WO2015085826A1 - Procédé et appareil pour accéder à une ressource partagée - Google Patents

Procédé et appareil pour accéder à une ressource partagée Download PDF

Info

Publication number
WO2015085826A1
WO2015085826A1 PCT/CN2014/088928 CN2014088928W WO2015085826A1 WO 2015085826 A1 WO2015085826 A1 WO 2015085826A1 CN 2014088928 W CN2014088928 W CN 2014088928W WO 2015085826 A1 WO2015085826 A1 WO 2015085826A1
Authority
WO
WIPO (PCT)
Prior art keywords
lock
node
identifier
client
shared resource
Prior art date
Application number
PCT/CN2014/088928
Other languages
English (en)
Chinese (zh)
Inventor
邹蛟同
Original Assignee
华为技术有限公司
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 华为技术有限公司 filed Critical 华为技术有限公司
Publication of WO2015085826A1 publication Critical patent/WO2015085826A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46—Multiprogramming arrangements
    • G06F9/52—Program synchronisation; Mutual exclusion, e.g. by means of semaphores
    • G06F9/526—Mutual exclusion algorithms

Definitions

  • the present invention relates to the field of data communication technologies, and in particular, to a method and an apparatus for accessing shared resources.
  • the storage array is the storage carrier of the storage device.
  • the storage array provides virtualized shared resources for the host application.
  • data is simultaneously written to the storage arrays of the two storage devices.
  • the other storage device can still provide external services to implement data disaster recovery.
  • a mutual exclusion mechanism needs to be provided between two storage devices to prevent concurrent access of shared resources (each storage device includes multiple nodes, and each node includes multiple clients) As shown in FIG.
  • the client refers to a process in which a node accesses a shared resource
  • the client refers to a process in which a node accesses a shared resource
  • the lock manager is a commonly used mutual exclusion protection mechanism between nodes. It allows a shared resource to be accessed by only one client at a time.
  • the process of accessing shared resources through the lock manager is as follows (as shown in the figure). 1C):
  • node 1 node 1
  • node 2 node 3
  • Step a assign a lock manager to the shared resource A;
  • Step b When the node 2 needs to access the shared resource A, apply to the lock manager for the lock authority corresponding to the shared resource A;
  • Step c After obtaining the lock permission corresponding to the shared resource A, the node 2 accesses the shared resource A;
  • Step d Node 3 applies to the lock manager for the lock permission corresponding to the shared resource A. Since the lock has been authorized, the lock manager suspends the authorization of the lock request of other rights conflicts, and only the lock holder of the conflict releases the lock permission. After that, the new lock request will be authorized.
  • the lock manager is used to achieve the orderly access of the same shared resource by multiple clients, and the consistency of the accessed data is ensured.
  • the current lock manager has the following drawbacks: when some nodes are not the same node as the lock manager node, when acquiring the lock identifier corresponding to the lock authority of any shared resource, the other node is required to acquire the lock permission. A problem that takes a long time.
  • the embodiment of the invention provides a method and a device for accessing a shared resource, which are used to solve the problem that the current method for accessing the shared resource has a long time.
  • a method of accessing a shared resource including:
  • the lock permission request is forwarded when the first node sends the lock identifier that is sent by the client of the first node and does not find the identifier of the shared resource in the first node;
  • the first node is configured to cache a lock identifier corresponding to a lock authority occupied by each client in the first node, or an occupied idle time The lock identifier corresponding to the lock authority that is smaller than the delete threshold.
  • the receiving, by the first node, the lock permission request that carries the identifier of the shared resource specifically includes:
  • the lock permission request is forwarded by the second node when receiving the lock identifier sent by the first node and not finding the identifier of the shared resource in the first node.
  • the second node is configured to cache a lock identifier corresponding to the occupied lock authority in the specified lock authority, or The lock identifier corresponding to the lock authority that is occupied by the lock authority and whose idle time is less than the deletion threshold.
  • the determining, by the first node, the lock identifier is Client, specifically:
  • the determining, by the first node, the lock identifier is Client, specifically:
  • the lock permission recall instruction is sent to the client occupying the lock permission, so that the client occupying the lock authority completes accessing the shared resource and then releases The lock authority;
  • an apparatus for accessing a shared resource including:
  • a receiving unit configured to receive a lock permission request that is forwarded by the first node and that carries the identifier of the shared resource, where the lock permission request is sent by the first node at the client that receives the first node, and is in the first Forwarded when the lock identifier of the identifier of the shared resource is not found in the node;
