WO2011111131A1 - コンピュータシステム及び現用系コンピュータ並びに予備系コンピュータ - Google Patents
コンピュータシステム及び現用系コンピュータ並びに予備系コンピュータ Download PDFInfo
- Publication number
- WO2011111131A1 WO2011111131A1 PCT/JP2010/006095 JP2010006095W WO2011111131A1 WO 2011111131 A1 WO2011111131 A1 WO 2011111131A1 JP 2010006095 W JP2010006095 W JP 2010006095W WO 2011111131 A1 WO2011111131 A1 WO 2011111131A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- data
- computer
- transmission
- information
- storage device
- 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
- G06F11/2097—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 maintaining the standby controller/processing unit updated
-
- 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
- G06F11/1658—Data re-synchronization of a redundant component, or initial sync of replacement, additional or spare unit
- G06F11/1662—Data re-synchronization of a redundant component, or initial sync of replacement, additional or spare unit the resynchronized component or unit being a persistent storage device
-
- 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
-
- 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
- G06F11/2038—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 with a single idle spare processing component
Definitions
- the present invention relates to data backup technology in a computer system that performs replication, particularly data replication in an asynchronous manner.
- the computer system disclosed in Patent Document 1 includes a failure prediction unit that predicts the occurrence of a failure in the computer, and all services running on the computer where the failure occurrence is predicted by the failure prediction unit At the same time, the service is re-executed on another computer. Then, after all services are re-executed on another computer, the computer on which the failure occurrence is predicted by the failure prediction means is stopped.
- a service running on a computer that is predicted to fail before the failure occurs is transferred to another computer, and the failure is predicted. It is said that the computer can be stopped normally.
- the business computer (active computer) is provided with an abnormality detection sensor for detecting a sign that the computer will be destroyed, and the abnormality detection sensor indicates the sign described above.
- the backup computer receives the electronic information from the business computer, the backup computer stores it in a recording medium provided in the backup computer.
- the active device includes an active TM (Transaction Manager) that processes a transaction and an active DBMS (Data Base Management System) that reflects update data generated by the transaction.
- the standby system apparatus includes a standby system TM in which update data is notified from the active system TM and a standby system DBMS that makes the data contents stored in the active system DBMS the same.
- the active TM notifies the active DBMS of the update data generated by the execution of the transaction and also notifies the standby TM via synchronous communication.
- the active DBMS receives the update data notified from the active TM itself. The data is reflected in the database to be managed, and update data is notified to the standby DBMS by asynchronous communication.
- the backup TM stores the notified update data in the difference file, reads the update data from the difference file at a predetermined opportunity, and notifies the backup DBMS, and the backup DBMS is acquired from the active DBMS or the backup TM.
- the updated data is reflected in the database managed by itself.
- update data is collected by one computer and transmitted together with control information of the update data, and the update data is assembled based on the control information by the other computer, and the update data is returned to the transaction unit and the other database. If a failure occurs during the process of collecting update data in one computer when using the database identification method to be reflected in the database, the database in the one computer and the database in the other computer cannot be identified. It is said that the reliability of database identification can be improved.
- Patent Document 1 the occurrence of a failure is known by the abnormality detection sensor and the failure prediction means provided in the system.
- Patent Document 4 there is also known a method of knowing the occurrence of a failure by receiving disaster notification information for notifying the occurrence of a disaster.
- data replication for avoiding failures.
- data replication is required to back up new data generated by execution of an application in the active computer to the standby computer.
- Synchronous replication means that the active computer sends the data to the standby computer and stores it in the standby computer in synchronization with the generation of the data to be updated.
- Asynchronous replication means that the active computer does not return control to the writing application after sending the data to the standby computer in synchronization with the generation of the update target data.
- Means that the data to be updated is transmitted to the standby computer after returning control to the application that performed the writing before transmitting to the standby computer.
- the generated update target data may be temporarily stored, and the data stored at a predetermined opportunity may be collectively transmitted to the standby computer.
- a system that uses asynchronous replication for data replication has the advantage that communication latency for data replication in the active computer can be suppressed.
- communication latency for data replication in the active computer can be suppressed.
- data that has not been transmitted from the active computer to the standby computer is lost, and when the standby computer is later used as the active computer for business operation, the lost data is recovered. There is a problem that it takes time to resume business.
- Patent Literature 1 terminates all services executed on a computer in which a failure is predicted, and the occurrence of a failure is predicted after these services are re-executed on another computer. Stop the calculator.
- Patent Document 1 there is no specific disclosure about data replication. However, assuming that asynchronous replication is used for data replication, all services executed on the computer on which a failure has been predicted are re-executed on another computer. In order to execute, it is necessary to transmit data that has not yet been transmitted to other computers until the time when the occurrence of a failure is predicted.
- Patent Document 2 transmits data in the business computer to the backup computer when an abnormality detection sensor detects a sign that the business computer will be destroyed. This technique is the ultimate asynchronous replication, if anything. This method is also described when the method of Patent Document 1 is described when a failure occurs between the detection of a sign of destruction of the business computer and the completion of transmission of data to the backup computer. Have similar problems.
- Patent Document 3 substantially eliminates the above-described problems of asynchronous replication by using synchronous replication and asynchronous replication in combination with data replication. This has the problem of limiting the benefits of asynchronous replication.
- the present invention has been made in view of the above circumstances, and provides a replication technology that makes use of the advantages of asynchronous replication for data replication and can guarantee the reliability of data backed up to a backup computer when a failure occurs.
- One aspect of the present invention is an active computer on which a business application is executed, and the active computer performs asynchronous replication of data generated by the execution of the business application with a standby computer. ing.
- the present active computer includes a storage device for the business application to write data, a transmission queue, a reception unit, a control unit, and a transmission unit.
- the transmission queue queues data that has not been transmitted to the standby computer among data written to the storage device by the business application.
- the receiving unit receives a notice of advance notice for notifying the occurrence of a failure.
- the control unit stops the execution of the business application upon receiving the notice of notice from the receiving unit.
- the transmission unit When the notification is received by the reception unit, the transmission unit receives transmission start information indicating the start of data transmission for avoiding a failure, data queued in the transmission queue, and transmission completion information indicating the completion of data transmission. Send to the standby computer.
- Another aspect of the present invention is a standby computer that performs asynchronous replication of data generated by execution of the business application on the active computer with the active computer on which the business application is executed.
- the standby computer includes a storage device and a backup unit that writes data from the active computer to the storage device in association with asynchronous replication.
- the backup unit When receiving the transmission start information from the active computer, the backup unit writes the data received after the transmission start information to the storage device and indicates that the data received before the transmission start information is reliable data First reliability assurance information is generated and held.
