WO2007026380A2 - Procede et appareil pouvant fournir un espace memoire dans un reseau - Google Patents

Procede et appareil pouvant fournir un espace memoire dans un reseau Download PDF

Info

Publication number
WO2007026380A2
WO2007026380A2 PCT/IN2006/000341 IN2006000341W WO2007026380A2 WO 2007026380 A2 WO2007026380 A2 WO 2007026380A2 IN 2006000341 W IN2006000341 W IN 2006000341W WO 2007026380 A2 WO2007026380 A2 WO 2007026380A2
Authority
WO
WIPO (PCT)
Prior art keywords
node
nodes
network
storage
capacity
Prior art date
Application number
PCT/IN2006/000341
Other languages
English (en)
Other versions
WO2007026380A3 (fr
Inventor
Puneet Puri
A. K. Rajesh
Original Assignee
Hewlett-Packard Development Company, L.P.
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Hewlett-Packard Development Company, L.P. filed Critical Hewlett-Packard Development Company, L.P.
Publication of WO2007026380A2 publication Critical patent/WO2007026380A2/fr
Publication of WO2007026380A3 publication Critical patent/WO2007026380A3/fr

Links

Classifications

    • 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
    • G06F3/0602—Interfaces specially adapted for storage systems specifically adapted to achieve a particular effect
    • G06F3/0608—Saving storage space on storage systems
    • 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
    • G06F3/0628—Interfaces specially adapted for storage systems making use of a particular technique
    • G06F3/0629—Configuration or reconfiguration of storage systems
    • G06F3/0631—Configuration or reconfiguration of storage systems by allocating resources to storage systems
    • 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
    • G06F3/0668—Interfaces specially adapted for storage systems adopting a particular infrastructure
    • G06F3/067—Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS]
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/01—Protocols
    • H04L67/10—Protocols in which an application is distributed across nodes in the network

Definitions

  • the present invention relates to a method and apparatus for providing storage in a network.
  • Computer networks comprise a number of computers interconnected via the network to enable communication between the computers.
  • Each computer may be associated with storage devices such as a disk drive.
  • a common problem with computers and other processing devices is a lack of storage capacity.
  • Another common problem with storage in a network of computers is inefficient utilization of storage contained among them While some computers in a network may have available storage, managing the provisioning and utilization of such storage over the network is a complex and time consuming task. This problem is compounded by the fact that available storage of a useable size may be scattered across different systems in the network.
  • Embodiments provide a method for providing storage in a network of nodes, the method comprising the steps of: a) identifying a plurality of unused storage volumes provided by a first and second nodes in the network; b) reserving at least a part of two of the unused storage volumes; and c) presenting the reserved parts of the unused storage volumes as a single storage volume for use by a third node in the network.
  • the first and third node may be the same node.
  • a fourth node may provide a set of data identifying unused storage volumes in the network.
  • the first and second nodes may contribute data identifying their respective unused storage volumes to the set of data on the fourth node.
  • the first or second nodes may be arranged to periodically re-contribute updated data identifying their respective unused storage volumes
  • the reserving step may be carried out by indicating in the set of data that a given unused storage volume is reserved.
  • the reserving step may include reserving the given unused storage volume on its providing node.
  • the presenting step may be carried out by a block virtualization manager (BVM).
  • BVM block virtualization manager
  • One or more of the unused storage volumes may be connected to the third node via an internet small computer system interface (iSCSI) interface.
  • iSCSI internet small computer system interface
  • a group of unused storage volumes identified in step a) may be selected for reserving in step b) in accordance with one or more predetermined criteria.
  • the criteria may require that no two unused storage volumes are selected from the same node.
  • Each unused storage volume may be associated with a quality of service (QOS) and the criteria require that only unused storage volumes of compatible QOS are selected.
  • Steps a) to c) may only be carried out by a permitted subset of nodes of the network. The permitted subset of nodes may carry out the steps via a secure network sockets
  • Other embodiments provide a method of providing storage on a node in a network for use by other nodes in the network in buiiding a logical storage volume, the method comprising Lhe step of. a) identifying sharable storage on a node; b) making the identified storage available to other nodes over the network; and c) in response to a request from another node tor the use of the identified storage, reserving at least a part of the storage for use by the other node.
  • Other embodiments provide a method of distributing storage capacity over a network of nodes comprising one or more provider nodes having available capacity and one or more consumer nodes requiring additional capacity, the method comprising the sleps of: a) a provider node identifying available capacity, designating the capacity as shareable and making the sharable capacity available to consumer nodes over the network; and b) a consumer node determining a requirement for additional capacity, identifying one or more provider nodes having sharable capacity and combining the sharable capacity Io provide a single storage volume for access from the consumer node.
  • inventions provide apparatus for providing storage on a node in a network for use by other nodes in the network in building a logical storage volume, the apparatus being operable to: identify sharable storage on a node; expose the identified storage available to other nodes over the network; and reserve at least a part of the storage for use by another node, in response to a request from the other node for the use of the identified storage.
  • inventions provide apparatus for distributing storage capacity over a network of nodes comprising one or more provider nodes having available capacity and one or more consumer nodes requiring additional capacity, the apparatus comprising: a provider node operable to identify available capacity, designate the capacity as shareable and make the sharable capacity available to consumer nodes over the network; and a consumer node operable to determine a requirement for additional capacity, identify one or more provider nodes having sharable capacity and combine the sharable capacity to provide a single storage volume for access from the consumer node.
  • FIG. 1 For the use of the storage identified in the data structure, and d) in response to the request, marking the data as reserved for use by the consumer node
  • FIG. 1 For the use of the storage identified in the data structure, and d) in response to the request, marking the data as reserved for use by the consumer node
  • FIG. 1 For the use of the storage identified in the data structure, and d) in response to the request, marking the data as reserved for use by the consumer node
  • FIG. 1 For the use of the storage identified in the data structure, and d) in response to the request, marking the data as reserved for use by the consumer node
  • FIG. 1 For the use of the storage identified in the data structure, and d) in response to the request, marking the data as reserved for use by the consumer node
