Lock management method in cluster, lock server, and client

• US 10,609,150 B2
• Filed: 02/27/2019
• Issued: 03/31/2020
• Est. Priority Date: 12/14/2015
• Status: Active Grant

• Current Assignee: Huawei Technologies Co., Ltd. (Huawei Investment & Holding Co., Ltd.)
• Original Assignee: Huawei Technologies Co., Ltd. (Huawei Investment & Holding Co., Ltd.)
• Inventors: Lan, Wenhai, Zhang, Wei, Wang, Xueyou, Zhang, Yue
• Primary Examiner(s): Won, Michael
• Application Number:
  US16/287,479
• Publication Number:
  US 20190199801A1
• Time in Patent Office: 398 Days
• CPC Class Codes: G06F 15/17331 Distributed shared memory [DSM], e.g. remote direct memory access [RDMA]
• CPC Class Codes: G06F 15/177 Initialisation or configuration control processor initialisation G06F9/4405
• CPC Class Codes: G06F 3/0622 in relation to access
• CPC Class Codes: G06F 3/0637 Permissions
• CPC Class Codes: G06F 3/067 Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS]
• CPC Class Codes: G06F 9/52 Program synchronisation; Mutual exclusion, e.g. by means of semaphores
• CPC Class Codes: G06F 9/526 Mutual exclusion algorithms
• CPC Class Codes: H04L 67/14 Session management for real-time applications in data packet communications networks H04L65/1066

Abstract

A lock management solution in a cluster, where the cluster includes a client and a lock server, the lock server includes an interface card and a memory, the memory stores a read lock request queue recording an identifier of a client waiting for a read lock or obtaining the read lock, the memory further stores a write lock request queue recording an identifier of a client waiting for a write lock or obtains the write lock, and the memory further includes a read lock allocation count and a write lock allocation identifier, where the read lock allocation count records an allocated read lock, and the write lock allocation identifier indicates whether the write lock has been allocated.

Claims

1. A lock server comprising:

a memory configured to;

store a read lock request queue, wherein the read lock request queue records an identifier of a client that is in a client cluster and is either in a read lock waiting state or obtaining a read lock for a shared resource, and wherein the read lock request queue further records a write lock allocation identifier indicating whether a write lock for the shared resource is allocated; and

store a read lock allocation count indicating a quantity of read locks allocated for the shared resource; and

an interface card coupled to the memory and configured to;

receive, from a first client in the client cluster, a first read lock request carrying an identifier of the first client and carrying a first memory address in the read lock request queue;

write the identifier of the first client into the first memory address;

increase the read lock allocation count according to a quantity of read locks allocated to the first client when the write lock allocation identifier indicates that the write lock is not allocated; and

send, to the first client, a first message carrying the write lock allocation identifier and indicating that the first client obtains the read lock.

2. The lock server of claim 1, wherein the first message further indicates that the first client is in the read lock waiting state when the write lock allocation identifier indicates that the write lock has been allocated.

3. The lock server of claim 2, wherein the memory is further configured to store a write lock request queue, wherein the write lock request queue records an identifier of a client that is in the client cluster and is in a write lock waiting state for the shared resource, an identifier of a client that is in the client cluster and is obtaining the write lock for the shared resource, and an identifier that is of a second client in the client cluster and that is being stored in a memory address of a queue head of the write lock request queue when the write lock allocation identifier indicates that the write lock has been allocated.

4. The lock server of claim 1, wherein an identifier of a third client in the client cluster is stored in a memory address of a queue head of the read lock request queue, and wherein the first memory address comprises a memory address in a sequence from the queue head to a queue tail of the read lock request queue into which the identifier of the first client can be written.

5. The lock server of claim 1, wherein the first client obtains the read lock, and wherein the interface card is further configured to:

receive, from the first client, a read lock release request carrying the first memory address;

decrease the read lock allocation count according to the quantity of read locks allocated to the first client; and

delete the identifier of the first client from the first memory address.

6. The lock server of claim 1, wherein the first client becomes faulty after obtaining the read lock, and wherein the interface card is further configured to:

decrease the read lock allocation count according to the quantity of read locks allocated to the first client; and

delete the identifier of the first client from the first memory address.

7. A lock management method comprising:

storing, by a memory of a lock server, a read lock request queue, wherein the read lock request queue records an identifier of a client that is in a client cluster and is either in a read lock waiting state or that-is-obtaining a read lock for a shared resource, and wherein the read lock request queue further records a write lock allocation identifier indicating whether a write lock for the shared resource is allocated;

storing, by the memory, a read lock allocation count indicating a quantity of read locks allocated for the shared resource;

receiving, by an interface card of the lock server and from a first client in the client cluster, a first read lock request carrying an identifier of the first client and carrying a first memory address in the read lock request queue;

writing, by the interface card, the identifier of the first client into the first memory address;

increasing, by the interface card, the read lock allocation count according to a quantity of read locks allocated to the first client when the write lock allocation identifier indicates that the write lock is not allocated; and

sending, by the interface card and to the first client, a first message carrying the write lock allocation identifier and indicating that the first client obtains the read lock.

8. The lock management method of claim 7, further comprising storing, by the memory, a write lock request queue, wherein the write lock request queue records an identifier of a client that is in the client cluster and is in a write lock waiting state for the shared resource, an identifier of a client obtaining the write lock for the shared resource, and an identifier that is of a second client in the client cluster and that is being stored in a memory address of a queue head of the write lock request queue when the write lock allocation identifier indicates that the write lock has been allocated.

9. The lock management method of claim 8, further comprising:

receiving, by the interface card and from the first client, a read lock release request carrying the first memory address;

decreasing, by the interface card, the read lock allocation count according to the quantity of read locks allocated to the first client; and

deleting, by the interface card, the identifier of the first client from the first memory address.

10. The lock management method of claim 8, further comprising:

decreasing, by the interface card, the read lock allocation count according to the quantity of read locks allocated to the first client; and

deleting, by the interface card, the identifier of the first client from the first memory address.

11. The lock management method of claim 7, wherein an identifier of a third client in the client cluster is stored in a memory address of a queue head of the read lock request queue, and wherein the first memory address comprises a memory address in a sequence from the queue head to a queue tail of the read lock request queue into which the identifier of the first client can be written.

12. A computer program product comprising computer-executable instructions for storage on a non-transitory computer-readable medium that, when executed by a processor, cause an apparatus to:

store a read lock request queue, wherein the read lock request queue records an identifier of a client that is in a client cluster and that is either in a read lock waiting state or obtaining a read lock for a shared resource, and wherein the read lock request queue further records a write lock allocation identifier indicating whether a write lock for the shared resource is allocated;

store a read lock allocation count indicating a quantity of read locks allocated for the shared resource;

receive, from a first client in the client cluster, a first read lock request carrying an identifier of the first client and carrying a first memory address in the read lock request queue;

write the identifier of the first client into the first memory address;

increase the read lock allocation count according to a quantity of read locks allocated to the first client when the write lock allocation identifier indicates that the write lock is not allocated; and

send, to the first client, a first message carrying the write lock allocation identifier.

13. The computer program product of claim 12, wherein the instructions further cause the apparatus to store a write lock request queue, wherein the write lock request queue records an identifier of a client that is in the client cluster and is in a write lock waiting state for the shared resource, an identifier of a client that is in the client cluster and is obtaining the write lock for the shared resource, and an identifier that is of a second client in the client cluster and that is being stored in a memory address of a queue head of the write lock request queue when the write lock allocation identifier indicates that the write lock has been allocated.

14. The computer program product of claim 12, wherein an identifier of a third client in the client cluster is stored in a memory address of a queue head of the read lock request queue.

15. The computer program product of claim 14, wherein the first memory address comprises a memory address in a sequence from the queue head to a queue tail of the read lock request queue into which the identifier of the first client can be written.

16. The computer program product of claim 12, wherein the instructions further cause the apparatus to receive, from the first client, a read lock release request carrying the first memory address.

17. The computer program product of claim 16, wherein the instructions further cause the apparatus to decrease the read lock allocation count according to the quantity of read locks allocated to the first client.

18. The computer program product of claim 17, wherein the instructions further cause the apparatus to delete the identifier of the first client from the first memory address.

19. The computer program product of claim 12, wherein the instructions further cause the apparatus to decrease the read lock allocation count according to the quantity of read locks allocated to the first client.

20. The computer program product of claim 19, wherein the instructions further cause the apparatus to delete the identifier of the first client from the first memory address.