- the transmission start information is information indicating the start of “data transmission” performed for avoiding a failure when the active computer receives a notification of notification of occurrence of a failure.
- the “data transmission” is a backup system. This means sending data that has not yet been sent to the computer.
- the backup unit when the backup computer receives the transmission completion information transmitted after the completion of the “data transmission”, the backup unit indicates that the data received before the transmission completion information is reliable data. Generate and maintain reliability assurance information.
- a method, apparatus, or system in which the active computer or the standby computer of the above aspect is replaced and expressed, a program that causes the computer to execute the operation of the active computer or the standby computer, and a computer reading that records the program A possible recording medium and a computer system including the active computer and the standby computer are also effective as an aspect of the present invention.
- FIG. 5 is a diagram for explaining a relationship between a writing time of write data queued in a transmission queue of the computer shown in FIG. 4 and temporary holding time information. It is a figure for demonstrating the additional time information queued to a transmission queue with write data. It is a figure for demonstrating the meaning of the synchronization start packet etc. in the computer system shown in FIG.
- FIG. 4 is a diagram for explaining switching after a failure occurs in the computer system shown in FIG. 3.
- non-transitory computer-readable media examples include magnetic recording media (eg, flexible disks, magnetic tapes, hard disk drives), magneto-optical recording media (eg, magneto-optical disks), CD-ROM (Read Only Memory) CD-R, CD -R / W, including semiconductor memory (for example, mask ROM, PROM (Programmable ROM), EPROM (Erasable PROM), flash ROM, RAM (Random Access Memory)).
- the program may be supplied to the computer by various types of temporary computer readable media. Examples of transitory computer readable media include electrical signals, optical signals, and electromagnetic waves.
- the temporary computer-readable medium can supply the program to the computer via a wired communication path such as an electric wire and an optical fiber, or a wireless communication path.
- the computer system 100 includes an active computer 110 and a standby computer 130 that are communicably connected.
- the active computer 110 is a computer on which a business application is executed, and asynchronous replication of data generated by the execution of the business application on the active computer 110 is performed with the standby computer 130.
- asynchronous replication of data transmits the data to the standby computer as needed as the data is generated, and transmits the data to the standby computer instead of returning control to the business application after the transmission is completed.
- Processing is asynchronously returning write control to the business application and sending data to the backup computer for backup.
- Generated data is temporarily stored, and the data stored at a predetermined predetermined trigger is sent to the standby computer at predetermined time intervals or when the processing load on the active computer is low. May be.
- the backup computer may write the data to the storage device provided in the standby computer, or store the data in a difference file and collect the differences at a predetermined opportunity. You may make it read from a file and write in a memory
- storage device may be used to write the data to the standby computer.
- the data replication performed between the active computer 110 and the standby computer 130 may be any conventionally known asynchronous replication method, and therefore the technique according to the present invention will be described here. Except for the points required above, details of asynchronous replication and functional blocks necessary for this are omitted.
- the computer system 100 includes a storage device 112, an application execution unit 114, a main processing unit 115, a transmission unit 116, a transmission queue 118, a reception unit 120, and a control unit 122.
- the application execution unit 114 performs control such as execution and stop of business applications.
- the main processing unit 115 writes the write data generated by the execution of the business application in the storage device 112 and accumulates the same data as the data written in the storage device 112 in the transmission queue 118.
- the storage device 112 is a recording medium such as a hard disk, and stores data written by the main processing unit 115.
- the transmission unit 116 transmits the same data as the data written to the storage device 112 by the main processing unit 115 to the standby computer 130, and data transmission by the transmission unit 116 is transmitted to the storage device 112 by the main processing unit 115.
- the transmission unit 116 includes a transmission queue 118, accumulates the same data as the data written in the storage device 112 by the main processing unit 115 in the transmission queue 118, and sequentially stores the data in the standby computer 130 if transmission is possible. Send. Instead of sequentially transmitting data when transmission is possible, the data may be transmitted to the standby computer 130 collectively at a predetermined trigger.
- the receiving unit 120 is for receiving a notice of notice for notifying the occurrence of a failure. When the notice of notice is received, the receiving unit 120 notifies the control unit 122 accordingly.
- the “notice notice” is a notice for the occurrence of a failure in the active computer 110, and may be any information for notifying the occurrence of a failure in the active computer 110.
- a failure is detected from information from a failure notification organization that notifies a disaster such as an earthquake at the installation location of the active computer 110 or a result of monitoring the state of the memory, CPU, etc. of the active computer 110 provided in the computer system 100. It may be information from a means for notifying the occurrence.
- the control unit 122 performs control for failure avoidance on the application execution unit 114 and the main processing unit 115 when the reception unit 120 receives the advance notice.
- control unit 122 causes the application execution unit 114 to stop the execution of the business application when the reception unit 120 receives the notice of notice.
- main processing unit 115 is controlled so that transmission to the standby computer 130 is performed in the order of transmission start information, data transmission, and transmission completion information.
- Transmission start information and “transmission completion information” are information indicating the start and completion of the data transmission, respectively.
- the standby computer 130 includes a storage device 132 and a backup unit 140.
- the storage device 132 is a recording medium such as a hard disk, and stores data written by the backup unit 140.
- the backup unit 140 writes the data from the active computer 110 to the storage device 132 by asynchronous replication of data, and receives the data received after the transmission start information when the transmission start information is received from the active computer 110.
- the first reliability assurance information is written and stored in the storage device 132, and the data received before the transmission start information is reliable data. Further, when the transmission completion information is received from the active computer 110, the second reliability assurance information is generated and held, the data received before the transmission completion information being reliable data.
- the transmission start information and the transmission completion information can be in any format as long as the start and completion of the “data transmission” from the active computer 110 for avoiding the failure can be notified to the standby computer 130. Also good.
- the transmission start information may be a synchronization start packet indicating the start of the “data transmission”, the time information of the first queue of data accumulated in the transmission queue of the “data transmission”, or the like. May be a synchronization completion packet indicating completion of the “data transmission” or time information of the last queue of data accumulated in the transmission queue of the “data transmission”.
- the first reliability assurance information may be in any format as long as it can indicate that the data received before the transmission start information is reliable data. For example, it may be information indicating data received last before the transmission start information.
- Asynchronous replication is performed, and data waiting to be transmitted to the standby computer 130 is accumulated in the transmission queue 118 of the active computer 110.
- the data stored in the transmission queue 118 is sequentially transmitted to the standby computer 130 if transmission is possible.
- “data transmission” for transmitting the data stored in the transmission queue 118 to the standby computer 130 is started to avoid a failure. Transmission start information and transmission completion information are transmitted at the start and completion of the transmission, respectively.
