阅读说明：本技术 将数据从非能量辅助磁盘表面迁移到能量辅助磁盘表面的数据存储设备 (Data storage device for migrating data from a non-energy-assisted disk surface to an energy-assisted disk surface ) 是由 P·巴拉苏布拉马尼亚姆 D·R·霍尔 于 2020-06-11 设计创作，主要内容包括：本发明题为“将数据从非能量辅助磁盘表面迁移到能量辅助磁盘表面的数据存储设备”。本发明公开了一种数据存储设备,数据存储设备包括被配置为访问第一磁盘表面的非能量辅助(NEA)磁头和被配置为访问第二磁盘表面的能量辅助(EA)磁头。数据存储设备还包括控制电路,控制电路被配置为将数据写入第一磁盘表面并且将数据的至少一部分迁移到第二磁盘表面。(The invention provides a data storage device for migrating data from a non-energy-assisted disk surface to an energy-assisted disk surface. A data storage device includes a non-energy assisted (NEA) head configured to access a first disk surface and an Energy Assisted (EA) head configured to access a second disk surface. The data storage device also includes control circuitry configured to write data to the first disk surface and to migrate at least a portion of the data to the second disk surface.)

1. A data storage device, comprising:

a first disk surface;

a non-energy-assisted (NEA) head configured to access the first disk surface;

a second disk surface;

a first Energy Assisted (EA) head configured to access the second disk surface; and

a control circuit configured to:

writing data to the first disk surface; and

migrating at least a portion of the data to the second disk surface.

2. The data storage device of claim 1, wherein at least a portion of the first disk surface operates as a write cache for write commands received from a host.

3. The data storage device of claim 2, wherein at least a portion of the data is migrated to the second disk surface by flushing at least a portion of the write cache.

4. The data storage device of claim 1, wherein the control circuitry is further configured to:

identifying cold data from the data written to the first disk surface; and

migrating the identified cold data to the second disk surface.

5. The data storage device of claim 1, further comprising a third disk surface and a second EA head configured to access the third disk surface, wherein the control circuitry is further configured to migrate at least a portion of the data from the first disk surface to the second disk surface and the third disk surface by:

first writing a first segment of the data to the second disk surface; and

second writing a second segment of the data to the third disk surface.

6. The data storage device of claim 5, wherein the control circuitry is further configured to:

configuring a length of the first section to control an operating temperature of the first EA head; and

configuring a length of the second section to control an operating temperature of the second EA head.

7. The data storage device of claim 6, wherein the control circuitry is further configured to:

measuring a quality of the first EA head;

measuring a quality of the second EA head;

configuring the length of the first section based on the measured quality of the first EA head; and

configuring the length of the second section based on the measured quality of the second EA head.

8. The data storage device of claim 5, wherein the control circuitry is further configured to migrate at least a portion of the data from the first disk surface to the second disk surface and the third disk surface by:

writing a third section of the data to the second disk surface; and

writing a fourth sector of the data to the third disk surface.

9. The data storage device of claim 8, wherein the first write, the second write, the third write, and the fourth write are interleaved.

10. The data storage device of claim 5, wherein at least a portion of the first write is concurrent with at least a portion of the second write.

11. A data storage device, comprising:

a first disk surface;

a non-energy-assisted (NEA) head configured to access the first disk surface;

a second disk surface;

a first Energy Assisted (EA) head configured to access the second disk surface;

a third disk surface;

a second Energy Assisted (EA) head configured to access the third disk surface; and

control circuitry configured to write data to the first disk surface and to migrate at least a portion of the data from the first disk surface to the second disk surface and the third disk surface by at least:

first writing a first segment of the data to the second disk surface; and

second writing a second segment of the data to the third disk surface.

12. The data storage device of claim 11, wherein the control circuitry is further configured to:

configuring a length of the first section to control an operating temperature of the first EA head; and

configuring a length of the second section to control an operating temperature of the second EA head.

