US 2015.0160872A1 (19) United States (12) Patent Application Publication (10) Pub. No.: US 2015/0160872 A1 CHEN (43) Pub. Date: Jun. 11, 2015

(54) OPERATION METHOD OF DISTRIBUTED (52) U.S. Cl. MEMORY DISKCLUSTER STORAGE CPC ...... G06F 3/0619 (2013.01); G06F 3/0689 SYSTEM (2013.01); G06F 3/0664 (2013.01) (71) Applicant: HSUN-YUAN CHEN, TAIPEI CITY 116 (TW) (57) ABSTRACT (72) Inventor: HSUN-YUAN CHEN, TAIPEI CITY 116 (TW) The present invention relates to anoperation method of dis (21) Appl. No.: 14/562,892 tributed memory disk cluster storage system, a distributed rº 3. memory storage system is adopted thereby satisfying four (22) Filed: Dec. 8, 2014 desired expansions which are the expansion of network band ------width, the expansion of hard disk capacity, the expansion of (30) Foreign Application Priority Data IOPS speed, and the expansion of memory I/O transmitting speed. Meanwhile, the system can be cross-region operated, Dec. 9, 2013 (TW) ------102145155 data center and WAN, so the user’s requirements can be Publication Classification collected through the local memory disk cluster for being provided with the correspondingp services, the capacity of the (51) Int. CI. memory disk cluster can also be gradually expanded for fur G06F 3/06 (2006.01) ther providing cross-region or cross-country data service.

user end user end user end user end

iSCSI FC FCOE NAS LAN P SAN virtualized Scheme Connection LAN iP

T T T------—----- 25 ------I | 1 | 101 102 | 103 - - — — — — ------—ill r------t - - - - Th|APP Eliº AFF EAFF EAFF

| 10 iiii |Tºº, ?º º Tºº

| | 11 || | i || ; : |||| |

} i || ||| | | 13 13 { } || 13 13 || | 13 13 l– — — — — — — — — — — — I li- ~ — — — — — — |# - -

| | | 20 i 20 i | virtualized distributed switch || i 1/8/10/16/40/56/100 1/8/10/16/40/56!400 1/8/10/16/40/56/100 Gbe physical switch Gbe physical switch Gbe physical switch

router

| SSL VPN or VPN Connection WAN iP º| Patent Application Publication Jun. 11, 2015 Sheet 1 of 2 US 2015/0160872 A1

