WO2016122723A1 - Procédés permettant de faciliter des services de stockage à haute disponibilité de n façons et dispositifs correspondants - Google Patents

Procédés permettant de faciliter des services de stockage à haute disponibilité de n façons et dispositifs correspondants Download PDF

Info

Publication number
WO2016122723A1
WO2016122723A1 PCT/US2015/051631 US2015051631W WO2016122723A1 WO 2016122723 A1 WO2016122723 A1 WO 2016122723A1 US 2015051631 W US2015051631 W US 2015051631W WO 2016122723 A1 WO2016122723 A1 WO 2016122723A1
Authority
WO
WIPO (PCT)
Prior art keywords
storage controllers
active
passive
controllers
active storage
Prior art date
Application number
PCT/US2015/051631
Other languages
English (en)
Inventor
Joseph Caradonna
Rajesh Rajaraman
Ahmed SHIHAB
Original Assignee
Netapp, Inc.
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Priority claimed from US14/608,756 external-priority patent/US9632890B2/en
Application filed by Netapp, Inc. filed Critical Netapp, Inc.
Publication of WO2016122723A1 publication Critical patent/WO2016122723A1/fr

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00—Error detection; Error correction; Monitoring
    • G06F11/07—Responding to the occurrence of a fault, e.g. fault tolerance
    • G06F11/16—Error detection or correction of the data by redundancy in hardware
    • G06F11/20—Error detection or correction of the data by redundancy in hardware using active fault-masking, e.g. by switching out faulty elements or by switching in spare elements
    • G06F11/2053—Error detection or correction of the data by redundancy in hardware using active fault-masking, e.g. by switching out faulty elements or by switching in spare elements where persistent mass storage functionality or persistent mass storage control functionality is redundant
    • G06F11/2089—Redundant storage control functionality
    • G06F11/2092—Techniques of failing over between control units
    • 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