- the standby computer 130 holds the first reliability assurance information indicating that the data received before the transmission start information is reliable data, and the transmission is completed.
- second reliability assurance information indicating that the received data is reliable data is held before the transmission completion information.
- transmission start information indicates that “the backup computer 130 has received”
- X indicates that “the backup computer 130 has not received”.
- “ ⁇ ” indicates “retained in the standby computer 130
- “ ⁇ ” indicates“ retained in the standby computer 130. Not ".
- Case 1 As shown in FIG. 2, when the standby computer 130 has not received the transmission start information from the active computer 110 (of course, it has not received the transmission completion information), the standby computer 130 The reliability assurance information and the second reliability assurance information are not held. This case is a case where the active computer 110 has not received a notice of notice of the occurrence of a failure, such as normal asynchronous replication.
- the standby computer 130 when the standby computer 130 is used as the active computer later to execute a business application, the reliability of the data backed up in the storage device 132 of the standby computer 130 can be confirmed, and the business application is executed from where. Can be dealt with.
- the data received before the transmission start information is reliable data
- the business application can be executed from the point of obtaining the last received data among the reliable data.
- the data received before the transmission completion information is reliable data
- the business application can be executed from the last received data of these data.
- asynchronous replication of data is performed between the active computer 110 and the standby computer 130 until the active computer 110 receives an advance notice, and the active computer 110 notifies the advance notice.
- data synchronization is performed between the active computer 110 and the standby computer 130, and information indicating whether the data synchronization is complete, that is, how far the data is reliable. (First reliability assurance information, second reliability assurance information) is generated and held in the standby computer 130. Therefore, it is possible to make use of the advantages of asynchronous replication for data replication and to guarantee the reliability of data backed up to a backup computer when a failure occurs.
- the active computer 110 can suppress the amount of data to be transmitted to the receiving unit 120 by the data synchronization by stopping the business application being executed, and the data synchronization is completely performed. Can increase the probability of being caught.
- FIG. 3 shows a computer system 200 according to an embodiment of the present invention.
- the computer system 200 includes a plurality of computers (only two of the computer 210 and the computer 220 are illustrated in the figure) and a failure notice service device 240. These computers and the failure notice service device 240 are connected via a network 230 such as a LAN or a WAN.
- a network 230 such as a LAN or a WAN.
- the plurality of computers provided in the computer system 200 of the present embodiment have the same configuration.
- an operating system hereinafter referred to as an OS
- replication software 216 and a business application (hereinafter referred to as AP) AP 218 are installed in a computer 210, and these software read and write data first.
- Storage device 212 and a second storage device 213 different from the first storage device 212.
- an OS 224, replication software 226, and AP 228 are installed in the computer 220.
- the first storage device 222 from which these software read and write data is different from the first storage device 222.
- a second storage device 223 is included.
- the AP 218 mounted on the computer 210 and the AP 228 mounted on the computer 220 are the same business application, and the AP 218 surrounded by the solid line frame is executed, and the AP 228 surrounded by the dotted line frame Has been stopped. That is, in this case, the computer 210 is an active computer, and the computer 220 is a standby computer. Further, data generated by the execution of AP 218 is transmitted to the computer 220 by asynchronous replication and backed up.
- the failure notice service device 240 transmits a notice of notice for notifying of the occurrence of the trouble to the computer via the network 230.
- the failure notice service device 240 notifies a notice of a natural disaster such as an earthquake that may cause a failure of the computer, and is provided, for example, in an organization that predicts a disaster.
- the active computer and the standby computer normally perform asynchronous data replication.
- This asynchronous replication is performed by replication software installed in the active computer and the standby computer.
- the active computer receives the notice of notice, it stops the running business application and starts data synchronization, and the backup computer backs up the data transmitted from the active computer during data synchronization to its own storage device. To do.
- FIG. 4 shows a specific configuration of each computer in the computer system 200.
- FIG. 4 only the portion related to the “data synchronization” described above is shown, and illustration and description of the other portions are omitted.
- the computer 210 since each computer has the same configuration, the computer 210 will be described as a representative.
- the computer 210 includes a first storage device 212, a second storage device 213, a transmission / reception unit 300, a control unit 302, a main processing unit 310, an I / O request queue 312, a transmission queue 314, decompression.
- the computer 210 can be either an active computer or a standby computer.
- solid lines between functional blocks indicate the flow of data and signals when the computer 210 is an active computer
- dotted lines indicate the flow of data and signals when the computer 210 is a standby computer. .
- the main processing unit 310 has a function for executing a business application and a backup function.
- a function for executing a business application is executed, and when the computer 210 is a standby computer, a backup function is executed. That is, the main processing unit 310 can operate as an application execution unit when the computer 210 is an active computer, and the main processing unit 310 can operate as a backup unit when the computer 210 is a standby computer.
- the main processing unit 310 queues write data generated by the execution of the business application in the I / O request queue 312 and the transmission queue 314.
- temporary holding time information described later is queued together with the write data as additional time information, and the temporary holding time information is updated to the current writing occurrence time (hereinafter referred to as writing time). To do.
- the relationship between the data writing time and the temporary holding time information will be described. As an example, it is assumed that writing of data 0, data 1, data 2, and data 3 occurs in time order, and the writing times of these data are time 0, time 1, time 2, and time 3, respectively.
- the main processing unit 310 holds the latest writing occurrence time as temporary holding time information. As shown in FIG. 5, writing of data 0 occurs at time 0, and time 0 is stored as temporary holding time information.
- the temporary holding time information is updated to time 2 when data 2 is written and updated to time 3 when data 3 is written.
- the main processing unit 115 queues the write data to the transmission queue 314.
- the main processing unit 115 queues the temporary holding time information before the update in association with the data. This will be described with reference to FIG.
- the temporary holding time information being held immediately before the data 1 write time (time 1) is the data 0 write time (time 0). Therefore, at time 1, data 1 is queued in the transmission queue 314 together with additional time information at time 0. Accordingly, the temporary holding time information is updated to time 1.
- the temporary holding time information is time 1 immediately before the data 2 write time (time 2). Therefore, at time 2, data 2 is queued in the transmission queue 314 together with the additional time information at time 1. The Accordingly, the temporary holding time information is updated at time 2.
- the temporary holding time information is time 2 immediately before the data 3 write time (time 3), at time 3, the data 3 is queued in the transmission queue 314 together with the additional time information at time 2. . Accordingly, the temporary holding time information is updated at time 3.
- the transmission queue 314 queues the write data and the write time of the write data immediately before the write data in association with each other.
- the I / O request queue 312 sequentially queues the queued data to the first storage device 212.
- the first storage device 212 stores data from the I / O request queue 312.