puæuasnpuÐJasn

puædesnpuÐ13Sn|può10SnpuÐ

Patent Application Publication Jun. 11, 2015 Sheet 2 of 2 US 2015/0160872 A1

TOE„',() T?TODELDO@LODOEL

||||l.|||||| |||z||?zu| zu

US 2015/0160872 A1 Jun. 11, 2015

and other upward compatible type having different format, BRIEF DESCRIPTION OF THE DRAWINGS , GlusterFS, SphereFS, Taobao , ZFS, [0033] The present invention will be apparent to those SDFS, MooseRS, AdvKS, (BFS), , , skilled in the art by reading the following detailed description CrossDOS, disk file system (DFS), Episode, EFS, exFAT, ext, of a preferred embodiment thereof, with reference to the FAT, (GFS), (HFS), attached drawings, in which: HFS Plus, high performance file system, IBM general parallel [0034] FIG. 1 is a schematic view illustrating the operation file system, JFS, , MINIX, NetWare file method of distributed memory disk cluster storage system system, NILFS, Novell storage service, NTFS, QFS, according to one embodiment provided by the present inven QNX4FS, ReiserFS (), SpadPS, UBIFS, Unix file tion; and system, (VxIS), VFAT, write anywhere [0035] FIG. 2 is another schematic view illustrating the file layout (WAFL), XFS, , ZFS, CHFS, FFS2, F2FS, operation method of distributed memory disk cluster storage JFFS, JFFS2, LogFS, NVFS, YAFFS, UBIFS, DCE/DFS, system according to one embodiment provided by the present MFS, CXFS, GFS2, , OCFS, OCFS2, invention. QFS, Xsan, AFS, OpenAFS, AFP. MS-DFS, GPFS, , NCP, NFS, POHMELFS, Hadoop, HAMMER, SMB (CIFS), DETAILED DESCRIPTION OF THE PREFERRED , FUSE, SquashFS, UMSDOS, UnionFS, , EMBODIMENT devfs, , spec?s, , trnpfs, WinFS, EncPS, EFS, ZFS, [0036] The following descriptions are of exemplary RAW, ASM, LVM, SFS, MPFS or MGFS. embodiments only, and are not intended to limit the scope, [0030] According to the operation method of distributed applicability or configuration of the invention in any way. memory disk cluster storage system provided by the present Rather, the following description provides a convenient illus invention, the distributed memory storage system can satisfy tration for implementing exemplary embodiments of the invention. Various changes to the described embodiments four desired expansions which are the expansion of network may be made in the function and arrangement of the elements bandwidth, the expansion of hard disk capacity, the expansion described without departing from the scope of the invention of IOPS speed, and the expansion of memory I/O transmitting as set forth in the appended claims. speed. Meanwhile, the system can be cross-region operated, [0037] Referring from FIG. 1, the present invention pro data center and WAN, so the user’s requirements can be vides an operation method of distributed memory disk cluster collected through the local memory disk cluster for being storage system, wherein one preferred embodiment for illus provided with the corresponding services, the capacity of the trating the operation method of distributed memory disk clus memory disk cluster can also be gradually expanded for fur ter storage system is as following: ther providing cross-region or cross-country data service. [0038] The installation of a distributed memory storage [0031] With the increased quantity of the storage devices, equipment includes a plurality of computer units (10) for increasing one server would have the network bandwidth and assembling a cluster scheme (1) so as to form a cluster the disk capacity