  • a determining unit configured to determine, from the stored lock identifier, a lock label including an identifier of the shared resource knowledge
  • An allocating unit configured to allocate the determined lock identifier to the client by using the first node, and give the client a lock right corresponding to the lock identifier of the shared resource, for the client Access to the shared resource.
  • the lock permission request received by the receiving unit is sent by the first node, and the first node is used to cache the first node.
  • the receiving unit is specifically configured to:
  • the lock permission request is forwarded by the second node when receiving the lock identifier sent by the first node and not finding the identifier of the shared resource in the first node.
  • the lock permission request received by the receiving unit is sent by the second node, and the second node is used by the second node.
  • the allocation unit is specifically configured to:
  • the allocation unit is specifically configured to:
  • the lock permission recall instruction is sent to the client occupying the lock permission, so that the client occupying the lock authority completes accessing the total Release the lock permission after enjoying the resource;
  • the lock permission request that carries the identifier of the shared resource forwarded by the first node is received, where the lock permission request is sent by the first node to the client that receives the first node.
  • the lock identifier including the identifier of the shared resource is not found in the first node, and then determining a lock identifier including the identifier of the shared resource from the stored lock identifier, and finally, determining The lock identifier is allocated to the client by the first node, and the client is given a lock right corresponding to the lock identifier of the shared resource, and is used by the client to access the shared resource.
  • the first node after receiving the lock permission request sent by the client of the first node, the first node does not find the target including the shared resource in the first node. The lock is only forwarded when the lock is identified.
  • the lock identifier of the identifier of the shared resource is first searched in the first node, and only when it does not exist, the forwarding is performed, and when it exists, the direct assignment is performed.
  • FIG. 1A is a schematic structural diagram of a dual active data center in the prior art
  • 1B is a schematic structural diagram of a node and a client in the prior art
  • 1C is a schematic diagram of accessing shared resources in a dual-active data center in the prior art
  • FIG. 2 is a schematic diagram of accessing a shared resource according to an embodiment of the present invention.
  • FIG. 3 is a first embodiment of accessing a shared resource according to an embodiment of the present invention.
  • FIG. 5 is a schematic structural diagram of a device for accessing a shared resource according to an embodiment of the present invention.
  • system and “network” are used interchangeably herein.
  • the term “and/or” in this context is merely an association describing the associated object, indicating that there may be three relationships, for example, A and / or B, which may indicate that A exists separately, and both A and B exist, respectively. B these three situations.
  • the letter “/” in this article generally indicates that the contextual object is an "or" relationship.
  • the lock permission request that carries the identifier of the shared resource forwarded by the first node is received, where the lock permission request is received by the first node. And forwarding, when the lock identifier sent by the client of the first node and not identifying the identifier of the shared resource is found in the first node, and then determining the lock identifier including the identifier of the shared resource from the stored lock identifier, Finally, the determined lock identifier is assigned to the client through the first node, and the lock permission corresponding to the lock identifier of the shared resource is given to the client for accessing the shared resource by the client.
  • the first node is receiving After the lock permission request sent by the client of the first node is forwarded, the lock identifier including the identifier of the shared resource is not found in the first node, that is, the first node is first searched for whether to include the share.
  • the lock identifier of the identifier of the resource when it exists, directly allocates it, and only forwards when it does not exist, and the client obtains the lock identifier from the first node. To identify the other nodes to acquire the lock takes less time, therefore, to solve the long time-consuming problems of current methods to access shared resources.
  • Step 200 Receive a lock permission request that carries the identifier of the shared resource forwarded by the first node, where the lock permission request is sent by the first node after receiving the client of the first node, and is not found in the first node. Forwarded when the lock identifier of the shared resource identifier is used;
  • Step 210 Determine, from the stored lock identifier, a lock identifier that includes an identifier of the shared resource.
  • Step 220 Assign the determined lock identifier to the client through the first node, and give the client the lock permission corresponding to the lock identifier of the shared resource, and use the client to access the shared resource.
