MODULAR ARCHITECTURE FOR HARD PLATE STORAGE SYSTEMS
The modular HDD storage platform addresses the challenges of high-density storage by stacking HDDs vertically with interposer connectivity and a central controller, improving signal integrity and reducing costs through efficient electrical transmission and cost-effective materials.
Patent Information
- Application Number
- DE102025124387
- Authority / Receiving Office
- DE · DE
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2024-09-17
- Filing Date
- 2025-06-24
- Publication Date
- 2026-03-19
AI Technical Summary
Existing data storage systems face challenges in achieving high-density storage with efficient electrical transmission and cost-effective signal integrity, particularly in archival and enterprise data centers, due to the use of large PCBs and expensive low-loss laminates, which increase manufacturing costs and thermal issues.
A modular, high-density data storage platform architecture that stacks HDDs vertically, using interposer connectivity and a centrally located main controller to minimize electrical transmission lengths and reduce PCB interconnect losses, allowing for both low-latency and high-latency configurations with cost-effective materials.
This approach enhances signal integrity and reduces manufacturing costs by minimizing electrical transmission lengths and using less expensive PCB materials, while supporting flexible IOPS configurations and improving performance in data storage systems.
Smart Images

Figure 00000000_0000_ABST
Abstract
Description
AREA OF EXECUTION FORMS
[0001] Embodiments of the invention can generally relate to data storage, in particular to a flexible, high-density hard disk drive storage platform. BACKGROUND
[0002] A hard disk drive (HDD) is a non-volatile storage device housed in a protective enclosure that stores digitally encoded data on one or more circular platters with magnetic surfaces. When an HDD is operating, each magnetic recording platter is rapidly spun by a spindle system. Data is read from and written to a magnetic recording platter using a read / write head (or transducer) that is positioned over a specific location on a platter by an actuator. A read / write head uses magnetic fields to write data and to read data from the surface of a magnetic recording platter. A write head uses the flow of electricity through its coil to generate a magnetic field. Electrical pulses are sent to the write head with different patterns of positive and negative currents.The current in the coil of the write head generates a localized magnetic field through the gap between the head and the magnetic disk, which in turn magnetizes a small area on the recording medium.
[0003] As the number and power of networked computer systems increase, there is a need for greater data storage capacity. Large-scale enterprise, cloud computing / storage, and data processing environments continue to drive the demand for digital data storage systems (generally referred to as "data centers") capable of transferring and storing substantial amounts of data. One approach to providing adequate data storage in data centers is the use of arrays of data storage devices, typically configured and deployed as one or more data storage systems.One such approach for large-scale data storage is known, for example, as JBOD (Just a Bunch of Disks or Just a Bunch of Drives), which is usually a collection of hard disk drives (HDDs) that can be made available as independent devices or combined into a logical volume.
[0004] Furthermore, there is an increasing need for archived data storage (also known as "cold storage"). Magnetic tapes are a traditional solution for data backup, but access to the stored data is particularly slow. Current archives are increasingly "active" archives, meaning that a certain degree of continuous, direct access to the data is required. In addition to faster access times, there are several advantages that a magnetic disk library can offer over a traditional tape library. Regarding the cost of magnetic media, magnetic disks in HDDs have the lowest proven cost per terabyte (e.g., $ / Tb). Moreover, magnetic disks are known to have a relatively long lifespan, especially when managed in a controlled environment, which keeps the magnetic bits on the media stable for a relatively long time.
[0005] All approaches that can be described in this section are approaches that could be pursued, but not necessarily approaches that have been previously conceived or pursued. Therefore, unless otherwise stated, it should not be assumed that any of the approaches described in this section qualify as prior art simply because it is included here. BRIEF DESCRIPTION OF THE DRAWINGS
[0006] Embodiments are illustrated by way of example and without limitation in the figures of the accompanying drawings, in which the same reference numerals are used to denote similar elements: Fig. Figure 1 is a top view illustrating a hard disk drive (HDD) according to one embodiment; Fig. Figure 2 is a perspective view that schematically illustrates a modular data storage system according to one embodiment; Fig. Figure 3A is a perspective view illustrating a hard disk drive with electrical interposer connectivity according to one embodiment; Fig. Figure 3B is a perspective view illustrating a hard disk drive with electrical connectivity to a customer-specific enclosure according to one embodiment; Fig. Figure 4A is a schematic diagram illustrating a modular single-channel data storage system according to one embodiment; Fig. Figure 4B is a schematic diagram illustrating a modular dual-channel data storage system according to one embodiment; Fig. Figure 5A is a schematic side view diagram illustrating a modular data storage system with electrical interposer connectivity according to one embodiment; Fig. Figure 5B is a schematic side view diagram illustrating a modular data storage system with electrical connectivity to a customer-specific enclosure according to one embodiment; Fig. Figure 6A is a perspective view illustrating a modular data storage system with electrical interposer connectivity according to one embodiment; Fig. 6B is a perspective view showing the electrical connectivity of the modular data storage system of Fig. 6A illustrated according to one embodiment; Fig. 6C is a perspective view showing an interposer board of the modular data storage system from Fig. 6A illustrated according to one embodiment; Fig. Figure 7 is a schematic side-view diagram illustrating a modular data storage system with electrical interposer connectivity according to one embodiment; and Fig. Figure 8 is a table illustrating the electrical interposer connectivity options according to one embodiment. DETAILED DESCRIPTION
[0007] In general, approaches for a modular, high-density data storage platform are described. For explanatory purposes, numerous specific details are presented in the following description to provide a thorough understanding of the embodiments of the invention described herein. However, it will be evident that the embodiments of the invention described herein can be implemented without these specific details. In other cases, known structures and devices may be shown in block diagram form to avoid making the embodiments of the invention described herein unnecessarily unclear. Introduction Terminology
[0008] References herein to “an embodiment” and the like are intended to mean that the particular feature, structure, or characteristic is included in at least one embodiment of the invention. However, the occurrence of such expressions does not necessarily refer to the same embodiment.