Definitions

  • FIELD FIELD
  • a storage fabric may include multiple storage controllers, including physical and/or virtual storage controllers, which store and manage data on behalf of clients.
  • one common technique to provide high availability is to cross wire storage drives or fabric between two physical storage controllers to provide a seamless transfer if one of the physical storage controllers fails.
  • a method for facilitating n-way high availability storage services includes monitoring, with one or more passive storage controllers, a plurality of active storage controllers. A determination is made, with one of the passive storage controllers, when a failure of one of the active storage controllers has occurred based on the monitoring. Storage device(s) previously assigned to the one of the active storage controllers are remapped, with the passive storage controller, to the passive storage controller. The transaction log associated with the failed storage controller is retrieved by the passive storage controller, from a transaction log database. Transaction(s) in the transaction log are replayed by the passive storage controller, and upon completion the passive storage controller transitions its role to an active storage controller. When the previously failed controller is healed, it returns to the storage fabric with the role of a passive controller.
  • An apparatus includes a processor and a memory coupled to the processor which is configured to be capable of executing programmed instructions comprising and stored in the memory to monitor with a passive storage controller a plurality of active storage controllers. A determination is made with the passive storage controller when a failure of one of the active storage controllers has occurred based on the monitoring. Storage device(s) previously assigned to the one of the active storage controllers are remapped to the passive storage controller. The transaction log associated with the failed storage controller is retrieved by a passive storage controller, from a transaction log database. Transaction(s) in the transaction log are replayed by the passive storage controller, and upon completion the passive storage controller transitions its role to an active storage controller. When the previously failed controller is healed, it returns to the storage fabric with the role of a passive controller.
  • a non-transitory computer readable medium having stored thereon instructions for facilitating n-way high availability storage services includes executable code which when executed by a processor, causes the processor to perform steps including monitoring with a passive storage controller a plurality of active storage controllers. A determination is made with the passive storage controller when a failure of one of the active storage controllers has occurred based on the monitoring. Storage device(s) previously assigned to the one of the active storage controllers are remapped with the passive storage controller to the passive storage controller, The transaction log associated with the failed storage controller is retrieved by a passive storage controller, from a transaction log database. Transaction(s) in the transaction log are replayed by the passive storage controller, and upon completion the passive storage controller transitions its role to an active storage controller.
  • This technology provides a number of advantages including more efficient and effective methods, non-transitory computer readable media, and host devices for facilitating high availability storage services.
  • a storage controller can assume the role and responsibility of a storage controller that has failed, without having to return traffic to a recovered storage controller, reserve headroom in the active controller, or replicate data.
  • This technology is highly scalable and high availability can be provided for many or "n" active storage controllers by only one passive storage controller, although more passive storage controllers can be utilized depending on the desired level of protection.
  • FIG. 1 a block diagram of a network environment with an exemplary storage fabric including a plurality of exemplary storage controllers
  • FIG. 2 is a block diagram of an exemplary storage controller
  • FIG. 3 is a flowchart of an exemplary method for facilitating n-way high availability storage services with an active storage controller;
  • FIG. 4 is a flowchart of an exemplary method for facilitating high availability storage services with a passive storage controller;
  • FIG. 5 is another exemplary network environment with three active storage controllers and a passive storage controller
  • FIG. 6 is the exemplary network environment of FIG. 5 in which an active storage controller has failed and a formerly passive storage controller has become an active storage controller
  • FIG. 7 is the exemplary network environment of FIGS. 5 and 6 in which an active storage controller that failed has become a passive storage controller.
  • FIG. 1 this environment 10(1) can include other numbers and types of systems, devices, components, and/or elements in other configurations, such as multiple numbers of each of these apparatuses and devices.
  • the storage controllers 16( 1 )- 16(11) can be virtual storage controllers running as virtual machines or physical storage controllers included in purpose built storage arrays. This technology provides a number of advantages including methods, non-transitory computer readable medium, and devices that relatively efficiently facilitate n-way high availability of storage services provided by storage controllers.
