WO2021259194A1 - 一种存储设备 - Google Patents

一种存储设备 Download PDF

Info

Publication number
WO2021259194A1
WO2021259194A1 PCT/CN2021/101211 CN2021101211W WO2021259194A1 WO 2021259194 A1 WO2021259194 A1 WO 2021259194A1 CN 2021101211 W CN2021101211 W CN 2021101211W WO 2021259194 A1 WO2021259194 A1 WO 2021259194A1
Authority
WO
WIPO (PCT)
Prior art keywords
hard disk
board
storage device
cascade
backplane
Prior art date
Application number
PCT/CN2021/101211
Other languages
English (en)
French (fr)
Inventor
金勇臣
罗飞
王国宇
陈明
唐银中
Original Assignee
华为技术有限公司
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 华为技术有限公司 filed Critical 华为技术有限公司
Priority to EP21828891.8A priority Critical patent/EP4152325A4/en
Publication of WO2021259194A1 publication Critical patent/WO2021259194A1/zh
Priority to US18/083,694 priority patent/US20230124534A1/en

Links

Images

Classifications

    • G—PHYSICS
    • G11—INFORMATION STORAGE
    • G11B—INFORMATION STORAGE BASED ON RELATIVE MOVEMENT BETWEEN RECORD CARRIER AND TRANSDUCER
    • G11B33/00—Constructional parts, details or accessories not provided for in the other groups of this subclass
    • G11B33/12—Disposition of constructional parts in the apparatus, e.g. of power supply, of modules
    • G11B33/125—Disposition of constructional parts in the apparatus, e.g. of power supply, of modules the apparatus comprising a plurality of recording/reproducing devices, e.g. modular arrangements, arrays of disc drives
    • G11B33/126—Arrangements for providing electrical connections, e.g. connectors, cables, switches
    • G—PHYSICS
    • G11—INFORMATION STORAGE
    • G11B—INFORMATION STORAGE BASED ON RELATIVE MOVEMENT BETWEEN RECORD CARRIER AND TRANSDUCER
    • G11B33/00—Constructional parts, details or accessories not provided for in the other groups of this subclass
    • G11B33/02—Cabinets; Cases; Stands; Disposition of apparatus therein or thereon
    • G11B33/04—Cabinets; Cases; Stands; Disposition of apparatus therein or thereon modified to store record carriers
    • G11B33/0405—Cabinets; Cases; Stands; Disposition of apparatus therein or thereon modified to store record carriers for storing discs
    • G11B33/0433—Multiple disc containers
    • G—PHYSICS
    • G11—INFORMATION STORAGE
    • G11B—INFORMATION STORAGE BASED ON RELATIVE MOVEMENT BETWEEN RECORD CARRIER AND TRANSDUCER
    • G11B33/00—Constructional parts, details or accessories not provided for in the other groups of this subclass
    • G11B33/14—Reducing influence of physical parameters, e.g. temperature change, moisture, dust
    • G11B33/1406—Reducing the influence of the temperature
    • G11B33/1413—Reducing the influence of the temperature by fluid cooling
    • G11B33/142—Reducing the influence of the temperature by fluid cooling by air cooling