[0009] The term "essentially" is to be understood as describing a feature that is largely or almost fully structured, configured, dimensioned, etc., but where, in practice, manufacturing tolerances and the like may lead to a situation where the structure, configuration, dimensions, etc., are not always or necessarily exactly as specified. For example, describing a structure as "essentially vertical" would give this term its obvious meaning, such that the structure is vertical for all practical purposes, but may not be exactly at 90 degrees everywhere.
[0010] Even though terms such as "optimal," "optimize," "minimal," "minimize," "maximize," and the like may not be associated with specific values, the intention hereof is that those skilled in the art would understand such terms to include a value, parameter, metric, and the like in a beneficial direction consistent with the entirety of this disclosure. For example, describing a value of something as "minimal" does not require that the value actually be equal to a theoretical minimum (e.g., zero), but should be understood in a practical sense as meaning that a corresponding goal would be to move the value in a beneficial direction toward a theoretical minimum. context
[0011] It's worth remembering that there is an increasing need for archived data storage, as well as a continued demand for enterprise data centers, cloud computing and storage, and data processing at scale. One approach to meeting the expansive need for storage at scale involves the use of disaggregated storage, where compute resources are generally separated from storage resources. This allows the different types of resources to be provisioned, controlled, managed, and so on, separately. Maximizing the potential benefits of disaggregated storage can also be achieved through a flexible, high-density storage platform architecture.One aspect of storage platform flexibility might include the ability to use both faster (relatively high IOPS or input / output per second) and slower (relatively low IOPS) storage devices. Furthermore, the implementation of a high-density storage platform architecture should not preclude consideration of the performance and cost associated with the underlying storage devices.
[0012] Previously known approaches for archiving storage platforms using shared electronics rely on very large printed circuit boards (PCBs) to house the array of data storage devices, requiring long electrical transmission lengths and likely also high-frequency multiplexers. These requirements, in turn, likely necessitate the use of low-loss, expensive PCB laminates, which can be up to five times more expensive than conventional PCB laminates. Modular architecture for hard disk drive storage platform
[0013] According to embodiments, a multi-modular (HD-MM) architecture / construction of a hard disk drive (HDD) allows an HDD to be configured in various ways and with different capacities. As such, an HDD can operate in a single-drive mode or as part of a group with other HDDs operating via a common printed circuit board (PCB) that incorporates one or more electronic controllers (also referred to as control switching logic or "SOC" (System on a Chip)). Such a data storage system implemented in HD-MM form is therefore capable of supporting both low-latency / IOPS configurations and high-latency / IOPS configurations. For example, an HD-MM storage system can be deployed in an "NxHDD T" configuration using a single controller or in an "NxHDD Parallel" configuration using multiple controllers.In an NxHDD-T configuration, one or more T-shaped connections (“T-connections”) can be implemented to branch from multiple HDDs to a single controller, for example, replaceable HDDs that primarily utilize existing electronics. Alternatively, an NxHDD-Parallel configuration can mimic multi-actuator architectures, for example, when each controller operates independently with a corresponding logical storage unit equivalent to the HDDs, utilizing the existing HDD mechanics. In either type of configuration, a constituent HDD is intended to be interchangeable in both NxHDD-Parallel and NxHDD-T configurations.
[0014] Fig. Figure 2 is a perspective view that schematically illustrates a modular data storage system according to one embodiment. Fig. Figure 2 simply illustrates an exemplary "8x" data storage system 200 with eight HDDs 202, each coupled to or mounted on a common (i.e., shared) main PCB 204, for example, in mechanical and electrical connection to it. Exemplary dimensions are included here to show that such a system, in a quadruple-stacked configuration (four HDDs stacked on top of each other), can fit into a 4U slot in various orientations (e.g., main PCB at the bottom, main PCB at the back), where "U" or "RU" refers to a standard rack unit or a unit of measurement defined as 1.75 inches (44.45 millimeters) in height. In a rack installation where the main PCB 204 is installed at the bottom, the system / box can be serviced from the top, making the HDDs 202 easily replaceable.
