an installation number determination section 112, and also holds threshold information 113 and a performance history database 114.

The performance monitoring unit 110 monitors the performance of the infrastructure 102 during HCI construction. The construction time prediction unit 111 predicts the time required to construct the HCI (construction time). The installation number determining unit 112 determines the number of parallel installations (the number of parallel executions of tasks) of the VM 133.

The threshold information 113 is information for managing thresholds used to determine the occurrence of a performance bottleneck in the infrastructure 102. The performance history database 114 is a database that stores monitoring results by the performance monitoring unit 110.

In Example 1, an HIC is constructed using the following procedure.

(Procedure 1) When the construction execution system 101 receives an HCI construction start instruction from the user, it starts HCI construction processing. The construction start instruction includes the requested time, the total number of VMs 133 to be installed, and the like. The construction execution system 101 installs a hypervisor 131 on the platform 102 and instructs the hypervisor 131 to generate an SDS 132. The construction execution system 101 transmits a process start instruction to the construction control system 100.

(Procedure 2) The construction control system 100 instructs the construction execution system 101 to install a predetermined number of VMs 133, monitors the performance bottleneck of the platform 102, and determines the number of parallel installations based on the monitoring results. The construction control system 100 notifies the construction execution system 101 of the number of parallel installations.

(Procedure 3) The construction execution system 101 repeatedly executes a cycle process of executing tasks as many times as the number of parallel installations until installation of all VMs 133 is completed. For example, if it is necessary to install 20 VMs 133 in total and the number of parallel installations is 5, after the number of parallel installations is determined, a cycle process including 5 tasks for installing VMs 133 is executed three times. . Note that if the number of parallel installations is the same as the total number of VMs 133 to be installed, cycle processing is not executed.

Regarding each module included in each of the construction control system 100 and the construction execution system 101, a plurality of modules may be combined into one module, or one module may be divided into a plurality of modules for each function.

FIG. 3 is a diagram showing an example of the data structure of the threshold information 113 according to the first embodiment.

The threshold information 113 stores entries including performance attributes 301 and thresholds 302. One entry exists for one performance attribute.

The performance attribute 301 is a field that stores items (performance attributes) monitored by the performance monitoring unit 110. The threshold value 302 is a field that stores the threshold value of the item corresponding to the performance attribute 301. In the first embodiment, the construction control system 100 determines that a bottleneck has occurred when the value of the item is larger than the threshold value.

4A, FIG. 4B, FIG. 4C, and FIG. 4D are diagrams showing an example of the data structure of the performance history database 114 of the first embodiment.

The performance history database 114 stores performance information 500 that stores entries including a VM ID 501 and a measured value 502. One piece of performance information 500 exists for one measurement history. Further, one entry exists for one VM 133. Performance information 500 is associated with a timestamp.

The VM ID 501 is a field that stores identification information of the VM 133. Measured value 502 is a field group that stores values of performance attributes.

5A and 5B are flowcharts illustrating an example of a process executed by the construction control system 100 of the first embodiment.

The construction control system 100 sets an initial value "1" to a variable p representing the number of parallel installations (step S101). The construction control system 100 transmits a task execution request to the construction execution system 101 (step S102). When the construction execution system 101 receives a task execution request, it starts installing one VM 133.

After transmitting the task execution request, the construction control system 100 periodically acquires the performance value of the computer resources of the VM 1300. The period is, for example, 5 minutes. The construction control system 100 stores performance information 500 including the acquired performance values in the performance history database 114. When there is only one VM 133 being installed, performance information 500 as shown in FIG. 4A is stored in the performance history database 114.

The construction control system 100 obtains the progress rate of the VM 133 being installed via the construction execution system 101 (step S103). Note that it is assumed that the progress rate of the VM 133 and the elapsed time of the task are acquired.

The construction control system 100 calculates the installation time t of the VM 133 that is currently being installed (step S104). For example, the construction control system 100 calculates the progress rate per unit time based on the elapsed time and progress rate of the task, and calculates the time until the progress rate reaches 100% based on the progress rate per unit time. It is calculated as the introduction time t. Note that the introduction time t is a predicted value.

The construction control system 100 calculates the construction time T (step S105). Specifically, the following processing is executed. Note that the construction time T is a predicted value.

(S105-1) The construction control system 100 adds a delay time according to the installation start order to the installation time t for each VM 133 currently being installed. For example, the delay time of VM133 whose installation was started first is "0 minutes", the delay time of VM133 whose installation was started second and third is "1 minute", and the delay time of VM133 whose installation started from fourth onward is "1 minute". The delay time will be "5 minutes".

(S105-2) The construction control system 100 sets the longest time as the construction time T.

The above is the explanation of the process of step S105.

The construction control system 100 determines whether the construction time T is shorter than the required time (step S106).