  • the lock identifier includes the following information, the identifier of the protected shared resource, and the manner of accessing the shared resource.
  • other information than the above two types of information may also be included, and details are not further described herein. Said.
  • a shared resource for example, a method of reading a shared resource.
  • the client acquires the permission to read the shared resource, and, for example, writes the shared resource.
  • the permission obtained by the client to write the shared resource wherein if the acquired permission to read the shared resource is obtained, the client can only perform the read operation on the shared resource, and cannot perform the write operation; if the obtained write share is obtained.
  • the permission of the resource the client can not only read the shared resource, but also perform the write operation.
  • there are other ways to access the shared resource and the details are not detailed here. .
  • the first node has multiple forms, for example, may be used to cache a lock identifier corresponding to the lock authority occupied by each client in the first node, or the occupied idle time is less than the deletion threshold.
  • the lock identifier corresponding to the lock authority may also be used to cache other information, which is not detailed here.
  • the client may send a lock permission request for accessing the shared resource to the first node where the client is located, If the lock identifier of the identifier of the shared resource to be accessed is currently stored in the first node, the first node allocates the corresponding lock identifier to the client, if the first node does not currently store the shared resource to be accessed.
  • the lock identifier of the identifier the first node sends a lock permission request for accessing the shared resource to the lock manager that manages the lock authority of the shared resource of the different node, and then assigns the lock identifier returned by the received lock manager to The client, and stores the lock identifier, then the first node receives the lock permission for accessing the shared resource sent by the client again. While, if the lock identifier is not allocated, then the lock identification assigned to clients, thereby avoiding a longer acquire the lock identified problems exist in the process time-consuming.
  • the node where the client 1 is located is in the first storage device, and the lock manager is located in the second storage device, wherein the lock manager manages the lock permission of the first storage device and the second storage device to access the shared resource, and the client 1
  • the lock identifier of the first shared resource is obtained, that is, the lock permission
  • the lock permission request for accessing the first shared resource may be directly sent to the lock manager located at the second storage device, and at this time, because it is between the two storage devices Communication interaction, therefore, there is a problem that takes a long time.
  • the client 1 can send the client to the client.
  • the first node that is located at 1 sends a lock permission request for accessing the first shared resource. If the lock identifier of the first shared resource is cached in the first node, and the lock identifier is not allocated, the first node sends the lock identifier. To the client 1, that is, to assign the lock permission to the first shared resource to the client 1; if the lock of the first shared resource is not cached in the first node The first node sends a lock permission request for accessing the first shared resource to the lock manager, sends the lock identifier returned by the received lock manager to the client, and caches the lock identifier, so as to receive the client again. 1 or when the client sends a lock permission request to access the first shared resource, if the lock identifier is not If it is assigned, the lock ID is sent to the client.
  • the request for the lock permission to carry the identifier of the shared resource forwarded by the first node may be received by the first node, for example, the lock permission request of the identifier of the shared resource that is forwarded by the first node by the second node may be received, where The lock permission request is forwarded by the second node when receiving the lock identifier sent by the first node and not identifying the identifier of the shared resource in the first node, where the foregoing is only receiving the shared resource carried by the first node.
  • An implementation manner of the identified lock permission request in actual application, there are other implementation manners, which are not described in detail herein.
  • the implementation of the lock permission request for receiving the identifier of the shared resource forwarded by the first node by the second node is as follows:
  • the first storage device and the second storage device share 10 shared resources: shared resource 1, shared resource 2, ..., each shared resource corresponds to a lock identifier, and the second node located at the first storage device can store 10 The lock identifier corresponding to the shared resource, that is, the lock permission for accessing the 10 shared resources.
  • the second node sends a lock permission request for accessing the shared resource 1, and acquires a lock identifier corresponding to the shared resource 1 from the second node; in order to improve efficiency, the client 1 may also first send the access shared resource 1 to the first node where it is located.