13. The data storage device of claim 12, wherein the control circuitry is further configured to:

measuring a quality of the first EA head;

measuring a quality of the second EA head;

configuring the length of the first section based on the measured quality of the first EA head; and

configuring the length of the second section based on the measured quality of the second EA head.

14. The data storage device of claim 11, wherein the control circuitry is further configured to migrate at least a portion of the data from the first disk surface to the second disk surface and the third disk surface by:

writing a third section of the data to the second disk surface; and

writing a fourth sector of the data to the third disk surface.

15. The data storage device of claim 14, wherein the first write, the second write, the third write, and the fourth write are interleaved.

16. The data storage device of claim 11, wherein at least a portion of the first write is concurrent with at least a portion of the second write.

17. The data storage device of claim 11, wherein at least a portion of the first disk surface operates as a write cache for write commands received from a host.

18. The data storage device of claim 17, wherein at least a portion of the data is migrated to the second disk surface and the third disk surface by flushing at least a portion of the write cache.

19. The data storage device of claim 11, wherein the control circuitry is further configured to:

identifying cold data from the data written to the first disk surface; and

migrating the identified cold data to the first disk surface and the second disk surface.

20. A data storage device, comprising:

a first disk surface;

a non-energy-assisted (NEA) head configured to access the first disk surface;

a second disk surface;

a first Energy Assisted (EA) head configured to access the second disk surface;

means for writing data to said first disk surface; and

means for migrating at least a portion of the data to the second disk surface.

Background

Data storage devices, such as disk drives, include a disk and a head connected to a distal end of an actuator arm that is pivoted by a Voice Coil Motor (VCM) to position the head radially over the disk. The magnetic disk includes a plurality of radially spaced concentric tracks for recording user data sectors and embedded servo sectors. The embedded servo sectors include head positioning information (e.g., track addresses) that is read by the head and processed by a servo controller to control the velocity of the actuator arm as it seeks from track to track.

A disk drive typically includes a plurality of disks, each disk having a top surface and a bottom surface that are accessed by a corresponding head. That is, the VCM typically rotates multiple actuator arms about pivots in order to simultaneously position multiple heads over respective disk surfaces based on servo data recorded on each disk surface. FIG. 1 shows a prior art disk format 2 that includes servo sectors 6 recorded by a circumference around each servo track₀-6_NA plurality of servo tracks 4 are defined. Each servo sector 6_iIncluding a preamble 8 for storing a periodic pattern that allows proper gain adjustment and timing synchronization of the read signal and a synchronization mark 10 for storing a special pattern for symbol synchronization to a servo data field 12. The servo data field 12 stores coarse head positioning information, such as servo track addresses, used to position the head over a target data track during a seek operation. Each servo sector 6_iAlso included are sets of servo bursts 14 (e.g., N servo bursts and Q servo bursts) that are recorded at predetermined phases relative to each other and relative to the servo track centerline. The phase based servo bursts 14 provide fine head position information for centerline tracking while accessing the data tracks during write/read operations. A Position Error Signal (PES) is generated by reading servo bursts 14, where the PES represents the measured position of the head relative to the centerline of the target servo track. The servo controller processes the PES to generate control signals that are applied to a head actuator (e.g., a voice coil motor) to actuate the head radially over the disk in a direction that reduces the PES.

Drawings

FIG. 1 illustrates a prior art disk format that includes a plurality of servo tracks defined by servo sectors.

Fig. 2A and 2B illustrate a data storage device in the form of a disk drive according to an embodiment, the data storage device including a non-energy-assisted (NEA) head actuated over a first disk surface and an energy-assisted (EA) head actuated over a second disk surface.

Fig. 2C is a flow diagram according to an embodiment in which data is first written to an NEA disk surface using an NEA head, and then migrated to the EA disk surface using an EA head.

FIG. 3 is a flow diagram according to an embodiment in which at least a portion of a NEA disk surface operates as a write cache flushed to an EA disk surface.

FIG. 4 is a flow diagram according to an embodiment in which after data is written to a NEA disk surface, cold data is identified and then migrated to an EA disk surface.

FIG. 5A illustrates an embodiment in which a disk drive includes a plurality of disks including at least one NEA disk surface and at least two EA disk surfaces.

FIG. 5B is a flow diagram according to an embodiment in which data is written to multiple EA disk surfaces in an interleaved manner when migrating data from the NEA disk surfaces to prevent overheating of the EA heads.

Fig. 6 is a flow diagram according to an embodiment, where a quality of an EA head is measured to configure a migration data segment length for avoiding overheating of the EA head.

FIG. 7 illustrates an embodiment where when migrating data interleave to EA disk surface, the interleave order is based on a calibrated data sector length for each EA disk surface.

Detailed Description

Fig. 2A and 2B illustrate a data storage device in the form of a disk drive according to an embodiment, the data storage device including a non-energy-assisted (NEA) head 16 configured to access a first disk surface 18, and configured to access a second disk surface 22₁First Energy Assisted (EA) head 20₁. The disk drive also includes control circuitry 24 configured to execute the flowchart of FIG. 2C, wherein data is written to the first disk surface (block 26), and at least a portion of the data is subsequently migrated to the second disk surface (block 28).

In the embodiment of FIG. 2A, each disk surface includes a plurality of servo sectors 30 defining a plurality of servo tracks₀-30_NWherein the data tracks 32 are defined at the same or different radial densities relative to the servo tracks. Control circuit 24 processesA read signal 34 from the head is used to demodulate the servo sectors and generate a Position Error Signal (PES) indicative of the error between the actual position of the head and the target position relative to the target track. The servo control system in the control circuit 24 filters the PES using a suitable compensation filter to generate a control signal 36 that is applied to the VCM 38, which pivots the actuator arm 40 about a pivot to actuate the head radially over the disk in a direction that reduces the PES. Servo sector 30₀-30_NAny suitable head position information may be included, such as track addresses for coarse positioning and servo bursts for fine positioning. The servo bursts may include any suitable pattern, such as an amplitude-based servo pattern or a phase-based servo pattern (FIG. 1).

In the embodiment of fig. 2B, NEA head 16 includes a suitable write element (e.g., an inductive coil), a suitable read element (e.g., a magnetoresistive element), and optionally a suitable Fly Height Actuator (FHA) configured to control the fly height of the head over the disk surface. In addition to these elements, EA head 20₁Also included is a suitable EA element to facilitate writing operations, such as a suitable laser (e.g., a laser diode) configured to heat the disk surface to achieve Heat Assisted Magnetic Recording (HAMR) or a suitable rotational torque oscillator (STO) configured to generate an auxiliary magnetic field to achieve Microwave Assisted Magnetic Recording (MAMR).

In one embodiment, the EA element and/or the recording element of the EA head may have a limited operational life due to degradation over time (e.g., due to thermal degradation). In one embodiment, as the EA head approaches the end of life, the corresponding disk surface is converted to a read-only disk surface, meaning that previously written data can still be read from the disk surface, but no new data is written to the disk surface. As described in more detail below, converting the disk surface to read-only may ultimately reduce the overall capacity of the disk drive when data stored on the read-only disk surface becomes invalid due to an overwrite operation. Thus, in one embodiment, to conserve disk drive capacity, the EA disk surface(s) are written to in a parsimonious manner, and in one embodiment, are used to store "cold data" that is not written to frequently.

In one embodiment, understood with reference to the flow diagram of fig. 3, at least a portion of the NEA disk surface may be configured as a write cache, wherein data associated with a new write command received from a host (block 42) is written by the first to the write cache of the NEA disk surface (block 44). Thereafter, based on any suitable criteria (such as the amount of free space remaining in the write cache), a decision is made to flush at least a portion of the write cache. When a decision is made to flush at least a portion of the write cache (block 46), at least a portion of the data is flushed from the write cache by migrating the data to one or more EA disk surfaces (block 48).

In another embodiment, understood with reference to the flow diagram of fig. 4, when a write command is received from a host (block 50), data associated with the write command is first written to the NEA disk surface (block 52). Data written to the NEA disk surface is evaluated over time to identify cold data based on any suitable criteria. In one embodiment, cold data is identified by evaluating write frequency of Logical Block Addresses (LBAs) assigned to the data, where LBAs having a low write frequency can be considered to store cold data, where the cold data is migrated to the EA disk surface (block 56) when the cold data is identified (block 54). Migrating cold data to the EA disk surface effectively migrates low frequency writes to the EA disk surface, thereby preserving EA head life.

In one embodiment, after migrating cold data to the EA disk surface and remapping LBAs assigned to the cold data to the EA disk surface, one or more of the LBAs may be overwritten by a new write command. When this occurs, in one embodiment, the data of the new write command is written to the EA disk surface (e.g., when performing log-structured writes such as Shingled Magnetic Recording (SMR), the data is written to the same physical location or a different physical location). That is, when a low write frequency LBA assigned to an EA disk surface is overwritten, in one embodiment, the data of the new write command is assumed to remain in a "cold data" state. In an alternative embodiment, when a low write frequency LBA assigned to an EA disk surface is overwritten, the data of the new write command is reclassified as "hot data" and thus is initially written to the NEA disk surface (e.g., written to the write cache of the NEA disk surface) and the corresponding LBA is remapped to the NEA disk surface. Over time, the LBA may again be identified as storing cold data, and thus again be migrated to the EA disk surface.

FIG. 5A shows an embodiment in which the data storage device may include multiple disks (e.g., disk 58)₁And a magnetic disk 58₂) Each disk has a top disk surface and a bottom disk surface. In the embodiment of FIG. 5A, the NEA head 16 is on the disk 58₁Is actuated over the top disk surface, and an EA head (20)₁-20₃) Is actuated over each of the remaining three disk surfaces. In other embodiments, two or more NEA heads may be actuated over respective disk surfaces and one or more EA heads may be actuated over respective disk surfaces. In embodiments that migrate data (e.g., cold data) from the NEA disk surface to multiple EA disk surfaces, the data may be migrated to each EA disk surface in a staggered manner to ensure that zones of the EA heads that do not overheat, thereby reducing thermal stress of each EA head.

An example of this embodiment is understood with reference to the flow diagram of fig. 5B, where when a write command is received from a host (block 60), data associated with the write command is first written to the NEA disk surface (block 62). Finally (such as when the amount of cold data stored on the NEA disk surface exceeds a predetermined threshold), a decision is made (block 64) to migrate at least some of the data to multiple ones of the EA disk surfaces (three EA disk surfaces in this example). In this embodiment, the migration of data is performed in sectors, such as by writing a data sector to a first EA disk surface (block 66), then writing a data sector to a second EA disk surface (block 68), and then writing a data sector to a third EA disk surface (block 70). The process of migrating the data in sectors to each EA disk surface in an interleaved manner is then repeated until the migration is complete or interrupted (e.g., due to a need to execute a host access command) at block 72. In this embodiment, the interleaved sequence for migrating data to the EA disk surface is sequential and cyclic (i.e., 1, 2, 3, … …), while in other embodiments the sequence may be in forward order followed by reverse order (i.e., 1, 2, 3, 2, 1, 2, 3, … …). In another embodiment described below, the interleaved sequence may be ordered based on the length of each data sector in order to balance the migration load of each EA disk surface. That is, in one embodiment, the sector length for migrating data to each EA disk surface may be calibrated based on the measured quality of the corresponding EA head, and the interleaved sequence may then be ordered to achieve a substantially balanced migration load on the EA disk surface.

An example of this embodiment is understood with reference to fig. 6, wherein a quality metric of the first EA head is measured (block 74), and a data sector length for migrating data to a corresponding disk surface is configured based on the measured quality metric (block 76). In one embodiment, the data sector length is selected to have a positive correlation with the quality of the EA head so that a higher quality EA head can perform longer sequential writes than a lower quality EA head. That is, higher quality EA heads may allow for longer sequential writes before significant stress due to overheating exists as compared to lower quality EA heads. In the embodiment of fig. 6, the quality of each EA head is measured to configure a corresponding data segment length, such as measuring a quality metric of a second EA head (block 78) and configuring a corresponding data segment length for the second EA head (block 80).

Any suitable quality metric of the EA head may be measured, such as overwrite capability, which may be measured by: a first frequency pattern is written to the EA disk surface, the first frequency pattern is overwritten with a second frequency pattern, and then a residual intensity of the first frequency pattern is measured during a read operation. In another embodiment, the quality metric of the EA head may be based on a calibrated operating power of the EA head, where a higher operating power may indicate a lower quality head. In yet another embodiment, the quality (e.g., endurance) of the EA head may be based on the heating effect of a fly-height actuator configured to adjust the fly height of the head to a nominal fly height during a write operation. EA heads requiring higher power to be applied to the fly-height actuator (and thus increased heat generation) can be considered lower quality heads.

In one embodiment, the quality of each EA head may be measured and updated periodically during the life of the data storage device, and corresponding adjustments may be made to the data sector length of each EA head as the quality metric may change over time (or as environmental conditions such as changes in ambient temperature). That is, in one embodiment, the quality (and heat-up tolerance) of each EA head may vary as one or more components of the head degrade over time and/or as heat-up effects change due to changes in environmental conditions (e.g., as ambient temperature fluctuates). Thus, in one implementation, the data segment length may vary over time to avoid excessive stress on the EA head during write operations.

Fig. 7 illustrates an embodiment in which the data sector length calibrated for each of the three EA heads is substantially the same for the first head and the third head, but shorter for the second head. That is, in this embodiment, the quality of the first EA head and the third EA head are substantially the same, while the quality of the second EA head is relatively lower. In this embodiment, the interleaving order used to migrate data to the EA disk surface may be configured to substantially balance the load when migrating data from the NEA disk surface. In the example shown in FIG. 7, the interleaving order is

1、2、3、2、1、2、3……

This results in data migrating to the second EA disk surface more often, but using smaller data sectors, thereby helping to balance the migration load on all three EA disk surfaces. In one embodiment, the migration load of each EA disk surface may be tracked over time and the interleaving order adjusted accordingly to maintain a substantially balanced migration load on the EA disk surfaces. That is, in one embodiment, the staggered order in which data is migrated may not be a repeating sequence, but a varying sequence that helps ensure load balancing.

In one embodiment, balancing the migration load on the EA disk surface as described above helps reduce access latency when reading and writing data when migrating data to multiple EA disk surfaces. For example, when migrating large video files from a NEA disk surface to multiple EA disk surfaces, maintaining a substantially balanced migration load helps ensure that the cylinders of interleaved data sectors are relatively close to each other, thereby reducing seek latency associated with accessing data tracks of each EA disk surface during read operations.

In one embodiment, data may be migrated to two or more EA disk surfaces by writing the data to the two or more disk surfaces concurrently (such as by writing to the top and bottom surfaces of the EA disk concurrently). In one embodiment, data may be concurrently written in data sectors of finite length, where concurrent writes to different groups of disk surfaces may be interleaved in a manner similar to interleaving a single write operation as described above, in order to avoid EA head overheating. When the calibrated data segment lengths of a group of concurrently written EA heads have different lengths, in one embodiment, the data segment length of each EA head in the group is configured to be the shortest calibrated length of all EA heads in the group.

In one embodiment, data may be written to at least the EA disk surface using a log structured write system, where new data is written to the head of the ring buffer and when LBAs are overwritten, previously written data may become invalid. Shingled Magnetic Recording (SMR) is an example of a log structured write system in which data is written as sequentially overlapping data tracks (i.e., previously written data tracks are partially overwritten by currently written data tracks). In one embodiment, when the valid sector of the ring buffer can be rewritten to the head of the ring buffer, the calibrated data sector length as described above can be used during a garbage collection operation of the EA disk surface to retrieve the storage area of the invalid data sector. In one embodiment, at least a portion of the NEA disk surface may operate as non-volatile memory that facilitates garbage collection operations to maintain operational status even when a power failure event is experienced.

In one embodiment, when degradation of an energy-assist element of an EA head reaches a critical level, the corresponding EA disk surface may be converted to a read-only disk surface (i.e., a write operation to the disk surface may be disabled). Before converting the EA disk surface to read-only, in one embodiment, the coldest data on the other disk surfaces may be migrated to the failing EA disk surface, and the relatively hotter data may be migrated away from the failing EA disk surface. In this way, cold data will remain valid and readable even if write operations have been disabled, even when the failed EA disk surface is converted to read-only.

The flow diagrams in the above embodiments may be implemented using any suitable control circuitry, such as any suitable integrated circuit or circuitry. For example, the control circuitry may be implemented within a read channel integrated circuit or in a component separate from the read channel, such as a data storage controller, or some of the operations described above may be performed by the read channel while other operations may be performed by the data storage controller. In one embodiment, the read channel and the data storage controller are implemented as separate integrated circuits, and in an alternative embodiment, they are fabricated as a single integrated circuit or system on a chip (SOC). Furthermore, the control circuit may comprise a suitably powered large scale integrated circuit (PLSI) implemented as a separate integrated circuit, integrated into the read channel or data storage controller circuit, or integrated into the SOC.

In one embodiment, the control circuit includes a microprocessor executing instructions operable to cause the microprocessor to perform the flow diagrams described herein. The instructions may be stored in any computer readable medium. In one embodiment, they may be stored on non-volatile semiconductor memory external to the microprocessor or integrated with the microprocessor in the SOC. In another embodiment, the instructions are stored on a magnetic disk and read into volatile semiconductor memory when the disk drive is powered on. In another embodiment, the control circuitry includes suitable logic circuitry, such as state machine circuitry. In some embodiments, at least some of the flowchart blocks may be implemented using analog circuitry (e.g., analog comparators, timers, etc.), and in other embodiments, some of the blocks may be implemented using digital circuitry or a combination of analog/digital circuitry.

In various embodiments, the disk drive may comprise a disk drive, a hybrid disk drive including non-volatile semiconductor memory, or the like. Further, some embodiments may include an electronic device, such as a computing device, data server device, media content storage device, etc., that includes a storage medium and/or control circuitry as described above.

The various features and processes described above may be used independently of one another or may be combined in various ways. All possible combinations and sub-combinations are intended to fall within the scope of the present disclosure. In addition, certain method, event, or process blocks may be omitted in some implementations. The methods and processes described herein are also not limited to any particular sequence, and the blocks or states associated therewith may be performed in other sequences as appropriate. For example, described tasks or events may be performed in an order different than that specifically disclosed, or multiple may be combined in a single block or state. Exemplary tasks or events may be performed serially, in parallel, or in some other manner. Tasks or events can be added to, or deleted from, the disclosed exemplary embodiments. The exemplary systems and components described herein may be configured differently than as described. For example, elements may be added, removed, or rearranged in comparison to the disclosed exemplary embodiments.

While certain exemplary embodiments have been described, these embodiments have been presented by way of example only, and are not intended to limit the scope of the invention disclosed herein. Thus, nothing in the above description is intended to imply that any particular feature, characteristic, step, module, or block is essential or necessary. Indeed, the novel methods and systems described herein may be embodied in a variety of other forms. Furthermore, various omissions, substitutions and changes in the form of the methods and systems described herein may be made without departing from the spirit of the embodiments disclosed herein.