Methods for enhancing management of backup data sets and devices thereof

Abstract

A method, non-transitory computer readable medium, and apparatus that enhance management of backup data sets include receiving an operation on a region of a production data set. A corresponding region of a backup data set is marked as having a change state status until the received operation is completed on the region of the production data set and mirrored on a corresponding region of a backup data set.

Description

FIELD

This technology relates to methods for enhancing management of backup data sets to support transparent failover and devices thereof.

BACKGROUND

Synchronous mirroring of data sets assures that a backup copy of the data set is always a perfect replica of the current production copy of the data set. Therefore, failover can be performed automatically without human intervention since there is no question about the quality of the backup data.

Unfortunately, synchronous mirroring requires that an application's write be stalled until both the current production data set and the backup data set have been updated. This need to synchronize writes causes unacceptable performance loss in many real-world situations. The performance loss is particularly high when the backup data set is updated over a slow network link such as over a WAN to a cloud storage provider.

Asynchronous mirroring of data sets greatly reduces the performance penalty discussed above. With asynchronous mirroring, an application's write is acknowledged before the backup data set has been updated.

Unfortunately, this relaxed update comes at a cost. At the time of a failover, the backup copy is in an unknown state that may or may not represent the state of the production data at the time of the failover. This uncertainty greatly complicates the failover process. Essentially the challenge comes down to how a storage administrator determines that the quality of the data in the backup data set is “good enough” to support a successful failover.

SUMMARY

A method for enhancing management of backup data sets includes receiving at a virtualization management computing device an operation on a region of a production data set. A corresponding region of a backup data set is marked as having a change state status with the virtualization management computing device until the received operation is completed on the region of the production data set and mirrored on a corresponding region of a backup data set.

A computer readable medium having stored thereon instructions for enhancing management of backup data sets comprising machine executable code which when executed by at least one processor, causes the processor to perform including receiving an operation on a region of a production data set. A corresponding region of a backup data set is marked as having a change state status until the received operation is completed on the region of the production data set and mirrored on a corresponding region of a backup data set.

A virtualization management computing device includes a memory coupled to one or more processors which are configured to execute programmed instructions stored in the memory including receiving an operation on a region of a production data set. A corresponding region of a backup data set is marked as having a change state status until the received operation is completed on the region of the production data set and mirrored on a corresponding region of a backup data set.

This technology provides a number of advantages including providing a method, computer readable medium and apparatus that further enhances management of backup data sets to support transparent failover. This technology reduces the performance penalty associated with the highest-form of mirror data management, i.e. synchronous mirroring, while still maintaining the same assurance of data quality, i.e. never return an incorrect data set. This technology can be utilized with storage virtualization technology, applied to block or file storage, and implemented as part of a file server or integrated with WAN optimization technology. Further, this technology can be utilized with more complex mirror flows, such as mirroring data to another local location synchronously combined with remote change notification by way of example only.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG. 1 is a block diagram of an exemplary network environment with enhanced management of backup data sets to support transparent failover;

FIG. 2 is a partial block diagram and partial functional diagram of the exemplary environment illustrated in FIG. 1; and

FIG. 3 is a flow chart of an exemplary method for managing a write operation with a production data set and a backup data set; and

FIG. 4 is a flow chart of an exemplary method for managing a read operation with the production data set and the backup data set with a failover.

DETAILED DESCRIPTION

An exemplary environment 10 in which enhanced management of backup data sets is illustrated in FIGS. 1 and 2. The environment 10 includes a virtualization management computing device or VMCD 12, a plurality of client computing devices or CCD 14(1)-14(n), a production data storage device or PDSD 16, and a backup data storage device or BDSD 18 which are all coupled together by one or more communication networks 20(1)-20(4), although this environment can include other numbers and types of systems, devices, components, and elements in other configurations. This technology provides a number of advantages including providing improved management of backup data sets to support transparent failover.

