CN106325761A - Storage resource management system and method - Google Patents
Storage resource management system and method Download PDFInfo
- Publication number
- CN106325761A CN106325761A CN201510369563.2A CN201510369563A CN106325761A CN 106325761 A CN106325761 A CN 106325761A CN 201510369563 A CN201510369563 A CN 201510369563A CN 106325761 A CN106325761 A CN 106325761A
- Authority
- CN
- China
- Prior art keywords
- hard disk
- rmc
- information
- bmc
- sas
- 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
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Debugging And Monitoring (AREA)
- Small-Scale Networks (AREA)
Abstract
The invention provides a storage resource management system and method. The storage resource management system includes: a rack management controller (RMC) which is used for managing storage resources according to one or more of received self-monitoring analysis and reporting technology SMART information, serial attached small computer system interface SAS topological information, and hard disk information; a server node board connected to the RMC, wherein the server node board is used for acquiring the SMART information and reporting the SMART information to the RMC; an exchange node board connected to the RMC, wherein the exchange node board is used for acquiring the SAS topological information and reporting the SAS topological information to the RMC; a storage node board connected to the RMC, wherein the storage node board is used for acquiring the hard disk information and reporting the hard disk information to the RMC, the storage node board includes a first board management controller connected to the storage node board in the RMC, a just bundle of disk JBOD connected to the RMC, and the first BMC is used for managing hard disk information acquired from the JBOD.
Description
Technical field
The present invention relates to memory technology, particularly relate to the system and method for a kind of SRM.
Background technology
Storage capacity requirement is increased by geometric progression by data center, and conventional blades server uses this locality to deposit
Storage can not meet the market demand, and be born Cabinet-type server for this, server only retains and deposits on a small quantity
Version and daily record are put in storage, and resource is independent to be managed collectively as a resource pool storing, all
Server can share memory resource pool.
SAS (Serial Attached SCSI, Serial Attached SCSI (SAS), wherein SCSI (Small Computer
System Interface, small computer system interface)) it is that in storage network, most popular one is hard
Dish interconnection technique, with serial communication for protocol basis framework, uses SCSI-3 expansion instruction set, combines
Existing parallel SCSI and the advantage of technology connected in series, and can compatible SATA device.SAS possesses currently
Highest interface speed inside hard disk access technology, it is special that the speed of SAS3.0 standard reaches 12Gb/s, SAS
Some wide port technology so that transmission bandwidth obtains lifting at double, as a example by 12Gbps SAS passage,
4*SAS wide port bandwidth is up to 48Gbps.
When multiple SAS device need intercommunication, it is necessary to connected by SAS expander expander.
SAS expander has multiple SAS port, built-in MIPS (Million Instructions Per Second,
Single-length fixed point instruction averagely performs speed) processor, it is divided into SAS switch exchange and JBOD according to function
(Just Bundle of Disk, simple hard disk bunch), wherein JBOD simply does hard disk extension, several
Hard disk connects together and forms a big logic hard disk.SAS Switch connects several JBOD and forms one
Individual SAS switching domain, just can manage whole SAS switching domain by SAS Switch.
Fig. 1 is a typical rack server system, and the built-in JBOD of rack, several server service
Device connects JBOD by SAS switch.
Rack server system has the following characteristics that 1, transmits isolation: isolate server and storage resource,
Prevent unauthorized access.2, control is accessed: limit the storage resource that each server can access, such as Fig. 1
In, each server can only access the part hard disk of JBOD;3, resource distribution flexibly: if certain
Server needs more resource, can distribute new hard disk.To this end, ANSI (American National Standards Institute (ANSI))
T10 technical committee proposes SAS zoning regional development and technology, is similar to the VLAN (Virtual of Ethernet
Local Area Network, VLAN) technology, the SAS of SAS switch and JBOD composition hands over
Change territory and be divided into different ZONE (subregion), the most invisible between different ZONE.In Fig. 1, server1
It is the hard disk that ZONE1, server1 can only access in ZONE1 with several hard disk partition, the need to
More hard disk, it is only necessary to new hard disk is joined ZONE1.SAS zoning particular by
ZPT table (Zoning Permission Table, zoning permissions table) in SAS expander controls not
Whether can communicate with between ZONE.
Rack server system exists two communication layers, is datum plane and management plane respectively.Data
Plane uses in-band channel (SAS) interconnection, and current networking generally uses multipath Redundancy Design, network
In at least two switching nodes, have two SAS expander to connect two ports of hard disks in JBOD,
Each switching node is cross interconnected with server and JBOD, and server upper operation main frame multi-path software comes real
The link redundancy of existing a plurality of I/O path and load balancing.Management plane is generally divided into in-band management and band outer tube
Reason, in-band management uses HBA (Host Bus Adapter, host bus adaptor) management SAS expander,
Being managed by SES (SCSI Enclosure Services) protocol realization casing, outband management passage has eth
(Ethernet), UART (Universal Asynchronous Receiver/Transmitter, universal asynchronous receipts
Send out transmitter or asynchronous receiving-transmitting transmitter) or I2C (Inter-Integrated Circuit, twin wire serial is total
Line) etc..Owing to the hardware cost of HBA is expensive, therefore switching node generally uses outband management.Fig. 1
It is shown that managing customer end 5 (PC) and connects one of them SAS switch by out-band channel, in management
Web GUI (Graphical User Interface, graphic user interface) is provided, by figure in client 5
The storage resource that shape interface management server uses.
Fig. 2 is a kind of management plane that existing rack server system is common, HBA24, JBOD42 all with
SAS Switch32 connects, BMC21,31,41 (Board Management Controller, substrate pipes
Reason controller) out-of-band supervision pipe, firmware management and sensor 23,33,43 management etc. are provided.Server saves
Point plate 2 on BMC21 be responsible for sensor 23 function, by with BIOS22 (Basic Input Output
System, basic input output system) carry out data exchange, obtain the system information of veneer, receive from
The system event of BIOS22, (Rack Management Controller, rack manages to report RMC1
Plate).BMC31 the sensor 33 of switching node plate 3 manages, and SAS Switch32 passes through out-band channel
Directly communicate with RMC1.The BMC41 of memory node plate 4 is only responsible for sensor 43 function, JBOD42
Only in-band channel connects switching node plate 3.
Summary of the invention
The purpose of the embodiment of the present invention is to provide the system and method for a kind of SRM, can be direct
Obtain JBOD and store resource, improve transmission efficiency.
To achieve these goals, the system of a kind of SRM that the embodiment of the present invention provides, including:
Rack management board RMC, for according to the self-monitoring analysis received and reporting techniques SMART
One in information, serial connecting small computer system interface SAS topology information and hard disk information or
Multiple, managing memory source;
The server node plate being connected with described RMC, is used for obtaining described SMART information, and reports
To described RMC;
The switching node plate being connected with described RMC, is used for obtaining described SAS topology information, and reports to
Described RMC;
The memory node plate being connected with described RMC, is used for obtaining described hard disk information, and reports to described
RMC, wherein said memory node plate includes: the first base being connected in the memory node plate of described RMC
Board management controller BMC, the simple hard disk bunch JBOD being connected on a described BMC, wherein said
Oneth BMC, the hard disk information obtained from described JBOD for management.
