WO2009081737A1 - 縮退構成設計システムおよび方法 - Google Patents
縮退構成設計システムおよび方法 Download PDFInfo
- Publication number
- WO2009081737A1 WO2009081737A1 PCT/JP2008/072437 JP2008072437W WO2009081737A1 WO 2009081737 A1 WO2009081737 A1 WO 2009081737A1 JP 2008072437 W JP2008072437 W JP 2008072437W WO 2009081737 A1 WO2009081737 A1 WO 2009081737A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- server
- configuration
- virtual
- virtual server
- degenerate
- Prior art date
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/07—Responding to the occurrence of a fault, e.g. fault tolerance
- G06F11/16—Error detection or correction of the data by redundancy in hardware
- G06F11/20—Error detection or correction of the data by redundancy in hardware using active fault-masking, e.g. by switching out faulty elements or by switching in spare elements
- G06F11/202—Error detection or correction of the data by redundancy in hardware using active fault-masking, e.g. by switching out faulty elements or by switching in spare elements where processing functionality is redundant
- G06F11/2023—Failover techniques
- G06F11/2028—Failover techniques eliminating a faulty processor or activating a spare
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/07—Responding to the occurrence of a fault, e.g. fault tolerance
- G06F11/14—Error detection or correction of the data by redundancy in operation
- G06F11/1479—Generic software techniques for error detection or fault masking
- G06F11/1482—Generic software techniques for error detection or fault masking by means of middleware or OS functionality
- G06F11/1484—Generic software techniques for error detection or fault masking by means of middleware or OS functionality involving virtual machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/07—Responding to the occurrence of a fault, e.g. fault tolerance
- G06F11/16—Error detection or correction of the data by redundancy in hardware
- G06F11/20—Error detection or correction of the data by redundancy in hardware using active fault-masking, e.g. by switching out faulty elements or by switching in spare elements
- G06F11/202—Error detection or correction of the data by redundancy in hardware using active fault-masking, e.g. by switching out faulty elements or by switching in spare elements where processing functionality is redundant
- G06F11/2035—Error detection or correction of the data by redundancy in hardware using active fault-masking, e.g. by switching out faulty elements or by switching in spare elements where processing functionality is redundant without idle spare hardware
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2201/00—Indexing scheme relating to error detection, to error correction, and to monitoring
- G06F2201/815—Virtual
Definitions
- the present invention relates to a degenerate configuration design system and method for degenerating a redundant computer system constructed using virtual machine technology when a failure occurs.
- Patent Document 1 Japanese Patent Laid-Open No. 2002-55840 describes a duplex, N + M configuration, and N + 1 configuration.
- Duplication is a technique for preparing redundant servers (physical servers) for all servers.
- Non-Patent Document 1 B. Dragovic, K. Fraser, S. Hand, T. Harris, A. Ho, I. Pratt, A. Warfield, P. Barham and R. Neugebauer, Xen and the Art of Virtualization, 19th In ACM Symposium on Operating Systems Principles (SOSP19), 2003.
- a technology that uses computer resources (CPU, memory devices, etc.) provided in a physical server as a plurality of virtual servers realized by a required processing program is disclosed. Yes.
- This non-patent document 1 proposes to dynamically change the amount of computer resources allocated to each virtual server according to the service to be provided. If such virtual machine technology is used, a redundant server is provided for each subsystem (application program (hereinafter simply referred to as application)) that provides services by simply adding a virtual server without introducing a new physical server. The computer system can be made redundant at a lower cost.
- application application program
- the total amount of computer resources that can be used on a physical server is limited. Therefore, in the redundancy method using the virtual machine technology described above, if the amount of computer resources allocated to the virtual server that has been waiting as a redundant system is increased, the computer resources are reduced and the amount of computer resources necessary for providing the service is reduced. There may be virtual servers that do not meet.
- the minimum number of virtual servers required for each subsystem (application) is determined according to the availability requirements required for each subsystem (application). Care must be taken not to create subsystems (applications) that violate the availability requirements as a result of the transition to.
- Non-Patent Document 1 since the redundancy method described in Non-Patent Document 1 does not consider the influence on other virtual servers due to the change in the amount of computer resources allocated to an arbitrary virtual server, redundancy using virtual machine technology It cannot be applied as it is to the conversion method. That is, there is a need for a migration method to a degenerate configuration that satisfies the availability requirements required for each subsystem (application) operating in the computer system.
- the redundancy technique of the background art does not include a technique for changing the allocation amount of computer resources to a virtual server and shifting to a reduced configuration, a reduced configuration corresponding to a physical server in which a failure has occurred cannot be determined. .
- the present invention provides a degenerate configuration design system and method capable of shifting to a degenerate configuration that satisfies the availability requirement required for each subsystem (application) in a computer system made redundant using virtual machine technology. With the goal.
- the degenerate configuration design system of the present invention includes an input means for inputting information of a physical server in which a failure has occurred, For each subsystem executed in the computer system, the number of processing programs that are insufficient to satisfy the required availability requirements is calculated, and the degeneration that satisfies the availability requirements by changing the amount of computer resources allocated to the processing programs.
- Degenerate configuration determining means for determining the configuration Have
- the degenerate configuration design method of the present invention when information of a physical server in which a failure has occurred is input, for each subsystem executed in the computer system, a processing program that is insufficient to meet the availability requirement requested in advance. Calculate the number, In this method, a degenerate configuration that satisfies the availability requirement is determined by changing the amount of computer resources allocated to the processing program.
- FIG. 1 is a block diagram showing a configuration of a degenerate configuration design system according to an embodiment of the present invention.
- FIG. 2 is a block diagram illustrating another configuration example of the degenerate configuration design system.
- FIG. 3 is a block diagram showing a configuration example of the degenerate configuration determining unit shown in FIGS. 1 and 2.
