CN104657316A - Server - Google Patents
Server Download PDFInfo
- Publication number
- CN104657316A CN104657316A CN201510101293.7A CN201510101293A CN104657316A CN 104657316 A CN104657316 A CN 104657316A CN 201510101293 A CN201510101293 A CN 201510101293A CN 104657316 A CN104657316 A CN 104657316A
- Authority
- CN
- China
- Prior art keywords
- node
- disk
- sas
- computational resource
- storage resources
- Prior art date
- Legal status (The legal status 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 status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0602—Interfaces specially adapted for storage systems specifically adapted to achieve a particular effect
- G06F3/0608—Saving storage space on storage systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0668—Interfaces specially adapted for storage systems adopting a particular infrastructure
- G06F3/067—Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a server, which comprises a calculation resource node, a storage resource node and an SAS (serial attached small computer system interface) switch, wherein the calculation resource node and the storage resource node are respectively connected with the SAS switch, and are physically separated. The server has the advantages that a storage resource can be statically or dynamically distributed to one or a plurality of calculating resource nodes by using a single disc as granularity, so pooling sharing of the storage resource is realized, and the resource utilization rate is improved; the server can be flexibly expanded.
Description
Technical field
The present invention relates to calculating communication technical field, particularly relate to a kind of server.
Background technology
Traditional local storage server is usually by central processing unit (Central Processing Unit, CPU), mechanical hard disk (Hard Disk Drive, HDD), solid state hard disc (Solid State Disk, etc. SSD) concentrate in single physics cabinet, usually different application is met to capacity, bandwidth and number of times (the Input/output Per Second carrying out read-write operation per second with different server design schemes, IOPS) differentiated demand, cannot flexible expansion change to meet different application demands.In addition, local storage resources easily occurs that utilization factor is not enough, and these storage resources more than needed cannot be shared with the use of other computational resources efficiently.
Summary of the invention
The present invention is intended to solve one of technical matters in correlation technique at least to a certain extent.
For this reason, one object of the present invention is to propose a kind of server, and this server can flexible expansion, the ratio of static or dynamic conditioning computational resource and storage resources, and the pondization that can realize storage resources is shared.
For achieving the above object, the server that the embodiment of the present invention proposes, comprising: computational resource node; Storage resources node; SAS switch; Wherein, described computational resource node is connected with described SAS switch respectively with described storage resources node, and described computational resource node is physically be separated setting with described storage resources node.
The server that the embodiment of the present invention proposes, by computational resource node is separated setting with storage resources node, computational resource can be realized be coupled with the solution of storage resources, and be connected with computational resource node and storage resources node respectively by SAS switch, computational resource can be realized and storage resources is interconnected by SAS switch, corresponding configuration can be carried out to SAS switch, static or between dynamic conditioning computational resource and storage resources access relation is shared with the pondization realizing storage resources, thus can realize the flexible configuration of server.
The aspect that the present invention adds and advantage will part provide in the following description, and part will become obvious from the following description, or be recognized by practice of the present invention.
Accompanying drawing explanation
The present invention above-mentioned and/or additional aspect and advantage will become obvious and easy understand from the following description of the accompanying drawings of embodiments, wherein:
Fig. 1 is the structural representation of the server that one embodiment of the invention proposes;
Fig. 2 is the structural representation of the server that another embodiment of the present invention proposes;
Fig. 3 is the structural representation of the server that another embodiment of the present invention proposes;
Fig. 4 is the structural representation of the server that another embodiment of the present invention proposes;
Fig. 5 is the structural representation of the server that another embodiment of the present invention proposes;
Fig. 6 is the structural representation of the server that another embodiment of the present invention proposes;
Fig. 7 is the structural representation of the server that another embodiment of the present invention proposes;
Fig. 8 is the structural representation of the server that another embodiment of the present invention proposes;
Fig. 9 is the structural representation of the server that another embodiment of the present invention proposes.
Embodiment
Be described below in detail embodiments of the invention, the example of described embodiment is shown in the drawings, and wherein same or similar label represents same or similar module or has module that is identical or similar functions from start to finish.Being exemplary below by the embodiment be described with reference to the drawings, only for explaining the present invention, and can not limitation of the present invention being interpreted as.On the contrary, embodiments of the invention comprise fall into attached claims spirit and intension within the scope of all changes, amendment and equivalent.
Fig. 1 is the structural representation of the server that one embodiment of the invention proposes, this server comprises: computational resource node 11, storage resources node 12 and be connected in series SCSI (Serial Attached SCSI, SAS) switch (Switch) 13, wherein, SCSI is small computer system interface (Small Computer System Interface).
Wherein, described computational resource node 11 is connected with described SAS switch 13 respectively with described storage resources node 12, and described computational resource node 11 is physically be separated setting with described storage resources node 12.
Computational resource node 11 is one or more, and storage resources node 12 is one or more, multiplely refers at least two.
Computational resource node 11 specifically can refer to main frame (Host), storage resources node 12 specifically can comprise disk cluster (Just a Bunch of Disks, JBOD), computational resource node 11 is connected with SAS switch 13 respectively by one or more SAS cables with storage resources node 12.SAS cable can the SAS3.0 cable of specifically x4.CPU and host bus adaptor (Host Bus Adapter can be comprised in each main frame, HBA) card or Redundant Array of Independent Disks (RAID) (Redundant Array of Independent Disks, RAID) block, certainly, all the other peripheral hardwares can also be comprised in each main frame.
Comprise CPU and HBA card for main frame, as shown in Figure 2, computational resource node 21 comprises: CPU and HBA card, and storage resources node 22 is JBOD, and described HBA cartoon is crossed SAS cable 24 and connected described SAS switch 23; Described JBOD connects described SAS switch 23 by SAS cable 24.