- the transmission queue 314 sequentially queues the queued write data to the compression unit 318.
- the compression unit 318 compresses the data from the transmission queue 314 and outputs the compressed data to the transmission / reception unit 300.
- the transmission / reception unit 300 sequentially outputs data from the compression unit 318 (hereinafter referred to as compressed data) to the standby computer (in this case, the computer 220) via the network 230.
- the main processing unit 310 stores the data in the difference storage unit 320 without queuing the data to the transmission queue 314. Thereafter, when communication with the standby computer becomes possible, the data stored in the difference storage unit 320 is queued in the transmission queue 314.
- the notice of notice from the trouble notice service device 240 is transmitted via the network 230. That is, the transmission / reception unit 300 of the computer 210 also serves as a reception unit that receives the notice of advance notice.
- the transmission / reception unit 300 When the transmission / reception unit 300 receives the advance notice, the transmission / reception unit 300 notifies the control unit 302 to that effect.
- the control unit 302 When the control unit 302 is notified from the control unit 302 that the notification of the advance notice is received, the control unit 302 outputs a data synchronization start command to the main processing unit 310, and the business application is asynchronous with the data synchronization start command.
- the stop command is output.
- the main processing unit 310 stops the business application upon receiving the business application stop command. This eliminates the generation of new data by the business application.
- the main processing unit 310 When the main processing unit 310 receives the data synchronization start command, the main processing unit 310 operates as follows. First, the main processing unit 310 interrupts transmission data stored in the transmission queue 314 and causes the transmission / reception unit 300 to transmit a “synchronization start packet” indicating the start of data synchronization.
- This synchronization start packet includes the additional time information of the head queue of the data accumulated in the transmission queue 314. This additional time information is the additional time information of the write data queued at the head of the transmission queue 314, that is, the write time of the write data immediately before the write data.
- the transmission queue 314, the compression unit 318, and the transmission / reception unit 300 are controlled so that the write data accumulated in the transmission queue 314 is sequentially transmitted after the “synchronization start packet”.
- the main processing unit 310 causes the transmission / reception unit 300 to transmit a “synchronization completion packet” indicating the completion of data synchronization.
- This synchronization completion packet is the current temporary holding time information, that is, the write time of the last queue of data accumulated in the transmission queue 314.
- the computer 210 when the computer 210 is an active computer and receives a notification of a notice of occurrence of a failure (a disaster notice in this embodiment), the business application being executed is stopped in the computer 210. At the same time, the computer 210 transmits the synchronization start packet, the compressed data of the data queued in the transmission queue 314, and the synchronization completion packet in this order.
- the transmission / reception unit 300 receives data from the active computer along with asynchronous data replication. This data is compressed data of data generated during execution on the active computer.
- the main processing unit 310 causes the decompression unit 316 to decompress the compressed data received by the transmission / reception unit 300.
- the decompression unit 316 outputs the decompressed data to the I / O request queue 312.
- the I / O request queue 312 sequentially queues the data from the decompression unit 316 to the first storage device 212.
- the first storage device 212 stores data from the I / O request queue 312.
- the above processing is processing on the standby computer side when asynchronous data replication is executed, and detailed description thereof is omitted here.
- the main processing unit 310 When the transmission / reception unit 300 receives the “synchronization start packet”, the main processing unit 310 outputs the additional time information included in the synchronization start packet to the I / O request queue 312 as the first reliability assurance information. In addition, the I / O request queue 312 is controlled so that this additional time information is queued to the second storage device 213.
- the main processing unit 310 sequentially decompresses each data received by the transmission / reception unit 300 after the “synchronization start packet” to the decompression unit 316 and outputs the decompressed data to the I / O request queue 312. For these data, the main processing unit 310 controls the I / O request queue 312 to queue out to the first storage device 212.
- the main processing unit 310 When the transmission / reception unit 300 receives the “synchronization completion packet”, the main processing unit 310 outputs the temporary holding time information included in the synchronization completion packet to the I / O request queue 312 as the second reliability assurance information. To do. In addition, the I / O request queue 312 is controlled so that the temporary holding time information is queued to the second storage device 213.
- FIG. 8 is a flowchart showing the flow of processing in the active computer in the computer system 200.
- the active computer executes the business application until the notice of notice is received, and performs asynchronous replication of data generated by the execution of the business application with the standby computer (S100: No). , S102).
- the asynchronous replication of data in step S102 returns the write control to the business application asynchronously with the process of transmitting the data to the standby computer, compresses the data accumulated in the transmission queue, and transfers it to the standby computer. It is a process to transmit.
- control unit When the notice notice is received in the active computer, the control unit issues a business application stop command and a data synchronization start command (S110, S120).
- the main processing unit of the active computer stops the business application being executed (S112).
- the transmission / reception unit transmits the synchronization start packet including the additional time information of the head queue of the data stored in the transmission queue to the standby computer. After that, the data accumulated in the transmission queue is compressed and transmitted until the transmission queue becomes empty (S124, S126: No, S124 ⁇ ).
- the main processing unit causes the transmission unit to transmit a synchronization completion packet including temporary holding time information to the standby computer.
- FIG. 9 is a flowchart showing the flow of processing in the standby computer in the computer system 200.
- the backup computer backs up data (compressed data) from the active computer until it receives a synchronization start packet from the active computer (S150: No, S152).
- the backup in step S152 is decompression of compressed data from the active computer, queuing to the I / O request queue, and queuing from the I / O request queue to the first storage device.
- the main processing unit of the standby computer uses the additional time information included in the synchronization start packet as the first reliability assurance information to the second storage device via the I / O request queue.
- the compressed data from the active computer is backed up and written to the first storage device until a synchronization completion packet is received (S150: Yes, S160, S162: No, S164-).
- the main processing unit of the standby computer uses the temporary storage time information included in the synchronization completion packet as second reliability assurance information via the I / O request queue to the second storage device. (S162: Yes, S170).
- FIG. 10 is an example showing switching of computers that execute business applications manually or automatically after a failure occurs.
- FIG. 10 shows an example in which HA cluster software is installed together with replication software on each computer.
- the HA cluster software installed on each computer monitors the state of each other's computer and executes business applications exclusively.
- the replication software performs asynchronous data replication between a computer on which a business application is executed, a computer on which the business application is installed, and a computer on which the business application is not executed.
- the HA cluster software also switches the computer that executes the business application when a failure occurs in the computer on which the business application is executed. This switching can be selected automatically or manually depending on the setting.
- this example is an example of switching when the computer 210 is an active computer and the computer 220 is a standby computer.
- the active computer 210 is stopped.
- the HA cluster software 227 in the computer 220 causes the AP 228 to be executed.
- the computer 220 that was the standby system is switched to the active computer.