- 4 is a block diagram showing an example of a configuration for realizing the degenerate configuration design system shown in FIG. 1 and the degenerate configuration management server shown in FIG.
- FIG. 5 is a flowchart showing a processing procedure of the redundant configuration design means shown in FIG.
- FIG. 6 is a flowchart showing a processing procedure when a redundant configuration is designed by the virtual server management means and virtual server control means shown in FIG.
- FIG. 1 is a block diagram showing a configuration of a degenerate configuration design system according to an embodiment of the present invention.
- FIG. 2 is a block diagram illustrating another configuration example of the degenerate configuration design system
- FIG. 7 is a flowchart showing a processing procedure of the degenerate configuration determining means shown in FIGS.
- FIG. 8 is a flowchart showing a processing procedure at the time of degenerate configuration design by the virtual server management means and virtual server control means shown in FIG.
- FIG. 9 is a table showing an example of availability requirements used by the redundant configuration design means shown in FIG.
- FIG. 10 is a table showing an example of virtual server arrangement information used by the redundant configuration design means shown in FIG.
- FIG. 11 is a table showing an example of insufficient server number information used by the degenerate configuration determining means shown in FIGS. 1 and 2.
- FIG. 12 is a table showing an example of the degenerate configuration information output from the degenerate configuration determining unit shown in FIGS. 1 and 2.
- FIG. 13 is a block diagram showing the configuration of an embodiment of the degenerate configuration design system.
- FIG. 14 is a table showing an example of system configuration information used in the degenerate configuration design system shown in FIG.
- FIG. 15 is a table showing an example of availability requirements input to the degenerate configuration design system shown in FIG.
- FIG. 16 is a table showing an example of virtual server arrangement information output from the redundant configuration design means shown in FIG.
- FIG. 17 is a table showing an example of failure information input to the degenerate configuration design system shown in FIG.
- FIG. 18 is a table showing an example of the shortage server number information calculated when the failure information shown in FIG. 17 is input.
- FIG. 19 is a flowchart showing a degenerate configuration design procedure by the degenerate configuration determining means shown in FIG.
- FIG. 20 is a table showing an example of the shortage server number information obtained by recalculation of the shortage server number.
- FIG. 21 is a table showing an example of the shortage server number information obtained by recalculation of the shortage server number.
- FIG. 22 is a table showing an example of the degenerate configuration information output from the degenerate configuration determining unit shown in FIG.
- FIG. 1 is a block diagram showing a configuration of a degenerate configuration design system according to an embodiment of the present invention.
- FIG. 2 is a block diagram illustrating another configuration example of the degenerate configuration design system
- FIG. 3 is a block diagram illustrating a configuration example of the degenerate configuration determination unit illustrated in FIGS. 1 and 2.
- the degenerate configuration design system of one embodiment of the present invention has an input unit 11 and a degenerate configuration determination unit 13.
- the degenerate configuration design system shown in FIG. 1 is used to manage a redundant configuration of a computer system including a plurality of physical servers 2 and a virtual server 3 constructed on the physical server 2 as shown in FIG.
- the input unit 11 and the degenerate configuration determination unit 13 illustrated in FIG. 1 are realized by, for example, the degenerate configuration management server 1 illustrated in FIG.
- the degenerate configuration management server 1 and a plurality of physical servers 2 that are managed by the degenerate configuration design system are connected via a network 22, for example.
- the physical server 2 includes virtual server control means 21 and controls zero or more virtual servers 3 built on the own physical server 2 by the virtual server control means 21.
- the degenerate configuration management server 1 shown in FIG. 2 includes an input unit 11, a redundant configuration design unit 12, a degenerate configuration determination unit 13, a virtual server management unit 14, a system configuration information storage unit 16, and a deficient server number information storage unit 18. Yes.
- FIG. 2 shows a configuration example in which the virtual server control means 21 is provided in each physical server 2, the virtual server control means 21 may be provided in the degenerate configuration management server 1.
- the input means 11 is used, for example, for inputting an availability requirement required by an administrator who manages a computer system.
- the input unit 11 is used by a monitoring system (not shown) or a computer system administrator for monitoring the presence or absence of a failure in the physical server 2 to input information (failure information) of the physical server 2 in which the failure has occurred.
- the availability requirement is provided by, for example, the maximum possible simultaneous failure number indicating the number of virtual servers 3 that can continuously operate the computer system even when failures occur simultaneously in a plurality of physical servers 2, or each subsystem (application).
- Information such as a minimum operation level indicating the minimum number of virtual servers 3 required for the service is included.
- the redundant configuration design means 12 refers to the availability requirements input by the administrator and the system configuration information stored in the system configuration information storage unit 16 to make the computer system redundant and to meet the above availability requirements.
- the placement of the virtual server with respect to the server is determined, and information indicating the result (virtual server placement information) is output.
- the system configuration information is information indicating the current configuration of the computer system to be managed.
- the virtual server management unit 14 manages the virtual server 3 constructed on each physical server 2 based on the virtual server arrangement information output from the redundant configuration design unit 12.
- the virtual server control means 21 receives various control requests from the virtual server management means 14 and controls the virtual server 3 in the own physical server 2 in accordance with the control requests.
- the control request for the virtual server 3 includes, for example, generation of the virtual server 3, operation stop of the virtual server 3, switching between the active virtual server and the redundant virtual server.
- the degenerate configuration determining unit 13 includes a shortage server number calculating unit 131, a resource allocation change determining unit 132, and a shortage server number correcting unit 133.
- the deficient server number calculation means 131 refers to, for example, the failure information input by the administrator, the availability requirements, and the system configuration information stored in the system configuration information storage unit 16, and the subsystems (applications) that are insufficient to satisfy the availability requirements )
- the number of virtual servers (hereinafter referred to as insufficient servers) is calculated.