[0015] According to embodiments, an HDD configured for this HD-MM architecture can be one of two types. Fig. Figure 3A is a perspective view illustrating a hard disk drive with electrical interposer connectivity according to one embodiment. Fig. Figure 3A illustrates an HDD 302 configured for electrical interposer connectivity, referred to herein as the HDD-IC (HDD interposer connection). The HDD-IC form factor represents only a minor change in physical placement compared to a conventional HDD PCB, as the current / traditional electronics are used, with the exception of the main control / SOC. For example, the preamplifier, actuation control(s) (e.g., voice coil motor (VCM), fine adjuster(s)), motor control(s) (e.g., disk spindle motor(s)), and switching logic for sensors (e.g., temperature, torsional vibration, and the like) all remain on a modified PCB 304 to support a cost-effective bus input of the end connector 305. h, whereby an interposer board / bus is used to transfer I / Os (a multitude of inputs / outputs) between an HDD IC and a main controller on a separate main PCB (see, for example, the main PCB 204 in Fig. 2) and to support additional controls if required. In the HDD IC form factor, the package of a conventional HDD can be used to minimize manufacturing complexity and costs, and the associated interposer PCB, according to one embodiment, is a cost-effective minimum-layer PCB (e.g., four layers, as a non-limiting example, with fewer vias).
[0016] Fig. Figure 3B is a perspective view illustrating a hard disk drive with electrical connectivity to a customer-specific enclosure according to one embodiment. Fig. Figure 3B illustrates an HDD 312 configured for electrical connectivity with a custom housing referred to herein as the HDD-CH (HDD-Custom Housing). The HDD-CH form factor uses a new end connector 315 for bus input to support I / O from a separate main PCB (see, for example, Main PCB 204 of [reference missing]). Fig. 2), on which the main controller / SOC is located, and an HDD PCB (see, for example, PCB 304 of Fig. 3A) is eliminated. For example, the switching logic of the actuation control(s) (e.g., VCM, fine adjustment element(s)), the motor control(s) (e.g., disk spindle motor(s)), and the sensors (e.g., temperature, torsional vibration, etc.) are moved internally to the HDD housing or can be located on the main PCB 204. The spindle motor connections would either be located internally or via a jumper connection scheme that would reconnect to connector 315. Signal integrity of the data storage system
[0017] As discussed elsewhere herein, previously known approaches for archival storage platforms using shared electronics relied on considerably large PCBs to support the array of data storage devices, requiring long electrical transmission lengths (e.g., up to 300 mm) and likely also high-frequency electrical multiplexers. These requirements, in turn, likely necessitate the use of low-loss, expensive PCB laminates, which are, for example, at least five times more expensive than conventional PCB laminates. Manufacturing such a low-loss dielectric incurs additional costs, and thermal issues with large laminates necessitate special pre-adjustments due to potential component misalignment.Furthermore, there are limited possibilities for electrical T-connections with such long transmission lengths, as electrical multiplexers are usually required in this context.
[0018] According to one embodiment, PCB connection losses are reduced by stacking HDDs (see, for example, HDDs 202 in Fig. 2) in mechanical and electrical connection with the main board (see e.g. main PCB 204 in Fig. 2) reduced. By stacking the HDDs 202 on top of each other (e.g., vertically stacking) and thus connecting each HDD 202 to the main PCB 204 via an end connector (at or near the elongated / rear end of the HDD), efficient electrical transmission line lengths are enabled. In other words, stacking the HDDs 202 (e.g., instead of placing them all in an array pattern across a main PCB) allows the main controller / SOC to be positioned centrally on the main PCB 204, minimizing the overall length of the electrical transmission line between the HDDs 202 and the controller. According to one embodiment, the controller is positioned on the main PCB 204 such that each length of electrical transmission line between a given HDD 202 and the controller is substantially equivalent (e.g., similar, but not necessarily absolutely identical).
[0019] Fig. Figure 4A is a schematic diagram illustrating a modular single-channel data storage system according to one embodiment. Diagram 400 illustrates a 4x2 HDD 402 (or “HDDC” for HDD components comprising the mechanical components of the head assembly (HDA) plus interposer connection) configuration in which a single single-channel controller 406 is sensibly positioned centrally on the main PCB 404, providing an equivalent / nearly equivalent line length between the grouping of HDDs 402, i.e., at a specific rate corresponding to the single-channel controller 406. In conjunction with a dual-channel controller 406 (e.g., at approximately 1.5 times the cost of a single-channel controller) or two single-channel controllers 406, the system could operate at a rate approximately twice that corresponding to the single-channel controller 406.
[0020] In the example configuration of Fig. Figure 4A shows a main PCB 404, which includes a multiplexer switching logic 408 (“Mux” or simply “Mux 408”) between a system control switching logic 406 (simply “Control 406”) and several groupings of HDD storage devices 402 (simply “HDDs 402”), as well as an electrical T-connection 409 between the Mux 408 and each pair of HDDs 402 in each grouping of storage devices. To continue with the example of an 8x storage system, each grouping of HDDs 402 contains two groupings (e.g., a first and a second grouping) of four stacked (shown here vertically stacked) HDDs 402 (a 2x4 configuration).Thus, a first Mux 408a is used to select and route the signal(s) sent by the controller 406 to each of the first and second groupings; a second Mux 408b is used to select and route each of these signals sent by the first Mux 408a to each of the two pairs of the first grouping; and a third Mux 408c is used to select and route each of these signals sent by the first Mux 408a to each of the two pairs of the second grouping. Furthermore, a T-connection 409 is used to route each of these signals, sent by each of the second and third Muxes 408b and 408c, to each HDD 402 of each pair of the first and second groupings.
[0021] Since the controller 406 is generally positioned centrally on the main PCB 404 (in this example 129 mm x 230 mm) and between the installed HDDs 402, and taking into account the vertical and horizontal gaps between the stacked HDDs 402, the length of the transmission line between the controller 406 and each HDD 402 (through the series of Muxes 408a-408c and T-connections 409) in this example is approximately 90-95 mm (approximately 2-5 mm from the controller 406 to the first Mux 408a, plus approximately 88 mm from the first Mux 408a through a corresponding Mux 408b, 408c to each HDD 402 (shown dashed for the top left HDD)). Therefore, a minimization of the total cable length (and the associated connection losses) and a high degree of equivalence between the individual cable lengths / paths (cable tracks) are made possible, at least partially by means of the symmetrical / balanced layout of the HDDs 402.Therefore, signal integrity for high-speed interfaces is significantly simplified, and shorter intermediate connections support adherence to timing requirements for low-speed interfaces, meaning that performance can be better compared to alternative storage systems. Furthermore, and to reiterate, relatively inexpensive PCB material with a minimum layer thickness can be used here, unlike the relatively expensive, low-loss PCB materials used in alternative systems. Note that in implementations of a main PCB 404 with multiple controllers 406, the trace lengths should be even shorter, since each controller 406 can be positioned closer to the corresponding grouping of HDDs 402 with which each controller 406 operates.
[0022] Fig. Figure 4B is a schematic diagram illustrating a modular dual-channel data storage system according to one embodiment. Diagram 410 shows a 4x2 HDD-402 configuration in which a single dual-channel controller 416 is sensibly positioned centrally on the main PCB 414, such that an equivalent / nearly equivalent trace length is provided within the grouping of HDDs 402, i.e., at a given rate corresponding to the parallel channels of the dual-channel controller 416. In the example configuration of Fig. 4B is a main PCB 414 shown, which has several (one for each channel of the controller 416) multiplexer switching logic 408 between the two-channel system control switching logic 416 (simply "controller 416") and several groupings of HDDs 402 and T-connections 409 between each Mux 408 and each pair of HDDs 402 in each grouping. To continue with the example of an 8x storage system, each grouping of HDDs 402 contains two groupings (e.g., a first and a second grouping) of four stacked (shown here vertically stacked) HDDs 402 (a 2x4 configuration). Thus, a first Mux 408a is used to select and route the signal(s) sent by a first channel of the controller 416 for each of the first and second groupings, and a second Mux 408b is used to select and route the signal(s) sent by a second channel of the controller 416 for each of the first and second groupings.From there, a T-connection 409 is used to route each of the signals sent by the first and second Mux 408a and 408b to each HDD 402 of each pair in the first and second grouping. Alternatively, a Mux 408 can be implemented instead of a T-connection 409. This also minimizes the overall line length (and the associated link losses) and allows for a high degree of equivalence of the individual line lengths / paths (line traces), as well as corresponding advantages regarding signal integrity, at least partially due to the symmetrical / balanced layout of the HDDs 402. Energy management of the storage device
[0023] A large-scale power supply interface (PLSI) refers to the power chip that controls the two main moving components of an HDD: the spindle motor and the VCM (Voltage Control Module). The SOC (System-on-a-Chip), the main drive controller, sends control signals to the PLSI, which in turn controls the VCM movement and the spindle motor speed. The PLSI is primarily analog and therefore not integrated into the SOC, which is primarily digital. In the context of a modular data storage system (HD-MM) architecture described herein, the placement of the PLSI(s) depends on the configuration used, e.g., HDD IC ( Fig. 3A) or HDD-CH ( Fig. 3B).
[0024] Fig. Figure 5A is a schematic side-view diagram illustrating a modular data storage system with electrical interposer connectivity according to one embodiment. According to one embodiment, in conjunction with an HDD configured according to the HDD IC form factor described herein, each HDD 502 (see also HDD 202 of Fig. 2, HDD 302 of Fig. 3A, HDD 402 from Fig. 4A-4B) each has a PLSI 503 chip. According to one embodiment, the main PCB 504 (see also main PCB 204 of Fig. 2, Main PCB 404 of Fig. 4A-4B) also includes a PLSI chip 505, which limits the power levels to the area of the main PCB 504. Here, the actuator and spindle motor control signals of PLSI 505 are practically unused, since the operating actuator and spindle motor control signals from each PLSI 503 are dedicated to each corresponding HDD 502. Regarding EPO (emergency stop) situations, the BEMF (counter-electromotive force) can be provided by the PLSI 503 of the active HDDs 502, which is then passed on to the PLSI 505 of the main PCB 504.
[0025] Fig. Figure 5B is a schematic side view diagram illustrating a modular data storage system with electrical connectivity to a customer-specific enclosure according to one embodiment. According to one embodiment, in connection with an HDD configured according to the HDD-CH shape described herein, the main PCB 514 (see also main PCB 204 of [reference missing]) features [reference missing]. Fig. 2, Main PCB 404 of Fig. 4A-4B) a PLSI 515 chip, with the power levels limited to the area of the main PCB 514. Here, the actuator and spindle motor control signals are transmitted from the PLSI 515 chip to each HDD 512 (e.g., via a Mux 518). Alternatively, the main PCB 514 can have a separate PLSI 515 chip corresponding to each HDD 512. With the HDD-CH form factor, the EPO is inherently handled. Therefore, in the scenario where only one PLSI 515 chip serves multiple HDDs 512, the PLSI 515 acts as an active PLSI to maintain the BEMF and provide the necessary power for the EPO procedures. Interposer connectivity between main PCB and HDDs
[0026] Fig. Figure 6A is a perspective view illustrating a modular data storage system with electrical interposer connectivity. Fig. 6B is a perspective view showing the electrical connectivity of the modular data storage system of Fig. 6A illustrates, and Fig. 6C is a perspective view showing an interposer board of the modular data storage system from Fig. Figure 6A illustrates all embodiments. In the context of the modular data storage system (HD-MM) architecture described herein, the electrical (and mechanical) connection between each HDD 602 (see also HDD 202 of Fig. 2, HDD 302 of Fig. 3A, HDD 402 from Fig. 4A-4B, HDD 502 from Fig. 5A, HDD 512 from Fig. 5B) and the main PCB 604 (see also main PCB 204 of Fig. 2, Main PCB 404 of Fig. 4A-4B, Main PCB 504 of Fig. 5A, Main PCB 514 of Fig. 5B), which is configured for an electrical connection with one or more hosts via a host connector 604a, is required for electrical transmission / communication (e.g., bus). For this connectivity purpose, an electrical interposer connectivity is used according to embodiments.
[0027] Fig. Figure 7 is a schematic side-view diagram illustrating a modular data storage system with electrical interposer connectivity according to one embodiment. The interposer connectivity includes a board connector 607a electrically connected to the main PCB 604, an interposer board 607b electrically connected to the board connector 607a, and an HDD connector 607c electrically connected to the HDD 602. According to one embodiment, the interposer board 607b is a solid board (e.g., PCB). According to another embodiment, the interposer board 607b is a flexible board (e.g., a flexible printed circuit board or "FPC"). Furthermore, the table in Figure 7 details the interposer board 607b. Fig. Eight options for suitable types of electrical connectors for each of the PCB connectors 607a and HDD connectors 607c are shown.
[0028] Fig. Figure 8 is a table illustrating the electrical interposer connectivity options according to one embodiment. While such connectivity options are mainly applicable to HDD ICs, these connectivity options or related hybrid options can utilize a form of HDD CH without PCB 304 (see, for example, Figure 8). Fig. 6A). With regard to the use of a fixed interposer board 607b ( Fig. 7) (Nos. 1-4 in Fig. 8) can a circuit board connector 607a ( Fig. 7) be selected from a group consisting of the following connector types: (i) a board edge connector, (ii) a normal board-to-board (B2B) connector, (iii) a floating B2B connector, and (iv) a compression connector. In this scenario with board edge and normal B2B connectors, the alignment between each HDD 602 ( Fig. 6A-6B, 7) and the main PCB 604 ( Fig. 6A-6C, 7) exhibit higher accuracy due to the smaller positional clearance for connecting the connector. Similarly, with regard to the use of a flexible interposer board 607b (Nos. 5, 6, 8 in Fig. 8) A PCB connector 607a is selected from a group consisting of the following connector types: (ii) a standard B2B connector, (iii) a floating B2B connector, and (iv) a compression connector. Again, with standard B2B connectors, the alignment between each HDD 602 and the main PCB 604 should be more accurate due to the smaller positional clearance when connecting the connector. Furthermore, with regard to the use of a flexible interposer board 607b (No. 7 in Fig. 8) A PCB connector 607a may be a board-to-flex connector (B2F). In this scenario with a B2F connector, the alignment between each HDD 602 and the main PCB 604 for connecting the connector can be relaxed compared to the previous scenarios. In each of the preceding connector implementations (Nos. 1-8 of Fig. 8) according to embodiments, a normal B2B connector for HDD connector 607c ( Fig. 6C, Fig. 7) used. Finally, with regard to the use of a flexible interposer board 607b and a B2F HDD connector 607c (Nos. 9-12 in Fig. 8) a PCB connector 607a is selected from a group consisting of the following connector types: (i) a PCB edge connector, (ii) a normal PCB-to-PCB (B2B) connector, (iii) a B2F connector and (iv) a compression connector.
[0029] According to the embodiments of a modular hard disk-based data storage system described herein, most HDD-specific components are located on each drive, while other electronic components (in particular, control and associated switching logic, including host connectors, DRAM, and the like, according to embodiments) are relocated to a shared mainboard. Stacking HDDs in mechanical and electrical connection with the mainboard reduces PCB interconnect losses, enabling efficient lengths of electrical transmission traces. That is, by stacking the HDDs, rather than placing them all in an array pattern across a main PCB, the main controller / SOC can be centrally located on the main PCB, thus minimizing the overall length of the electrical transmission trace between the HDDs and the controller. Hard disk drive configuration
[0030] As discussed, embodiments can be used in connection with a data storage system in which multiple data storage devices (DSDs), including hard disk drives (HDDs), are used. Thus, according to one embodiment, a top view illustrating a typical HDD 100 is shown in Fig. Figure 1A is shown to illustrate exemplary operating components. However, an HDDC (e.g., HDA mechanics with some, but less than typical, electronics, plus an interposer), such as an HDD-IC and / or HDD-CH, as described herein, are preferred candidates for use in the modular HD-MM storage system architecture / platform described herein.
[0031] Fig. Figure 1 illustrates the functional arrangement of components of the HDD 100, including a slider 110b enclosing a magnetic read / write head 110a. Collectively, the slider 110b and the head 110a can be referred to as the head slider. The HDD 100 includes at least one head gimbal suspension (HGA) 110, which includes the head slider, a guide suspension 110c typically attached to the head slider by a bend, and a load beam 110d attached to the guide suspension 110c. The HDD 100 also includes at least one recording medium 120 rotatably mounted on a spindle 124, and a drive motor (not shown) attached to the spindle 124 to rotate the medium 120. The read / write head 110a, which can also be referred to as a converter, includes a write element and a read element for the respective writing and reading of information stored on the medium 120 of the HDD 100.The medium 120 or a variety of plate media can be attached to the spindle 124 using a plate clamp 128.
[0032] The HDD 100 further includes an arm 132 attached to the HGA 110, a carriage 134, a voice coil motor (VCM) comprising an armature 136 including a voice coil 140 attached to the carriage 134, and a stator 144 including a voice coil magnet (not shown). The armature 136 of the VCM is attached to the carriage 134 and is configured to move the arm 132 and the HGA 110 to access sections of the medium 120, all of which are mounted on a pivot 148 with a rotary bearing assembly 152 positioned between them. In the case of a multi-disk HDD, the carriage 134 can be referred to as an "E-block" or comb, since the carriage is arranged to support a series of arms, giving it the appearance of a comb.
[0033] An arrangement comprising a head gimbal suspension (e.g., the HGA 110), including a bend to which the head slider is coupled, an actuating arm (e.g., the arm 132) and / or a load beam to which the bend is coupled, and an actuator (e.g., the VCM) to which the actuating arm is coupled, can be collectively referred to as a head stack arrangement (HSA). However, an HSA may include more or fewer components than those described. For example, an HSA may refer to an arrangement that further includes electrical connection components. In general, an HSA is the arrangement configured to move the head slider to access portions of the medium 120 for read and write operations.
[0034] With further reference to Fig. 1. Electrical signals (e.g., current to the voice coil 140 of the VCM), comprising a write signal to and a read signal from the head 110a, are transmitted via a flexible cable assembly (FCA) 156 (or “flexible cable” or “flexible circuit board”). The connection between the flexible cable 156 and the head 110a may include an arm electronics (AE) module 160, which may include an integrated preamplifier for the read signal as well as other electronic components of the read and write channels. The AE module 160 may be attached to the carriage 134 as shown. The flexible cable 156 may be coupled to an electrical connector block 164, which in some configurations provides an electrical connection through an electrical feedthrough provided by an HDD enclosure 168.The HDD enclosure 168 (or “enclosure base” or “base plate” or simply “base”) in conjunction with an HDD cover provides a semi-sealed (or in some configurations hermetically sealed) protective enclosure for the information storage components of the HDD 100.
[0035] Other electronic components, including a disk controller and servo electronics with a digital signal processor (DSP), provide electrical signals to the drive motor, the voice coil 140 of the VCM, and the head 110a of the HGA 110. The electrical signal provided to the drive motor enables it to rotate and provide torque to the spindle 124, which in turn is transmitted to the medium 120 attached to the spindle 124. This causes the medium 120 to rotate in a direction 172. The rotating medium 120 creates an air cushion that acts as an air bearing on which the air bearing surface (ABS) of the glider 110b runs, allowing the glider 110b to float above the surface of the medium 120 without coming into contact with a thin magnetic recording layer where information is recorded.Similarly, in an HDD where a lighter gas than air is used, such as helium as a non-restrictive example, the rotating medium 120 creates a gas cushion that acts as a gas or fluid bearing on which the glider 110b runs.
[0036] The electrical signal supplied to the voice coil 140 of the VCM enables the head 110a of the HGA 110 to access a track 176 on which information is recorded. Thus, the armature 136 of the VCM oscillates through an arc 180, allowing the head 110a of the HGA 110 to access various tracks on the medium 120. Information is stored on the medium 120 in a multitude of radially nested tracks within sectors on the medium 120, such as sector 184. Accordingly, each track consists of a multitude of sectored track sections (each can also be referred to as a "track sector"), such as a sectored track section 188. Each sectored track section 188 can include recorded information and a header containing error correction code information and a servo burst signal pattern, such as an ABCD servo burst signal pattern, which is information that identifies the track 176.When accessing track 176, the read element of the head 110a of the HGA 110 reads the servo burst signal pattern, which provides the servo electronics with a position error signal (PES). This PES controls the electrical signal supplied to the voice coil 140 of the VCM, thus enabling the head 110a to follow track 176. After locating track 176 and identifying a specific sectored track segment 188, the head 110a either reads information from track 176 or writes information to track 176, depending on instructions that the disk controller receives from an external agent, for example, a microprocessor of a computer system.
[0037] The electronic architecture of a hard disk drive (HDD) incorporates a variety of electronic components for performing their respective functions in operating the HDD, such as a hard disk controller (HDC), an interface controller, an arm electronics module, a data channel, a motor driver, a servo processor, buffer memory, etc., some, but not necessarily all, of which may be part of an HDDC, as described herein. Two or more such components may be combined on a single integrated circuit board, referred to as a "system-on-a-chip" (SOC). Some, if not all, of these electronic components are typically arranged on a circuit board that is coupled to the bottom of an HDD, such as the HDD enclosure 168.
[0038] References herein to a hard disk drive, such as the HDD 100, which refers to Fig.As illustrated and described in Figure 1, a data storage device, sometimes referred to as a hybrid drive, may have the functionality of both a conventional hard disk drive (HDD) (see, for example, the HDD 100) and a solid-state storage device (SSD) using non-volatile memory, such as flash memory, or other solid-state memory (e.g., integrated circuits) that is electrically erasable and programmable. Since the operation, management, and control of the different types of storage media typically differ, the solid-state portion of a hybrid drive may include its own corresponding control functionality, which, along with the HDD functionality, can be integrated into a single controller.A hybrid drive can be designed and configured to utilize the solid-state portion in various ways, such as, as non-limiting examples, using the solid-state storage as cache memory, for storing frequently accessed data, for storing I / O-intensive data, and so on. Furthermore, a hybrid drive can essentially be designed and configured as two storage devices in a single enclosure—that is, a traditional hard disk drive and an SSD—with either one or more interfaces for host connectivity. Extensions and alternatives
[0039] The preceding description described embodiments of the invention with reference to numerous specific details that may vary from implementation to implementation. Therefore, various modifications and changes may be made to it without departing from the broader spirit and scope of protection of the embodiments. Thus, the sole and exclusive indicator of what the invention is and what the applicants refer to as the invention is the set of claims arising from this application, in the specific form in which those claims are asserted, including any subsequent amendment. All definitions expressly set forth herein for terms contained in such claims govern the meaning of the terms used in the claims.Therefore, no limitation, element, property, feature, advantage, or attribute that is not expressly mentioned in a claim should in any way restrict the scope of protection of such claim. Accordingly, the description and drawings should be considered illustrative rather than limiting.
[0040] Furthermore, this description may specify that certain process steps can be performed in a particular order, and alphabetical and alphanumeric reference symbols may be used to identify specific steps. Unless expressly stated otherwise in the description, embodiments are not necessarily restricted to a specific order in which such steps are performed. In particular, the reference symbols serve only to conveniently identify steps and are not intended to specify or require a particular order in which such steps are performed.
Claims
[1] Data storage system, comprising: a main printed circuit board (PCB) comprising at least one system control circuit; and a plurality of stacked storage devices, each storage device being mechanically and electrically connected to the main PCB at or near a longitudinal end of the storage device; the system control switching logic is centrally positioned on the main PCB, thus minimizing the overall length of the electrical transmission line between the multitude of storage devices and the system switching logic. [2] Data storage system according to claim 1, wherein the system control switching logic is positioned on the main PCB such that each length of electrical transmission line between a respective storage device and the system control switching logic is substantially equivalent. [3] Data storage system according to claim 1, wherein the plurality of storage devices comprises a plurality of hard disk drives (HDDs). [4] Data storage system according to claim 1, wherein: The system control switching logic includes a single-channel switching logic; and The main PCB includes: a multiplexer switching logic between the system control switching logic and at least two groupings of the storage devices; and a T-connection between the multiplexer switching logic and each pair of storage devices of each grouping of storage devices. [5] Data storage system according to claim 1, wherein the system control switching logic comprises a two-channel switching logic. [6] Data storage system according to claim 5, wherein the main PCB comprises: a first multiplexer switching logic between a channel of the system control switching logic and at least one first set of storage devices; and a second multiplexer switching logic between another channel of the system control switching logic and at least a second set of storage devices. [7] Data storage system according to claim 6, wherein the main PCB further comprises: a first T-connection between the first multiplexer switching logic and a pair of the first set of storage devices; and a second T-connection between the first multiplexer switching logic and another pair of the first set of storage devices. [8] Data storage system according to claim 1, wherein: The multitude of storage devices includes a multitude of hard disk drives (HDDs), each HDD comprising: a variety of disc media mounted rotatably on a motor spindle, a multitude of head gliders, each head glider accommodating a read / write converter configured to read from and write to a disk medium of the multitude of disk media, one or more actuators configured to move the head sliders to access sections of the disk medium, and Electronics, including a preamplifier, actuation control, motor control and sensor switching logic; and The main PCB also includes large-scale power switching logic (PLSI switching logic) configured to send signals to the electronics of each hard disk drive via a multiplexer on the main PCB. [9] Data storage system according to claim 1, wherein: The multitude of storage devices includes a multitude of hard disk drives (HDDs), each HDD comprising: a variety of disc media mounted rotatably on a motor spindle, a multitude of head gliders, each head glider accommodating a read / write converter configured to read from and write to a disk medium of the multitude of disk media, one or more actuators configured to move the head sliders to access sections of the disk medium, and electronics, including large-scale power switching logic (PLSI switching logic), a preamplifier, actuation control, motor control, and sensor switching logic. [10] Data storage system according to claim 1, wherein the main PCB further comprises a plurality of independent system control switching logics, each system control switching logic being configured to operate with a corresponding logical unit of the memory corresponding to the plurality of storage devices. [11] Data storage system according to claim 1, further comprising: a plurality of fixed interposer printed circuit boards, each fixed interposer printed circuit board being configured to electrically connect a corresponding connector of the main board to a corresponding board-to-board connector of a storage device of the plurality of storage devices; wherein each mainboard connector is one of a group consisting of a board edge connector, a non-floating board-to-board connector, a floating board-to-board connector and a compression connector. [12] Data storage system according to claim 1, further comprising: a plurality of flexible interposer printed circuit boards, each configured to electrically connect a corresponding connector of the main board to a corresponding board-to-board connector of a storage device of the plurality of storage devices; where each mainboard connector is one of a group consisting of a board-to-flex connector, a non-floating board-to-board connector, a floating board-to-board connector, and a compression connector. [13] Data storage system according to claim 1, further comprising: a plurality of flexible interposer printed circuit boards, each configured to electrically connect a corresponding connector of the main board to a corresponding board-to-flex connector of a storage device of the plurality of storage devices; where each mainboard connector is one of a group consisting of a board-to-flex connector, a non-floating board-to-board connector, a floating board-to-board connector, and a compression connector. [14] Data storage system, comprising: a main printed circuit board (PCB) comprising at least one system control circuit; and a large number of stacked hard disk drives (HDDs), each HDD being mechanically and electrically connected to the main PCB at or near one longitudinal end of the HDD; wherein the system control switching logic is positioned on the main PCB such that the length of the electrical transmission line between each HDD and the system control switching logic is essentially equivalent. [15] Data storage system according to claim 14, wherein: The multitude of HDDs comprises a first grouping of four stacked HDDs connected to one lateral side of the main PCB, and a second grouping of four stacked HDDs connected to the other lateral side of the main PCB; and Each length of the electrical transmission line between a given HDD and the system control switching logic is less than 100 millimeters (mm). [16] Data storage system according to claim 15, wherein: The system control switching logic includes a single-channel switching logic; and The main PCB includes: a first multiplexer switching logic between the system control switching logic and the first and second grouping of HDDs; a multitude of secondary multiplexer switching logics between the primary multiplexer switching logic and each of the first and secondary groupings of HDDs; and a T-connection between every second multiplexer switching logic and a pair of HDDs of the first and second groupings of HDDs. [17] Data storage system according to claim 14, wherein: The multitude of HDDs comprises a first grouping of four stacked HDDs connected to one lateral side of the main PCB, and a second grouping of four stacked HDDs connected to the other lateral side of the main PCB; The system control switching logic includes a two-channel switching logic; and The main PCB includes: a first multiplexer circuit between a first channel of the system controller circuit and the first grouping of HDDs; a second multiplexer circuit between a second channel of the system controller circuit and the second group of HDDs; a first T-connection between the first multiplexer switching logic and a first pair of the first grouping of HDDs; a second T-connection between the first multiplexer switching logic and a first pair of the second grouping of HDDs; a third T-connection between the second multiplexer switching logic and a second pair of the first grouping of HDDs; and a fourth T-connection between the second multiplexer switching logic and a second pair of the second grouping of HDDs. [18] Data storage system according to claim 14, wherein: Each HDD of the multitude of HDDs includes: a variety of disc media mounted rotatably on a motor spindle, a multitude of head gliders, each head glider accommodating a read / write converter configured to read from and write to a disk medium of the multitude of disk media, an actuator system configured to move the multitude of head sliders to access sections of the disk medium, and Electronics, including a preamplifier, actuation control, motor control and sensor switching logic; and The main board also includes large-scale power switching logic (PLSI switching logic) configured to send signals to at least one section of the electronics of each HDD via a multiplexer on the main PCB. [19] Data storage system according to claim 14, wherein: Each HDD of the multitude of HDDs includes: a variety of disc media mounted rotatably on a motor spindle, Means for housing a read / write converter configured to read from and write to a disk medium of the multitude of disk media, Means of moving the read / write converters to access sections of the disk medium, and Electronics, including large-scale power switching logic (PLSI switching logic), a preamplifier, actuation control, motor control and sensor switching logic. [20] Data storage system, comprising: a main printed circuit board (PCB) comprising at least one system control circuit; and multiple stacked hard disk drives (HDDs), each HDD being mechanically and electrically connected to the main PCB at or near one longitudinal end of the HDD, each HDD comprising: Disc media that are rotatably mounted on a motor spindle, Means of storing data by reading from and writing to a disk medium, Means of moving the means of storage in order to access sections of the disk medium, and Electronics, including a preamplifier, actuation control, motor control and sensor switching logic; the system control switching logic is positioned on the main PCB in such a way that the length of the electrical transmission line between each HDD and the system control switching logic is minimized.