CPU, HDD, SSD etc. concentrate in single physics cabinet by traditional local storage server design proposal usually, it cannot flexible expansion change to meet different application demands, therefore usually meets different application demands with different server design schemes.And in the present embodiment, as implied above, computational resource node and storage resources node are physically separated setting, by SAS switch-fabric, realize the solution coupling of computational resource and storage resources, thus the physical restriction of unit can be broken through.
In the present embodiment, on the one hand, SAS cable can be one or more, can connect new JBOD by SAS cable, increase the quantity of JBOD, therefore the quantity of JBOD increases flexibly, thus the flexible expansion of memory capacity can be realized, on the other hand, JBOD can have one-level or multi-stage cascade structure, can further expand memory capacity when reducing SAS switch ports themselves and taking.
The interconnected bandwidth of the single cable of SAS cable can reach 48Gb, the number of computational resource node and the SAS cable between storage resources node and SAS switch can be multiple, by increasing the number of the cable between node and SAS switch, interconnected bandwidth can be expanded.
The embodiment of the present invention can realize the performance of Direct Attached Storage (Direct Attached Storage, DAS), possesses the dirigibility of storage area network (Storage Area Network, SAN) network simultaneously.At interior of equipment cabinet, computational resource node is directly by the storage resources node of SAS switch-access rear end.
Across rack node between the access of storage resources then can use common distributed file system, such as, see Fig. 2, Ethernet cabinet top (Top of Rack is also comprised in this server, TOR) switch 25, computational resource node 21 is connected with Ethernet TOR switch 25 by Ethernet 26.
In addition, see Fig. 2, can also comprise in server: colony dispatching center 27, colony dispatching center 27 is connected with Ethernet TOR switch 25 by Ethernet 26, when computational resource node needs to send message to colony dispatching center, message can be sent to colony dispatching center via Ethernet and Ethernet TOR switch by computational resource node.SAS switch 23 is also connected with Ethernet TOR switch 25 by Ethernet 26, and when colony dispatching center needs to send message to SAS switch, message can be sent to SAS switch via Ethernet and Ethernet TOR switch by colony dispatching center.
In another embodiment, described SAS switch for: with the single disc on described storage resources node for granularity, set up the mapping relations of computational resource and storage resources.
Such as, the mapping relations that static configuration is above-mentioned on SAS switch, to reduce server Configuration Type.And, the present embodiment is take single disc as granularity when configuring, the mapping relations of configuration are the mapping relations in each computational resource node and storage resources node between each disk, and the different disk on same storage resources node can configure to different computational resource nodes.
In addition, disk can specifically: SATA HDD, SATA SSD, SAS HDD or SAS SSD, wherein, SATA HDD refers to the HDD of SATA interface, SATA SSD refers to the SSD of SATA interface, and SAS HDD refers to the HDD of SAS interface, and SASSSD refers to the SSD of SAS interface.
In the present embodiment, can according to capacity, bandwidth, per second number of times (the Input/output Per Second that carry out read-write operation of different application for storage resources, IOPS) different demands, dispose dissimilar JBOD in rack (Rack) aspect, and determine according to bandwidth demand the topological structure that SAS connects.
Concrete, utilize T10zoning technology can set up the logical access relation of the upper each disk resource of node Host and JBOD, be namely equivalent to the logical server constructing different configuration.
As shown in Figure 3, it is two for computational resource node, two computational resource nodes 31 represent with node A and Node B respectively, JBOD 32 comprises: series connection enhancing technology connects (Serial Advanced Technology Attachment, SATA) hard disk drive (Hard Disk Drive, HDD) JBOD, SATA SSD JBOD and SAS HDD JBOD, often kind of JBOD can comprise multiple disk, can in SAS switch 33 static configuration, node A accesses three disks, 1xSATA HDD and 2xSATA SSD respectively, and, Node B accesses four disks, 1xSATA SSD and 3xSASHDD respectively.
The present embodiment, can be that granularity is to set up the mapping relations of storage resources and computational resource with single disc, the logical server that therefore can build arbitrary disposition in theory to meet various different application demand, as hot storage, warm storage and cold storage.
In another embodiment, server can also comprise:
Colony dispatching center, is connected with described computational resource node and described SAS switch, for receiving the resource allocation request that described computational resource node sends, and sends resource distribution instruction according to described resource allocation request to described SAS switch;
Described SAS switch is used for the mapping relations upgrading described computational resource and storage resources according to described resource distribution instruction.
Such as, the computational resource node changing mapping relations sends resource allocation request to colony dispatching center, the information of computational resource node and the disk mark after upgrading is comprised in this resource allocation request, colony dispatching center sends resource distribution instruction to SAS switch, the information of computational resource node and the disk mark after upgrading is comprised in resource distribution instruction, after SAS switch receives resource distribution instruction, the information of computational resource node and the disk mark after upgrading is obtained from resource distribution instruction, and the mapping relations of computational resource and storage resources are upgraded, make the information of this computational resource node to the disk mark after should upgrading.
See Fig. 4, suppose that computational resource node 41 is two, and be expressed as: node A and Node B, JBOD 42 comprises: SATA HDD JBOD, SATA SSD JBOD and SAS HDD JBOD, often kind of JBOD can comprise multiple disk, time initial, can in SAS switch 43 computational resource of static configuration acquiescence and the mapping relations of storage resources.
Such as, time initial, the corresponding 1xSATA HDD and 2xSATA SSD of node A, through upgrading, mapping relations can be updated to: the corresponding 1xSATA HDD and 3xSATA SSD of node A.