- the resource allocation change determining unit 132 changes the computer resource allocation amount for each virtual server 3 so that the insufficient server calculated by the insufficient server number calculating unit 131 becomes “0”, and information indicating the result (degenerate configuration) Information).
- the deficient server number correction means 133 monitors fluctuations in the number of deficient servers for each subsystem (application) due to the change in the computer resource allocation amount, and rewrites the information stored in the deficient server number information storage unit 18.
- the virtual server management unit 14 changes the arrangement of the virtual server 3 constructed on the physical server 2 using the virtual server control unit 21 based on the degeneration configuration information output from the degeneration configuration determination unit 13.
- the reduced configuration design system shown in FIG. 1 and the reduced configuration management server apparatus 1 shown in FIG. 2 can be realized by a computer shown in FIG. 4, for example.
- the computer shown in FIG. 4 monitors a processing device 4 that executes predetermined processing according to a program, an input device 5 for inputting a command, information, and the like to the processing device 4, and a processing result of the processing device 4. And an output device 6 for this purpose.
- the processing device 4 includes a CPU 41, a main storage device 42 that temporarily holds information necessary for the processing of the CPU 41, and processing of the redundant configuration design unit 12, the degenerate configuration determination unit 13, and the virtual server management unit 14. , A data storage device 44 used as the system configuration information storage unit 16 and the insufficient server number information storage unit 18, a main storage device 42, a recording medium 43, and data storage Communication between a memory control interface unit 45 that controls data transfer with the device 44, an I / O interface unit 46 that is an interface device between the input device 5 and the output device 6, and a plurality of physical servers 2 that are management targets A communication control device 47 that is an interface to control, and these are connected via a bus 48. And is a configuration.
- the processing device 4 executes the processes of the redundant configuration design unit 12, the degenerate configuration determination unit 13, and the virtual server management unit 14 according to the program recorded in the recording medium 43.
- the recording medium 43 may be a magnetic disk, a semiconductor memory, an optical disk, or other recording medium.
- the data storage device 44 does not have to be provided in the redundant configuration management server device 1 and may be an independent device.
- the physical server 2 shown in FIG. 2 can also be realized by the computer shown in FIG. 4 except that the operating program is different. Therefore, the description thereof is omitted here.
- FIG. 5 is a flowchart showing a processing procedure of the redundant configuration design means shown in FIG. 2
- FIG. 6 is a flowchart showing a processing procedure at the time of redundant configuration design by the virtual server management means and virtual server control means shown in FIG. is there.
- the redundant configuration design unit 12 refers to the system configuration information storage unit 16 and acquires the current system configuration information. Then, the number of virtual servers 3 satisfying the input availability requirement is calculated, and it is checked whether or not the number of virtual servers 3 required for computer system redundancy is within the number of currently available virtual servers 3. It is determined whether or not a redundant configuration can be designed (step 1001).
- the availability requirement is a requirement indicating the level of reliability required for the managed computer system.
- An example is shown in FIG. FIG. 9 shows an example of the maximum possible simultaneous failure number and the minimum operation level, which are availability requirements.
- the maximum number of possible simultaneous failures is the number of failures of the physical server 2 that can be tolerated in the entire computer system. It is an indicator to show.
- the minimum operation level is a value that defines the minimum requirements necessary for continuously operating the computer system. For example, the minimum number of virtual servers required for each subsystem (application) (hereinafter referred to as the minimum number of servers). Is set. When designing a redundant configuration using virtual machine technology, it is necessary to prepare a redundant virtual server 3 in preparation for the occurrence of a failure so as to satisfy these availability requirements.
- the redundant configuration design means 12 determines the arrangement of the virtual server 3 with respect to the physical server 2 and outputs information indicating the result (virtual server arrangement information) (step 1002). If it is determined that a redundant configuration cannot be designed, for example, the number of physical servers 2 to be added necessary for redundancy is output and the process is terminated.
- the virtual server management unit 15 and the virtual server control unit 21 start processing for building a redundant configuration.
- the construction of the redundant configuration may be started after the administrator confirms the virtual server arrangement information output from the redundant configuration design means 12, or may be started without confirmation by the administrator. In any case, the construction of the redundant configuration is started when the virtual server arrangement information is input to the virtual server management means 15.
- FIG. 10 shows an example in which a virtual server 3 to be operated on each physical server 2 is defined.
- two types of virtual servers 3 of active and redundant systems operate on each physical server 2, and three types of subsystems (applications) are assigned to each virtual server 3.
- the active virtual server 3 and the redundant virtual server 3 that execute the same application are arranged on different physical servers 2.
- an active virtual server that operates with application A and a redundant virtual server that operates with application B are arranged on the first physical server (physical server 1), and the second physical server (physical server 2).
- An active virtual server operating in the application B and a redundant virtual server operating in the application C are arranged.
- an active virtual server operating in the application C and a redundant virtual server operating in the application A are arranged on the third physical server (physical server 3).
- the virtual server management means 15 controls the virtual server control means 21 on each physical server 2 based on the virtual server arrangement information.
- a control request is transmitted (step 2001).
- control request includes generation of the virtual server 3, operation stop, change from the active virtual server to the redundant virtual server, change from the redundant virtual server to the active virtual server, and the like. included.
- the virtual server control unit 21 When the virtual server control unit 21 receives a control request for the virtual server 3 (step 2002), the virtual server control unit 21 executes the requested control (step 2003) and transmits the control result to the virtual server management unit 15 (step 2004).
- the virtual server management means 15 terminates the redundant configuration construction process when it receives control results from all the virtual server control means 21 provided in each physical server 2 (step 2005).
- FIG. 7 is a flowchart showing a processing procedure of the degenerate configuration determining means shown in FIGS. 1 and 2, and FIG. 8 shows a processing procedure at the time of degenerate configuration design by the virtual server management means and virtual server control means shown in FIG. It is a flowchart to show.
