US20080162594A1 - Data storage system and process - Google Patents

Data storage system and process Download PDF

Info

Publication number
US20080162594A1
US20080162594A1 US12/046,376 US4637608A US2008162594A1 US 20080162594 A1 US20080162594 A1 US 20080162594A1 US 4637608 A US4637608 A US 4637608A US 2008162594 A1 US2008162594 A1 US 2008162594A1
Authority
US
United States
Prior art keywords
data
log
sector
disk
computer
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Abandoned
Application number
US12/046,376
Inventor
Lloyd Alan POSTON
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Quantum Corp
Original Assignee
Quantum Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Quantum Corp filed Critical Quantum Corp
Priority to US12/046,376 priority Critical patent/US20080162594A1/en
Assigned to QUANTUM CORPORATION reassignment QUANTUM CORPORATION ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: SANLIGHT, INC.
Publication of US20080162594A1 publication Critical patent/US20080162594A1/en
Assigned to WELLS FARGO CAPITAL FINANCE, LLC, AS AGENT reassignment WELLS FARGO CAPITAL FINANCE, LLC, AS AGENT SECURITY AGREEMENT Assignors: QUANTUM CORPORATION
Assigned to QUANTUM CORPORATION reassignment QUANTUM CORPORATION RELEASE BY SECURED PARTY (SEE DOCUMENT FOR DETAILS). Assignors: WELLS FARGO CAPITAL FINANCE, LLC, AS AGENT
Abandoned legal-status Critical Current

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F12/00Accessing, addressing or allocating within memory systems or architectures
    • G06F12/16Protection against loss of memory contents
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00Error detection; Error correction; Monitoring
    • G06F11/07Responding to the occurrence of a fault, e.g. fault tolerance
    • G06F11/14Error detection or correction of the data by redundancy in operation
    • G06F11/1402Saving, restoring, recovering or retrying
    • G06F11/1471Saving, restoring, recovering or retrying involving logging of persistent data for recovery
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00Error detection; Error correction; Monitoring
    • G06F11/07Responding to the occurrence of a fault, e.g. fault tolerance
    • G06F11/14Error detection or correction of the data by redundancy in operation
    • G06F11/1402Saving, restoring, recovering or retrying
    • G06F11/1446Point-in-time backing up or restoration of persistent data
    • G06F11/1458Management of the backup or restore process
    • G06F11/1464Management of the backup or restore process for networked environments
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F2201/00Indexing scheme relating to error detection, to error correction, and to monitoring
    • G06F2201/84Using snapshots, i.e. a logical point-in-time copy of the data

