JPS62172437A - High reliability system - Google Patents

High reliability system

Info

Publication number
JPS62172437A
JPS62172437A JP61014263A JP1426386A JPS62172437A JP S62172437 A JPS62172437 A JP S62172437A JP 61014263 A JP61014263 A JP 61014263A JP 1426386 A JP1426386 A JP 1426386A JP S62172437 A JPS62172437 A JP S62172437A
Authority
JP
Japan
Prior art keywords
computer
real
virtual
real computer
party
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
JP61014263A
Other languages
Japanese (ja)
Inventor
Shizuo Mihashi
三橋 鎮雄
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.)
Fujitsu Ltd
Original Assignee
Fujitsu 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 Fujitsu Ltd filed Critical Fujitsu Ltd
Priority to JP61014263A priority Critical patent/JPS62172437A/en
Publication of JPS62172437A publication Critical patent/JPS62172437A/en
Pending legal-status Critical Current

Links

Landscapes

  • Hardware Redundancy (AREA)

Abstract

PURPOSE:To efficiently use a real machine by connecting an input/output device connected to an opposite side to its own real computer when the real computer fails to operate at the opposite side, and making perform an operation handled with a virtual computer in the real computer at the opposite side, with the virtual computer controlled at its own side. CONSTITUTION:When a real computer 1 fails to operate, a virtual computer monitor 21 at a real computer 2 side can recognize the down of the real computer 1 because the periodical sending of a bit of information from the real computer 1 to the real computer 2 is ceased. When the real computer 1 fails to operate,a system switching part 23 at the real computer 2 side issues a command to switch I/O devices 5 and 6 to the real computer 2 side. And the virtual computer monitor 21 allocates the I/O devices 5 and 6 to a virtual computer 25-2, and informs the fact that the virtual computer 25-2 operates as a main system for the I/O devices, then making operate the virtual computer 25-2. The virtual computer 25-2 performs the initialization of a communication control program, and restarts the operation setting an operation A'' in an operation possible state, and the virtual computer 25-2 as the main system. In this way, a high reliability system in which the real machine can be used efficiently can be obtained.

Description

【発明の詳細な説明】 〔概要〕 2台の実計算機上にそれぞれ複数の仮想計算機を実現し
、1台の実計算機が故障した場合にはその業務を他の実
計算機で引き継ぐようにし、1台の実計算機上の仮想計
算機が故障した場合にはその実計算機上の他の仮想計算
機がその業務を引き継ぐようにした高信頼性システムで
ある。
[Detailed Description of the Invention] [Summary] A plurality of virtual computers are realized on each of two real computers, and when one real computer breaks down, the work is taken over by another real computer. This is a highly reliable system in which if a virtual computer on one real computer fails, another virtual computer on that real computer will take over the work.

〔産業上の利用分野〕[Industrial application field]

本発明は、複数の仮想計算機が構築された実計算機Aと
複数の仮想計算機が構築された実計算機Bとを有する高
信頼性システムに関するものである。
The present invention relates to a highly reliable system having a real computer A in which a plurality of virtual computers are constructed and a real computer B in which a plurality of virtual machines are constructed.

〔従来技術と問題点〕[Prior art and problems]

高信頼性を持つ計算機システムとしては、待機システム
や並列システム等が知られている。待機システムでは、
現用システムがオンライン業務を行い、待機システムが
バッチ・ジョブを行い、現用システムが故障した場合に
は現用システムが待機システムとなり、待機システムが
現用システムとなってオンライン業務を実行する。並列
システムでは、2台の計算機システムが同じ業務を行っ
ており、一方の計算機システムが故障しても業務を支障
なく遂行することができる。
Standby systems, parallel systems, and the like are known as highly reliable computer systems. In the standby system,
The active system performs online operations, the standby system executes batch jobs, and if the active system fails, the active system becomes the standby system, and the standby system becomes the active system and executes the online operations. In a parallel system, two computer systems perform the same task, and even if one computer system malfunctions, the task can be carried out without any problems.

従来の高信頼性システムでは、1台の計算機には1個の
オペレーティング・システムしか存在ぜず、システム数
に等しい数の実マシンが必要になり、高価な実マシンを
効率的に使用出来ないと言う欠点があった。
In conventional high-reliability systems, there is only one operating system per computer, and a number of real machines equal to the number of systems is required, making it difficult to use expensive real machines efficiently. There was a drawback.