In the system of wherein said SRM,
Described server node plate includes: be connected to the second substrate in the server node plate of described RMC
Management Controller BMC, respectively outband management are connected to the host bus adaptor on described 2nd BMC
HBA, basic input-output system BIOS and temperature sensor, wherein, described 2nd BMC, uses
Temperature information in the described SMART information managing described HBA record.
In the system of wherein said SRM,
Described switching node plate includes: the 3rd substrate management being connected in the switching node plate of described RMC
Controller BMC, respectively outband management are connected to the Serial Attached Small Computer on described 3rd BMC
System interface exchange SAS Switch and temperature sensor, wherein, described 3rd BMC, it is used for managing
The SAS topology information obtained from described SAS Switch.
In the system of wherein said SRM,
Described SAS topology information includes that described HBA connects the port numbers Port ID of SAS Switch, institute
State the address of SAS.
In the system of wherein said SRM,
Described hard disk information includes the port information of hard disk, capacity, device type and interface type.
In the system of wherein said SRM,
Described RMC is additionally operable to obtaining the distribution request of the first hard disk, resolves described in described distribution request
The port of the first hard disk and capacity information;Port according to described first hard disk and described capacity information, by institute
The port stating the first hard disk joins, the partner's fdisk mated with described first hard-disk capacity, Qi Zhongsuo
Stating partner's fdisk is to pre-build the subregion of one-to-one relationship with server node plate subregion.
In the system of wherein said SRM,
Described RMC is additionally operable to after described first hard disk distributes, obtains a deletion distribution request, root
Delete distribution request according to described, described first hard disk is exited partner's fdisk.
In the system of wherein said SRM,
A described BMC is additionally operable to get the second hard disk and extracts event, and described second hard disk is extracted thing
Part reports described RMC, described RMC carry out the deletion of the second hard disk information.
In the system of wherein said SRM,
A described BMC is additionally operable to get the second hard disk and inserts event, is distributed to by described second hard disk
Preset default partition, and give described RMC by described insertion reporting events.
The embodiment of the present invention also provides in a kind of method of SRM, including:
Server node plate obtains self-monitoring analysis and reporting techniques SMART information, and reports to rack
Management board RMC;
Switching node plate obtains serial connecting small computer system interface SAS topology information, and reports to
Described RMC;
Memory node plate obtains hard disk information, and reports to described RMC, wherein said memory node plate bag
Include: the first substrate Management Controller BMC that is connected in the memory node plate of described RMC, be connected to
Simple hard disk bunch JBOD on a described BMC, a wherein said BMC, for management from described
The hard disk information that JBOD obtains;
Described RMC is according to the described SMART information received, described SAS topology information and described
One or more in hard disk information, managing memory source.
In the method for wherein said SRM,
Described server node plate includes: be connected to the second substrate in the server node plate of described RMC
Management Controller BMC, respectively outband management are connected to the host bus adaptor on described 2nd BMC
HBA, basic input-output system BIOS and temperature sensor, wherein, described 2nd BMC management
Temperature information in the described SMART information of described HBA record.
In the method for wherein said SRM,
Described switching node plate includes: the 3rd substrate management being connected in the switching node plate of described RMC
Controller BMC, respectively outband management are connected to the Serial Attached Small Computer on described 3rd BMC
System interface exchange SAS Switch and temperature sensor, wherein, described 3rd BMC, it is used for managing
The SAS topology information obtained from described SAS Switch.
In the method for wherein said SRM,
Described SAS topology information includes that described HBA connects the port numbers Port ID of SAS Switch, institute
State the address of SAS.
In the method for wherein said SRM,
Described hard disk information includes the port information of hard disk, capacity, device type and interface type.
In the method for wherein said SRM,
Described RMC is obtaining the distribution request of the first hard disk, resolves described in described distribution request first hard
The port of dish and capacity information;Port according to described first hard disk and described capacity information, by described first
The port of hard disk joins, the partner's fdisk mated with described first hard-disk capacity, wherein said partner
Fdisk is to pre-build the subregion of one-to-one relationship with server node plate subregion.
In the method for wherein said SRM,
Described RMC, after described first hard disk distributes, obtains a deletion distribution request, according to described
Delete distribution request, described first hard disk is exited partner's fdisk.
In the method for wherein said SRM,
A described BMC gets the second hard disk and extracts event, and described second hard disk is extracted reporting events
To described RMC, described RMC carry out the deletion of the second hard disk information.
In the method for wherein said SRM,
A described BMC gets the second hard disk and inserts event, distributes to described second hard disk preset and writes from memory
Recognize subregion, and give described RMC by described insertion reporting events.
In the method for wherein said SRM,
Described RMC sends the order of inquiry the 3rd hard disk running status to described 2nd BMC;
Described RMC receives and is fed back the SMATR information in described HBA by described 2nd BMC, and
According to the described 3rd hard disk actual temperature in described SMATR information, the cooling system that regulation and control are overall;
Described RMC receives and is fed back the SMATR information in described HBA by described 2nd BMC, and
Running status according to described 3rd hard disk in described SMATR information, it is judged that described 3rd hard disk be
The no hard disk that breaks down;
Described RMC, after described 3rd hard disk breaks down, alerts and isolates.
Having the beneficial effect that of the technique scheme of the embodiment of the present invention:
In the scheme of the embodiment of the present invention, by directly the most respectively from server node plate, switching node plate and deposit
Storage gusset plate obtains self-monitoring analysis and reporting techniques SMART information, serial connecting small computer
System interface SAS topology information and hard disk information are managed, and existing rack is serviced by the embodiment of the present invention
The management plane of device system is optimized, and uses a BMC to realize out-of-band resource management and distribution, and
And manage JBOD by a BMC of memory node plate, can directly obtain JBOD and store resource,
Simplify the software complexity of SAS Switch, improve transmission efficiency.
Accompanying drawing explanation
Fig. 1 is existing SAS Zoning schematic diagram;
Fig. 2 is existing rack server system management plane schematic diagram;
Fig. 3 is embodiment of the present invention rack server system management plane schematic diagram;
Fig. 4 is embodiment of the present invention storage resource distribution schematic diagram;
Fig. 5 is embodiment of the present invention SRM state machine;
Fig. 6 is the step schematic diagram of the method for the SRM of the embodiment of the present invention.
Detailed description of the invention
For making the technical problem to be solved in the present invention, technical scheme and advantage clearer, below in conjunction with attached
Figure and specific embodiment are described in detail.
The embodiment of the present invention directly connects with RMC1 for SAS Switch32 in prior art, then will hand over
Change BMC31 and RMC1 in gusset plate 3 to connect, can only obtain by the BMC31 from switching node plate 3
Get sensor 43 information, the problem that resource management information can not be got, the most existing pass through SAS
Switch32 forward JBOD42 to RMC1, not only inefficient, and condition requires higher problem.