  • Each of the client devices 14( l )- 14(n) in this example can include a processor, a memory, a network interface, an input device, and a display device, which are coupled together by a bus or other link, although each of the client devices 14(l)-14(n) can have other types and numbers of components or other elements and other numbers and types of network devices could be used.
  • the client devices 14(l)-14(n) may run interface applications that provide an interface to make requests for and send content and/or data to the storage controllers 16(l)-16(n) via the communication network(s) 20, for example.
  • Each of the client devices 14(l)-14(n) may be, for example, a conventional personal computer, a workstation, a smart phone, a virtual machine running in a cloud, or other processing and/or computing device.
  • the transaction log database 21 can optionally be hosted by a shared memory server, which includes a processor, a memory, and a network interface coupled together by a bus or other communication link, and can be an in-memory database or cache (e.g., the ElastiCache web service product available from Amazon.com, Inc. of Seattle, Washington) or flash-based storage, for example, although other types of storage can also be used for the transaction log database 21. .
  • the transaction log database 21 is configured to store a plurality of transaction logs, each associated with an active storage controller, which are used by the active storage controllers to store information associated with transactions received from the client devices 14(l)-14(n), for example, although the transaction logs can also be used to store other information received from other sources, as described and illustrated in more detail later.
  • the communication network(s) 20 in this example may employ any suitable interface mechanisms and network communication technologies including, for example, teletraffic in any suitable form (e.g., voice, modem, and the like), Public Switched Telephone Network (PSTNs), Ethernet-based Packet Data Networks (PDNs), combinations thereof, and the like.
  • PSTNs Public Switched Telephone Network
  • PDNs Ethernet-based Packet Data Networks
  • the communication network(s) 20 may also comprise any local area network and/or wide area network (e.g., Internet), although any other type of traffic network topologies may be used.
  • FIG. 2 a block diagram of an exemplary one of the storage controllers 16( 1 )- 16(n) is illustrated.
  • the storage controller 16 in this example includes a processor 24, a memory 26, at least one network interface 28, storage devices 22(l)-22(n), and an operating system 34 coupled together by a bus 28 or other communication link.
  • the storage controller 16 can be operating in an active or passive state, as described and illustrated in more detail later.
  • an active state the storage controller 16 services traffic associated with the storage and retrieval of data stored by one or more of the storage devices 22(l)-22(n), for example.
  • a passive state the storage controller 16 monitors one or more active storage controllers to determine when one of the active storage controllers fails, at which time the storage controller 16 operating in a passive state assumes the role of the failed one of the active storage controllers, as described and illustrated in more detail later.
  • the processor 24 of the storage controller 16 may execute programmed instructions stored in the memory 26 for various functions and/or operations illustrated and described herein.
  • the memory 26 of the storage controller 16 may include any of various forms of read only memory (ROM), random access memory (RAM), Flash memory, non- volatile, or volatile memory, or the like, or a combination of such devices, for example.
  • the network interface 28 operatively couples and communicates between the storage controller 16. the client devices 14(l)-14(n), and the transaction log database 21 , which are all coupled together by the communication network(s) 20, although other types and numbers of connections and configurations to other devices and elements can also be used.
  • the communication network(s) 20 can use TCP/IP over Ethernet and industry- standard protocols, including NFS, CIFS, SOAP, XML, LDAP, and SNMP, although other types and numbers of communication networks, can also be used.
  • the storage devices 22(1 )-22(n) in this example can include conventional magnetic disks, solid-state drives (SSDs), or any other type of stable, non-volatile storage device suitable for storing large quantities of data.
  • the storage devices 22(l)-22(n) may be organized into one or more volumes of Redundant Array of Inexpensive Disks (RAID).
  • RAID Redundant Array of Inexpensive Disks
  • client devices 14(l)-14(n), storage controllers 16(1)- 16(n), and transaction log database 21 are described herein, it is to be understood that the devices and systems of the examples described herein are for exemplary purposes, as many variations of the specific hardware and software used to implement the examples are possible, as will be appreciated by those skilled in the relevant art(s). In addition, two or more computing systems or devices can be substituted for any one of the systems in any embodiment of the examples.
  • the examples also may be embodied as a non-transitory computer readable medium having instructions stored thereon for one or more aspects of the present technology as described and illustrated by way of the examples herein, as described herein, which when executed by the processor, cause the processor to carry out the steps necessary to implement the methods of this technology as described and illustrated with the examples herein.
  • An exemplary method for facilitating n-way high availability storage services will now be described with reference to FIGS. 1 -7. Referring more specifically to FIG. 3, an exemplary method for facilitating high availability storage services with an active one of the storage controllers 16(l)-16(n) is illustrated.
  • the active one of the storage controllers 16(l)-16(n) receives one or more transactions, such as from one or more of the client devices 14(l)-14(n), for example, although the transactions can be received from other sources including internal processes executing on the active one of the storage controllers 16(1)- 16(n).
  • Exemplary transactions can include requests from one of the client devices 14( l)- 14(n) to read or write data, although other numbers and types of transactions can be received in step 300.
  • the active one of the storage controllers 16( 1 )- 16(n) stages the transactions, such as by storing the one or more transactions in the transaction log database 21 in a transaction log associated with the active one of the storage controllers 16( l )-16(n), for example.
  • the transactions are staged because they may be received more quickly than they can be processed by the one of the active one of the storage controllers 16(l)-16(n).
  • processing the transactions requires a relatively long period of time considering the mechanical nature of the operation of storing and retrieving data on disks of the storage devices 22(l)-22(n).
  • the active one of the storage controllers 16( l )- 16(n) can send the one or more transactions to the transaction log database 21 with a unique identifier of the active one of the storage controllers 16( l )-16(n).
  • the transaction log database 21 stores the one or more transactions in a transaction log associated with the active one of the storage controllers 16(l)-16(n), as identified based on the unique identifier.
  • only a subset of the one or more transactions received in step 300 are sent to the transaction log database 21, such as those write transactions that affect data stored by the storage devices 22(l)-22(n), for example.
  • step 304 the active one of the storage controllers 16(l)-16(n) executing on the host device 12 receives an acknowledgement that each transaction was successfully stored by the transaction log database 21. After receiving each acknowledgement, the active one of the storage controllers 16(l)-16(n) acknowledges the transaction to the source of the transactions, such as one or more of the client devices 14(l)-14(n), for example.
  • step 306 the active one of the storage controllers 16(l)-16(n) processes the transactions received in step 300 from the corresponding transaction log in the transaction log database 21, such as by retrieving requested data from one or more of the storage devices 22(1)- 22(n) and/or writing data to one or more of the storage devices 22( l )-22(n), for example.
  • step 400 in this example the passive one of the storage controllers 16(l)-16(n) monitors one or more active ones of the storage controllers 16(l)-16(n). Accordingly, the passive one of the storage controllers 16( l )- 16( n) may monitor any numbers of active ones of the storage controllers 16(l )-16(n) and/or other numbers of passive ones of the storage controllers 16(l)-16(n) could be used to monitor the active ones of the storage controllers 16(l )-16(n).
  • the monitoring can be based on a heartbeat signal periodically sent from the monitored one or more of the active ones of the storage controllers 16(l)-16(n) to the passive one of the storage controllers 16( 1 )- 16(n) using an interconnect or other communication link, for example.
  • the monitored one or more active ones of the storage controllers 16(1)- 16( n) can be configured to periodically initiate the heartbeat signal or the passive one of the storage controllers 16(l)-16(n) can periodically send a message using the interconnect or other communication link to prompt the monitored active ones of the storage controllers 16(l)-16(n) to send the heartbeat signal.
  • the heartbeat message received from each of the monitored active ones of the storage controllers 16( l )- 16(n) includes a unique identifier of the respective one of the active ones of the storage controllers 16(l)-16(n), which is used as described and illustrated in more detail later.
  • Other methods of monitoring the health of one or more of the active ones of the storage controllers 16(l)-16(n) also can be used.
  • the passive one of the storage controllers 16(l)-16(n) determines whether a monitored active one of the storage controllers 16(l)-16(n) has entered a failure state.
  • the passive one of the storage controllers 16(l)-16(n) can determine whether the active one of the storage controllers 16(l)-16(n) has failed based on whether it has received a heartbeat signal within a specified period of time since a prior heartbeat signal.
  • the active one of the storage controllers 16( l )- 16(n) can be configured to communicate to the passive one of the storage controllers 16(l)-16(n), using an interconnect or other communication link, that it has entered a failure state.
  • Other methods of determining that the active one of the storage controllers 16(l)-16(n) has failed also can be used.
  • the failure identified by the passive one of the storage controllers 16( l )- 16(n) can be of the one of the operating systems 34 of the monitored one of the active storage controllers 16(l)-16(n), a hypervisor failure, or a hardware failure, for example.
  • step 402 If the passive one of the storage controllers 16(l)-16(n) determines in step 402 that none of the monitored active ones of the storage controllers 16( l )-) 6(n) has failed, then the No branch is taken back to step 400 and the passive one of the storage controllers 16( l )- 16(n) continues to monitor active ones of the storage controllers 16(l )-16(n) and effectively wait for one of the active ones of the storage controllers 16(l)-16(n) to fail.
  • step 404 the passive one of the storage controllers 16( l )- 16(n) remaps at least one or more of the storage devices 22( l )-22(n) previously assigned to the failed active one of the storage controllers 16(l)-16(n) to be assigned to the passive one of the storage controllers 16(l)-16(n).
  • the remapped one or more of the storage devices 22(1)- 22(n) also can be virtual storage devices corresponding to one or more of the storage devices 22(l)-22(n) or portions thereof, for example.
  • the passive one of the storage controllers 16(l)-16(n) can make call(s) to an application programming interface (API) supported by the cloud platform provider, for example, although other methods of remapping the one or more of the storage devices 22(l)-22(n) can also be used.
  • API application programming interface
  • the passive one of the storage controllers 16(l)-16(n) also remaps the network interface 28, or more specifically a network interface controller (NIC) of the network interface 28, previously assigned to the failed active one of the storage controllers 16(l)-16(n) to be associated with the passive one of the storage controllers 16(l)-16(n).
  • NIC network interface controller
  • an application associated with one or more of the client devices 14(l)-14(n) previously communicating with the one of the operating systems 34 associated with the failed active one of the storage controllers 16( l )- 16(n) can communicate with the operating system 34 of the passive one of the storage controllers 16(l)-16(n).
  • the NIC can be remapped using call(s) to the API provided by the cloud platform provider or through IP address translation of the traffic received from one or more of the client devices 14(l)-14(n), as managed by the operating system 34, for example, although other methods o remapping the NIC can also be used.
  • step 406 the passive one of the storage controllers 16( 1 )- 16(n) retrieves the transaction log associated with the failed one of the active storage controllers 30(l)-30(n) from the transaction log database 21.
  • the passive one of the storage controllers 16(l)-16(n) can use a unique identifier of the failed active one of the storage controllers 16(l)-16(n), such as communicated with the heartbeat signal, for example, to retrieve the transaction log
  • step 408 the passive one of the storage controllers 16(l)-16(n) replays the transactions stored in the transaction log retrieved in step 406 and effectively assumes the role of the failed active one of the storage controllers 16(l)-16(n).
  • the failed active one of the storage controllers 16( 1 )- 16(n) performs a failure processing routine including performing a core dump and rebooting the associated operating system 34, for example. Upon rebooting, the failed active one of the storage controllers 16(l)-16(n) can effectively assume the role of the passive one of the storage controllers 16(l)-16(n).
  • FIG. 5 in another example, another exemplary network environment 10(2) with three active storage controllers 16(1), 16(2), and 16(3) and a passive storage controller 16(4) is illustrated. Additionally, the network environment 10(2) in this example includes three client devices 14(1), 14(2), 14(3), and a transaction log database.
  • the exemplary network environment 10(2) is illustrated in which one of the active storage controllers 16(2) (also referred to in FIG. 6 as “storage controller B") has failed and the formerly passive storage controller 16(4) (also referred to in FIG. 6 as “storage controller D”) has become an active storage controller 16(5).
  • the active storage controllers 16(2) also referred to in FIG. 6 as “storage controller B”
  • the formerly passive storage controller 16(4) also referred to in FIG. 6 as “storage controller D”
  • active storage controller B 16(2) fails, passive storage controller D 16(4) retrieves storage controller B's 16(2) transaction log from the transaction log database, and replays the transactions, as described and illustrated earlier with reference to FIG. 4. Thereafter, storage controller D transitions its role to an active storage controller 16(5).
  • the transaction log associated with the active storage controller B 16(2) that is retrieved and replayed was previously maintained by the active storage controller B 16(2) as described and illustrated earlier with reference to FIG. 3.
  • FIG. 7 an exemplary network environment 10(2) is illustrated in which the one of the active storage controllers 16(2) that failed has become a passive storage controller 16(6). Accordingly, in this example, once storage controller B is healed, it returns to the storage fabric as passive controller 16(6). [0046] Accordingly, with this technology, a passive storage controller can retrieve and replay transactions in a transaction log corresponding to a failed active storage controller and retrieved from a transaction log database. By maintaining transaction logs on a shared memory service, a passive storage controller can monitor any number of active storage controllers.
  • this technology is optimized for scalability and network administrators can control the ratio of passive and active storage controllers in order to provide a desired level of protection and availability. Further, high availability of storage controllers can advantageously be provided on a cloud platform without requiring replication of data and associated cost, with reduced disruption to applications utilizing the storage controllers, and with increased scalability.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Quality & Reliability (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Debugging And Monitoring (AREA)

Abstract

L'invention concerne un procédé, un support lisible par ordinateur non transitoire, et un appareil qui surveille, avec un contrôleur de stockage passif, une pluralité de contrôleurs de stockage actifs. Une détermination est faite par le contrôleur de stockage passif lorsqu'une défaillance de l'un des contrôleurs de stockage actif s'est produite sur la base de la surveillance. Le ou les dispositifs de stockage précédemment affectés à l'un des contrôleurs de stockage actifs sont remappés vers le contrôleur de stockage passif. Un journal de transactions associé à l'un des contrôleurs de stockage actifs est récupéré au moyen du contrôleur de stockage passif à partir d'une base de données du journal de transactions. Une ou des transactions dans le journal de transactions sont reproduites à l'aide du contrôleur de stockage passif, lorsque la défaillance de l'un des contrôleurs de stockage actif est déterminée comme s'étant produite.
PCT/US2015/051631 2015-01-29 2015-09-23 Procédés permettant de faciliter des services de stockage à haute disponibilité de n façons et dispositifs correspondants WO2016122723A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US14/608,756 2015-01-29
US14/608,756 US9632890B2 (en) 2014-07-08 2015-01-29 Facilitating N-way high availability storage services

Publications (1)

Publication Number Publication Date
WO2016122723A1 true WO2016122723A1 (fr) 2016-08-04

Family

ID=54289087

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/US2015/051631 WO2016122723A1 (fr) 2015-01-29 2015-09-23 Procédés permettant de faciliter des services de stockage à haute disponibilité de n façons et dispositifs correspondants

Country Status (1)

Country Link
WO (1) WO2016122723A1 (fr)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7111189B1 (en) * 2000-03-30 2006-09-19 Hewlett-Packard Development Company, L.P. Method for transaction log failover merging during asynchronous operations in a data storage network
US8255739B1 (en) * 2008-06-30 2012-08-28 American Megatrends, Inc. Achieving data consistency in a node failover with a degraded RAID array
US20120278429A1 (en) * 2011-04-28 2012-11-01 Fujitsu Limited Cluster system, synchronization controlling method, server, and synchronization controlling program

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7111189B1 (en) * 2000-03-30 2006-09-19 Hewlett-Packard Development Company, L.P. Method for transaction log failover merging during asynchronous operations in a data storage network
US8255739B1 (en) * 2008-06-30 2012-08-28 American Megatrends, Inc. Achieving data consistency in a node failover with a degraded RAID array
US20120278429A1 (en) * 2011-04-28 2012-11-01 Fujitsu Limited Cluster system, synchronization controlling method, server, and synchronization controlling program

Similar Documents

Publication Publication Date Title
US9535862B2 (en) System and method for supporting a scalable message bus in a distributed data grid cluster
US10983880B2 (en) Role designation in a high availability node
EP3304311B1 (fr) Écriture miroir dynamique
US8627136B2 (en) Non-disruptive failover of RDMA connection
US8930316B2 (en) System and method for providing partition persistent state consistency in a distributed data grid
US20160098331A1 (en) Methods for facilitating high availability in virtualized cloud environments and devices thereof
US10771318B1 (en) High availability on a distributed networking platform
US20160077752A1 (en) Fibre Channel Storage Array Methods for Handling Cache-Consistency Among Controllers of an Array and Consistency Among Arrays of a Pool
US9832269B2 (en) Methods for migrating data between heterogeneous storage platforms and devices thereof
US10067841B2 (en) Facilitating n-way high availability storage services
US9507674B2 (en) Methods for preserving state across a failure and devices thereof
US20210271420A1 (en) Method and apparatus for performing data access management of all flash array server
US20160011929A1 (en) Methods for facilitating high availability storage services in virtualized cloud environments and devices thereof
CN105100185B (zh) 事务中间件机器环境中处理数据库状态通知的系统和方法
US20120272253A1 (en) Distributed multi-system management
CN112292661A (zh) 扩展分布式存储系统
WO2016122723A1 (fr) Procédés permettant de faciliter des services de stockage à haute disponibilité de n façons et dispositifs correspondants
EP3545402B1 (fr) Procédés de gestion dynamique d'accès à des numéros d'unités logiques dans un environnement de réseau à zone de stockage distribuée et dispositifs associés
CN115509433A (zh) 一种数据读写方法以及相关装置
US20240184610A1 (en) Path selection method based on an active-active configuration for a hyperconverged infrastructure storage environment
RU2018122861A (ru) Метод построения высокопроизводительных отказоустойчивых систем хранения данных на основе распределенных файловых систем и технологии NVMe over Fabrics
US11216348B2 (en) All flash array server and control method thereof

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 15778110

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 15778110

Country of ref document: EP

Kind code of ref document: A1