CN101533336B - Redundant array of independent disks memory system and method thereof - Google Patents
Redundant array of independent disks memory system and method thereof Download PDFInfo
- Publication number
- CN101533336B CN101533336B CN2009100823879A CN200910082387A CN101533336B CN 101533336 B CN101533336 B CN 101533336B CN 2009100823879 A CN2009100823879 A CN 2009100823879A CN 200910082387 A CN200910082387 A CN 200910082387A CN 101533336 B CN101533336 B CN 101533336B
- Authority
- CN
- China
- Prior art keywords
- disk
- raid
- write command
- frame
- read
- 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.)
- Expired - Fee Related
Links
Images
Abstract
The invention discloses a redundant array of an independent disks (RAID) memory system and a method thereof. The invention employs the manner of combination of centralized RAID calculation and distributive RAID calculation to use the centralized RAID calculation resources when each disk composing the RAID is located in different disk frames so that guarantee the RAID calculation resources belonging to different disk frames can share the hot spare disk spanning the disk frames; when all the disks composing the RAID are located in a certain disk frame, then the RAID calculation resource belonging to the disk frame is used. Therefore, the calculation capacity sum of all the RAID calculation resources in the RAID memory system can change in correspondence with the number of the disk frames, the RAID calculation resource belonging to the disk frame is added at the same time with the increase of the disk frames to alleviate the impact on the system performance due to the calculation capacity deficiency; and the RAID calculation resource belonging to the disk frame is removed at the same time with the decrease of the disk frames to avoid resources waste owing to unused RAID calculation resources.
Description
Technical field
The present invention relates to redundant arrays of inexpensive disks (RAID) memory technology, particularly a kind of RAID storage system and a kind of RAID storage means.
Background technology
Fig. 1 is the building-block of logic of existing RAID storage system.As shown in Figure 1, this system adopts centralized RAID account form, and specifically comprise: RAID calculation processing unit, some disk frame 1～n and with some disk frame 1～n disk control module 1～n one to one, be the corresponding disk control module of disk frame i i, n is the positive integer greater than 1, and i is greater than 1 and smaller or equal to the positive integer of n.
And, all having some disks in each disk frame among some disk frame 1～n, the disk in the identical or different disk frame all can be formed different RAID arbitrarily.
The RAID calculation processing unit is used to receive the read write command (" read write command " the expression read command or the write order that occur) of client herein, has indicated its corresponding RAID in the read write command and which disk in which disk frame has been made of; Carry out RAID at the read write command that receives and calculate, according to RAID result of calculation with this read write command be decomposed into each disk of forming corresponding RAID operational order, and send to respectively and the corresponding disk control module of each disk place disk frame.Wherein, corresponding disk of each operational order.
Each disk control module, the operational order that is used for receiving are sent to and the corresponding disk of the corresponding disk frame of this disk control module, carry out corresponding read-write operation to control corresponding disk.
In the practical application, the RAID calculation processing unit can be carried in the master controller in the disk chassis at all disk frame places, the disk control module then can be carried in the processor in the corresponding disk frame, and the processor in each disk frame respectively with this disk frame in each disk physical connection, in all disk frame processor all with the master controller physical connection.
In the above-mentioned RAID storage system, the required computing power that possesses of RAID calculation processing unit is along with the variation of disk sum changes:
For the more situation of disk sum, promptly in the RAID storage system, increased the disk frame of some, the RAID quantity that all disks may be formed also can be bigger, the RAID calculation processing unit just can't satisfy the more required computing power of disk sum so, thereby becomes the restriction system bottleneck of performance;
And for the less situation of disk sum, promptly from the RAID storage system, removed the disk frame of some, the RAID quantity that all disks may be formed is just less, and because the RAID calculation processing unit normally designs according to the most needed max calculation ability of disk sum, though thereby can satisfy the more required computing power of disk sum, can cause the significant wastage of RAID computational resource.
As seen, the computing power of the RAID computational resource in the existing RAID storage system can't be adjusted with the variation of number of disks, thereby makes the RAID computational resource can influence RAID performance of storage system and RAID computational resource when number of disks increases can partly to leave unused when number of disks reduces and cause the wasting of resources.