being correspondingly accumulated thereby memory disk; wherein the computer unit (10) is installed with forming a resource pool, the distributed memory disk cluster a CPU, at least a memory, at least a hard disk, at least a storage is served like a physical hard disk, so the whole network card, a mother board, an I/O interface card, at least a operation would not be affected due to one of the physical connection cable and a housing. [0039] The computer unit (10) is installed with a system mainframes being failed, the chunk memory disk in the copy virtual machine platform operation system, so the computer could copy the stored data to a new chunk memory disk, so a unit (10) is formed with a plurality of virtual machines, and fundamental data backup is maintained, meanwhile the con the computerunit (10) is used for setting the required machine tinuous data protector (CDP) is also adopted for providing memory resource capacity, the operation system is used for novel service of data backup and recovery, thus the disadvan setting the memory capacity occupying manner, or a program tages of the tape backup often being failed and the backup software is utilized for planning the memory to a hard disk only being performed once a day are improved. device for forming as a chunk memory disk (11) which is the [0032] In addition, the data generated through the copy can same as the tracks of a hard disk. be sent from different chunk memory disk thereby achieving [0040] As such, a file is enabled to be divided into one or the many-to-one data transmission, when the user amount plural data, and the file size can bed. MB or bigger, one or increases, only increasing the quantity of the chunk memory plural copies are evenly distributed in the chunk memory disk disk can achieve the many-to-many transmission, so the dis (11), so the data is actually stored in a , and a advantages of the multiple RAID hard disks crashing causing memory bus with multiple channels is utilized for parallel the whole data being missed, the limitation of the quantity of accessing the memory module thereby allowing the capacity network interface of storage device and the network speed of the memory module to be planned for being used as a hard causing the excessive data being overly jammed and delayed disk, wherein the access of the memory module supports all for transmitting, the expansion of LUN and the data center the file formats of the operation system, and a distributed being unable to be cross-region operated can be solved; the storage scheme is utilized for allowing the data to be copied to present invention adopts the memory being served as a disk, one or more copies, with the above-mentioned method, the each file or each virtual machine can be stored in the memory data center can still be operated even if the machine is broken with a file format, the highest I/O speed of the memory bus and/or the data center is damaged. can be directly utilized, the data can be transmitted between [0041) Each copied data can be encrypted through mixing the CPU and the memory, the highest I/O number, distance the 1-4096 bit AES and RSA for being stored in the memory, and speed can be provided. Accordingly, the present invention when the data is desired to be accessed, the data is transmitted is novel and more practical in use comparing to prior art. between the memory and the CPU thereby minimizing the US 2015/0160872 A1 Jun. 11, 2015