The embodiment of the present invention provide a kind of SRM system and method, by BMC respectively with JBOD
Connect with HBA, so that it may obtain resource management information and sensor information, it is achieved that directly obtain resource,
It is managed, and decreases the software complexity of RMC, and forward JBOD safety by BMC
Reliably, efficiency is high.
As shown in Figure 3 and Figure 4, the system of the SRM that the embodiment of the present invention provides, including:
Rack management board RMC31, for according to the self-monitoring analysis received and reporting techniques SMART
One in information, serial connecting small computer system interface SAS topology information and hard disk information or
Multiple, managing memory source;
The server node plate 32 being connected with described RMC31, is used for obtaining described SMART information, and
Report to described RMC31;
The switching node plate 33 being connected with described RMC31, is used for obtaining described SAS topology information, and
Report to described RMC31;
The memory node plate 34 being connected with described RMC31, is used for obtaining described hard disk information, and reports to
Described RMC31, wherein said memory node plate 34 includes: be connected to the memory node plate of described RMC
In first substrate Management Controller BMC341, the simple hard disk that is connected on a described BMC341
Bunch JBOD342, a wherein said BMC341, the hard disk obtained from described JBOD342 for management
Information.
In the embodiment of the present invention, by directly the most respectively from server node plate 32, switching node plate 33 and deposit
Storage gusset plate 34 obtains self-monitoring analysis and reporting techniques SMART information, serial connecting small calculate
Machine system interface SAS topology information and hard disk information are managed, compared with RMC1 in traditional Fig. 2
(management of JBOD42 is needed SAS switch32 to carry out to the hard disk information of acquisition JBOD42 by RMC1
The outer conversion in band of band, when obtaining storage resource information, SAS switch32 needs first to resolve band outer tube
Reason order, is converted into scsi command and is sent to JBOD42, and to SAS switch32 software requirement relatively
Height, a lot of functions need specific customization) problem for, the embodiment of the present invention is to existing equipment cabinet server system
The management plane of system is optimized, and uses a BMC341 to realize out-of-band resource management and distribution, and
And manage JBOD342 by a BMC341 of memory node plate, can directly obtain JBOD342 and deposit
Storage resource, simplifies the software complexity of SAS Switch, improves transmission efficiency.
It should be understood that as it is shown on figure 3, described memory node plate 34 also includes: it is connected to described
Temperature sensor 343 on one BMC341, wherein said memory node plate 34 can configure one piece or many
Block.
JBOD and SAS expander automated topology on above-mentioned memory node plate finds SAS switching domain
In the information of all hard disks, including connecting Port ID, SAS address of SAS expander, equipment class
Type, interface type, capacity, hard disk serial number etc..
Above-mentioned simple hard disk bunch JBOD is also had to include serial connecting small computer system Interface Extender
SAS expander and hard disk.
The JBOD being connected with a described BMC and temperature sensor are all to be connected by outband management,
The connection of wherein said outband management includes but not limited to Ethernet, UART (Universal Asynchronous
Receiver/Transmitter, universal asynchronous receiving-transmitting transmitter or asynchronous receiving-transmitting transmitter), I2C (Inter-
Integrated Circuit, twin wire universal serial bus), concrete connection correspondence depends on HBA, SAS switch
And SAS expander chip ability, and the server node plate that above-mentioned and described RMC is connected, hand over
Change gusset plate and memory node plate is all attached by Ethernet.
Further, above-mentioned SAS topology information include described HBA connect SAS Switch port numbers Port ID,
The address of described SAS.Above-mentioned hard disk information include the port information of hard disk, capacity, device type and
Interface type.
It addition, above-mentioned SMART (Self Monitoring Analysis and Reporting Technology,
Self-monitoring analysis and reporting techniques) information is to have the operation time of hard disk, operational factor, running temperature
Etc. information, for the state of recording disk;Information is directly obtained by the SMART information of inquiry hard disk,
Do not affect system radiating effect, be also convenient for monitoring reliably hardware temperatures.
Above-mentioned RMC, manages node as the rack in system, has converged all joints by Ethernet exchanging
The BMC of some plate, forms the management plane of described rack server system.
Managing customer end 35, as the webmaster backstage in system, Ethernet connects RMC, is responsible for whole clothes
Version management, fault management and the resource management etc. of business device rack gusset plate.Web GUI, Yong Huke are provided
Graphically change the storage resource managed in described rack server system.
Further, rack management board RMC if SMART information, SAS topology information and hard
A kind of information in dish information, then illustrate that other do not have the path of reporting information to occur abnormal, it is possible to realize
Abnormal I/O path detection, can not cover complete server for traditional RMC to the detection of hard disk
The I/O path of node is (as in Fig. 2, RMC can not find occur between HBA and SAS Switch
Chain rupture), the embodiment of the present invention is capable of faulty hard disk isolation and changes function.
As it is shown on figure 3, in order to realize on the temperature information in the described SMART information that HBA324 records
Offering RMC, in the system of the SRM of the embodiment of the present invention, described server node plate includes:
The second substrate Management Controller BMC321 that is connected in the server node plate of described RMC, carry respectively
Outer management is connected to host bus adaptor HBA324 on described 2nd BMC321, basic input and output
System bios 322 and temperature sensor 323, wherein, described 2nd BMC321, it is used for managing described
Temperature information in the described SMART information of HBA324 record.
In the embodiment of the present invention, the 2nd BMC of described server node plate manages HBA, can make up
SAS expander outband management passage cannot directly obtain the defect of the SMART information of hard disk.
It should be understood that described server node plate can configure one piece or polylith, by described second
BMC monitors disk state, detects the I/O path of described server node, and adjusts according to hard disk actual temperature
Joint cooling system, isolated fault hard disk.
As it is shown on figure 3, in order to the SAS topology information realized from SAS Switch332 obtains reports RMC,
In the system of the SRM of the embodiment of the present invention, described switching node plate includes: be connected to described
The 3rd baseboard management controller BMC331 in the switching node plate of RMC, respectively outband management are connected to
On described 3rd BMC331 serial connecting small computer system interface exchange SAS Switch332 and
Temperature sensor 333, wherein, described 3rd BMC331, for management from described SAS Switch332
The SAS topology information obtained.
In the embodiment of the present invention, the 3rd BMC of described switching node plate manages SAS Switch, to RMC
Shield the difference of different manufacturers SAS Switch.
It should be understood that switching node plate described above at least configures two pieces constitutes multipath Redundancy Design,
And the SAS Switch automated topology being connected on the 3rd BMC finds owning in SAS switching domain
SAS device and the information of SAS expander, including HBA connect SAS Switch Port ID,
SAS address.