If the construction time T is smaller than the required time, the construction control system 100 records the current number of parallel installations and the construction time as provisional values (step S107).

The construction control system 100 determines whether the current number of parallel installations matches the total number of VMs 133 to be installed on the platform 102 (step S108).

If the current number of parallel installations matches the total number of VMs 133 to be installed on the platform 102, the construction control system 100 notifies the construction execution system 101 of the current number of parallel installations (step S116), and ends the process.

If the current number of parallel installations does not match the total number of VMs 133 to be installed on the platform 102, the construction control system 100 sets the value obtained by adding 1 to the variable p to the variable p (step S109), and then returns to step S102. return. As a result, installation of a new VM 133 is started. When two VMs 133 are installed, performance information 500 as shown in FIG. 4B is acquired.

In step S106, if the construction time T is equal to or longer than the required time, the construction control system 100 determines whether a bottleneck has occurred based on the latest performance information 500 and threshold information 113 (step S110). For example, when performance information 500 as shown in FIG. 4C is acquired, it is determined that a bottleneck has occurred.

If no bottleneck has occurred, the construction control system 100 notifies the user of an alert (step S117), and ends the process. In this case, HCI construction stops.

If a bottleneck has occurred, the construction control system 100 sets the value obtained by subtracting 1 from the value of the variable p to the variable p (step S111).

The construction control system 100 calculates the time required to install all the VMs 133 that have not yet been installed (installation time t') (step S112). Specifically, the following processing is executed.

(S112-1) The construction control system 100 determines whether the total number of uninstalled VMs 133 is smaller than the number of parallel installations recorded as a provisional value.

(S112-2) If the total number of uninstalled VMs 133 is smaller than the number of parallel installations (provisional value), the construction control system 100 calculates the construction time recorded as the provisional value as the installation time t'.

(S112-3) If the total number of VMs 133 that have not been installed is equal to or greater than the number of parallel installations (provisional value), the construction control system 100 calculates the installation time t' using equation (1). The above is the explanation of the process of step S112.

The construction control system 100 determines whether the sum of the introduction time t and the introduction time t' is smaller than the required time (step S113).

If the total of the introduction time t and the introduction time t' is equal to or greater than the required time, the construction control system 100 notifies the user of an alert (step S117) and ends the process. In this case, HCI construction stops.

If the sum of the introduction time t and the introduction time t' is smaller than the required time, the construction control system 100 transmits a task stop request to the construction execution system 101 (step S114). When the construction execution system 101 receives a task stop request, it stops the installation of the VM 133 that has the latest start order. This is expected to eliminate bottlenecks.

The construction control system 100 determines whether the bottleneck has been resolved based on the latest performance information 500 and threshold information 113 (step S115). For example, when performance information 500 as shown in FIG. 4D is acquired, it is determined that the bottleneck has been resolved.

If the bottleneck has not been resolved, the construction control system 100 notifies the user of an alert (step S117) and ends the process. In this case, HCI construction stops.

If the bottleneck has been resolved, the construction control system 100 notifies the construction execution system 101 of the current number of parallel installations (step S116), and ends the process.

After receiving the notification of the number of parallel installations, the construction execution system 101 repeatedly executes a cycle process of installing VMs 133 by the number of parallel installations at a time until installation of all VMs 133 is completed. This allows the HCI construction time to be shortened without the user having to perform explicit operations or judgments.

By increasing the number of parallel installations of VMs 133 one by one, the construction control system 100 can efficiently search for a boundary value at which the construction time exceeds the required time due to the occurrence of a bottleneck. By setting a number one smaller than the boundary value as the number of parallel introductions, bottlenecks can be avoided and the HCI construction time can be reduced to the maximum.

As described above, according to the first embodiment, it is possible to automatically determine the number of parallel installations of VMs 133 that can suppress the occurrence of bottlenecks and shorten the construction time.

Although the embodiment has been described using HCI as an example of a virtualization infrastructure, the present invention can be applied to the construction of various virtualization infrastructures.

Note that the present invention is not limited to the above-described embodiments, and includes various modifications. Further, for example, the configurations of the embodiments described above are explained in detail in order to explain the present invention in an easy-to-understand manner, and the present invention is not necessarily limited to having all the configurations described. Further, a part of the configuration of each embodiment can be added to, deleted from, or replaced with other configurations.

Further, each of the above-mentioned configurations, functions, processing units, processing means, etc. may be partially or entirely realized in hardware by designing, for example, an integrated circuit. Further, the present invention can also be realized by software program codes that realize the functions of the embodiments. In this case, a storage medium on which a program code is recorded is provided to a computer, and a processor included in the computer reads the program code stored on the storage medium. In this case, the program code itself read from the storage medium realizes the functions of the embodiments described above, and the program code itself and the storage medium storing it constitute the present invention. Examples of storage media for supplying such program codes include flexible disks, CD-ROMs, DVD-ROMs, hard disks, SSDs (Solid State Drives), optical disks, magneto-optical disks, CD-Rs, magnetic tapes, A non-volatile memory card, ROM, etc. are used.