The virtualization management computing device 12 provides a number of functions including management of backup data sets and virtualized access to these data sets between the client computing devices 14(1)-14(n) and data storage devices 16 and 18, although other numbers and types of systems can be used and other numbers and types of functions can be performed. In this particular example, the virtualization management computing device 12 includes an active VMCD node 320 and a standby VMCD node 322, although for example the active VMCD node and the standby VMCD node could each be in separate computing device. In this example, the virtualization management computing device 12 includes a central processing unit (CPU) or processor 22, a memory 24, and an interface system 26 which are coupled together by a bus or other link, although other numbers and types of systems, devices, components, and elements in other configurations production data storage device 16, and a backup data storage device 18 and locations can be used. The processor 22 executes a program of stored instructions for one or more aspects of the present technology as described and illustrated by way of the examples herein including for the active and standby VMCD nodes, although other types and numbers of processing devices and logic could be used and the processor 22 could execute other numbers and types of programmed instructions.

The memory 24 stores these programmed instructions for one or more aspects of the present technology as described and illustrated herein, although some or all of the programmed instructions could be stored and executed elsewhere. In this particular example, the memory 24 includes for the active VMCD node 320 a read error injector module (REI) 300, an invalid data table (IDT) 304, and a data mirror manager module (DMM) 306 and for the standby VMCD node 322 another read error injector module (REI) 310, another invalid data table (IDT) 314, and another data mirror manager module (DMM) 316 which are described in greater detail herein and in this example are all configured to be in communication with each other, although the memory 24 can comprise other types and numbers of modules, tables, and other programmed instructions and databases. A variety of different types of memory storage devices, such as a random access memory (RAM) or a read only memory (ROM) in the system or a floppy disk, hard disk, CD ROM, DVD ROM, or other computer readable medium which is read from and written to by a magnetic, optical, or other reading and writing system that is coupled to the processor 22, can be used for the memory 24.

The interface system in the virtualization management computing device 12 is used to operatively couple and communicate between the virtualization management computing device 12 and the client computing devices 14(1)-14(n), the production data storage device 16, and the backup data storage device 18 via one or more of the communications networks 20(1)-20(4), although other types and numbers of communication networks or systems with other types and numbers of connections and configurations can be used. By way of example only, the one or more the communications networks can use TCP/IP over Ethernet and industry-standard protocols, including NFS, CIFS, SOAP, XML, LDAP, and SNMP, although other types and numbers of communication networks, such as a direct connection, a local area network, a wide area network, modems and phone lines, e-mail, and wireless communication technology, each having their own communications protocols, can be used. In the exemplary environment 10 shown in FIGS. 1-2, four communication networks 20(1)-20(4) are illustrated, although other numbers and types could be used.

Each of the client computing devices 14(1)-14(n) utilizes the active VMCD node 320 in the virtualization management computing device 12 to conduct one or more operations with one or more of the production data storage device 16 and the backup data storage device 18, such as to create a file or directory, read or write a file, delete a file or directory, or rename a file or directory by way of example only, although other numbers and types of systems could be utilizing these resources and other types and numbers of functions utilizing other types of protocols could be performed. Each of the production data storage device 16 and the backup data storage device 18 store content, such as files and directories, although other numbers and types of storage systems which could have other numbers and types of functions and store other data could be used.

The client computing devices 14(1)-14(n), the production data storage device 16 and the backup data storage device 18 each include a central processing unit (CPU) or processor, a memory, and an interface or I/O system, which are coupled together by a bus or other link, although each could comprise other numbers and types of elements and component, such as control logic. The client computing devices 14(1)-14(n) may run interface applications, such as Web browsers, that may provide an interface to make requests for and send data to the production data storage device 16 and the backup data storage device 18 via the virtualization management computing device 12, although other types and numbers of applications may be executed. The virtualization management computing device 12 processes requests received from applications executing on client computing devices 14(1)-14(n) for files or directories on one or more of the production data storage device 16 and the backup data storage device 18 and also manages mirroring of data sets and interactions with the production data storage device 16 and the backup data storage device 18 as a result of these operations. The production data storage device 16 and the backup data storage device 18 provide access to stored data sets in response to received requests. Although a production data storage device 16 and a backup data storage device 18 are shown, other types and numbers of data storage devices can be used.

Although an example of the virtualization management computing device 12 with the active VMCD node 320 and the standby VMCD node 322, the plurality of client computing devices 14(1)-14(n), the production data storage device 16, and the backup data storage device 18 are described herein, each of these devices could be implemented in other configurations and manners on one or more of any suitable computer system or computing device. It is to be understood that the devices and systems of the examples described herein are for exemplary purposes, as many variations of the specific hardware and software used to implement the examples are possible, as will be appreciated by those skilled in the relevant art(s).

Furthermore, each of the systems of the examples may be conveniently implemented using one or more general purpose computer systems, microprocessors, digital signal processors, and micro-controllers, programmed according to the teachings of the examples, as described and illustrated herein, and as will be appreciated by those ordinary skill in the art.

In addition, two or more computing systems or devices can be substituted for any one of the systems in any embodiment of the examples. Accordingly, principles and advantages of distributed processing, such as redundancy and replication also can be implemented, as desired, to increase the robustness and performance of the devices and systems of the examples. The examples may also be implemented on computer system or systems that extend across any suitable network using any suitable interface mechanisms and communications technologies, including by way of example only telecommunications in any suitable form (e.g., voice and modem), wireless communications media, wireless communications networks, cellular communications networks, G3 communications networks, Public Switched Telephone Network (PSTNs), Packet Data Networks (PDNs), the Internet, intranets, and combinations thereof.

The examples may also be embodied as a computer readable medium having instructions stored thereon for one or more aspects of the present technology as described and illustrated by way of the examples herein, as described herein, which when executed by a processor, cause the processor to carry out the steps necessary to implement the methods of the examples, as described and illustrated herein.

An exemplary method for managing a write operation with a production data set and a backup data set will now be described with reference to FIGS. 1-4. In this illustrative example, initially there are duplicate stored data sets comprising a production data set stored in the production data storage device (PDSD) 16 and a backup data set stored in the backup data storage device (BDSD) 18, although there can be other numbers and types of data sets and storage devices in other configurations.

In step 100, the virtualization management computing device 12 receives a write request from the one of the client computing devices or CCDs 14(1)-14(b) with respect to a region in the product data set, although other types and numbers of operations could be requested and from other sources.

In step 102, the data mirror manager (DMM) 306 in the active VMCD node 320 detects the received write request and sends an invalidate notification to invalid table (IDT) 314. In this example, the invalidate notification includes sufficient information to describe the exact region of the product data set in PDSD 16 that is being modified or added to by the write operation. At some time in future IDT 314 in the standby VMCD 322 will persistently store this invalidate information and then acknowledge the notification from DMM 306. Each region in the backup data set in the NDSD 18 corresponding to an invalidate notification entry stored in the IDT 314 is considered to be in an invalid state, although other types of designations could be used. By way of example only, the list of change notification includes different types of change notifications, although the change notification can include other types or amounts of change notification. By extension, all regions in the backup data set in the BDSD 18 that do not have corresponding invalidate notification entry in IDT 314 are considered to be in a valid state, although other types of designations could be used.

In step 104, DMM 306 sends a write request including the new data to the designated region in the production data set stored at the production data storage device 16, although the new data could be written into other types and numbers of storage devices. At some time in the future PDSD 16 will acknowledge this write request has been successfully performed.

In step 106, DMM 306 sends a write request including the new data to the designated region in the backup data set stored at the backup data storage device 18, although the new data could be written into other types and numbers of behalf for the write operation. At some time in the future BDSD 18 will acknowledge this write request has been successfully performed.

In step 108, DMM 306 waits for incoming responses to the various requests it has issued on behalf of the original write request from one of the client computing devices 14(1)-14(n).

In step 110, the virtualization management computing device 12 determines if the requested write in the production data set in the production data storage device 18 was successful. If in step 110, the virtualization management computing device 12 determines the requested write in the production data set in the production data storage device 16 was successful, then the Yes branch is taken to step 112.

In step 112, the virtualization management computing device 12 determines if the requested update for the received write request in the invalid data table 314 in the standby VMCD 322 was successful. If in step 112, the virtualization management computing device 12 determines the requested update for the received write request in the invalid data table 314 in the standby VMCD 322 was successful, then the Yes branch is taken to step 114. In step 114, the virtualization management computing device 12 transmits the fast acknowledgement or FAST ACK, i.e. an acknowledgement before determining whether the corresponding write to the backup data set in the backup data storage device 18 was successful, to the requesting one of the client computing devices 14(1)-14(n) and then this exemplary method can end. In this example, the successful write to the invalid data table 314 would provide an indication that the data in the corresponding region in the backup data set in the backup data storage device 18 was invalid in case of a failover and request for that data.

