CN112230851A - Novel software and hardware cooperation RAID improvement method - Google Patents
Novel software and hardware cooperation RAID improvement method Download PDFInfo
- Publication number
- CN112230851A CN112230851A CN202011095092.8A CN202011095092A CN112230851A CN 112230851 A CN112230851 A CN 112230851A CN 202011095092 A CN202011095092 A CN 202011095092A CN 112230851 A CN112230851 A CN 112230851A
- Authority
- CN
- China
- Prior art keywords
- raid
- module
- board card
- data
- software
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0602—Interfaces specially adapted for storage systems specifically adapted to achieve a particular effect
- G06F3/0604—Improving or facilitating administration, e.g. storage management
- G06F3/0607—Improving or facilitating administration, e.g. storage management by facilitating the process of upgrading existing storage systems, e.g. for improving compatibility between host and storage device
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0628—Interfaces specially adapted for storage systems making use of a particular technique
- G06F3/0629—Configuration or reconfiguration of storage systems
- G06F3/0631—Configuration or reconfiguration of storage systems by allocating resources to storage systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0628—Interfaces specially adapted for storage systems making use of a particular technique
- G06F3/0655—Vertical data movement, i.e. input-output transfer; data movement between one or more hosts and one or more storage devices
- G06F3/0656—Data buffering arrangements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0668—Interfaces specially adapted for storage systems adopting a particular infrastructure
- G06F3/0671—In-line storage system
- G06F3/0683—Plurality of storage devices
- G06F3/0689—Disk arrays, e.g. RAID, JBOD
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Debugging And Monitoring (AREA)
Abstract
The invention relates to a novel software and hardware cooperation RAID improvement method, and belongs to the field of hard disk arrays. According to the invention, a RAID software calculating module and a monitoring module are added at a computer host terminal, a data path 2 and a counting module are added at a RAID board card terminal, the current CPU load is monitored by the monitoring module, when the CPU load is low, RAID calculation processing is carried out by using the RAID software calculating module, and a calculation result is transmitted to a cache module through the data path 2, in addition, whether the data amount in the cache module is more than or equal to the total data amount (L +1) or not is calculated by the counting module, and if the data amount is more than or equal to the total data amount (L +1), calculation is stopped, and repeated calculation is prevented. Because the data calculation module of the RAID board card and the RAID software calculation module are used for simultaneous calculation, the RAID calculation processing speed is increased, and the residual CPU resources are utilized. The invention realizes faster RAID performance by matching software with the RAID board card, and does not cause the shortage of CPU resources at the computer end.
Description
Technical Field
The invention belongs to the technical field of hard disk arrays, and particularly relates to a novel software and hardware cooperation RAID improvement method.
Background
Raid (redundant Array of Independent disks) technology is also called redundant Array of Independent hard disks (raid Array) technology, and it is intended to combine a plurality of inexpensive small hard disks to replace expensive large-capacity hard disks, and at the same time, it is ensured that the correctness of data is not affected after a single hard disk is damaged. Through continuous development, the RAID technology can provide a perfect storage device solution, and while the capacity of the hard disk is increased, the speed of the hard disk can be sufficiently increased, so that data is safer, and the hard disk is easier to manage. Due to the high reliability and high fault tolerance of data in RAID technology, RAID technology has a wide application in military storage systems.
The RAID board is a hardware board that can perform RAID calculation. The computer is inserted into the RAID board card, and the hard disk is connected to the RAID board card, so that the RAID function can be realized. The computer and the RAID interface card are connected through a pcie interface, and the RAID interface card is externally connected to a hard disk constituting a RAID array, as shown in fig. 1. The RAID interface card is responsible for realizing all RAID algorithms, external hard disks are organized into RAID arrays, the workload of a host computer at a computer end is reduced, the operation efficiency is improved, and the computer end sees that the RAID board card and the external hard disks are complete hard disks.
The data flow of the conventional RAID implementation by means of RAID cards is shown in fig. 2. Data flows between the memory of the computer host and the hard disk. The data circulation path comprises a PCIE interface, a RAID board data processing path, a cache module of the RAID board and an SATA interface.
The traditional RAID implementation mode has the advantage of not occupying the computing resources of the computer host, and the performance of the RAID only depends on the hardware performance of the RAID board card, but not on the performance of the computer host. However, the traditional RAID implementation method can only make full use of the hardware capability of the RAID board, but cannot limit full use of the hardware capability of the entire RAID platform by means of the remaining performance of the computer host, and cannot maximize the RAID performance.
Disclosure of Invention
Technical problem to be solved
The invention aims to solve the technical problem of how to provide a novel software and hardware cooperation RAID improvement method so as to solve the problems that the existing RAID implementation mode cannot limit the full utilization of the hardware performance of the whole set of RAID platform and cannot maximize the RAID performance by means of the residual performance of a computer host.
(II) technical scheme
In order to solve the technical problems, the invention provides a novel software and hardware cooperation RAID improvement method, which is applied to an RAID improvement system, wherein the system comprises a computer host end, an RAID board card and a hard disk forming an RAID array, the computer host end is connected with the RAID board card through a pci interface, and the RAID board card is externally connected with the hard disk forming the RAID array; a data flow path is arranged between the memory of the host and the hard disk, and comprises a RAID board card data path 1 consisting of a PCIE interface, a storage module and a data calculation module, and a cache module of the RAID board card; the computer host end also comprises an RAID software calculation module and a monitoring module, the RAID board card also comprises a data path 2 and a counting module, a 2 nd data flow path is formed between the memory of the host and the hard disk, and the data flow path comprises the RAID software calculation module, a PCIE interface, the RAID board card data path 2 and a cache module of the RAID board card; meanwhile, the RAID software calculation module is connected to the monitoring module, and the counting module is connected with the data calculation module of the RAID board card and the cache module of the RAID board card through a PCIE interface and the RAID software calculation module, and the method comprises the following steps:
s1, the computer host side transmits the address addr of data to be transmitted and the storage address of the relevant information with the length L +1 to the RAID board card, and the RAID board card receives the information address and then fetches data from the addr address in the memory through the PCIE interface;
s2, the RAID board card stores the data in the storage module on the board card, then the data calculation module of the RAID board card starts to carry out RAID operation on the data, and the result is stored in the cache module of the RAID board card;
s3, the monitoring module at the computer host side measures the current cpu load, if a cpu core is in a low load state, the RAID software computing module is informed to reversely perform RAID computing processing from the data of addr + L address, and the processed data reaches the cache module of the RAID board card through a PCIE interface and a data path 2;
and S4, calculating whether the data volume in the cache module is greater than or equal to total data volume L +1 by the counting module of the RAID board card, if so, stopping the RAID software calculating module at the host computer end and the data calculating module at the RAID board card end, and writing data into a hard disk, otherwise, continuing to wait.
(III) advantageous effects
The invention provides a novel software and hardware cooperation RAID improvement method, which is characterized in that a RAID software calculation module and a monitoring module are added at the end of a computer host, a data path 2 and a counting module are added at the end of a RAID board card, the current CPU load can be monitored through the monitoring module, when the CPU load is lower, the RAID software calculation module can be used for carrying out RAID calculation processing, in order to avoid the conflict with the RAID calculation processing carried out by the data calculation module of the RAID board card, the RAID software calculation module starts to calculate from the tail part of a memory of the host and transmits the calculation result to a cache module through the data path 2, and because the data calculation module of the RAID board card and the RAID software calculation module carry out calculation processing at the same time, the RAID calculation processing speed is accelerated, and the residual CPU resource is utilized. The counting module calculates whether the data amount in the cache module is equal to or greater than the total data amount (L +1), and stops the calculation to prevent the repeated calculation if the data amount is equal to or greater than the total data amount (L + 1). The invention realizes faster RAID performance by matching software with the RAID board card, and does not cause the shortage of CPU resources at the computer end.
Drawings
FIG. 1 is a conventional RAID board connection diagram;
FIG. 2 is a conventional RAID board design;
fig. 3 is a diagram of the new software and hardware cooperating RAID improvement of the present invention.
Detailed Description
In order to make the objects, contents and advantages of the present invention clearer, the following detailed description of the embodiments of the present invention will be made in conjunction with the accompanying drawings and examples.
As shown in fig. 3, the present invention provides a novel software and hardware cooperation RAID system, which can implement faster RAID performance by matching software with a RAID board, and does not cause CPU resource shortage at a computer end.
The novel software and hardware cooperative RAID system proposed by the present patent is shown in fig. 3. The computer host end is inserted with an RAID board card, a hard disk is connected to the RAID board card, the computer host end is connected with the RAID board card through a pcie interface, and the RAID board card is externally connected with the hard disk to form an RAID array. A data flow path is arranged between the memory of the host and the hard disk, and comprises a PCIE interface, a RAID board card data path 1, a cache module of the RAID board card and an SATA interface. The RAID board data path 1 comprises a storage module and a data calculation module.
The technical frame is additionally provided with a RAID software calculation module and a monitoring module at the computer host end, and a data path 2 and a counting module at the RAID board card end. And a 2 nd data flow path is formed from the memory of the host computer to the hard disk, and the data flow path comprises a RAID software calculation module, a PCIE interface, a RAID board card data path 2, a cache module of a RAID board card and a SATA interface. Meanwhile, the RAID software calculation module is connected to the monitoring module, the counting module is connected with the data calculation module of the RAID board card, and the counting module is also connected with the cache module of the RAID board card and connected with the RAID software calculation module through a PCIE interface.
The monitoring module is used for measuring the current cpu load by the monitoring module, and if a cpu core is in a low-load state, the monitoring module informs the RAID software computing module to perform RAID computing processing;
the RAID software calculation module is used for receiving the notification of the monitoring module, starting to reversely perform RAID calculation processing from the data of the (addr + L) address, and sending the processed data to the RAID board card cache module through the PCIE interface and the data path 2;
the counting module calculates whether the data volume in the cache module is larger than or equal to the total data volume (L +1), if so, the counting module sends signals to the RAID software calculating module at the host computer end and the data calculating module at the RAID board card end, stops the RAID software calculating module at the host computer end and the data calculating module at the RAID board card end, and writes the data into the hard disk, otherwise, the counting module continues to wait.
Through the addition of the modules and the cooperation of a software algorithm, a RAID technical scheme with better performance can be realized.
The patent provides a novel software and hardware cooperation RAID algorithm, the algorithm can realize faster RAID performance by matching software with an RAID board card, and the shortage of CPU resources at a computer end can not be caused.
The data flow of the novel software and hardware cooperated RAID algorithm strategy proposed by the patent is shown in FIG. 3.
The novel software and hardware cooperation RAID improvement method provided by the patent comprises the following steps:
the computer host transmits the address addr of data to be sent and the storage address of the relevant information with the length L +1 to the RAID board card, and the RAID board card receives the information address and then fetches data from the address addr in the memory through the PCIE interface;
the RAID board card stores data in a storage module on the board card, then a data calculation module of the RAID board card starts to perform RAID operation on the data, and the result is stored in a cache module of the RAID board card;
a monitoring module at the computer host end measures the current cpu load, if a cpu core is in a low-load state, a RAID software computing module is notified to perform RAID computing processing in the reverse direction from data of an address (addr + L), and the processed data reaches a RAID board card cache module through a PCIE interface and a data path 2;
and the counting module of the RAID board card calculates whether the data volume in the cache module is more than or equal to the total data volume (L +1), if so, the RAID software calculating module at the host computer end and the data calculating module at the RAID board card end are stopped, and the data are written into the hard disk, otherwise, the waiting is continued.
The above description is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, several modifications and variations can be made without departing from the technical principle of the present invention, and these modifications and variations should also be regarded as the protection scope of the present invention.
Claims (1)
1. A novel software and hardware cooperation RAID improvement method is characterized in that the method is applied to an RAID improvement system, the system comprises a computer host side, an RAID board card and a hard disk forming an RAID array, the computer host side is connected with the RAID board card through a pci interface, and the RAID board card is externally connected with the hard disk forming the RAID array; a data flow path is arranged between the memory of the host and the hard disk, and comprises a RAID board card data path 1 consisting of a PCIE interface, a storage module and a data calculation module, and a cache module of the RAID board card; the computer host end also comprises an RAID software calculation module and a monitoring module, the RAID board card also comprises a data path 2 and a counting module, a 2 nd data flow path is formed between the memory of the host and the hard disk, and the data flow path comprises the RAID software calculation module, a PCIE interface, the RAID board card data path 2 and a cache module of the RAID board card; meanwhile, the RAID software calculation module is connected to the monitoring module, and the counting module is connected with the data calculation module of the RAID board card and the cache module of the RAID board card through a PCIE interface and the RAID software calculation module, and the method comprises the following steps:
s1, the computer host side transmits the address addr of data to be transmitted and the storage address of the relevant information with the length L +1 to the RAID board card, and the RAID board card receives the information address and then fetches data from the addr address in the memory through the PCIE interface;
s2, the RAID board card stores the data in the storage module on the board card, then the data calculation module of the RAID board card starts to carry out RAID operation on the data, and the result is stored in the cache module of the RAID board card;
s3, the monitoring module at the computer host side measures the current cpu load, if a cpu core is in a low load state, the RAID software computing module is informed to reversely perform RAID computing processing from the data of addr + L address, and the processed data reaches the cache module of the RAID board card through a PCIE interface and a data path 2;
and S4, calculating whether the data volume in the cache module is greater than or equal to total data volume L +1 by the counting module of the RAID board card, if so, stopping the RAID software calculating module at the host computer end and the data calculating module at the RAID board card end, and writing data into a hard disk, otherwise, continuing to wait.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011095092.8A CN112230851A (en) | 2020-10-14 | 2020-10-14 | Novel software and hardware cooperation RAID improvement method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011095092.8A CN112230851A (en) | 2020-10-14 | 2020-10-14 | Novel software and hardware cooperation RAID improvement method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112230851A true CN112230851A (en) | 2021-01-15 |
Family
ID=74112550
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011095092.8A Pending CN112230851A (en) | 2020-10-14 | 2020-10-14 | Novel software and hardware cooperation RAID improvement method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112230851A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102122235A (en) * | 2011-01-24 | 2011-07-13 | 武汉固捷联讯科技有限公司 | RAID4 (redundant array of independent disks) system and data reading and writing method thereof |
| WO2016141785A1 (en) * | 2015-03-11 | 2016-09-15 | 中兴通讯股份有限公司 | Processing method and apparatus for high-performance redundant array of inexpensive disks (raid) mechanism |
| CN107239825A (en) * | 2016-08-22 | 2017-10-10 | 北京深鉴智能科技有限公司 | Consider the deep neural network compression method of load balancing |
| CN109358809A (en) * | 2018-09-28 | 2019-02-19 | 方信息科技（上海）有限公司 | A kind of RAID data storage system and method |
| CN110515040A (en) * | 2019-08-23 | 2019-11-29 | 睿清电子技术(南京)有限公司 | A kind of radar transmit-receive simulation integrated system and its application |
| CN112783684A (en) * | 2019-11-06 | 2021-05-11 | 华为技术有限公司 | Check data calculation method and device |
-
2020
- 2020-10-14 CN CN202011095092.8A patent/CN112230851A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102122235A (en) * | 2011-01-24 | 2011-07-13 | 武汉固捷联讯科技有限公司 | RAID4 (redundant array of independent disks) system and data reading and writing method thereof |
| WO2016141785A1 (en) * | 2015-03-11 | 2016-09-15 | 中兴通讯股份有限公司 | Processing method and apparatus for high-performance redundant array of inexpensive disks (raid) mechanism |
| CN107239825A (en) * | 2016-08-22 | 2017-10-10 | 北京深鉴智能科技有限公司 | Consider the deep neural network compression method of load balancing |
| CN109358809A (en) * | 2018-09-28 | 2019-02-19 | 方信息科技（上海）有限公司 | A kind of RAID data storage system and method |
| CN110515040A (en) * | 2019-08-23 | 2019-11-29 | 睿清电子技术(南京)有限公司 | A kind of radar transmit-receive simulation integrated system and its application |
| CN112783684A (en) * | 2019-11-06 | 2021-05-11 | 华为技术有限公司 | Check data calculation method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103002046B (en) | Multi-system data copying remote direct memory access (RDMA) framework | |
| US20140006742A1 (en) | Storage device and write completion notification method | |
| CN105045531A (en) | Buffer synchronization mechanism between double storage controllers | |
| CN103403667A (en) | Data processing method and device | |
| CN104317770A (en) | Data storage structure and data access method for multiple core processing system | |
| US11126367B2 (en) | Storage system and method for determining ecosystem bottlenecks and suggesting improvements | |
| CN103488582A (en) | Method and device for writing cache memory | |
| CN116719764B (en) | Data synchronization method, system and related device | |
| CN112230851A (en) | Novel software and hardware cooperation RAID improvement method | |
| CN112214095A (en) | Method and equipment for controlling power consumption of hard disk | |
| CN112286447A (en) | Novel software and hardware cooperation RAID improvement system | |
| CN212084122U (en) | NVMe controller | |
| CN210155650U (en) | Solid state hard disk controller | |
| CN111338567B (en) | Mirror image caching method based on Protocol Buffer | |
| CN210129223U (en) | RAID adapter plate and system for realizing RAID | |
| US20220171569A1 (en) | Data storage device and operating method thereof | |
| CN111860821B (en) | Control method and system for data transmission of data flow architecture neural network chip | |
| CN103049218A (en) | Data storage method and controller | |
| US10747615B2 (en) | Method and apparatus for non-volatile memory array improvement using a command aggregation circuit | |
| CN104025198A (en) | Phase Change Memory with Switch (PCMS) write error detection | |
| CN103064762A (en) | Method and device for recovering deleted backup data | |
| CN116601616A (en) | Data processing device, method and related equipment | |
| CN108334459B (en) | Implementation scheme of multi-port solid state disk | |
| CN109783034A (en) | A kind of method and its system promoting disk array treatment effeciency | |
| CN117591036B (en) | Bit occupation data filling method and system based on firmware and chip microkernel |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210115 |
|
| RJ01 | Rejection of invention patent application after publication |