WO2010071661A1 - Method for implementing multi-array consistency groups using a write queuing mechanism - Google Patents
Method for implementing multi-array consistency groups using a write queuing mechanism Download PDFInfo
- Publication number
- WO2010071661A1 WO2010071661A1 PCT/US2009/000430 US2009000430W WO2010071661A1 WO 2010071661 A1 WO2010071661 A1 WO 2010071661A1 US 2009000430 W US2009000430 W US 2009000430W WO 2010071661 A1 WO2010071661 A1 WO 2010071661A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- write
- storage array
- slave
- timestamp
- master
- Prior art date
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F12/00—Accessing, addressing or allocating within memory systems or architectures
-
- 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
- G06F11/1458—Management of the backup or restore process
- G06F11/1466—Management of the backup or restore process to make the backup process non-disruptive
-
- 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
- G06F11/1471—Saving, restoring, recovering or retrying involving logging of persistent data for recovery
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F12/00—Accessing, addressing or allocating within memory systems or architectures
- G06F12/16—Protection against loss of memory contents
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2201/00—Indexing scheme relating to error detection, to error correction, and to monitoring
- G06F2201/80—Database-specific techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2201/00—Indexing scheme relating to error detection, to error correction, and to monitoring
- G06F2201/82—Solving problems relating to consistency
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2201/00—Indexing scheme relating to error detection, to error correction, and to monitoring
- G06F2201/84—Using snapshots, i.e. a logical point-in-time copy of the data
Definitions
- the present disclosure generally relates to the field of storage systems, and more particularly to methods for implementing multi-array consistency groups for database backup.
- a single application may use multiple Logical Units (LUs).
- LUs Logical Units
- a database system may have a log file on one LU and a data file on another LU.
- Databases may employ a backup technique which takes a snapshot of database LUs, and backup the snapshots to an appropriate storage media, such as tape.
- Such a backup technique may be performed without offlining the database; the database may not quiesce I/O (input/output) functionality.
- the database application may continue to run while snapshots are taken, where the snapshots may not be coordinated with the database activity.
- the snapshot backup technique may require a consistent snapshot of all LUs used by the database application before a backup may be performed. This consistency may ensure that the application actually be restored correctly from the backup.
- a consistency group may be used when database systems have LUs located on different storage arrays.
- a CG may consist of one or more LUs, and may be used to create a snapshot of all members of the CG as a single atomic operation.
- a method for implementing multi-array consistency groups includes applying a write Input/Output (I/O) queue interval to a Logical Unit (LU) member of a consistency group (CG).
- a storage array where the LU member of the CG resides is a participating storage array.
- the method also includes marking each write I/O with a timestamp and suspending I/O from the participating storage array to the LU member of the CG upon the participating storage array receiving a snapshot request from a master storage array.
- the snapshot request has a snapshot request timestamp.
- the method further includes determining whether the snapshot request timestamp is within the write I/O queue interval of the participating storage array.
- the participating storage array When the snapshot request timestamp is determined to be within the write I/O queue interval of the participating storage array, the participating storage array performs at least one of: (a) completing each write I/O older than the snapshot request timestamp, (b) creating a local snapshot for the LU member of the CG, or (c) resuming I/O to the LU member of the CG.
- a method for implementing multi-array consistency groups includes initiating a consistency group (CG) snapshot on a controller of a CG storage array.
- the CG storage array with the controller is defined as a master, and a storage array where a Logical Unit (LU) member of the CG resides is a participating storage array.
- the method also includes recording a timestamp for the initiated CG snapshot and sending a PREPARE request from the master to each controller of each participating storage array.
- Each participating storage array to receive a PREPARE request is defined as a slave.