In order to manage all resources by RMC management SAS Switch one end, by described storage joint
JBOD, described HBA on some plate are all connected with SAS Switch, a described BMC, the 3rd BMC
All it is connected with RMC with the 2nd BMC, therefore can be managed by RMC management SAS Switch one end
Manage all resources, it is to avoid RMC with HBA and JBOD such as Fig. 2 are not connected, it is impossible to carry out
The problem of management.Detection method concrete in the embodiment of the present invention is as follows:
Step 101:RMC transmitting order to lower levels, to the 2nd BMC in server node plate, detects I/O path.
Step 102: the 2nd BMC order HBA obtains switching node plate SAS Switch by scsi command
SAS address.If obtaining unsuccessfully, report exception.
Step 103: the 2nd BMC order HBA obtains memory node plate SAS by scsi command
The SAS address of expander.If obtaining unsuccessfully, report exception.
Step 104: the 2nd BMC order HBA obtains memory node plate hard disk serial by scsi command
Number.If obtaining unsuccessfully, report exception.
The System planes signal of the embodiment of the present invention.
For ease of describing as shown in Figure 4, only display 32, switching node plate of two server node plates
33 and two memory node plates 34.Such as two blocks of memory node plates 34 have 3 hard disks, and user wishes
Initial state, Servers-all gusset plate be can't see any hard disk, RMC according to user's configuration, hard disk divided
The server node plate 32 that dispensing is concrete, such as hard disk HDD1 (Hard Disk Drive, hard disk drive)
Distribute to HBA1, hard disk HDD2 and distribute to HBA2.Unappropriated hard disk is referred to as without master, in Fig. 4
Hard disk HDD3 is without master.Because the groove position of server node plate is fixing, HBA connects SAS
The port of Switch also determines that, SAS Switch need not be concerned about that whether this groove position server node plate exists
Position, distributes the ZONE of Servers-all node board slot position during initialization, server node plate is after the power-up
It is seen that allocated hard disk.
In order to realize resource distribution, in the system of the SRM of the embodiment of the present invention, described RMC
Obtain the distribution request of the first hard disk, resolve port and the capacity of the first hard disk described in described distribution request
Information;Port according to described first hard disk and described capacity information, add the port of described first hard disk
Arriving, the partner's fdisk mated with described first hard-disk capacity, wherein said partner's fdisk is and clothes
Business device gusset plate subregion pre-builds the subregion of one-to-one relationship.
In the embodiment of the present invention, before server node does not power up, realize Dynamic Resource Allocation for Multimedia, depositing of employing
Storage resource allocation methods, it is only necessary to synchronize a ZPT table when initializing, follow-up SAS topology becomes
During change, SAS can be realized easily by the group identification code group ID of change hard disk correspondence SAS PHY
Zoning configures.
It should be understood that arrange server node ZONE and partner's hard disk by described SAS Switch
ZONE, described server node ZONE refer to switching node plate SAS Switch corresponding server node
The set of properties group ID, such as SAS of the SAS PHY (Physical Layer, physical layer) of board slot position
The group ID of the port P1 that Switch amendment HBA1 is corresponding is that (SAS Zoning specifies group 8
Group0~7 is for retaining group), the group ID of the port P2 that amendment HBA2 is corresponding is group9.Institute
State partner hard disk ZONE and refer to the ZONE that described server node can communicate.Such as the partner of HBA1
The partner memory node ZONE accompanying memory node ZONE to be group64, HBA2 is group65.
SAS expander arranges all hard disks and belongs to same default ZONE, is generally selected a reservation
Group is as default ZONE.Such as SAS expander1 arranges port P3's corresponding for hard disk HDD1
Group ID is the group ID that group0, SAS expander2 arranges port P4 corresponding for hard disk HDD2
It is group0 for group0, the group ID of port P5 corresponding for hard disk HDD3.
Further, pre-build described in and refer to that described switching node plate SAS Switch arranges clothes when initializing
Business device gusset plate ZONE and partner hard disk ZONE so that described server node plate ZONE and partner
Hard disk ZONE is relation one to one.
Described memory node plate SAS expander arranges all hard disks and belongs to same default ZONE.
Described SAS Switch arranges ZPT table, only allows described server node plate ZONE hard with partner
Dish ZONE communicates.
Described SAS Switch is synchronized to all SAS expander when Topology Discovery ZPT.
SAS Switch creates ZPT table (agreement to be used this table and carry out dividing communication), server node
ZONE and partner hard disk ZONE sets up and communicates.Such as the ZPT table such as table 1 below that SAS Switch creates
Shown in.
The X-axis of ZPT table represents source ZONE, and Y-axis represents that purpose ZONE, ZP (X, Y) are 0 table
Showing that groupX with groupY can not communicate, 1 represents that groupX with groupY can communicate.M represents maximum
Group, relevant with SAS expander chip ability, 128 group of general support.Fig. 4 example handle
ZP (8,64) and ZP (64,8) be both configured to 1 make group8 and group64 can with intercommunication,
ZP (9,65) and ZP (65,9) is both configured to 1 makes group9 and group65 to communicate mutually
Letter.
SAS Switch is synchronized to SAS expander, such as SAS Switch1 and SAS Switch2 ZPT
ZPT is synchronized to SAS expander1 and SAS expander2.
The embodiment of the present invention to implement process as follows.
Step 201: user distributes hard disk, such as HBA1 to server node plate at managing customer end 35
Distribution hard disk HDD1, distributes hard disk HDD2 to HBA2, and transmitting order to lower levels is to RMC.
Step 202:RMC transmitting order to lower levels gives a BMC.
Step 203: a BMC order SAS expander revises partner hard disk ZONE.Described partner
Hard disk ZONE refers to the group ID of memory node plate SAS expander correspondence hard disk SAS PHY attribute.
The group ID of such as corresponding for SAS expander1 amendment hard disk HDD1 port P3 is group64,
The group ID of the port P4 that SAS expander2 amendment hard disk HDD2 is corresponding is group65.
Step 204: resource is allocated successfully, RMC preserves user data.
For in the embodiment of the present invention, need first to report hardware resource, be allocated to server joint further according to user
Point distribution hardware, it is exactly default set that hard disk first loads group 0, is judging hardware capabilities and interface letter
Breath machine reports resource that hard disk is assigned as according to reporting information the partner ZONE of service to RMC, RMC
Group ID (will original group 0 be revised as group 64), so can be obtained by passing through RMC
Server needed for the subscription client instruction forwarded and amount of capacity.
In order to realize the resource of distribution being deleted, in the system of the SRM of the embodiment of the present invention,
Described RMC is additionally operable to after described first hard disk distributes, obtains a deletion distribution request, root
Delete distribution request according to described, described first hard disk is exited partner's fdisk.
The embodiment of the present invention to implement process as follows.
Step 301: user deletes the hard disk distributing to server node plate at managing customer end 35, such as
Deleting the hard disk HDD1 distributing to HBA1, transmitting order to lower levels is to RMC.
Step 302:RMC transmitting order to lower levels gives a BMC.
Step 303: a BMC order SAS expander exits hard disk from partner memory node ZONE,
The group ID of such as corresponding for SAS expander1 amendment hard disk HDD1 port P3 is group0 (0
To 9), exit group64.
User safeguards or changes hard disk for convenience, and then extracts hard disk, the storage money of the embodiment of the present invention
In the system of source control, a described BMC is additionally operable to get the second hard disk and extracts event, by described
Two hard disks extract reporting events give described RMC, described RMC carry out the deletion of the second hard disk information.
User increases hard disk or changes hard disk for convenience, and then inserts new hard disk, the embodiment of the present invention
SRM system in, a described BMC is additionally operable to get the second hard disk and inserts event,
Described second hard disk is distributed to preset default partition, and gives described RMC by described insertion reporting events.
It should be understood that above-mentioned default default partition is group0.
Further, as it is shown in figure 5, RMC described in the embodiment of the present invention can realize above-mentioned several functions,
Hard disk management, resource deletion, the functions such as I/O path detects, hard disk insertion.
As shown in Figure 6, the embodiment of the present invention provides a kind of method of SRM, including:
Step 61, server node plate obtains self-monitoring analysis and reporting techniques SMART information, and
Report to rack management board RMC;
Step 62, switching node plate obtains serial connecting small computer system interface SAS topology information,
And report to described RMC;
Step 63, memory node plate obtains hard disk information, and reports to described RMC, wherein said storage
Gusset plate includes: the first substrate Management Controller BMC that is connected in the memory node plate of described RMC,
It is connected to the simple hard disk bunch JBOD on a described BMC, a wherein said BMC, is used for managing
The hard disk information obtained from described JBOD;
Step 64, described RMC is according to the described SMART information received, described SAS topology letter
One or more in breath and described hard disk information, managing memory source.
In the embodiment of the present invention, by directly respectively from server node plate, switching node plate and memory node
Plate obtains self-monitoring analysis and reporting techniques SMART information, serial connecting small computer system interface
SAS topology information and hard disk information are managed, thus the embodiment of the present invention is to existing equipment cabinet server system
The management plane of system is optimized, and uses a BMC to realize out-of-band resource management and distribution, and leads to
The BMC crossing memory node plate manages JBOD, can directly obtain JBOD and store resource, simplify
The software complexity of SAS Switch, improves transmission efficiency.
In order to preferably obtain topology information, the present invention obtains the idiographic flow of topology information and is exemplified below:
Step 401, the 3rd BMC obtains SAS topology information, such as SAS Switch to SAS Switch
Obtain the port information of HBA1 and HBA2, connect SAS expander1 and the end of SAS expander 2
Message ceases.
Step 402: the 3rd BMC reports SAS topology information to RMC.
Step 403:RMC collects the SAS topology that all switching node plates report, such as to plate SAS
The SAS topology that Switch reports respectively, if inconsistent, alerts, and selects optimum topology.
Step 404 a: BMC obtains SAS topology information, such as SAS to SAS expander
Expander1 and SAS expander 2 obtains SAS topology information, including the port information of hard disk, capacity,
Device type, interface type.
Step 405 a: BMC reports SAS topology to RMC.
Step 406:RMC collects the SAS topology that all memory node plates report, and such as contrasts SAS
The SAS topology that expander 1 and SAS expander 2 reports respectively, if inconsistent, alerts, and selects
(described optimum topology refers to that numeral is the highest, is such as to be examined by a SAS expander1 to select optimum topology
Measuring 3 hard disks, a SAS expander2 detects 2 hard disks, in order to avoid omitting hard disk, because of
This is according to 3 hard disks.There is SAS expander1 and SAS expander2 two, prevent one to go out
After mistake, another can ensure that business, is that general one can also meet in order to select optimum topology herein
Require).
In the method for the SRM of another embodiment of the present invention, described server node plate includes:
Outside the second substrate Management Controller BMC that is connected in the server node plate of described RMC, respectively band
Manage host bus adaptor HBA, the basic input output system being connected on described 2nd BMC
BIOS and temperature sensor, wherein, described 2nd BMC manages the described of described HBA record
Temperature information in SMART information.
In the embodiment of the present invention, the 2nd BMC in described server node plate manages HBA, can make up
SAS expander outband management passage cannot directly obtain the defect of the SMART information of hard disk.
In the method for the SRM of another embodiment of the present invention, described switching node plate includes: even
The 3rd baseboard management controller BMC that is connected in the switching node plate of described RMC, respectively outband management
Be connected on described 3rd BMC serial connecting small computer system interface exchange SAS Switch and
Temperature sensor, wherein, described 3rd BMC, the SAS obtained from described SAS Switch for management
Topology information.
In the embodiment of the present invention, the 3rd BMC in described switching node plate manages SAS Switch, right
RMC shields the difference of different manufacturers SAS Switch.
In the method for the SRM of another embodiment of the present invention, described SAS topology information includes
Described HBA connects the port numbers Port ID of SAS Switch, the address of described SAS.
In the embodiment of the present invention, a BMC, the 2nd BMC are connected with JBOD and HBA respectively,
A described BMC manages JBOD, it is also possible to directly obtains JBOD and stores resource, simplifies SAS
The software complexity of Switch.
In the method for the SRM of another embodiment of the present invention, described hard disk information includes hard disk
Port information, capacity, device type and interface type.
In the method for the SRM of another embodiment of the present invention, described RMC is hard in acquisition first
The distribution request of dish, resolves port and the capacity information of the first hard disk described in described distribution request;According to institute
State the port of the first hard disk and described capacity information, the port of described first hard disk is joined, with described
Partner's fdisk of one hard-disk capacity coupling, wherein said partner's fdisk is for divide with server node plate
District pre-builds the subregion of one-to-one relationship.
The storage resource allocation methods that the present invention uses, it is only necessary to synchronize a ZPT table when initializing,
When follow-up SAS topology changes, by change hard disk correspondence SAS PHY (Physical layer, thing
Reason layer) group ID can realize easily SAS zoning configuration.
In the method for the SRM of another embodiment of the present invention, described RMC is described first hard
After dish distributes, obtain a deletion distribution request, delete distribution request according to described, by described first hard
Dish exits partner's fdisk.
In the method for the SRM of another embodiment of the present invention, a described BMC gets
Event extracted by two hard disks, described second hard disk is extracted reporting events give described RMC, by described RMC
Carry out the deletion of the second hard disk information.
In the method for the SRM of another embodiment of the present invention, a described BMC gets
Two hard disks insert event, distribute to described second hard disk preset default partition, and by described insertion event
Offer described RMC.
In the method for the SRM of another embodiment of the present invention,
Described RMC sends the order of inquiry the 3rd hard disk running status to described 2nd BMC;
Described RMC receives and is fed back the SMATR information in described HBA by described 2nd BMC, and
According to the described 3rd hard disk actual temperature in described SMATR information, the cooling system that regulation and control are overall;
Described RMC receives and is fed back the SMATR information in described HBA by described 2nd BMC, and
Running status according to described 3rd hard disk in described SMATR information, it is judged that described 3rd hard disk be
The no hard disk that breaks down;
Described RMC, after described 3rd hard disk breaks down, alerts and isolates.