- step 3000 when a failure occurs in the physical server, information on the physical server 2 in which the failure has occurred is input to the degenerate configuration determination unit 13 via the input unit 11 (step 3000).
- the degeneration process it is necessary to design a redundant configuration (degenerate configuration) that satisfies the minimum operation level, which is an availability requirement, in the remaining physical servers 2 excluding the physical server 2 in which the failure has occurred.
- the degenerate configuration determining means 13 first compares the number of physical servers 2 in which a failure has occurred with the maximum number of possible simultaneous failures, which is an availability requirement, and determines whether degeneration is possible (step 3001). If the number of failed physical servers 2 exceeds the maximum possible number of simultaneous failures, it is not possible to shift to the degenerated configuration, so a message indicating that degeneration is not possible is output and the process is terminated.
- the degeneration configuration determination unit 13 satisfies the availability requirement by the insufficient server number calculation unit 131.
- the number of virtual servers 3 (hereinafter referred to as the number of insufficient servers) for each subsystem (application) that is insufficient is calculated, and the calculation result (insufficient server number information) is stored in the insufficient server number information storage unit 18 (step 3002).
- the number of insufficient servers is obtained by subtracting the number of active virtual servers remaining after a failure from the minimum number (minimum number of servers) of virtual servers 3 required for each subsystem (application) input as availability requirements. Ask.
- insufficient server number information is shown in FIG.
- the minimum number of servers of application A is “1”
- the number of remaining virtual servers (hereinafter referred to as the number of remaining servers) is “0”. “1”.
- the degenerate configuration determination means 13 designs a degenerate configuration that replenishes this insufficient server.
- the degenerate configuration determining means 13 starts a process for replenishing the insufficient virtual server obtained for each subsystem (application) using the redundant virtual server.
- the degenerate configuration determining unit 13 selects one subsystem (application) in which the virtual server 3 is insufficient by the resource allocation change determining unit 132 (step 3003), and the redundant system allocated to the subsystem (application).
- the virtual server 3 is searched (step 3004).
- the resource allocation change determining unit 132 detects a redundant virtual server allocated to the selected subsystem (application)
- the resource allocation change determining unit 132 changes the allocation amount of the computer resource for the redundant virtual server (step 3005).
- the degenerate configuration determining unit 13 recalculates the number of virtual servers 3 for each subsystem (application) that is insufficient to satisfy the availability requirement by the insufficient server number correcting unit 133 and stores it in the insufficient server number information storage unit 18. Information on the number of insufficient servers to be updated is updated (step 3006).
- the deficient server number correcting means 133 determines whether or not the deficient server number is “0” (step 3007). If the deficient server number is “1” or more, the process returns to step 3003 to return to steps 3003 to 3003. The process of 3007 is repeated.
- the deficient server number correcting unit 133 determines the degenerated configuration by repeating the processing of steps 3003 to 3007 until the deficient server number becomes “0”, and outputs degenerated configuration information indicating the degenerated configuration.
- FIG. 12 shows a virtual server assigned to the application A arranged in the third physical server (physical server 3) when a failure occurs in the first physical server (physical server 1) in the redundant configuration shown in FIG. Shows an example of a degeneration process for switching from the redundant system to the active system and switching the virtual server assigned to the application C from the active system to the redundant system.
- the degenerate configuration information output from the degenerate configuration determining unit 13 is input to the virtual server management unit 15 and the degeneration process is started.
- the degeneration process may be started after obtaining the approval of the administrator, or may be started without obtaining the approval of the administrator.
- the virtual server management unit 15 transmits a control request to the virtual server control unit 21 based on the degenerate configuration information (step 4001).
- the virtual server control means 21 When the virtual server control means 21 receives the control request (step 4002), it executes the requested control (step 4003) and transmits the control result to the virtual server management means 15 (step 4004).
- the virtual server management unit 15 ends the degeneration process when receiving the control results from all the virtual server control units 21 provided in each physical server 2 (step 4005).
- the degenerate configuration design system of this embodiment when a failure occurs, the number of insufficient servers is calculated for each subsystem (application) based on availability requirements, and the allocation amount of computer resources to the remaining virtual servers is changed. Since the degenerated configuration is determined, it is possible to move to a degenerated configuration that satisfies the availability requirements without depending on the physical server in which the failure has occurred.
- the subsystem A degenerate configuration that satisfies the availability requirement required for each (application) can be determined.
- FIG. 13 is a block diagram showing the configuration of an embodiment of the degenerate configuration design system.
- the degenerate configuration design system shown in FIG. 13 includes six physical servers 2 as management targets, and two virtual servers each operate on each physical server 2.
- FIG. 14 is a table showing an example of system configuration information used in the degenerate configuration design system shown in FIG.
- the system configuration information of the present embodiment is information in which active virtual servers 3 operating in three types of subsystems (applications) are respectively assigned to six physical servers 2. Including.
- the active virtual server of application A is assigned to the first physical server (physical server 1) to the third physical server (physical server 3), and the fourth physical server (physical server 4).
- the fifth physical server (physical server 5) are assigned the active virtual server of application B
- the sixth physical server (physical server 6) is assigned the active virtual server of application C.
- the availability requirement shown in FIG. 15 is input to the degenerate configuration design system shown in FIG. As shown in FIG. 15, in the availability requirement of this embodiment, the maximum possible simultaneous failure number is “3”, and the minimum number of servers for each application specified as the minimum operation level is “1”.
- the redundant configuration design means 12 determines the arrangement of the virtual server 3 with respect to the physical server 2 that satisfies the availability requirements shown in FIG. 15, and outputs virtual server arrangement information as shown in FIG. 16, for example.
- a redundant virtual server of application B is allocated to the first physical server (physical server 1) and the second physical server (physical server 2), and the third physical server (physical server 3).
- the redundant virtual server of application C is allocated, and the redundant virtual server of application A is allocated to the sixth physical server (physical server 6).
- the degenerate configuration determination unit 13 shifts to a degenerate configuration that satisfies the availability requirements. It is determined whether or not it is possible (step 3001).
- FIG. 17 shows an example of failure information for specifying a physical server in which a failure has occurred.
- the first physical server physical server 1
- the second physical server physical server 2
- the six physical servers included in the degenerate configuration design system shown in FIG. Assume that a failure has occurred in the third physical server (physical server 3).
- the degenerate configuration determining means 13 determines that degeneration is possible because the number of physical servers in which a failure has occurred is three and is less than or equal to the maximum possible simultaneous failure number that is the availability requirement shown in FIG.
- the degenerate configuration determining means 13 calculates the number of virtual servers 3 that are insufficient to satisfy the availability requirement (number of insufficient servers) for each subsystem (application) by the insufficient server number calculating means 131, and the calculation result Is stored in the shortage server number information storage unit 18 (step 3002).
- FIG. 18 shows an example of the shortage server number information calculated by the shortage server number calculation means 131.
- degenerate configuration determining means 13 selects application A by resource allocation change determining means 132 (step 3003).
- the redundant virtual server 3 assigned to the subsystem (application A) is searched (step 3004).
- the resource allocation change determining unit 132 When the resource allocation change determining unit 132 detects the redundant virtual server allocated to the application A, the resource allocation change determining unit 132 changes the allocation amount of the computer resource for the redundant virtual server (step 3005).
- the degenerate configuration determining unit 13 recalculates the number of insufficient servers for each subsystem (application) by the insufficient server number correcting unit 133, stores the calculation result in the insufficient server number information storage unit 18, and stores the insufficient server number information. Is updated (step 3006).
- the degenerate configuration determining means 13 determines whether or not the number of insufficient servers is “0”. If the number of insufficient servers is not “0”, the processing returns to step 3003 and the processing of steps 3003 to 3007 is performed. repeat. By repeating the processing of steps 3003 to 3007 until the number of insufficient servers becomes “0”, a degenerated configuration after migration is obtained.
- each application is defined as a_i
- application A is a_1
- application B is a_2
- application C is a_3.
- ⁇ (a_i) be the number of insufficient servers generated in each application a_i.
- the degenerate configuration determination means 13 selects the application a_1 (step 5001), and determines whether or not the number of servers deficient in the selected application ⁇ (a_1) is “0” (step 5002).
- the degenerate configuration determining means 13 is assigned a redundant virtual server of application a_1, and the active virtual server is the application virtual server.
- the physical server Sh that is not executing the process is searched (step 5006).
- the degenerate configuration determining means 13 determines whether or not there is a physical server Sh (step 5007). If there is no physical server Sh, the process proceeds to step 5003.
- the degenerate configuration determining means 13 determines a change in the allocation amount of computer resources in the sixth physical server (step 5008).
- the degenerate configuration determining unit 13 changes the allocation amount of the computer resources, so that the remaining server of the application a_3 The number of servers is reduced by “1”, and the number of remaining servers of application a_1 is increased by “1” (step 5009).
- the degenerate configuration determining unit 13 calculates the number of insufficient servers again (step 5010).
- the shortage server number information after recalculation is as shown in FIG. In the example shown in FIG. 20, a shortage server is newly generated in the application C (a_3) by changing the allocation amount of computer resources.
- the insufficient server number information after recalculation is stored in the insufficient server number storage unit 18.
- the degenerate configuration determining means 13 determines whether or not the number of servers deficient in the selected application (here, a_1) ⁇ (a_1) is “0” (step 5011).
- ⁇ (a_1) 0
- the degenerate configuration determination unit 13 returns to the process of step 5001 and executes the same process as described above for the application a_2.
- the degenerate configuration determination means 13 first selects the application a_2 (step 5001), and determines whether or not the number of insufficient servers ⁇ (a_2) of the selected application is “0” (step 5002).
- the degenerate configuration determining unit 13 returns to the process of step 5001 and executes the same process as described above for the application a_3.
- the degenerate configuration determining means 13 first selects the application a_3 (step 5001), and determines whether or not the shortage server number ⁇ (a_2) of the selected application is “0” (step 5002).
- the degenerate configuration determination means 13 A redundant virtual server of the application a_3 is allocated, and the active virtual server searches for a physical server Sh that is not executing the application (step 5006).
- the degenerate configuration determining means 13 determines whether or not there is a physical server Sh (step 5007). If there is no physical server Sh, the process proceeds to step 5003.
- the degenerate configuration determining means 13 determines a change in the allocation amount of computer resources in the fourth physical server (step 5008).
- the degenerate configuration determining means 13 changes the allocation amount of the computer resources, thereby changing the remaining server of the application a_2 The number is reduced by “1”, and the number of remaining servers of the application a — 3 is increased by “1” (step 5009).
- the degenerate configuration determining unit 13 calculates the number of insufficient servers again (step 5010).
- the information on the number of insufficient servers after recalculation is as shown in FIG. In the example shown in FIG. 21, the number of insufficient servers is “0” in all applications by changing the allocation amount of computer resources.
- the insufficient server number information after recalculation is stored in the insufficient server number storage unit 18.
- the degenerate configuration determining means 13 determines whether or not the number of servers deficient in the selected application (here, a_3) ⁇ (a_3) is “0” (step 5011).
- ⁇ (a — 3) 0
- the degenerate configuration determining unit 13 proceeds to the process of Step 5005 and calculates the sum of the number of insufficient servers of all applications. Then, it is determined whether or not the total number of insufficient servers is “0”. If the total number of insufficient servers is “0”, the process ends. If the total number of insufficient servers is not “0”, the process returns to step 5001 and the processes of steps 5001 to 5012 are repeated.
- the allocation amount of computer resources is changed in the fourth physical server and the sixth physical server, and degenerate configuration information as shown in FIG. 22, for example, is obtained.
- the active physical server of application C and the redundant virtual server of application B are allocated to the fourth physical server (physical server 4), and the sixth physical server (physical server 6) is assigned.
- An active virtual server for application A and a redundant virtual server for application C are allocated.
- the redundant configuration of the computer system is changed according to the procedure shown in FIG.
- the computer system resource allocation amount of the virtual servers arranged in the fourth physical server and the sixth physical server is changed to replace the active system and the redundant system. Since the change of the computer resource allocation amount ends immediately, the degeneration process can be executed at high speed.
- the amount of computer resources allocated can be reduced by updating the shortage server number information. Since the virtual server to be changed is repeatedly searched, a degenerate configuration that satisfies the availability requirement can be determined.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Hardware Redundancy (AREA)
Abstract
Description
コンピュータシステムで実行するサブシステム毎に、予め要求された可用性要件を満たすのに不足する処理プログラムの数を計算し、前記処理プログラムに対する計算機資源の割り当て量を変更することで前記可用性要件を満たす縮退構成を決定する縮退構成決定手段と、
を有する。
前記処理プログラムに対する計算機資源の割り当て量を変更することで前記可用性要件を満たす縮退構成を決定する方法である。
(実施例)
次に本発明の実施例について図面を用いて説明する。
図21に示す例では、計算機資源の割り当て量を変更することで全てのアプリケーションで不足サーバ台数が「0」になっている。再計算後の不足サーバ台数情報は不足サーバ台数格納部18に格納される。
Claims (17)
- 障害が発生した物理サーバの情報を入力するための入力手段と、
コンピュータシステムで実行するサブシステム毎に、予め要求された可用性要件を満たすのに不足する処理プログラムの数を計算し、前記処理プログラムに対する計算機資源の割り当て量を変更することで前記可用性要件を満たす縮退構成を決定する縮退構成決定手段と、
を有する縮退構成設計システム。 - 前記処理プログラムは、仮想サーバを実現するためのものである請求項1記載の縮退構成設計システム。
- 前記縮退構成を示す縮退構成情報に基づいて前記物理サーバに配置された前記仮想サーバを管理するための制御要求を出力する仮想サーバ管理手段と、
前記制御要求にしたがって前記物理サーバに配置された前記仮想サーバの構成を制御する仮想サーバ制御手段と、
をさらに有する請求項2記載の縮退構成設計システム。 - 前記コンピュータシステムを冗長化すると共に前記可用性要件を満たすように前記物理サーバに対する前記仮想サーバの配置を決定する冗長構成設計手段をさらに有し、
前記仮想サーバ管理手段は、
前記縮退構成情報および前記冗長構成設計手段で決定した前記仮想サーバの配置を示す冗長構成情報に基づいて前記物理サーバに配置された前記仮想サーバを管理するための制御要求を出力する請求項3記載の縮退構成設計システム。 - 前記縮退構成決定手段は、
前記可用性要件を満たすのに不足する前記サブシステム毎の仮想サーバの数を計算する不足サーバ台数計算手段と、
前記不足する前記サブシステム毎の仮想サーバの数が零となるように前記仮想サーバに対する計算機資源の割り当て量を変更する資源割り当て変更決定手段と、
前記計算機資源の割り当て量の変更によって発生する、前記可用性要件を満たすのに不足する前記サブシステム毎の仮想サーバの数を再度計算する不足サーバ台数補正手段と、
を有する請求項2から4のいずれか1項記載の縮退構成設計システム。 - 障害が発生した物理サーバの情報が入力されると、コンピュータシステムで実行するサブシステム毎に、予め要求された可用性要件を満たすのに不足する処理プログラムの数を計算し、
前記処理プログラムに対する計算機資源の割り当て量を変更することで前記可用性要件を満たす縮退構成を決定する縮退構成設計方法。 - 前記処理プログラムは、仮想サーバを実現するためのものである請求項6記載の縮退構成設計方法。
- 前記縮退構成を示す縮退構成情報に基づいて前記物理サーバに配置された前記仮想サーバを管理するための制御要求を出力し、
前記制御要求にしたがって前記物理サーバに配置された前記仮想サーバの構成を制御する請求項7記載の縮退構成設計方法。 - 前記コンピュータシステムを冗長化すると共に前記可用性要件を満たすように前記物理サーバに対する前記仮想サーバの配置を決定し、
前記縮退構成情報および前記決定した仮想サーバの配置を示す冗長構成情報に基づいて前記物理サーバに配置された前記仮想サーバを管理する請求項8記載の縮退構成設計方法。 - 前記可用性要件を満たすのに不足する前記サブシステム毎の仮想サーバの数を計算し、
前記不足する前記サブシステム毎の仮想サーバの数が零となるように前記仮想サーバに対する計算機資源の割り当て量を変更し、
前記計算機資源の割り当て量の変更によって発生する、前記可用性要件を満たすのに不足する前記サブシステム毎の仮想サーバの数を再度計算する請求項7から9のいずれか1項記載の縮退構成設計方法。 - 障害が発生した物理サーバの情報が入力されると、前記物理サーバを含むコンピュータシステムで実行するサブシステム毎に、予め要求された可用性要件を満たすのに不足する処理プログラムの数を計算し、
前記処理プログラムに対する計算機資源の割り当て量を変更することで前記可用性要件を満たす縮退構成を決定する処理をコンピュータに実行させるためのプログラム。 - 前記処理プログラムは、仮想サーバを実現するためのものである請求項11記載のプログラム。
- 前記縮退構成を示す縮退構成情報に基づいて前記物理サーバに配置された前記仮想サーバを管理するための制御要求を出力し、
前記制御要求にしたがって前記物理サーバに配置された前記仮想サーバの構成を制御する処理をコンピュータに実行させるための請求項12記載のプログラム。 - 前記コンピュータシステムを冗長化すると共に前記可用性要件を満たすように前記物理サーバに対する前記仮想サーバの配置を決定し、
前記縮退構成情報および前記決定した仮想サーバの配置を示す冗長構成情報に基づいて前記物理サーバに配置された前記仮想サーバを管理する処理をコンピュータに実行させるための請求項13記載のプログラム。 - 前記可用性要件を満たすのに不足する前記サブシステム毎の仮想サーバの数を計算し、
前記不足する前記サブシステム毎の仮想サーバの数が零となるように前記仮想サーバに対する計算機資源の割り当て量を変更し、
前記計算機資源の割り当て量の変更によって発生する、前記可用性要件を満たすのに不足する前記サブシステム毎の仮想サーバの数を再度計算する処理をコンピュータに実行させるための請求項12から14のいずれか1項記載のプログラム。 - 仮想マシン技術を利用したコンピュータシステムの冗長構成を縮退するための縮退構成設計サーバに接続された、前記コンピュータシステムを構成する物理サーバであって、
前記縮退構成設計サーバから出力される、仮想サーバを管理するための制御要求にしたがって、前記仮想サーバの構成を制御する仮想サーバ制御手段を備えた物理サーバ。 - コンピュータシステムの可用性要件および障害が発生した物理サーバの情報を入力するための入力手段と、
前記コンピュータシステムを冗長化すると共に前記可用性要件を満たすように前記物理サーバに対する前記仮想サーバの配置を決定する冗長構成設計手段と、
前記コンピュータシステムで実行するサブシステム毎に、前記可用性要件を満たすのに不足する仮想サーバの数を計算し、前記仮想サーバに対する計算機資源の割り当て量を変更することで前記可用性要件を満たす縮退構成を決定する縮退構成決定手段と、
前記縮退構成を示す縮退構成情報に基づいて前記物理サーバに配置された前記仮想サーバを管理するための制御要求を出力する仮想サーバ管理手段と、
を有する縮退構成設計サーバ。
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2009547025A JP5526784B2 (ja) | 2007-12-26 | 2008-12-10 | 縮退構成設計システムおよび方法 |
US12/747,957 US9141490B2 (en) | 2007-12-26 | 2008-12-10 | Graceful degradation designing system and method |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2007-334442 | 2007-12-26 | ||
JP2007334442 | 2007-12-26 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2009081737A1 true WO2009081737A1 (ja) | 2009-07-02 |
Family
ID=40801045
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2008/072437 WO2009081737A1 (ja) | 2007-12-26 | 2008-12-10 | 縮退構成設計システムおよび方法 |
Country Status (3)
Country | Link |
---|---|
US (1) | US9141490B2 (ja) |
JP (1) | JP5526784B2 (ja) |
WO (1) | WO2009081737A1 (ja) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2012190175A (ja) * | 2011-03-09 | 2012-10-04 | Nec Corp | フォールトトレラントシステム、サーバ、フォールトトレラント化方法およびプログラム |
JP2013206379A (ja) * | 2012-03-29 | 2013-10-07 | Nec Corp | クラスタ監視装置、クラスタ監視方法、及びプログラム |
JP2016071771A (ja) * | 2014-10-01 | 2016-05-09 | 株式会社デンソー | 制御装置及び監視装置 |
Families Citing this family (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20120158923A1 (en) * | 2009-05-29 | 2012-06-21 | Ansari Mohamed | System and method for allocating resources of a server to a virtual machine |
US8429449B2 (en) * | 2010-03-01 | 2013-04-23 | International Business Machines Corporation | Optimized placement of virtual machines in a network environment |
US8631406B2 (en) * | 2010-06-30 | 2014-01-14 | Sap Ag | Distributed cloud computing architecture |
JP2012128697A (ja) * | 2010-12-16 | 2012-07-05 | Hitachi Ltd | 情報処理装置 |
JP6179119B2 (ja) * | 2013-02-19 | 2017-08-16 | 日本電気株式会社 | 管理装置、管理方法、及び管理プログラム |
US10552272B2 (en) * | 2016-12-14 | 2020-02-04 | Nutanix, Inc. | Maintaining high availability during N-node failover |
US10944581B2 (en) * | 2018-11-08 | 2021-03-09 | International Business Machines Corporation | Increasing processing capacity of processor cores during initial program load processing |
CN111245873B (zh) * | 2018-11-28 | 2023-09-05 | 北京京东尚科信息技术有限公司 | 服务降级方法、装置、设备及存储介质 |
US11327767B2 (en) | 2019-04-05 | 2022-05-10 | International Business Machines Corporation | Increasing resources for partition to compensate for input/output (I/O) recovery event |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2003330740A (ja) * | 2002-05-15 | 2003-11-21 | Hitachi Ltd | 多重化計算機システム、論理計算機の割当方法および論理計算機の割当プログラム |
JP2004318578A (ja) * | 2003-04-17 | 2004-11-11 | Hitachi Ltd | 情報処理システム |
Family Cites Families (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH0827735B2 (ja) * | 1987-03-26 | 1996-03-21 | 株式会社日立製作所 | 分散システムにおけるバツクアツプ方式 |
JPH06110715A (ja) | 1992-09-25 | 1994-04-22 | Hitachi Ltd | 仮想計算機システムにおける計算機資源の動的割付け方法 |
JP2807862B2 (ja) | 1994-07-15 | 1998-10-08 | 博 吉田 | 衝撃吸収用クリップ |
JP3196004B2 (ja) * | 1995-03-23 | 2001-08-06 | 株式会社日立製作所 | 障害回復処理方法 |
JP3621634B2 (ja) | 2000-08-08 | 2005-02-16 | 日本電信電話株式会社 | 冗長構成切替システム |
JP4072392B2 (ja) | 2002-07-29 | 2008-04-09 | Necエンジニアリング株式会社 | マルチプロセッサの切り替え方式 |
JP2004110509A (ja) | 2002-09-19 | 2004-04-08 | Nec Corp | 冗長構成システムにおける系切替制御処理方式 |
US8776050B2 (en) * | 2003-08-20 | 2014-07-08 | Oracle International Corporation | Distributed virtual machine monitor for managing multiple virtual resources across multiple physical nodes |
JP3861087B2 (ja) | 2003-10-08 | 2006-12-20 | 株式会社エヌ・ティ・ティ・データ | 仮想マシン管理装置及びプログラム |
JP4315016B2 (ja) | 2004-02-24 | 2009-08-19 | 株式会社日立製作所 | コンピュータシステムの系切替方法 |
US8914606B2 (en) | 2004-07-08 | 2014-12-16 | Hewlett-Packard Development Company, L.P. | System and method for soft partitioning a computer system |
JP2006072591A (ja) | 2004-09-01 | 2006-03-16 | Hitachi Ltd | 仮想計算機制御方法 |
JP4462024B2 (ja) * | 2004-12-09 | 2010-05-12 | 株式会社日立製作所 | ディスク引き継ぎによるフェイルオーバ方法 |
JP4671399B2 (ja) | 2004-12-09 | 2011-04-13 | 株式会社日立製作所 | データ処理システム |
JP4544146B2 (ja) | 2005-11-29 | 2010-09-15 | 株式会社日立製作所 | 障害回復方法 |
US8156492B2 (en) * | 2007-09-07 | 2012-04-10 | Oracle International Corporation | System and method to improve memory usage in virtual machines running as hypervisor guests |
-
2008
- 2008-12-10 JP JP2009547025A patent/JP5526784B2/ja active Active
- 2008-12-10 WO PCT/JP2008/072437 patent/WO2009081737A1/ja active Application Filing
- 2008-12-10 US US12/747,957 patent/US9141490B2/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2003330740A (ja) * | 2002-05-15 | 2003-11-21 | Hitachi Ltd | 多重化計算機システム、論理計算機の割当方法および論理計算機の割当プログラム |
JP2004318578A (ja) * | 2003-04-17 | 2004-11-11 | Hitachi Ltd | 情報処理システム |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2012190175A (ja) * | 2011-03-09 | 2012-10-04 | Nec Corp | フォールトトレラントシステム、サーバ、フォールトトレラント化方法およびプログラム |
JP2013206379A (ja) * | 2012-03-29 | 2013-10-07 | Nec Corp | クラスタ監視装置、クラスタ監視方法、及びプログラム |
JP2016071771A (ja) * | 2014-10-01 | 2016-05-09 | 株式会社デンソー | 制御装置及び監視装置 |
Also Published As
Publication number | Publication date |
---|---|
US20100293256A1 (en) | 2010-11-18 |
JP5526784B2 (ja) | 2014-06-18 |
JPWO2009081737A1 (ja) | 2011-05-06 |
US9141490B2 (en) | 2015-09-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP5526784B2 (ja) | 縮退構成設計システムおよび方法 | |
JP5353712B2 (ja) | 冗長構成管理システムおよび方法 | |
CN112015583B (zh) | 一种数据存储的方法、装置和系统 | |
JP4620455B2 (ja) | サーバ連結環境のための業務継続ポリシー | |
KR102199278B1 (ko) | 가속 자원 처리 방법 및 장치, 및 네트워크 기능 가상화 시스템 | |
JP5851503B2 (ja) | 高可用性仮想機械環境におけるアプリケーションの高可用性の提供 | |
EP3210134B1 (en) | Composite partition functions | |
US20100299447A1 (en) | Data Replication | |
US10613898B2 (en) | Apparatuses and methods for flexible scheduling in a database system | |
US20180285169A1 (en) | Information processing system and computer-implemented method | |
US9509637B1 (en) | Methods and apparatus for virtualizing switch control plane engine | |
JP5822125B2 (ja) | サービス連携装置、サービス連携方法およびサービス連携プログラム | |
CN115225642B (zh) | 超融合系统的弹性负载均衡方法及系统 | |
CN110609699A (zh) | 维护存储系统的组件的方法、电子设备和计算机程序产品 | |
US20210409343A1 (en) | Network controller | |
JP7533576B2 (ja) | コンテナリソース設計システムおよびコンテナリソース設計方法 | |
JP5321195B2 (ja) | 監視制御システム、監視制御方法、監視制御サーバ及び監視制御プログラム | |
JP2014182737A (ja) | 情報処理装置、情報処理方法、ストレージシステム及びコンピュータプログラム | |
JP2009003537A (ja) | 計算機 | |
JP6098167B2 (ja) | 仮想マシン管理プログラム及びその方法 | |
US20240004720A1 (en) | Computational resource cluster management device, computational resource cluster management method, and computational resource cluster management program | |
WO2017203556A1 (ja) | 管理計算機及びシステムのパラメータの最適値算出方法 | |
JP4595892B2 (ja) | データベース管理システム構築方法、装置、プログラム及び記録媒体 | |
RU2797756C1 (ru) | Система управления, сбора, обработки, хранения и предоставления доступа к данным устройств промышленной автоматизации и интернета вещей | |
JP2016130962A (ja) | データ退避制御方法、データ退避制御プログラム、及びデータ退避制御装置 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 08864053 Country of ref document: EP Kind code of ref document: A1 |
|
WWE | Wipo information: entry into national phase |
Ref document number: 12747957 Country of ref document: US |
|
ENP | Entry into the national phase |
Ref document number: 2009547025 Country of ref document: JP Kind code of ref document: A |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 08864053 Country of ref document: EP Kind code of ref document: A1 |