  • FIG. 1 For the use of the storage identified in the data structure, and d) in response to the request, marking the data as reserved for use by the consumer node
  • FIG. 1 For the use of the storage identified in the data structure, and d) in
  • Figure 1 is a schematic illustration of a computer network
  • Figure 2 is a schematic illustration of elements of the computer network of Figure 1 configured to operate in accordance with an embodiment of the invention
  • Figure 3 is a schematic illustration of a storage arrangement produced by the elements of figure 2;
  • Figures 4 and 5 are flow charts illustrating processing carried out in the computer network of Figure 1. ,
  • a computer system 101 comprises four nodes in the form of first, second, third and fourth computers 103, 105, 107, 109, interconnected by a local area network (LAN) 111
  • LAN local area network
  • Each of the computers 103, 105, 107, 109 is connected to a respective storage device in the form of a disk drive 113.
  • Each computer is running the LinuxTM operating system.
  • the computers 103, 105, 107, 109 communicate with each other over the network 111 to access data or processes.
  • Operating systems can include block virtualization managers (BVIvI).
  • BVIvI block virtualization managers
  • the BVM is in the form of a logical volume manager (LVIvI).
  • a BVM is a facility for managing storage resources on a computer which enables a set of physically separate storage volumes to be presented to the OS as if they were a single storage volume.
  • Figure 2 shows software elements of the first computer 103 in further detail. The same details are present in the remaining computers 105, 107, 109 but are omitted from figure 2 for clarity.
  • the computer 103 is running an OS 201 which includes a block visualization manager in the form of a logical volume manager (LVM) 203.
  • the computer is also running managing agent software (MA) 205 which uses an internet small computer system interface (iSCSI) target interface 207 and an iSCSI initiator interface 209 as described further below.
  • iSCSI is an internet protocol (IP) based standard for linking data storage devices over a network and transferring data by carrying standard small computer system interface (SCSI) commands over IP networks.
  • IP internet protocol
  • an iSCSI target interface passes the SCSI commands and data to the SCSI controller of the target SCSI storage device.
  • the MA 205 is arranged to identify unused storage capacity on the disk 113 of the computer 103 and to expose the identified storage as an iSCSI target via the interface 207. The unused storage is then accessible to the other computers 105, 107, 109 over the network 111 as an iSCSI device via the initiator interfaces 209 on computers 105, 107, 109.
  • the MA 205 is also arranged to log details of the identified storage in a data structure referred to as a logical storage directory (LSD) 211 .
  • LSD logical storage directory
  • the MA software on each of the computers is arranged to log their respective unused storage as iSCSI targets in the LSD 21 1 so that the LSD contains data identifying all of the unused storage in the computer system 101 Only one of the computers 103, 105, 10.7, 109 is arranged to host the LSD 211 In the present embodiment, the LSD is hosted by the second computer '105.
  • the MA 205 is further arranged, 'in response to a user command, to create a logical volume (LV) of a user specified size.
  • the MA uses the LSD to identify the unused storage available in the computer system as iSCSI targets.
  • the MA selects ⁇ set of iSCSI targets sufficient to provide storage of the size required by the user.
  • the MA also adds data to the LSD to indicate that the portions have been reserved for its use and thereby preventing other MAs from attempting to use the same storage resources.
  • the iSCSI targets are then passed to a logical volume) manager (LVM) 203 which manages the set of iSCSI targets as a single logical volume and makes this volume available for block access by the operating system.
  • LVM logical volume manager
  • the respective MAs expose these three unused portions 301 , 303, 305 as iSCSI targets and log their details in the LSD 211. If the user of the first computer then requests a 75 GB LV, the MA can then select the three 25 GB portions and pass their details to the LVM 203. The LVM will then present the unused portions 301 , 303, 305 to the OS of the first computer as a single 75 GB logical storage volume 307.
  • the LSD 211 is hosted by the second computer 105 and can be accessed by any of the MAs running on any of the computers 103, 105, 107, 109.
  • the MAs log the following types of data in the LSD:
  • Hostname the network identifier of the computer providing storage
  • iSCSI Target the iSCSI target name
  • LUN a unique identifier used on a SCSI bus to distinguish between devices that share the same bus
  • a step 401 the processing starts in response to a user command to the MA to set up a shared storage system as described above with reference to figure 2 and processing moves to step 403.
  • the MA identifies any unused storage which is available locally on the disk drive 113 and processing moves to step 405.
  • the MA selects 50% of the identified unused storage to be used as shareable storage and processing moves to step 407.
  • the storage is allocated an iSCSI target name and LUN and exposed as an iSCSI target by the iSCSI target interface.
  • Step 409 the network identifier for the computer, iSCSI target name, LUN, size and reservation status of the sharable storage is entered in the LSD.
  • the initial reservation status of the sharable storage is set to "available”.
  • the MA receives and instruction from the user to create an LV of a specified size and processing then moves to step 503.
  • the MA inspects the LSD and identifies a set of sharable storage resources that together provide the size of storage requested by the user.
  • the MA inspects the reservation status for each element of sharable resource to determine if they are marked as "available", indicating they can be incorporated in the LV or "reserved", indicating that they are already in use in another LV.
  • step 507 Processing then moves to step 507 where, if all of the identified resources are marked as available, the MA reserves these resources by updating their respective reservation status to "reserved' and processing moves to step 509. If at step 507 any of the identified resources are already reserved then the processing of steps 503 to 507 are repeated until a suitable set of free resources are identified.
  • the MA retrieves the Hostname, iSCSI Target name, LUN and size for each identified resource.
  • the MA initiates iSCSI connections with the identified resources using iSCSI initiator interface 209 and passes the shareable storage information to the LVM. Processing then moves to step 511 where the LVM creates a logical volume from the identified storage resources and presents the logical volume to the operating system ready for use via the compuler 103.
  • the hailing In order to delete an LV, the room issues a command to the MA and identifies the volume for deletion. In response to the instruction, the MA identifies shared storage resources that constitute the volume to be deleted in the LSD and revokes the reservations on these shared storage resources by updating the reservation status in the LSD to "available".
  • the user issues a command identifying the LV, The MA on the consumer queries the LSD for an available resource to provide the extension. The MA identifies suitable resources in the LSD in the same way as it does for volume creation. The MA then interfaces with the block virtualization manager to append the additional resource to the existing LV
  • an instruction is issued to the MA indicating the resource to be reclaimed.
  • the MA identifies the resources in the LSD and if the resource is not allocated to an LV, the MA removes the entry from the LSD. If however, the resource is allocated to a LV, the MA on the provider node sends a message to the MA on the consumer node indicating thai the resource needs to be reclaimed.
  • the MA on the consumer node then initiates the following reclamation process: a) Identifies a replacement for the resource from the LSD and extends the LV to include the additional resource; b) Moves the data from the reclaimed resource to the additional resource; and c) Changes the "reserved" status to "available" in the LSD for resource to be reclaimed.
  • the MA on the consumer then updates the LSD Io remove the reclaimed resource entry and stops exposing the storage resource as an iSCSI target.
  • ail free storage is exposed as a sharable resource.
  • a variable proportion of the free storage is exposed, the proportion being determined by ⁇ user.
  • one or more nodes in the network are both providers and consumers of sharable storage.
  • the LSD ic on the same node as an MA. In further embodiments, the LSD is on a different node from any MA.
  • a set of rules are provided to govern sharable storage selection for an LV.
  • the rules may require that local storage should be used first or that all LVs must include a part of local storage. Rules may also enforce certain proportions of local or remote resources in a LV. Rules may also require an LV to have no more than a certain number of parts from the same node.
  • the all communication between MA and LSD are conducted through secure socket connections such as secure socket layer (SSL), with access to shared storage resources being limited to iSCSI initiators identified in an access control list maintained in the LSD.
  • SSL secure socket layer
  • a quality of storage (QOS) attribute is associated with the resources contributed to the LSD.
  • the QOS attribute is designated as low, medium and high to indicate characteristics of the storage resource.
  • the consumer of sharable storage can match QOS attributes to choose appropriate resources for the construction of an LV. For example, a high QOS volume will only be used with other volumes with equally high QOS attributes. In the event of non-availability of resources with high QOS, resources in the next level are used.
  • an alternative reservation mechanism is used for reserving resources advertised in the LSD to avoid IVlAs simultaneously accessing and updating the LSD data.
  • each MA polls the LSD at predetermined intervals.. During the polling process, each MA is informed of any changes made to any entry in which the MA has an interest, either as a consumer or as a provider.
  • the reservation mechanism is as follows:
  • the consumer node MA identifies resources to be reserved
  • the consumer node MA sends a reservation request with all the identified resources to the LSD. This set ⁇ the reservation status to "wanted" on the requested resources,
  • the LSD marks them as allocated and returns a positive response to the consumer node MA; 5) If any of the requested/esources is in use, the MA repeats steps 1-3 to select a different set of resources;
  • the MA on the consumer node checks the LSD after the next polling period for "confirmed" status on all the requested resources. Once all requested resource status have been confirmed, the MA proceeds to consume the resource and create the LV
  • the apparatus that embodies a part or all of the present invention may be a general purpose device having software arranged to provide a part or all of an embodiment of the invention.
  • the device could be single device or a group of devices and the software could be a single program or a set of programs.
  • any or all of the software used to implement the invention can be communicated via any suitable transmission or storage means so that the software can be loaded onto one or more devices.