  • the lock permission request if the first node caches a lock identifier corresponding to the shared resource 1, the first node sends the lock identifier to the client 1, and assigns the lock permission to the client 1, if the first node is not cached
  • the lock identifier corresponding to the shared resource 1 is forwarded by the first node to the second node to access the lock permission request of the shared resource 1, and the received second node sends the shared resource 1 corresponding to the client ID to the lock 1, the lock authority to assign a client.
  • the second node has multiple forms, optionally, used to cache the lock identifier corresponding to the occupied lock authority in the specified lock authority, or the idle time occupied by the specified lock authority is less than Delete the lock identifier corresponding to the lock permission of the threshold.
  • a storage device may further include a plurality of second nodes, where the second node is configured to cache a lock identifier corresponding to the occupied lock authority in the specified lock authority, or is occupied by the specified lock authority.
  • the lock identifier corresponding to the lock authority whose idle time is less than the deletion threshold. At this time, the second node is different. You can manage lock identifiers for different shared resources.
  • the first storage device and the second storage device share 10 shared resources: shared resource 1, shared resource 2, ..., each shared resource corresponds to a lock identifier, and the second node 1 located at the first storage device manages sharing.
  • the identifier that is, the lock permission for accessing 10 shared resources. If the client 1 located at the first storage device wants to access the shared resource 1, the client 1 can directly send the access shared resource to the lock manager located at the second storage device.
  • the lock permission request acquires the lock identifier corresponding to the shared resource 1 from the lock manager; in order to improve the efficiency, the client 1 may first send a lock permission request for accessing the shared resource 1 to the first node where the first node is located, if the first node
  • the cache has a lock identifier corresponding to the shared resource 1, and the first node sends the lock identifier to the client 1, and assigns the lock permission to the client 1, if the first node is not cached
  • the lock identifier corresponding to the shared resource 1 is forwarded to the second node 1 by the first node to access the lock permission request of the shared resource 1. If the lock identifier of the identifier including the shared resource is not found in the second node 1, the switch forwards to the lock.
  • the manager sends the lock identifier corresponding to the shared resource 1 sent by the received lock manager to the client 1 through the first node, and assigns the lock authority to the client 1.
  • the client 2 located at the first storage device wants to access the shared resource 10
  • the client 2 can directly send a lock permission request for accessing the shared resource 10 to the lock manager located at the second storage device, from the lock manager.
  • the lock identifier is sent by the third node to the client 2, and the lock authority is assigned to the client 2.
  • the third node is The second node 2 forwards the lock permission request for accessing the shared resource 10. If the lock identifier corresponding to the shared resource 10 is not cached in the second node 2, the second node 2 forwards the lock permission request for accessing the shared resource 10 to the lock manager. And the lock identifier corresponding to the shared resource 10 sent by the received lock manager is sent to the client 2 through the third node, and the lock authority is allocated to the client 2.
  • the above embodiment only enumerates the case where only one second node exists in one storage device, in practice. In an application, there may also be a case where a storage device has multiple second nodes. If a storage device has multiple second nodes, when the client sends a lock permission request for accessing the shared resource, the client first sends a lock permission request for accessing the shared resource to the first node where the client is located, if the client is located at the first node.
  • a lock identifier corresponding to the shared resource to be accessed is cached in a node, and the first node where the client is located sends a lock identifier corresponding to the shared resource to be accessed to the client, if the first node where the client is located is not If the lock identifier corresponding to the shared resource to be accessed is cached, the lock permission request for accessing the shared resource is forwarded to the corresponding second node, and if the lock identifier corresponding to the shared resource to be accessed is cached in the second node, The two nodes send the lock identifier corresponding to the shared resource to be accessed to the client. If the lock identifier corresponding to the shared resource to be accessed is not cached in the second node, the lock permission request for accessing the shared resource is forwarded to the lock management. Device.
  • the first node may directly receive the lock permission request of the identifier of the shared resource that is forwarded by the first node.
  • the second node may receive a lock permission request that receives the identifier of the shared resource forwarded by the first node.
  • the determined lock identifier is allocated to the client through the first node.
  • the determined lock identifier may be directly allocated to the client through the first node; or, The determined lock identifier is sent to the first node by the second node such that the first node assigns the lock identifier to the client.
  • the client sends a lock permission request for accessing the shared resource to the first node or the second node, whether the lock permission request for accessing the shared resource is directly sent to the lock manager, and the lock for receiving the request is received.
  • the lock identifier corresponding to the accessed shared resource may be stored in the manager or the node, but the lock identifier is sent to the client, that is, the lock authority corresponding to the lock identifier is occupied. At this time, the lock corresponding to the determined lock identifier is used.
  • the lock permission recall instruction is sent to the client occupying the lock permission, so that the client occupying the lock privilege releases the lock privilege after accessing the shared resource; and the lock privilege released by the client occupying the lock privilege corresponds to
  • the lock identifier is assigned to the client through the first node.
  • the determined lock identifier there are multiple ways to assign the determined lock identifier to the client through the first node. For example, if the lock permission corresponding to the determined lock identifier is occupied by other clients, the lock permission is sent to the client occupying the lock permission.
  • the recall indication is such that the client occupying the lock authority releases the lock permission after accessing the shared resource, and the lock identifier corresponding to the lock authority released by the client occupying the lock authority is allocated to the client through the first node.
  • the client 1 sends a lock permission request for accessing the shared resource 1 to the second node, and if the lock identifier corresponding to the shared resource 1 cached in the second node is assigned to another node, that is, the lock corresponding to the lock identifier
  • the lock privilege recall instruction is sent to the client 2 occupying the lock privilege, so that the client 2 occupying the lock privilege releases the lock privilege when accessing the shared resource, and then the second node occupies the lock privilege again.
  • the lock identifier corresponding to the lock permission released by the client 2 is assigned to the client 1.
  • the lock identifier corresponding to the shared resource to be accessed in the second node is allocated to the other client as an example.
  • the first node where the client is located may be used, or The lock identifier corresponding to the shared resource to be accessed cached in the lock manager is allocated to other clients.
  • the first node or the lock manager sends a lock permission recall instruction to the client occupying the lock authority, and the process is as follows. The embodiments are the same and will not be described in detail herein.
  • An embodiment of obtaining a lock identifier by a primary lock authority agent node An embodiment of obtaining a lock identifier by a primary lock authority agent node.
  • Embodiment 1 (shown in Figure 3):
  • Step 300 The client 1 sends a lock permission request for accessing the shared resource 1 to the first node where the client 1 is located;
  • Step 310 The first node determines whether the lock identifier corresponding to the shared resource 1 is stored in the first node, and the lock identifier is not allocated, and if so, step 350 is performed; otherwise, step 320 is performed;
  • Step 320 The first node sends a lock permission request for accessing the shared resource 1 to the lock manager.
  • the lock manager is located at the second storage device.
  • Step 330 The lock manager determines whether a lock label corresponding to the shared resource 1 is stored in the first node. Knowledge, and the lock identifier is not assigned; if yes, step 340 is performed, otherwise, step 360 is performed;
  • Step 340 The lock manager sends the lock identifier corresponding to the shared resource 1 to the first node;
  • Step 350 The first node sends a lock identifier corresponding to the shared resource 1 to the client 1;
  • Step 360 The lock manager sends a lock permission recall indication to the client 2 occupying the lock authority, and sends the lock identifier corresponding to the lock authority released by the client 2 occupying the lock authority to the client 1 through the first node.
  • Embodiment 2 (as shown in Figure 4):
  • Step 400 The client 1 sends a lock permission request for accessing the shared resource 1 to the first node where the client 1 is located;
  • Step 410 The first node determines whether the lock identifier corresponding to the shared resource 1 is stored in the first node, and the lock identifier is not allocated, and if so, step 480 is performed; otherwise, step 420 is performed;
  • Step 420 The first node sends a lock permission request for accessing the shared resource 1 to the second node.
  • the client 1 and the second node are located at the first storage device.
  • Step 430 The second node determines whether the lock identifier corresponding to the shared resource 1 is stored in the first node, and the lock identifier is not allocated, and if so, step 470 is performed; otherwise, step 440 is performed;
  • Step 440 The second node sends a lock permission request for accessing the shared resource 1 to the lock manager.
  • the lock manager is located at the second storage device.
  • Step 450 The lock manager determines whether the lock identifier corresponding to the shared resource 1 is stored in the first node, and the lock identifier is not allocated; if yes, step 460 is performed; otherwise, step 490 is performed;
  • Step 460 The lock manager sends the lock identifier corresponding to the shared resource 1 to the second node;
  • Step 470 The second node sends the lock identifier corresponding to the shared resource 1 to the first node.
  • Step 480 The first node sends a lock identifier corresponding to the shared resource 1 to the client 1;
  • Step 490 The lock manager sends a lock permission recall indication to the client 2 that occupies the lock authority, and forwards the lock identifier corresponding to the lock authority released by the client 2 that occupies the lock authority to the first node through the second node, so that the first The node sends to client 1.
  • an embodiment of the present invention further provides an apparatus for accessing a shared resource, where the apparatus includes a receiving unit 500, a determining unit 510, and an allocating unit 520, where:
  • the receiving unit 500 is configured to receive, by the first node, a lock permission request that carries the identifier of the shared resource, where the lock permission request is sent by the first node on the client that receives the first node, and is not in the first node. Forwarded when a lock identifier including the identity of the shared resource is found;
  • a determining unit 510 configured to determine, from the stored lock identifier, a lock identifier that includes an identifier of the shared resource
  • the allocating unit 520 is configured to allocate the determined lock identifier to the client by using the first node, and give the client a lock right corresponding to the lock identifier of the shared resource, for the client to access the shared resource.
  • the lock permission request received by the receiving unit 500 is sent by the first node, and the first node is configured to cache a lock identifier corresponding to the lock authority occupied by each client in the first node. Or the lock identifier corresponding to the lock authority whose idle time is less than the deletion threshold.
  • the receiving unit 500 is specifically configured to:
  • the lock permission request is forwarded by the second node when receiving the lock identifier sent by the first node and not identifying the identifier including the shared resource in the first node.
  • the lock permission request received by the receiving unit 500 is sent by the second node, and the second node is configured to cache the lock identifier corresponding to the occupied lock authority in the specified lock authority, or specify The lock identifier corresponding to the lock authority that is occupied by the lock authority and whose idle time is less than the delete threshold.
  • the allocating unit 520 is specifically configured to:
  • the determined lock identifier is sent to the first node through the second node such that the first node assigns the lock identifier to the client.
  • the allocating unit 520 is specifically configured to:
  • the lock permission recall instruction is sent to the client occupying the lock permission, so that the client occupying the lock permission releases the lock right after accessing the shared resource;
  • the lock identifier corresponding to the lock authority released by the client occupying the lock authority is allocated to the client through the first node.
  • the lock permission request that carries the identifier of the shared resource forwarded by the first node is received, where the lock permission request is sent by the first node on the client that receives the first node, and And forwarding, when the lock identifier of the identifier of the shared resource is not found in the first node, and then determining a lock identifier including the identifier of the shared resource from the stored lock identifier, and finally, determining the determined lock identifier by using the first node Assigned to the client, giving the client the lock permission corresponding to the lock identifier of the shared resource, for the client to access the shared resource, in the scheme, the first node receives the lock permission sent by the client of the first node After the request, the lock identifier of the identifier including the shared resource is not found in the first node, that is, the lock identifier of the identifier of the shared resource is first searched in the first node, and only exists in the absence of the lock identifier of the
  • the forwarding when it exists, the direct allocation is performed, and the client obtains the lock identifier from the first node than when the other node acquires the lock identifier. Less, therefore, to solve the problem of a longer time-consuming methods currently exist to access shared resources.
  • the computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture comprising the instruction device.
  • the apparatus functions in one or more blocks of a flow or a flow diagram and/or block diagram of a flowchart.
  • These computer program instructions can also be loaded onto a computer or other programmable data processing device such that a series of operational steps are performed on a computer or other programmable device to produce computer-implemented processing for execution on a computer or other programmable device.
  • the instructions provide steps for implementing the functions in one or more blocks of the flowchart or in a flow or block of the flowchart.

Abstract

La présente invention concerne le domaine technique des communications de données, ainsi qu'un procédé et un appareil pour accéder à une ressource partagée. Dans un procédé décrit dans des modes de réalisation de la présente invention, après avoir reçu une requête de permission de verrouillage, envoyée par un client d'un premier nœud, le premier nœud transfère la requête de permission de verrouillage seulement lorsqu'un identifiant de verrouillage comprenant un identifiant d'une ressource partagée n'est pas trouvé dans le premier nœud, c'est-à-dire qu'une recherche est effectuée en premier dans le premier nœud pour déterminer si l'identifiant de verrouillage comprenant l'identifiant de la ressource partagée existe dans le premier nœud ; la requête de permission de verrouillage est transférée seulement lorsque l'identifiant de verrouillage comprenant l'identifiant de la ressource partagée n'existe pas dans le premier nœud et, lorsque l'identifiant de verrouillage comprenant l'identifiant de la ressource partagée existe dans le premier nœud, la requête de permission de verrouillage est directement attribuée. Le client met moins de temps à acquérir l'identifiant de verrouillage auprès du premier nœud qu'auprès d'autres nœuds. Par conséquent, le problème selon lequel un procédé existant pour accéder à une ressource partagée est chronophage est résolu.
PCT/CN2014/088928 2013-12-13 2014-10-20 Procédé et appareil pour accéder à une ressource partagée WO2015085826A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201310689369.3 2013-12-13
CN201310689369.3A CN103716383B (zh) 2013-12-13 2013-12-13 一种访问共享资源的方法及装置

Publications (1)

Publication Number Publication Date
WO2015085826A1 true WO2015085826A1 (fr) 2015-06-18

Family

ID=50408953

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2014/088928 WO2015085826A1 (fr) 2013-12-13 2014-10-20 Procédé et appareil pour accéder à une ressource partagée

Country Status (2)

Country Link
CN (1) CN103716383B (fr)
WO (1) WO2015085826A1 (fr)

Families Citing this family (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103716383B (zh) * 2013-12-13 2017-12-15 华为技术有限公司 一种访问共享资源的方法及装置
CN106202074B (zh) * 2015-04-29 2021-02-23 中兴通讯股份有限公司 一种处理共享文件的方法及装置
CN107402821B (zh) * 2017-07-03 2020-06-30 阿里巴巴集团控股有限公司 共享资源的访问控制方法、装置和设备
CN109697127B (zh) * 2017-10-24 2020-12-01 华为技术有限公司 一种对共享资源的访问操作加锁的方法和装置
CN108038005A (zh) * 2017-12-28 2018-05-15 广东蜂助手网络技术股份有限公司 基于zookeeper的共享资源访问方法、客户端、服务端、系统
CN109063132B (zh) * 2018-08-02 2020-08-25 上海达梦数据库有限公司 闩锁请求方法、闩锁授权方法、装置及终端设备
CN109947575B (zh) * 2019-03-21 2021-08-24 恒生电子股份有限公司 读写锁的加锁、释放方法及相关系统
CN110879743B (zh) * 2019-11-20 2023-07-18 深圳市网心科技有限公司 基于边缘计算环境的任务剔除方法、设备、系统及介质
CN114500390B (zh) * 2021-12-29 2024-01-19 中国航空工业集团公司西安航空计算技术研究所 RapidIO网络流量控制方法

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20120072763A1 (en) * 2010-08-17 2012-03-22 Emc Corporation System and method of file locking in a network file system federated namespace
CN103248667A (zh) * 2012-02-14 2013-08-14 阿里巴巴集团控股有限公司 一种分布式系统的资源访问方法和系统
CN103297268A (zh) * 2013-05-13 2013-09-11 北京邮电大学 基于p2p技术的分布式数据一致性维护系统和方法
CN103716383A (zh) * 2013-12-13 2014-04-09 华为技术有限公司 一种访问共享资源的方法及装置

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN100576848C (zh) * 2005-12-09 2009-12-30 英业达股份有限公司 分布式数据动态程序代理方法
US8078622B2 (en) * 2008-10-30 2011-12-13 Network Appliance, Inc. Remote volume access and migration via a clustered server namespace

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20120072763A1 (en) * 2010-08-17 2012-03-22 Emc Corporation System and method of file locking in a network file system federated namespace
CN103248667A (zh) * 2012-02-14 2013-08-14 阿里巴巴集团控股有限公司 一种分布式系统的资源访问方法和系统
CN103297268A (zh) * 2013-05-13 2013-09-11 北京邮电大学 基于p2p技术的分布式数据一致性维护系统和方法
CN103716383A (zh) * 2013-12-13 2014-04-09 华为技术有限公司 一种访问共享资源的方法及装置

Also Published As

Publication number Publication date
CN103716383B (zh) 2017-12-15
CN103716383A (zh) 2014-04-09

Similar Documents

Publication Publication Date Title
WO2015085826A1 (fr) Procédé et appareil pour accéder à une ressource partagée
US11366768B2 (en) Data write method, apparatus, and system
US8782323B2 (en) Data storage management using a distributed cache scheme
EP2985702B1 (fr) Méthode et dispositif de traitement de données, et système informatique
US10248175B2 (en) Off-line affinity-aware parallel zeroing of memory in non-uniform memory access (NUMA) servers
WO2019161557A1 (fr) Procédé et appareil de communication
WO2015169145A1 (fr) Procédé et dispositif de gestion de mémoire
US11741022B2 (en) Fine grained memory and heap management for sharable entities across coordinating participants in database environment
US10310986B1 (en) Memory management unit for shared memory allocation
US9654582B2 (en) Enhanced shared memory based communication driver for improved performance and scalability
CN109144406B (zh) 分布式存储系统中元数据存储方法、系统及存储介质
US20120066191A1 (en) Optimized concurrent file input/output in a clustered file system
WO2022000799A1 (fr) Procédé et dispositif de gestion de mémoire
WO2022120522A1 (fr) Procédé et dispositif d'attribution d'espace mémoire et support de stockage
CN114041119A (zh) 跨越信任边界的存储器解除分配
US9250977B2 (en) Tiered locking of resources
KR20220085831A (ko) 능력 관리 방법 및 컴퓨터 장치
US9251101B2 (en) Bitmap locking using a nodal lock
WO2023236629A1 (fr) Procédé et appareil d'accès aux données, et système de stockage et support de stockage
US11573719B2 (en) PMEM cache RDMA security
KR20190010508A (ko) 메시지 스케줄링 방법

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: 14869724

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: 14869724

Country of ref document: EP

Kind code of ref document: A1