Above-mentioned to revise mapping relations, or, also can be release portion or whole disk resources during renewal, such as, after node A does not need certain disk resource, disk resource corresponding for node A can be discharged.Concrete, node A can send resource allocation request to colony dispatching center, this resource allocation request also can be specifically releasing request, send to SAS switch after colony dispatching receive centre to releasing request and release order, the information of node A is comprised in releasing order, the mark of the disk that will discharge can also be comprised, the information that obtain node A the releasing request that colony dispatching center specifically can send from node A and the mark of disk that will discharge, after SAS switch receives and releases order, from the information of the middle acquisition node A that releases order and the mark of disk that will discharge, and storage resources corresponding for node A is updated to the mark not comprising the disk that will discharge.Concrete releasing request and the composition form released order can pre-define, and corresponding each equipment can be known and currently whether receive releasing request or release order.
In the present embodiment, can the mapping relations of dynamic-configuration computational resource and storage resources, thus realize resource pool, disk resource of can distributing according to need.
In traditional scheme, SAS disk supports that in agreement multinode is shared, and jumbo SATA disk is then given tacit consent to and do not supported that multinode is shared, and usually adopts NLSAS disk to replace SATA disk in enterprise-level storage scheme.But the single Gb cost requirement of Internet user to mass-memory unit is higher, therefore use SATA disk in a large number.In another embodiment of the present invention, can support that the multiple spot of SATA disk is shared.
In another embodiment, described storage resources node comprises at least one disk, described disk comprises: SATA HDD, SATASSD, SAS HDD or SAS SSD, described SAS switch is used for when a distribution disk, is configured by the disk of described distribution to one or more computational resource node, storage resources node belonging to the disk of described distribution comprises: extender, and described extender logically comprises:
SAS physical layer entity, is connected with described SAS switch, for receiving SAS message.
Concrete, when the disk of described distribution is SATA HDD or SATA SSD, described extender logically also comprises:
STP bridge, is connected with the disk of described SAS physical layer entity and described distribution respectively, for being realized the communication of the computational resource node of described correspondence and the disk of described distribution by described SAS physical layer entity.
Concrete, see Fig. 5, suppose that computational resource node 51 is two, represent respectively with node A and Node B, disk is the disk of SATA interface, such as, SATA HDD or SATA SSD, in the present embodiment, comprises SATA HDD JBOD for storage resources node 52, when static state or dynamic-configuration, node A and Node B are configured to share the part or all of disk on this SATA HDD JBOD by SAS switch 53.
Wherein, see Fig. 6, JBOD extender (Expander) 521 and SATA HDD522 can be comprised in SATA HDD JBOD, the number of SATA HDD 522 is one or more, the present embodiment is for three, JBOD extender (Expander) 521 logically comprises: SAS physical layer entity (PHY) 5211 and SATA channel protocol (SATA Tunnelling Protocol, STP) bridge (Bridge) 5212.
The number of SAS physical layer entity 5211 is identical or different from the number of the computational resource node sharing same SATA disk, as shown in Figure 6, is two for SAS physical layer entity.
Logically UNICOM and certain SATA HDD are connected STP bridge 5212 physically with described SAS physical layer entity 5211 respectively.
Concrete, first same SATA disk is distributed to simultaneously the node of more than 2, then multi affiliation function is achieved at the STP bridge end of JBOD expander, it intercepts and captures the STP BPDUs being derived from multiple main frame, and the behavior of simulation SATA Host port ensures to access the consistance of SATA disk.
In the present embodiment, sharing many computing nodes of SATA disk can be realized by bridge.
The queue depth of the native command queue NCQ (Native Command Queuing) of SATA disk represents the command sequence number that SATA disk can process simultaneously, this value is generally 32, when multinode shares same SATA disk, the pending order number sum that each node sends simultaneously should be less than 32, otherwise there will be queue overflow at SATA disk end and cause loss of data.For individual node, queue depth (queue_depth) represents can simultaneously to the order number that disk sends.
In another embodiment, when multinode shares same SATA physical disk, different queue depths can be set, to provide different QoS service.The queue depth of each node, can pre-set according to certain rule static state, also can according to certain tactful dynamic-configuration with the parallel processing capability of maximum using disk.
Concrete, when the disk of described distribution is configured to multiple computational resource node, described multiple computational resource node comprises: host node and at least one is from node, described SAS switch is also for configuring queue depth corresponding to each computational resource node, and the queue depth that described host node is corresponding is greater than queue depth corresponding from node arbitrarily.
See Fig. 7, in practical application, for some disks, the computational resource node type of this disk of access can be divided into host node (primary initiator) 71 and represent from node (Secondary initiator) 72, wherein primaryinitiator only has one, and Secondary initiator can have a lot of.System preferentially should ensure the access performance of primaryinitiator to this disk, then can provide the service of doing one's best for Secondary initiator.
In the present embodiment, by for host node with from the different queue depth of Joint Enterprise, the storage resources access of different service quality can be realized.
In another embodiment, when break down in described computational resource node node time, described colony dispatching center also for: send owner's configuration-direct to described SAS switch, in described owner's configuration-direct, comprise the information of the computational resource node after switching;
The disk corresponding with described malfunctioning node also for according to described owner's configuration-direct, is remapped on the computational resource node after switching by described SAS switch.
Such as, each disk only has a primary initiator under normal circumstances, and when this initiator breaks down, data will temporarily cannot be accessed.For one-of-a-kind system, until node restart reparation normally reach the standard grade after data could again access; For distributed file system, then need the replication carrying out data, this needs to redistribute storage space in the cluster and causes unnecessary network traffics and CPU pressure.