- the HA cluster software 227 executes the AP 228, the additional time information included in the synchronization start packet and the temporary holding time information included in the synchronization completion packet are recorded in the second storage device 223 of the computer 220.
- the execution start point of the AP 228 is determined based on the confirmation result.
- the HA cluster software 227 is recorded in the first storage device 222.
- the data transmitted and received before the transmission time is regarded as reliable data, and the AP 228 is executed from the point where the last received data is obtained.
- the HA cluster software 227 As the data received before the synchronization completion packet recorded in the storage device 222 is reliable, the AP 228 is executed from the last received data among these data.
- the computer system 200 according to the present embodiment is an example in which the computer system 100 shown in FIG. 1 is embodied, and each effect of the computer system 100 can be obtained.
- the standby computer records the first reliability assurance information and the second reliability assurance information in a second storage device different from the first storage device, whereby the active computer and the standby computer are recorded.
- the data in the first storage device can be matched.
- each computer has the functions of both the active computer and the standby computer.
- both of the above functions are mounted only on a computer that becomes a server, for example. May be.
- only the function of the active computer may be mounted on the active server, and only the function of the standby computer may be mounted on the standby server.
- the function of the active computer can be installed in the active shared storage device, and the function of the spare computer can be installed in the standby shared storage.
- the notice of notice is received via a network.
- the notice of notice may be received by any communication method such as a radio wave.
- the present invention can be used for data backup in a computer system that performs replication, particularly data replication in an asynchronous manner.
Abstract
Description
図2に示すように、予備系コンピュータ130が現用系コンピュータ110から送信開始情報を受信していない(当然ながら送信完了情報も受信していない)場合に、予備系コンピュータ130には、第1の信頼性保証情報と第2の信頼性保証情報が保持されない。このケースは、通常の非同期レプリケーションが行われているなど、現用系コンピュータ110において障害発生の予告を通知する予告通知を受信しなかった場合である。
一方、予備系コンピュータ130が現用系コンピュータ110から送信開始情報を受信しており、送信完了情報を受信しなかった場合、予備系コンピュータ130には、第1の信頼性保証情報が保持されるが、第2の信頼性保証情報が保持されない。このケースは、現用系コンピュータ110が予告通知を受信し、まだ送信していないデータを予備系コンピュータ130に送信するデータ送信(以下「データ同期」ともいう)を行ったが、例えばデータ同期中に障害が発生してしまったなど、データ同期が完全にできなかった場合である。
また、予備系コンピュータ130が現用系コンピュータ110から送信開始情報と送信完了情報の両方を受信した場合、予備系コンピュータ130には、第1の信頼性保証情報と第2の信頼性保証情報の両方が保持される。このケースは、現用系コンピュータ110が予告通知を受信した後にデータ同期を行い、このデータ同期は完全に行われた場合である。
図3は、本発明の実施の形態にかかるコンピュータシステム200を示す。コンピュータシステム200は、複数のコンピュータ(図においてコンピュータ210とコンピュータ220の2つのみを例示)と、障害予告サービス装置240を備える。これらのコンピュータと障害予告サービス装置240は、LANやWANなどのネットワーク230を介して接続されている。
この場合、主処理部310は、業務アプリケーションの実行により生じた書き込みデータをI/Oリクエストキュー312と送信キュー314にキューイングする。送信キュー314へキューイングする際、後述する一時保持時刻情報を付加時刻情報として当該書き込みデータと一緒にキューイングすると共に、一時保持時刻情報を今回の書き込みの発生時刻(以下書込み時刻という)に更新する。
まず、主処理部310は、送信キュー314に蓄積されている送信データに割り込み、データ同期の開始を示す「同期開始パケット」を送受信部300に送信させる。この同期開始パケットには、送信キュー314に蓄積されたデータの先頭キューの付加時刻情報が含まれている。この付加時刻情報は、送信キュー314の先頭にキューイングされた書込みデータの付加時刻情報、すなわち該書込みデータの1つ前の書込みデータの書込み時刻である。
この場合、送受信部300は、データの非同期レプリケーションに伴って現用系コンピュータからのデータを受信する。このデータは、現用系コンピュータで実行中により生じたデータの圧縮データである。
図7に示すように、予備系コンピュータが現用系コンピュータから同期開始パケットを受信していない(当然ながら同期完了パケットも受信していない)場合に、予備系コンピュータの第2の記憶装置には、同期開始パケットに含まれる付加時刻情報と、同期完了パケットに含まれる一時保持時刻情報が記録されない。このケースは、通常の非同期レプリケーションが行われているなど、現用系コンピュータにおいて障害発生の予告を通知する予告通知を受信しなかった場合である。
一方、予備系コンピュータが現用系コンピュータから同期開始パケットを受信しており、同期完了パケットを受信しなかった場合、予備系コンピュータの第2の記憶装置には、同期開始パケットに含まれる付加時刻情報が記録されるが、同期完了パケットに含まれる一時保持時刻情報が記録されない。このケースは、現用系コンピュータが予告通知を受信し、まだ送信していないデータを予備系コンピュータに送信するデータ送信(すなわち「データ同期」)を行ったが、データ同期中に障害が発生してしまったなど、データ同期が完全にできなかった場合である。
また、予備系コンピュータが現用系コンピュータから同期開始パケットと同期完了パケットの両方を受信した場合、予備系コンピュータの第2の記憶装置には、同期開始パケットに含まれる付加時刻情報と同期完了パケットに含まれる一時保持時刻情報の両方が記録される。このケースは、現用系コンピュータが予告通知を受信した後にデータ同期を行い、このデータ同期は完全に行われた場合である。
112 記憶装置 114 アプリケーション実行部
115 主処理部 116 送信部
118 送信キュー 120 受信部
122 制御部 130 予備系コンピュータ
132 記憶装置 140 バックアップ部
200 コンピュータシステム 210 コンピュータ
212 第1の記憶装置 213 第2の記憶装置
214 OS 216 レプリケーションソフトウェア
217 HAクラスタソフトウェア 218 アプリケーション
220 コンピュータ 222 第1の記憶装置
223 第2の記憶装置 224 OS
226 レプリケーションソフトウェア 227 HAクラスタソフトウェア
228 アプリケーション 230 ネットワーク
240 障害予告サービス装置 300 送受信部
302 制御部 310 主処理部
312 I/Oリクエストキュー 314 送信キュー
316 伸張部 318 圧縮部
320 差分記憶部
Claims (9)
- 業務アプリケーションが実行されている現用系コンピュータと、
前記現用系コンピュータとの間で、前記現用系コンピュータにおける前記業務アプリケーションの実行により生じたデータの非同期レプリケーションが行われる予備系コンピュータとを備えたコンピュータシステムにおいて、
前記現用系コンピュータは、
前記業務アプリケーションがデータを書き込むための記憶装置と、
前記業務アプリケーションにより前記記憶装置に書き込まれたデータのうちの、前記予備系コンピュータにまだ送信していないデータをキューイングする送信キューと、
障害発生の予告を通知する予告通知を受信する受信手段と、
該受信手段により前記予告通知を受信すると、前記業務アプリケーションの実行を停止する制御手段と、
前記受信手段により前記予告通知を受信すると、障害回避のためのデータ送信の開始を示す送信開始情報、前記送信キューにキューイングされているデータ、前記データ送信の完了を示す送信完了情報の順で前記予備系コンピュータへの送信を行う送信手段とを有し、
前記予備系コンピュータは、
記憶装置と、
前記非同期レプリケーションに伴って前記現用系コンピュータからのデータを前記記憶装置に書き込むバックアップ手段とを有し、
該バックアップ手段は、
前記送信開始情報を受信したとき、
該送信開始情報の後に受信したデータを前記記憶装置に書き込むと共に、前記送信開始情報の前に受信したデータが信頼できるデータであることを示す第1の信頼性保障情報を生成して保持し、
前記送信完了情報を受信したとき、
該送信完了情報の前に受信したデータが信頼できるデータであることを示す第2の信頼性保障情報を生成して保持することを特徴とするコンピュータシステム。 - 前記送信開始情報は、前記現用系コンピュータにおける前記送信キューの先頭にキューイングされているデータの1つ前に生じたデータの書込時刻が含まれており、
前記送信完了情報は、前記送信キューの末尾にキューイングされているデータの書込時刻が含まれており、
前記予備系コンピュータにおける前記バックアップ手段は、
前記送信開始情報と前記送信完了情報に含まれる書込時刻を夫々前記第1の信頼性保障情報と第2の信頼性保障情報として保持することを特徴とする請求項1に記載のコンピュータシステム。 - 業務アプリケーションが実行されている現用系コンピュータであって、予備系コンピュータとの間で、前記業務アプリケーションの実行により生じたデータの非同期レプリケーションが行われる前記現用系コンピュータにおいて、
前記業務アプリケーションがデータを書き込むための記憶装置と、
前記業務アプリケーションにより前記記憶装置に書き込まれたデータのうちの、前記予備系コンピュータにまだ送信していないデータをキューイングする送信キューと、
障害発生の予告を通知する予告通知を受信する受信手段と、
該受信手段により前記予告通知を受信すると、前記業務アプリケーションの実行を停止する制御手段と、
前記受信手段により前記予告通知を受信すると、障害回避のためのデータ送信の開始を示す送信開始情報、前記送信キューにキューイングされているデータ、前記データ送信の完了を示す送信完了情報の順で前記予備系コンピュータへの送信を行う送信手段とを有することを特徴とする現用系コンピュータ。 - 前記送信開始情報は、前記送信キューの先頭にキューイングされているデータの1つ前に生じたデータの書込時刻が含まれており、
前記送信完了情報は、前記送信キューの末尾にキューイングされているデータの書込時刻が含まれていることを特徴とする請求項3に記載の現用系コンピュータ。 - 業務アプリケーションが実行されている現用系コンピュータとの間で、前記現用系コンピュータにおける前記業務アプリケーションの実行により生じたデータの非同期レプリケーションが行われる予備系コンピュータにおいて、
記憶装置と、
前記非同期レプリケーションに伴って前記現用系コンピュータからのデータを前記記憶装置に書き込むバックアップ手段とを有し、
前記バックアップ手段は、
前記現用系コンピュータが障害発生の予告を通知する予告通知を受信した時に障害回避のために行うデータ送信であって、前記予備系コンピュータにまだ送信されていないデータの送信である前記データ送信の開始を示す送信開始情報を前記現用系コンピュータから受信したとき、
該送信開始情報の後に受信したデータを前記記憶装置に書き込むと共に、前記送信開始情報の前に受信したデータが信頼できるデータであることを示す第1の信頼性保障情報を生成して保持し、
前記現用系コンピュータが前記データ送信の完了後に送信する送信完了情報を受信したとき、
該送信完了情報の前に受信したデータが信頼できるデータであることを示す第2の信頼性保障情報を生成して保持することを特徴とする予備系コンピュータ。 - 前記送信開始情報は、前記送信キューの先頭にキューイングされているデータの1つ前に生じたデータの書込時刻が含まれており、
前記送信完了情報は、前記送信キューの末尾にキューイングされているデータの書込時刻が含まれていることを特徴とする請求項2に記載の現用系コンピュータ。
前記バックアップ手段は、前記送信開始情報と前記送信完了情報に含まれる書込時刻を前記第1の信頼性保障情報と第2の信頼性保障情報として夫々保持することを特徴とする請求項5に記載の予備系コンピュータ。 - 前記記憶装置とは別の記憶装置をさらに備え、
前記バックアップ手段は、前記第1の信頼性保障情報と前記第2の信頼性保障情報を前記別の記憶装置に書き込むことにより保持することを特徴とする請求項5または請求項6に記載の予備系コンピュータ。 - 業務アプリケーションが実行され、障害発生の予告を通知する予告通知を受信可能な現用系コンピュータであって、予備系コンピュータとの間で、前記業務アプリケーションの実行により生じたデータの非同期レプリケーションが行われる前記現用系コンピュータに対して、
前記予告通知を受信した際に、
前記業務アプリケーションの実行を停止し、
障害回避のためのデータ送信の開始を示す送信開始情報、前記業務アプリケーションが記憶装置に書き込まれたデータのうちの、前記予備系コンピュータにまだ送信されていないデータ、前記データ送信の完了を示す送信完了情報の順で前記予備系コンピュータへの送信を行う処理を実行せしめるプログラムを格納した非一時的なコンピュータ可読媒体。 - 業務アプリケーションが実行されている現用系コンピュータとの間で、前記現用系コンピュータにおける前記業務アプリケーションの実行により生じたデータの非同期レプリケーションが行われる予備系コンピュータに対して、
前記現用系コンピュータが障害発生の予告を通知する予告通知を受信した時に障害回避のために行うデータ送信であって、前記予備系コンピュータにまだ送信されていないデータの送信である前記データ送信の開始を示す送信開始情報を前記現用系コンピュータから受信したとき、
該送信開始情報の後に受信したデータを記憶装置に書き込み、
前記送信開始情報の前に受信したデータが信頼できるデータであることを示す第1の信頼性保障情報を生成して保持し、
前記現用系コンピュータが前記データ送信の完了後に送信する送信完了情報を受信したとき、
該送信完了情報の前に受信したデータが信頼できるデータであることを示す第2の信頼性保障情報を生成して保持する処理を実行せしめるプログラムを格納した非一時的なコンピュータ可読媒体。
Priority Applications (4)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201080065267.9A CN102792287B (zh) | 2010-03-08 | 2010-10-13 | 计算机系统、现用系统计算机和待机系统计算机 |
EP20100847364 EP2546753B1 (en) | 2010-03-08 | 2010-10-13 | Computer system, active system computer and standby system computer |
JP2012504164A JP5459389B2 (ja) | 2010-03-08 | 2010-10-13 | コンピュータシステム及び現用系コンピュータ並びに予備系コンピュータ、プログラム |
US13/578,889 US9128903B2 (en) | 2010-03-08 | 2010-10-13 | Computer system, active system computer, and standby system computer |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2010-050784 | 2010-03-08 | ||
JP2010050784 | 2010-03-08 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2011111131A1 true WO2011111131A1 (ja) | 2011-09-15 |
Family
ID=44562979
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2010/006095 WO2011111131A1 (ja) | 2010-03-08 | 2010-10-13 | コンピュータシステム及び現用系コンピュータ並びに予備系コンピュータ |
Country Status (5)
Country | Link |
---|---|
US (1) | US9128903B2 (ja) |
EP (1) | EP2546753B1 (ja) |
JP (1) | JP5459389B2 (ja) |
CN (1) | CN102792287B (ja) |
WO (1) | WO2011111131A1 (ja) |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
MX2016003673A (es) * | 2013-10-11 | 2016-09-16 | Landmark Graphics Corp | Captura automatica de flujo de trabajo para analizar e informar errores en una aplicacion de perforacion. |
US10587688B2 (en) | 2014-09-19 | 2020-03-10 | Netapp, Inc. | Techniques for coordinating parallel performance and cancellation of commands in a storage cluster system |
CN104216803A (zh) * | 2014-09-29 | 2014-12-17 | 北京奇艺世纪科技有限公司 | 一种退服节点的数据备份方法及装置 |
CN115037674B (zh) * | 2022-05-16 | 2023-08-22 | 郑州小鸟信息科技有限公司 | 一种中央控制系统单机及多设备冗余备份方法 |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2001236258A (ja) * | 1999-12-16 | 2001-08-31 | Hitachi Ltd | 記憶制御装置 |
JP2004005066A (ja) * | 2002-05-30 | 2004-01-08 | Internatl Business Mach Corp <Ibm> | 複数の記録装置に記録されたデータのバックアップ技術 |
JP2004326365A (ja) | 2003-04-23 | 2004-11-18 | Alps Electric Co Ltd | コンピュータバックアップシステム |
JP2004334713A (ja) | 2003-05-09 | 2004-11-25 | Toshiba Corp | 計算機システム、サービス継続制御プログラム |
JP2005222110A (ja) * | 2004-02-03 | 2005-08-18 | Hitachi Ltd | ストレージサブシステム |
JP2007094925A (ja) | 2005-09-30 | 2007-04-12 | Sanyo Electric Co Ltd | サーバおよびクライアント機器 |
JP2008310517A (ja) | 2007-06-13 | 2008-12-25 | Hitachi Ltd | データ同一化方法、データ同一化プログラム、および、現用系装置 |
JP2010050784A (ja) | 2008-08-22 | 2010-03-04 | Nikon Corp | デジタルカメラ |
Family Cites Families (31)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5544347A (en) * | 1990-09-24 | 1996-08-06 | Emc Corporation | Data storage system controlled remote data mirroring with respectively maintained data indices |
US6684306B1 (en) * | 1999-12-16 | 2004-01-27 | Hitachi, Ltd. | Data backup in presence of pending hazard |
JP2002169738A (ja) | 2000-11-30 | 2002-06-14 | Mitsubishi Electric Corp | ファイル配信方法 |
JP2002189570A (ja) * | 2000-12-20 | 2002-07-05 | Hitachi Ltd | 記憶システムの二重化方法および記憶システム |
US6948089B2 (en) * | 2002-01-10 | 2005-09-20 | Hitachi, Ltd. | Apparatus and method for multiple generation remote backup and fast restore |
US7426559B2 (en) * | 2002-05-09 | 2008-09-16 | International Business Machines Corporation | Method for sequential coordination of external database application events with asynchronous internal database events |
US7266665B2 (en) * | 2003-06-17 | 2007-09-04 | International Business Machines Corporation | Method, system, and article of manufacture for remote copying of data |
US7801851B2 (en) * | 2003-06-30 | 2010-09-21 | Gravic, Inc. | Method for ensuring referential integrity in multi-threaded replication engines |
JP4764596B2 (ja) * | 2003-12-08 | 2011-09-07 | 株式会社日立製作所 | データ転送方法及びサーバコンピュータ |
US7383463B2 (en) * | 2004-02-04 | 2008-06-03 | Emc Corporation | Internet protocol based disaster recovery of a server |
WO2005083569A1 (ja) * | 2004-02-26 | 2005-09-09 | Nec Corporation | ネットワーク間のプロセス移動方法およびそのネットワークシステム |
US7490083B2 (en) * | 2004-02-27 | 2009-02-10 | International Business Machines Corporation | Parallel apply processing in data replication with preservation of transaction integrity and source ordering of dependent updates |
JP2005292865A (ja) * | 2004-03-31 | 2005-10-20 | Hitachi Ltd | ストレージシステム及びストレージシステムのバックアップ方法 |
US7213103B2 (en) * | 2004-04-22 | 2007-05-01 | Apple Inc. | Accessing data storage systems without waiting for read errors |
US20070174484A1 (en) | 2006-01-23 | 2007-07-26 | Stratus Technologies Bermuda Ltd. | Apparatus and method for high performance checkpointing and rollback of network operations |
US7676702B2 (en) * | 2006-08-14 | 2010-03-09 | International Business Machines Corporation | Preemptive data protection for copy services in storage systems and applications |
US8131924B1 (en) * | 2008-03-19 | 2012-03-06 | Netapp, Inc. | De-duplication of data stored on tape media |
US8234243B2 (en) * | 2008-06-19 | 2012-07-31 | Microsoft Corporation | Third tier transactional commit for asynchronous replication |
US8499297B2 (en) * | 2008-10-28 | 2013-07-30 | Vmware, Inc. | Low overhead fault tolerance through hybrid checkpointing and replay |
US8266107B2 (en) * | 2009-03-11 | 2012-09-11 | International Business Machines Corporation | Method for mirroring a log file by threshold driven synchronization |
US20100287407A1 (en) * | 2009-05-05 | 2010-11-11 | Siemens Medical Solutions Usa, Inc. | Computer Storage Synchronization and Backup System |
US8930527B2 (en) * | 2009-05-26 | 2015-01-06 | Oracle International Corporation | High availability enabler |
US8140914B2 (en) * | 2009-06-15 | 2012-03-20 | Microsoft Corporation | Failure-model-driven repair and backup |
KR101265388B1 (ko) * | 2009-07-02 | 2013-05-20 | 엔에이치엔비즈니스플랫폼 주식회사 | 고가용성 데이터베이스 관리 시스템 및 이를 이용한 데이터베이스 관리 방법 |
US20120124311A1 (en) * | 2009-08-04 | 2012-05-17 | Axxana (Israel) Ltd. | Data Gap Management in a Remote Data Mirroring System |
US8285956B2 (en) * | 2009-10-22 | 2012-10-09 | Symantec Corporation | Efficient logging for asynchronously replicating volume groups |
US8448014B2 (en) * | 2010-04-23 | 2013-05-21 | International Business Machines Corporation | Self-healing failover using a repository and dependency management system |
US8484503B2 (en) * | 2010-08-18 | 2013-07-09 | International Business Machines Corporation | Disaster recovery replication throttling in deduplication systems |
US8406233B2 (en) * | 2010-09-07 | 2013-03-26 | Check Point Software Technologies Ltd. | Predictive synchronization for clustered devices |
US8667236B2 (en) * | 2010-09-29 | 2014-03-04 | Hewlett-Packard Development Company, L.P. | Host based write ordering for asynchronous replication |
US9864772B2 (en) * | 2010-09-30 | 2018-01-09 | International Business Machines Corporation | Log-shipping data replication with early log record fetching |
-
2010
- 2010-10-13 WO PCT/JP2010/006095 patent/WO2011111131A1/ja active Application Filing
- 2010-10-13 US US13/578,889 patent/US9128903B2/en not_active Expired - Fee Related
- 2010-10-13 EP EP20100847364 patent/EP2546753B1/en not_active Not-in-force
- 2010-10-13 CN CN201080065267.9A patent/CN102792287B/zh not_active Expired - Fee Related
- 2010-10-13 JP JP2012504164A patent/JP5459389B2/ja not_active Expired - Fee Related
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2001236258A (ja) * | 1999-12-16 | 2001-08-31 | Hitachi Ltd | 記憶制御装置 |
JP2004005066A (ja) * | 2002-05-30 | 2004-01-08 | Internatl Business Mach Corp <Ibm> | 複数の記録装置に記録されたデータのバックアップ技術 |
JP2004326365A (ja) | 2003-04-23 | 2004-11-18 | Alps Electric Co Ltd | コンピュータバックアップシステム |
JP2004334713A (ja) | 2003-05-09 | 2004-11-25 | Toshiba Corp | 計算機システム、サービス継続制御プログラム |
JP2005222110A (ja) * | 2004-02-03 | 2005-08-18 | Hitachi Ltd | ストレージサブシステム |
JP2007094925A (ja) | 2005-09-30 | 2007-04-12 | Sanyo Electric Co Ltd | サーバおよびクライアント機器 |
JP2008310517A (ja) | 2007-06-13 | 2008-12-25 | Hitachi Ltd | データ同一化方法、データ同一化プログラム、および、現用系装置 |
JP2010050784A (ja) | 2008-08-22 | 2010-03-04 | Nikon Corp | デジタルカメラ |
Non-Patent Citations (1)
Title |
---|
See also references of EP2546753A4 * |
Also Published As
Publication number | Publication date |
---|---|
US20120324300A1 (en) | 2012-12-20 |
EP2546753B1 (en) | 2015-04-08 |
EP2546753A4 (en) | 2013-08-28 |
US9128903B2 (en) | 2015-09-08 |
JPWO2011111131A1 (ja) | 2013-06-27 |
CN102792287A (zh) | 2012-11-21 |
CN102792287B (zh) | 2016-01-06 |
JP5459389B2 (ja) | 2014-04-02 |
EP2546753A1 (en) | 2013-01-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US7793060B2 (en) | System method and circuit for differential mirroring of data | |
US7694177B2 (en) | Method and system for resynchronizing data between a primary and mirror data storage system | |
JP4796854B2 (ja) | 差分リモートコピーにおける中間ボリュームのデータ溢れ対策 | |
US7437598B2 (en) | System, method and circuit for mirroring data | |
US11907561B2 (en) | Data backup method and apparatus | |
US9075772B2 (en) | Storage apparatus, controller and storage apparatus control method | |
JP5343436B2 (ja) | 情報管理システム | |
US20100042795A1 (en) | Storage system, storage apparatus, and remote copy method | |
US7797571B2 (en) | System, method and circuit for mirroring data | |
JP4288418B2 (ja) | 計算機システムおよび状態取得方法ならびに状態取得プログラム | |
JP2004303122A (ja) | データ転送制御システム | |
CN105159795A (zh) | 数据同步方法、装置和系统 | |
JP5459389B2 (ja) | コンピュータシステム及び現用系コンピュータ並びに予備系コンピュータ、プログラム | |
US8880552B2 (en) | Database system and database control method | |
JP2008090798A (ja) | データ処理システムのバックアップ制御装置及びシステム | |
JP6539974B2 (ja) | 障害通報装置、障害通報方法及び障害通報プログラム | |
WO2016129275A1 (ja) | 情報処理装置、ログ管理システム、ログ管理方法及びプログラム記録媒体 | |
US9971654B2 (en) | Safe storing data for disaster recovery | |
JP4721057B2 (ja) | データ管理システム,データ管理方法及びデータ管理用プログラム | |
US8135982B2 (en) | Parallel multiplex storage systems | |
JP2014006771A (ja) | リモートバックアップ装置、リモートバックアップシステム、方法およびプログラム | |
JP5684016B2 (ja) | 入退管理制御装置、及び入退管理システム | |
JP6900732B2 (ja) | ディザスタリカバリシステム、ディザスタリカバリ方法及びプログラム | |
JPWO2007116467A1 (ja) | ボリューム管理装置およびボリューム管理方法 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
WWE | Wipo information: entry into national phase |
Ref document number: 201080065267.9 Country of ref document: CN |
|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 10847364 Country of ref document: EP Kind code of ref document: A1 |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2010847364 Country of ref document: EP |
|
WWE | Wipo information: entry into national phase |
Ref document number: 13578889 Country of ref document: US |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2012504164 Country of ref document: JP |
|
WWE | Wipo information: entry into national phase |
Ref document number: 7626/CHENP/2012 Country of ref document: IN |
|
NENP | Non-entry into the national phase |
Ref country code: DE |