I/O accessing times and distance, the virtual machine is and the data access speed and the data liability can also be formed as a file format for being stored in the memory mod increased, and the above-mentioned can be gradually ule, the memory capacity planned for the virtual memory is increased according to the user’s desire. also in the same sector. [0048] When the cluster schemes (1) are formed, each of [0042] When the operation system of the virtual machine the cluster schemes can be independently operated, and each directly accesses the required file through the CPU, the pro of the clusterschemes (1) can be used as a distributed memory cessed data is stored in the memory module, the memory disk cluster storage (DMDCS) (1A), the network layer inter required by the virtual machine for computing is also in the face is used for stacking, so each of the distributed memory memory module, the computed data is directly stored in the disk cluster storages (1A) can be used for simulating a chunk original location of the memory module of the virtual memory disk, a new cluster data control station (1011) and a machine operation system; with the reduced access path and new cluster data backup station (1021) are provided for con the fastest I/O speed, the storage system provided by the trolling the amount of processed data to be distributed in all present invention allows most of the data in the computer unit the chunk memory disks. (10) to be processed in the chunk memory disk (11) with a [0049] Accordingly, the above-mentioned is the same as parallel computing manner, the data which is not in the com utilizing the resource of each mainframe for parallel comput puter unit (10) accesses the chunk memory disk (11) of other ing, the data is divided into blocks for being transmitted to computer unit (10) through a network card (13) being con each machine for computing, then eventually integratedto a nected to a connection port cluster link (20). final result. [0043] Wherein, the virtual machine platform operation [0050] When one of the chunk memory disks (11) is failed system can be VMware vSphereeSXi 4.1 or later version, or one of the distributed memory disk cluster storages (1A) is Microsoft Server 2012 R2 Hyper-V or later version, Citrix failed, the operation of the whole disk is not affected and the XenServer Oracle VM, Oeacle VM, Red Hat KVM. Red Hat whole disk is prevented from being totally crashed. Control groups (), Red Hat Containers (LXC), [0051] Moreover, when the memory of one of the computer KVM, Eucalyptus, OpenStack, User Mode Linux, LXC, units (10) is failed, the server computer unit marks the dam OpenVZ, OpenNebula, Enomaly’s Elastic Computing, aged memory as malfunction, and the chunk memory IC of OpenFlow, or Linux-Base KVM; and the virtual machine the DIMM memory is no longer in use, the resource would operation system can be Linux (Linux 2.6.14 and up have only be used again after the memory is replaced. FUSE Support included in the official kernel), FreeBSD, [0052] The memory of the virtual machine is operated OpenSolaris orMacOS X. through a (SAN), a network layer inter [0044) Moreover, each of the chunk memory disks (11) can face virtualized by a software is adopted for connecting all the be provided with a monitor unit for monitoring the operation chunk memory disks so as to be jointly operated; the network status, the detection unit can adopt the Splunk or any software layer interface adopts SAN, SAN iSCSI, SAN FC, SAN provided by other search engine for the purpose of monitor FCoE, NFS, NAS, JBOD, CIFS, FUSE interface for commu ing, when a problem is detected, a service of restarting appli nicating with the server and the disk driver, and the cation software can be provided thereby achieving a recovery RAMSTORAGETM API is provided and served as a backup function, the mentioned program is prior art therefore no program. further illustration is provided. [0053] Wherein the RAMSTORAGETM API adopts REST, [0045] With respect to the assigned functions, each of the Restful, C++, PHP, Python, Java, Perl, Javascript and other computer units (10) can be categorized to a first data center program developing software for forming the RAMSTOR (101), at least a second data center (102) and a backup center AGETM API, and the API function of the distributed memory (103); wherein the first data center (101) is provided with a disk cluster storage (1A) includes tolerance, backup, shift, virtual cluster data control station (1011) for controlling, rapidly layout virtual machine, planningdisk size, automati wherein each of the second data centers (102) is provided cally increasing the chunk memory disks (11) according to with a virtual cluster data backup station (1021) for control the actual needs, balancing the data loading between chunks, ling, and the backup center (103) is provided with a virtual backup recovery, continuous back protector (CDP), rapid cluster data backup station (1021) for controlling, wherein the capture and monitoring resource. first data center (101) and the second data center (102) jointly [0054] In addition, each of the chunk memory disks (11) is form a distributed memory file system (40). respectively and electrically connected to at least a hard disk [0046) Referring to FIG. 2, a stack scheme is provided for storage device (12), the hard disk storage device (12) is served expanding the storage capacity scheme, the access means of a to backup the data in the chunk memory disk (11) in every network layer interface is utilized to plan the plural chunk preset period of time thereby avoiding any unanticipated mal memory disks (11) of a computer unit (10) to a resource pool function, for example in every minute, the altered portion of of cluster memory disk unit with a cluster concept, the oper certain data in each of the chunk memory disks (11) is copied ating theory is the same as that of the bus of the computer. to the hard disk storage device (12) for the purpose of data [0047] When the 64 bit chunk memory disks (11) of the backup. plural computer units (10) are adopted, the operation is the [0055] When each of the chunk memory disks (11) restarts, same as the 64 bit CPU bus for synchronously using all the the last backup data stored in the hard disk storage device (12) chunk memory disks (11) for accessing data; when the quan would be fully recovered to the chunk memory disk (11), and tity of the chunk memory disks (11) is expanded, the opera the cluster data control station (1011) is informed for joining tion is the same as upgrading the 64 bit CPU bus to 128 bit or the cluster operation. 256 bit, the access speed is increased with an accumulating [0056] All the chunk memory disks (11) of all the computer manner, so the memory disk capacity can be increased units (10) use the continuous data protector (CDP) for con through the quantity of chunk memory disk (11) being stantly and continuously backup the data to a common large increased, the limitation of the disk capacity can be increased, scale hard disk cluster array for the purpose of back up, when

US 2015/0160872 A1 Jun. 11, 2015

WiMAX, 3G broadcast network, CDMA20001X, Wi-Fi, the appended claims. Although specific terms are employed SuperWiFi, Wi-Fi GO and other upward compatible IEEE herein, they are used in a generic and descriptive sense only network transmission protocol. and not for purposes of limitation. [0068] With the technical breakthrough for theqistributed memory disk cluster storage systemprovided by the present What is claimed is: invention, the distributed memory storage system can satisfy 1. An operation method of distributed memory disk cluster four desired expansions which are the expansion of network storage system, characterized in: firstly the installation of a bandwidth, the expansion of hard disk capacity, the expansion distributed memory storage equipment includes a plurality of of IOPS speed, and the expansion of memory I/O transmitting computer units for assembling a cluster scheme so as to form speed. Meanwhile, the system can be cross-region operated, a cluster memory disk; data center and WAN, so the user’s requirements can be the computer unit is installed with a system virtual machine collected through the local memory disk cluster for being platform operation system, the computer unit is formed provided with the corresponding services, the capacity of the with a plurality of virtual machines, and the computer memory disk cluster can also be gradually expanded for fur unit is used for setting the memory capacity occupying ther providing cross-region or cross-country data service. means through the operation system or a program soft [0069] With the increased quantity of the storage devices, ware, so the memory is able to be planed as a storage increasing one server would have the network bandwidth and device thereby forming as a plurality of chunk memory the disk capacity being correspondinglyaggregatedthereby disks; a file is divided into one or plural data, one or forming a resource pool, the distributed memory disk cluster plural copies are evenly distributed in the chunk memory storage (1A) is served like a physical hard disk, so the whole disk, a memory bus with multiple channels is utilized for operation would not be affected due to one of the physical parallel accessing the memory module thereby allowing mainframes being failed, the chunk memory disk (11) in the the capacity of the memory module to be planned for copy could copy the stored data to a new chunk memory disk being used as a hard disk, wherein the access of the (11), so a fundamental data backup is maintained, meanwhile memory module supports all the file formats of the the continuous data protector (CDP) is also adopted for pro operation system, and a distributed storage scheme is viding novel service of data backup and recovery, thus the utilized for allowing the data to be copied to one or more disadvantages of the tape backup often being failed and the copies; backup only being performed once a day are improved. [0070] In addition, the data generated through the copy can when the operation system of the virtual machine directly be sent from different chunk memory disk (11) thereby accesses the required file through the CPU, the pro achieving the many-to-one data transmission, when the user cessed data is stored in the memory module, the memory amount increases, only increasing the quantity of the chunk used by the virtual machine for computing is also in the memory disk (11) can achieve the many-to-many transmis memory module, the computed data is directly stored in sion, so the disadvantages of the multiple RAID hard disks the original location of the memory module of the virtual crashing causing the whole data being missed, the limitation machine operation system, so most of the data in the of the quantity of network interface of storage device and the computer unit is able to be processed in the chunk network speed causing the excessive data being overly memory disk with a parallel computing manner; the data jammed and delayed for transmitting, the expansion of LUN which is not in the computer unit accesses the chunk and the data center being unable to be cross-region operated memory disk of other computer unit through a network can be solved; the present invention adopts the memory being card being connected to a connection port cluster link; served as a disk, each file or each virtual machine can be with respect to the assigned functions, each of the com stored in the memory with a file format, the highest I/O speed puter units is categorized to a first data center, at least a of the memory bus can be directly utilized, the data can be second data center and a backup center; wherein the first transmitted between the CPU and the memory, the highest I/O data center is provided with a virtual cluster data control number, distance and speed can be provided. Accordingly, the station for controlling, wherein each of the second data present invention is novel and more practical in use compar centers is provided with a virtual cluster data backup ing to prior art. station for controlling, and the backup centeris provided [0071] It is to be understood, however, that even though with a virtual cluster data backup station for controlling, numerous characteristics and advantages of the present wherein the first data center and the second data center invention have been set forth in the foregoing description, together form a distributed memory file system; more together with details of the structure and function of the over, a stack scheme is provided for expanding the stor invention, the disclosure is illustrative only, and changes may age capacity scheme, the access means of a network be made in detail, especially in matters of shape, size, and layer interface is utilized to plan the plural chunk arrangement of parts within the principles of the invention to memory disks of a computer unit to a resource pool of the fill indicated by the broad general meaning of the cluster memory disk unit with a cluster concept, and all terms in which the appended claims are expressed. the chunk memory disks are enabled to be synchro [0072] Many modifications and other embodiments of the nously operated for accessing data; inventions set forth herein will come to mind to one skilled in when the cluster schemes are formed, each of the cluster the art to which these inventions pertain having the benefit of schemes is able to be independently operated, and each the teachings presented in the foregoing descriptions and the of the clusterschemesis able to be served as a distributed associated drawings. Therefore, it is to be understood that the memory disk cluster storage, the network layerinterface inventions are not to be limited to the specific examples of the is used for stacking, each of the distributed memory disk embodiments disclosed and that modifications and other cluster storages is able to beused for simulating a chunk embodiments are intended to be included within the scope of memory disk, a new cluster data control station and a US 2015/0160872 A1 Jun. 11, 2015

