WO1993022719A1 - Disk storage system - Google Patents
Disk storage system Download PDFInfo
- Publication number
- WO1993022719A1 WO1993022719A1 PCT/US1993/003779 US9303779W WO9322719A1 WO 1993022719 A1 WO1993022719 A1 WO 1993022719A1 US 9303779 W US9303779 W US 9303779W WO 9322719 A1 WO9322719 A1 WO 9322719A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- index
- physical address
- entry
- group
- segments
- Prior art date
Links
- 230000015654 memory Effects 0.000 claims abstract description 33
- 230000004044 response Effects 0.000 claims abstract description 18
- 238000013500 data storage Methods 0.000 claims abstract description 5
- 108090000248 Deleted entry Proteins 0.000 claims description 12
- 238000004891 communication Methods 0.000 claims description 9
- 238000012217 deletion Methods 0.000 claims description 7
- 230000037430 deletion Effects 0.000 claims description 7
- 238000012546 transfer Methods 0.000 claims description 2
- 208000000044 Amnesia Diseases 0.000 abstract description 3
- 208000026139 Memory disease Diseases 0.000 abstract description 3
- 230000006984 memory degeneration Effects 0.000 abstract description 3
- 208000023060 memory loss Diseases 0.000 abstract description 3
- 238000011084 recovery Methods 0.000 description 6
- 230000004888 barrier function Effects 0.000 description 4
- 238000003780 insertion Methods 0.000 description 4
- 230000037431 insertion Effects 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000000034 method Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G11—INFORMATION STORAGE
- G11B—INFORMATION STORAGE BASED ON RELATIVE MOVEMENT BETWEEN RECORD CARRIER AND TRANSDUCER
- G11B27/00—Editing; Indexing; Addressing; Timing or synchronising; Monitoring; Measuring tape travel
- G11B27/10—Indexing; Addressing; Timing or synchronising; Measuring tape travel
- G11B27/11—Indexing; Addressing; Timing or synchronising; Measuring tape travel by using information not detectable on the record carrier
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/07—Responding to the occurrence of a fault, e.g. fault tolerance
- G06F11/14—Error detection or correction of the data by redundancy in operation
- G06F11/1402—Saving, restoring, recovering or retrying
- G06F11/1446—Point-in-time backing up or restoration of persistent data
- G06F11/1448—Management of the data involved in backup or backup restore
- G06F11/1451—Management of the data involved in backup or backup restore by selection of backup contents
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
-
- G—PHYSICS
- G11—INFORMATION STORAGE
- G11B—INFORMATION STORAGE BASED ON RELATIVE MOVEMENT BETWEEN RECORD CARRIER AND TRANSDUCER
- G11B20/00—Signal processing not specific to the method of recording or reproducing; Circuits therefor
- G11B20/10—Digital recording or reproducing
-
- G—PHYSICS
- G11—INFORMATION STORAGE
- G11B—INFORMATION STORAGE BASED ON RELATIVE MOVEMENT BETWEEN RECORD CARRIER AND TRANSDUCER
- G11B20/00—Signal processing not specific to the method of recording or reproducing; Circuits therefor
- G11B20/10—Digital recording or reproducing
- G11B20/12—Formatting, e.g. arrangement of data block or words on the record carriers
- G11B20/1217—Formatting, e.g. arrangement of data block or words on the record carriers on discs
- G11B20/1252—Formatting, e.g. arrangement of data block or words on the record carriers on discs for discontinuous data, e.g. digital information signals, computer programme data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F2003/0697—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers device management, e.g. handlers, drivers, I/O schedulers
-
- G—PHYSICS
- G11—INFORMATION STORAGE
- G11B—INFORMATION STORAGE BASED ON RELATIVE MOVEMENT BETWEEN RECORD CARRIER AND TRANSDUCER
- G11B20/00—Signal processing not specific to the method of recording or reproducing; Circuits therefor
- G11B20/10—Digital recording or reproducing
- G11B20/12—Formatting, e.g. arrangement of data block or words on the record carriers
- G11B2020/1264—Formatting, e.g. arrangement of data block or words on the record carriers wherein the formatting concerns a specific kind of data
- G11B2020/1265—Control data, system data or management information, i.e. data used to access or process user data
- G11B2020/1281—Servo information
- G11B2020/1282—Servo information in embedded servo fields
Definitions
- the present invention relates generally to electronic computers and more particularly to systems for storing data in non-volatile storage such as magnetic media.
- the task of organizing data on a storage medium such as a rotating magnetic disk has traditionally been performed by the file system of a host processor.
- a file system which may be part of an operating system, a database system, or some other application, has more information on the global system state than does a local disk controller.
- the ability to use such global information offers a theoretical advantage, and for this reason it has generally been believed that the host processor can do a better job of organizing the data on the disk than can the local disk controller.
- a small number of segments on the disk typically not more than about five percent, are reserved as free segments. These free segments are scattered about the surface of the disk.
- the local disk controller selects the nearest free segment to the current head position and writes the data there. This results in very fast writes because there is usually a free segment within a fraction of a revolution of the disk. Writes can be performed in the order in which received without any performance penalty. Also, an update never overwrites the old copy of the data.
- An “indirection table” is kept in memory to keep track of where on the disk each block of data is written.
- a “free map” is used to find free segments efficiently.
- reverse indices are written in the segments on the disk. The reverse indices make it possible to rebuild the indirection table if the one in memory is lost, although this is time-consuming because the entire disk must be read in order to recover all the information. This system significantly improves the performance of disk memory systems.
- the present invention provides an electronic data storage system in which the time required to write data in a multiple-spindle disk drive system is greatly reduced and the recovery speed is greatly increased when compared to other disk drive systems.
- the present invention also facilitates provisional storage operations that are not visible outside a defined "rollback group”.
- a host computer provides the disk storage system with a logical address and a block of data for storage at that logical address.
- the disk controller selects a disk unit and a segment for the data, according to am algorithm such as which segment can be accessed the fastest, and writes the data there.
- the controller maintains an index in memory (such as RAM) to correlate logical addresses with physical addresses.
- the index is maintained partly as a global index and partly as one or more dynamically- created rollback group indices.
- the disk system controller maintains these indices along with a free list indicating which segments are available for storage of data and an obsolete list indicating which storage segments contain obsolete data but are not yet ready to be released to the free list.
- These indices and lists are maintained in volatile memory but are readily recoverable if there is a failure of the memory. Recovery of these lists and indices can be done without having to read the entire disk. A small number of the segments on the disk are reserved as "checkpoint segments"; these segments contain enough information to reconstruct the indices without having to read the entire disk.
- FIGURE 1 is a block diagram of a preferred embodiment of a disk storage system according to the invention.
- FIG. 2 is a block diagram of a disk unit of the kind shown as a block in FIG. 1, and
- FIG. 3 is a close-up view of a portion of the disk unit shown in FIG. 2.
- an electronic data storage system 13 includes a central controller 15, a memory 17 and a plurality of storage units 21 and 23.
- the controller 15 communicates with the memory 17 through a communication channel 19 and with the storage units 21 and 23 through a communication channel 25.
- the controller 15 receives commands from a host processor 11 through a communication channel 27, and data is exchanged between the controller 15 and the host processor 11 through a communication channel 29.
- the storage unit 21 is illustrated in greater detail in FIG. 2.
- a unit controller 31 is in communication with the central controller 15 through the channel 25.
- a unit memory 33 is in communication with the controller 31 through a communication channel 35.