In the present embodiment, see Fig. 8, server comprises computational resource node 81, the present embodiment is two for computational resource node, represent with node A and Node B respectively, the server of the present embodiment also comprises storage resources node 82, and storage resources node is for SATA HDDJBOD, and this server also comprises SAS switch 83 and colony dispatching center 84.When primaryinitiator node breaks down as node A, by " colony dispatching " center " reconfigures; node A is remapped to the B node in this network as the disk of primary initiator node, fast quick-recovery data can ensures its availability.
Such as, time initial, corresponding disk _ 1 of node A, after remapping, can remap disk _ 1 to Node B.Concrete, colony dispatching center can send owner's configuration-direct to SAS switch, comprise the identification information of disk _ 1 and the information of Node B in owner's configuration-direct, computational resource is updated to corresponding disk _ 1 of Node B with the mapping relations of storage resources from corresponding disk _ 1 of node A by SAS switch.
In the present embodiment, upgrade mapping relations by colony dispatching center instruction SAS switch, after computational resource node failure, storage resources corresponding for the computational resource node of fault can be switched on the computational resource node of non-fault, to ensure availability of data.
In another embodiment, described computational resource node comprises the first computing node and the second computing node, when needing data corresponding for described second computing node to be saved on disk corresponding to the first computing node, described second computing node is used for the disk mark obtaining data to be written from described first node, and send to described colony dispatching center and remap request, described in remap in request and comprise described disk mark;
Described colony dispatching center also sends mapping configuration-direct for remapping request described in basis to described SAS switch, comprises described disk mark in described mapping configuration-direct;
Disk corresponding for described disk mark also for according to described mapping configuration-direct, is also mapped on described second computing node by described SAS switch.
Such as, see Fig. 9, when two nodes being in a SAS network together need copies data, in prior art, a usual node sends the data to another one node by front network path, and data are saved on local disk by another node again.
And in the present embodiment, when supposing that Secondary initiator needs data to be passed to Primary initiator, can directly be write data on the disk of (own) belonging to Primary initiator by rear end store path.The disk that Secondary initiator and Primary initiator obtains data to be written through " synchro control " identifies, rear to colony dispatching center send " remapping request ", colony dispatching center sends " mapping configuration " to SAS Switch and corresponding disk is not only mapped to Primary initiator, also be mapped to Secondary initiator, thus realize Secondary initiator and data are write on disk corresponding to Primary initiator.
In addition, after data are transmitted, Secondary initiator can ask to discharge corresponding storage resources, such as, Secondary initiator writes data to disk _ 1 belonging to Primary initiator, after data write, Secondary initiator can pass through the resource of colony dispatching center and SAS switch release disk _ 1, and the mode of concrete releasing resource can see the associated description in above-described embodiment.
In the present embodiment, transmit data by rear end, can avoid carrying out by front network front network pressure that data interaction brings, CPU takies and larger time delay, distributed file system such as the multicopy of data under Hadoop environment can be applied to and copy.
In the such scheme of the application, provide a kind of computational resource and the uncoupled server of storage resources, computational resource and various storage resources are gathered together by its multistage network topology consisted of SASSwitch, can realize the Quick Extended of computational resource and storage resources; Can be that granularity sets up mapping relations therebetween to build the logical server of various difference configuration with single-deck, reduce server Configuration Type; Inner in global resource pond, can resource utilization be promoted by dynamic-configuration distribution according to need release storage resources; Multinode can be realized access same physical disk according to certain QoS and realize the fast quick-recovery of data based on this mechanism and optimize specific environment as the data backup speed of Rack inside under Hadoop.The present embodiment cost is low, bandwidth is high, time delay is low, very easily expansion and to be easy to existing distributed file system integrated.
It should be noted that, in describing the invention, term " first ", " second " etc. only for describing object, and can not be interpreted as instruction or hint relative importance.In addition, in describing the invention, except as otherwise noted, the implication of " multiple " is two or more.
Describe and can be understood in process flow diagram or in this any process otherwise described or method, represent and comprise one or more for realizing the module of the code of the executable instruction of the step of specific logical function or process, fragment or part, and the scope of the preferred embodiment of the present invention comprises other realization, wherein can not according to order that is shown or that discuss, comprise according to involved function by the mode while of basic or by contrary order, carry out n-back test, this should understand by embodiments of the invention person of ordinary skill in the field.
Should be appreciated that each several part of the present invention can realize with hardware, software, firmware or their combination.In the above-described embodiment, multiple step or method can with to store in memory and the software performed by suitable instruction execution system or firmware realize.Such as, if realized with hardware, the same in another embodiment, can realize by any one in following technology well known in the art or their combination: the discrete logic with the logic gates for realizing logic function to data-signal, there is the special IC of suitable combinational logic gate circuit, programmable gate array (PGA), field programmable gate array (FPGA) etc.
Those skilled in the art are appreciated that realizing all or part of step that above-described embodiment method carries is that the hardware that can carry out instruction relevant by program completes, described program can be stored in a kind of computer-readable recording medium, this program perform time, step comprising embodiment of the method one or a combination set of.
In addition, each functional unit in each embodiment of the present invention can be integrated in a processing module, also can be that the independent physics of unit exists, also can be integrated in a module by two or more unit.Above-mentioned integrated module both can adopt the form of hardware to realize, and the form of software function module also can be adopted to realize.If described integrated module using the form of software function module realize and as independently production marketing or use time, also can be stored in a computer read/write memory medium.
The above-mentioned storage medium mentioned can be ROM (read-only memory), disk or CD etc.