- the method further includes suspending I/O to the LU member and determining whether the timestamp fits within a write Input/Output (I/O) queue interval of the slave, when the slave receives the PREPARE request, flushing each write I/O in the write I/O queue interval that is older than the timestamp when the timestamp fits in the write I/O queue interval, and performing at least one of: (a) creating a snapshot of the LU member, (b) resuming I/O, (c) logging a PREPARED state to a persistent memory, or (d) sending a PREPARE-ACK message to the master.
- I/O write Input/Output
- a computer-readable medium having computer-executable instructions for performing a method, where the method includes applying a write Input/Output (I/O) queue interval to a Logical Unit (LU) member of a consistency group (CG).
- a storage array where the LU member of the CG resides is a participating storage array.
- the method also includes marking each write I/O with a timestamp and suspending I/O from the participating storage array to the LU member of the CG upon the participating storage array receiving a snapshot request from a master storage array.
- the snapshot request has a snapshot request timestamp.
- the method further includes determining whether the snapshot request timestamp is within the write I/O queue interval of the participating storage array.
- the participating storage array When the snapshot request timestamp is determined to be within the write I/O queue interval of the participating storage array, the participating storage array performs at least one of: (a) completing each write I/O older than the snapshot request timestamp, (b) creating a local snapshot for the LU member of the CG, or (c) resuming I/O to the LU member of the CG.
- FIG. 1 A displays a block diagram of a multi-array storage database
- FIG. 1 B displays a block diagram of a plurality of write I/Os across a plurality of consistency group members of a storage database
- FIGS. 2A and 2B are flow charts illustrating an implementation of a snapshot request on a multi-array storage database
- FIG. 3 is a flow chart illustrating a method for implementing multi- array consistency groups using a write queuing mechanism
- FIG. 4 is a flow chart illustrating a further embodiment of a method for implementing multi-array consistency groups using a write queuing mechanism.
- FIGS. 1A and 1 B a block diagram of a multi-array storage database and a block diagram illustrating a plurality of write I/Os across a plurality of consistency group members of a storage database are displayed.
- a storage database 102 may comprise multiple storage arrays 104, with Logical Units (LUs) located on different storage arrays.
- a consistency group (CG) may comprise of one or more LUs across a multitude of storage arrays to support creating a snapshot of all CG members as a single atomic operation.
- a host visible small computer system interface (SCSI) Logical Unit (LU) may be mapped to a virtual volume 106, for instance, when a storage virtual ization manager (SVM) 108 is deployed in the storage array 104.
- Virtual volume 106 may be derived from a capacity of one or more storage pools 110 in a storage array 104.
- FIG. 1 B displays three virtual volumes, VV1 , VV2, VV3, with a plurality of queued write I/Os, W11 , W12, W13, W21 , W22, W23, W31 , W32, W33.
- a consistency group may include VV1 , VV2, and VV3, however it is appreciated that any number of virtual volumes may be included in the consistency group.
- a write I/O queuing mechanism in a storage array controller cache 112 may be used to create a time window during which snapshots may be created over multiple storage arrays 104.
- the write I/O queuing mechanism may be applied to LUs that are members of a consistency group.
- a storage array that includes an LU member of a consistency group may be referred to as a participating storage array 114.
- Each of the participating storage arrays 114 may have a common notion of time, such as through the use of a distributed clock synchronization mechanism 116.
- the distributed clock synchronization mechanism 116 may be a Network Time Protocol (NTP).
- NTP Network Time Protocol
- One or more write I/Os may be queued for an LU in a First-In-First- Out (FIFO) order.
- the FIFO order may be used regardless of whether the write I/O has a Logical Block Address (LBA) that may overlap with the LBA of a write that is already in a cache memory 112 of a storage array controller 118.
- LBA Logical Block Address
- Each write I/O may be marked with a timestamp from the distributed clock synchronization mechanism 116 used by the participating storage arrays 114.
- the write I/O queue for an LU in a consistency group may represent a time interval from current time to the timestamp of the oldest write I/O in the queue.