If in step 112, the virtualization management computing device 12 determines the requested update for the received write request in the invalid data table 314 in the standby VMCD 322 was unsuccessful, then the No branch is taken to step 116. In step 116, the virtualization management computing device 12 transmits an indication that the write to the production data set in the production data storage device 16 was successful, but that the requested update for the received write request in the invalid data table 314 in the standby VMCD 322 was unsuccessful and then this exemplary method can end, although other manners for handling this type of error could be used depending on the particular administrative need.

If back in step 110, the virtualization management computing device 12 determines the requested write in the production data set in the production data storage device 16 was unsuccessful, then an invalid state is set for that region of the production data set in the invalid data table 304 and the No branch is taken to step 118. In step 118, the virtualization management computing device 12 determines if the requested write in the backup data set in the backup data storage device 18 was successful. If in step 118, the virtualization management computing device 12 determines the requested write in the backup data set in the backup data storage device 18 was successful, then the Yes branch is taken to step 120. In step 120, the virtualization management computing device 12 provides an indication to the requesting one of the client computing devices 14(1)-14(n) that the primary write to the production data set in the PDSD 16 failed, but that the backup write to the backup data set in the BDSD was successful and then this exemplary method can end.

If in step 118, the virtualization management computing device 12 determines the requested write in the backup data set in the backup data storage device 18 was unsuccessful, then the No branch is taken to step 122. In step 122, the virtualization management computing device 12 provides an indication to the requesting one of the client computing devices 14(1)-14(n) that the primary write to the production data set in the PDSD 16 and the backup write to the backup data set in the BDSD were both unsuccessful and then this exemplary method can end.

An exemplary method for managing a read operation will now be described with reference to FIGS. 1-2 and 4. In step 200 the virtualization management computing device 12 receives a read request from one of the client computing devices 14(1)-14(n), although other types and numbers of operations could be received and from other sources.

In step 202, the read error injector (REI) 300 in the active VMCD node 320 in the virtualization management computing device 12 determines if the received read request is for a region of the production data set in the PDSD 16 with a change notification entry in the IDT 304. If in step 202, the REI 300 in the virtualization management computing device 12 determines the read request is not for a region of the production data set with a change notification entry in the IDT 304, then the No branch is taken to step 204. In step 204, the virtualization management computing device 12 processes the read request and sends a response to the requesting one of the client computing devices 14(1)-14(n).

If back in step 202, the REI in the virtualization management computing device 12 determines the read request is for a region of the production data set in the PDSD 16 with a change notification entry in the IDT 304, then the Yes branch is taken to step 206. In step 206, the read error injector (REI) 300 in the active VMCD node 320 in the virtualization management computing device 12 determines if the received read request is for a region of the backup data set in the BDSD 18 with a change notification entry in the IDT 314. If in step 206, the read error injector (REI) 300 in the active VMCD node 320 in the virtualization management computing device 12 determines the received read request is not for a region of the backup data set in the BDSD 18 with a change notification entry in the IDT 314, then the Yes branch is taken to step 208. For ease of illustration in FIG. 2, not all of the connections between the elements are illustrated, for example the connection between REI 300 and IDT 314 is discussed, but not shown. As noted earlier, in this example read error injector module (REI) 300, invalid data table (IDT) 304, data mirror manager module (DMM) 306, read error injector module (REI) 310, invalid data table (IDT) 314, and another data mirror manager module (DMM) 316 are all configured to be in communication with each other, although other types of configurations can be used. In step 208, the virtualization management computing device 12 responds to the read request from one of the client computing devices 14(1)-14(n) with data from the corresponding region of the backup data set along with a primary fail error to indicate the data in the production data set in the PDSD 16 is invalid, although other manners for responding can be used.

If in step 206, the read error injector (REI) 300 in the active VMCD node 320 in the virtualization management computing device 12 determines the received read request is for a region of the backup data set in the BDSD 18 with a change notification entry in the IDT 314, then the No branch is taken to step 210. In step 210, the virtualization management computing device 12 can provide an indication to the requesting one of the client computing devices 14(1)-14(n) that the requested data in the production data set in the PDSD 16 and the backup data in the backup data set in the BDSD are both invalid, although, other manners for responding can be used and other numbers of optional steps could be executed as discussed below.

In this example, in step 210 the virtualization management computing device 12 optionally determines whether to delay or stall the requested read operation for a first period of time and send an inquiry or other notification to a designated administrator at an administrative computing device with a request for instructions on how to respond to the read operation and error. If in step 210, the virtualization management computing device 12 optionally determines to delay or stall the requested read operation for the first period of time and send an inquiry, then the Yes branch is taken to step 212.

In step 212, the virtualization management computing device 12 sends an inquiry or other notification to a designated administrator at an administrative computing device stored in memory 24 or otherwise designated with a request for instructions on how to respond to the read operation and error. In step 214, the virtualization management computing device 12 obtains a response to the request for instructions on how to respond to the read operation and error from the administrative computing device, processes the read request in accordance with those instructions and then this exemplary method can end.

If back in step 210, the virtualization management computing device 12 optionally determined not to delay or stall the requested read operation for the first period of time and send an inquiry, then the No branch is taken to step 216. In step 216, the virtualization management computing device 12 optionally can determine whether the error with the requested region of the data from the backup data set in the BDSD 18 is critical based on one or more factors. By way of example only, the virtualization management computing device 12 can determine whether the error indicated a corruption rate in the data below a set threshold for the type of data or can determine if the error could be compensated for by executing an error correction application, and then providing the data from the backup data set if the error was not critical.

If in step 216 the virtualization management computing device 12 optionally determines the error with the requested region of data is not critical based on one or more factors, then the No branch is taken to step 218. In step 218, the virtualization management computing device 12 processes the read request to obtain the requested data from the corresponding region in the backup data set in the backup data storage device 18 and provides this data in a response to the requesting one of the client computing devices 14(1)-14(n) and then this exemplary method can end.

If in step 216 the virtualization management computing device 12 optionally determines the error with the requested region of data is critical based on one or more factors, then the Yes branch is taken to step 220. In step 220, the virtualization management computing device 12 sends an error message in a response to the read request to the requesting one of the client computing devices 14(1)-14(n) and then this exemplary method can end.

Accordingly, as illustrated and described herein this technology provides this technology provides a hybrid solution that combines the data quality certainty of synchronous mirroring with the low performance impact of asynchronous mirroring. Additionally, this technology can be used to enhance a globally distributed data caching infrastructure.

Having thus described the basic concept of this technology, it will be rather apparent to those skilled in the art that the foregoing detailed disclosure is intended to be presented by way of example only, and is not limiting. Various alterations, improvements, and modifications will occur and are intended to those skilled in the art, though not expressly stated herein. These alterations, improvements, and modifications are intended to be suggested hereby, and are within the spirit and scope of this technology. Additionally, the recited order of processing elements or sequences, or the use of numbers, letters, or other designations therefore, is not intended to limit the claimed processes to any order except as may be specified in the claims. Accordingly, this technology is limited only by the following claims and equivalents thereto.

Claims

1. A method for enhancing management of backup data sets, the method comprising: receiving, by a virtualization management computing device comprising a processor, a request to perform an operation on a region of a production data set;marking, by the virtualization management computing device comprising the processor, a region of a backup data set corresponding to the region of the production data set on which the operation will be performed, to indicate a change state status for the marked region of the backup data set; anddetermining, by the virtualization management computing device comprising the processor, when a critical error has occurred in the marked region of the backup data set based on a data corruption rate for the marked region of the backup data set exceeding a set threshold after performance of the operation is completed on the region of the production data set and mirrored on the marked region of the backup data set.

2. The method as set forth in claim 1, further comprising: executing, by the virtualization management computing device comprising the processor, the received operation on the region of the production data set;mirroring, by the virtualization management computing device comprising the processor the executed operation on the corresponding region of the backup data set; andmarking, by the virtualization management computing device comprising the processor, the corresponding region of the backup data set as a valid state when the received operation is completed on the region of the production data set and mirrored on the corresponding region of the backup data set.

3. The method as set forth in claim 2 wherein the marking by the virtualization management computing device the corresponding region of the backup data set as valid further comprises: executing, by the virtualization management computing device comprising the processor, a write operation by the virtualization management computing device to clear the change state status.

4. The method as set forth in claim 1 further comprising: maintaining, by the virtualization management computing device comprising the processor, one or more tables of change state regions of the production data set and the backup data set.

5. The method as set forth in claim 1 further comprising: maintaining, by the virtualization management computing device comprising the processor, a list of change notifications.

6. The method as set forth in claim 1, further comprising: performing, by the virtualization management computing device comprising the processor, error correction on the marked region of the backup data set when the critical error was determined to have occurred.

7. A method for enhancing management of backup data sets, the method comprising: receiving, by a virtualization management computing device comprising a processor, an operation on a region of a production data set;marking, by the virtualization management computing device comprising the processor, a corresponding region of a backup data set as having a change state status until the received operation is completed on the region of the production data set and mirrored on the corresponding region of the backup data set;receiving, by the virtualization management computing device comprising the processor, a read operation to the corresponding region of the backup data set as a result of a failover;determining, by the virtualization management computing device comprising the processor, an error with respect to the received read operation when the marking indicates the corresponding region of the backup data set has the change state status;receiving, by the virtualization management computing device comprising the processor, another operation to the corresponding region of the backup data set as a result of a failover; andexecuting, by the virtualization management computing device comprising the processor, the received another operation on the corresponding region of the backup data set when the marking indicates the corresponding region of the backup data set is valid.

8. The method as set forth in claim 7 further comprising: returning, by the virtualization management computing device comprising the processor, an error message with respect to the received read operation when the error is determined.

9. The method as set forth in claim 7 further comprising: determining, by the virtualization management computing device comprising the processor, when to attempt a recovery from the production data set when the error is determined; andexecuting, by the virtualization management computing device comprising the processor, the read operation on the production data set when the determining provides an indication to attempt the recovery.

10. The method as set forth in claim 7 further comprising: introducing, by the virtualization management computing device comprising the processor, a delay to a response to the read operation for a first period of time when the error is determined; andproviding, by the virtualization management computing device comprising the processor, a request for instructions to a designated administrator error during the first period of time.

11. The method as set forth in claim 7 further comprising: determining, by the virtualization management computing device comprising the processor, when the error is critical based on one or more factors when the error is determined; andexecuting, by the virtualization management computing device comprising the processor, the read operation on the backup data set when the error is determined not to be critical.

12. A non-transitory computer readable medium having stored thereon instructions for enhancing management of backup data sets comprising machine executable code which when executed by at least one processor, causes the processor to perform steps comprising: receiving a request to perform an operation on a region of a production data set;marking a region of a backup data set corresponding to the region of the production data set on which the operation will be performed, to indicate a change state status for the marked region of the backup data set; anddetermining when a critical error has occurred in the marked region of the backup data set based on a data corruption rate for the marked region of the backup data set exceeding a set threshold after performance of the operation is completed on the region of the production data set and mirrored on the marked region of the backup data set.

13. The medium as set forth in claim 12, further having stored thereon instructions that when executed by the processor cause the processor to perform steps further comprising: executing the received operation on the region of the production data set;mirroring the executed operation on the corresponding region of the backup data set; andmarking the corresponding region of the backup data set as a valid state when the received operation is completed on the region of the production data set and mirrored on the corresponding region of the backup data set.

14. The medium as set forth in claim 13 wherein the marking the corresponding region of the backup data set as valid further comprises: executing a write operation to clear the change state status.

15. The medium as set forth in claim 12 further having stored thereon instructions that when executed by the processor cause the processor to perform steps further comprising: maintaining one or more tables of change state status regions of the production data set and the backup data set.

16. The medium as set forth in claim 12 further having stored thereon instructions that when executed by the processor cause the processor to perform steps further comprising: maintaining a list of change notifications.

17. The medium as set forth in claim 12, further having stored thereon instructions that when executed by the processor cause the processor to perform steps further comprising: performing error correction on the marked region of the backup data set when the critical error was determined to have occurred.

18. A non-transitory computer readable medium having stored thereon instructions for enhancing management of backup data sets comprising machine executable code which when executed by at least one processor, causes the processor to perform steps comprising: receiving an operation on a region of a production data set;marking a corresponding region of a backup data set as having a change state status until the received operation is completed on the region of the production data set and mirrored on the corresponding region of the backup data set;receiving a read operation to the corresponding region of the backup data set as a result of a failover;determining an error with respect to the received read operation when the marking indicates the corresponding region of the backup data set has the change state status;receiving another operation to the corresponding region of the backup data set as a result of a failover; andexecuting the received another operation on the corresponding region of the backup data set when the marking indicates the corresponding region of the backup data set is valid.

19. The medium as set forth in claim 18 further having stored thereon instructions that when executed by the processor cause the processor to perform steps further comprising: returning an error message with respect to the received read operation when the error is determined.

20. The medium as set forth in claim 18 further having stored thereon instructions that when executed by the processor cause the processor to perform steps further comprising: determining when to attempt a recovery from the production data set when the error is determined; andexecuting the read operation on the production data set when the determining provides an indication to attempt the recovery.

21. The medium as set forth in claim 18 further having stored thereon instructions that when executed by the processor cause the processor to perform steps further comprising: introducing a delay to a response to the read operation for a first period of time when the error is determined; andproviding a request for instructions to a designated administrator error during the first period of time.

22. The medium as set forth in claim 18 further having stored thereon instructions that when executed by the processor cause the processor to perform steps further comprising: determining when the error is critical based on one or more factors when the error is determined; andexecuting the read operation on the backup data set when the error is determined not to be critical.

23. A virtualization management computing device comprising: one or more processors;a memory coupled to the one or more processors which are configured to be capable of executing programmed instructions, which comprise the programmed instructions stored in the memory to:receive a request to perform an operation on a region of a production data set;mark a region of a backup data set corresponding to the region of the production data set on which the operation will be performed, to indicate a change state status for the marked region of the backup data set; anddetermine when a critical error has occurred in the marked region of the backup data set based on a data corruption rate for the marked region of the backup data set exceeding a set threshold after performance of the operation is completed on the region of the production data set and mirrored on the marked region of the backup data set.

24. The device as set forth in claim 23, wherein the one or more processors is further configured to be capable of executing programmed instructions, which comprise the programmed instructions stored in the memory to: execute the received operation on the region of the production data set;mirror the executed operation on the corresponding region of the backup data set; andmark the corresponding region of the backup data set as a valid state when the received operation is completed on the region of the production data set and mirrored on the corresponding region of the backup data set.

25. The device as set forth in claim 24 wherein the one or more processors is further configured to be capable of executing programmed instructions, which comprise the programmed instructions stored in the memory to: mark the corresponding region of the backup data set as valid further comprising executing a write operation to clear the change state status.

26. The device as set forth in claim 23 wherein the one or more processors is further configured to be capable of executing programmed instructions comprising and stored in the memory to: maintain one or more tables of change state status regions of the production data set and the backup data set.

27. The device as set forth in claim 23 wherein the one or more processors is further configured to be capable of executing programmed instructions comprising and stored in the memory to: maintain a list of change notifications.

28. The device as set forth in claim 23, wherein the one or more processors is further configured to be capable of executing programmed instructions comprising and stored in the memory to: perform error correction on the marked region of the backup data set when the critical error was determined to have occurred.

29. A virtualization management computing device comprising: one or more processors;a memory coupled to the one or more processors which are configured to be capable of executing programmed instructions comprising and stored in the memory to:receive an operation on a region of a production data set;mark a corresponding region of a backup data set as having a change state status until the received operation is completed on the region of the production data set and mirrored on the corresponding region of the backup data set;receive a read operation to the corresponding region of the backup data set as a result of a failover anddetermine an error with respect to the received read operation when the marking indicates the corresponding region of the backup data set has the change state status;receive another operation to the corresponding region of the backup data set as a result of a failover; andexecute the received another operation on the corresponding region of the backup data set when the marking indicates the corresponding region of the backup data set is valid.

30. The device as set forth in claim 29 wherein the one or more processors is further configured to be capable of executing programmed instructions comprising and stored in the memory to: return an error message with respect to the received read operation when the error is determined.

31. The device as set forth in claim 29 wherein the one or more processors is further configured to be capable of executing programmed instructions comprising and stored in the memory to: determine when to attempt a recovery from the production data set when the error is determined; andexecute the read operation on the production data set when the determining provides an indication to attempt the recovery.

32. The device as set forth in claim 29 wherein the one or more processors is further configured to be capable of executing programmed instructions comprising and stored in the memory to: delay a response to the read operation for a first period of time when the error is determined; andprovide a request for instructions to a designated administrator error during the first period of time.

33. The device as set forth in claim 29 wherein the one or more processors is further configured to be capable of executing programmed instructions comprising and stored in the memory to: determine when the error is critical based on one or more factors when the error is determined; andexecute the read operation on the backup data set when the error is determined not to be critical.