In the description of this instructions, specific features, structure, material or feature that the description of reference term " embodiment ", " some embodiments ", " example ", " concrete example " or " some examples " etc. means to describe in conjunction with this embodiment or example are contained at least one embodiment of the present invention or example.In this manual, identical embodiment or example are not necessarily referred to the schematic representation of above-mentioned term.And the specific features of description, structure, material or feature can combine in an appropriate manner in any one or more embodiment or example.
Although illustrate and describe embodiments of the invention above, be understandable that, above-described embodiment is exemplary, can not be interpreted as limitation of the present invention, and those of ordinary skill in the art can change above-described embodiment within the scope of the invention, revises, replace and modification.
Claims (11)
1. a server, is characterized in that, comprising:
Computational resource node;
Storage resources node;
SAS switch;
Wherein, described computational resource node is connected with described SAS switch respectively with described storage resources node, and described computational resource node is physically be separated setting with described storage resources node.
2. server according to claim 1, is characterized in that,
Described computational resource node comprises: CPU, and, HBA card or RAID card, described HBA card or RAID card connect described SAS switch by SAS cable; Or,
Described storage resources node is JBOD, and described JBOD connects described SAS switch by SAS cable.
3. server according to claim 2, it is characterized in that, described computational resource node is at least one, and described storage resources node is at least one, and each computational resource node or each storage resources node are connected with described SAS switch by least one SAS cable.
4. server according to claim 2, is characterized in that, described JBOD has one-level or multi-stage cascade structure.
5. the server according to any one of claim 1-4, is characterized in that, described SAS switch is used for:
With the single disc on described storage resources node for granularity, set up the mapping relations of computational resource and storage resources.
6. server according to claim 5, is characterized in that, also comprises:
Colony dispatching center, is connected with described computational resource node and described SAS switch, for receiving the resource allocation request that described computational resource node sends, and sends resource distribution instruction according to described resource allocation request to described SAS switch;
Described SAS switch is used for the mapping relations upgrading described computational resource and storage resources according to described resource distribution instruction.
7. the server according to any one of claim 1-4, it is characterized in that, described storage resources node comprises at least one disk, described disk comprises: SATA HDD, SATA SSD, SAS HDD or SAS SSD, described SAS switch is used for when a distribution disk, configured by the disk of described distribution to one or more computational resource node, the storage resources node belonging to the disk of described distribution comprises: extender, and described extender logically comprises:
SAS physical layer entity, is connected with described SAS switch, for receiving SAS message.
8. server according to claim 7, is characterized in that, when the disk of described distribution is SATA HDD or SATA SSD, described extender logically also comprises:
STP bridge, is connected with the disk of described SAS physical layer entity and described distribution respectively, for being realized the communication of the computational resource node of described correspondence and the disk of described distribution by described SAS physical layer entity.
9. server according to claim 7, it is characterized in that, when the disk of described distribution is configured to multiple computational resource node, described multiple computational resource node comprises: host node and at least one is from node, described SAS switch is also for configuring queue depth corresponding to each computational resource node, and the queue depth that described host node is corresponding is greater than queue depth corresponding from node arbitrarily.
10. server according to claim 6, it is characterized in that, when break down in described computational resource node node time, described colony dispatching center also for: send owner's configuration-direct to described SAS switch, in described owner's configuration-direct, comprise the information of the computational resource node after switching;
The disk corresponding with described malfunctioning node also for according to described owner's configuration-direct, is remapped on the computational resource node after switching by described SAS switch.
11. servers according to claim 6, it is characterized in that, described computational resource node comprises the first computing node and the second computing node, when needing data corresponding for described second computing node to be saved on disk corresponding to the first computing node, described second computing node is used for the disk mark obtaining data to be written from described first node, and send to described colony dispatching center and remap request, described in remap in request and comprise described disk mark;
Described colony dispatching center also sends mapping configuration-direct for remapping request described in basis to described SAS switch, comprises described disk mark in described mapping configuration-direct;
Disk corresponding for described disk mark also for according to described mapping configuration-direct, is also mapped on described second computing node by described SAS switch.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510101293.7A CN104657316B (en) | 2015-03-06 | 2015-03-06 | Server |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510101293.7A CN104657316B (en) | 2015-03-06 | 2015-03-06 | Server |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104657316A true CN104657316A (en) | 2015-05-27 |
| CN104657316B CN104657316B (en) | 2018-01-19 |
Family
ID=53248468
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510101293.7A Active CN104657316B (en) | 2015-03-06 | 2015-03-06 | Server |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104657316B (en) |
Cited By (36)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104932837A (en) * | 2015-06-05 | 2015-09-23 | 浪潮电子信息产业股份有限公司 | Storage pool framework |
| CN104967577A (en) * | 2015-06-25 | 2015-10-07 | 北京百度网讯科技有限公司 | SAS switch and server |
| CN105045336A (en) * | 2015-06-25 | 2015-11-11 | 北京百度网讯科技有限公司 | JBOD (Just Bunch of Disks) |
| CN105068836A (en) * | 2015-08-06 | 2015-11-18 | 北京百度网讯科技有限公司 | SAS (serial attached SCSI) network based remotely-shareable start-up system |
| CN105159617A (en) * | 2015-09-24 | 2015-12-16 | 浪潮(北京)电子信息产业有限公司 | Pooled storage system framework |
| CN105472047A (en) * | 2016-02-03 | 2016-04-06 | 天津书生云科技有限公司 | Storage system |
| CN105657066A (en) * | 2016-03-23 | 2016-06-08 | 天津书生云科技有限公司 | Load rebalance method and device used for storage system |
| CN105786414A (en) * | 2016-03-24 | 2016-07-20 | 天津书生云科技有限公司 | Memory system as well as access method and access device thereof |
| CN105843557A (en) * | 2016-03-24 | 2016-08-10 | 天津书生云科技有限公司 | Redundant storage system, redundant storage method and redundant storage device |
| CN105872031A (en) * | 2016-03-26 | 2016-08-17 | 天津书生云科技有限公司 | Storage system |
| CN105867842A (en) * | 2016-03-23 | 2016-08-17 | 天津书生云科技有限公司 | Access control method and apparatus for storage system |
| CN105897859A (en) * | 2016-03-25 | 2016-08-24 | 天津书生云科技有限公司 | Storage system |
| CN106325779A (en) * | 2016-08-31 | 2017-01-11 | 浪潮电子信息产业股份有限公司 | Design scheme of SAS Switch/JBOD topology |
| CN106445791A (en) * | 2016-10-25 | 2017-02-22 | 广东浪潮大数据研究有限公司 | Method for grabbing SAS Switch register data on SAS Switch whole cabinet |
| WO2017054697A1 (en) * | 2015-09-28 | 2017-04-06 | 天津书生云科技有限公司 | Method and device for implementing access of hba card to sata disk in sas storage system |
| CN106598908A (en) * | 2015-10-19 | 2017-04-26 | 阿里巴巴集团控股有限公司 | Computing device and management method and system of storage component thereof |
| CN106603445A (en) * | 2016-12-09 | 2017-04-26 | 东南大学 | Data exchange method in multiple stages of network systems and multiple stages of network systems |
| CN106708745A (en) * | 2016-12-05 | 2017-05-24 | 郑州云海信息技术有限公司 | 24-tub NVME dynamic allocation structure and method |
| CN106850804A (en) * | 2017-02-07 | 2017-06-13 | 郑州云海信息技术有限公司 | A kind of method that mass storage system (MSS) reduces network connection quantity |
| CN106873914A (en) * | 2017-02-21 | 2017-06-20 | 郑州云海信息技术有限公司 | A kind of design of JBOD cascades |
| CN107346210A (en) * | 2016-05-06 | 2017-11-14 | 阿里巴巴集团控股有限公司 | Hard disc data method for deleting, server and system |
| CN107506143A (en) * | 2017-08-25 | 2017-12-22 | 郑州云海信息技术有限公司 | A kind of SAS Switch design methods of redundancy |
| CN108153684A (en) * | 2017-12-30 | 2018-06-12 | 广东技术师范学院 | A kind of disk Cache's prefetches space allocation method |
| CN108227901A (en) * | 2017-12-30 | 2018-06-29 | 广东技术师范学院 | It is a kind of based on the disk power consumption state switching method sporadicly asked |
| CN108268343A (en) * | 2016-12-31 | 2018-07-10 | 中国移动通信集团四川有限公司 | The devices, systems, and methods of data backup |
| CN108762673A (en) * | 2018-05-24 | 2018-11-06 | 浪潮电子信息产业股份有限公司 | A kind of remote data access processing system |
| CN109450681A (en) * | 2018-11-06 | 2019-03-08 | 英业达科技有限公司 | Cabinet-type server system and server |
| WO2019100701A1 (en) * | 2017-11-23 | 2019-05-31 | 郑州云海信息技术有限公司 | Sas switch controller extension architecture and design method thereof |
| CN109960614A (en) * | 2019-03-27 | 2019-07-02 | 英业达科技有限公司 | Server system and management method |
| WO2019223444A1 (en) * | 2018-05-22 | 2019-11-28 | 杭州海康威视数字技术股份有限公司 | Data storage system |
| CN110557354A (en) * | 2018-05-31 | 2019-12-10 | 杭州海康威视数字技术股份有限公司 | Method and device for realizing communication between nodes and electronic equipment |
| CN110703870A (en) * | 2019-09-12 | 2020-01-17 | 苏州浪潮智能科技有限公司 | JBOD mainboard and storage system |
| CN112579384A (en) * | 2019-09-27 | 2021-03-30 | 杭州海康威视数字技术股份有限公司 | Method, device and system for monitoring nodes of SAS domain and nodes |
| CN113190167A (en) * | 2020-01-14 | 2021-07-30 | 伊姆西Ip控股有限责任公司 | Method for managing computing device, electronic device and computer storage medium |
| CN113918092A (en) * | 2021-09-18 | 2022-01-11 | 中国长城科技集团股份有限公司 | Method and system for allocating storage space |
| CN116661688A (en) * | 2023-05-23 | 2023-08-29 | 无锡众星微系统技术有限公司 | Service response method and device of SAS storage system |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101055511A (en) * | 2007-05-16 | 2007-10-17 | 华为技术有限公司 | Memory array system and its data operation method |
| US20080195581A1 (en) * | 2007-02-08 | 2008-08-14 | Dot Hill Systems Corp. | Method and apparatus for identifying enclosures and devices |
| CN101841526A (en) * | 2010-03-04 | 2010-09-22 | 清华大学 | Cluster streaming media server system applied to large-scale user demand |
| CN101923444A (en) * | 2009-06-09 | 2010-12-22 | Lsi公司 | N-way directly connected any to any controller architecture |
| CN103095796A (en) * | 2011-11-04 | 2013-05-08 | Lsi公司 | Server direct attached storage shared through virtual sas expanders |
| CN203982354U (en) * | 2014-06-19 | 2014-12-03 | 天津书生投资有限公司 | A kind of redundant storage system |
| CN104216805A (en) * | 2014-08-26 | 2014-12-17 | 浪潮(北京)电子信息产业有限公司 | System and method for link failure protection of disk cabinet at rear end of high-end disk array |
-
2015
- 2015-03-06 CN CN201510101293.7A patent/CN104657316B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080195581A1 (en) * | 2007-02-08 | 2008-08-14 | Dot Hill Systems Corp. | Method and apparatus for identifying enclosures and devices |
| CN101055511A (en) * | 2007-05-16 | 2007-10-17 | 华为技术有限公司 | Memory array system and its data operation method |
| CN101923444A (en) * | 2009-06-09 | 2010-12-22 | Lsi公司 | N-way directly connected any to any controller architecture |
| CN101841526A (en) * | 2010-03-04 | 2010-09-22 | 清华大学 | Cluster streaming media server system applied to large-scale user demand |
| CN103095796A (en) * | 2011-11-04 | 2013-05-08 | Lsi公司 | Server direct attached storage shared through virtual sas expanders |
| CN203982354U (en) * | 2014-06-19 | 2014-12-03 | 天津书生投资有限公司 | A kind of redundant storage system |
| CN104216805A (en) * | 2014-08-26 | 2014-12-17 | 浪潮(北京)电子信息产业有限公司 | System and method for link failure protection of disk cabinet at rear end of high-end disk array |
Cited By (51)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104932837A (en) * | 2015-06-05 | 2015-09-23 | 浪潮电子信息产业股份有限公司 | Storage pool framework |
| CN104932837B (en) * | 2015-06-05 | 2018-09-04 | 浪潮电子信息产业股份有限公司 | Storage pool framework |
| CN104967577B (en) * | 2015-06-25 | 2019-09-03 | 北京百度网讯科技有限公司 | SAS switch and server |
| CN105045336A (en) * | 2015-06-25 | 2015-11-11 | 北京百度网讯科技有限公司 | JBOD (Just Bunch of Disks) |
| CN104967577A (en) * | 2015-06-25 | 2015-10-07 | 北京百度网讯科技有限公司 | SAS switch and server |
| CN105068836A (en) * | 2015-08-06 | 2015-11-18 | 北京百度网讯科技有限公司 | SAS (serial attached SCSI) network based remotely-shareable start-up system |
| CN105159617B (en) * | 2015-09-24 | 2018-09-07 | 浪潮(北京)电子信息产业有限公司 | A kind of pond storage system framework |
| CN105159617A (en) * | 2015-09-24 | 2015-12-16 | 浪潮(北京)电子信息产业有限公司 | Pooled storage system framework |
| WO2017054697A1 (en) * | 2015-09-28 | 2017-04-06 | 天津书生云科技有限公司 | Method and device for implementing access of hba card to sata disk in sas storage system |
| CN106598908A (en) * | 2015-10-19 | 2017-04-26 | 阿里巴巴集团控股有限公司 | Computing device and management method and system of storage component thereof |
| WO2017067402A1 (en) * | 2015-10-19 | 2017-04-27 | 阿里巴巴集团控股有限公司 | Computing device and computing device memory component management method and system |
| CN106598908B (en) * | 2015-10-19 | 2020-09-08 | 阿里巴巴集团控股有限公司 | Computing device and management method and system of storage component of computing device |
| CN105472047B (en) * | 2016-02-03 | 2019-05-14 | 天津书生云科技有限公司 | Storage system |
| CN105472047A (en) * | 2016-02-03 | 2016-04-06 | 天津书生云科技有限公司 | Storage system |
| CN105867842A (en) * | 2016-03-23 | 2016-08-17 | 天津书生云科技有限公司 | Access control method and apparatus for storage system |
| CN105657066B (en) * | 2016-03-23 | 2019-06-14 | 天津书生云科技有限公司 | Load for storage system equalization methods and device again |
| CN105657066A (en) * | 2016-03-23 | 2016-06-08 | 天津书生云科技有限公司 | Load rebalance method and device used for storage system |
| WO2017162177A1 (en) * | 2016-03-24 | 2017-09-28 | 北京书生国际信息技术有限公司 | Redundant storage system, redundant storage method and redundant storage device |
| WO2017162176A1 (en) * | 2016-03-24 | 2017-09-28 | 北京书生国际信息技术有限公司 | Storage system, access method for storage system, and access device for storage system |
| CN105843557A (en) * | 2016-03-24 | 2016-08-10 | 天津书生云科技有限公司 | Redundant storage system, redundant storage method and redundant storage device |
| CN105843557B (en) * | 2016-03-24 | 2019-03-08 | 天津书生云科技有限公司 | Redundant storage system, redundant storage method and redundant storage device |
| CN105786414A (en) * | 2016-03-24 | 2016-07-20 | 天津书生云科技有限公司 | Memory system as well as access method and access device thereof |
| CN105897859A (en) * | 2016-03-25 | 2016-08-24 | 天津书生云科技有限公司 | Storage system |
| CN105872031A (en) * | 2016-03-26 | 2016-08-17 | 天津书生云科技有限公司 | Storage system |
| CN105872031B (en) * | 2016-03-26 | 2019-06-14 | 天津书生云科技有限公司 | Storage system |
| CN107346210B (en) * | 2016-05-06 | 2020-08-14 | 阿里巴巴集团控股有限公司 | Hard disk data erasing method, server and system |
| CN107346210A (en) * | 2016-05-06 | 2017-11-14 | 阿里巴巴集团控股有限公司 | Hard disc data method for deleting, server and system |
| CN106325779A (en) * | 2016-08-31 | 2017-01-11 | 浪潮电子信息产业股份有限公司 | Design scheme of SAS Switch/JBOD topology |
| CN106445791A (en) * | 2016-10-25 | 2017-02-22 | 广东浪潮大数据研究有限公司 | Method for grabbing SAS Switch register data on SAS Switch whole cabinet |
| CN106708745A (en) * | 2016-12-05 | 2017-05-24 | 郑州云海信息技术有限公司 | 24-tub NVME dynamic allocation structure and method |
| CN106603445A (en) * | 2016-12-09 | 2017-04-26 | 东南大学 | Data exchange method in multiple stages of network systems and multiple stages of network systems |
| CN108268343B (en) * | 2016-12-31 | 2020-12-08 | 中国移动通信集团四川有限公司 | Data backup device, system and method |
| CN108268343A (en) * | 2016-12-31 | 2018-07-10 | 中国移动通信集团四川有限公司 | The devices, systems, and methods of data backup |
| CN106850804A (en) * | 2017-02-07 | 2017-06-13 | 郑州云海信息技术有限公司 | A kind of method that mass storage system (MSS) reduces network connection quantity |
| CN106873914A (en) * | 2017-02-21 | 2017-06-20 | 郑州云海信息技术有限公司 | A kind of design of JBOD cascades |
| CN107506143A (en) * | 2017-08-25 | 2017-12-22 | 郑州云海信息技术有限公司 | A kind of SAS Switch design methods of redundancy |
| WO2019100701A1 (en) * | 2017-11-23 | 2019-05-31 | 郑州云海信息技术有限公司 | Sas switch controller extension architecture and design method thereof |
| CN108153684A (en) * | 2017-12-30 | 2018-06-12 | 广东技术师范学院 | A kind of disk Cache's prefetches space allocation method |
| CN108227901A (en) * | 2017-12-30 | 2018-06-29 | 广东技术师范学院 | It is a kind of based on the disk power consumption state switching method sporadicly asked |
| WO2019223444A1 (en) * | 2018-05-22 | 2019-11-28 | 杭州海康威视数字技术股份有限公司 | Data storage system |
| CN108762673A (en) * | 2018-05-24 | 2018-11-06 | 浪潮电子信息产业股份有限公司 | A kind of remote data access processing system |
| CN110557354B (en) * | 2018-05-31 | 2020-10-13 | 杭州海康威视数字技术股份有限公司 | Method and device for realizing communication between nodes and electronic equipment |
| CN110557354A (en) * | 2018-05-31 | 2019-12-10 | 杭州海康威视数字技术股份有限公司 | Method and device for realizing communication between nodes and electronic equipment |
| CN109450681A (en) * | 2018-11-06 | 2019-03-08 | 英业达科技有限公司 | Cabinet-type server system and server |
| CN109960614A (en) * | 2019-03-27 | 2019-07-02 | 英业达科技有限公司 | Server system and management method |
| CN110703870A (en) * | 2019-09-12 | 2020-01-17 | 苏州浪潮智能科技有限公司 | JBOD mainboard and storage system |
| CN112579384A (en) * | 2019-09-27 | 2021-03-30 | 杭州海康威视数字技术股份有限公司 | Method, device and system for monitoring nodes of SAS domain and nodes |
| CN113190167A (en) * | 2020-01-14 | 2021-07-30 | 伊姆西Ip控股有限责任公司 | Method for managing computing device, electronic device and computer storage medium |
| CN113918092A (en) * | 2021-09-18 | 2022-01-11 | 中国长城科技集团股份有限公司 | Method and system for allocating storage space |
| CN116661688A (en) * | 2023-05-23 | 2023-08-29 | 无锡众星微系统技术有限公司 | Service response method and device of SAS storage system |
| CN116661688B (en) * | 2023-05-23 | 2023-12-12 | 无锡众星微系统技术有限公司 | Service response method and device of SAS storage system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104657316B (en) | 2018-01-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104657316A (en) | Server | |
| CN110312999B (en) | Dynamic partitioning of PCIe disk arrays based on software configuration/policy distribution | |
| JP6957431B2 (en) | VM / container and volume allocation determination method and storage system in HCI environment | |
| US11392307B2 (en) | Data-protection-aware capacity provisioning of shared external volume | |
| US8898385B2 (en) | Methods and structure for load balancing of background tasks between storage controllers in a clustered storage environment | |
| CN104965677B (en) | Storage system | |
| US10282136B1 (en) | Storage system and control method thereof | |
| US9542320B2 (en) | Multi-node cache coherency with input output virtualization | |
| US20080005470A1 (en) | System and method for sharing sata drives in active-active raid controller system | |
| WO2016101287A1 (en) | Method for distributing data in storage system, distribution apparatus and storage system | |
| JP2002334049A (en) | Storage subsystem and control method for storage subsystem | |
| US9253257B2 (en) | Storage subsystem | |
| JP2010271808A (en) | Storage device and data copying method | |
| CN105472047A (en) | Storage system | |
| CN104967577B (en) | SAS switch and server | |
| WO2017167106A1 (en) | Storage system | |
| JP5996098B2 (en) | Computer, computer system, and I / O request processing method for realizing high-speed access and data protection of storage device | |
| CN105045336A (en) | JBOD (Just Bunch of Disks) | |
| US9898205B1 (en) | Scheduling of commands in a storage area network to minimize latency | |
| CN104994135A (en) | Method and device for fusing SAN and NAS storage frameworks in storage system | |
| WO2021012169A1 (en) | Method of improving reliability of storage system, and related apparatus | |
| US10732872B2 (en) | Storage system and storage control method | |
| US10514846B2 (en) | Computer system and management method for computer | |
| US11768744B2 (en) | Alerting and managing data storage system port overload due to host path failures | |
| US8904108B2 (en) | Methods and structure establishing nested Redundant Array of Independent Disks volumes with an expander |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |