WO2016058247A1 - 一种块设备输入输出请求调度的方法及装置 - Google Patents

一种块设备输入输出请求调度的方法及装置 Download PDF

Info

Publication number
WO2016058247A1
WO2016058247A1 PCT/CN2014/092691 CN2014092691W WO2016058247A1 WO 2016058247 A1 WO2016058247 A1 WO 2016058247A1 CN 2014092691 W CN2014092691 W CN 2014092691W WO 2016058247 A1 WO2016058247 A1 WO 2016058247A1
Authority
WO
WIPO (PCT)
Prior art keywords
block device
request
output request
device input
generated
Prior art date
Application number
PCT/CN2014/092691
Other languages
English (en)
French (fr)
Inventor
黄凯明
刘文涛
归建章
Original Assignee
深圳市锐明视讯技术有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 深圳市锐明视讯技术有限公司 filed Critical 深圳市锐明视讯技术有限公司
Priority to US15/323,966 priority Critical patent/US10254965B2/en
Priority to EP14904085.9A priority patent/EP3166010A4/en
Publication of WO2016058247A1 publication Critical patent/WO2016058247A1/zh

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
    • G06F3/0601—Interfaces specially adapted for storage systems
    • G06F3/0602—Interfaces specially adapted for storage systems specifically adapted to achieve a particular effect
    • G06F3/061—Improving I/O performance
    • 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
    • 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
    • G06F3/0614—Improving the reliability of storage systems
    • G06F3/0616—Improving the reliability of storage systems in relation to life time, e.g. increasing Mean Time Between Failures [MTBF]
    • 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
    • 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
    • G06F3/0659—Command handling arrangements, e.g. command buffers, queues, command scheduling
    • 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
    • G06F3/0673—Single storage device
    • G06F3/0679—Non-volatile semiconductor memory device, e.g. flash memory, one time programmable memory [OTP]
    • 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
    • G06F3/0688—Non-volatile semiconductor memory arrays
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46—Multiprogramming arrangements
    • G06F9/48—Program initiating; Program switching, e.g. by interrupt
    • G06F9/4806—Task transfer initiation or dispatching
    • G06F9/4843—Task transfer initiation or dispatching by program, e.g. task dispatcher, supervisor, operating system
    • G06F9/4881—Scheduling strategies for dispatcher, e.g. round robin, multi-level priority queues