In the embodiment of the present invention, it is possible to according to the heat radiation of hard disk temperature dynamic adjusting system the operation shape to hard disk
State is monitored.
It should be understood that above-mentioned SMART information is to have the operation time of hard disk, operational factor,
The information such as running temperature, for the state of recording disk.
Flow process for the hard disk management of RMC is exemplified below:
Step 501:RMC transmitting order to lower levels gives the 2nd BMC, inquires about hard disk running status.
Step 502: the SMART letter of the 2nd BMC order HBA inquiry hard disk in server node plate
Breath.
Step 503:RMC gets the running status of hard disk.
Step 504:RMC regulates and controls cooling system according to hard disk actual temperature.
Step 505:RMC finds faulty disk (different with normal parameter), and alerting and isolating (is exactly to exit
Hard disk).
In the embodiment of the present invention, carry out reporting of temperature data for traditional data by single sensor
The error of data (concrete due to memory plane more, corresponding each memory plane can not have sensor,
Or the distance of each memory plane of distance also can affect measurement data on each sensor so that storage joint
There is error by the hard disk temperature of temperature sensor monitors and the actual temperature of hard drive internal in point, affects system
Radiating effect and the problem shortening hard disk life-span.As Fig. 2 only having the HBA in server node permissible
As SAS initiator Device (device of promoter) by SCSI (Small Computer System
Interface, small computer system interface) agreement goes to obtain.The out-band channel of switching node is cannot be straight
Obtain the SMART information that takes, but server node generally use commercial OS (Operation System,
Operating system), inconvenience directly increases application program and goes to control HBA.) embodiment of the present invention is by inquiry firmly
The SMART information of dish directly obtains information, does not affect system radiating effect, is also convenient for monitoring reliably firmly
Part temperature.
It should be noted that the device that the present invention provides is the device of the method applying above-mentioned SRM,
All embodiments of the method for the most above-mentioned SRM are all applicable to this device, and all can reach identical or
Similar beneficial effect.
The above is the preferred embodiment of the present invention, it is noted that for the common skill of the art
For art personnel, on the premise of without departing from principle of the present invention, it is also possible to make some improvements and modifications,
These improvements and modifications also should be regarded as protection scope of the present invention.
Claims (19)
1. the system of a SRM, it is characterised in that including:
Rack management board RMC, for according to the self-monitoring analysis received and reporting techniques SMART
One in information, serial connecting small computer system interface SAS topology information and hard disk information or
Multiple, managing memory source;
The server node plate being connected with described RMC, is used for obtaining described SMART information, and reports
To described RMC;
The switching node plate being connected with described RMC, is used for obtaining described SAS topology information, and reports to
Described RMC;
The memory node plate being connected with described RMC, is used for obtaining described hard disk information, and reports to described
RMC, wherein said memory node plate includes: the first base being connected in the memory node plate of described RMC
Board management controller BMC, the simple hard disk bunch JBOD being connected on a described BMC, wherein said
Oneth BMC, the hard disk information obtained from described JBOD for management.
The system of SRM the most according to claim 1, it is characterised in that described service
Device gusset plate includes: the second substrate Management Controller being connected in the server node plate of described RMC
BMC, respectively outband management are connected to host bus adaptor HBA on described 2nd BMC, basic
Input-output system BIOS and temperature sensor, wherein, described 2nd BMC, it is used for managing described
Temperature information in the described SMART information of HBA record.
The system of SRM the most according to claim 1, it is characterised in that described exchange
Gusset plate includes: the 3rd baseboard management controller BMC that is connected in the switching node plate of described RMC,
The serial connecting small computer system interface exchange that outband management is connected on described 3rd BMC respectively
SAS Switch and temperature sensor, wherein, described 3rd BMC, for management from described SAS
The SAS topology information that Switch obtains.
4. according to the system of the SRM described in claim 1 or 3, it is characterised in that described
SAS topology information includes that described HBA connects the port numbers Port ID of SAS Switch, described SAS
Address.
The system of SRM the most according to claim 1, it is characterised in that described hard disk
Information includes the port information of hard disk, capacity, device type and interface type.
6. according to the system of the SRM described in claim 1,2 or 3, it is characterised in that
Described RMC is additionally operable to obtaining the distribution request of the first hard disk, resolves described in described distribution request
The port of the first hard disk and capacity information;Port according to described first hard disk and described capacity information, by institute
The port stating the first hard disk joins, the partner's fdisk mated with described first hard-disk capacity, Qi Zhongsuo
Stating partner's fdisk is to pre-build the subregion of one-to-one relationship with server node plate subregion.
The system of SRM the most according to claim 6, it is characterised in that
Described RMC is additionally operable to after described first hard disk distributes, obtains a deletion distribution request, root
Delete distribution request according to described, described first hard disk is exited partner's fdisk.
The system of SRM the most according to claim 1, it is characterised in that
A described BMC is additionally operable to get the second hard disk and extracts event, and described second hard disk is extracted thing
Part reports described RMC, described RMC carry out the deletion of the second hard disk information.
The system of SRM the most according to claim 1, it is characterised in that
A described BMC is additionally operable to get the second hard disk and inserts event, is distributed to by described second hard disk
Preset default partition, and give described RMC by described insertion reporting events.
10. the method for a SRM, it is characterised in that including:
Server node plate obtains self-monitoring analysis and reporting techniques SMART information, and reports to rack
Management board RMC;
Switching node plate obtains serial connecting small computer system interface SAS topology information, and reports to
Described RMC;
Memory node plate obtains hard disk information, and reports to described RMC, wherein said memory node plate bag
Include: the first substrate Management Controller BMC that is connected in the memory node plate of described RMC, be connected to
Simple hard disk bunch JBOD on a described BMC, a wherein said BMC, for management from described
The hard disk information that JBOD obtains;
Described RMC is according to the described SMART information received, described SAS topology information and described
One or more in hard disk information, managing memory source.
The method of 11. SRMs according to claim 10, it is characterised in that described clothes
Business device gusset plate includes: the second substrate Management Controller being connected in the server node plate of described RMC
BMC, respectively outband management are connected to host bus adaptor HBA on described 2nd BMC, basic
Input-output system BIOS and temperature sensor, wherein, described 2nd BMC manages described HBA
Temperature information in the described SMART information of record.
The method of 12. SRMs according to claim 10, it is characterised in that described friendship
Change gusset plate to include: the 3rd baseboard management controller BMC that is connected in the switching node plate of described RMC,
The serial connecting small computer system interface exchange that outband management is connected on described 3rd BMC respectively
SAS Switch and temperature sensor, wherein, described 3rd BMC, for management from described SAS
The SAS topology information that Switch obtains.
13. according to the method for the SRM described in claim 10 or 12, it is characterised in that institute
State SAS topology information and include that described HBA connects the port numbers Port ID of SAS Switch, described SAS
Address.