- the storage array controller 118 may keep enough write I/Os in the queue such that the time interval represented by the write I/O queue is greater than the longest latency for a message communicated between the participating storage arrays 114.
- a participating storage array 114 may suspend I/O to a consistency group member when the participating storage array 114 receives a snapshot request from a master storage array 114a.
- the master storage array 114a may be defined as the storage array that receives a snapshot request from at least one of a user or a host.
- the participating storage array 114 may determine whether the timestamp of the snapshot request from the master storage array 114a is within the write I/O queue interval. If the snapshot request timestamp is within the write queue interval, the participating storage array 114 may complete writes that are older than the consistency group snapshot request timestamp, create a local snapshot for the LU member of the consistency group, and resume I/O to the LU member of the consistency group.
- a consistency group snapshot may include writes W11 , W21 , and W31 , and not include later writes. However, due to delays in a multi-array system, by the time the last storage array suspends the last LU member of the consistency group, writes W22, W12, W32, and W23 have already been enqueued. For the consistency group snapshot to be successful, the queues in the participating storage arrays 114 may be large enough such that writes W22, W12, W32, and W23 are still on the respective participating storage array queue and not written to the LU member of the consistency group when the participating storage arrays 114 receive the consistency group snapshot request. If any of W11 , W21 , and W31 is still in the queue, each may be flushed to a member LU before the local snapshots are created.
- Each participating storage array 114 of a consistency group may exchange test messages with the other participating storage arrays, such as on a regular basis, to determine a roundtrip latency.
- the roundtrip latency may be used to determine a minimum time interval of the write I/O queue interval.
- it is contemplated that setting the minimum time interval using the roundtrip latency may not always be feasible.
- the size of the queue for an LU may be limited by a storage array-wide threshold for how much cache memory each LU in a consistency group is allowed to utilize.
- the write queuing mechanism may be deployed for storage arrays that include a battery-backed cache memory. Further, the cache memory may be mirrored to another controller in the storage array, such as for redundancy purposes.
- FIGS. 2A and 2B flow charts are depicted illustrating an implementation of a snapshot request on a multi-array storage database.
- the coordination of the consistency group snapshot creation may leverage the two-phase commit (2PC) protocol.
- a controller may be defined as a master of the transaction 200 when a consistency group snapshot is initiated on the controller of a participating storage array.
- the transaction 200 implementing the snapshot request may proceed according to the flow charts of FIGS. 2A and 2B.
- a beginning of transaction 200 is timestamped. For instance, a master may timestamp the beginning of transaction 200 according to the distributed clock synchronization mechanism.
- a PREPARE request is sent all the participating storage array controllers in the consistency group. For instance, the master may send the PREPARE request to all the participating storage array controllers in the consistency group.
- Each participating storage array to receive a PREPARE request may be defined as a slave.
- I/O to the LU member of the consistency group is suspended. For instance, the slave may suspend I/O upon receiving a PREPARE request.
- a fit query is transmitted, the fit query including whether the consistency group timestamp from the master fits within the write I/O queue interval of the slave. For instance, the fit query may be transmitted to the slave's controller. If the result of operation 208 is no, (i.e., the timestamp does not fit within the write I/O queue interval), in operation 210, an ABORT is logged and an ABORT-ACK is sent. For instance, the slave may log ABORT to a persistent memory and send an ABORT-ACK message to the master. The transaction 200 may then proceed to operation 220, explained below.
- write I/Os that are older than the timestamp of transaction 200 are flushed. For instance, the slave may flush any write I/Os in the queue that are older than the timestamp of transaction 200.
- a snapshot of the LU is created. For instance, the slave may create a snapshot of the LU.
- I/O to the LU is resumed. For instance, the slave may resume I/O to the LU.
- a PREPARED state is logged and a PREPARE-ACK message is sent. For instance, the slave may log a PREPARED state to a persistent memory, and the slave may send a PREPARE-ACK message to the master. The transaction may then proceed to operation 220.
- a receive query is transmitted, the receive query including whether the master received PREPARE-ACK messages from all slaves. For instance, the receive query may be transmitted to the master. If the result of operation 220 is no, in operation 222, a ROLLBACK message is issued. For instance, the master may issue a ROLLBACK message to all slaves. In operation 224, the ROLLBACK state is logged, and any locks are released. For instance, when a slave receives the ROLLBACK message, the slave may log the ROLLBACK state to a persistent memory, and the slave may release any locks the slave may have held on behalf of the global transaction 200. In operation 226, the snapshot taken in operation 214 is deleted.
- the slave may delete the snapshot taken in operation 214.
- a ROLLBACK-ACK message is sent.
- the slave may send the ROLLBACK-ACK message to the master.
- the transaction 200 may then end 236, the results of which are explained below. If the result of operation 220 is yes (i.e., a PREPARE-ACK message was received, such as by the master from all slaves), transaction 200 may proceed to operation 230.
- a COMMIT request is issued.
- the master may issue the COMMIT request to all slaves.
- a COMMIT state is logged, and any locks are released.
- the slave may log the COMMIT state to a persistent memory, and the slave may release any locks it was holding on behalf of the global transaction 200.
- a COMMIT-ACK message is sent.
- the slave may send a COMMIT-ACK message to the master.
- the transaction 200 may then end 236. The result of transaction 200 at end 236 may therefore depend on what message the master receives from the slaves.
- the global transaction 200 succeeded, and a consistent snapshot has been taken of all the LUs in the consistency group. If the -master receives ROLLBACK-ACK messages from all slaves, the global transaction 200 did not result in a consistent snapshot, but each slave cleaned up (e.g., released any locks and deleted the snapshot taken in operation 214).
- the 2PC protocol may be a variation called 2PC with presumed ABORT.
- a timer is started when a PREPARE request is sent.
- the master may start a timer when the master sends a PREPARE request to all the participating storage array controllers in the consistency group (operation 204). If the timer expires before the master receives responses from all slaves, a ROLLBACK message is sent. For instance, if the timer expires without receiving a response from all slaves, the master may assume the global transaction 200 needs to be aborted, and the master may send a ROLLBACK message to all slaves.
- transaction 200 may be treated as though the result to operation 220 is no.
- a PREPARE-ACK message is sent after the time expires, the ROLLBACK message may be resent. For instance, if a slave sends a PREPARE-ACK message to the master after the timer expires, such as where a slave went down and came back up after the ROLLBACK message was sent, the master may then resend the ROLLBACK message to that slave so the slave may cleanup.
- each slave may require a manual ROLLBACK.
- the manual ROLLBACK is performed by a user.
- SSDs Solid State Drives
- write I/Os may be flushed from the cache memory to the other storage device using a conventional controller cache management mechanism. Then, the write I/O queues are maintained on the other storage device.
- These computer program instructions may also be stored in a computer-readable tangible medium (thus comprising a computer program product) that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable tangible medium produce an article of manufacture including instruction means which implement the function/act specified in the flowchart.
- the write I/O queuing mechanism may be implemented as a compliment to existing RAID (redundant array of independent disks) engine, which may support consistency groups that span multiple storage arrays.
- RAID redundant array of independent disks
- the present disclosure may use any local snapshot mechanism known in the art that a storage array supports.
- the local snapshot mechanism may not be required to be aware of a multi-storage array consistency group, or of the write I/O queue in order to function properly.
- use of the 2PC protocol may enable automatic clean-up of storage arrays in case a consistency group snapshot does not complete.
- Method 300 may apply a write Input/Output (I/O) queue interval to a Logical Unit (LU) member of a consistency group (CG) 302.
- a storage array where the LU member of the CG resides may be a participating storage array.
- Method 300 may mark each write I/O with a timestamp 304.
- Method 300 may suspend I/O from the participating storage array to the LU member of the CG upon the participating storage array receiving a snapshot request from a master storage array 306.
- the snapshot request may have a snapshot request timestamp.
- Method 300 may determine whether the snapshot request timestamp is within the write I/O queue interval of the participating storage array 308.
- the participating storage array may perform at least one of: (a) completing each write I/O older than the snapshot request timestamp, (b) creating a local snapshot for the LU member of the CG, or (c) resuming I/O to the LU member of the CG.
- Applying a write I/O queue interval to a LU member of a CG of method 300 may include queuing write I/Os in a First-In-First-Out (FIFO) order. Marking each write I/O with a timestamp of method 300 may includes synchronizing each participating storage array of the CG according to a distributed clock synchronization mechanism.
- the distributed clock synchronization mechanism may be a network time protocol (NTP).
- Applying a write I/O queue interval to a LU member of a CG of method 300 may include representing the write I/O queue interval as a time interval from current time to the timestamp of the oldest write I/O in the queue.
- Method 300 may further include exchanging a test message between each participating storage array of the CG for determining a roundtrip latency.
- Method 300 may further include determining a minimum time interval of the write I/O queue interval using the roundtrip latency.
- Method 400 may initiate a consistency group (CG) snapshot on a controller of a CG storage array 402.
- the CG storage array with the controller may be defined as a master, and a storage array where a Logical Unit (LU) member of the CG resides may be a participating storage array.
- Method 400 may record a timestamp for the initiated CG snapshot 404.
- Method 400 may send a PREPARE request from the master to each controller of each participating storage array 406.
- Each participating storage array to receive a PREPARE request may be defined as a slave.
- Method 400 may suspend I/O to the LU member and determining whether the timestamp fits within a write Input/Output (I/O) queue interval of the slave, when the slave receives the PREPARE request 408.
- Method 400 may flush each write I/O in the write I/O queue interval that is older than the timestamp when the timestamp fits in the write I/O queue interval 410.
- Method 400 may perform at least one of: (a) creating a snapshot of the LU member, (b) resuming I/O, (c) logging a PREPARED state to a persistent memory, or (d) sending a PREPARE-ACK message to the master 412.
- Method 400 may further include issuing a COMMIT request from the master to each slave when the master receives the PREPARE-ACK message from each slave.
- each slave may perform at least one of: (a) logging a new state to a persistent memory, (b) releasing a lock held on behalf of a global transaction, (c) deleting the snapshot of the LU member, or (d) sending a COMMIT-ACK message to the master.
- the slave may log an ABORT message to a persistent memory and the slave sends an ABORT message to the master.
- Method 400 may further include issuing a ROLLBACK message from the master to each slave when the master receives the ABORT message from at least one slave.
- each slave may perform at least one of: (a) logging a new state to a persistent memory, (b) releasing a lock held on behalf of a global transaction, (c) deleting the snapshot of the LU member, or (d) sending a ROLLBACK-ACK message to the master.
- Method 400 may further include initiating a timer, the timer may be initiated upon the step of sending a PREPARE request from the master to each controller of each participating storage array of method 400.
- Method 400 may further include sending a first ROLLBACK message to each slave when the timer expires prior to the master receiving a response from each slave.
- Method 400 may further include sending a second ROLLBACK message to a slave when the slave sends a PREPARE-ACK message after the first ROLLBACK message was sent.
- the methods disclosed may be implemented as sets of instructions or software readable by a device.
- Such a software package may be a computer program product which employs a computer-readable storage medium including stored computer code which is used to program a computer to perform the disclosed function and process of the present disclosure.
- the computer-readable medium may include, but is not limited to, any type of conventional floppy disk, optical disk, CD-ROM, magnetic disk, hard disk drive, magneto- optical disk, ROM, RAM, EPROM, EEPROM, magnetic or optical card, or any other suitable media for storing electronic instructions.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Quality & Reliability (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
Description
Claims
Priority Applications (6)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US13/139,462 US8566281B2 (en) | 2008-12-18 | 2009-01-23 | Method for implementing multi-array consistency groups using a write queuing mechanism |
JP2011542100A JP5452615B2 (en) | 2008-12-18 | 2009-01-23 | Method for implementing multi-array consistency groups using a write queuing mechanism |
KR1020117013941A KR101351222B1 (en) | 2008-12-18 | 2009-01-23 | Method for implementing multi-array consistency groups using a write queuing mechanism |
EP09833765.2A EP2359251B1 (en) | 2008-12-18 | 2009-01-23 | Method for implementing multi-array consistency groups using a write queuing mechanism |
CN200980148789.2A CN102239479B (en) | 2008-12-18 | 2009-01-23 | Method for implementing multi-array consistency groups using a write queuing mechanism |
TW098115501A TWI400651B (en) | 2008-12-18 | 2009-05-11 | A method for implementing a multi-array coherency group, and a computer-readable medium having computer-executable instructions for performing the method |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US20302308P | 2008-12-18 | 2008-12-18 | |
US61/203,023 | 2008-12-18 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2010071661A1 true WO2010071661A1 (en) | 2010-06-24 |
Family
ID=42269097
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/US2009/000430 WO2010071661A1 (en) | 2008-12-18 | 2009-01-23 | Method for implementing multi-array consistency groups using a write queuing mechanism |
Country Status (7)
Country | Link |
---|---|
US (1) | US8566281B2 (en) |
EP (1) | EP2359251B1 (en) |
JP (1) | JP5452615B2 (en) |
KR (1) | KR101351222B1 (en) |
CN (1) | CN102239479B (en) |
TW (1) | TWI400651B (en) |
WO (1) | WO2010071661A1 (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140201149A1 (en) * | 2013-01-16 | 2014-07-17 | Ca, Inc. | Consistent bookmark |
Families Citing this family (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9507841B2 (en) * | 2011-06-16 | 2016-11-29 | Sap Se | Consistent backup of a distributed database system |
US9569310B2 (en) * | 2013-02-27 | 2017-02-14 | Netapp, Inc. | System and method for a scalable crash-consistent snapshot operation |
US9280296B2 (en) * | 2013-05-23 | 2016-03-08 | Globalfoundries Inc. | Recovery from failure of primary storage volumes by using mirrored data maintained with host timestamps |
US9110601B2 (en) | 2013-06-24 | 2015-08-18 | Sap Se | Backup lifecycle management |
US9990161B2 (en) * | 2014-12-17 | 2018-06-05 | Vmware, Inc. | Consistent replication of virtual computing instance data |
US9912748B2 (en) * | 2015-01-12 | 2018-03-06 | Strato Scale Ltd. | Synchronization of snapshots in a distributed storage system |
CN106250322B (en) * | 2016-08-12 | 2019-11-19 | 华为技术有限公司 | A kind of method and apparatus for writing data |
CN106648993B (en) * | 2016-12-30 | 2019-07-19 | 杭州宏杉科技股份有限公司 | The method and device of consistency group snapshot management |
US10423609B1 (en) * | 2017-03-29 | 2019-09-24 | Amazon Technologies, Inc. | Consistent snapshot points in a distributed storage service |
CN109726151B (en) * | 2017-10-27 | 2022-11-08 | 伊姆西Ip控股有限责任公司 | Method, apparatus, and medium for managing input-output stack |
US11048590B1 (en) | 2018-03-15 | 2021-06-29 | Pure Storage, Inc. | Data consistency during recovery in a cloud-based storage system |
US10929376B2 (en) * | 2018-03-22 | 2021-02-23 | Microsoft Technology Licensing, Llc | Performing transactions in distributed transactional memory systems |
US11144408B2 (en) * | 2019-10-24 | 2021-10-12 | EMC Holding Company, LLC | System and method for improving asynchronous replication performance in dual controller storage systems |
WO2022157784A1 (en) | 2021-01-25 | 2022-07-28 | Volumez Technologies Ltd. | Operating system based storage method and system |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7266652B1 (en) * | 2004-06-30 | 2007-09-04 | Emc Corporation | System and method for managing data consistency between different data volumes on one or more data storage systems in a data storage environment |
US20070220311A1 (en) * | 2006-02-17 | 2007-09-20 | Michael Lewin | Cross tagging of data for consistent recovery |
US20080243952A1 (en) * | 2007-03-28 | 2008-10-02 | Erez Webman | Group Stamping Style Asynchronous Replication Utilizing A Loosely-Accurate Global Clock |
Family Cites Families (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6243141B1 (en) * | 1997-05-06 | 2001-06-05 | Matsushita Electric Industrial Co., Ltd. | Video signal processing device |
US6708227B1 (en) * | 2000-04-24 | 2004-03-16 | Microsoft Corporation | Method and system for providing common coordination and administration of multiple snapshot providers |
JP4255699B2 (en) * | 2003-01-20 | 2009-04-15 | 株式会社日立製作所 | Storage device control apparatus control method and storage device control apparatus |
US7127577B2 (en) | 2003-01-21 | 2006-10-24 | Equallogic Inc. | Distributed snapshot process |
US8037264B2 (en) * | 2003-01-21 | 2011-10-11 | Dell Products, L.P. | Distributed snapshot process |
TWI252977B (en) * | 2004-11-22 | 2006-04-11 | Inventec Corp | Disk array data protection system and method thereof |
US20070033356A1 (en) * | 2005-08-03 | 2007-02-08 | Boris Erlikhman | System for Enabling Secure and Automatic Data Backup and Instant Recovery |
US7765187B2 (en) | 2005-11-29 | 2010-07-27 | Emc Corporation | Replication of a consistency group of data storage objects from servers in a data network |
US7516352B2 (en) * | 2006-03-21 | 2009-04-07 | International Business Machines Corporation | Isolating a drive from disk array for diagnostic operations |
US8140785B2 (en) * | 2006-06-29 | 2012-03-20 | International Business Machines Corporation | Updating metadata in a logical volume associated with a storage controller for data units indicated in a data structure |
US7644204B2 (en) * | 2006-10-31 | 2010-01-05 | Hewlett-Packard Development Company, L.P. | SCSI I/O coordinator |
JP4951326B2 (en) * | 2006-12-12 | 2012-06-13 | 株式会社野村総合研究所 | Computer program for optimizing the processing order of I / O requests |
US8255562B2 (en) * | 2008-06-30 | 2012-08-28 | International Business Machines Corporation | Adaptive data throttling for storage controllers |
-
2009
- 2009-01-23 CN CN200980148789.2A patent/CN102239479B/en not_active Expired - Fee Related
- 2009-01-23 KR KR1020117013941A patent/KR101351222B1/en not_active IP Right Cessation
- 2009-01-23 JP JP2011542100A patent/JP5452615B2/en not_active Expired - Fee Related
- 2009-01-23 US US13/139,462 patent/US8566281B2/en not_active Expired - Fee Related
- 2009-01-23 EP EP09833765.2A patent/EP2359251B1/en active Active
- 2009-01-23 WO PCT/US2009/000430 patent/WO2010071661A1/en active Application Filing
- 2009-05-11 TW TW098115501A patent/TWI400651B/en not_active IP Right Cessation
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7266652B1 (en) * | 2004-06-30 | 2007-09-04 | Emc Corporation | System and method for managing data consistency between different data volumes on one or more data storage systems in a data storage environment |
US20070220311A1 (en) * | 2006-02-17 | 2007-09-20 | Michael Lewin | Cross tagging of data for consistent recovery |
US20080243952A1 (en) * | 2007-03-28 | 2008-10-02 | Erez Webman | Group Stamping Style Asynchronous Replication Utilizing A Loosely-Accurate Global Clock |
Non-Patent Citations (2)
Title |
---|
"EMC NetWorker PowerSnap Module for EMC Symmetrix DMX Version 2.2.1 ADMINISTRATION GUIDE", PIN 300-003-670 A, 1 July 2006 (2006-07-01), XP008139876, Retrieved from the Internet <URL:http://docs.iws.cs.uni-magdeburg.de/admin/networker-7.3.2/networkermodules/powersnap/symmetrix2.2.1/nm_powersnap_symmetrix_2.2.1ag.pdf> [retrieved on 20090224] * |
See also references of EP2359251A4 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140201149A1 (en) * | 2013-01-16 | 2014-07-17 | Ca, Inc. | Consistent bookmark |
Also Published As
Publication number | Publication date |
---|---|
US20110246423A1 (en) | 2011-10-06 |
JP2012513061A (en) | 2012-06-07 |
CN102239479B (en) | 2014-06-04 |
EP2359251A1 (en) | 2011-08-24 |
TWI400651B (en) | 2013-07-01 |
CN102239479A (en) | 2011-11-09 |
US8566281B2 (en) | 2013-10-22 |
TW201025128A (en) | 2010-07-01 |
EP2359251B1 (en) | 2014-03-12 |
KR101351222B1 (en) | 2014-01-13 |
JP5452615B2 (en) | 2014-03-26 |
EP2359251A4 (en) | 2013-02-20 |
KR20110097846A (en) | 2011-08-31 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
EP2359251B1 (en) | Method for implementing multi-array consistency groups using a write queuing mechanism | |
US8407435B2 (en) | Efficiently creating a snapshot of a large consistency group using multiple commands including a snapshot preparation command | |
US8788772B2 (en) | Maintaining mirror and storage system copies of volumes at multiple remote sites | |
US8468313B2 (en) | Asynchronous replication with write concurrency grouping | |
EP3198445B1 (en) | Snapshot and replication of a multi-stream application on multiple hosts at near-sync frequency | |
US7908448B1 (en) | Maintaining data consistency in mirrored cluster storage systems with write-back cache | |
US8689047B2 (en) | Virtual disk replication using log files | |
US9335931B2 (en) | System and method for making snapshots of storage devices | |
US7594138B2 (en) | System and method of error recovery for backup applications | |
EP2304569B1 (en) | Performing a data write on a storage device | |
US20050071710A1 (en) | Method, system, and program for mirroring data among storage sites | |
US10365978B1 (en) | Synchronization of snapshots in a distributed consistency group | |
US20040260896A1 (en) | Method, system, and article of manufacture for consistent copying of storage volumes | |
US9213752B2 (en) | Asynchronous pausing of the formation of consistency groups | |
EP2569921B1 (en) | System and method for providing reliable storage | |
US10289320B1 (en) | Utilizing a virtual backup appliance within data storage equipment | |
WO2017211099A1 (en) | Data backup method and apparatus | |
CN110413370B (en) | Method and system for implementing data backup of virtual machine depending on original equipment mapping disk | |
JP2006221487A (en) | Remote copy system | |
US9928285B1 (en) | Optimized cloning for backup to disk | |
Liu et al. | ELVM: A LVM-Based remote replication system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
WWE | Wipo information: entry into national phase |
Ref document number: 200980148789.2 Country of ref document: CN |
|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 09833765 Country of ref document: EP Kind code of ref document: A1 |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2009833765 Country of ref document: EP |
|
WWE | Wipo information: entry into national phase |
Ref document number: 13139462 Country of ref document: US |
|
ENP | Entry into the national phase |
Ref document number: 2011542100 Country of ref document: JP Kind code of ref document: A |
|
ENP | Entry into the national phase |
Ref document number: 20117013941 Country of ref document: KR Kind code of ref document: A |
|
NENP | Non-entry into the national phase |
Ref country code: DE |