Definitions

  • the present invention relates to the field of computer memory, and in particular, to a method and apparatus for scheduling input and output requests of a block device.
  • Traditional device operating system (such as Linux and windows) block device input and output scheduling algorithm to optimize the performance of mechanical disk input and output, as far as possible to allow the mechanical head to move continuously in one direction, to reduce the time overhead of mechanical head seek positioning .
  • flash granules Secure Digital Memory
  • Secure Digital Card Secure Digital Card
  • flash granules do not have the overhead of mechanical head seek positioning, but the internal flash memory needs to run garbage collection operations in the background to erase unused data blocks and make room for subsequent write operations.
  • the invention provides a method and a device for scheduling input and output request of a block device, which improves the efficiency of the write operation.
  • the present invention provides a method for scheduling input and output request of a block device, the method comprising:
  • step C1 Determining whether the generated block device input and output request can be merged with the block device input and output request in the request queue, and if not, executing step C1;
  • the generated block device input and output request is sent to the foremost position of the request queue.
  • the present invention provides an apparatus for scheduling input and output request of a block device, the apparatus comprising:
  • a generating module configured to generate a block device input and output request, where the block device input and output request includes a write operation request;
  • a judging module configured to determine whether the generated block device input and output request can be merged with the block device input and output request in the request queue, and if not, step C1 is performed;
  • the sending module is configured to send the generated block device input and output request to a front position of the request queue when the generated destination device of the block device input/output request is a solid state disk or an SD card.
  • the block device input and output request since the block device input and output request is first generated, the block device input and output request includes a write operation request; and then it is determined whether the generated block device input/output request can be merged with the block device input and output request in the request queue, and if not, Then, when the generated destination device of the block device input/output request is a solid state disk or an SD card, the generated block device input and output request is sent to the foremost position of the request queue, thereby improving the efficiency of the write operation.
  • FIG. 1 is a flowchart of a method for scheduling input and output request of a block device according to Embodiment 1 of the present invention
  • FIG. 2 is another flowchart of a method for scheduling input and output request of a block device according to Embodiment 1 of the present invention
  • FIG. 3 is a schematic structural diagram of an apparatus for scheduling input and output request of a block device according to Embodiment 3 of the present invention.
  • FIG. 4 is a schematic structural diagram of a device repair module for inputting and output request scheduling of a block device according to Embodiment 3 of the present invention.
  • Embodiment 1 is a diagrammatic representation of Embodiment 1:
  • Embodiment 1 of the present invention provides a method for scheduling input and output request of a block device.
  • a method for scheduling input and output request of a block device includes the following steps:
  • step 103a It is judged whether the generated block device input/output request can be merged with the block device input/output request in the request queue, and if not, step 103a is performed.
  • step 102 it is determined whether the generated block device input/output request can be combined with the block device input and output request in the request queue, and the specific purpose is: determining whether the generated starting address of the block device input/output request is input and output with the block device in the request queue. Whether the requested end destination address is the same, or whether the generated end destination address of the block device input/output request is the same as the start destination address of the block device input/output request in the request queue.
  • the generated block device input and output request is sent to the foremost position of the request queue.
  • step 102 further includes step 103b.
  • the generated block device input and output request is sorted according to the destination address in sequence with the block device input and output request in the request queue to update the request queue.
  • step 102 further includes step 103c.
  • step 103a further includes step 104a.
  • the file system generates a write operation request with a destination address of 00000 to 0045 H, the destination address of the write operation request in the request queue is 00600 to 006 H 7, it is determined that the generated write operation request cannot be merged with the write operation request in the request queue.
  • the destination device of the generated write operation request is a solid state disk, the generated write operation request is sent to the foremost position of the request queue, and is executed. A write operation request at the foremost position of the request queue.
  • the file system generates a write operation request with a destination address of 00000 to 0045. H, the destination address of the first write operation request in the request queue is 00600 to 006 H 7.
  • the destination address of the second write operation request in the request queue is 00700 to 008F4.
  • the generated destination device of the block device input and output request is a mechanical hard disk
  • the input and output requests of the generated block device are sequentially performed according to the order of the destination address.
  • the block device input and output requests in the request queue are sorted to update the request queue, that is, the write operation request order in the updated request queue is a newly generated write operation request, a first write operation request, and a second write operation request.
  • the file system generates a write operation request with a destination address of 00000 to 0045.
  • the destination address of the write operation request in the request queue is 0045 H to 001H 7.
  • the end destination address of the generated write operation request is the same as the start destination address of the write operation request in the request queue, and the generated write operation request and the write operation request in the request queue are merged into a new write operation request. Its destination address is 00000 to 001 H 7.
  • the block device input and output request includes a write operation request; and then determining whether the generated block device input and output request can be merged with the block device input and output request in the request queue, and if not, then
  • the generated destination device of the block device input and output request is a solid state disk or In the case of the SD card, the generated block device input/output request is sent to the foremost position of the request queue, thereby improving the efficiency of the write operation.
  • Embodiment 2 is a diagrammatic representation of Embodiment 1:
  • the second embodiment of the present invention provides an apparatus for scheduling input and output request of a block device.
  • the apparatus 30 for inputting and outputting request of a block device includes a generating module 310, a determining module 320, and a sending module 330a.
  • a generating module 310 configured to generate a block device input and output request, where the block device input and output request includes a write operation request;
  • the determining module 320 is configured to determine whether the generated block device input and output request can be merged with the block device input and output request in the request queue, and if not, execute step C1;
  • the sending module 330a is configured to send the generated block device input and output request to the foremost position of the request queue when the generated destination device of the block device input/output request is a solid state disk or an SD card.
  • the device 30 for inputting and outputting the request of the block device further includes a sorting module 330b, a merging module 330c, and an executing module 340a.
  • the sorting module 330b is configured to: when the generated destination device of the block device input and output request is a mechanical hard disk, sort and update the generated block device input and output request and the block device input and output request in the request queue according to the order of destination addresses to update Request queue.
  • the merging module 330c is configured to merge the generated block device input and output request with the block device input and output request in the request queue.
  • the execution module 340a is configured to execute a block device input and output request of the foremost position of the request queue.
  • the determining module 320 determines whether the generated block device input/output request can be combined with the block device input and output request in the request queue, and specifically determines whether the generated destination device of the block device input/output request is the same as the block device in the request queue. Whether the end destination address of the input/output request is the same, or whether the end destination address of the generated block device input/output request is the same as the start destination address of the block device input/output request in the request queue.
  • the block device input and output request includes a write operation request; and then determining whether the generated block device input and output request can be merged with the block device input and output request in the request queue, and if not, then
  • the generated destination device of the block device input and output request is a solid state disk or In the case of the SD card, the generated block device input/output request is sent to the foremost position of the request queue, thereby improving the efficiency of the write operation.
  • a person skilled in the art may understand that all or part of the steps of implementing the above embodiments may be completed by hardware, or may be instructed by a program to execute related hardware, and the program may be stored in a computer readable storage medium.
  • the storage medium mentioned may be a read only memory, a magnetic disk or an optical disk or the like.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Human Computer Interaction (AREA)
  • Software Systems (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Signal Processing For Digital Recording And Reproducing (AREA)

Abstract

一种块设备输入输出请求调度的方法及装置，属于计算机存储器领域。首先生成块设备输入输出请求，块设备输入输出请求包括写操作请求（101）；然后判断生成的块设备输入输出请求是否能与请求队列中的块设备输入输出请求合并（102），若否，则当生成的块设备输入输出请求的目的设备是固态盘或SD卡时，将生成的块设备输入输出请求送入请求队列的最前位置（103a）。通过所述块设备输入输出请求调度的方法及装置，提高了写操作的效率。

Description

一种块设备输入输出请求调度的方法及装置 技术领域
本发明涉及计算机存储器领域，特别涉及一种块设备输入输出请求调度的方法及装置。
 背景技术
传统的操作系统（如Linux和windows等）的块设备输入输出调度算法以优化机械磁盘输入输出性能为目标，尽可能地让机械磁头往一个方向连续移动，以减少机械磁头寻道定位的时间开销。
随着技术的发展，采用闪存颗粒的固态硬盘和SD卡（Secure Digital Memory Card，安全数码卡）开始逐渐取代带有机械磁盘磁头的机械磁盘。与机械硬盘的一个主要差别是：闪存颗粒没有机械磁头寻道定位的开销，但闪存内部需要后台运行垃圾回收操作，擦除无用数据块，为后续写入操作预先腾出空间。
在测试中发现，操作系统的块设备调度算法与闪存的垃圾及时回收存在配合冲突问题。表现如下：持续不断地写SD卡，每次写64KB，写地址随机。一段时间后，出现连续的数十次前后相邻写操作耗时均超过3秒，个别写操作耗时甚至长达数十秒。持续1~2分钟后恢复短暂正常，然后又重现。在实时性很强的数据采集应用场景，如此持续时间长的连续耗时过长写操作会导致数据缓冲阻塞，造成严重的实时数据丢失事故。
 技术问题
本发明提供了一种块设备输入输出请求调度的方法及装置，提高了写操作的效率。
 技术解决方案
一方面，本发明提供了一种块设备输入输出请求调度的方法，所述方法包括：
A. 生成块设备输入输出请求，所述块设备输入输出请求包括写操作请求；
B. 判断生成的所述块设备输入输出请求是否能与请求队列中的块设备输入输出请求合并，若否，执行步骤C1；
C1. 当生成的所述块设备输入输出请求的目的设备是固态盘或SD卡时，将生成的所述块设备输入输出请求送入所述请求队列的最前位置。
第二方面，本发明提供了一种块设备输入输出请求调度的装置，所述装置包括：
生成模块，用于生成块设备输入输出请求，所述块设备输入输出请求包括写操作请求；
判断模块，用于判断生成的所述块设备输入输出请求是否能与请求队列中的块设备输入输出请求合并，若否，执行步骤C1；
送入模块，用于当生成的所述块设备输入输出请求的目的设备是固态盘或SD卡时，将生成的所述块设备输入输出请求送入所述请求队列的最前位置。
 有益效果
在本发明中，由于首先生成块设备输入输出请求，块设备输入输出请求包括写操作请求；然后判断生成的块设备输入输出请求是否能与请求队列中的块设备输入输出请求合并，若否，则当生成的块设备输入输出请求的目的设备是固态盘或SD卡时，将生成的块设备输入输出请求送入请求队列的最前位置，因此，提高了写操作的效率。
 附图说明
为了更清楚地说明本发明实施例中的技术方案，下面将对实施例描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本发明的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。
图1为本发明实施例一提供的块设备输入输出请求调度的方法一种流程图；
图2为本发明实施例一提供的块设备输入输出请求调度的方法另一种流程图；
图3为本发明实施例三提供的块设备输入输出请求调度的装置一种结构示意图；
图4为本发明实施例三提供的一种块设备输入输出请求调度的装置修复模块结构示意图。
 本发明的实施方式
为使本发明的目的、技术方案和优点更加清楚，下面将结合附图对本发明实施方式作进一步地详细描述。
实施例一：
本发明实施例一提供了一种块设备输入输出请求调度的方法，参见图1，块设备输入输出请求调度的方法包括以下步骤：
101. 生成块设备输入输出请求，块设备输入输出请求包括写操作请求。
102. 判断生成的块设备输入输出请求是否能与请求队列中的块设备输入输出请求合并，若否，执行步骤103a。
步骤102中判断生成的块设备输入输出请求是否能与请求队列中的块设备输入输出请求合并具体为：判断生成的块设备输入输出请求的起始目的地址是否与请求队列中的块设备输入输出请求的结束目的地址是否相同，或判断生成的块设备输入输出请求的结束目的地址是否与请求队列中的块设备输入输出请求的起始目的地址是否相同。
103a. 当生成的块设备输入输出请求的目的设备是固态盘或SD卡时，将生成的块设备输入输出请求送入请求队列的最前位置。
如图2所示，当步骤102判断为否时，步骤102之后还包括步骤103b。
103b. 当生成的块设备输入输出请求的目的设备是机械硬盘时，按照目的地址的先后顺序对生成的块设备输入输出请求与请求队列中的块设备输入输出请求进行排序以更新请求队列。
如图2所示，当步骤102判断为是时，步骤102之后还包括步骤103c。
103c. 将生成的块设备输入输出请求与请求队列中的块设备输入输出请求合并。
如图2所示，步骤103a之后还包括步骤104a。
104a. 执行请求队列的最前位置的块设备输入输出请求。
例如，文件系统生成写操作请求，目的地址为00000至0045 H，请求队列中的写操作请求的目的地址为00600至006 H 7，则判定生成的写操作请求不能与请求队列中的写操作请求合并，当生成的写操作请求的目的设备是固态盘时，将生成的写操作请求送入请求队列的最前位置，并执行请求队列的最前位置的写操作请求。
再例如，文件系统生成写操作请求，目的地址为00000至0045 H，请求队列中的第一写操作请求的目的地址为00600至006 H 7，请求队列中的第二写操作请求的目的地址为00700至008F4，当生成的块设备输入输出请求的目的设备是机械硬盘时，按照目的地址的先后顺序对生成的块设备输入输出请求与请求队列中的块设备输入输出请求进行排序以更新请求队列，即更新后的请求队列中写操作请求顺序为新生成的写操作请求、第一写操作请求和第二写操作请求。
再例如，文件系统生成写操作请求，目的地址为00000至0045 H，请求队列中的写操作请求的目的地址为0045 H至001H 7，生成的写操作请求的结束目的地址与请求队列中的写操作请求的起始目的地址相同，则将生成的写操作请求与请求队列中的写操作请求合并为一个新的写操作请求，其目的地址为00000至至 001 H 7。
本实施例通过首先生成块设备输入输出请求，块设备输入输出请求包括写操作请求；然后判断生成的块设备输入输出请求是否能与请求队列中的块设备输入输出请求合并，若否，则当生成的块设备输入输出请求的目的设备是固态盘或 SD卡时，将生成的块设备输入输出请求送入请求队列的最前位置，因此，提高了写操作的效率。
实施例二：
本发明实施例二提供了一种块设备输入输出请求调度的装置，如图3所示，块设备输入输出请求调度的装置30包括生成模块310、判断模块320和送入模块330a。
生成模块310，用于生成块设备输入输出请求，块设备输入输出请求包括写操作请求；
判断模块320，用于判断生成的块设备输入输出请求是否能与请求队列中的块设备输入输出请求合并，若否，执行步骤C1；
送入模块330a，用于当生成的块设备输入输出请求的目的设备是固态盘或SD卡时，将生成的块设备输入输出请求送入请求队列的最前位置。
可选的，如图4所示，块设备输入输出请求调度的装置30还包括排序模块330b、合并模块330c和执行模块340a。
排序模块330b，用于当生成的块设备输入输出请求的目的设备是机械硬盘时，按照目的地址的先后顺序对生成的块设备输入输出请求与请求队列中的块设备输入输出请求进行排序以更新请求队列。
合并模块330c，用于将生成的块设备输入输出请求与请求队列中的块设备输入输出请求合并。
执行模块340a，用于执行请求队列的最前位置的块设备输入输出请求。
其中，判断模块320判断生成的块设备输入输出请求是否能与请求队列中的块设备输入输出请求合并具体为：判断生成的块设备输入输出请求的起始目的地址是否与请求队列中的块设备输入输出请求的结束目的地址是否相同，或判断生成的块设备输入输出请求的结束目的地址是否与请求队列中的块设备输入输出请求的起始目的地址是否相同。
本实施例通过首先生成块设备输入输出请求，块设备输入输出请求包括写操作请求；然后判断生成的块设备输入输出请求是否能与请求队列中的块设备输入输出请求合并，若否，则当生成的块设备输入输出请求的目的设备是固态盘或 SD卡时，将生成的块设备输入输出请求送入请求队列的最前位置，因此，提高了写操作的效率。
上述本发明实施例序号仅仅为了描述，不代表实施例的优劣。
本领域普通技术人员可以理解实现上述实施例的全部或部分步骤可以通过硬件来完成，也可以通过程序来指令相关的硬件完成，所述的程序可以存储于一种计算机可读存储介质中，上述提到的存储介质可以是只读存储器，磁盘或光盘等。
以上所述仅为本发明的较佳实施例，并不用以限制本发明，凡在本发明的精神和原则之内，所作的任何修改、等同替换、改进等，均应包含在本发明的保护范围之内。

Claims (10)

  1. 一种块设备输入输出请求调度的方法，其特征在于，所述方法包括：
    A. 生成块设备输入输出请求，所述块设备输入输出请求包括写操作请求；
    B. 判断生成的所述块设备输入输出请求是否能与请求队列中的块设备输入输出请求合并，若否，执行步骤C1；
    C1. 当生成的所述块设备输入输出请求的目的设备是固态盘或SD卡时，将生成的所述块设备输入输出请求送入所述请求队列的最前位置。
  2. 根据权利要求1所述的方法，其特征在于，步骤B判断为否时，所述步骤B之后还包括：
    C2. 当生成的所述块设备输入输出请求的目的设备是机械硬盘时，按照目的地址的先后顺序对生成的所述块设备输入输出请求与所述请求队列中的块设备输入输出请求进行排序以更新所述请求队列。
  3. 根据权利要求1所述的方法，其特征在于，所述步骤B具体为：
    判断生成的所述块设备输入输出请求的起始目的地址是否与请求队列中的块设备输入输出请求的结束目的地址是否相同，或判断生成的所述块设备输入输出请求的结束目的地址是否与请求队列中的块设备输入输出请求的起始目的地址是否相同。
  4. 根据权利要求1所述的方法，其特征在于，所述步骤B判断为是时，所述步骤B之后还包括以下步骤：
    C3. 将生成的所述块设备输入输出请求与所述请求队列中的块设备输入输出请求合并。
  5. 根据权利要求4所述的方法，其特征在于，所述步骤C1之后还包括：
    执行所述请求队列的最前位置的块设备输入输出请求。
  6. 一种块设备输入输出请求调度的装置，其特征在于，所述装置包括：
    生成模块，用于生成块设备输入输出请求，所述块设备输入输出请求包括写操作请求；
    判断模块，用于判断生成的所述块设备输入输出请求是否能与请求队列中的块设备输入输出请求合并，若否，执行步骤C1；
    送入模块，用于当生成的所述块设备输入输出请求的目的设备是固态盘或SD卡时，将生成的所述块设备输入输出请求送入所述请求队列的最前位置。
  7. 根据权利要求6所述的装置，其特征在于，还包括：
    排序模块，用于当生成的所述块设备输入输出请求的目的设备是机械硬盘时，按照目的地址的先后顺序对生成的所述块设备输入输出请求与所述请求队列中的块设备输入输出请求进行排序以更新所述请求队列。
  8. 根据权利要求6所述的装置，其特征在于，所述判断模块判断生成的所述块设备输入输出请求是否能与请求队列中的块设备输入输出请求合并具体为：
    判断生成的所述块设备输入输出请求的起始目的地址是否与请求队列中的块设备输入输出请求的结束目的地址是否相同，或判断生成的所述块设备输入输出请求的结束目的地址是否与请求队列中的块设备输入输出请求的起始目的地址是否相同。
  9. 根据权利要求6所述的装置，其特征在于，还包括：
    合并模块，用于将生成的所述块设备输入输出请求与所述请求队列中的块设备输入输出请求合并。
  10. 根据权利要求6所述的装置，其特征在于，还包括：
    执行模块，用于执行所述请求队列的最前位置的块设备输入输出请求。
PCT/CN2014/092691 2014-10-14 2014-12-01 一种块设备输入输出请求调度的方法及装置 WO2016058247A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
US15/323,966 US10254965B2 (en) 2014-10-14 2014-12-01 Method and apparatus for scheduling block device input/output requests
EP14904085.9A EP3166010A4 (en) 2014-10-14 2014-12-01 Method and apparatus for scheduling block device input/output requests

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201410541441.2 2014-10-14
CN201410541441.2A CN104317656B (zh) 2014-10-14 2014-10-14 一种块设备输入输出请求调度的方法及装置

Publications (1)

Publication Number Publication Date
WO2016058247A1 true WO2016058247A1 (zh) 2016-04-21

Family

ID=52372891

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2014/092691 WO2016058247A1 (zh) 2014-10-14 2014-12-01 一种块设备输入输出请求调度的方法及装置

Country Status (4)

Country Link
US (1) US10254965B2 (zh)
EP (1) EP3166010A4 (zh)
CN (1) CN104317656B (zh)
WO (1) WO2016058247A1 (zh)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106325994B (zh) * 2016-08-24 2018-05-29 广东欧珀移动通信有限公司 一种控制写请求的方法及终端设备
CN107943413B (zh) * 2017-10-12 2021-02-09 记忆科技(深圳)有限公司 一种固态硬盘提升读性能的方法
CN107832020A (zh) * 2017-11-24 2018-03-23 苏州韦科韬信息技术有限公司 一种固态硬盘的写入方法

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101639763A (zh) * 2009-08-27 2010-02-03 中兴通讯股份有限公司 一种io调度方法及调度装置
CN102402401A (zh) * 2011-12-13 2012-04-04 云海创想信息技术（无锡）有限公司 一种磁盘io请求队列调度的方法
CN103823636A (zh) * 2012-11-19 2014-05-28 苏州捷泰科信息技术有限公司 Io调度方法及装置
US20140223071A1 (en) * 2013-02-04 2014-08-07 Lsi Corporation Method and system for reducing write latency in a data storage system by using a command-push model

Family Cites Families (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5430859A (en) * 1991-07-26 1995-07-04 Sundisk Corporation Solid state memory system including plural memory chips and a serialized bus
US5687390A (en) * 1995-11-14 1997-11-11 Eccs, Inc. Hierarchical queues within a storage array (RAID) controller
US6160812A (en) * 1998-05-04 2000-12-12 Cabletron Systems, Inc. Method and apparatus for supplying requests to a scheduler in an input buffered multiport switch
US6490635B1 (en) * 2000-04-28 2002-12-03 Western Digital Technologies, Inc. Conflict detection for queued command handling in disk drive controller
US6954835B1 (en) * 2002-10-30 2005-10-11 Emc Corporation Intercepting control of a host I/O process
US7596670B2 (en) * 2005-11-30 2009-09-29 International Business Machines Corporation Restricting access to improve data availability
US7493419B2 (en) * 2005-12-13 2009-02-17 International Business Machines Corporation Input/output workload fingerprinting for input/output schedulers
CN101354636A (zh) * 2008-09-08 2009-01-28 创新科存储技术（深圳）有限公司 一种向磁盘阵列中写入数据的方法及系统
US8135924B2 (en) * 2009-01-14 2012-03-13 International Business Machines Corporation Data storage device driver
US8078799B2 (en) * 2009-06-10 2011-12-13 Lsi Corporation Method and system of an adaptive input/output scheduler for storage arrays
US8301805B2 (en) * 2009-09-15 2012-10-30 Hewlett-Packard Development Company, L.P. Managing I/O request in a storage system
TW201111986A (en) * 2009-09-29 2011-04-01 Silicon Motion Inc Memory apparatus and data access method for memories
US8732342B1 (en) * 2011-03-31 2014-05-20 Emc Corporation I/O scheduling system and method
US9134909B2 (en) * 2011-08-30 2015-09-15 International Business Machines Corporation Multiple I/O request processing in a storage system
US9116625B2 (en) * 2012-05-11 2015-08-25 Micron Technology, Inc. Write command overlap detection
WO2014002126A1 (en) * 2012-06-25 2014-01-03 Hitachi, Ltd. Computer system and method of controlling i/o with respect to storage apparatus
US9026819B2 (en) * 2012-10-01 2015-05-05 College Of William And Mary Method of conserving power based on electronic device's I/O pattern
CN103064636B (zh) * 2012-12-24 2016-04-13 创新科存储技术有限公司 一种固态硬盘读写方法以及一种固态硬盘