The method of 14. SRMs according to claim 10, it is characterised in that described firmly
Dish information includes the port information of hard disk, capacity, device type and interface type.
15. according to the method for the SRM described in claim 10,11 or 12, it is characterised in that
Described RMC is obtaining the distribution request of the first hard disk, resolves described in described distribution request first hard
The port of dish and capacity information;Port according to described first hard disk and described capacity information, by described first
The port of hard disk joins, the partner's fdisk mated with described first hard-disk capacity, wherein said partner
Fdisk is to pre-build the subregion of one-to-one relationship with server node plate subregion.
The method of 16. SRMs according to claim 15, it is characterised in that
Described RMC, after described first hard disk distributes, obtains a deletion distribution request, according to described
Delete distribution request, described first hard disk is exited partner's fdisk.
The method of 17. SRMs according to claim 10, it is characterised in that
A described BMC gets the second hard disk and extracts event, and described second hard disk is extracted reporting events
To described RMC, described RMC carry out the deletion of the second hard disk information.
The method of 18. SRMs according to claim 10, it is characterised in that
A described BMC gets the second hard disk and inserts event, distributes to described second hard disk preset and writes from memory
Recognize subregion, and give described RMC by described insertion reporting events.
The method of 19. SRMs according to claim 11, it is characterised in that
Described RMC sends the order of inquiry the 3rd hard disk running status to described 2nd BMC;
Described RMC receives and is fed back the SMATR information in described HBA by described 2nd BMC, and
According to the described 3rd hard disk actual temperature in described SMATR information, the cooling system that regulation and control are overall;
Described RMC receives and is fed back the SMATR information in described HBA by described 2nd BMC, and
Running status according to described 3rd hard disk in described SMATR information, it is judged that described 3rd hard disk be
The no hard disk that breaks down;
Described RMC, after described 3rd hard disk breaks down, alerts and isolates.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510369563.2A CN106325761B (en) | 2015-06-29 | 2015-06-29 | System and method for managing storage resources |
PCT/CN2016/080051 WO2017000639A1 (en) | 2015-06-29 | 2016-04-22 | Storage resource management system and method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510369563.2A CN106325761B (en) | 2015-06-29 | 2015-06-29 | System and method for managing storage resources |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106325761A true CN106325761A (en) | 2017-01-11 |
CN106325761B CN106325761B (en) | 2020-04-28 |
Family
ID=57607686
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510369563.2A Active CN106325761B (en) | 2015-06-29 | 2015-06-29 | System and method for managing storage resources |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN106325761B (en) |
WO (1) | WO2017000639A1 (en) |
Cited By (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107315542A (en) * | 2017-06-29 | 2017-11-03 | 郑州云海信息技术有限公司 | A kind of JBOD cascade systems |
CN107577580A (en) * | 2017-09-18 | 2018-01-12 | 郑州云海信息技术有限公司 | A kind of cabinet management system and method |
CN107783841A (en) * | 2017-11-10 | 2018-03-09 | 郑州云海信息技术有限公司 | A kind of method of RACK server pools management of product optimization |
CN108197009A (en) * | 2018-02-02 | 2018-06-22 | 郑州云海信息技术有限公司 | A kind of Jbod system log acquisition methods, system, medium and equipment |
CN108460126A (en) * | 2018-02-28 | 2018-08-28 | 郑州云海信息技术有限公司 | A kind of acquisition methods and device of the daily record of equipment cabinet server unit of memory allocation |
CN108762667A (en) * | 2018-04-20 | 2018-11-06 | 烽火通信科技股份有限公司 | The method that the multi node server of disk can be dynamically distributed and dynamically distribute disk |
CN108959146A (en) * | 2017-05-19 | 2018-12-07 | 三星电子株式会社 | Data-storage system |
CN109189326A (en) * | 2018-07-25 | 2019-01-11 | 华为技术有限公司 | The management method and device of distributed type assemblies |
CN109189644A (en) * | 2018-09-17 | 2019-01-11 | 郑州云海信息技术有限公司 | Whole machine cabinet RMC, the method and system that whole machine cabinet increases number of nodes newly are automatically configured |
CN109376052A (en) * | 2018-09-10 | 2019-02-22 | 联想(北京)有限公司 | It is a kind of to monitor the method for disk state, electronic equipment |
CN110515540A (en) * | 2019-07-26 | 2019-11-29 | 苏州浪潮智能科技有限公司 | A kind of method and device of topology hard disk |
CN110601887A (en) * | 2019-09-06 | 2019-12-20 | 苏州浪潮智能科技有限公司 | Out-of-band management method, server, computer storage medium and terminal |
CN110941535A (en) * | 2019-11-22 | 2020-03-31 | 山东超越数控电子股份有限公司 | Hard disk load balancing method |
CN111045602A (en) * | 2019-11-25 | 2020-04-21 | 浙江大华技术股份有限公司 | Cluster system control method and cluster system |
CN111092759A (en) * | 2019-12-13 | 2020-05-01 | 苏州浪潮智能科技有限公司 | Log management method, device and medium in JBOD (just in Bunch) out-of-band management system |
TWI796211B (en) * | 2022-04-29 | 2023-03-11 | 神雲科技股份有限公司 | Port setting method |
CN117311634A (en) * | 2023-10-08 | 2023-12-29 | 无锡众星微系统技术有限公司 | Method and device for processing disk exception of SAS (serial attached small computer system interface) storage system |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106817413A (en) * | 2017-01-11 | 2017-06-09 | 郑州云海信息技术有限公司 | A kind of control node method for start-up and shutdown, system and RMC |
CN108616390B (en) * | 2018-04-11 | 2019-09-13 | 新华三信息技术有限公司 | The realization device of girff management method, device and girff management |
CN109586994B (en) * | 2018-11-01 | 2022-02-18 | 郑州云海信息技术有限公司 | Aging test monitoring method and system for server of whole cabinet |
CN114816887B (en) * | 2022-05-31 | 2024-06-28 | 苏州浪潮智能科技有限公司 | Method, system, equipment and medium for checking server hard disk backboard topology setting |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2011227841A (en) * | 2010-04-23 | 2011-11-10 | Hitachi Ltd | Computer system and identifier management method |
CN102510344A (en) * | 2011-11-23 | 2012-06-20 | 华为技术有限公司 | Rack server system |
CN103154927A (en) * | 2010-10-16 | 2013-06-12 | 惠普发展公司,有限责任合伙企业 | Device hardware agent |
CN103793307A (en) * | 2012-10-31 | 2014-05-14 | 英业达科技有限公司 | Electronic device, management method thereof and cabinet servo system |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
TWI403884B (en) * | 2010-11-30 | 2013-08-01 | Inventec Corp | Rack server system |