Summary of the invention
In view of this, the invention provides a kind of RAID storage system and a kind of RAID storage means, can make that the computing power of RAID computational resource is adjusted with the variation of number of disks in the RAID storage system.
A kind of RAID storage system provided by the invention, comprise: order transfer unit, the RAID host computer unit that links to each other with order transfer unit, link to each other with order transfer unit and with some disk frame RAID computation subunit one to one, and link to each other with order transfer unit and with some disk frame disk control module one to one, wherein
Order transfer unit, be used for judging whether the pairing RAID of the read write command that receives is made up of the disk of different disk frame, if, then this read write command is sent to RAID host computer unit, otherwise this read write command is sent to the corresponding RAID computation subunit of each disk place disk frame of forming corresponding RAID;
RAID host computer unit, be used for carrying out RAID and calculate, this read write command is decomposed into the operational order of forming each disk of corresponding RAID in the different disk frame, and sends to respectively and the corresponding disk control module of each disk place disk frame according to RAID result of calculation at the read write command that receives;
The RAID computation subunit, be used for carrying out RAID and calculate, this read write command is decomposed into the operational order of each disk in the pairing disk frame of this RAID computation subunit and is sent to and the corresponding disk control module of this disk frame according to RAID result of calculation at the read write command that receives;
Disk control module, the operational order that is used for receiving are sent to and the corresponding disk of the corresponding disk frame of this disk control module.
Described disk control module be further used for receiving with the corresponding disk frame of this disk control module in the corresponding read-write that disk returned successfully instruct, and the read-write that will receive is successfully instructed and is back to described order transfer unit;
The read-write that described order transfer unit further will receive is successfully instructed and is back to the client that sends read write command.
Described order transfer unit is further used for returning read-write to the client that sends this read write command and finishing instruction receiving after pairing all read-write operations of same read write command successfully instruct.
Further record each disk of the different RAID of composition and the disk frame at each disk place in the described order transfer unit, whether the pairing RAID of read write command that receives in order to judgement is made up of the disk in the different disk frame.
Some disk frame are arranged in the disk chassis, also have a master controller in the described disk chassis, and described order transfer unit and described RAID host computer unit are carried in the described master controller;
Further have the processor that links to each other and link to each other with described master controller in each disk frame, and the pairing RAID computation subunit of each disk frame and disk control module are carried in the processor in this disk frame with some disks in this disk frame.
Described master controller links to each other with client by IP network or optical-fibre channel FC network.
A kind of RAID storage means provided by the invention comprises:
A, judge whether the pairing RAID of read write command receive is made up of the disk in the different disk frame, if, execution in step b then, otherwise execution in step c;
The RAID computational resource that b, utilization are concentrated, carrying out RAID at the read write command that receives calculates, according to RAID result of calculation with this read write command be decomposed in the different disk frame each disk of forming corresponding RAID operational order, and send to respectively and each disk place disk frame, execution in step d then;
C, this read write command is sent to each disk place disk frame of forming corresponding RAID, utilize the RAID computational resource that belongs to this disk frame then, carrying out RAID at the read write command that receives calculates, according to RAID result of calculation this read write command is decomposed into the operational order of each disk in this disk frame, execution in step d then;
D, operational order is sent in the disk frame corresponding disk.
After the described steps d, this method further comprises: e, the read-write that each disk returned successfully instructed be back to the client that sends read write command.
After the described step e, this method further comprises: f, receiving after pairing all read-write operations of same read write command successfully instruct, return read-write to the client that sends this read write command and finish instruction.
Before the described step a, this method further writes down each disk of the different RAID of composition and the disk frame at each disk place, and whether the pairing RAID of read write command that receives in order to judgement is made up of the disk in the different disk frame.
As seen from the above technical solution, the present invention utilizes centralized RAID to calculate with distributed raid and calculates the mode that combines, and uses concentrated RAID computational resource when each disk branch of forming RAID is in the different disk frame, can shares the HotSpare disk of striding disk frame to guarantee the RAID computational resource that belongs to the different disk frame; When each disk of forming RAID all is in a certain disk frame, then use the RAID computational resource that belongs to this disk frame, to share the required computing power of RAID that each disk is formed in this disk frame.
Like this, in the RAID storage system computing power summation of all RAID computational resources can be along with the variation of disk frame quantity respective change, when increasing disk frame, increase the RAID computational resource that belongs to this disk frame, to reduce of the influence of computing power deficiency to system performance; And the RAID computational resource that will belong to this disk frame when reducing disk frame removes, to avoid the idle wasting of resources that is caused owing to the RAID computational resource.
Description of drawings
Fig. 1 is the building-block of logic of existing RAID storage system;
Fig. 2 is the building-block of logic of RAID storage system in the embodiment of the invention;
Fig. 3 is a kind of hardware configuration synoptic diagram of RAID storage system in the embodiment of the invention;
Fig. 4 is the schematic flow sheet of RAID storage means in the embodiment of the invention.
Embodiment
For making purpose of the present invention, technical scheme and advantage clearer, below with reference to the accompanying drawing embodiment that develops simultaneously, the present invention is described in more detail.
In embodiments of the present invention, utilize centralized RAID to calculate and calculate the mode that combines with distributed raid, needs for overall HotSpare disk, when each disk branch of forming RAID is in the different disk frame, use the RAID computational resource of concentrating, can share the HotSpare disk of striding disk frame to guarantee the RAID computational resource that belongs to the different disk frame; And when each disk of forming RAID all is in a certain disk frame, then use the RAID computational resource that belongs to this disk frame, to share the required computing power of RAID that each disk is formed in this disk frame.
Fig. 2 is the building-block of logic of RAID storage system in the embodiment of the invention.As shown in Figure 2, RAID storage system in the present embodiment comprises: order transfer unit, the RAID host computer unit that links to each other with order transfer unit, and some disk frame 1～n one to one RAID computation subunit 1～n and with some disk frame 1～n disk control module 1～n one to one, be corresponding RAID computation subunit i of disk frame i and disk control module i, n is the positive integer greater than 1, and i is greater than 1 and smaller or equal to the positive integer of n.And RAID computation subunit 1～n and disk control module 1～n can be arranged at respectively in disk frame 1～n.
Order transfer unit, be used for judging whether the pairing RAID of the read write command that receives is made up of the disk of different disk frame, if, then this read write command is sent to RAID host computer unit, otherwise this read write command is sent to the corresponding RAID computation subunit of each disk place disk frame of forming corresponding RAID.Alternatively, the order transfer can further record each disk of the different RAID of composition and the disk frame at each disk place in the unit, and whether the pairing RAID of read write command that receives in order to judgement is made up of the disk in the different disk frame.
RAID host computer unit is as the RAID computational resource of concentrating, be used for carrying out RAID and calculate, this read write command is decomposed into the operational order of forming each disk of corresponding RAID in the different disk frame, and sends to respectively and the corresponding disk control module of each disk place disk frame according to RAID result of calculation at the read write command that receives.Wherein, corresponding disk of each operational order.
Each RAID computation subunit is as the RAID computational resource that belongs to corresponding disk frame, be used for carrying out RAID and calculate, this read write command is decomposed into the operational order of each disk in the pairing disk frame of this RAID computation subunit and is sent to and the corresponding disk control module of this disk frame according to RAID result of calculation at the read write command that receives.Wherein, corresponding disk of each operational order.
Each disk control module, be used for to be received from operational order with the corresponding RAID computation subunit of this disk control module, be sent to the corresponding disk frame of this disk control module in corresponding disk, carry out corresponding read-write operation to control corresponding disk; With the operational order branch that is received from RAID host computer unit deliver to the corresponding disk frame of this disk control module in corresponding disk, carry out corresponding read-write operation to control corresponding disk.
In addition, each disk control module also be further used for receiving with the corresponding disk frame of this disk control module in the corresponding read-write that disk returned successfully instruct, and the read-write that will receive is successfully instructed and is back to order transfer unit.Correspondingly, the read-write that order transfer unit is further used for receiving is successfully instructed and is back to the client that sends read write command, and, return read-write to the client that sends this read write command and finish instruction receiving after pairing all read-write operations of same read write command successfully instruct.