Definitions

  • the embodiments of the present application relate to the field of storage technology, and in particular to a storage device.
  • HDD high-density hard disk drives
  • Expander (expander) plus hard disk array is a typical architecture of high-density HDD.
  • Expanders mainly exist in two forms in high-density HDDs.
  • FRU field replaceable unit
  • the expander When the expander is used as a FRU, it can also be called a level. Union board.
  • the expander When the expander is directly soldered on the PCB board, the expander has a smaller size and flexible layout position, which can reduce the difficulty of the realization of the whole machine structure and shorten the length of the high-speed link. But when the expander chip fails, or the whole machine needs to be upgraded and evolved, the hard disk backplane or even the whole machine must be replaced.
  • the expander When the expander is used as an independent FRU, although it is easy to maintain, the FRU layout location is limited by the structure of the whole machine, and it is difficult to shorten the high-speed link, which leads to an increase in the cost of PCB boards and drivers.
  • the present application provides a storage device with a novel cascading board architecture, which can reduce the cost of the storage device and improve the maintainability of the storage device.
  • a storage device which includes a hard disk backplane, a first cascade board, and a hard disk array, wherein the hard disk array includes a plurality of hard disks; the hard disk array is located on the first side of the hard disk backplane; the first cascade board is Field replaceable unit FRU, the first expansion board is located on the second side of the hard disk backplane.
  • the cascade board and the hard disk array are located on both sides of the hard disk backplane.
  • the cascade board neither occupies the hard disk slot nor affects the capacity of the storage device, nor does it squeeze the gap of the hard disk array and reduce the storage device.
  • the expansion board of the storage device is FRU, which can be replaced at any time for easy maintenance.
  • the storage device includes a second cascade board, the second cascade board is located on the second side of the hard disk backplane, the hard disk array includes a first hard disk area and a second hard disk area, the first cascade board The board manages the first hard disk area, and the second cascade board manages the second hard disk area.
  • the hard disk array can be managed regionally.
  • Each expansion board manages the nearby hard disk array area, shortening the length of the high-speed link between the expansion board and the hard disk backplane.
  • the first cascade board is located at the center of the first hard disk area; the second cascade board is located at the center of the second hard disk area.
  • the link distance between the farthest hard disk in each hard disk area and the expansion board can be further shortened.
  • the first cascade board is pluggably installed on the second side of the hard disk backplane.
  • the second cascade board is pluggably installed on the second side of the hard disk backplane.
  • the cascade board of the storage device can be easily pulled out and inserted from the side of the storage device, which facilitates the replacement of the cascade board, and improves the maintainability of the storage system.
  • the first cascade board has an expander chip.
  • an expander chip is provided on the second cascade board.
  • first side and the second side are the upper side and the lower side of the hard disk backplane, respectively.
  • first side and the second side are the lower side and the upper side of the hard disk backplane, respectively.
  • first side and the second side are the left and right sides of the hard disk backplane, respectively.
  • first side and the second side are the right and left sides of the hard disk backplane, respectively.
  • Fig. 1 is an architecture intention of a cascade board in the prior art.
  • Fig. 2 is a schematic diagram of another cascade board architecture in the prior art.
  • FIG. 3 is a schematic diagram of another cascade board architecture in the prior art.
  • Fig. 4 is a schematic structural diagram of a storage device according to an embodiment of the present application.
  • Fig. 5 is a side view of a storage device according to an embodiment of the present application.
  • Fig. 6 is a top view of a storage device according to an embodiment of the present application.
  • Fig. 7 is a top view of another storage device according to an embodiment of the present application.
  • FIG. 8 is a schematic diagram of plugging and unplugging a cascade board of a storage device according to an embodiment of the present application.
  • High-density hard disk drives have a wide range of applications in the storage field. Machine capacity, unit density, cost, and maintainability are the key competitiveness of high-density HDDs.
  • Expander (expander) plus hard disk array is a typical architecture of high-density HDD.
  • Expanders mainly exist in two forms. One is that the expander is directly soldered on a printed circuit board (PCB), and the other is that the expander exists as an independent field replaceable unit (FRU). When the expander is used as an independent FRU, it can be called a cascade board in the storage device.
  • PCB printed circuit board
  • FRU field replaceable unit
  • storage devices mainly have the following cascading board architectures.
  • Method 1 The expansion board is located on one side of the hard disk array in a flat insertion mode.
  • Figure 1 provides a schematic diagram of a cascade board architecture.
  • (A) in FIG. 1 is a side view of a storage device adopting the cascading board architecture of mode one
  • (b) in FIG. 1 is a top view of a storage device adopting the cascading board architecture of mode one.
  • the cascade board 130 and the hard disk array are both located on the same side of the hard disk backplane 110.
  • the expansion board 130 is connected to the hard disk backplane 110 in a flat insertion manner.
  • FIG. 1(b) when this cascade board architecture is adopted, the high-speed link 140 is longer.
  • the cascading board architecture of mode one is suitable for 3G small computer system interface (SCSI) (serial attached SCSI, SAS) scenarios.
  • SCSI serial attached SCSI
  • SAS serial attached SCSI
  • the main reason is that the 3G SAS scenario has a low rate and strong link insertion. Loss tolerance, even if the link is long, has less impact on the board selection.
  • SATA serial advanced technology attachment
  • the hard disk backplane must use low loss (low loss) Loss level, even very low loss (very low loss) level of panels, the cost of panels is higher.
  • the hard disk backplane needs to add drives, which affects the passive characteristics of the backplane and increases the possibility of failure of the backplane.
  • Method 2 The expansion board occupies the hard disk slot.
  • FIG. 2 provides a schematic diagram of another cascade board architecture.
  • FIG. 2 is a top view of the cascaded board structure of the second method.
  • the cascade board 130 and the hard disk array are located on the same side of the hard disk backplane 110.
  • the cascade board is installed in the hard disk array with a vertical fork, which occupies the slot of the hard disk array.
  • the high-speed link length is relatively shorter under the cascade board architecture of the second method.
  • the cascade board occupies the hard disk slot, it has a greater impact on the hard disk density and capacity of the whole machine.
  • the cascade board will be further split.
  • two cascade boards occupy two hard disk slots. If the height link length is shortened by adding cascade boards (for example, 4 cascade boards are used), more hard disks will be occupied The slot position has a greater impact on the capacity of the whole machine.
  • the high link length has been improved compared to the first method, for 6G SATA hard disks, low-loss or even very low-loss tier plates are still required, and the cost is relatively high.
  • Method 3 Insert the expansion board vertically on both sides of the hard disk array.
  • FIG. 3 is a schematic diagram that provides another cascade board architecture.
  • FIG. 3 is a top view of the cascade board structure of the third mode.
  • the cascade board 130 and the hard disk array are located on the same side of the hard disk backplane 110.
  • the cascade board 130 is arranged on both sides of the hard disk array in a vertical insertion manner.
  • the cascading board architecture of Mode 3 does not occupy the hard disk slot and does not affect the capacity of the whole machine.
  • the length of the high-speed link 140 is between Mode 1 and Mode 2, but for higher specification hard drives, such as 6G SATA specification hard drives, low loss or even very low loss levels are still required.
  • the cascade board needs to be arranged on both sides of the hard disk array, when the area of the hard disk backplane is certain, the gap of the hard disk array may be squeezed, which affects the heat dissipation of the hard disk 120 and increases the heat dissipation cost.
  • Fig. 4 is a schematic structural diagram of a storage device according to an embodiment of the present application.
  • the storage device of the embodiment of the present application includes a hard disk backplane 410, an array hard disk including a plurality of hard disks 420, and a cascade board 430 (for example, a first cascade board).
  • the hard disk array is located on the first side of the hard disk backplane.
  • the cascade board 430 is located on the second side of the hard disk backplane 410, and the cascade board 430 is an FRU.
  • the storage device shown in FIG. 4 only shows two cascade boards 430. In other embodiments, the storage device may also include other numbers of cascade boards (for example, second cascade boards). The embodiment of the present application does not limit the number of cascade boards.
  • the cascade board 430 may include an expander chip.
  • the hard disk backplane 410 is arranged horizontally, and the hard disk array including a plurality of hard disks 420 and the cascade board 430 are respectively located on the upper and lower sides of the horizontal hard disk backplane.
  • the hard disk backplane can also be placed vertically. In this case, the hard disk array and the cascade board are respectively located on the left and right sides of the hard disk backplane.
  • Fig. 5 is a side view of the storage device shown in Fig. 4. As shown in FIG. 5, a hard disk array including a plurality of hard disks 420 is located on the first side of the hard disk backplane 410, and the cascade board 430 is located on the second side of the hard disk backplane 410, wherein the cascade board 430 includes an expander chip.
  • the first side and the second side of the hard disk backplane are opposite sides, such as the left side and the right side, or the upper side and the lower side, or the right side and the left side, or the lower side and the upper side .
  • an implementation scheme is that the cascade board includes the expander chip and its related components to form an FRU.
  • the cascade board can be an FRU, which can realize the passive hard disk backplane and reduce the overall storage device Failure Rate.
  • the cascade board and the hard disk array are located on both sides of the hard disk backplane.
  • the cascade board neither occupies the hard disk slot nor affects the capacity of the storage device, nor squeezes the gap of the hard disk array, and does not affect the heat dissipation of the storage device. .
  • the expander chip is an independent FRU, only the cascade board needs to be replaced when the expander chip needs to be replaced, which improves the maintainability of the storage device.
  • the storage device may include multiple cascade boards, and the expander of each cascade board manages an area of the hard disk array.
  • the storage device includes 4 cascade boards.
  • Fig. 6 is a top view of a storage device including four cascade boards. Since the expansion board is located on the other side of the hard disk backplane, the hard disk array on the first side of the hard disk backplane is represented by a solid line, and the expansion board on the second side of the hard disk backplane is represented by a dashed line.
  • the storage device includes 4 expansion boards, the hard disk array is divided into 4 areas, and each expansion board manages the hard disk area closest to the expansion board. For example, cascade board 1 manages hard disk area 1, cascade board 2 manages hard disk area 2, cascade board 3 manages hard disk area 3, and cascade board 4 manages hard disk area 4.
  • FIG. 6 is only an example of multiple cascade boards.
  • the storage device in the embodiment of the present application may also include other numbers of cascade boards, and the embodiment of the present application also divides the hard disk area managed by the cascade board. Not limited.
  • the hard disk array can be managed regionally.
  • Each cascade board manages the nearby hard disk array area, which shortens the length of the high-speed link between the cascade board and the hard disk backplane.
  • FIG. 7 is a top view of another storage device including four cascade boards in an embodiment of the present application.
  • the storage device includes 4 expansion boards, the hard disk array is divided into 4 areas, and each expansion board manages the hard disk area closest to the expansion board.
  • cascade board 1 manages hard disk area 1
  • cascade board 2 manages hard disk area 2
  • cascade board 3 manages hard disk area 3
  • cascade board 4 manages hard disk area 4.
  • each expansion board is located in the center of the corresponding hard disk area.
  • the expansion board 1 is located in the center of the hard disk area 1.
  • the cascade board and the hard disk array are respectively located on both sides of the hard disk backplane, the cascade board is spatially decoupled from the hard disk array, so that the position of the cascade board can be flexibly changed without being connected to the hard disk.
  • Array interference greatly shortens the link length from the expansion board to the remote hard disk slot.
  • FIG. 8 is a schematic diagram of plugging and unplugging the expansion board of the storage device according to an embodiment of the present application.
  • S1 is the direction in which the cascade board 430 is pulled out.
  • the cascade board on the second side of the hard disk backplane can be taken out along the direction S1 parallel to the hard disk backplane.
  • S2 is the direction in which the cascade board 430 is installed.
  • the cascade board can be inserted into the second side of the hard disk backplane along the direction S2 parallel to the hard disk backplane.
  • the cascade board can be easily plugged and unplugged, which improves the maintainability of the storage device.
  • the layout of the hard disk array, the expansion board, and the plugging and unplugging methods of the expansion board are similar to the horizontal installation of the hard board backplane. For brevity, the details are omitted.
  • the hard disk array and the cascade board are located on both sides of the hard disk backplane, and the position of the cascade board can be flexibly arranged, which shortens the link length from the cascade board to the hard disk slot, and reduces the link length.
  • Road loss Therefore, a middle-loss (middle-loss)-level board can be used to implement a higher specification (for example, 6G SATA) hard disk device, which reduces the cost of the board.
  • a middle-loss (middle-loss)-level board can be used to implement a higher specification (for example, 6G SATA) hard disk device, which reduces the cost of the board.
  • 6G SATA 6G SATA
  • Due to the short link there is no need to design a drive on the hard disk backplane, which reduces the cost of the drive.
  • the hard disk backplane implements a passive design, which greatly reduces the failure rate of the whole machine.
  • the cascade board Since the hard disk array and the cascade board are located on both sides of the hard disk backplane, the cascade board will not occupy the hard disk slot, and will not affect the capacity and hard disk density of the storage device, and the capacity of the storage device can be increased by 5% to 10%.
  • the cascade board and the hard disk array are not on the same side, so the cascade board will not squeeze the gap of the hard disk array, so the hard disk array can be laid out with a larger gap, and the heat dissipation air duct can be expanded, which is beneficial to reduce the cost of heat dissipation. The noise of the whole machine.
  • the expansion board can be made into FRU, which can be replaced separately, which is convenient for the upgrade and maintenance of storage devices.

Landscapes

  • Cooling Or The Like Of Electrical Apparatus (AREA)

Abstract

本申请提供了一种存储设备，包括：硬盘背板、第一级联板和硬盘阵列，其中硬盘阵列包括多个硬盘；硬盘阵列位于硬盘背板的第一侧；第一级联板是现场可更换单元FRU，第一级联板位于硬盘背板的第二侧。本申请的存储设备具有新型级联板架构，能够降低存储设备的成本，提高存储设备的可维护性。

Description

一种存储设备
本申请要求于2020年6月22日提交中国专利局、申请号为202010572355.3、申请名称为“一种存储设备”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请实施例涉及存储技术领域，尤其涉及一种存储设备。
背景技术
在存储领域，例如传统企业存储、视频监控等应用中，高密度硬盘驱动器(hard disk drive，HDD)是不可替代的一部分。扩展器(expander)加上硬盘阵列是高密度HDD的典型架构。
expander在高密度HDD中主要以两种形式存在。一种是expander直接焊接在印制电路板(printed circuit board，PCB)上，另一种是expander作为独立的现场可更换单元(field replaceable unit，FRU)存在，expander作为FRU时也可以称为级联板。当expander直接焊接在PCB板上时，expander具有较小的体积，布局位置灵活，能够降低整机结构的实现难度以及缩短高速链路长度。但是当expander芯片出现故障，或者需要整机升级演进时，必须更换硬盘背板甚至整机。当expander作为独立FRU时，虽然易于维护，但是FRU布局位置受整机结构限制，高速链路难以缩短，导致PCB板材、驱动器成本上升。
因此，存储设备中需要一种全新的级联板架构，以满足整机成本、可维护性方面的要求。
发明内容
本申请提供一种存储设备，该存储设备具有新型级联板架构，能够降低存储设备的成本，提高存储设备的可维护性。
第一方面，提供了一种存储设备，包括硬盘背板、第一级联板和硬盘阵列，其中硬盘阵列包括多个硬盘；硬盘阵列位于硬盘背板的第一侧；第一级联板是现场可更换单元FRU，第一级联板位于硬盘背板的第二侧。
在上述方案中，级联板与硬盘阵列分别位于硬盘背板的两侧，级联板既不占用硬盘槽位，不影响存储设备的容量，又不会挤压硬盘阵列的间隙，降低存储设备的散热成本。存储设备的级联板是FRU，可以随时更换，便于维护。
在一种可能的实现方式中，该存储设备包括第二级联板，第二级联板位于硬盘背板的第二侧，硬盘阵列包括第一硬盘区域和第二硬盘区域，第一级联板管理第一硬盘区域，第二级联板管理第二硬盘区域。
通过多个级联板，可以对硬盘阵列进行区域化管理，每块级联板管理附近的硬盘 阵列区域，缩短了级联板和硬盘背板之间的高速链路长度。
在另一种可能的实现方式中，第一级联板位于第一硬盘区域的居中位置；第二级联板位于第二硬盘区域的居中位置。
级联板位于每个区域的居中位置时，可以进一步缩短每个硬盘区域的最远硬盘和级联板之间的链路距离。
在另一种可能的实现方式中，第一级联板可插拔地安装在硬盘背板的第二侧。
在另一种可能的实现方式中，第二级联板可插拔地安装在硬盘背板的第二侧。
存储设备的级联板可以方便地从存储设备的侧面拔出和插入，便于更换级联板，提高了存储系统的可维护性。
在另一种可能的实现方式中，第一级联板上具有扩展器芯片。
在另一种可能的实现方式中，第二级联板上具有扩展器芯片。
在另一种可能的实现方式中，第一侧和第二侧分别为硬盘背板的上侧和下侧。
在另一种可能的实现方式中，第一侧和第二侧分别为硬盘背板的下侧和上侧。
在另一种可能的实现方式中，第一侧和第二侧分别为硬盘背板的左侧和右侧。
在另一种可能的实现方式中，第一侧和第二侧分别为硬盘背板的右侧和左侧。
附图说明
图1是现有技术的一种级联板架构意图。
图2是现有技术的另一种级联板架构示意图。
图3是现有技术的另一种级联板架构示意图。
图4是本申请实施例的一种存储设备的结构示意图。
图5是本申请实施例的一种存储设备的侧视图。
图6是本申请实施例的一种存储设备的俯视图。
图7是本申请实施例的另一种存储设备的俯视图。
图8是本申请实施例的一种存储是设备的级联板的插拔示意图。
具体实施方式
下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例是本申请的一部分实施例，而不是全部实施例。
高密度硬盘驱动器(hard disk drive，HDD)在存储领域有广泛的应用。整机容量、单位密度、成本、维护性是高密HDD的关键竞争力。扩展器(expander)加上硬盘阵列是高密度HDD的典型架构。expander主要以两种形式存在，一种是expander直接焊接在印制电路板(printed circuit board，PCB)上，另一种是expander作为独立的现场可更换单元(field replaceable unit，FRU)存在。当expander作为独立的FRU时，在存储设备中可以称为级联板。通常存储设备主要有以下几种级联板架构。
方式一：级联板采用平插方式位于硬盘阵列的一侧。
图1提供了一种级联板架构的示意图。图1中的(a)是采用方式一的级联板架构的存储设备的侧视图，图1中的(b)是采用方式一的级联板架构的存储设备的俯视图。如图1中的(a)所示，包含多个硬盘120的硬盘阵列，级联板130和硬盘阵列均位于 硬盘背板110的同一侧。级联板130采用平插的方式连接在硬盘背板110上。如图1中的(b)所示，采用这种级联板的架构时，高速链路140较长。
方式一的级联板架构适用于3G串行小型计算机接口(small computer system interface，SCSI)(serial attached SCSI，SAS)场景，主要原因是3G SAS场景速率较低，且具有较强的链路插损容忍能力，即使链路较长，对板材选型影响也比较小。但是想要在串行高级技术附件(serial advanced technology attachment，SATA)硬盘中使用这种级联板架构时，由于高速链路较长，链路损耗大，因此硬盘背板必须使用低损耗(low loss)层级、甚至是非常低损耗(very low loss)层级的板材，板材的成本较高。另外，为了支持SATA硬盘，硬盘背板需要增加驱动器，影响背板的无源特性，增大了背板发生故障的可能性。
方式二：级联板占用硬盘槽位。
图2提供了另一种级联板架构的示意图。图2是方式二的级联板架构的俯视图。如图2所示，级联板130和硬盘阵列位于硬盘背板110的同一侧。并且，级联板采用竖叉的方式安装在硬盘阵列中，占用了硬盘阵列的槽位。与方式一相比，方式二的级联板架构下，高速链路长度相对较短。但是，由于级联板占用了硬盘的槽位，对整机的硬盘密度以及整机容量有较大的影响。并且，在一些实施方式中，为了进一步缩短高速链路的长度，会进一步拆分级联板。例如，如图2所示，两块级联板占用了两个硬盘槽位，如果采用增加级联板的方式缩短高度链路长度(例如，采用4块级联板)，将占用更多硬盘槽位，对整机容量产生更大的影响。此外，虽然高链路长度相较于方式一有了改善，但是对于6G SATA规格的硬盘，仍然需要使用low loss甚至very low loss层级的板材，成本较高。
方式三：级联板竖插于硬盘阵列两侧。
图3是提供了另一种级联板架构的示意图。图3是方式三的级联板架构的俯视图。如图3所示，级联板130和硬盘阵列位于硬盘背板110的同一侧。并且，级联板130采用竖插的方式布局在硬盘阵列的两侧。方式三的级联板架构不会占用硬盘的槽位，不影响整机容量。在方式三的级联板架构中，高速链路140的长度在方式一和方式二之间，但是对于更高规格的硬盘，例如6G SATA规格的硬盘，仍然需要使用low loss甚至very low loss层级的板材，或者增加驱动器，成本较高，影响硬盘背板的无源特性。另外，由于级联板需要布局在硬盘阵列的两侧，在硬盘背板的面积一定的情况下，可能挤压硬盘阵列的间隙，影响硬盘120的散热，增加了散热成本。
以上的几种级联板架构均不适用于高规格的硬盘结构。本申请提供了一种新的存储设备的级联板的架构，可以应用于各种高规格的存储设备中，并且实现成本较低。
下面结合图4至图8详细介绍本申请实施例的存储设备的级联板架构。
图4是本申请实施例的一种存储设备的结构示意图。如图4所示，本申请实施例的存储设备包括硬盘背板410、包含多个硬盘420的阵列硬盘和级联板430(例如，第一级联板)。该硬盘阵列位于硬盘背板的第一侧。级联板430位于硬盘背板410的第二侧，级联板430是FRU。应理解，图4所示的存储设备中仅示出了两个级联板430，在其他实施例中，该存储设备还可以包括其他数量的级联板(例如，第二级联板)，本申请实施例对级联板的数量不做限定。在一些实施例中，该级联板430上可以包括 扩展器(expander)芯片。
应理解，图4所示的存储设备中，硬盘背板410水平设置，包含多个硬盘420的硬盘阵列和级联板430分别位于水平放置的硬盘背板的上下两侧。在另一些实施例中，硬盘背板也可以竖直放置，在这种情况下，硬盘阵列和级联板分别位于硬盘背板的左右两侧。
图5是图4所示的存储设备的侧视图。如图5所示，包含多个硬盘420的硬盘阵列位于硬盘背板410的第一侧，级联板430位于硬盘背板410的第二侧，其中级联板430上包括expander芯片。
本发明实施例中，硬盘背板的第一侧和第二侧是相对的两侧，例如左侧和右侧，或者上侧和下侧，或者右侧和左侧，或者下侧和上侧。
本申请实施例的存储设备中，一种实现方案，级联板包含expander芯片及其相关组件，形成FRU，级联板可为FRU，可以实现硬盘背板无源化，降低了存储设备整机失效率。并且，级联板与硬盘阵列分别位于硬盘背板的两侧，级联板既不占用硬盘槽位，不影响存储设备的容量，又不会挤压硬盘阵列的间隙，不影响存储设备的散热。另外，由于expander芯片是独立的FRU，expander芯片需要更换时仅需替换级联板，提高了存储设备的可维护性。
在一些实施例中，存储设备可以包括多个级联板，每块级联板的expander管理硬盘阵列的一个区域。示例性的，存储设备包括4个级联板。图6是包括四块级联板的存储设备的俯视图。由于级联板位于硬盘背板的另一侧，因此硬盘背板第一侧的硬盘阵列用实线表示，硬盘背板第二侧的级联板用虚线表示。如图6所示，该存储设备包括4块级联板，硬盘阵列划分为4个区域，每块级联板管理与该级联板距离最近的硬盘区域。例如，级联板1管理硬盘区域1，级联板2管理硬盘区域2，级联板3管理硬盘区域3，级联板4管理硬盘区域4。
应理解，图6仅仅是多块级联板的一个实例，本申请实施例的存储设备还可以包括其他数量的级联板，并且，本申请实施例对级联板管理的硬盘区域的划分也不做限定。
通过多个级联板，可以对硬盘阵列进行区域化管理，每块级联板管理附近的硬盘阵列区域，缩短了级联板和硬盘背板之间的高速链路长度。
在另一些实施例中，可以进一步优化多个级联板槽位的位置。以存储设备包括4块级联板为例，图7是本申请实施例的另一种包括四块级联板的存储设备的俯视图。如图7所示，该存储设备包括4块级联板，硬盘阵列划分为4个区域，每块级联板管理与该级联板距离最近的硬盘区域。例如，级联板1管理硬盘区域1，级联板2管理硬盘区域2，级联板3管理硬盘区域3，级联板4管理硬盘区域4。并且，每块级联板位于对应硬盘区域的居中位置。例如，级联板1位于硬盘区域1的居中位置。通过这种居中布局的方式，进一步缩短了每个区域中的高速链路长度。
本申请实施例的存储设备中，由于级联板和硬盘阵列分别位于硬盘背板的两侧，级联板在空间上与硬盘阵列解耦，使得级联板的位置可以灵活变化，不与硬盘阵列干涉，大幅缩短级联板到远端硬盘槽位的链路长度。
本申请实施例的存储系统中，级联板和硬盘阵列分别位于硬盘背板的两侧，并且 级联板是独立FRU，当级联板上的部件(例如，expander芯片)需要更换时，可以直接从存储设备的侧面对级联板进行插拔，便于设备的维护。图8是本申请实施例的存储设备的级联板插拔的示意图。
如图8所示，S1是将级联板430拔出的方向。当级联板需要更换或者维护时，可以沿着与硬盘背板平行的方向S1将硬板背板第二侧的级联板取出。S2是将级联板430装入的方向。当需要将级联板安装到硬盘背板的第二侧时，可以沿着与硬盘背板平行的方向S2将级联板插入到硬盘背板的第二侧。
通过这种方式，可以方便地对级联板进行插拔，提高了存储设备的可维护性。
当存储设备的硬盘背板竖直设置时，硬盘阵列、级联板的布局、级联板的插拔方式与硬板背板水平设置是相似，为了简洁，不再详述。
本申请实施例的存储设备中，硬盘阵列和级联板位于硬盘背板的两侧，并且级联板的位置可以灵活布局，缩短了级联板到硬盘槽位的链路长度，降低了链路的损耗。因此，可以使用中等损失(middle loss)层级的板材实现较高规格(例如，6G SATA)的硬盘设备，降低了板材的成本。并且，由于链路较短，硬盘背板上无需设计驱动器，降低了驱动器的成本，硬盘背板实现无源设计，大大降低整机失效率。
由于硬盘阵列和级联板分别位于硬盘背板的两侧，级联板不会占用硬盘槽位，不会影响存储设备的容量和硬盘密度，存储设备的容量可以提高5％～10％。另外，级联板和硬盘阵列不在同一侧，因此级联板不会挤压硬盘阵列的间隙，因此硬盘阵列可以以较大的间隙进行布局，扩展散热风道，有利于降低散热成本、减小整机噪声。
级联板可以做成FRU，可单独更换，便于存储设备的升级和维护。
应理解，说明书通篇中提到的“一些实施例”或“一实施例”意味着与实施例有关的特定特征、结构或特性包括在本申请的至少一些实施例中。因此，在整个说明书各处出现的“在一些实施例中”或“在一实施例中”未必一定指相同的实施例。此外，这些特定的特征、结构或特性可以任意适合的方式结合在一个或多个实施例中。应理解，在本申请的各种实施例中，上述各过程的序号的大小并不意味着执行顺序的先后，各过程的执行顺序应以其功能和内在逻辑确定，而不应对本申请实施例的实施过程构成任何限定。
以上所述，仅为本申请的具体实施方式，但本申请的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本申请揭露的技术范围内，可轻易想到变化或替换，都应涵盖在本申请的保护范围之内。因此，本申请的保护范围应以所述权利要求的保护范围为准。

Claims (11)

  1. 一种存储设备，其特征在于，包括：硬盘背板(410)、第一级联板(430)和硬盘阵列，所述硬盘阵列包括多个硬盘(420)；
    所述硬盘阵列位于所述硬盘背板(410)的第一侧；
    所述级第一联板(430)是现场可更换单元FRU，所述第一级联板(430)位于所述硬盘背板(410)的第二侧。
  2. 根据权利要求1所述的存储设备，其特征在于，所述存储设备还包括第二级联板，所述第二级联板位于所述硬盘背板的第二侧，所述硬盘阵列包括第一硬盘区域和第二硬盘区域，所述第一级联板管理所述第一硬盘区域，所述第二级联板管理所述第二硬盘区域。
  3. 根据权利要求2所述的存储设备，其特征在于，所述第一级联板位于所述第一硬盘区域的居中位置；所述第二级联板位于所述第二硬盘区域的居中位置。
  4. 根据权利要求1-3中任一项所述的存储设备，其特征在于，所述第一级联板可插拔地安装在所述硬盘背板的第二侧。
  5. 根据权利要求2或3所述的存储设备，其特征在于，所述第二级联板可插拔地安装在所述硬盘背板的第二侧。
  6. 根据权利要求1-5中任一项所述的存储设备，其特征在于，所述第一级联板上具有扩展器芯片。
  7. 根据权利要求2-5中任一项所述的存储设备，其特征在于，所述第二级联板上具有扩展器芯片。
  8. 根据权利要求1-7中任一项所述的存储设备，其特征在于，所述第一侧和所述第二侧分别为所述硬盘背板的上侧和下侧。
  9. 根据权利要求1-7中任一项所述的存储设备，其特征在于，所述第一侧和所述第二侧分别为所述硬盘背板的下侧和上侧。
  10. 根据权利要求1-7中任一项所述的存储设备，其特征在于，所述第一侧和所述第二侧分别为所述硬盘背板的左侧和右侧。
  11. 根据权利要求1-7中任一项所述的存储设备，其特征在于，所述第一侧和所述第二侧分别为所述硬盘背板的右侧和左侧。
PCT/CN2021/101211 2020-06-22 2021-06-21 一种存储设备 WO2021259194A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
EP21828891.8A EP4152325A4 (en) 2020-06-22 2021-06-21 STORAGE DEVICE
US18/083,694 US20230124534A1 (en) 2020-06-22 2022-12-19 Storage device

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010572355.3A CN113903369A (zh) 2020-06-22 2020-06-22 一种存储设备
CN202010572355.3 2020-06-22

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US18/083,694 Continuation US20230124534A1 (en) 2020-06-22 2022-12-19 Storage device

Publications (1)

Publication Number Publication Date
WO2021259194A1 true WO2021259194A1 (zh) 2021-12-30

Family

ID=79186394

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/101211 WO2021259194A1 (zh) 2020-06-22 2021-06-21 一种存储设备

Country Status (4)

Country Link
US (1) US20230124534A1 (zh)
EP (1) EP4152325A4 (zh)
CN (1) CN113903369A (zh)
WO (1) WO2021259194A1 (zh)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN201402609Y (zh) * 2009-05-15 2010-02-10 成都市华为赛门铁克科技有限公司 磁盘阵列
CN104166611A (zh) * 2013-05-17 2014-11-26 鸿富锦精密工业（深圳）有限公司 硬盘温度信息获取装置及方法
CN205028221U (zh) * 2015-10-21 2016-02-10 浪潮电子信息产业股份有限公司 一种服务器机箱新型盘位结构
US20160132078A1 (en) * 2014-11-10 2016-05-12 Inventec (Pudong) Technology Corporation Server

Family Cites Families (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7415011B2 (en) * 2003-08-29 2008-08-19 Sun Microsystems, Inc. Distributed switch
US7526684B2 (en) * 2004-03-24 2009-04-28 Seagate Technology Llc Deterministic preventive recovery from a predicted failure in a distributed storage system
JP4105121B2 (ja) * 2004-05-14 2008-06-25 富士通株式会社 電子機器の筐体構造、及びディスクアレイ装置
US7275935B2 (en) * 2005-02-28 2007-10-02 Kuang Wei Chen Universal backplane connection or computer storage chassis
US7481679B1 (en) * 2006-11-01 2009-01-27 Emc Corporation Electrical connector and circuit card assembly
JP5022803B2 (ja) * 2006-12-13 2012-09-12 株式会社日立製作所 記憶制御装置
EP2650879A1 (en) * 2010-12-07 2013-10-16 Fujitsu Limited Storage device, and partitiion plate in storage device
CN103677159A (zh) * 2012-09-21 2014-03-26 英业达科技有限公司 存储伺服器
CN103838297A (zh) * 2012-11-21 2014-06-04 鸿富锦精密工业（深圳）有限公司 服务器背板及服务器背板组合
US20140273556A1 (en) * 2013-03-15 2014-09-18 Silicon Graphics International Corp. High-density multidirectional midplane
CN105446437A (zh) * 2014-08-19 2016-03-30 华为技术有限公司 一种硬盘阵列散热装置
CN113407244A (zh) * 2016-03-01 2021-09-17 华为技术有限公司 一种级联板、ssd远程共享访问的系统和方法
US11467997B2 (en) * 2017-02-22 2022-10-11 Seagate Technology Llc Hot-swappable protocol expander module for storage array
CN115269717B (zh) * 2019-08-22 2023-06-02 华为技术有限公司 存储设备、分布式存储系统以及数据处理方法

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN201402609Y (zh) * 2009-05-15 2010-02-10 成都市华为赛门铁克科技有限公司 磁盘阵列
CN104166611A (zh) * 2013-05-17 2014-11-26 鸿富锦精密工业（深圳）有限公司 硬盘温度信息获取装置及方法
US20160132078A1 (en) * 2014-11-10 2016-05-12 Inventec (Pudong) Technology Corporation Server
CN205028221U (zh) * 2015-10-21 2016-02-10 浪潮电子信息产业股份有限公司 一种服务器机箱新型盘位结构

Also Published As

Publication number Publication date
CN113903369A (zh) 2022-01-07
US20230124534A1 (en) 2023-04-20
EP4152325A1 (en) 2023-03-22
EP4152325A4 (en) 2023-11-01

Similar Documents

Publication Publication Date Title
CN104182003B (zh) 服务器
US9036342B2 (en) Storage apparatus and storage controller of storage apparatus
US7493444B2 (en) Substrate structure of disk array apparatus, disk array apparatus and disk array system
US20170156234A1 (en) System And Method For Flexible Storage And Networking Provisioning In Large Scalable Processor Installations
US11596073B2 (en) Electronic equipment that provides multi-function slots
JP3157935U (ja) サーバー
CN108829561B (zh) 一种支持40块硬盘的4u服务器
CN104182004A (zh) 服务器
WO2020114021A1 (zh) 具有平行背板的电子设备及存储设备
CN108874711B (zh) 一种优化散热的硬盘背板系统
CN102566680A (zh) Sas背板
US20050210188A1 (en) Storage system
WO2021259194A1 (zh) 一种存储设备
KR100883005B1 (ko) 고가용성 대용량 저장 시스템 및 이의 생성 방법
TWI542976B (zh) 服務器
WO2016192136A1 (zh) 内存子卡、主板及机箱
US12072827B2 (en) Scaling midplane bandwidth between storage processors via network devices
WO2024066456A1 (zh) 服务器
WO2024045752A1 (zh) 服务器及电子设备
TWI558298B (zh) 伺服器
CN113839263B (zh) 浮动插入器
US8806123B1 (en) Expandable data storage system
CN219349502U (zh) 用于机架式计算机的计算机主板
CN210244283U (zh) 一种节点分布式装置
CN214225846U (zh) 机箱的高密度PCIe扩展结构

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: 21828891

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2021828891

Country of ref document: EP

Effective date: 20221215

NENP Non-entry into the national phase

Ref country code: DE