TWI437426B (en) * | 2011-07-08 | 2014-05-11 | Quanta Comp Inc | Rack server system |
CN104683147B (en) * | 2015-01-27 | 2018-10-30 | 加弘科技咨询(上海)有限公司 | It is a kind of to large-scale data central hardware management method and system |
-
2015
- 2015-06-29 CN CN201510369563.2A patent/CN106325761B/en active Active
-
2016
- 2016-04-22 WO PCT/CN2016/080051 patent/WO2017000639A1/en active Application Filing
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2011227841A (en) * | 2010-04-23 | 2011-11-10 | Hitachi Ltd | Computer system and identifier management method |
CN103154927A (en) * | 2010-10-16 | 2013-06-12 | 惠普发展公司,有限责任合伙企业 | Device hardware agent |
CN102510344A (en) * | 2011-11-23 | 2012-06-20 | 华为技术有限公司 | Rack server system |
CN103793307A (en) * | 2012-10-31 | 2014-05-14 | 英业达科技有限公司 | Electronic device, management method thereof and cabinet servo system |
Cited By (25)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US11842052B2 (en) | 2017-05-19 | 2023-12-12 | Samsung Electronics Co., Ltd. | Method and apparatus for fine tuning and optimizing NVMe-oF SSDs |
CN108959146A (en) * | 2017-05-19 | 2018-12-07 | 三星电子株式会社 | Data-storage system |
CN108959146B (en) * | 2017-05-19 | 2023-09-05 | 三星电子株式会社 | data storage system |
CN107315542A (en) * | 2017-06-29 | 2017-11-03 | 郑州云海信息技术有限公司 | A kind of JBOD cascade systems |
CN107577580A (en) * | 2017-09-18 | 2018-01-12 | 郑州云海信息技术有限公司 | A kind of cabinet management system and method |
CN107783841A (en) * | 2017-11-10 | 2018-03-09 | 郑州云海信息技术有限公司 | A kind of method of RACK server pools management of product optimization |
CN107783841B (en) * | 2017-11-10 | 2020-07-21 | 苏州浪潮智能科技有限公司 | RACK server pooling product management optimization method |
CN108197009A (en) * | 2018-02-02 | 2018-06-22 | 郑州云海信息技术有限公司 | A kind of Jbod system log acquisition methods, system, medium and equipment |
CN108460126A (en) * | 2018-02-28 | 2018-08-28 | 郑州云海信息技术有限公司 | A kind of acquisition methods and device of the daily record of equipment cabinet server unit of memory allocation |
CN108762667A (en) * | 2018-04-20 | 2018-11-06 | 烽火通信科技股份有限公司 | The method that the multi node server of disk can be dynamically distributed and dynamically distribute disk |
CN109189326A (en) * | 2018-07-25 | 2019-01-11 | 华为技术有限公司 | The management method and device of distributed type assemblies |
CN109189326B (en) * | 2018-07-25 | 2020-09-08 | 华为技术有限公司 | Management method and device of distributed cluster |
CN109376052A (en) * | 2018-09-10 | 2019-02-22 | 联想(北京)有限公司 | It is a kind of to monitor the method for disk state, electronic equipment |
CN109189644A (en) * | 2018-09-17 | 2019-01-11 | 郑州云海信息技术有限公司 | Whole machine cabinet RMC, the method and system that whole machine cabinet increases number of nodes newly are automatically configured |
CN109189644B (en) * | 2018-09-17 | 2021-10-22 | 郑州云海信息技术有限公司 | Whole cabinet RMC, and method and system for automatically configuring number of newly added nodes of whole cabinet |
CN110515540A (en) * | 2019-07-26 | 2019-11-29 | 苏州浪潮智能科技有限公司 | A kind of method and device of topology hard disk |
CN110601887B (en) * | 2019-09-06 | 2021-11-26 | 苏州浪潮智能科技有限公司 | Out-of-band management method, server, computer storage medium and terminal |
CN110601887A (en) * | 2019-09-06 | 2019-12-20 | 苏州浪潮智能科技有限公司 | Out-of-band management method, server, computer storage medium and terminal |
CN110941535A (en) * | 2019-11-22 | 2020-03-31 | 山东超越数控电子股份有限公司 | Hard disk load balancing method |
CN111045602A (en) * | 2019-11-25 | 2020-04-21 | 浙江大华技术股份有限公司 | Cluster system control method and cluster system |
CN111045602B (en) * | 2019-11-25 | 2024-01-26 | 浙江大华技术股份有限公司 | Cluster system control method and cluster system |
CN111092759A (en) * | 2019-12-13 | 2020-05-01 | 苏州浪潮智能科技有限公司 | Log management method, device and medium in JBOD (just in Bunch) out-of-band management system |
TWI796211B (en) * | 2022-04-29 | 2023-03-11 | 神雲科技股份有限公司 | Port setting method |
CN117311634A (en) * | 2023-10-08 | 2023-12-29 | 无锡众星微系统技术有限公司 | Method and device for processing disk exception of SAS (serial attached small computer system interface) storage system |
CN117311634B (en) * | 2023-10-08 | 2024-04-12 | 无锡众星微系统技术有限公司 | Method and device for processing disk exception of SAS (serial attached small computer system interface) storage system |
Also Published As
Publication number | Publication date |
---|---|
WO2017000639A1 (en) | 2017-01-05 |
CN106325761B (en) | 2020-04-28 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106325761A (en) | Storage resource management system and method | |
US8046627B2 (en) | Server failover control method and apparatus and computer system group | |
JP4432488B2 (en) | Method and apparatus for seamless management of disaster recovery | |
US6757753B1 (en) | Uniform routing of storage access requests through redundant array controllers | |
JP5976842B2 (en) | Computer system and computer system virtual server migration control method | |
US7356640B2 (en) | Storage apparatus and storage system | |
CN106789168B (en) | Deployment method of data center server management network and rack top type switch | |
CN103729321B (en) | Management device and multi-expander chip management method | |
CN105808158B (en) | Method and apparatus for grouping multiple SAS expanders to form a single cohesive SAS expander | |
US7523176B2 (en) | Method, apparatus, and computer program product for reconfiguring a storage area network to support the execution of an application automatically upon execution of the application | |
CN205490680U (en) | High available cloud computing system based on general server and universal exchange | |
JP4121255B2 (en) | Cluster configuration storage system | |
CN102195815B (en) | Network management method and device | |
US7003642B2 (en) | System and method for controlling access to storage in a distributed information handling system | |
US20220342832A1 (en) | Expander i/o module discovery and management system | |
CN105515870A (en) | Blade server and resource distribution method and system | |
CN103246262B (en) | Comprehensive service system for network data analysis | |
US11593287B2 (en) | Port configuration migration system | |
CN203204423U (en) | Comprehensive service system for network data analysis | |
CN101252593B (en) | Data storage enclosure management system and providing method thereof | |
KR101943899B1 (en) | A system for providing data movement services using volumes in a san network environment | |
CN110061937A (en) | A kind of SAN Fabric level zone and way symmetric inspection method and system | |
JP2003158536A (en) | Managing of one or more domains in system through network connection | |
CN117743218A (en) | Dual-activity arbitration method, system, equipment and storage medium | |
JP2005235008A (en) | Storage control device and server |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |