Data processing system and memory management method of data processing system

1. A memory management method of a data processing system, comprising:

creating a first memory zone and a second memory zone related to a first node of a first server, wherein the first server is located in the data processing system, and the first node comprises a processor and a first memory;

mapping the first memory zone to the first memory;

mapping the second memory zone to a second memory of a second server, wherein the second server is located in the data processing system, and the processor is configured to access the second memory of the second server through an interface circuit of the first server and through an interface circuit of the second server; and

mapping the second memory zone to a third memory included in a second node of the first server, wherein the processor of the first node is configured to access the third memory of the second node through a node interconnection.

2. The memory management method of claim 1 , further comprising:

when the first memory or the third memory has a free space, allocating a memory page associated with a process running on the first node to the free space; and

when each of the first memory and the third memory is full, allocating the memory page to the second memory of the second server.

3. The memory management method of claim 1 , further comprising:

allocating a plurality of memory pages associated with a process running on the first node to the first memory, the second memory and the third memory in an interleaved manner.

4. The memory management method of claim 1 , further comprising:

allocating a first memory page associated with a process running on the first node to the second memory; and

utilizing the interface circuit of the first server to store a page table, wherein the page table indicates a mapping relationship between a virtual address and a physical address corresponding to the first memory page.

5. The memory management method of claim 4 , further comprising:

utilizing the page table to record a number of times the first memory page is accessed; and

when the number of times the first memory page is accessed reaches a predetermined number of times, swapping the first memory page and a second memory page allocated to the first memory.

6. The memory management method of claim 5 , wherein the step of swapping the first memory page and the second memory page comprises:

determining the second memory page according to a least recently used algorithm or a least frequently used algorithm.

7. The memory management method of claim 5 , further comprising:

when the number of times the first memory page is accessed reaches the predetermined number of times, sending an interrupt request to an operating system running on the first node.

8. The memory management method of claim 4 , further comprising:

utilizing the page table to record metadata corresponding to the second memory, wherein the metadata is indicative of a memory type of the second memory.

9. The memory management method of claim 4 , wherein a portion of bits of the virtual address is arranged to indicate that the first memory page is allocated to the second server.

10. A data processing system, comprising:

a first server, comprising a first node and a first interface circuit, the first node comprising a processor and a first memory, wherein the processor is configured to create a first memory zone and a second memory zone related to the first node, and map the first memory zone to the first memory; and

a second server, comprising a second memory and a second interface circuit, wherein the first interface circuit is coupled to the second memory through the second interface circuit; the processor of the first server is configured to access the second memory of the second server through the first interface circuit and the second interface circuit, and map the second memory zone to the second memory of the second server;

wherein the first server further comprises a second node, and the processor is configured to access a third memory of the second node through a node interconnection, and map the second memory zone to the third memory.

11. The data processing system of claim 10 , wherein when the first memory or the third memory has a free space, the processor is configured to allocate a memory page associated with a process running on the first node to the free space; when each of the first memory and the third memory is full, the processor is configured to allocate the memory page to the second memory of the second server.

12. The data processing system of claim 10 , wherein the processor is configured to allocate a plurality of memory pages associated with a process running on the first node to the first memory, the second memory and the third memory in an interleaved manner.

13. The data processing system of claim 10 , wherein the processor is configured to allocate a first memory page associated with a process running on the first node to the second memory; the first interface circuit is configured to store a page table indicative of a mapping relationship between a virtual address and a physical address corresponding to the first memory page.

14. The data processing system of claim 13 , wherein the page table is arranged to record a number of times the first memory page is accessed; when the number of times the first memory page is accessed reaches a predetermined number of times, the processor is configured to swap the first memory page and a second memory page allocated to the first memory.

15. The data processing system of claim 14 , wherein the processor is configured to determine the second memory page according to a least recently used algorithm or a least frequently used algorithm.

16. The data processing system of claim 14 , wherein when the number of times the first memory page is accessed reaches the predetermined number of times, the first interface circuit is configured to send an interrupt request to the processor.

17. The data processing system of claim 13 , wherein the page table is arranged to record metadata corresponding to the second memory; the metadata is indicative of a memory type of the second memory.

18. The data processing system of claim 13 , wherein a portion of bits of the virtual address is arranged to indicate that the first memory page is allocated to the second server.