Further, the program code for realizing the functions described in this embodiment can be implemented in a wide range of program or script languages such as assembler, C/C++, Perl, Shell, PHP, Python, and Java (registered trademark).

Furthermore, by distributing the software program code that realizes the functions of the embodiment via a network, it can be stored in a storage means such as a computer's hard disk or memory, or a storage medium such as a CD-RW or CD-R. Alternatively, a processor included in the computer may read and execute the program code stored in the storage means or the storage medium.

In the above-described embodiments, the control lines and information lines are those considered necessary for explanation, and not all control lines and information lines are necessarily shown in the product. All configurations may be interconnected.

100 Construction control system 101 Construction execution system 102 Platform 103 Management terminal 104 Network 110 Performance monitoring section 111 Construction time prediction section 112 Installation number determination section 113 Threshold information 114 Performance history database 120 Construction section 121 Progress monitoring section 130 Server 131 Hypervisor 132 SDS
133 VMs
134 OS
200 Computer 201 Processor 202 Main storage device 203 Secondary storage device 204 Network interface 500 Performance information

Claims (8)

A computer system comprising at least one computer,
Connects to the construction execution system that executes the construction process of the virtualization infrastructure,
The virtualization infrastructure construction process includes a task of introducing a virtual machine,
The computer system is
When a predetermined number of the tasks are being executed by the construction execution system, obtaining a progress rate of the virtual machine installed by the task and a performance value of computer resources of the virtual machine;
Based on the progress rate and the performance value of the computer resource, calculate the number of parallel installations of the virtual machines that can construct the virtualization infrastructure without causing a bottleneck and within a specified request time. A computer system featuring: The computer system according to claim 1,
Based on the progress rate of each of the plurality of virtual machines currently installed, calculate the predicted construction time to complete the installation of all the virtual machines,
If the predicted construction time is less than the specified required time, instructing the construction execution system to newly execute the task;
If the predicted construction time is greater than or equal to the required time, determine whether a bottleneck has occurred based on the performance value of the computer resource of each of the currently installed virtual machines;
A computer system characterized in that, when a bottleneck occurs, a value obtained by subtracting 1 from the current number of executions of the tasks is calculated as the number of parallel introductions. The computer system according to claim 2,
A computer system characterized in that when a bottleneck occurs, the construction execution system is instructed to stop one of the tasks. The computer system according to claim 2,
A computer system characterized in that the construction execution system is notified of the number of parallel introductions in order to cause the construction execution system to repeatedly execute a cycle process of executing the tasks by the number of parallel introductions. A method for controlling the construction of a virtualization infrastructure executed by a computer system including at least one computer, the method comprising:
The computer system is connected to a construction execution system that executes construction processing of a virtualization infrastructure,
The virtualization infrastructure construction process includes a task of introducing a virtual machine,
The virtualization infrastructure construction control method includes:
When the at least one computer has a predetermined number of the tasks executed by the construction execution system, the progress rate of the virtual computer installed by the task and the performance value of computer resources of the virtual computer. a first step of obtaining
The at least one computer is a virtual computer that can build the virtualization infrastructure without bottlenecks and within a specified request time based on the progress rate and the performance value of the computer resources. A method for controlling construction of a virtualization infrastructure, comprising: a second step of calculating the number of parallel installations. 6. The virtualization infrastructure construction control method according to claim 5,
The second step is
a third step in which the at least one computer calculates a predicted construction time for completing installation of all the virtual computers based on the progress rate of each of the plurality of virtual computers currently installed;
a fourth step in which the at least one computer instructs the construction execution system to newly execute the task if the predicted construction time is less than the specified required time;
If the predicted construction time is greater than or equal to the required time, the at least one computer determines whether a bottleneck is occurring based on the performance value of the computer resource of each of the currently installed virtual computers. a fifth step of determining whether
If a bottleneck has occurred, a sixth step in which the at least one computer calculates a value obtained by subtracting 1 from the number of the plurality of virtual computers currently installed as the number of parallel installations. A method for controlling the construction of a virtualization infrastructure, comprising: 7. The virtualization infrastructure construction control method according to claim 6,
The method for controlling construction of a virtualization infrastructure, wherein the sixth step includes a step in which the at least one computer instructs the construction execution system to stop one of the tasks. 7. The virtualization infrastructure construction control method according to claim 6,
In the sixth step, the at least one computer notifies the construction execution system of the number of parallel introductions in order to cause the construction execution system to repeatedly execute a cycle process of executing the task by the number of parallel introductions. A method for controlling the construction of a virtualization infrastructure, the method comprising steps.

Images