Definitions

  • the present invention relates to data storage systems and, in particular embodiments, to data storage systems that provide the ability for continuous up to date backup of a computer hard disk drive.
  • a common scheme for backing up data is to take a snapshot of the data during a period of low user activity. For example, many computer systems are commonly backed up at night when few or no users are using the system.
  • a common method of backup is to merely copy all of the data on hard disks to a mass storage media such as a tape or RAID (Redundant Array of Inexpensive Disks).
  • a first obvious difficulty arises because, although the files are backed up once per day, a failure during the day can cause the loss of several hours of data or work product.
  • Another difficulty can arise because, during the back up period, a large amount of network bandwidth may be consumed in transferring files to a backup system. This bandwidth usage requirement can interfere with other system functions that may be running concurrently.
  • Some systems have attempted to deal with the problem of losing several hours of data, which can occur if a backup is only done once per day, by increasing the frequency of backups.
  • some word processing programs may have facilities to store the open files on a timed basis.
  • the method of storing files on a timed basis can somewhat alleviate the problem of losing many hours of data due to a catastrophic failure.
  • the continual storing of files from many users in a network can consume a large amount of the network bandwidth, however, thereby slowing down all users.
  • the usable bandwidth and hence the capability and efficiency of the network is reduced.
  • preferred embodiments of the present invention relate to a system and method for enabling efficient continuous backups of mass storage within a computer system.
  • a preferred embodiment of the present invention provides the ability to restore data up to an arbitrary time, or up to the point that a failure occurred.
  • preferred embodiments of the present system provide a continuous backup capability in which, instead of storing snapshots of the system data at any particular time creates a continuous record of data changes.
  • a system and process for enabling efficient continuous backups is based on log-assisted disk technology (LAD).
  • LAD log-assisted disk technology
  • One embodiment of the LAD comprises a software layer that is added to an operating system's normal disk interface.
  • the LAD software allows extra capabilities to be added to the disk interface.
  • a disk interface with a LAD software layer looks and acts just like a normal disk drive interface to the operating system. Its operation can also be transparent to the user.
  • data written to the LAD is also queued for transmission to a separate storage program running on a server.
  • Data is sent to the storage server in the order in which it was written to the LAD.
  • These ordered transmissions of data allow the storage server to maintain a complete copy of the data written to the LAD. Because the storage server maintains a complete copy of the data written to the LAD the storage server can determine for any point in time all of the data that was current as of that time. This facility allows the creation of a virtual disk image of the local workstation hard disk as it was at any particular point in time.
  • the server then can provide complete backup coverage of all data written to the workstation disk, an improvement over a daily-snapshot system, which only captures data at the time of the snapshot.
  • Another benefit of the LAD system is that it can serve as a backup for both inactive and active files.
  • the disk activity which is queued for transmission to the server is sent only during periods in which the traffic on the network is light. In this manner continual backup of the workstation data does not adversely impact the overall performance of the network.
  • FIG. 1 is a block diagram of a prior art backup system in which a workstation is backed up using a network connection.
  • FIG. 2 is a block diagram according to an embodiment of the invention in which a workstation is backed up using a network connection.
  • FIG. 3 is a block diagram according to an embodiment of the invention in which the function of a log-assisted disk is illustrated.
  • FIG. 4 is an exemplary embodiment of the invention implemented on a single workstation.
  • FIG. 5 is an illustration of data structures used to implement a log-assisted disk based system (LAD) according to an embodiment of the invention.
  • LAD log-assisted disk based system
  • FIG. 6 is a graphical representation of a portion of the data structures of a log assisted disk system according to embodiments of the invention in which the log assisted disk construct is further used to increase the efficiency of disk accesses.
  • embodiments of the present invention relate, generally, to continuous backup systems implemented on any computing platform.
  • preferred embodiments are described herein with relation to backups performed for workstations connected to a network.
  • This exemplary embodiment is chosen as an example likely to be familiar to those skilled in the art, but is not intended to limit the invention to the example embodiment.
  • Those skilled in the art will recognize the wide applicability of the inventive aspects disclosed herein. Accordingly, the examples disclosed are intended to illustrate the inventive aspects of this disclosure, and not to limit them to a particular form or implementation.
  • FIG. 1 is a block diagram illustrating an example of a prior art backup system.
  • a workstation 101 is backed up using network 127 .
  • An application running on workstation 101 performs writes 105 that will be recorded on the mass storage device of the workstation, in the present example disk 117 .
  • the application 103 writes 105 are accepted by the operating system 107 .
  • the operating system changes the application writes into sector writes 109 , each of which comprise a sector address 111 and data 113 .
  • the sector writes are communicated to a disk controller 115 , which then performs the actual sector writes to the disk 117 .
  • a backup is performed at a designated period, for example once per day or on command.
  • the backup communicates copies of the files on disk 117 , which have been changed since the last backup, to a network interface card (NIC) 119 .
  • the network interface card 119 comprises an ethernet card.
  • the card is connected to an ethernet cable 121 , which is then further connected to a server 123 .
  • the server receives the communications from the network interface card 119 across the ethernet 121 and writes the communications to the mass storage 125 . In this way any files that are changed on disk 117 during a particular day will be copied to the mass storage 125 , to preserve them in case of catastrophic failure within the workstation.
  • FIG. 2 represents a workstation according to one embodiment of the present invention.
  • the workstation 201 runs an application 103 , which proceeds to issue application writes 105 , as described above.
  • the writes 105 are accepted by an operating system 107 and converted into sector writes 109 .
  • the sector writes each comprise a sector address 111 and sector data 113 .
  • items 103 through 113 in the illustrative embodiments of FIG. 2 , may be identical to the similarly numbered items in FIG. 1 , the prior art system.
  • Sector writes 109 are communicated to a log-assisted disk LAD 203 .
  • the log-assisted disk system 203 accumulates the sector writes 109 and time stamps sector writes with a workstation clock 205 time.
  • the new data structure comprising the sector writes 109 which have been time stamped by the workstation clock 205 are provided to the network interface card 119 .
  • the network interface card 119 illustratively an Ethernet card, couples the sector writes time stamped by the workstation clock into the Ethernet 121 and further to the server 123 then to a mass storage 125 .
  • the mass storage contains a log of the sector writes to the disk.
  • the sector writes also have been time stamped by the workstation clock 205 so that the time when each was generated by the operating system is known. Additionally, since the log assisted disk system may write to a mass storage through the network many times per day, for example during periods in which the network traffic is low, the need for a fixed backup period can be eliminated.
  • the LAD 203 may be controlled to write to mass storage 125 through the network 127 as the writes occur. In this manner, if a catastrophic event should befall the workstation 201 , minimal or no data is lost because all writes are effectively being continuously recorded in the mass storage 125 .
  • An additional advantage provided over the periodic backup is that the original system data can be recreated with a fine granularity. This means that the most data which can be lost is that waiting to be written to the network from the LAD.
  • the latency period between writes of the log assisted disk system 203 to the mass storage of the network 125 may be made as short as desired. If the period were made to equal five minutes then the most data that a catastrophic failure at the workstation 201 could cause would be the data that had occurred in writes of five minutes since the last log assisted disk transmission.
  • the workstation disk 117 can be re-created up to any given time within the log.
  • the ability to recreate the workstation disk can be very useful if an application for example were to cause a catastrophic failure at the workstation 201 .
  • the writes of the application could then be traced through the log-assisted disk and a new disk could be created that mirrored the old workstation disk 117 .
  • the new disk record could be recreated up to any point in time within the log, including the point for example when the application causing the catastrophic failure was initiated. Because the disk can be recreated as it existed at any time up until the failure the backup system provides great flexibility.
  • FIG. 3 is a more detailed description of the operation of a log-assisted disk system according to an example embodiment of the invention.
  • Sector writes 109 containing a sector address 111 and sector data 113 are communicated to the log-assisted disk (LAD) 203 .
  • the sector writes 109 are also communicated from the LAD to a disk controller 115 , as needed for recording on the workstation disk 117 .
  • the sector writes 109 are also time stamped 303 by the workstation clock 205 , or other source of time information, and then passed into the log assisted disk queue 305 .
  • the log queue 305 queues the sector writes along with their time stamp until such time as they are to be written to the network.
  • the queue is communicated to the network interface card 119 , in the illustrated example an ethernet card, and then to the ethernet 121 and further to server 123 and the mass storage unit 125 .
  • FIG. 4 is an example of a backup system within a workstation according to a further embodiment of the invention.
  • sector writes 109 containing sector addresses 111 and data 113 are accepted by the log-assisted disk system 403 .
  • the sector writes are then provided by the log-assisted disk system 403 to the disk controller 115 , which writes the sector addresses and data to the disk 117 utilizing normal disk writes 407 .
  • the sector writes are time stamped by workstation clock 205 and are queued within the log assisted disk 403 so as not to interfere with the normal disk writes 407 .
  • the time stamped sector writes are then written into a log file 405 and onto disk 117 by the disk controller 115 .
  • Other embodiments, instead of using a workstation clock may use other sources of time. Time may come from a network clock, an independent time source—such as one synchronized to a particular time standard, or a variety of other sources.
  • the log file 405 may be written to a second physical disk that is different from the disk being used to record normal disk writes 407 . If the first disk to which the normal disk writes 407 were occurring fails, the log file on the second disk could be used to recreate the state of the first disk prior to the failure of the first disk.
  • inventive techniques should be inferred because a hard disk has been chosen as the illustrative memory device.
  • Devices such as removable media, tape, writable CD-ROMS, WORM (Write Once Read Many) flash memory, EEPROM (Electrically Erasable Programmable Read Only Memory) as well as other storage devices may be used.
  • the inventive techniques disclosed herein are applicable to storage devices, combinations of storage devices and systems in general.
  • FIG. 5 is an illustration of example log assisted disk data structures. Since the log-assisted disk system is, effectively, a change record, it must have a point in time with which to reference the change. Ideally, the log-assisted disk is started when the hard disk drive is first put into use and therefore any intermediate state of the hard disk may be recreated upon a failure. If the hard disk is already in use, a snapshot of the disk 501 can be taken, for example, as part of the initial operation of the log assisted disk system. A snapshot of the disk is a copy of all the written sectors of the disk. The snapshot of the disk is set to correspond, for example, to time zero and copied onto a backup unit, such as the mass storage unit 125 .
  • a backup unit such as the mass storage unit 125 .
  • the log assisted disk system has ascertained a beginning point and can record any subsequent change to the snapshot image. Changes comprise the time of the sector writes, the actual sector being written, and the sector data 507 .
  • the disk can be then recreated to a time end 509 by taking the snapshot of the disk 501 and performing the data writes 507 to the sectors 505 that exist between time zero and time N.
  • any intermediate state of the disk within the log can also be recreated.
  • a particular write can be ascertained.
  • the log assisted disk system may also be used to ascertain various metrics regarding the changes in a computer system.
  • a computer system controlling a process or recording data events could use a Log Assisted Disk in order to determine the time at which events happened, periodic activity in a system, profiles of and volume of events within a system.
  • the history of activity in a system would be captured and that history could be mined for any inherent data present within that history of activity.
  • FIG. 6 is an illustration of an operation of a log assisted disk system to produce a backup with a minimum of sector writes.
  • sector (N ⁇ 1) and (N+1) are displayed.
  • the data of sector (N ⁇ 1) has data( 1 )
  • the data of sector N has data( 1 )
  • the data of sector (N+1) has data( 1 ).
  • sector N has data( 2 )
  • sector (N+1) has data( 2 ) written to it.
  • data( 3 ) is written into sector (N ⁇ 1)
  • data( 3 ) is written into sector N and nothing is written into sector (N+1) so data( 2 ) still exists within sector (N+1).
  • data( 2 ) in sector N i.e. 601
  • sector N started with data( 1 ), had data( 2 ) written to it and then was overwritten by data( 3 ). Therefore, data( 2 ), i.e. 601 , is only an intermediate state of the disk to be destroyed by a future write in normal disk operations.
  • log assisted disks can eliminate a larger number of sector writes and thereby further minimize the network traffic necessary to backup a system using a log assisted disk.
  • a log-assisted disk system can provide a flexibility within computer systems that was previously unknown in backup systems.
  • a log-assisted disk system could also be used for creating parallel or mirror sites at different locations.
  • data could be posted, for example, as it occurred, to a number of sites that were interested in the same data.
  • Each remotely computed site would then have a hard disk copy of the data that was used to create the initial site.
  • applications such as remote databases could be continuously kept up to date while, in effect, providing a backup for the original data disk.
  • the Log Assisted Disk system can provide backup for personal computers as well as workstations connected to a network, as for example shown in FIG. 3 .
  • the network interface card 119 coupled to an ethernet connection is merely one example of interconnection that the LAD system might employ.
  • the NIC could also provide connection via a phone line, digital subscriber line (DSL), cable modem, or other connection to the Internet.
  • the Internet can then provide the connection through a server 123 connected to the Internet to a remote mass storage 125 .
  • the NIC 119 need not even connect to a network.
  • the NIC 119 can, for example, connect via a phone line or dedicated line to a remote backup facility designed to accept log entries and return log entries on request.
  • log entries could be written directly to a local mass storage device, such as a tape drive, without any network connection of any type required.

Abstract

Computer systems may loose data when a failure occurs within a system. To counteract such loss of data a backup system may be employed. Common backup systems make a copy of either of the data on a storage device or the data, which has changed, on a storage device. The process of backing up data may involve storing a relatively large amount of data and so is commonly done infrequently, such as once per day. If a computer's data is backed up only once per day, several hours of data may be lost if a computer system falls. Embodiments of the present invention may be used to prevent this type of data loss by backing up more frequently. In order to back up more frequently less data at a time is backed up. Instead of the data undergoing a wholesale backup infrequently, embodiments of the present invention form a timed log of the storage writes performed by the computer system. The log provides a running picture of activity to the computer storage system. By preserving the log, for example storing it at a remote site through a network connection, the state of the computer can be recreated with any desired granularity, by using the log entries to recreate the state of the data within the computer system at any desired time.

Description

    RELATED APPLICATIONS
  • This application is a continuation of U.S. patent application Ser. No. 11/271,104, entitled DATA STORAGE SYSTEM AND PROCESS, filed on Nov. 10, 2005, issued as U.S. Pat. No. 7,343,460 on Mar. 11, 2008; which is continuation of U.S. patent application Ser. No. 09/588,242, entitled PRODUCING A MASS STORAGE BACKUP USING A LOG OF WRITE COMMANDS AND TIME INFORMATION, filed on Jun. 6, 2000, issued as U.S. Pat. No. 7,334,098 on Feb. 19, 2008; all of which are incorporated herein by reference in their entireties.
  • FIELD OF THE INVENTION
  • The present invention relates to data storage systems and, in particular embodiments, to data storage systems that provide the ability for continuous up to date backup of a computer hard disk drive.
  • BACKGROUND OF THE INVENTION
  • Since the beginning of computer systems there have been computer system failures, crashes, power outages and other conditions that result in data loss. Often when a computer system fails, the data within the computer system, which is not stored on a nonvolatile media storage device, is lost. To prevent the loss of computer data, users of computer systems have implemented a variety of schemes to protect computer data from loss. One method of preventing loss of computer data is through data backup schemes. Backup schemes, in general, protect computer data by copying data to a storage device, which can then be accessed if the original data is lost or corrupted.
  • Because of the proliferation of computer data, for example within a company wide network, facilities for backing up large amounts of data are relatively common. One common scheme for backing up data, for example in a network, is to take a snapshot of the data during a period of low user activity. For example, many computer systems are commonly backed up at night when few or no users are using the system. A common method of backup is to merely copy all of the data on hard disks to a mass storage media such as a tape or RAID (Redundant Array of Inexpensive Disks).
  • As the amount of data within a network increases, daily backups of the entire data within a system may become impractical. Most systems commonly limit the data backed up to include only those files which have been changed during the course of a day. While the method of backing up only the files that have changed can ease the backup burden, the process of restoring of the data after a catastrophic failure can require loading data from multiple sequential days. Nonetheless, network backup systems are still commonly snapshot based, that is they run periodically—commonly once per day. In large systems, in which only the changed files are backed up once per day, a full system back up is commonly performed once per week, for example, on the weekends.
  • There are several difficulties with these common schemes of computer system backups. A first obvious difficulty arises because, although the files are backed up once per day, a failure during the day can cause the loss of several hours of data or work product. Another difficulty can arise because, during the back up period, a large amount of network bandwidth may be consumed in transferring files to a backup system. This bandwidth usage requirement can interfere with other system functions that may be running concurrently.
  • Some systems have attempted to deal with the problem of losing several hours of data, which can occur if a backup is only done once per day, by increasing the frequency of backups. For example, some word processing programs may have facilities to store the open files on a timed basis. The method of storing files on a timed basis can somewhat alleviate the problem of losing many hours of data due to a catastrophic failure. The continual storing of files from many users in a network can consume a large amount of the network bandwidth, however, thereby slowing down all users. In addition to slowing down the network response time by burdening the networks with the extra backup traffic, the usable bandwidth and hence the capability and efficiency of the network is reduced.
  • Because of the aforementioned difficulties in current systems there is a need for efficient continuous backups that can minimize the loss of data during a catastrophic failure and yet not adversely impact the functioning of the computer system with excessive backup traffic.
  • SUMMARY OF THE DISCLOSURE
  • Accordingly, to overcome limitations in the prior art described above, and to overcome other limitations that will become apparent upon reading the present specification, preferred embodiments of the present invention relate to a system and method for enabling efficient continuous backups of mass storage within a computer system.
  • A preferred embodiment of the present invention provides the ability to restore data up to an arbitrary time, or up to the point that a failure occurred.
  • In particular, preferred embodiments of the present system provide a continuous backup capability in which, instead of storing snapshots of the system data at any particular time creates a continuous record of data changes.
  • In one illustrative embodiment, a system and process for enabling efficient continuous backups is based on log-assisted disk technology (LAD). One embodiment of the LAD comprises a software layer that is added to an operating system's normal disk interface. The LAD software allows extra capabilities to be added to the disk interface. A disk interface with a LAD software layer looks and acts just like a normal disk drive interface to the operating system. Its operation can also be transparent to the user.
  • In an exemplary LAD based system, implemented on a workstation within a computer network, data written to the LAD is also queued for transmission to a separate storage program running on a server. Data is sent to the storage server in the order in which it was written to the LAD. These ordered transmissions of data allow the storage server to maintain a complete copy of the data written to the LAD. Because the storage server maintains a complete copy of the data written to the LAD the storage server can determine for any point in time all of the data that was current as of that time. This facility allows the creation of a virtual disk image of the local workstation hard disk as it was at any particular point in time. The server then can provide complete backup coverage of all data written to the workstation disk, an improvement over a daily-snapshot system, which only captures data at the time of the snapshot. Another benefit of the LAD system is that it can serve as a backup for both inactive and active files.
  • In a further embodiment of a system containing LAD capability, the disk activity which is queued for transmission to the server is sent only during periods in which the traffic on the network is light. In this manner continual backup of the workstation data does not adversely impact the overall performance of the network.
  • BRIEF DESCRIPTION OF THE DRAWINGS
  • Referring now to the drawings in which consistent numbers refer to like elements throughout.
  • FIG. 1 is a block diagram of a prior art backup system in which a workstation is backed up using a network connection.
  • FIG. 2 is a block diagram according to an embodiment of the invention in which a workstation is backed up using a network connection.
  • FIG. 3 is a block diagram according to an embodiment of the invention in which the function of a log-assisted disk is illustrated.
  • FIG. 4 is an exemplary embodiment of the invention implemented on a single workstation.
  • FIG. 5 is an illustration of data structures used to implement a log-assisted disk based system (LAD) according to an embodiment of the invention.
  • FIG. 6 is a graphical representation of a portion of the data structures of a log assisted disk system according to embodiments of the invention in which the log assisted disk construct is further used to increase the efficiency of disk accesses.
  • DETAILED DESCRIPTION OF PREFERRED EMBODIMENTS
  • In the following description, reference is made to the accompanying drawings, which form a part hereof, and in which is shown by way of illustration specific embodiments in which the invention may be practiced. It is to be understood that other embodiments may be utilized as structural changes without departing from the scope and inventive concepts of the present disclosure.
  • Accordingly embodiments of the present invention relate, generally, to continuous backup systems implemented on any computing platform. However, for the purposes of simplifying this disclosure, preferred embodiments are described herein with relation to backups performed for workstations connected to a network. This exemplary embodiment is chosen as an example likely to be familiar to those skilled in the art, but is not intended to limit the invention to the example embodiment. Those skilled in the art will recognize the wide applicability of the inventive aspects disclosed herein. Accordingly, the examples disclosed are intended to illustrate the inventive aspects of this disclosure, and not to limit them to a particular form or implementation.
  • FIG. 1 is a block diagram illustrating an example of a prior art backup system. In FIG. 1, a workstation 101 is backed up using network 127. An application running on workstation 101 performs writes 105 that will be recorded on the mass storage device of the workstation, in the present example disk 117. The application 103 writes 105 are accepted by the operating system 107. The operating system changes the application writes into sector writes 109, each of which comprise a sector address 111 and data 113. The sector writes are communicated to a disk controller 115, which then performs the actual sector writes to the disk 117. At a designated period, for example once per day or on command, a backup is performed. The backup communicates copies of the files on disk 117, which have been changed since the last backup, to a network interface card (NIC) 119. In the present exemplary embodiment the network interface card 119 comprises an ethernet card. The card is connected to an ethernet cable 121, which is then further connected to a server 123. The server receives the communications from the network interface card 119 across the ethernet 121 and writes the communications to the mass storage 125. In this way any files that are changed on disk 117 during a particular day will be copied to the mass storage 125, to preserve them in case of catastrophic failure within the workstation.
  • FIG. 2 represents a workstation according to one embodiment of the present invention. The workstation 201 runs an application 103, which proceeds to issue application writes 105, as described above. The writes 105 are accepted by an operating system 107 and converted into sector writes 109. The sector writes each comprise a sector address 111 and sector data 113. In the present example items 103 through 113, in the illustrative embodiments of FIG. 2, may be identical to the similarly numbered items in FIG. 1, the prior art system.
  • Sector writes 109 are communicated to a log-assisted disk LAD 203. The log-assisted disk system 203 accumulates the sector writes 109 and time stamps sector writes with a workstation clock 205 time. At predetermined times, which may be when a log assisted disk queue is nearly full, at pre-determined time intervals, or when there is minimal traffic on the network, the new data structure comprising the sector writes 109 which have been time stamped by the workstation clock 205 are provided to the network interface card 119. The network interface card 119, illustratively an Ethernet card, couples the sector writes time stamped by the workstation clock into the Ethernet 121 and further to the server 123 then to a mass storage 125.
  • In the present example, however, instead of mass storage containing changed files the mass storage contains a log of the sector writes to the disk. The sector writes also have been time stamped by the workstation clock 205 so that the time when each was generated by the operating system is known. Additionally, since the log assisted disk system may write to a mass storage through the network many times per day, for example during periods in which the network traffic is low, the need for a fixed backup period can be eliminated.
  • In a further embodiment, the LAD 203 may be controlled to write to mass storage 125 through the network 127 as the writes occur. In this manner, if a catastrophic event should befall the workstation 201, minimal or no data is lost because all writes are effectively being continuously recorded in the mass storage 125.
  • An additional advantage provided over the periodic backup is that the original system data can be recreated with a fine granularity. This means that the most data which can be lost is that waiting to be written to the network from the LAD. The latency period between writes of the log assisted disk system 203 to the mass storage of the network 125 may be made as short as desired. If the period were made to equal five minutes then the most data that a catastrophic failure at the workstation 201 could cause would be the data that had occurred in writes of five minutes since the last log assisted disk transmission.
  • Additionally, since the mass storage contains a log of events on, as opposed to a simple recording of the last updated version of each file, the workstation disk 117 can be re-created up to any given time within the log. The ability to recreate the workstation disk can be very useful if an application for example were to cause a catastrophic failure at the workstation 201. The writes of the application could then be traced through the log-assisted disk and a new disk could be created that mirrored the old workstation disk 117. The new disk record could be recreated up to any point in time within the log, including the point for example when the application causing the catastrophic failure was initiated. Because the disk can be recreated as it existed at any time up until the failure the backup system provides great flexibility.
  • FIG. 3 is a more detailed description of the operation of a log-assisted disk system according to an example embodiment of the invention. Sector writes 109 containing a sector address 111 and sector data 113 are communicated to the log-assisted disk (LAD) 203. The sector writes 109 are also communicated from the LAD to a disk controller 115, as needed for recording on the workstation disk 117. The sector writes 109 are also time stamped 303 by the workstation clock 205, or other source of time information, and then passed into the log assisted disk queue 305. The log queue 305 queues the sector writes along with their time stamp until such time as they are to be written to the network. When it is time for the LAD queue to be written to the network, the queue is communicated to the network interface card 119, in the illustrated example an ethernet card, and then to the ethernet 121 and further to server 123 and the mass storage unit 125.
  • FIG. 4 is an example of a backup system within a workstation according to a further embodiment of the invention. As in the previous FIGS. 1, 2 and 3, sector writes 109 containing sector addresses 111 and data 113 are accepted by the log-assisted disk system 403. The sector writes are then provided by the log-assisted disk system 403 to the disk controller 115, which writes the sector addresses and data to the disk 117 utilizing normal disk writes 407. In addition, the sector writes are time stamped by workstation clock 205 and are queued within the log assisted disk 403 so as not to interfere with the normal disk writes 407. The time stamped sector writes are then written into a log file 405 and onto disk 117 by the disk controller 115. Other embodiments, instead of using a workstation clock, may use other sources of time. Time may come from a network clock, an independent time source—such as one synchronized to a particular time standard, or a variety of other sources.
  • In a multi-disk system, the log file 405 may be written to a second physical disk that is different from the disk being used to record normal disk writes 407. If the first disk to which the normal disk writes 407 were occurring fails, the log file on the second disk could be used to recreate the state of the first disk prior to the failure of the first disk.
  • Utilizing this system of two disks, one containing a LAD system, also provides a sophisticated “undo” capability. So, for example, if an operator of the workstation decided that they needed to undo several hours of work they could use the log file to recreate the state of the disk as it was several hours previously. In addition, the log file 405 would be generating, in effect, a continuous backup of the normal disk writes 407. The examples of storage devices herein are illustrated herein with respect to hard disk drives. Those skilled in the art will recognize that any storage medium or device can be used with the inventive techniques disclosed herein. The hard disk has been chosen as the illustrative device only because it is an example likely to be familiar to those skilled in the art because of its widespread popularity. No limitations on the inventive techniques should be inferred because a hard disk has been chosen as the illustrative memory device. Devices such as removable media, tape, writable CD-ROMS, WORM (Write Once Read Many) flash memory, EEPROM (Electrically Erasable Programmable Read Only Memory) as well as other storage devices may be used. The inventive techniques disclosed herein are applicable to storage devices, combinations of storage devices and systems in general.
  • FIG. 5 is an illustration of example log assisted disk data structures. Since the log-assisted disk system is, effectively, a change record, it must have a point in time with which to reference the change. Ideally, the log-assisted disk is started when the hard disk drive is first put into use and therefore any intermediate state of the hard disk may be recreated upon a failure. If the hard disk is already in use, a snapshot of the disk 501 can be taken, for example, as part of the initial operation of the log assisted disk system. A snapshot of the disk is a copy of all the written sectors of the disk. The snapshot of the disk is set to correspond, for example, to time zero and copied onto a backup unit, such as the mass storage unit 125. Once the snapshot of the disk has been stored on the mass storage 125, the log assisted disk system has ascertained a beginning point and can record any subsequent change to the snapshot image. Changes comprise the time of the sector writes, the actual sector being written, and the sector data 507. The disk can be then recreated to a time end 509 by taking the snapshot of the disk 501 and performing the data writes 507 to the sectors 505 that exist between time zero and time N. Of course any intermediate state of the disk within the log can also be recreated. Alternatively a particular write can be ascertained.
  • The log assisted disk system may also be used to ascertain various metrics regarding the changes in a computer system. For example, a computer system controlling a process or recording data events could use a Log Assisted Disk in order to determine the time at which events happened, periodic activity in a system, profiles of and volume of events within a system. In essence the history of activity in a system would be captured and that history could be mined for any inherent data present within that history of activity.
  • FIG. 6 is an illustration of an operation of a log assisted disk system to produce a backup with a minimum of sector writes. At time one in FIG. 6, sector (N−1) and (N+1) are displayed. At time one the data of sector (N−1) has data(1), the data of sector N has data(1) and the data of sector (N+1) has data(1). At time two, sector N has data(2) and sector (N+1) has data(2) written to it. At time three, data(3) is written into sector (N−1), data(3) is written into sector N and nothing is written into sector (N+1) so data(2) still exists within sector (N+1). As can be seen from the illustration in FIG. 6, by implementing a smart log assisted disk, data(2) in sector N, i.e. 601, need never be written to the backup. This is because sector N started with data(1), had data(2) written to it and then was overwritten by data(3). Therefore, data(2), i.e. 601, is only an intermediate state of the disk to be destroyed by a future write in normal disk operations.
  • By maintaining a smart sector map such as illustrated in FIG. 6, intermediate values of the sectors need not be written as a backup. Only final values of a sector during any time period need be written as a backup. This of course would eliminate the ability to recreate a data disk at any point in time. However, in networks with heavy traffic this embodiment might be an acceptable compromise in order to minimize network traffic. If the smart disk technology were applied only between successive writes of the LAD system to the network, then at most the data that could be lost would be data in the time between successive LAD system writes to the network backup system. This period could be limited to a short period of minutes or even seconds.
  • Many operating systems control sector writes to blocks of a hard disk using various types of algorithms. For example, storage blocks might be arranged into a queue and the least recently used block used by the operating system. Such operating system embodiments of log assisted disks might be changed so that the most recently used blocks of a hard disk are reused whenever possible. By placing the emphasis of reusing blocks in a hard disk system, a smart log assisted disk can eliminate a larger number of sector writes and thereby further minimize the network traffic necessary to backup a system using a log assisted disk. A log-assisted disk system can provide a flexibility within computer systems that was previously unknown in backup systems.
  • A log-assisted disk system could also be used for creating parallel or mirror sites at different locations. Using a log assisted disk system, data could be posted, for example, as it occurred, to a number of sites that were interested in the same data. Each remotely computed site would then have a hard disk copy of the data that was used to create the initial site. And applications such as remote databases could be continuously kept up to date while, in effect, providing a backup for the original data disk.
  • The Log Assisted Disk system can provide backup for personal computers as well as workstations connected to a network, as for example shown in FIG. 3. The network interface card 119 coupled to an ethernet connection is merely one example of interconnection that the LAD system might employ.
  • The NIC could also provide connection via a phone line, digital subscriber line (DSL), cable modem, or other connection to the Internet. The Internet can then provide the connection through a server 123 connected to the Internet to a remote mass storage 125.
  • Additionally the NIC 119 need not even connect to a network. The NIC 119 can, for example, connect via a phone line or dedicated line to a remote backup facility designed to accept log entries and return log entries on request.
  • Additionally log entries could be written directly to a local mass storage device, such as a tape drive, without any network connection of any type required.
  • The foregoing descriptions of exemplary embodiments of the present disclosure have been presented for the purpose of illustration and description. It is not intended to be, exhaustive nor to limit the inventive concepts to the embodiments disclosed. Many modifications and variations are possible in light of the above teaching. It is intended that the scope of the invention be limited not within this detailed description, but rather by the claims appended hereto, which appear below.

Claims (13)

1. A method of continuous data storage, the method comprising:
receiving a write command;
combining the received write command with time information, wherein the time information indicates when the write command was received; and
storing the write command combined with the time information.
2. The method of claim 1, wherein combining the received write command with time information comprises:
converting the received write command to a sector write having a sector address and sector data; and
combining the sector write with a time stamp to create a log entry.
3. The method of claim 2, wherein storing the write command combined with the time information comprises:
storing the log entry in a log file.
4. The method of claim 3, further comprising:
queuing the log entry before storing the log entry in the log file.
5. The method of claim 3, wherein storing the log entry in a log file comprises:
determining a sector address to be written to from a received log entry;
searching for log entries in the log file having an earlier time stamp which were written to the same sector address; and
deleting any log entries in the log file with an earlier time stamp which were written to the same sector address as the received log entry.
6. A computer-readable storage medium having computer-executable instructions for continuous data storage, comprising instructions for:
receiving a write command;
combining the received write command with time information, wherein the time information indicates when the write command was received; and
storing the write command combined with the time information.
7. The computer-readable storage medium of claim 6, wherein combining the received write command with time information comprises instructions for:
converting the received write command to a sector write having a sector address and sector data; and
combining the sector write with a time stamp to create a log entry.
8. The computer-readable storage medium of claim 7, wherein storing the write command combined with the time information comprises instructions for:
storing the log entry in a log file.
9. The computer-readable storage medium of claim 8, further comprising instructions for:
queuing the log entry before storing the log entry in the log file.
10. The computer-readable storage medium of claim 8, wherein storing the log entry in a log file comprises instructions for:
determining a sector address to be written to from a received log entry;
searching for log entries in the log file having an earlier time stamp which were written to the same sector address; and
deleting any log entries in the log file with an earlier time stamp which were written to the same sector address as the received log entry.
11. A method of continuous data storage, the method comprising:
receiving a write command;
converting the received write command to a sector write having a sector address and sector data; and
combining the sector write with a time stamp to create a log entry, wherein the time stamp indicates when the write command was received; and
storing the log entry in a log file.
12. The method of claim 11, further comprising:
queuing the log entry before storing the log entry in the log file.
13. The method of claim 11, wherein storing the log entry in a log file comprises:
determining a sector address to be written to from a received log entry;
searching for log entries in the log file having an earlier time stamp which were written to the same sector address; and
deleting any log entries in the log file with an earlier time stamp which were written to the same sector address as the received log entry.
US12/046,376 2000-06-06 2008-03-11 Data storage system and process Abandoned US20080162594A1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US12/046,376 US20080162594A1 (en) 2000-06-06 2008-03-11 Data storage system and process

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
US09/588,242 US7334098B1 (en) 2000-06-06 2000-06-06 Producing a mass storage backup using a log of write commands and time information
US11/271,104 US7343460B2 (en) 2000-06-06 2005-11-10 Data storage system and process
US12/046,376 US20080162594A1 (en) 2000-06-06 2008-03-11 Data storage system and process

Related Parent Applications (1)

Application Number Title Priority Date Filing Date
US11/271,104 Continuation US7343460B2 (en) 2000-06-06 2005-11-10 Data storage system and process

Publications (1)

Publication Number Publication Date
US20080162594A1 true US20080162594A1 (en) 2008-07-03

Family

ID=24353053

Family Applications (3)

Application Number Title Priority Date Filing Date
US09/588,242 Expired - Lifetime US7334098B1 (en) 2000-06-06 2000-06-06 Producing a mass storage backup using a log of write commands and time information
US11/271,104 Expired - Lifetime US7343460B2 (en) 2000-06-06 2005-11-10 Data storage system and process
US12/046,376 Abandoned US20080162594A1 (en) 2000-06-06 2008-03-11 Data storage system and process

Family Applications Before (2)

Application Number Title Priority Date Filing Date
US09/588,242 Expired - Lifetime US7334098B1 (en) 2000-06-06 2000-06-06 Producing a mass storage backup using a log of write commands and time information
US11/271,104 Expired - Lifetime US7343460B2 (en) 2000-06-06 2005-11-10 Data storage system and process

Country Status (6)

Country Link
US (3) US7334098B1 (en)
EP (1) EP1307876A4 (en)
JP (1) JP2003536157A (en)
KR (1) KR20030017532A (en)
AU (1) AU2001268262A1 (en)
WO (1) WO2001095315A2 (en)

Cited By (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20060041650A1 (en) * 2002-12-04 2006-02-23 Huawel Technologies Co., Ltd. Method and system for cluster managing of network facilities
US20080243952A1 (en) * 2007-03-28 2008-10-02 Erez Webman Group Stamping Style Asynchronous Replication Utilizing A Loosely-Accurate Global Clock
US20080243951A1 (en) * 2007-03-28 2008-10-02 Erez Webman Write ordering style asynchronous replication utilizing a loosely-accurate global clock
US20080263384A1 (en) * 2007-04-23 2008-10-23 Miller Steven C System and method for prioritization of clock rates in a multi-core processor
US8099571B1 (en) 2008-08-06 2012-01-17 Netapp, Inc. Logical block replication with deduplication
US8150800B2 (en) 2007-03-28 2012-04-03 Netapp, Inc. Advanced clock synchronization technique
US20120151133A1 (en) * 2010-12-13 2012-06-14 International Business Machines Corporation Saving log data using a disk system as primary cache and a tape library as secondary cache
US20120239615A1 (en) * 2011-03-16 2012-09-20 Kabushiki Kaisha Toshiba Video server and method for managing activity log
US8321380B1 (en) 2009-04-30 2012-11-27 Netapp, Inc. Unordered idempotent replication operations
US8473690B1 (en) 2009-10-30 2013-06-25 Netapp, Inc. Using logical block addresses with generation numbers as data fingerprints to provide cache coherency
US8655848B1 (en) 2009-04-30 2014-02-18 Netapp, Inc. Unordered idempotent logical replication operations
US8671072B1 (en) 2009-09-14 2014-03-11 Netapp, Inc. System and method for hijacking inodes based on replication operations received in an arbitrary order
US8799367B1 (en) 2009-10-30 2014-08-05 Netapp, Inc. Using logical block addresses with generation numbers as data fingerprints for network deduplication
US9158579B1 (en) 2008-11-10 2015-10-13 Netapp, Inc. System having operation queues corresponding to operation execution time

Families Citing this family (19)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7669189B1 (en) 2002-06-26 2010-02-23 Oracle International Corporation Monitoring memory accesses for computer programs
US7844577B2 (en) 2002-07-15 2010-11-30 Symantec Corporation System and method for maintaining a backup storage system for a computer system
JP2004259079A (en) * 2003-02-27 2004-09-16 Hitachi Ltd Data processing system
US7398422B2 (en) * 2003-06-26 2008-07-08 Hitachi, Ltd. Method and apparatus for data recovery system using storage based journaling
US20050010588A1 (en) * 2003-07-08 2005-01-13 Zalewski Stephen H. Method and apparatus for determining replication schema against logical data disruptions
US7171511B2 (en) * 2004-03-24 2007-01-30 Hitachi, Ltd. WORM proving storage system
JP2006244123A (en) * 2005-03-03 2006-09-14 Fujitsu Ltd Data storage system and data storage control device
US7506116B2 (en) * 2005-07-19 2009-03-17 International Business Machines Corporation Maintaining and using information on updates to a data group after a logical copy is made of the data group
US7873601B1 (en) * 2006-06-29 2011-01-18 Emc Corporation Backup of incremental metadata in block based backup systems
US8151060B2 (en) * 2006-11-28 2012-04-03 Hitachi, Ltd. Semiconductor memory system having a snapshot function
EP2220559A4 (en) * 2007-11-07 2014-08-06 Avocent Corp System and method for managing virtual hard drives in a virtual machine environment
US8046380B2 (en) * 2008-04-08 2011-10-25 Quantum Corporation Data storage system
US8516450B2 (en) * 2010-03-19 2013-08-20 Oracle International Corporation Detecting real-time invalid memory references
US8224781B2 (en) * 2010-05-14 2012-07-17 Lsi Corporation Data protection in a data storage system
US9836370B2 (en) * 2010-11-18 2017-12-05 Lenovo Enterprise Solutions (Singapore) Pte. Ltd. Backup memory administration using an active memory device and a backup memory device
CN103685350B (en) * 2012-09-04 2016-12-21 阿里巴巴集团控股有限公司 The synchronous method of storage system and relevant equipment
US8977596B2 (en) * 2012-12-21 2015-03-10 Zetta Inc. Back up using locally distributed change detection
US10552043B2 (en) * 2014-09-09 2020-02-04 Toshiba Memory Corporation Memory system
JP2018160156A (en) * 2017-03-23 2018-10-11 東芝メモリ株式会社 Memory system

Citations (24)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5008786A (en) * 1985-09-11 1991-04-16 Texas Instruments Incorporated Recoverable virtual memory having persistant objects
US5086502A (en) * 1989-07-11 1992-02-04 Intelligence Quotient International Limited Method of operating a data processing system
US5239640A (en) * 1991-02-01 1993-08-24 International Business Machines Corporation Data storage system and method including data and checksum write staging storage
US5357622A (en) * 1990-09-27 1994-10-18 Dell U.S.A., L.P. Apparatus for queing and storing data writes into valid word patterns
US5403639A (en) * 1992-09-02 1995-04-04 Storage Technology Corporation File server having snapshot application data groups
US5479654A (en) * 1990-04-26 1995-12-26 Squibb Data Systems, Inc. Apparatus and method for reconstructing a file from a difference signature and an original file
US5555371A (en) * 1992-12-17 1996-09-10 International Business Machines Corporation Data backup copying with delayed directory updating and reduced numbers of DASD accesses at a back up site using a log structured array data storage
US5572672A (en) * 1991-06-10 1996-11-05 International Business Machines Corporation Method and apparatus for monitoring data processing system resources in real-time
US5764903A (en) * 1994-09-26 1998-06-09 Acer America Corporation High availability network disk mirroring system
US5819020A (en) * 1995-10-16 1998-10-06 Network Specialists, Inc. Real time backup system
US5930497A (en) * 1997-12-11 1999-07-27 International Business Machines Corporation Method and means for generation of realistic access patterns in storage subsystem benchmarking and other tests
US5943672A (en) * 1996-02-15 1999-08-24 Hitachi, Ltd. Network system
US6158019A (en) * 1996-12-15 2000-12-05 Delta-Tek Research, Inc. System and apparatus for merging a write event journal and an original storage to produce an updated storage using an event map
US6170063B1 (en) * 1998-03-07 2001-01-02 Hewlett-Packard Company Method for performing atomic, concurrent read and write operations on multiple storage devices
US6182198B1 (en) * 1998-06-05 2001-01-30 International Business Machines Corporation Method and apparatus for providing a disc drive snapshot backup while allowing normal drive read, write, and buffering operations
US6202136B1 (en) * 1994-12-15 2001-03-13 Bmc Software, Inc. Method of creating an internally consistent copy of an actively updated data set without specialized caching hardware
US6205450B1 (en) * 1997-10-31 2001-03-20 Kabushiki Kaisha Toshiba Computer system capable of restarting system using disk image of arbitrary snapshot
US6335843B2 (en) * 1997-05-23 2002-01-01 Sony Corporation Recording medium driving device
US6405329B1 (en) * 1999-07-27 2002-06-11 Dell Usa, L.P. Method and apparatus for HDD time stamp benchmark and installation identification
US6519568B1 (en) * 1999-06-15 2003-02-11 Schlumberger Technology Corporation System and method for electronic data delivery
US6591342B1 (en) * 1999-12-14 2003-07-08 Intel Corporation Memory disambiguation for large instruction windows
US6615253B1 (en) * 1999-08-31 2003-09-02 Accenture Llp Efficient server side data retrieval for execution of client side applications
US6763440B1 (en) * 2000-06-02 2004-07-13 Sun Microsystems, Inc. Garbage collection using nursery regions for new objects in a virtual heap
US6957237B1 (en) * 2000-06-02 2005-10-18 Sun Microsystems, Inc. Database store for a virtual heap

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP3490266B2 (en) * 1997-09-26 2004-01-26 株式会社日立製作所 Backup system and backup method using disk system and magnetic tape library device
JPH11120057A (en) * 1997-10-17 1999-04-30 Hitachi Ltd File backup method
JP2000137636A (en) * 1998-10-30 2000-05-16 Hitachi Ltd Backup device
JP2003503792A (en) 1999-06-30 2003-01-28 マイクロソフト コーポレイション Recover your computer to a previous state

Patent Citations (25)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5008786A (en) * 1985-09-11 1991-04-16 Texas Instruments Incorporated Recoverable virtual memory having persistant objects
US5086502A (en) * 1989-07-11 1992-02-04 Intelligence Quotient International Limited Method of operating a data processing system
US5479654A (en) * 1990-04-26 1995-12-26 Squibb Data Systems, Inc. Apparatus and method for reconstructing a file from a difference signature and an original file
US5357622A (en) * 1990-09-27 1994-10-18 Dell U.S.A., L.P. Apparatus for queing and storing data writes into valid word patterns
US5239640A (en) * 1991-02-01 1993-08-24 International Business Machines Corporation Data storage system and method including data and checksum write staging storage
US5572672A (en) * 1991-06-10 1996-11-05 International Business Machines Corporation Method and apparatus for monitoring data processing system resources in real-time
US5403639A (en) * 1992-09-02 1995-04-04 Storage Technology Corporation File server having snapshot application data groups
US5555371A (en) * 1992-12-17 1996-09-10 International Business Machines Corporation Data backup copying with delayed directory updating and reduced numbers of DASD accesses at a back up site using a log structured array data storage
US5764903A (en) * 1994-09-26 1998-06-09 Acer America Corporation High availability network disk mirroring system
US6202136B1 (en) * 1994-12-15 2001-03-13 Bmc Software, Inc. Method of creating an internally consistent copy of an actively updated data set without specialized caching hardware
US5819020A (en) * 1995-10-16 1998-10-06 Network Specialists, Inc. Real time backup system
US5943672A (en) * 1996-02-15 1999-08-24 Hitachi, Ltd. Network system
US6158019A (en) * 1996-12-15 2000-12-05 Delta-Tek Research, Inc. System and apparatus for merging a write event journal and an original storage to produce an updated storage using an event map
US6301677B1 (en) * 1996-12-15 2001-10-09 Delta-Tek Research, Inc. System and apparatus for merging a write event journal and an original storage to produce an updated storage using an event map
US6335843B2 (en) * 1997-05-23 2002-01-01 Sony Corporation Recording medium driving device
US6205450B1 (en) * 1997-10-31 2001-03-20 Kabushiki Kaisha Toshiba Computer system capable of restarting system using disk image of arbitrary snapshot
US5930497A (en) * 1997-12-11 1999-07-27 International Business Machines Corporation Method and means for generation of realistic access patterns in storage subsystem benchmarking and other tests
US6170063B1 (en) * 1998-03-07 2001-01-02 Hewlett-Packard Company Method for performing atomic, concurrent read and write operations on multiple storage devices
US6182198B1 (en) * 1998-06-05 2001-01-30 International Business Machines Corporation Method and apparatus for providing a disc drive snapshot backup while allowing normal drive read, write, and buffering operations
US6519568B1 (en) * 1999-06-15 2003-02-11 Schlumberger Technology Corporation System and method for electronic data delivery
US6405329B1 (en) * 1999-07-27 2002-06-11 Dell Usa, L.P. Method and apparatus for HDD time stamp benchmark and installation identification
US6615253B1 (en) * 1999-08-31 2003-09-02 Accenture Llp Efficient server side data retrieval for execution of client side applications
US6591342B1 (en) * 1999-12-14 2003-07-08 Intel Corporation Memory disambiguation for large instruction windows
US6763440B1 (en) * 2000-06-02 2004-07-13 Sun Microsystems, Inc. Garbage collection using nursery regions for new objects in a virtual heap
US6957237B1 (en) * 2000-06-02 2005-10-18 Sun Microsystems, Inc. Database store for a virtual heap

Cited By (33)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7904535B2 (en) * 2002-12-04 2011-03-08 Huawei Technologies Co., Ltd. Method of cluster management of network devices and apparatus thereof
US20060041650A1 (en) * 2002-12-04 2006-02-23 Huawel Technologies Co., Ltd. Method and system for cluster managing of network facilities
US8150800B2 (en) 2007-03-28 2012-04-03 Netapp, Inc. Advanced clock synchronization technique
US8290899B2 (en) 2007-03-28 2012-10-16 Netapp, Inc. Group stamping style asynchronous replication utilizing a loosely-accurate global clock
US20080243951A1 (en) * 2007-03-28 2008-10-02 Erez Webman Write ordering style asynchronous replication utilizing a loosely-accurate global clock
US7925629B2 (en) * 2007-03-28 2011-04-12 Netapp, Inc. Write ordering style asynchronous replication utilizing a loosely-accurate global clock
US20080243952A1 (en) * 2007-03-28 2008-10-02 Erez Webman Group Stamping Style Asynchronous Replication Utilizing A Loosely-Accurate Global Clock
US8015427B2 (en) 2007-04-23 2011-09-06 Netapp, Inc. System and method for prioritization of clock rates in a multi-core processor
US20080263384A1 (en) * 2007-04-23 2008-10-23 Miller Steven C System and method for prioritization of clock rates in a multi-core processor
US8099571B1 (en) 2008-08-06 2012-01-17 Netapp, Inc. Logical block replication with deduplication
US9158579B1 (en) 2008-11-10 2015-10-13 Netapp, Inc. System having operation queues corresponding to operation execution time
US9430278B2 (en) 2008-11-10 2016-08-30 Netapp, Inc. System having operation queues corresponding to operation execution time
US10860542B2 (en) 2009-04-30 2020-12-08 Netapp Inc. Unordered idempotent logical replication operations
US11880343B2 (en) 2009-04-30 2024-01-23 Netapp, Inc. Unordered idempotent logical replication operations
US8321380B1 (en) 2009-04-30 2012-11-27 Netapp, Inc. Unordered idempotent replication operations
US9659026B2 (en) 2009-04-30 2017-05-23 Netapp, Inc. Unordered idempotent logical replication operations
US8655848B1 (en) 2009-04-30 2014-02-18 Netapp, Inc. Unordered idempotent logical replication operations
US10852958B2 (en) 2009-09-14 2020-12-01 Netapp Inc. System and method for hijacking inodes based on replication operations received in an arbitrary order
US8671072B1 (en) 2009-09-14 2014-03-11 Netapp, Inc. System and method for hijacking inodes based on replication operations received in an arbitrary order
US9858001B2 (en) 2009-09-14 2018-01-02 Netapp, Inc. System and method for hijacking inodes based on replication operations received in an arbitrary order
US8473690B1 (en) 2009-10-30 2013-06-25 Netapp, Inc. Using logical block addresses with generation numbers as data fingerprints to provide cache coherency
US8799367B1 (en) 2009-10-30 2014-08-05 Netapp, Inc. Using logical block addresses with generation numbers as data fingerprints for network deduplication
US9043430B2 (en) 2009-10-30 2015-05-26 Netapp, Inc. Using logical block addresses with generation numbers as data fingerprints for network deduplication
US9372794B2 (en) 2009-10-30 2016-06-21 Netapp, Inc. Using logical block addresses with generation numbers as data fingerprints to provide cache coherency
US8543760B2 (en) * 2010-12-13 2013-09-24 International Business Machines Corporation Saving log data using a disk system as primary cache and a tape library as secondary cache
US9286000B2 (en) 2010-12-13 2016-03-15 International Business Machines Corporation Saving log data using a disk system as primary cache and a tape library as secondary cache
US8949524B2 (en) 2010-12-13 2015-02-03 International Business Machines Corporation Saving log data using a disk system as primary cache and a tape library as secondary cache
US9547452B2 (en) 2010-12-13 2017-01-17 International Business Machines Corporation Saving log data using a disk system as primary cache and a tape library as secondary cache
US8458397B2 (en) * 2010-12-13 2013-06-04 International Business Machines Corporation Saving log data using a disk system as primary cache and a tape library as secondary cache
US20120272005A1 (en) * 2010-12-13 2012-10-25 International Business Machines Corporation Saving log data using a disk system as primary cache and a tape library as secondary cache
US20120151133A1 (en) * 2010-12-13 2012-06-14 International Business Machines Corporation Saving log data using a disk system as primary cache and a tape library as secondary cache
US8788456B2 (en) * 2011-03-16 2014-07-22 Kabushiki Kaisha Toshiba Video server and method for managing activity log
US20120239615A1 (en) * 2011-03-16 2012-09-20 Kabushiki Kaisha Toshiba Video server and method for managing activity log

Also Published As

Publication number Publication date
US20060059322A1 (en) 2006-03-16
WO2001095315A3 (en) 2002-03-21
EP1307876A4 (en) 2007-03-07
US7334098B1 (en) 2008-02-19
KR20030017532A (en) 2003-03-03
EP1307876A2 (en) 2003-05-07
JP2003536157A (en) 2003-12-02
AU2001268262A1 (en) 2001-12-17
US7343460B2 (en) 2008-03-11
WO2001095315A2 (en) 2001-12-13

Similar Documents

Publication Publication Date Title
US7343460B2 (en) Data storage system and process
US6871271B2 (en) Incrementally restoring a mass storage device to a prior state
US6269381B1 (en) Method and apparatus for backing up data before updating the data and for restoring from the backups
US7783848B2 (en) Method and apparatus for backup and recovery using storage based journaling
US6366986B1 (en) Method and apparatus for differential backup in a computer storage system
US7660953B2 (en) Method and system for mirroring and archiving mass storage
US6141773A (en) Method and apparatus for undoing changes to computer memory
US7627727B1 (en) Incremental backup of a data volume
US7167880B2 (en) Method and apparatus for avoiding journal overflow on backup and recovery system using storage based journaling
US7350043B2 (en) Continuous data protection of block-level volumes
US8214685B2 (en) Recovering from a backup copy of data in a multi-site storage system
US7266654B2 (en) Storage system, server apparatus, and method for creating a plurality of snapshots
US7979649B1 (en) Method and apparatus for implementing a storage lifecycle policy of a snapshot image
US20050108302A1 (en) Recovery of data on a primary data volume
AU1114695A (en) A method of operating a computer system
JPH0991099A (en) Disk update log recording system
US8151069B1 (en) Multiprotection for snapsnots
US6978354B1 (en) Method for creating a virtual data copy of a volume being restored
US9063898B1 (en) Method of restoring backup data
AU2002246856A1 (en) Restoring a mass storage device to a prior state in response to processing information

Legal Events

Date Code Title Description
AS Assignment

Owner name: QUANTUM CORPORATION, CALIFORNIA

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:SANLIGHT, INC.;REEL/FRAME:021123/0425

Effective date: 20030805

AS Assignment

Owner name: WELLS FARGO CAPITAL FINANCE, LLC, AS AGENT, CALIFO

Free format text: SECURITY AGREEMENT;ASSIGNOR:QUANTUM CORPORATION;REEL/FRAME:027967/0914

Effective date: 20120329

STCB Information on status: application discontinuation

Free format text: ABANDONED -- FAILURE TO RESPOND TO AN OFFICE ACTION

AS Assignment

Owner name: QUANTUM CORPORATION, CALIFORNIA

Free format text: RELEASE BY SECURED PARTY;ASSIGNOR:WELLS FARGO CAPITAL FINANCE, LLC, AS AGENT;REEL/FRAME:040474/0079

Effective date: 20161021