new cluster data backup station are provided for control RAMSTORAGETMAPI adopts the REST, Restful, C++, PHP. ling the amount of processed data to be distributed in all Python, Java, Perl, JavaScript and other program developing the chunk memory disks. software for forming the RAMSTORAGETM API, and the 2. The operation method of distributed memory disk clus API function of the distributed memory disk cluster storage ter storage system according to claim 1, wherein each of the includes tolerance, backup, shift, rapidly layout virtual chunk memory disks is respectively and electrically con machine, managing disk size, automatically increasing the nected to at least a hard disk storage device, the hard disk chunk memory disks according to the actual needs, balancing storage device is served to backup the data in the chunk the data loading between chunks, backup recovery, continu memory disk in every preset period of time. ous back protector, rapid capture and monitoring resource. 3. The operation method of distributed memory disk clus 12. The operation method of distributed memory disk clus ter storage system according to claim 1, wherein the chunk terstorage system according to claim 1, where in the CPU, the memory disks of all the computer units use the continuous memory and the physical hard disk which are not in use is data protector for constantly and continuously backup the integrated as a common resource pool through the virtual data to a common large-scale hard disk cluster array for the machine platform operation system, and each required com purpose of back up. puter resource is able to be automatically adjusted and trans 4. The operation method of distributed memory disk clus mitted to other computer unit having richer resource. terstorage system according to claim 1, wherein the computer 13. The operation method of distributed memory disk clus unit is installed with a CPU, at least a memory, at least a hard ter storage system according to claim 1, wherein the connect disk, at least a network card, a mother board, an I/O interface ing manner of the plural distributed memory disk cluster card, at least a connection cable and a housing. storages is according to the physical internet transmission 5. The operation method of distributed memory disk clus protocol, and the packages is able to be transmitted through ter storage system according to claim 1, wherein each copied SSL, VPN or encryption computing manner; when the net data is encrypted through mixing the 1-4096 bit AES and work connection is unable to be established, each region is RSA for being stored in the memory, when the data is desired able to be independently operated, when the connection is to be accessed, the data is transmitted between the memory recovered, the data is able to be fully synchronized to each of and the CPU, the virtual machine is formed as a file format for the chunk memory disks of each of the distributed memory being stored in the memory module, the memory capacity disk cluster storages. planned for the virtual memory is also in the same sector. 14. The operation method of distributed memory disk clus 6. The operation method of distributed memory disk clus ter storage system according to claim 1, wherein the CPU is ter storage system according to claim 1, wherein each of the selected from , x86-64, IA-64, Alpha, ARM, SPARC 32 chunk memory disks is provided with a monitor unit for and 64, PowerPC, MIPS and Tilera. monitoring the operation status, the detection unit adopts the 15. The operation method of distributed memory disk clus Splunk or any software provided by other search engine for terstorage system according to claim 1, wherein the operating the purpose of monitoring, when a problem is detected, a manner of the memory installed in the computer unit is to service of restarting application software is provided thereby directly utilize the memory controller of the CPU to directly achieving a recovery function. access the memory data with a manner of three-channel or 7. The operation method of distributed memory disk clus multiple-channel and a speed of 800 MHz to 1,333 MHz or ter storage system according to claim 1, wherein the virtual higher. machine platform operation system is VMware vSphereBSXi 16. The operation method of distributed memory disk clus 4.1 or later version, Microsoft Server 2012 R2 Hyper-V or ter storage system according to claim 15, wherein the later version, Citrix XenServer Oracle VM, Oeacle VM, Red memory capacity is 1 MB to 16 ZB. Hat KVM, Red Hat Control groups (cgroups), Red Hat Linux 17. The operation method of distributed memory disk clus Containers (LXC), KVM, Eucalyptus, OpenStack, User terstorage system according to claim 15, wherein the adopted Mode Linux, LXC, OpenVZ, OpenNebula, Enomaly’s Elas memory type is a dynamic random access memory (DRAM), tic Computing, OpenFlow, or Linux-Base KVM. a synchronous dynamic memory (DRAM), a dynamic mobile 8. The operation method of distributed memory disk clus platform memory, a dynamic graphic process memory, a ter storage system according to claim 1, wherein the virtual dynamic memory, a static random access memory machine operation system is Linux, FreeBSD, OpenSolaris (SRAM), a -only memory (ROM), a magnetoresistive or MacOS X. random access memory or a . 9. The operation method of distributed memory disk clus 18. The operation method of distributed memory disk clus ter storage system according to claim 1, the memory of the ter storage system according to claim 17, wherein the virtual machine is operated through the storage area network, dynamic random access memory (DRAM) is FPM RAM or a network layer interface virtualized by a software is adopted EDO RAM. for connecting all the chunk memory disks so as to be jointly 19. The operation method of distributed memory disk clus operated. ter storage system according to claim 17, wherein the syn 10. The operation method of distributed memory disk clus chronous dynamic memory (DRA) is SDRAM, DDR ter storage system according to claim 9, wherein the network SDRAM, DDR2 SDRAM, DDR3 SDRAM, DDR4 SDRAM layer interface adopts the SAN, SAN iSCSI, SAN FC, SAN Or DDR5 SDRAM FCoE, NFS, NAS, JBOD, CIFS or FUSE interface for com 20. The operation method of distributed memory disk clus municating with the server and the disk driver, and the ter storage system according to claim 17, wherein the RAMSTORAGETM API is provided and served as a backup dynamic mobile platform memory is LPDDR, LPDDR2, program. LPDDR3 Or LPDDR4. 11. The operation method of distributed memory disk clus 21. The operation method of distributed memory disk clus ter storage system according to claim 10, where in the ter storage system according to claim 17, wherein the US 2015/0160872 A1 Jun. 11, 2015 dynamic graphic process memory is VRAM, WRAM, board is compatible with the x86, x86-64, IA-64, Alpha, MDRAM, SDRAM, SDRAM, GDDR, GDDR2, GDDR3, ARM, SPARC 32 and 64, PowerPC, MIPS and Tilera pro GDDR4, GDDR5 or GDDR6, GDDR7. CeSSer. 22. The operation method of distributed memory disk clus 29. The operation method of distributed memory disk clus terstorage systemaccording to claim 17, wherein the dynamic ter storage systemaccording to claim 1, wherein the file for mat of the operation system is VMFS3, VMFS5 and other Rambus memory is RDRAM, XDR DRAM or XDR2 upward compatible type having different format, VHD and DRAM. other upward compatible type having different format, 23. The operation method of distributed memory disk clus VHDX and other upward compatible type having different ter storage system according to claim 17, wherein the flash format, VMDIK and other upward compatible type having memory is NOR Flash, NAND Flash, 3D NAND Flash, different format, HDFS and other upward compatible type V-Flash, SLC, MLC, eMMC or TLC. having different format, IsilonCneFS and other upward com 24. The operation method of distributed memory disk clus patible type having different format, any format generated ter storage system according to claim 17, wherein the mag through memory-type pagefile and other upward compatible netoresistiverandom access memory is MRAM. type having different format, VEs and other upward compat ible type having different format, VPSs and other upward 25. The operation method of distributed memory disk clus compatible type having different format, Ceph, GlusterFS, ter storage system according to claim 17, wherein the hard SphereFS, Taobao File System, ZFS, SDFS, Moosef’S, disk storage device is a conventional disk head, a floppy-disk AdveS, Be file system (BFS), Btrfs, Coda, CrossDOS, disk drive, solid state drive, internet drive, SAS drive, SATA drive, file system (DFS), Episode, EFS, ex}AT, ext, FAT, global file mSATA drive, mPCIE drive, FC drive, SCSI drive, ATA drive, system (GFS), hierarchical file system (HFS), HFS Plus, high NAND Flash card, FCoE drive. performance file system, IBM general parallel file system, 26. The operation method of distributed memory disk clus JFS, Macintosh file system, MINIX, NetWare file system, terstorage system according to claim 1, wherein the network NILFS, Novell storage service, NTFS, QFS, QNX4 FS, Reis card is an Ethernet, fast Ethernet, gigabit Ethernet, glass fiber, erFS (ReiserA), SpadPS, UBIFS, , Veritas file token ring network, InfiniBand, FCoE or wireless network. system (VxIFS), VFAT, write anywhere file layout (WAFL), 27. The operation method of distributed memory disk clus XFS, Xsan, ZFS, CHFS, FFS2, F2 FS, JFFS, JFFS2, LogFS, terstorage system according to claim 26, wherein the network NVFS, YAFFS, UBIFS, DCE/DFS, MFS, CXFS, GFS2. speed is 2 Mbit/s, 10 Mbit/s, 11 Mbit/s, 40 Mbit/s, 54 Mbit/s, Google file system, OCFS, OCFS2, QFS, Xsan, AFS, 80 Mbit/s, 100 Mbit/s, 150 Mbit/s, 300 Mbit/s, 433 Mbit/s, OpenAFS, AFP MS-DFS, GPFS, Lustre, NCP, NFS, POHM 1,000 Mbit/s, 1 Gbit/s, 8 Gbit/s, 10 Gbit/s, 16 Gbit/s, 32 ELFS, Hadoop, HAMMER, SMB (CIFS), cramfs, FUSE, Gbit/s, 40 Gbit/s, 56 Gbit/s, 100 Gbit/s, 160 Gbit/s, 1,000 SquashFS, UMSDOS, UnionFS, configfs, devfs, procfs, Gbit/s or higher. spec?s, sysfs, trimpfs, WinFS, EncPS, EFS, ZFS, RAW, ASM, 28. The operation method of distributed memory disk clus LVM, SFS, MPFS or MGFS. ter storage system according to claim 1, wherein the mother