Below, lift two examples again and further specify.
Example one:
The read write command that receives at RAID all form by the some disks among the disk frame i, therefore, order transfer unit is sent to RAID computation subunit i with this read write command;
RAID computation subunit i carries out RAID at the read write command that receives and calculates, and according to RAID result of calculation this read write command is decomposed into the operational order of each corresponding disk among the disk frame i and is sent to disk control module i;
Disk control module i is sent to each corresponding disk among the disk frame i respectively with the operational order of each corresponding disk among the disk frame i that receives, and the read-write that each corresponding disk among the disk frame i is returned is successfully instructed and is back to order transfer unit successively then;
The read-write of being returned by each corresponding disk among the disk frame i that order transfer unit will receive is successfully instructed and is back to client successively, and after the read-write that all corresponding disks return in receiving by disk frame i successfully instructs, return read-write to client again and finish instruction.
Example two:
The read write command that receives at RAID in, the part disk is arranged in disk frame i, another part disk then is arranged in disk frame j, therefore, order transfer unit is sent to RAID host computer unit with this read write command;
RAID host computer unit carries out RAID at this read write command and calculates, according to RAID result of calculation this read write command is decomposed into the operational order of each corresponding disk among the operational order of each corresponding disk among the disk frame i and the disk frame j, then the operational order of each corresponding disk among the disk frame i is sent to disk control module i, the operational order of each corresponding disk among the disk frame j is sent to disk control module j;
Disk control module i is sent to each corresponding disk among the disk frame i respectively with the operational order of each corresponding disk among the disk frame i that receives, and the read-write that each corresponding disk among the disk frame i is returned is successfully instructed and is back to order transfer unit successively then;
Disk control module j is sent to each corresponding disk among the disk frame j respectively with the operational order of each corresponding disk among the disk frame j that receives, and the read-write that each corresponding disk among the disk frame j is returned is successfully instructed and is back to order transfer unit successively then;
The read-write of being returned by each corresponding disk among each corresponding disk and the disk frame j among the disk frame i that order transfer unit will receive is successfully instructed and is back to client successively, and the read-write that all corresponding disks return in receiving by disk frame i is successfully instructed and disk frame j in after the read-write returned of all corresponding disks successfully instructs, return read-write to client again and finish instruction.
In RAID storage system as shown in Figure 2,, then can correspondingly increase with it the RAID computational resource that RAID computation subunit conduct one to one belongs to this disk frame if increase by a disk frame; If reduce by a disk frame, then can correspondingly remove with it corresponding one by one, and as the RAID computation subunit that belongs to this disk frame RAID computational resource.Thus, the computing power summation of all RAID computational resources can be along with the variation of disk frame quantity respective change, this variation can be regarded the variation of a linear relationship as.
And, when increasing disk frame, increase the RAID computational resource that belongs to this disk frame, can reduce of the influence of computing power deficiency to system performance; And the RAID computational resource that will belong to this disk frame when reducing disk frame removes, and then can avoid because the idle wasting of resources that is caused of RAID computational resource.
In the practical application, each functional module in the above-mentioned logical organization as shown in Figure 2 can be carried in the disk chassis in the corresponding physical entity.
Fig. 3 is a kind of hardware configuration synoptic diagram of RAID storage system in the embodiment of the invention.As shown in Figure 3, comprise in the disk chassis: the master controller that can receive read write command, and be mounted on some disk frame 1～n under the described master controller, comprise a processor in each disk frame again and be mounted on some disks under this processor, but and the disk combination in any in the identical or different disk frame be different RAID.
Order transfer unit among Fig. 2 and RAID host computer unit can be carried in the master controller so, and RAID computation subunit and disk control module then are carried in the processor in the corresponding disk frame.
Thus, master controller as shown in Figure 3, be used for judging whether the pairing RAID of the read write command that receives is made up of the disk of different disk frame, if, then carry out RAID and calculate, this read write command is decomposed into the operational order of forming each disk of corresponding RAID in the different disk frame, and sends to processor in the different disk frame at each disk place respectively according to RAID result of calculation at the read write command that receives; Otherwise, this read write command is sent to the processor in each disk place disk frame of forming corresponding RAID.