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101639763A (zh) * 2009-08-27 2010-02-03 中兴通讯股份有限公司 一种io调度方法及调度装置
CN102402401A (zh) * 2011-12-13 2012-04-04 云海创想信息技术（无锡）有限公司 一种磁盘io请求队列调度的方法
CN103823636A (zh) * 2012-11-19 2014-05-28 苏州捷泰科信息技术有限公司 Io调度方法及装置
US20140223071A1 (en) * 2013-02-04 2014-08-07 Lsi Corporation Method and system for reducing write latency in a data storage system by using a command-push model

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP3166010A4 *

Also Published As

Publication number Publication date
CN104317656A (zh) 2015-01-28
US10254965B2 (en) 2019-04-09
EP3166010A4 (en) 2018-03-14
US20170206008A1 (en) 2017-07-20
EP3166010A1 (en) 2017-05-10
CN104317656B (zh) 2018-01-16

Similar Documents

Publication Publication Date Title
Dong et al. Data elevator: Low-contention data movement in hierarchical storage system
BR112019015271A2 (pt) rastreamento de hardware distribuído
JP4553936B2 (ja) アウト・オブ・オーダーのｄｍａコマンドキューにおけるコマンド順序の設定に関する技術
WO2019079008A1 (en) LEARNING EXECUTION LIBRARY MACHINE FOR NEURONAL NETWORK ACCELERATION
CN106575206B (zh) 计算机系统中的存储器写入管理
US20130159364A1 (en) Parallel log structured file system collective buffering to achieve a compact representation of scientific and/or dimensional data
CN106663047A (zh) 用于优化的签名比较和数据复制的系统和方法
US9400603B2 (en) Implementing enhanced performance flash memory devices
WO2012159863A1 (en) Storage adapter performance optimization
JP6822274B2 (ja) 情報処理システム、方法、及びプログラム
US11467764B2 (en) NVMe-based data read method, apparatus, and system
WO2016058247A1 (zh) 一种块设备输入输出请求调度的方法及装置
KR101835604B1 (ko) 메모리를 위한 스케줄러
WO2013176376A1 (ko) 칩 레벨 평행 플래시 메모리를 위한 정보 분별 방법 및 장치
WO2020000485A1 (zh) 一种基于NVMe的数据写入方法、装置及系统
Shi et al. A DAG model of synchronous stochastic gradient descent in distributed deep learning
Lee et al. ActiveSort: Efficient external sorting using active SSDs in the MapReduce framework
JP2013061795A (ja) 記憶装置、コントローラ、およびリードコマンド実行方法
Landgraf et al. An overview of the STAR DAQ system
Cong et al. Smem++: A pipelined and time-multiplexed smem seeding accelerator for genome sequencing
CN104462181A (zh) 一种ssd后端数据通路管理加速模块及ssd设备
JP2016029554A (ja) 計算装置、計算方法、および計算プログラム
Liao et al. RIO: Order-Preserving and CPU-Efficient Remote Storage Access
CN115904817A (zh) 分布式数据库并行回放方法、装置、电子设备和存储介质
WO2017082323A1 (ja) 分散処理システム、分散処理装置、方法および記憶媒体

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 14904085

Country of ref document: EP

Kind code of ref document: A1

REEP Request for entry into the european phase

Ref document number: 2014904085

Country of ref document: EP

WWE Wipo information: entry into national phase

Ref document number: 2014904085

Country of ref document: EP

WWE Wipo information: entry into national phase

Ref document number: 15323966

Country of ref document: US

NENP Non-entry into the national phase

Ref country code: DE