Abstract

L'invention concerne un procédé et un appareil au moyen desquels un élément de stockage non utilisé dans un système informatique mis en réseau peut être partagé au sein du réseau en tant que simple volume de stockage logique.
PCT/IN2006/000341 2005-08-29 2006-08-29 Procede et appareil pouvant fournir un espace memoire dans un reseau WO2007026380A2 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
IN1203CH2005 2005-08-29
IN1203/CHE/2005 2005-08-29

Publications (2)

Publication Number Publication Date
WO2007026380A2 true WO2007026380A2 (fr) 2007-03-08
WO2007026380A3 WO2007026380A3 (fr) 2007-06-07

Family

ID=37498142

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/IN2006/000341 WO2007026380A2 (fr) 2005-08-29 2006-08-29 Procede et appareil pouvant fournir un espace memoire dans un reseau

Country Status (1)

Country Link
WO (1) WO2007026380A2 (fr)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP2113832A1 (fr) * 2008-04-28 2009-11-04 Stone Technology International Co., Ltd. Support pour l'intégration de capacités de stockage de dispositifs de stockage multiples
GB2469555B (en) * 2009-04-14 2014-01-29 Fujitsu Ltd Storage system and storage control method

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20020129216A1 (en) * 2001-03-06 2002-09-12 Kevin Collins Apparatus and method for configuring available storage capacity on a network as a logical device
US20020129049A1 (en) * 2001-03-06 2002-09-12 Kevin Collins Apparatus and method for configuring storage capacity on a network for common use
WO2003090087A2 (fr) * 2002-04-15 2003-10-30 Emc Corporation Procede et appareil permettant de mettre en oeuvre un systeme de stockage virtuel d'entreprise
EP1509021A2 (fr) * 2003-08-21 2005-02-23 Microsoft Corporation Accès à un dispositif SCSI à travers un réseau
US20050044140A1 (en) * 2003-08-21 2005-02-24 Fujitsu Limited Information processing method, information processing system, information processing apparatus and computer readable information recording medium

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20020129216A1 (en) * 2001-03-06 2002-09-12 Kevin Collins Apparatus and method for configuring available storage capacity on a network as a logical device
US20020129049A1 (en) * 2001-03-06 2002-09-12 Kevin Collins Apparatus and method for configuring storage capacity on a network for common use
WO2003090087A2 (fr) * 2002-04-15 2003-10-30 Emc Corporation Procede et appareil permettant de mettre en oeuvre un systeme de stockage virtuel d'entreprise
EP1509021A2 (fr) * 2003-08-21 2005-02-23 Microsoft Corporation Accès à un dispositif SCSI à travers un réseau
US20050044140A1 (en) * 2003-08-21 2005-02-24 Fujitsu Limited Information processing method, information processing system, information processing apparatus and computer readable information recording medium

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP2113832A1 (fr) * 2008-04-28 2009-11-04 Stone Technology International Co., Ltd. Support pour l'intégration de capacités de stockage de dispositifs de stockage multiples
GB2469555B (en) * 2009-04-14 2014-01-29 Fujitsu Ltd Storage system and storage control method
US8856485B2 (en) 2009-04-14 2014-10-07 Fujitsu Limited Storage system and storage control method

Also Published As

Publication number Publication date
WO2007026380A3 (fr) 2007-06-07

Similar Documents

Publication Publication Date Title
US9787780B1 (en) Method and apparatus for web based storage on-demand
JP4455137B2 (ja) 記憶サブシステム管理方法
JP4961411B2 (ja) 計算機システム及びその構成管理方法
US8434078B2 (en) Quick deployment method
US6732166B1 (en) Method of distributed resource management of I/O devices in a network cluster
US8190717B2 (en) Method of booting an operating system
US9338128B2 (en) Controlling the status of network address space
US8412901B2 (en) Making automated use of data volume copy service targets
US8104038B1 (en) Matching descriptions of resources with workload requirements
US7464232B2 (en) Data migration and copying in a storage system with dynamically expansible volumes
US8001327B2 (en) Method and apparatus for managing placement of data in a tiered storage system
US8051262B2 (en) Storage system storing golden image of a server or a physical/virtual machine execution environment
US8224941B2 (en) Method, apparatus, and computer product for managing operation
WO2020233020A1 (fr) Procédé et dispositif pour distribuer préalablement un ip de conteneur, dispositif informatique et support de stockage
JP2003345631A (ja) 計算機システム及び記憶領域の割当方法
WO2013132910A1 (fr) Système de fourniture d'hôte et procédé de fourniture d'hôte
US20080192643A1 (en) Method for managing shared resources
WO2007026380A2 (fr) Procede et appareil pouvant fournir un espace memoire dans un reseau
WO2021248972A1 (fr) Procédé de gestion de passerelles par défaut, gestionnaire de passerelles, serveur et support de stockage
JP6244496B2 (ja) サーバストレージシステムの管理システム及び管理方法
JP5758519B2 (ja) 計算機システム及びその管理方法
JP5508458B2 (ja) 計算機システム及びその構成管理方法

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application
NENP Non-entry into the national phase in:

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 06796199

Country of ref document: EP

Kind code of ref document: A2