〔発明の目的〕[Purpose of the invention]

本発明は、上記の考察に基づくものであって、従来の高
信頼性システムに較べて実マシンを効率的に使用できる
高信頼性システムを提供することを目的としている。
The present invention is based on the above considerations, and aims to provide a highly reliable system that can use real machines more efficiently than conventional highly reliable systems.

〔目的を達成するための手段〕[Means to achieve the purpose]

そしてそのため、本発明の高信頼性システムは、2台の
実計算機と、これら2台の実計算機間に設置された通信
路と、入出力装置と、上記各実計算機からの切換え指令
に従って指定された入出力装置を指定された実計算機に
接続する入出力監視装置を具備する高信頼性システムで
あって、各実計算機は、仮想計算機モニタと、複数台の
仮想計算機と、自己の実計算機上に構築された仮想計算
機のシステム・ダウンを検出する監視手段と、自己の実
計算機がダウンしていないことを上記通信路を介して相
手方の実計算機に通知する通信機能手段と、相手方の実
計算機がダウンしたことを認識した時に上記入出力監視
装置に対して切換え指令を送出するシステム切換え手段
とを有し、上記仮想計算機モニタは、自己配下の仮想計
算機がシステム・ダウンした場合には、当該仮想計算機
の行っていた業務を自己配下の他の仮想計算機に行わせ
、相手方の実計算機がダウンした場合には、相手方の実
計算機に接続されていた入出力装置を自己の実計算機に
接続し、相手方の実計算機上に構築された仮想計算機で
行われていた業務を自己配下の仮想計算機に行わせるよ
うに構成されていることを特徴とするものである。
Therefore, the highly reliable system of the present invention has two real computers, a communication path installed between these two real computers, an input/output device, and a system specified according to switching commands from each of the above real computers. A highly reliable system equipped with an input/output monitoring device that connects a specified input/output device to a specified real computer, in which each real computer has a virtual computer monitor, multiple virtual computers, and its own real computer. a monitoring means for detecting a system down of a virtual computer built in a system, a communication function means for notifying the other party's real computer via the communication path that its own real computer is not down, and the other party's real computer and system switching means that sends a switching command to the input/output monitoring device when it recognizes that the virtual computer has gone down, and when the virtual computer under its own control goes down, the virtual computer monitor If you have another virtual machine under your control do the work that your virtual machine was doing, and the other party's real computer goes down, you can connect the input/output device that was connected to the other party's real computer to your own real computer. , is characterized in that it is configured to cause a virtual computer under its own control to perform tasks that were being performed on a virtual computer built on the other party's real computer.

〔発明の実施例〕[Embodiments of the invention]

以下、本発明を図面を参照しつつ説明する。図は本発明
の1実施例のブロック図である。図において、1と2は
実計算機、3はCPU間通信装置、4はI10監視装置
、5はディス、プレイ、6はプリンタ、7は共用DAS
D、11は仮想計算機モニタ、12はCPU間通信機能
部、13はシステム切換え部、14はCPU内監視部、
15−1ないし15−3は仮想計算機、21は仮想計算
機モニタ、22はCPU間通信機能部、23はシステム
切換え部、24はCPU内監視部、25−1ないし25
−3は仮想計算機をそれぞれ示している。
Hereinafter, the present invention will be explained with reference to the drawings. The figure is a block diagram of one embodiment of the present invention. In the figure, 1 and 2 are actual computers, 3 is an inter-CPU communication device, 4 is an I10 monitoring device, 5 is a display, 6 is a printer, and 7 is a shared DAS
D, 11 is a virtual machine monitor, 12 is an inter-CPU communication function section, 13 is a system switching section, 14 is a CPU internal monitoring section,
15-1 to 15-3 are virtual computers, 21 is a virtual computer monitor, 22 is an inter-CPU communication function section, 23 is a system switching section, 24 is a CPU internal monitoring section, 25-1 to 25
-3 indicates each virtual machine.

仮想計算機モニタl 1.CPU間通間通化部12、シ
ステム切換え部13、CPU内監視部14及び仮想計算
機15−1ないし15−3のそれぞれは、ソフトウェア
的な手段によって実現されるものであって、各部分に対
応するプログラムが存在する。実計算機2側のハードウ
ェア及びソフトウェアは、実計算機1側のそれと同じで
ある。仮想計算機モニタ11は、A V M (Adv
anced Vertual Machine)と呼ば
れるものであって、仮想計算機システム全体を制御する
ものである。CPU間通間通化部12は、一定時間毎に
実計算機1が正常に動作している旨の情報をcpu間通
信装置3を介して相手方に通知するものである。勿論、
実計算機lがダウンすると、この通信が行えな(なるこ
とは当然である。システム切換え部13は、相手方の実
計算機2がダウンした時に、I10資a5,6等を物理
的に実計算機1側に接続せよと言う指令をI10監視装
置4に対して送出する。
Virtual machine monitor 1. Each of the inter-CPU communication unit 12, system switching unit 13, internal CPU monitoring unit 14, and virtual machines 15-1 to 15-3 is realized by software means, and the A program exists. The hardware and software on the real computer 2 side are the same as those on the real computer 1 side. The virtual machine monitor 11 is an AV M (Adv
It is called an anced Virtual Machine) and controls the entire virtual computer system. The inter-CPU communication unit 12 notifies the other party via the inter-CPU communication device 3 of information that the actual computer 1 is operating normally at regular intervals. Of course,
If the real computer 1 goes down, this communication cannot be performed (it is natural that this will happen. When the other party's real computer 2 goes down, the system switching unit 13 physically transfers I10, A5, 6, etc. to the real computer 1 side. A command to connect to the I10 monitoring device 4 is sent to the I10 monitoring device 4.

I10監視装置4は、システム切換え部13又は23か
らの指令に従ってI10資源の物理的な切換えを行う。
The I10 monitoring device 4 performs physical switching of I10 resources according to commands from the system switching unit 13 or 23.

cpu内監視部14は、仮想計算機15−1.15−2
.15−3の監視を行うものである。図示しないが、監
視用テーブルが存在し、仮想計算機15−4  (i=
1.2.3)は、自己の障害を検出した場合には監視用
テーブルにその旨を記入すると共に、一定時間毎に自己
が生きている旨の情報を時刻と一緒に監視用テーブルに
記入する。CPU内監視部14は、監視用テーブルの内
容を読取って仮想計算機l5−1ないし15−3のシス
テム・ダウンを検出する。
The CPU internal monitoring unit 14 monitors the virtual machine 15-1.15-2.
.. 15-3. Although not shown, a monitoring table exists, and the virtual computer 15-4 (i=
1.2.3), if it detects its own failure, it will write that fact in the monitoring table, and at regular intervals it will also write information that it is alive along with the time in the monitoring table. do. The CPU internal monitoring unit 14 reads the contents of the monitoring table and detects a system down of the virtual machines 15-1 to 15-3.

今、I10装置5,6が仮想計算機15−1に割付けら
れ、仮想計算[15−1がA業務(例えば銀行業務)を
行っていたとする。この状態のもとでは、実計算機1例
の他の仮想計算機及び実計算機2側の仮想計算機はそれ
ぞれ他の業務を行っている。仮想計算機15−1がシス
テム;ダウンすると、このシステム・ダウンはCPU内
監視部14により検出され、CPU内監視部14はこの
旨を仮想計算機モニタ11に通知する。この通知を受は
取ると、仮想計算機モニタ11は、I10装置5,6を
仮想計算機15−2に割付け、仮想計算機15−2に制
御を渡す。装置の割付けはアタッチ(ATTAC)I)
コマンドを発行することにより行われる。仮想計算機1
5−2は、通信制御プログラムの初期設定を行い、業務
A′を動作可能状態にして、業務を仮想計算機15−2
を主系として再開する。図示しないが、仮想計算機のO
8とディスプレイ等の間の通信は、通信制御プログラム
を介して行われる。業務AとA′は同じであり、また図
示の例では、共用DASD7は仮想計算機15−1.1
5−2及び25−2からアクセス可能であり、これは切
換えの対象にならない。
Now, assume that the I10 devices 5 and 6 are allocated to the virtual computer 15-1, and the virtual computer 15-1 is performing business A (for example, banking business). Under this state, the other virtual computers of the real computer 1 and the virtual computers on the real computer 2 side are each performing other tasks. When the virtual computer 15-1 goes down, this system down is detected by the CPU internal monitoring unit 14, and the CPU internal monitoring unit 14 notifies the virtual computer monitor 11 of this fact. Upon receiving this notification, the virtual machine monitor 11 allocates the I10 devices 5 and 6 to the virtual machine 15-2, and passes control to the virtual machine 15-2. Device assignment is attached (ATTAC) I)
This is done by issuing a command. Virtual computer 1
Step 5-2 initializes the communication control program, puts the task A' into an operable state, and transfers the task to the virtual computer 15-2.
restart as the main system. Although not shown, the O of the virtual machine
Communication between 8 and the display etc. is performed via a communication control program. Businesses A and A' are the same, and in the example shown, the shared DASD 7 is the virtual machine 15-1.1.
It can be accessed from 5-2 and 25-2, and is not subject to switching.

実計算機1がダウンすると、実計算機1から実計算機2
に定期的に送られる情@(システムが正常に動作してい
る旨の情報)がなくなるので、実計算機2側の仮想計算
機モニタ21は実計算機1のダウンを認識することで出
来る。実計算機1がダウンすると、実計算機2側のシス
テム切換え部23は、I10装置5.6を実計算機1例
に切換えるべきことを指令する。そして、仮想計算機モ
ニタ21は、I10装置5.6を仮想計算機25−2に
割付け、仮想計算機25−2に主系として動作させる旨
を伝え、仮想計算機25−2を動作させる。仮想計算機
25−2は、通信制御プログラムの初期設定を行い、業
務A″を動作可能な状態として仮想計算機25−2を主
系として業務を再開する。業務Aと業務A#は同じであ
る。
When real computer 1 goes down, real computer 1 to real computer 2
Since the information @ (information indicating that the system is operating normally) that is periodically sent to the real computer 2 disappears, the virtual computer monitor 21 on the real computer 2 side can recognize that the real computer 1 is down. When the real computer 1 goes down, the system switching unit 23 on the real computer 2 side instructs the I10 device 5.6 to be switched to the real computer 1 example. Then, the virtual machine monitor 21 allocates the I10 device 5.6 to the virtual machine 25-2, notifies the virtual machine 25-2 that it will operate as the main system, and causes the virtual machine 25-2 to operate. The virtual machine 25-2 initializes the communication control program, puts the work A″ into an operable state, and restarts the work with the virtual machine 25-2 as the main system.The work A and the work A# are the same.

〔発明の効果〕〔Effect of the invention〕

以上の説明から明らかなように、本発明によれば、実マ
シンを効率的に使用できる高信頼性システムを得ること
ができる。
As is clear from the above description, according to the present invention, a highly reliable system that can efficiently use real machines can be obtained.

【図面の簡単な説明】 図は本発明の1実施例のブロック図である。 1と2・・・実計算機、3・・・CPU間通信装置、4
・・弓10監視装置、5・・・ディスプレイ、6・・・
プリンタ、7・・・共用DASD、11・・・仮想計算
機モニタ、12・・・CPU間通信機能部、13・・・
システム切換え部、14・・・CPU内監視部、15−
1ないし15−3・・・仮想針n機、21・・・仮想3
1算機モニタ、22・・・cpu間通間通化機能部3・
・・システム切換え部、24・・・CPU内監視部、2
5−1ないし25−3・・・仮想計算機。
BRIEF DESCRIPTION OF THE DRAWINGS The figure is a block diagram of one embodiment of the present invention. 1 and 2...actual computer, 3...inter-CPU communication device, 4
... Bow 10 Monitoring device, 5... Display, 6...
Printer, 7... Shared DASD, 11... Virtual computer monitor, 12... Inter-CPU communication function unit, 13...
System switching unit, 14... CPU internal monitoring unit, 15-
1 to 15-3...virtual needle n machines, 21...virtual 3
1 Computer monitor, 22...CPU communication function unit 3.
...System switching section, 24...CPU internal monitoring section, 2
5-1 to 25-3...virtual computers.

Claims (1)

【特許請求の範囲】[Claims] 2台の実計算機と、これら2台の実計算機間に設置され
た通信路と、入出力装置と、上記各実計算機からの切換
え指令に従って指定された入出力装置を指定された実計
算機に接続する入出力監視装置を具備する高信頼性シス
テムであって、各実計算機は、仮想計算機モニタと、複
数台の仮想計算機と、自己の実計算機上に構築された仮
想計算機のシステム・ダウンを検出する監視手段と、自
己の実計算機がダウンしていないことを上記通信路を介
して相手方の実計算機に通知する通信機能手段と、相手
方の実計算機がダウンしたことを認識した時に上記入出
力監視装置に対して切換え指令を送出するシステム切換
え手段とを有し、上記仮想計算機モニタは、自己配下の
仮想計算機がシステム・ダウンした場合には、当該仮想
計算機の行っていた業務を自己配下の他の仮想計算機に
行わせ、相手方の実計算機がダウンした場合には、相手
方の実計算機に接続されていた入出力装置を自己の実計
算機に接続し、相手方の実計算機上に構築された仮想計
算機で行われていた業務を自己配下の仮想計算機に行わ
せるように構成されていることを特徴とする高信頼性シ
ステム。
Two real computers, a communication path installed between these two real computers, an input/output device, and a specified input/output device connected to the specified real computer according to the switching command from each of the above real computers. A highly reliable system equipped with an input/output monitoring device, in which each real computer has a virtual computer monitor, multiple virtual computers, and detects system down of a virtual computer built on its own real computer. a communication function means for notifying the other party's real computer via the communication path that the own real computer is not down; and a communication function means for notifying the other party's real computer that the other party's real computer is down; and system switching means for sending a switching command to the device, and when the virtual machine under itself goes down, the virtual machine monitor transfers the work being performed by the virtual machine to the other virtual machine under itself. If the other party's real computer goes down, the input/output device connected to the other party's real computer is connected to the own real computer, and the virtual computer built on the other party's real computer is activated. A high-reliability system characterized by being configured so that a virtual computer under its control performs operations that were previously performed by a computer.
JP61014263A 1986-01-24 1986-01-24 High reliability system Pending JPS62172437A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP61014263A JPS62172437A (en) 1986-01-24 1986-01-24 High reliability system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP61014263A JPS62172437A (en) 1986-01-24 1986-01-24 High reliability system

Publications (1)

Publication Number Publication Date
JPS62172437A true JPS62172437A (en) 1987-07-29

Family

ID=11856203

Family Applications (1)

Application Number Title Priority Date Filing Date
JP61014263A Pending JPS62172437A (en) 1986-01-24 1986-01-24 High reliability system

Country Status (1)

Country Link
JP (1) JPS62172437A (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2007148839A (en) * 2005-11-29 2007-06-14 Hitachi Ltd Failure recovery method
JP2008140198A (en) * 2006-12-04 2008-06-19 Hitachi Ltd Failover method and its computer system
JP2010211819A (en) * 2010-04-26 2010-09-24 Hitachi Ltd Failure recovery method
JP2011216072A (en) * 2010-04-01 2011-10-27 Accenture Global Services Ltd Repurposable recovery environment

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2007148839A (en) * 2005-11-29 2007-06-14 Hitachi Ltd Failure recovery method
JP4544146B2 (en) * 2005-11-29 2010-09-15 株式会社日立製作所 Disaster recovery method
US7934119B2 (en) 2005-11-29 2011-04-26 Hitachi, Ltd. Failure recovery method
US8352778B2 (en) 2005-11-29 2013-01-08 Hitachi, Ltd. Failure recovery method
US8694820B2 (en) 2005-11-29 2014-04-08 Hitachi, Ltd. Failure recovery method
JP2008140198A (en) * 2006-12-04 2008-06-19 Hitachi Ltd Failover method and its computer system
JP2011216072A (en) * 2010-04-01 2011-10-27 Accenture Global Services Ltd Repurposable recovery environment
JP2010211819A (en) * 2010-04-26 2010-09-24 Hitachi Ltd Failure recovery method

Similar Documents

Publication Publication Date Title
US6529978B1 (en) Computer input/output (I/O) interface with dynamic I/O adaptor processor bindings
US9430266B2 (en) Activating a subphysical driver on failure of hypervisor for operating an I/O device shared by hypervisor and guest OS and virtual computer system
US20080005222A1 (en) System and Method for Server Information Handling System Management Through Local I/O Devices
JP2005215947A (en) Storage device with plurality of interfaces and control method for the same
JP2006195821A (en) Method for controlling information processing system, information processing system, direct memory access controller, and program
JP2018116648A (en) Information processor, control method thereof and program
JP2001209627A (en) Information processing system
JP5549733B2 (en) Computer management apparatus, computer management system, and computer system
JPS62172437A (en) High reliability system
JPH06214762A (en) Hot-plug support for computer input device
JPH0887341A (en) Computer system with automatic degeneratively starting-up function
JPH05314075A (en) On-line computer system
JPWO2015037078A1 (en) Information processing apparatus, backup program, and backup method
JP2019149053A (en) Information processing device, control method of information processing device and control program of information processing device
JP6822706B1 (en) Cluster system, server equipment, takeover method, and program
JPH0833835B2 (en) Error recovery controller
JP3394834B2 (en) Debugging method for devices that make up a multiprocessor system
JPH0264845A (en) Electronic computer multiplexing main control part
JPH10187473A (en) Duplex information processor
JP2744113B2 (en) Computer system
JP2629415B2 (en) A business process switching method in a mutual standby system
JPH01312658A (en) Computer system
JPS6324347A (en) Automatic recovery processing system for tss center system
JPH0441395Y2 (en)
JPH0250737A (en) Duplex system