- the controller 31 is in communication with a disk servo control circuit 37 through a control channel 39 and a data channel 41.
- the servo control circuit 37 controls electromechanical operation of a plurality of magnetic disks 104 and a plurality of read-write heads which are carried by actuator arms 106 and which at any given time are positioned over storage areas 123 on the various disks 104.
- a close-up view of a region 47 of one of the disks 104 is shown in FIG. 3, including a plurality of other nearby storage areas 105 on the disk 104.
- a plurality of control signals and information are managed by the central controller 15 and stored in the central memory 17.
- a global index includes entries each of which gives a logical address and a corresponding physical address (unit and segment identifiers) for data blocks that are stored on the disks.
- Some blocks of data are assigned to rollback groups.
- a group index is created dynamically for each designated rollback group.
- Each index includes entries each of which gives a logical address and a corresponding physical address for a data block that is stored on the disks and that is assigned to the particular rollback group which corresponds to that index.
- a block of data that is a member of one group may be referenced, not only by an entry in the index which corresponds with the group to which the block belongs, but also by an entry in the global index or in one or more other group indices.
- Each entry in a group index carries a status indicator that designates its status as being either "write", "no-write” or "delete".
- a "reference list" is maintained in memory by the controller.
- the reference list gives a reference count for each physical address that appears in any of the indices.
- the reference count for a given physical address indicates the number of times that that physical address is listed in all the indices.
- An "obsolete list” is also maintained by the controller. This list includes physical addresses for segments that contain obsolete data but that have not yet been released for the entry of new data.
- An “operations log” is maintained in memory and includes a record of all create group, copy, delete, commit, abort and barrier commands that have been issued subsequent to the most recent of any sync command and checkpoint operation.
- a “checkpoint log” lists all entries in and deletions from all the indices subsequent to the most recent of any sync command and checkpoint operation.
- checkpoint sections The portion of memory that contains the global and group indices is divided into a plurality of k "checkpoint sections", where _ is an integer.
- k an integer.
- k+1 a total of k+1 "checkpoint segments” are reserved. These may be all in one storage unit such as the unit 21 or they may be distributed among a plurality of the units as is convenient.
- checkpoint sections in memory, checkpoint segments on disk, and operations log are used for recovery if there is a memory loss, as will be described in more detail presently.
- the unit memory of each storage unit includes a free map which gives a list of the available storage segments in that unit.
- the various controller functions may be performed by one microprocessor or other control device, or the controller functions may be distributed among a central controller and a plurality of disk unit controllers as shown.
- Various commands are issued by the host processor 11.
- the host processor may be a general-purpose computer, a network server, or some other device that requires a data storage system.
- the storage units contemplated by the invention are magnetic disk storage units as described and illustrated. However, it will be apparent that the principles of the invention are equally applicable to other types of storage devices, such as optical media, bubble memories, and so on.
- the storage system receives various commands from the host processor and performs various actions in response to those commands, as will now be described in more detail.
- This command includes a logical address, one block of data to be written by itself or a plurality of blocks to be written as a multi-block write, and optionally a group identifier.
- the central disk controller 15 performs a series of tasks for each block to be written. First the controller selects a storage unit such as the disk unit 21 or the disk unit 23 according to a criterion such as which of the units has the most free space. A better criterion will usually be an algorithm for distributing writes equally among all the storage units.
- the controller selects a segment from the free list for the selected storage unit.
- One way of making this selection is to select that segment which can be reached in minimum time.
- this time includes seek time (the time required to move the magnetic recording head carried by the actuator arm 106 into position) , rotational delay time (the time required for the desired segment 123 to rotate into position) , and the time to actually transfer the data.
- seek time the time required to move the magnetic recording head carried by the actuator arm 106 into position
- rotational delay time the time required for the desired segment 123 to rotate into position
- the selection process which is dynamic because the heads and disks are in continuous or nearly-continuous motion, may be done by the central disk controller 15 or may be delegated to the disk unit controller 31 as desired.
- the controller appends a tag to the block.
- the tag includes the logical address and the next consecutive sequence number from a sequential set of such numbers.
- the tag also includes an end flag unless the block is a beginning or intermediate block in a multi-block write.
- the group identifier is also included in the tag.
- the controller records the block and its tag at the selected physical address (segment and storage unit) ; deletes the segment "from the free map; enters the logical and physical addresses in the group index with a write status indicator, or if there is no group identifier then in the global index; and increments the reference count for the physical address.
- the controller deletes the previous entry and decrement the reference count for the previous physical address.
- the controller inserts the previous entry into any of the group indices which do not already contain the address as "no-write" entries, and increments the reference count for the previous physical address once for each index into which the previous entry is inserted. If the count decrements to zero, which indicates that the physical address is not on any index, the physical address is moved to the obsolete list.
- controller enters all insertions and deletions in the checkpoint log.
- the "create rollback group” includes a group identifier for the new rollback group.
- the central disk controller 15 creates a group index for the new rollback group and assigns the next sequence number and enters the command in the operations log.
- the "read” command includes a logical address and optionally a group identifier.
- the central controller 15 searches the group index to find the physical address of the data block to be read. If not found, or if there is no group identifier, the controller searches the global index to find the physical address. The physical address is used to retrieve the data block from disk, and then the data block is sent to the host processor.
- the "delete” command includes a logical address and optionally a group identifier.
- the controller 15 does the following:
- the controller changes the entry to a delete entry and decrement the reference count for the physical address. If there is a group identifier and the block is not listed in the group index, the controller enters the logical address of the block in the group index as a delete entry.
- the controller deletes the entry from the global index and decrements the reference count for the physical address.
- the controller deletes the previous entry, decrements the reference count for the previous physical address, inserts the previous entry in all the other group indices which do not already contain that address as "no-write" entries, and increments the reference count for the previous physical address once for each index into which the previous entry is inserted. If the reference count for a physical address goes to zero, that address i's entered in the obsolete list.
- the controller assigns the next sequence number, enters the command in the operations log, and enters all insertions and deletions in the checkpoint log.
- the "barrier" command is issued by the host any time it wants to preserve a certain state of the various data items as a valid state to which it can return. It may identify a rollback group if its effect is to be limited to one group.
- the controller assigns the next sequence number and enters the command in the operations log.
- the "abort" command identifies a rollback group to be aborted.
- the controller decrements the reference count for the physical address of each write entry and each no-write entry in the group index, deletes the group index, assigns the next sequence number and enter the command in the operations log, and enters each deletion in the checkpoint log.
- the "commit" command identifies a rollback group to be committed.
- the controller does the following:
- the controller moves the entry from the group index to the global index and, if the same logical address appears together with a previous physical address in a previous entry in the global index, deletes the previous entry, decrements the reference count for the previous physical address, inserts the previous entry in all the other group indices which do not already contain that address as no-write entries, and increments the reference count for the previous physical address once for each index into which the previous entry is inserted.
- the controller decrements the reference count for the physical address. If the entry is a no-write entry, the controller decrements the reference count for the physical address. If the entry is a delete entry, the controller deletes any entry having the same logical address from the global index, decrements the reference count for the physical address of the deleted entry, inserts the previous entry in all the other group indices which do not already contain that address as no-write entries, and increments the reference count for the previous physical address once for each index into which the previous entry is inserted.
- the controller deletes the group index, assigns the next sequence number, enters the command in the operations log, and enters all insertions and deletions in the checkpoint log.
- This command includes a logical address of a block to be copied and a new logical address into which to copy the block.
- Group identifiers are optionally provided for one or both of these addresses.
- the controller looks up the physical address"of the block to be copied. Then it enters the new logical address as a write entry in the identified group index, or if none then in the global index, together with the physical address of the block being copied, and increments the reference count for the physical address.
- the controller deletes the previous entry and decrements the reference count for the previous physical address, and, if the previous entry was in the global index, inserts the previous entry into all the group indices which do not already contain the address as no-write entries, and increments the reference count for the previous physical address once for each index into which the previous entry is inserted.
- the controller assigns the next sequence number and enter the command in the operations log and enters all insertions and deletions in the checkpoint log.
- This command is issued by the host process any time it wants to ensure that commands which have previously been sent to the controller have been completed.
- the command optionally includes a group identifier that limits its scope to the identified group.
- the controller finishes any pending write commands that were issued before the latest barrier sent to the group. Any pending global write commands are finished, including ones that were placed there before a "commit" command.
- the operations log and the next sequence number are written to an available segment, and the physical address to which the log was written is added to the obsolete list.
- the operations log is only needed to recover a record of any operations subsequent to the most recent checkpoint operation. Therefore, its physical address can immediately be placed in the obsolete list.
- the controller If the operations log reaches a predetermined number of entries or if a sync or checkpoint command is issued, the controller writes the operations log together with the next sequence number to an available segment, adds the physical address to which the log was written to the obsolete list, and clears the operations log in memory.
- the controller If there is a power failure or some other event that wipes out the memory, and perhaps also interrupts a write in progress, the controller reads the k+1 checkpoint segments to get the k ones that are both most recent and valid. The information recovered from these segments is used in order, starting with the oldest, to reconstruct the global and group indices up through the most recent checkpoint operation.
- the controller reads all segments not listed in the reconstructed Indices and lists all the segments having sequence numbers older than the most recent checkpoint segment in the free maps. Then it arranges the remaining segments in order of increasing sequence numbers, recovers all data blocks and operations logs from the oldest through the most recent having an end flag until there is a gap in sequence numbers, and uses these to finish reconstructing the indices. Next any remaining segments are listed in the Free Maps. Finally, the sequence numbers are incremented to a number greater than that of the segment having the largest one.
- a "delete" status of an entry in a group index may be indicated by a flag or by the absence of a physical address or by a special nonexistent physical address code.
- the end of a block may be indicated by a flag or by some other form of encoding.
- the presence of a sequence number may be a sufficient indicator of the end of a block to confirm that the block has been completely written prior to any failure.
Abstract
An electronic data storage system (13) including a memory (17), a plurality of magnetic disk units (21, 23), and a controller (15). The memory contains an index cross-referencing logical address with physical addresses, an obsolete list and a free list. In response to a 'write' command, the controller selects a physical address according to which segment can be used the most quickly, appends a tag to the data to be written, and writes the data to the selected segment. Appropriate entries are made in the index and the free list. The system recovers from memory loss by using a checkpoint log and a set of checkpoint segments on the disk that together contain backups of the index and other critical information needed to restore the system. Group indices are used for roll-back groups; operations on data in a group are invisible outside the group until after a 'commit' command is issued.
Description
DISK STORAGE SYSTEM
BACKGROUND OF THE INVENTION
The present invention relates generally to electronic computers and more particularly to systems for storing data in non-volatile storage such as magnetic media.
The task of organizing data on a storage medium such as a rotating magnetic disk has traditionally been performed by the file system of a host processor. Such a file system, which may be part of an operating system, a database system, or some other application, has more information on the global system state than does a local disk controller. The ability to use such global information offers a theoretical advantage, and for this reason it has generally been believed that the host processor can do a better job of organizing the data on the disk than can the local disk controller.
In practice, detailed knowledge of disk performance characteristics, disk geometry and the like are readily available at the disk-controller level but are not conveniently utilized by the host processor. A system that could take advantage of this type of detailed knowledge would have the potential to provide greatly improved disk performance. Such a system has been proposed in the context of a single spindle disk drive system. This system relies on the disk controller rather than the host processor to organize data on the disk, but its ability to use the detailed knowledge of the disks results in significantly improved performance.
In the proposed system, a small number of segments on the disk, typically not more than about five percent, are reserved as free segments. These free segments are
scattered about the surface of the disk. When a block of data is to be written on the disk, the local disk controller selects the nearest free segment to the current head position and writes the data there. This results in very fast writes because there is usually a free segment within a fraction of a revolution of the disk. Writes can be performed in the order in which received without any performance penalty. Also, an update never overwrites the old copy of the data.
An "indirection table" is kept in memory to keep track of where on the disk each block of data is written. A "free map" is used to find free segments efficiently. To allow recovery of the indirection table in case of memory loss, for example due to a power failure, reverse indices are written in the segments on the disk. The reverse indices make it possible to rebuild the indirection table if the one in memory is lost, although this is time-consuming because the entire disk must be read in order to recover all the information. This system significantly improves the performance of disk memory systems.
Despite the improved performance offered by the above-described system, there remains a need for a way to improve the performance of a disk system having a plurality of spindles and to reduce the time reguired for recovery if system information such as the indirection table is lost from volatile memory.
SUMMARY OP THE INVENTION
The present invention provides an electronic data storage system in which the time required to write data in a multiple-spindle disk drive system is greatly reduced and the recovery speed is greatly increased when compared to other disk drive systems. The present
invention also facilitates provisional storage operations that are not visible outside a defined "rollback group".
Briefly, a host computer provides the disk storage system with a logical address and a block of data for storage at that logical address. The disk controller selects a disk unit and a segment for the data, according to am algorithm such as which segment can be accessed the fastest, and writes the data there. The controller maintains an index in memory (such as RAM) to correlate logical addresses with physical addresses.
Preferably the index is maintained partly as a global index and partly as one or more dynamically- created rollback group indices. The disk system controller maintains these indices along with a free list indicating which segments are available for storage of data and an obsolete list indicating which storage segments contain obsolete data but are not yet ready to be released to the free list. These indices and lists are maintained in volatile memory but are readily recoverable if there is a failure of the memory. Recovery of these lists and indices can be done without having to read the entire disk. A small number of the segments on the disk are reserved as "checkpoint segments"; these segments contain enough information to reconstruct the indices without having to read the entire disk.
Other aspects and advantages of the invention will become apparent from the following detailed description, taken in conjunction with the accompanying drawings, illustrating by way of example the principles of the invention.
BRIEF DESCRIPTION OF THE DRAWINGS
FIGURE 1 is a block diagram of a preferred embodiment of a disk storage system according to the invention,
FIG. 2 is a block diagram of a disk unit of the kind shown as a block in FIG. 1, and
FIG. 3 is a close-up view of a portion of the disk unit shown in FIG. 2.
DESCRIPTION OF THE PREFERRED EMBODIMENT
As shown in FIG. 1, in one embodiment an electronic data storage system 13 according to the invention includes a central controller 15, a memory 17 and a plurality of storage units 21 and 23. The controller 15 communicates with the memory 17 through a communication channel 19 and with the storage units 21 and 23 through a communication channel 25. The controller 15 receives commands from a host processor 11 through a communication channel 27, and data is exchanged between the controller 15 and the host processor 11 through a communication channel 29.
The storage unit 21 is illustrated in greater detail in FIG. 2. A unit controller 31 is in communication with the central controller 15 through the channel 25. A unit memory 33 is in communication with the controller 31 through a communication channel 35. The controller 31 is in communication with a disk servo control circuit 37 through a control channel 39 and a data channel 41. The servo control circuit 37 controls electromechanical operation of a plurality of magnetic disks 104 and a plurality of read-write heads which are carried by actuator arms 106 and which at any given time are positioned over storage areas 123 on the various disks 104. A close-up view of a region 47 of one of the disks
104 is shown in FIG. 3, including a plurality of other nearby storage areas 105 on the disk 104.
A plurality of control signals and information are managed by the central controller 15 and stored in the central memory 17. A global index includes entries each of which gives a logical address and a corresponding physical address (unit and segment identifiers) for data blocks that are stored on the disks.
Some blocks of data are assigned to rollback groups. A group index is created dynamically for each designated rollback group. Each index includes entries each of which gives a logical address and a corresponding physical address for a data block that is stored on the disks and that is assigned to the particular rollback group which corresponds to that index. Occasionally a block of data that is a member of one group may be referenced, not only by an entry in the index which corresponds with the group to which the block belongs, but also by an entry in the global index or in one or more other group indices. Each entry in a group index carries a status indicator that designates its status as being either "write", "no-write" or "delete".
A "reference list" is maintained in memory by the controller. The reference list gives a reference count for each physical address that appears in any of the indices. The reference count for a given physical address indicates the number of times that that physical address is listed in all the indices.
An "obsolete list" is also maintained by the controller. This list includes physical addresses for segments that contain obsolete data but that have not yet been released for the entry of new data.
An "operations log" is maintained in memory and includes a record of all create group, copy, delete, commit, abort and barrier commands that have been issued subsequent to the most recent of any sync command and checkpoint operation. A "checkpoint log" lists all entries in and deletions from all the indices subsequent to the most recent of any sync command and checkpoint operation.
The portion of memory that contains the global and group indices is divided into a plurality of k "checkpoint sections", where _ is an integer. Among the various disk storage units 21 and 23, a total of k+1 "checkpoint segments" are reserved. These may be all in one storage unit such as the unit 21 or they may be distributed among a plurality of the units as is convenient. These checkpoint sections in memory, checkpoint segments on disk, and operations log are used for recovery if there is a memory loss, as will be described in more detail presently.
The unit memory of each storage unit includes a free map which gives a list of the available storage segments in that unit.
These physical and memory elements, which are described and illustrated as discrete elements, may be combined in an actual physical embodiment. For example, all of the memories may be realized in a single bank of RAM memory. The free maps may be combined into a single free map that lists all free segments in all of the storage units. Some or all of the various controller functions may be performed by one microprocessor or other control device, or the controller functions may be distributed among a central controller and a plurality of disk unit controllers as shown.
Various commands are issued by the host processor 11. The host processor may be a general-purpose computer, a network server, or some other device that requires a data storage system.
The storage units contemplated by the invention are magnetic disk storage units as described and illustrated. However, it will be apparent that the principles of the invention are equally applicable to other types of storage devices, such as optical media, bubble memories, and so on.
COMMANDS ISSUED BY THE HOST PROCESSOR
The storage system receives various commands from the host processor and performs various actions in response to those commands, as will now be described in more detail.
"Write" command
This command includes a logical address, one block of data to be written by itself or a plurality of blocks to be written as a multi-block write, and optionally a group identifier.
In response to this command, the central disk controller 15 performs a series of tasks for each block to be written. First the controller selects a storage unit such as the disk unit 21 or the disk unit 23 according to a criterion such as which of the units has the most free space. A better criterion will usually be an algorithm for distributing writes equally among all the storage units.
Next the controller selects a segment from the free list for the selected storage unit. One way of making
this selection is to select that segment which can be reached in minimum time. In the context of a disk drive unit, this time includes seek time (the time required to move the magnetic recording head carried by the actuator arm 106 into position) , rotational delay time (the time required for the desired segment 123 to rotate into position) , and the time to actually transfer the data. By monitoring the positions of the heads and the angular positions of the disks, one can select from among the available segments a segment that can be accessed in minimum time relative to the access time of any other available segment. The selection process, which is dynamic because the heads and disks are in continuous or nearly-continuous motion, may be done by the central disk controller 15 or may be delegated to the disk unit controller 31 as desired.
Then the controller appends a tag to the block. The tag includes the logical address and the next consecutive sequence number from a sequential set of such numbers.
The tag also includes an end flag unless the block is a beginning or intermediate block in a multi-block write.
If the block is a member of a rollback group, the group identifier is also included in the tag.
Next the controller records the block and its tag at the selected physical address (segment and storage unit) ; deletes the segment "from the free map; enters the logical and physical addresses in the group index with a write status indicator, or if there is no group identifier then in the global index; and increments the reference count for the physical address.
If the same logical address appears together with a previous physical address in a previous entry, the controller deletes the previous entry and decrement the reference count for the previous physical address. In
S
addition, if the previous entry was in the global index, the controller inserts the previous entry into any of the group indices which do not already contain the address as "no-write" entries, and increments the reference count for the previous physical address once for each index into which the previous entry is inserted. If the count decrements to zero, which indicates that the physical address is not on any index, the physical address is moved to the obsolete list.
Finally, the controller enters all insertions and deletions in the checkpoint log.
"Create Rollback Group" command
The "create rollback group" includes a group identifier for the new rollback group. In response to this command, the central disk controller 15 creates a group index for the new rollback group and assigns the next sequence number and enters the command in the operations log.
"Read" command
The "read" command includes a logical address and optionally a group identifier. In response to this command, the central controller 15 searches the group index to find the physical address of the data block to be read. If not found, or if there is no group identifier, the controller searches the global index to find the physical address. The physical address is used to retrieve the data block from disk, and then the data block is sent to the host processor.
"Delete" command
The "delete" command includes a logical address and optionally a group identifier. In response to this command, the controller 15 does the following:
If there is a group identifier and the block is already listed in the group index, the controller changes the entry to a delete entry and decrement the reference count for the physical address. If there is a group identifier and the block is not listed in the group index, the controller enters the logical address of the block in the group index as a delete entry.
If there is no group identifier, the controller deletes the entry from the global index and decrements the reference count for the physical address. In addition, if the same logical address appears together with a previous physical address in a previous entry in the global index, the controller deletes the previous entry, decrements the reference count for the previous physical address, inserts the previous entry in all the other group indices which do not already contain that address as "no-write" entries, and increments the reference count for the previous physical address once for each index into which the previous entry is inserted. If the reference count for a physical address goes to zero, that address i's entered in the obsolete list.
Then the controller assigns the next sequence number, enters the command in the operations log, and enters all insertions and deletions in the checkpoint log.
"Barrier" command
The "barrier" command is issued by the host any time
it wants to preserve a certain state of the various data items as a valid state to which it can return. It may identify a rollback group if its effect is to be limited to one group. In response to this command, the controller assigns the next sequence number and enters the command in the operations log.
ABORT command
The "abort" command identifies a rollback group to be aborted. In response, the controller decrements the reference count for the physical address of each write entry and each no-write entry in the group index, deletes the group index, assigns the next sequence number and enter the command in the operations log, and enters each deletion in the checkpoint log.
COMMIT command
The "commit" command identifies a rollback group to be committed. In response to this command, the controller does the following:
If the entry is a "write" entry, the controller moves the entry from the group index to the global index and, if the same logical address appears together with a previous physical address in a previous entry in the global index, deletes the previous entry, decrements the reference count for the previous physical address, inserts the previous entry in all the other group indices which do not already contain that address as no-write entries, and increments the reference count for the previous physical address once for each index into which the previous entry is inserted.
If the entry is a no-write entry, the controller decrements the reference count for the physical address.
If the entry is a delete entry, the controller deletes any entry having the same logical address from the global index, decrements the reference count for the physical address of the deleted entry, inserts the previous entry in all the other group indices which do not already contain that address as no-write entries, and increments the reference count for the previous physical address once for each index into which the previous entry is inserted.
Then the controller deletes the group index, assigns the next sequence number, enters the command in the operations log, and enters all insertions and deletions in the checkpoint log.
As with the other commands, if the reference count of a physical address goes to zero, that address is thereupon listed in the obsolete list.
COPY command
This command includes a logical address of a block to be copied and a new logical address into which to copy the block. Group identifiers are optionally provided for one or both of these addresses.
In response to this command, the controller looks up the physical address"of the block to be copied. Then it enters the new logical address as a write entry in the identified group index, or if none then in the global index, together with the physical address of the block being copied, and increments the reference count for the physical address.
If the same logical address appears together with a previous physical address in a previous entry, the controller deletes the previous entry and decrements the
reference count for the previous physical address, and, if the previous entry was in the global index, inserts the previous entry into all the group indices which do not already contain the address as no-write entries, and increments the reference count for the previous physical address once for each index into which the previous entry is inserted.
Then the controller assigns the next sequence number and enter the command in the operations log and enters all insertions and deletions in the checkpoint log.
SYNC command
This command is issued by the host process any time it wants to ensure that commands which have previously been sent to the controller have been completed. The command optionally includes a group identifier that limits its scope to the identified group. In response to this command, if there is a group identifier the controller finishes any pending write commands that were issued before the latest barrier sent to the group. Any pending global write commands are finished, including ones that were placed there before a "commit" command. The operations log and the next sequence number are written to an available segment, and the physical address to which the log was written is added to the obsolete list.
The operations log is only needed to recover a record of any operations subsequent to the most recent checkpoint operation. Therefore, its physical address can immediately be placed in the obsolete list.
FREE LIST AND CHECKPOINT OPERATIONS
Certain operations are performed by the central
controller without a command from the host processor. These operations will be described next.
"Checkpoint"
Periodically, an image of the checkpoint log and of a sequential one of the checkpoint sections of memory, together with the next sequence number, are written to a sequential one of the checkpoint segments of the disk. Any physical addresses then in the obsolete list are transferred to the free maps.
"Reference Count"
If the reference count for a physical address goes to zero, that physical address is entered in the obsolete list. This is discussed above in connection with some of the specific commands. In general, entry of the physical address in the obsolete list would only occur at the end of the command during which the count goes to zero. This prevents an entry from being made in the obsolete list if the count goes to zero and then is incremented back to a positive value during one command.
"Operations Log"
If the operations log reaches a predetermined number of entries or if a sync or checkpoint command is issued, the controller writes the operations log together with the next sequence number to an available segment, adds the physical address to which the log was written to the obsolete list, and clears the operations log in memory.
"Recovery"
If there is a power failure or some other event that wipes out the memory, and perhaps also interrupts a write
in progress, the controller reads the k+1 checkpoint segments to get the k ones that are both most recent and valid. The information recovered from these segments is used in order, starting with the oldest, to reconstruct the global and group indices up through the most recent checkpoint operation.
Then the controller reads all segments not listed in the reconstructed Indices and lists all the segments having sequence numbers older than the most recent checkpoint segment in the free maps. Then it arranges the remaining segments in order of increasing sequence numbers, recovers all data blocks and operations logs from the oldest through the most recent having an end flag until there is a gap in sequence numbers, and uses these to finish reconstructing the indices. Next any remaining segments are listed in the Free Maps. Finally, the sequence numbers are incremented to a number greater than that of the segment having the largest one.
It will be apparent that there are various ways to store and encode the information in the indices and lists, and on the disk. For example, a "delete" status of an entry in a group index may be indicated by a flag or by the absence of a physical address or by a special nonexistent physical address code. Similarly, the end of a block may be indicated by a flag or by some other form of encoding. In some circumstances the presence of a sequence number may be a sufficient indicator of the end of a block to confirm that the block has been completely written prior to any failure.
Although a specific embodiment of the invention has been described and illustrated, the invention is not to be limited to the specific forms or arrangements of parts so described and illustrated, and various modifications and changes can be made without departing from the scope
and spirit of the invention. Within the scope of the appended claims, therefore, the invention may be practiced otherwise than as specifically described and illustrated.
Claims
1. An electronic data storage system (13) comprising a memory (17) ; a plurality of storage units (21, 23) each having a plurality of segments (123, 105) for storing blocks of data, each segment identified by a physical address; and a controller (15) in communication with the memory (17) and the storage units (21, 23) , the controller operative: to maintain in the memory an index containing entries each having a logical address and a corresponding physical address, an obsolete list containing physical addresses of segments that contain obsolete data, and a free list containing physical addresses of segments that are available to receive data for storage, and in response to a write command that provides a preselected logical address and an associated block of data for storage, to (a) select a physical address from the free list according to a predefined criterion, (b) obtain a next sequence number from a set of sequential numbers, (c) append to the block a tag that includes the sequence number, the preselected logical address, and an end flag, (d) store the block and its tag in the segment of the selected physical address, (e) delete the selected physical address from the free list, (f) enter the preselected logical address and the selected physical address in the index, (g) delete any previous index entry that contains a logical address which is the same as the preselected logical address, and (f) list the physical address from any such deleted entry in the obsolete list.
2. A system as in claim 1 wherein the controller (15) is operative, in response to a write command that provides a preselected logical address and a plurality of associated blocks of data for storage, for each such block to (a) select a physical address from the free list according to the predefined criterion, (b) obtain a next sequence number from the set of sequential numbers, (c) append a tag that includes the sequence number of that block, the tag for the first block also including the preselected logical address, the tag for each block after the first including a logical address calculated by incrementing the logical address of the preceding block, and the tag for the last block including an end flag, (d) store the block and its tag in the segment of the physical address that was selected for that block, (e) delete the selected physical address from the free list, (f) enter the logical address of the block and the selected physical address in the index, (g) delete any previous index entry that contains a logical address which is the same as the logical address of the block, and (f) list the physical address from any such deleted entry in the obsolete list.
3. A system as in claim 1 or 2 wherein the predefined criterion comprises which available segment can be accessed in a minimum amount of time relative to the time that would be reguired to access others of the available segments.
4. A system as in any preceding claim wherein the controller (15) is operative to (a) maintain in the memory a checkpoint log that includes a record of each entry in, and each deletion from, the index, (b) arrange the various index entries in a plurality of checkpoint sections, (c) reserve a plurality of the segments as checkpoint segments, and periodically (d) store the checkpoint log, an image of a sequential one of the checkpoint sections of the memory, and a tag that includes a next sequence number from the set of sequential numbers and an end flag in a sequential one of the checkpoint segments and transfer any physical addresses then in the obsolete list into the free list.
5. A system as in claim 4 wherein, if the contents of the memory are lost, the controller (15) is operative to recover the index and the free list by: reading the checkpoint segments to obtain the most recent valid segments that collectively contain all of the checkpoint sections of the memory, the recency of a segment being indicated by its sequence number and the validity of a segment being indicated by the presence of an end flag, starting with the oldest of the obtained checkpoint segments, using the checkpoint sections and checkpoint logs as stored in the checkpoint segments to recover the index up through the most recent checkpoint, and for all non-checkpoint segments not yet listed in the index, reading the sequence numbers of said segments, entering the physical address of each said segment having a sequence number older than that of the most recent checkpoint segment into the free list, arranging the remaining segments in order of increasing sequence numbers until an invalid segment is detected, entering the logical and physical addresses of each of the arranged segments into the index, and entering the physical address of any remaining segments into the free list.
6. A system as in claim 5 wherein the controller (15) detects an invalid non-checkpoint segment by locating a numerical" gap between the sequence numbers of the segments and going back through the segments in reverse order of sequence numbers until a segment having an end-of-block tag is located, the segment following the one having the end-of-block tag being the invalid one.
7. A system as in any preceding claim wherein the controller (15) is operative: to maintain the index as a global index and one or more group indices, to create a group index in response to a create- group command, each group index containing entries each having the logical address of a block that belongs to the group, a status indicator, and, if the indicated status is "write" or "no-write", the physical address of the block, to maintain in the memory a reference list that provides a reference count for each physical address that appears either in the global index or in any of the group indices, to include in the tag appended to a block an identifier of any group to which the block belongs, and in response to a write command (a) if the command does not include a group identifier, to enter the preselected logical address and the selected physical address in the global index, (b) if the command includes a group identifier, to enter the preselected logical address, the selected physical address and a "write" status indicator in the group index corresponding with the identified group, (c) to increment the reference count for the selected physical address, (d) to delete any previous entry in the same index that contains the same logical address together with a different physical address, (e) to decrement the reference count for the physical address of the deleted entry, (f) if the deleted entry was in the global index, to copy the logical and physical addresses of the deleted entry and a no-write status indicator into each group index, and (g) to increment the reference count for the physical address of the deleted entry once for each group index into which the entry is copied.
8. A system as in claim 7 wherein the controller (15) is operative in response to a delete command that includes a logical address: if the delete command contains no group identifier, to delete any global index entry that contains that logical address, to decrement the reference count of the physical address in the deleted entry, and to make corresponding entries in the various group indices; if the delete command contains a group identifier and the logical address is already entered in the corresponding group index, to delete any physical address from the entry, to change the status indicator to "delete", and to decrement the reference count of the deleted physical address, and if the delete command contains a group identifier and the logical address is not already entered in the corresponding group index, to enter the logical address in the index together with a "delete" status indicator.
9. A system as in claim 8 wherein the controller (15) is operative in response to a commit command that includes a group identifier to delete the corresponding group index and, for each entry in the deleted index: if the entry has a "no-write" status, to decrement the reference count for the physical address in the entry, if the entry has a "delete" status, to delete any entry in the global index having the same logical address and to decrement the reference count for the physical address in each such deleted entry, and if the entry has a "write" status, (a) to copy the logical and physical address of the entry into the global index, (b) to delete'any previous entry in the global index that contains the same logical address together with a different physical address, (c) to decrement the reference count for the physical address in any such deleted entry, (d) to copy the logical and physical addresses of any such deleted entry and a "no-write" status indicator into all other group indices, and (e) to increment the reference count for the physical address of the deleted entry once for each group index into which the entry is copied.
10. A system as in claim 9 wherein the controller (15) is operative to enter any delete and commit commands into an operations log and, in response to a sync command, to store the operations log in an available segment and enter the physical address of that segment into the obsolete list.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP5519368A JPH06508708A (en) | 1992-04-24 | 1993-04-22 | disk storage system |
EP93912337A EP0591520A1 (en) | 1992-04-24 | 1993-04-22 | Disk storage system |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US07/873,928 | 1992-04-24 | ||
US07/873,928 US5481694A (en) | 1991-09-26 | 1992-04-24 | High performance multiple-unit electronic data storage system with checkpoint logs for rapid failure recovery |
Publications (1)
Publication Number | Publication Date |
---|---|
WO1993022719A1 true WO1993022719A1 (en) | 1993-11-11 |
Family
ID=25362624
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/US1993/003779 WO1993022719A1 (en) | 1992-04-24 | 1993-04-22 | Disk storage system |
Country Status (4)
Country | Link |
---|---|
US (1) | US5481694A (en) |
EP (1) | EP0591520A1 (en) |
JP (1) | JPH06508708A (en) |
WO (1) | WO1993022719A1 (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO1995014273A1 (en) * | 1993-11-18 | 1995-05-26 | Microsoft Corporation | Method and system for tracking changed files |
GB2278487B (en) * | 1993-05-24 | 1997-06-18 | Mitsubishi Electric Corp | Improved recording apparatus and method for an arrayed recording apparatus |
EP1126373A2 (en) | 2000-02-15 | 2001-08-22 | International Business Machines Corporation | Storage allocation system and method |
EP0690369A3 (en) * | 1994-06-30 | 2003-01-02 | Sony Corporation | Disk control method and control apparatus capable of lowering data transfer load of computer |
SG99941A1 (en) * | 2000-08-30 | 2003-11-27 | Ibm | Transaction support on logical disks |
US7308606B2 (en) | 2000-02-15 | 2007-12-11 | International Business Machines Corporation | System and method for persistent and robust storage allocation |
CN111752913A (en) * | 2019-03-28 | 2020-10-09 | 阿里巴巴集团控股有限公司 | Data recovery method, medium, computer equipment and device of distributed system |
Families Citing this family (73)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6728832B2 (en) | 1990-02-26 | 2004-04-27 | Hitachi, Ltd. | Distribution of I/O requests across multiple disk units |
US5680574A (en) * | 1990-02-26 | 1997-10-21 | Hitachi, Ltd. | Data distribution utilizing a master disk unit for fetching and for writing to remaining disk units |
JP3183719B2 (en) * | 1992-08-26 | 2001-07-09 | 三菱電機株式会社 | Array type recording device |
GB2272549B (en) * | 1992-11-03 | 1997-01-29 | Tolsys Ltd | Memory checkpointing |
US5666551A (en) * | 1994-06-30 | 1997-09-09 | Digital Equipment Corporation | Distributed data bus sequencing for a system bus with separate address and data bus protocols |
US5708793A (en) * | 1995-03-31 | 1998-01-13 | International Business Machines Corporation | Method and apparatus using address and read head location information to provide optimal operation of a disk system |
JP3085899B2 (en) * | 1995-06-19 | 2000-09-11 | 株式会社東芝 | Multiprocessor system |
US5630047A (en) * | 1995-09-12 | 1997-05-13 | Lucent Technologies Inc. | Method for software error recovery using consistent global checkpoints |
AU1119097A (en) * | 1995-11-13 | 1997-06-05 | Answersoft, Inc. | Intelligent information routing system and method |
JPH09198195A (en) * | 1996-01-19 | 1997-07-31 | Nec Corp | Disk device capable of rearranging data |
SE510050C2 (en) * | 1997-07-21 | 1999-04-12 | Ericsson Telefon Ab L M | Method for collecting log information when changing database |
US6055604A (en) * | 1997-08-26 | 2000-04-25 | Hewlett-Packard Company | Forced transaction log posting using a least busy storage media without maintaining redundancy of the transaction log |
US6170063B1 (en) * | 1998-03-07 | 2001-01-02 | Hewlett-Packard Company | Method for performing atomic, concurrent read and write operations on multiple storage devices |
CA2244626A1 (en) * | 1998-07-31 | 2000-01-31 | Kom Inc. | A hardware and software system |
US6378038B1 (en) | 1999-03-31 | 2002-04-23 | International Business Machines Corporation | Method and system for caching data using raid level selection |
US6529995B1 (en) * | 1999-06-18 | 2003-03-04 | Storage Technology Corporation | Method and apparatus for maintaining and restoring mapping table entries and data in a raid system |
MXPA02004748A (en) * | 1999-11-10 | 2004-01-19 | Thomson Licensing Sa | A method of disaster recovery for re writable disk media. |
US6668304B1 (en) | 2000-01-18 | 2003-12-23 | International Business Machines Corporation | Transaction support on logical disks |
US6636941B1 (en) | 2000-01-18 | 2003-10-21 | International Business Machines Corporation | Enhanced stable disk storage |
US6601137B1 (en) * | 2000-04-19 | 2003-07-29 | Western Digital Technologies, Inc. | Range-based cache control system and method |
US6594744B1 (en) * | 2000-12-11 | 2003-07-15 | Lsi Logic Corporation | Managing a snapshot volume or one or more checkpoint volumes with multiple point-in-time images in a single repository |
US6751715B2 (en) * | 2001-12-13 | 2004-06-15 | Lsi Logic Corporation | System and method for disabling and recreating a snapshot volume |
US7085784B2 (en) * | 2002-01-10 | 2006-08-01 | International Business Machines Corporation | System and method for eliminating duplicate copies of activity history logs in bridging two or more backend database systems |
US7103729B2 (en) * | 2002-12-26 | 2006-09-05 | Intel Corporation | Method and apparatus of memory management |
US7231544B2 (en) * | 2003-02-27 | 2007-06-12 | Hewlett-Packard Development Company, L.P. | Restoring data from point-in-time representations of the data |
US7243200B2 (en) * | 2004-07-15 | 2007-07-10 | International Business Machines Corporation | Establishing command order in an out of order DMA command queue |
US7805632B1 (en) * | 2007-09-24 | 2010-09-28 | Net App, Inc. | Storage system and method for rapidly recovering from a system failure |
US7752175B2 (en) * | 2007-10-29 | 2010-07-06 | Objectivity, Inc. | Method, system and computer-readable media for repairing corruption of data record references |
US8341014B2 (en) * | 2007-12-28 | 2012-12-25 | International Business Machines Corporation | Recovery segments for computer business applications |
US20090171703A1 (en) * | 2007-12-28 | 2009-07-02 | International Business Machines Corporation | Use of multi-level state assessment in computer business environments |
US20090171731A1 (en) * | 2007-12-28 | 2009-07-02 | International Business Machines Corporation | Use of graphs in managing computing environments |
US8751283B2 (en) * | 2007-12-28 | 2014-06-10 | International Business Machines Corporation | Defining and using templates in configuring information technology environments |
US20090171730A1 (en) * | 2007-12-28 | 2009-07-02 | International Business Machines Corporation | Non-disruptively changing scope of computer business applications based on detected changes in topology |
US8990810B2 (en) * | 2007-12-28 | 2015-03-24 | International Business Machines Corporation | Projecting an effect, using a pairing construct, of execution of a proposed action on a computing environment |
US8365185B2 (en) * | 2007-12-28 | 2013-01-29 | International Business Machines Corporation | Preventing execution of processes responsive to changes in the environment |
US8682705B2 (en) * | 2007-12-28 | 2014-03-25 | International Business Machines Corporation | Information technology management based on computer dynamically adjusted discrete phases of event correlation |
US8826077B2 (en) * | 2007-12-28 | 2014-09-02 | International Business Machines Corporation | Defining a computer recovery process that matches the scope of outage including determining a root cause and performing escalated recovery operations |
US8677174B2 (en) * | 2007-12-28 | 2014-03-18 | International Business Machines Corporation | Management of runtime events in a computer environment using a containment region |
US8346931B2 (en) * | 2007-12-28 | 2013-01-01 | International Business Machines Corporation | Conditional computer runtime control of an information technology environment based on pairing constructs |
US8375244B2 (en) * | 2007-12-28 | 2013-02-12 | International Business Machines Corporation | Managing processing of a computing environment during failures of the environment |
US8326910B2 (en) * | 2007-12-28 | 2012-12-04 | International Business Machines Corporation | Programmatic validation in an information technology environment |
US8868441B2 (en) * | 2007-12-28 | 2014-10-21 | International Business Machines Corporation | Non-disruptively changing a computing environment |
US9558459B2 (en) * | 2007-12-28 | 2017-01-31 | International Business Machines Corporation | Dynamic selection of actions in an information technology environment |
US8782662B2 (en) * | 2007-12-28 | 2014-07-15 | International Business Machines Corporation | Adaptive computer sequencing of actions |
US7958393B2 (en) * | 2007-12-28 | 2011-06-07 | International Business Machines Corporation | Conditional actions based on runtime conditions of a computer system environment |
US20090172149A1 (en) * | 2007-12-28 | 2009-07-02 | International Business Machines Corporation | Real-time information technology environments |
US8447859B2 (en) * | 2007-12-28 | 2013-05-21 | International Business Machines Corporation | Adaptive business resiliency computer system for information technology environments |
US8428983B2 (en) * | 2007-12-28 | 2013-04-23 | International Business Machines Corporation | Facilitating availability of information technology resources based on pattern system environments |
US20090171708A1 (en) * | 2007-12-28 | 2009-07-02 | International Business Machines Corporation | Using templates in a computing environment |
US8763006B2 (en) | 2007-12-28 | 2014-06-24 | International Business Machines Corporation | Dynamic generation of processes in computing environments |
US20100274772A1 (en) * | 2009-04-23 | 2010-10-28 | Allen Samuels | Compressed data objects referenced via address references and compression references |
DE102009031923A1 (en) * | 2009-07-07 | 2011-01-13 | Sones Gmbh | Method for managing data objects |
JP5463780B2 (en) * | 2009-07-31 | 2014-04-09 | ブラザー工業株式会社 | Information processing device |
US11449394B2 (en) * | 2010-06-04 | 2022-09-20 | Commvault Systems, Inc. | Failover systems and methods for performing backup operations, including heterogeneous indexing and load balancing of backup and indexing resources |
JP5354138B1 (en) * | 2012-03-02 | 2013-11-27 | 日本電気株式会社 | Capacity management support apparatus, capacity management method and program |
US9015429B2 (en) * | 2013-04-18 | 2015-04-21 | Xerox Corporation | Method and apparatus for an efficient hardware implementation of dictionary based lossless compression |
US10198321B1 (en) * | 2014-04-01 | 2019-02-05 | Storone Ltd. | System and method for continuous data protection |
US9563518B2 (en) | 2014-04-02 | 2017-02-07 | Commvault Systems, Inc. | Information management by a media agent in the absence of communications with a storage manager |
CA2969210C (en) * | 2014-12-01 | 2024-02-20 | Informatica Llc | Method, apparatus, and comuter-readable medium for processing a message by a message broker system |
US9880755B2 (en) * | 2015-02-25 | 2018-01-30 | Western Digital Technologies, Inc. | System and method for copy on write on an SSD |
KR20170051563A (en) * | 2015-10-29 | 2017-05-12 | 에스케이하이닉스 주식회사 | Data storage device and operating method thereof |
US10180886B2 (en) * | 2015-11-16 | 2019-01-15 | Red Hat, Inc. | Recreating a computing environment using tags and snapshots |
US10031689B2 (en) * | 2016-09-15 | 2018-07-24 | Western Digital Technologies, Inc. | Stream management for storage devices |
US10474548B2 (en) | 2016-09-30 | 2019-11-12 | Commvault Systems, Inc. | Heartbeat monitoring of virtual machines for initiating failover operations in a data storage management system, using ping monitoring of target virtual machines |
US20190102262A1 (en) * | 2017-09-29 | 2019-04-04 | Intel Corporation | Automated continuous checkpointing |
US11003555B2 (en) * | 2017-12-16 | 2021-05-11 | Vmware, Inc. | Tracking and recovering a disk allocation state |
US10754785B2 (en) | 2018-06-28 | 2020-08-25 | Intel Corporation | Checkpointing for DRAM-less SSD |
US10776339B2 (en) | 2018-07-23 | 2020-09-15 | EMC IP Holding Company LLC | Intelligent log gap detection to prevent unnecessary backup promotion |
US10977137B2 (en) * | 2018-07-23 | 2021-04-13 | EMC IP Holding Company LLC | Intelligent log gap detection to ensure necessary backup promotion |
US11200124B2 (en) | 2018-12-06 | 2021-12-14 | Commvault Systems, Inc. | Assigning backup resources based on failover of partnered data storage servers in a data storage management system |
US11099956B1 (en) | 2020-03-26 | 2021-08-24 | Commvault Systems, Inc. | Snapshot-based disaster recovery orchestration of virtual machine failover and failback operations |
CN111697689B (en) * | 2020-05-13 | 2021-09-24 | 北京四方继保工程技术有限公司 | Power supply equipment hidden fault monitoring method and system |
US11645175B2 (en) | 2021-02-12 | 2023-05-09 | Commvault Systems, Inc. | Automatic failover of a storage manager |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP0440413A2 (en) * | 1990-02-02 | 1991-08-07 | Seagate Technology International | Disk drive system and method for accessing a physical memory location therein |
WO1991020025A1 (en) * | 1990-06-18 | 1991-12-26 | Storage Technology Corporation | Deleted data file space release system for a dynamically mapped virtual data storage subsystem |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5124987A (en) * | 1990-04-16 | 1992-06-23 | Storage Technology Corporation | Logical track write scheduling system for a parallel disk drive array data storage subsystem |
-
1992
- 1992-04-24 US US07/873,928 patent/US5481694A/en not_active Expired - Lifetime
-
1993
- 1993-04-22 JP JP5519368A patent/JPH06508708A/en active Pending
- 1993-04-22 WO PCT/US1993/003779 patent/WO1993022719A1/en not_active Application Discontinuation
- 1993-04-22 EP EP93912337A patent/EP0591520A1/en not_active Withdrawn
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP0440413A2 (en) * | 1990-02-02 | 1991-08-07 | Seagate Technology International | Disk drive system and method for accessing a physical memory location therein |
WO1991020025A1 (en) * | 1990-06-18 | 1991-12-26 | Storage Technology Corporation | Deleted data file space release system for a dynamically mapped virtual data storage subsystem |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
GB2278487B (en) * | 1993-05-24 | 1997-06-18 | Mitsubishi Electric Corp | Improved recording apparatus and method for an arrayed recording apparatus |
WO1995014273A1 (en) * | 1993-11-18 | 1995-05-26 | Microsoft Corporation | Method and system for tracking changed files |
US5590318A (en) * | 1993-11-18 | 1996-12-31 | Microsoft Corporation | Method and system for tracking files pending processing |
EP0690369A3 (en) * | 1994-06-30 | 2003-01-02 | Sony Corporation | Disk control method and control apparatus capable of lowering data transfer load of computer |
EP1126373A2 (en) | 2000-02-15 | 2001-08-22 | International Business Machines Corporation | Storage allocation system and method |
EP1126373A3 (en) * | 2000-02-15 | 2006-12-13 | International Business Machines Corporation | Storage allocation system and method |
US7308606B2 (en) | 2000-02-15 | 2007-12-11 | International Business Machines Corporation | System and method for persistent and robust storage allocation |
US7870359B2 (en) | 2000-02-15 | 2011-01-11 | International Business Machines Corporation | System and method for persistent and robust storage allocation |
SG99941A1 (en) * | 2000-08-30 | 2003-11-27 | Ibm | Transaction support on logical disks |
CN111752913A (en) * | 2019-03-28 | 2020-10-09 | 阿里巴巴集团控股有限公司 | Data recovery method, medium, computer equipment and device of distributed system |
CN111752913B (en) * | 2019-03-28 | 2024-03-01 | 阿里云计算有限公司 | Data recovery method, medium, computer equipment and device of distributed system |
Also Published As
Publication number | Publication date |
---|---|
US5481694A (en) | 1996-01-02 |
EP0591520A1 (en) | 1994-04-13 |
JPH06508708A (en) | 1994-09-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US5481694A (en) | High performance multiple-unit electronic data storage system with checkpoint logs for rapid failure recovery | |
US5764880A (en) | Method and system for rebuilding log-structured arrays | |
EP0357464B1 (en) | Information recording and reproducing apparatus using optical discs | |
Gait | The optical file cabinet: a random-access file system for write-once optical disks | |
KR100667114B1 (en) | Concurrent read and write access to simulated sequential data of a removable random access data storage medium | |
US5269019A (en) | Non-volatile memory storage and bilevel index structure for fast retrieval of modified records of a disk track | |
US6311193B1 (en) | Computer system | |
US4575827A (en) | Self-archiving data recording | |
US5802344A (en) | Method and apparatus for dynamic segment allocation in log structured arrays | |
US6502108B1 (en) | Cache-failure-tolerant data storage system storing data objects with version code equipped metadata tokens | |
US6360232B1 (en) | Disaster recovery method for a removable media library | |
US5551002A (en) | System for controlling a write cache and merging adjacent data blocks for write operations | |
US6691137B1 (en) | Cache management system utilizing cascading tokens | |
US6553509B1 (en) | Log record parsing for a distributed log on a disk array data storage system | |
JP2691087B2 (en) | Directory system, device and method for data files | |
JP2710717B2 (en) | A method for quickly accessing a desired logical data block identified by a logical block number on a tape | |
JPH039494B2 (en) | ||
US6209057B1 (en) | Storage device having data buffer | |
JPH04246746A (en) | Storage device system | |
JPH0452725A (en) | Fault recovering/processing method for storage device | |
JPS5921057B2 (en) | Intersystem shared file recovery control method | |
JPH03166634A (en) | Information recording/reproducing system | |
CN117519612B (en) | Mass small file storage system and method based on index online splicing | |
JP2612589B2 (en) | Directory search method | |
JP2721034B2 (en) | Clustering control system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
WWE | Wipo information: entry into national phase |
Ref document number: 1993912337 Country of ref document: EP |
|
AK | Designated states |
Kind code of ref document: A1 Designated state(s): JP |
|
AL | Designated countries for regional patents |
Kind code of ref document: A1 Designated state(s): AT BE CH DE DK ES FR GB GR IE IT LU MC NL PT SE |
|
121 | Ep: the epo has been informed by wipo that ep was designated in this application | ||
WWP | Wipo information: published in national office |
Ref document number: 1993912337 Country of ref document: EP |
|
WWW | Wipo information: withdrawn in national office |
Ref document number: 1993912337 Country of ref document: EP |