Alternatively; usually can have internal memory in the master controller; thereby can further record each disk of the different RAID of composition and the disk frame at each disk place in the internal memory of master controller, whether the pairing RAID of read write command that receives in order to judgement is made up of the disk in the different disk frame.
Each processor, the operational order that is used for receiving are sent to the corresponding disk of this processor place disk frame; Carry out RAID at the read write command that receives and calculate, this read write command is decomposed into the operational order of each disk of forming corresponding RAID in this processor place disk frame and is sent to disk corresponding in this processor place disk frame according to RAID result of calculation.
In addition, each processor also can be further used for receiving in this processor place disk frame the corresponding read-write that disk returned and successfully instruct, and the read-write that will receive is successfully instructed and is back to master controller.Correspondingly, the read-write that master controller is further used for receiving is successfully instructed and is back to the client that sends read write command, and, return read-write to the client that sends this read write command and finish instruction in that to receive same read write command pairing after all read and write successfully instruction.
And the master controller in the disk chassis as shown in Figure 3, (Internet Protocol, IP) (Fibre Channel, FC) network links to each other with client for network or optical-fibre channel also can to pass through Internet protocol via a memory controller.
It more than is detailed description to RAID storage system in the embodiment of the invention.Below, again the RAID storage means in the embodiment of the invention is described.
Fig. 4 is the schematic flow sheet of RAID storage means in the embodiment of the invention.As shown in Figure 4, the RAID storage means in the present embodiment comprises:
Step 400 judges whether the pairing RAID of read write command that receives is made up of the disk in the different disk frame, if then execution in step 401, otherwise execution in step 404.
Before this step, can further write down each disk of the different RAID of composition and the disk frame at each disk place, whether the pairing RAID of read write command that receives in order to judgement is made up of the disk in the different disk frame.
Step 401, utilize the RAID computational resource of concentrating, carrying out RAID at the read write command that receives calculates, according to RAID result of calculation with this read write command be decomposed in the different disk frame each disk of forming corresponding RAID operational order, and send to respectively and each disk place disk frame, execution in step 402 then.
Step 402 with forming the operational order of each disk of corresponding RAID in the different disk frame, is sent to disk corresponding in each disk frame respectively, and execution in step 403 then.
Step 405 is sent to disk corresponding in this disk frame with the operational order of each disk in the same disk frame, and execution in step 406 then.
So far, above-mentioned flow process finishes.
Need to prove, step 401 in the above-mentioned flow process, 402 can be carried out by the master controller in the disk chassis, step 404,405 is carried out by the processor in the disk frame in the corresponding disk chassis, and each step in the step 403 and 406 then all can successively be carried out by processor in the disk frame in the corresponding disk chassis and the master controller in the disk chassis.And step 403,406 is optional step.
The above is preferred embodiment of the present invention only, is not to be used to limit protection scope of the present invention.Within the spirit and principles in the present invention all, any modification of being done, be equal to and replace and improvement etc., all should be included within protection scope of the present invention.
Claims (10)
1. redundancy array in disc RAID storage system, it is characterized in that, comprise: order transfer unit, the RAID host computer unit that links to each other with order transfer unit, link to each other with order transfer unit and with some disk frame RAID computation subunit one to one, and link to each other with order transfer unit and with some disk frame disk control module one to one, wherein
Order transfer unit, be used for judging whether the pairing RAID of the read write command that receives is made up of the disk of different disk frame, if, then this read write command is sent to RAID host computer unit, otherwise this read write command is sent to the corresponding RAID computation subunit of each disk place disk frame of forming corresponding RAID;
RAID host computer unit, be used for carrying out RAID and calculate, this read write command is decomposed into the operational order of forming each disk of corresponding RAID in the different disk frame, and sends to respectively and the corresponding disk control module of each disk place disk frame according to RAID result of calculation at the read write command that receives;
The RAID computation subunit, be used for carrying out RAID and calculate, this read write command is decomposed into the operational order of each disk in the pairing disk frame of this RAID computation subunit and is sent to and the corresponding disk control module of this disk frame according to RAID result of calculation at the read write command that receives;
Disk control module, the operational order that is used for receiving are sent to and the corresponding disk of the corresponding disk frame of this disk control module.
2. RAID storage system as claimed in claim 1, it is characterized in that, described disk control module be further used for receiving with the corresponding disk frame of this disk control module in the corresponding read-write that disk returned successfully instruct, and the read-write that will receive is successfully instructed and is back to described order transfer unit;
The read-write that described order transfer unit further will receive is successfully instructed and is back to the client that sends read write command.
3. RAID storage system as claimed in claim 2, it is characterized in that, described order transfer unit is further used for returning read-write to the client that sends this read write command and finishing instruction receiving after pairing all read-write operations of same read write command successfully instruct.
4. as each described RAID storage system in the claim 1 to 3, it is characterized in that, further record each disk of the different RAID of composition and the disk frame at each disk place in the described order transfer unit, whether the pairing RAID of read write command that receives in order to judgement is made up of the disk in the different disk frame.
5. as each described RAID storage system in the claim 1 to 3, it is characterized in that, some disk frame are arranged in the disk chassis, also have a master controller in the described disk chassis, and described order transfer unit and described RAID host computer unit are carried in the described master controller;
Further have the processor that links to each other and link to each other with described master controller in each disk frame, and the pairing RAID computation subunit of each disk frame and disk control module are carried in the processor in this disk frame with some disks in this disk frame.
6. RAID storage system as claimed in claim 5 is characterized in that, described master controller links to each other with client by IP network or optical-fibre channel FC network.
7. a redundancy array in disc RAID storage means is characterized in that, comprising:
A, judge whether the pairing RAID of read write command receive is made up of the disk in the different disk frame, if, execution in step b then, otherwise execution in step c;
The RAID computational resource that b, utilization are concentrated, carrying out RAID at the read write command that receives calculates, according to RAID result of calculation with this read write command be decomposed in the different disk frame each disk of forming corresponding RAID operational order, and send to respectively and each disk place disk frame, execution in step d then;
C, this read write command is sent to each disk place disk frame of forming corresponding RAID, utilize the RAID computational resource that belongs to this disk frame then, carrying out RAID at the read write command that receives calculates, according to RAID result of calculation this read write command is decomposed into the operational order of each disk in this disk frame, execution in step d then;
D, operational order is sent in the disk frame corresponding disk.
8. RAID storage means as claimed in claim 7 is characterized in that, after the described steps d, this method further comprises: e, the read-write that each disk returned successfully instructed be back to the client that sends read write command.
9. RAID storage means as claimed in claim 8, it is characterized in that, after the described step e, this method further comprises: f, receiving after pairing all read-write operations of same read write command successfully instruct, return read-write to the client that sends this read write command and finish instruction.
10. as each described RAID storage means in the claim 7 to 9, it is characterized in that, before the described step a, this method further writes down each disk of the different RAID of composition and the disk frame at each disk place, and whether the pairing RAID of read write command that receives in order to judgement is made up of the disk in the different disk frame.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2009100823879A CN101533336B (en) | 2009-04-15 | 2009-04-15 | Redundant array of independent disks memory system and method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2009100823879A CN101533336B (en) | 2009-04-15 | 2009-04-15 | Redundant array of independent disks memory system and method thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN101533336A CN101533336A (en) | 2009-09-16 |
| CN101533336B true CN101533336B (en) | 2010-08-25 |
Family
ID=41103961
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2009100823879A Expired - Fee Related CN101533336B (en) | 2009-04-15 | 2009-04-15 | Redundant array of independent disks memory system and method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101533336B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101714126B (en) * | 2009-12-17 | 2011-12-07 | 成都市华为赛门铁克科技有限公司 | Storage system, method for connecting system and related equipment |
| CN102214073A (en) * | 2010-04-08 | 2011-10-12 | 杭州华三通信技术有限公司 | Hot spare switching control method of redundant array of independent disks (RAID) and controller |
| CN102103468B (en) * | 2010-12-31 | 2013-03-20 | 中国电子科技集团公司第十五研究所 | Multi-disk-cabin hard disk array system consisting of double-layer controller |
| CN103019622B (en) * | 2012-12-04 | 2016-06-29 | 华为技术有限公司 | The storage controlling method of a kind of data, controller, physical hard disk, and system |
| CN105245576B (en) * | 2015-09-10 | 2019-03-19 | 浪潮(北京)电子信息产业有限公司 | A kind of storage architecture system based on complete shared exchange |
| TWI547801B (en) * | 2015-10-22 | 2016-09-01 | Accelstor Inc | Data storage system and method |
| CN117234793B (en) * | 2023-11-14 | 2024-02-23 | 苏州元脑智能科技有限公司 | Data storage method, system, equipment and medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1274010A2 (en) * | 2001-07-02 | 2003-01-08 | Hitachi, Ltd. | Information processing system and storage area allocating method |
| CN1692335A (en) * | 2002-11-01 | 2005-11-02 | 国际商业机器公司 | Method and means for tolerating multiple dependent or arbitrary double disk failures in a disk array |
-
2009
- 2009-04-15 CN CN2009100823879A patent/CN101533336B/en not_active Expired - Fee Related
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1274010A2 (en) * | 2001-07-02 | 2003-01-08 | Hitachi, Ltd. | Information processing system and storage area allocating method |
| CN1692335A (en) * | 2002-11-01 | 2005-11-02 | 国际商业机器公司 | Method and means for tolerating multiple dependent or arbitrary double disk failures in a disk array |
Also Published As
| Publication number | Publication date |
|---|---|
| CN101533336A (en) | 2009-09-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101533336B (en) | Redundant array of independent disks memory system and method thereof | |
| US11444641B2 (en) | Data storage system with enforced fencing | |
| US11169723B2 (en) | Data storage system with metadata check-pointing | |
| US6601138B2 (en) | Apparatus system and method for N-way RAID controller having improved performance and fault tolerance | |
| US11438411B2 (en) | Data storage system with redundant internal networks | |
| US11237772B2 (en) | Data storage system with multi-tier control plane | |
| US8560772B1 (en) | System and method for data migration between high-performance computing architectures and data storage devices | |
| US10514847B2 (en) | Data storage system with multiple durability levels | |
| US6654831B1 (en) | Using multiple controllers together to create data spans | |
| US8751716B2 (en) | Adaptive data throttling for storage controllers | |
| CN101976178B (en) | Method for constructing vertically-arranged and centrally-inspected energy-saving disk arrays | |
| CN101976175A (en) | Method for constructing disk array by horizontal grouping parallel concentrated verification | |
| CN106557143B (en) | Apparatus and method for data storage device | |
| CN105786400A (en) | Heterogeneous hybrid memory module, system and storage method | |
| CN103092786A (en) | Double-control double-active storage control system and method | |
| CN107430494A (en) | Remote Direct Memory accesses | |
| CN106844052A (en) | A kind of method and device that fusion cluster is built based on Windows Server | |
| CN110674539B (en) | Hard disk protection device, method and system | |
| CN101625880B (en) | Control method and control device for realizing data reproduction among redundant arrays of independent disks (RAID) | |
| JP7358613B2 (en) | Method and related equipment for improving reliability of storage systems | |
| JP2003131818A (en) | Configuration of raid among clusters in cluster configuring storage | |
| Nachiappan et al. | Optimized proactive recovery in erasure-coded cloud storage systems | |
| KR102197379B1 (en) | Low-power raid scheduling method for distributed storage application | |
| CN110515536B (en) | Data storage system | |
| CN111338985A (en) | Data reading and writing method and device of service system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CP03 | Change of name, title or address |
Address after: 310052 Binjiang District Changhe Road, Zhejiang, China, No. 466, No. Patentee after: Xinhua three Technology Co., Ltd. Address before: 310053 Hangzhou hi tech Industrial Development Zone, Zhejiang province science and Technology Industrial Park, No. 310 and No. six road, HUAWEI, Hangzhou production base Patentee before: Huasan Communication Technology Co., Ltd. |
|
| CP03 | Change of name, title or address | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20100825 Termination date: 20200415 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |