Data management in a storage system

Abstract

A storage system, and a method of data management in the storage system, with non-volatile memory device characteristics determined during an inspection of non-volatile memory devices before a runtime operation of a storage device in the storage system including: a controller in the storage system: a drive-level control unit configured for an update of operational capabilities based on the non-volatile memory device characteristics during the runtime operation of the storage device and for a group of the non-volatile memory devices based on the operational capabilities; and a memory control unit, coupled to the drive-level control unit, the memory control unit configured to receive the operational capabilities for control of the non-volatile memory devices.

Description

TECHNICAL FIELD

The present invention relates generally to a storage system and more particularly to data management in a storage system.

BACKGROUND ART

Various forms of long-term storage in computer systems include, other than electromechanical hard disks, non-volatile storage rooted in semiconductor or other memory technology. NOT-AND (NAND) flash memory is one form of non-volatile memory used in solid-state storage devices. In a common configuration of flash memory, the memory cells are arranged in typical row and column fashion with circuitry for accessing individual cells. The data store elements (e.g., transistors) of those memory cells are configured to hold two logical states in the case of Single Level Cell (SLC) or more than two logical states in the case of Multi Level Cell (MLC).

A flash memory cell is light in weight, occupies very little space, and consumes less power than electromechanical disk drives. Construction of a storage system with this type of memory allows for much higher bandwidths and input/output operations per second (IOPS) than typical electromechanical disk drives. More importantly, it is especially rugged and can operate at a much high temperature range. It will withstand without adverse effects repeated drops, each of which would destroy a typical electromechanical hard disk drive. A problem exhibited by flash memory is endurance because it can tolerate only a limited number of operations over a given period of operational life of a storage system and as a result has a limited life.

Thus, a need still remains for better data management devices that can optimize operations and prolong the life of storage devices. In view of the ever-increasing commercial competitive pressures, along with growing consumer expectations and the diminishing opportunities for meaningful product differentiation in the marketplace, it is important to find answers for these problems.

Prior developments have long sought but not found optimal solutions to these problems. Hence, there remains a need that has long eluded those skilled in the art.

SUMMARY

The present disclosure covers various embodiments of a storage system and a method of data management in the storage system. In one implementation, the storage system includes a controller for updating operational capabilities to control non-volatile memory devices. The operational capabilities are updated based on non-volatile memory device characteristics during a runtime operation of a storage device in the storage system. For example, the operational capabilities include but not limited to retention measurements, endurance measurements, or bit error rate (BER). The non-volatile memory device characteristics associated with the non-volatile memory devices are obtained during an inspection of the non-volatile memory devices that occurs before the runtime operation of the storage device.

Certain embodiments have other steps or elements in addition to or in place of those mentioned above. The steps or elements will become apparent to those skilled in the art from a reading of the following detailed description when taken with reference to the accompanying drawings. The embodiments described herein are illustrative and should not limit the scope of the claimed invention as recited in the claims.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG. 1 is a storage system with data management in an embodiment of the present invention.

FIG. 2 is an exemplary hardware block diagram of the main memory controller.

FIG. 3 is an exemplary storage device architecture with a linked manufacturing process.

FIG. 4 is a flow chart of a method of data management in a storage system in a further embodiment of the present invention.

DETAILED DESCRIPTION

The following embodiments are described in sufficient detail to enable those skilled in the art to make and use the invention. It is to be understood that other embodiments would be evident based on the present disclosure, and that system, process, or mechanical changes may be made without departing from the scope of the present invention.

In the following description, numerous specific details are given to provide a thorough understanding of the invention. However, it will be apparent that the invention may be practiced without these specific details. In order to avoid obscuring the present invention, some well-known circuits, system configurations, and process steps are not disclosed in detail.

The drawings showing embodiments of the system may be drawn not to scale.

The same numbers are used in all the drawing FIGs. to relate to the same elements. The embodiments have been numbered first embodiment, second embodiment, etc. as a matter of descriptive convenience and are not intended to have any other significance or provide limitations for the present invention.

Various embodiments described here include a new approach for data management of endurance in a storage system. This approach includes a method of data management based on non-volatile memory device characteristics determined during an inspection of non-volatile memory devices before a runtime operation of a storage device in a storage system including: performing by a controller in the storage system: updating operational capabilities based on the non-volatile memory device characteristics during the runtime operation of the storage device; grouping the non-volatile memory devices based on the operational capabilities; and receiving the operational capabilities for controlling the non-volatile memory devices.

Various embodiments described here also include a storage system with non-volatile memory device characteristics determined during an inspection of non-volatile memory devices before a runtime operation of a storage device in the storage system including: a controller in the storage system: a drive-level control unit configured for an update of operational capabilities based on the non-volatile memory device characteristics during the runtime operation of the storage device and for a group of the non-volatile memory devices based on the operational capabilities; and a memory control unit, coupled to the drive-level control unit, the memory control unit configured to receive the operational capabilities for control of the non-volatile memory devices.

The current state of technology does not address problems solved by the embodiments described herein. The problems are related to drives that are built with specific device types and there is no selection of feed forward process that is used to group devices or align a group of devices with individual or groups of storage devices.

The problems are also related to current drive firmware algorithms that are for the most part static in nature. One of the typical methods for the reuse of erase blocks in the algorithms is a “round robin” scheme. Additionally, some firmware using the algorithms keep “short lists” of erase blocks that can be free or available for reuse based on a simple list. These simple algorithms have a tendency to overuse a small subset of the total of erase blocks that are available. The erase blocks in the subset are used until they eventually fail and are taken out of a pool of available erase blocks.

The term “erase block” referred to herein is defined as a group of pages, which is the smallest number of pages that are erased at one time. The term “page” referred to herein is defined as a memory component that is programmed as an individual unit. The page is a smallest group of data bytes that are read from or written to in an erase block.

Referring now to FIG. 1, therein is shown a storage system 100 with data management in an embodiment of the present invention. The storage system 100 includes a mechanism for an intelligent flash management. FIG. 1 depicts a high-level architecture diagram of a storage device using characterization data associated with non-volatile memory devices 102 at runtime.

This concept can be constructed and used in a solid state drive (SSD) under development. This concept can also be retrofitted into almost any SSD product with a design that requires a process to recover data after long retention times or an increase in data integrity at boot time. Functions or operations of the storage system 100 can be implemented in modules.

The term “retention” referred to herein is defined as an ability of memory cells to retain the programmed or correct information. Retention refers to an amount of correct data after a given period, which is a time when a drive is powered, not powered, or a combination thereof.

The term “module” referred to herein can include software, hardware, or a combination thereof in the present invention in accordance with the context in which the term is used. For example, the software can be machine code, firmware, embedded code, and application software. Also for example, the hardware can be circuitry, processor, computer, integrated circuit, integrated circuit cores, a microelectromechanical system (MEMS), passive devices, environmental sensors including temperature sensors, or a combination thereof.

The storage system 100 includes a main memory controller 104. The main memory controller 104 includes a host interface controller 106 for interfacing and interacting with a host system (not shown). The main memory controller 104 includes a drive-level control unit 108 for interfacing with the host interface controller 106 and providing the intelligence of the main memory controller 104.

The drive-level control unit 108 controls or manages data stored in operational characteristics tables 110, which are information used to keep a record of capabilities of each memory component or a portion of the memory component. The drive-level control unit 108 evaluates operational capabilities 112 stored in the operational characteristics tables 110.

The drive-level control unit 108 dynamically updates the operational capabilities 112. The drive-level control unit 108 accesses the operational characteristics tables 110 that are updated with the operational capabilities 112. For example, the term “dynamically” can refer to updates that are non-static including continuous, periodical, or triggered by an event.

The drive-level control unit 108 can dynamically evaluate the operational capabilities 112. The drive-level control unit 108 can dynamically evaluate the operational capabilities 112 by dynamically determining values or states of the operational capabilities 112 at predetermined intervals or times throughout the operation of the non-volatile memory devices 102.

The values or states of the operational capabilities 112 are dynamically determined as opposed to being statically determined at a predetermined time or the beginning of the operation of the non-volatile memory devices 102 after power up.

The operational capabilities 112 are information of or associated with the non-volatile memory devices 102. The operational capabilities 112 include information used to identify the non-volatile memory devices 102 or portions of the non-volatile memory devices 102. The operational capabilities 112 include information associated with current states of erase blocks 114 in the non-volatile memory devices 102 or how the erase blocks 114 are currently used.

The operational capabilities 112 include measurement information associated with the erase blocks 114 of the non-volatile memory devices 102 and used to control or manage the non-volatile memory devices 102. The operational capabilities 112 include information associated with current states and capabilities of the erase blocks 114 as well as information that indicate how the erase blocks 114 are to be used. The operational capabilities 112 are stored as entries in the operational characteristics tables 110.

The main memory controller 104 includes a memory control unit 116 for interfacing with the drive-level control unit 108 and enabling external communication to and from the main memory controller 104. The memory control unit 116 communicates with the non-volatile memory devices 102.

The drive-level control unit 108 accesses the operational characteristics tables 110 to retrieve and send the operational capabilities 112 to the memory control unit 116 to control or manage the non-volatile memory devices 102. The drive-level control unit 108 can also generate control information based on the operational capabilities 112 and send the control information to the memory control unit 116 to control or manage the non-volatile memory devices 102.

Referring now to FIG. 2, therein is shown an exemplary hardware block diagram of the main memory controller 104. The main memory controller 104 includes the host interface controller 106 of FIG. 1, the drive-level control unit 108 of FIG. 1, the memory control unit 116 of FIG. 1, and the operational characteristics tables 110 of FIG. 1.

The main memory controller 104 can include a control unit 202, a storage unit 204, a memory interface unit 206, and a host interface unit 208. The control unit 202 can include a control interface 210. The control unit 202 can execute a software 212 stored in the storage unit 204 to provide the intelligence of the main memory controller 104.

The control unit 202 can be implemented in a number of different manners. For example, the control unit 202 can be a processor, an embedded processor, a microprocessor, a hardware control logic, a hardware finite state machine (FSM), a digital signal processor (DSP), or a combination thereof.

The control interface 210 can be used for communication between the control unit 202 and other functional units in the main memory controller 104. The control interface 210 can also be used for communication that is external to the main memory controller 104.

The control interface 210 can receive information from the other functional units or from external sources, or can transmit information to the other functional units or to external destinations. The external sources and the external destinations refer to sources and destinations external to the main memory controller 104.

The control interface 210 can be implemented in different ways and can include different implementations depending on which functional units or external units are being interfaced with the control interface 210. For example, the control interface 210 can be implemented with a dedicated hardware including an application-specific integrated circuit (ASIC), a configurable hardware including a field-programmable gate array (FPGA), a discrete electronic hardware, or a combination thereof.

The storage unit 204 can include both hardware and the software 212. For example, the software 212 can include control firmware. The storage unit 204 can include a volatile memory, a nonvolatile memory, an internal memory, an external memory, or a combination thereof. For example, the storage unit 204 can be a nonvolatile storage such as non-volatile random access memory (NVRAM), Flash memory, disk storage, or a volatile storage such as static random access memory (SRAM).

The storage unit 204 can include a storage interface 214. The storage interface 214 can also be used for communication that is external to the main memory controller 104. The storage interface 214 can receive information from the other functional units or from external sources, or can transmit information to the other functional units or to external destinations. The external sources and the external destinations refer to sources and destinations external to the main memory controller 104.

The storage interface 214 can include different implementations depending on which functional units or external units are being interfaced with the storage unit 204. The storage interface 214 can be implemented with technologies and techniques similar to the implementation of the control interface 210.

The memory interface unit 206 can enable external communication to and from the main memory controller 104. For example, the memory interface unit 206 can permit the main memory controller 104 to communicate with the non-volatile memory devices 102 of FIG. 1.

The memory interface unit 206 can include a memory interface 216. The memory interface 216 can be used for communication between the memory interface unit 206 and other functional units in the main memory controller 104. The memory interface 216 can receive information from the other functional units or can transmit information to the other functional units.

The memory interface 216 can include different implementations depending on which functional units are being interfaced with the memory interface unit 206. The memory interface 216 can be implemented with technologies and techniques similar to the implementation of the control interface 210.

The host interface unit 208 allows the host system (not shown) to interface and interact with the main memory controller 104. The host interface unit 208 can include a host interface 218 to provide communication mechanism between the host interface unit 208 and the host system.

The control unit 202 can operate the host interface unit 208 to send control or status information generated by the main memory controller 104 to the host system. The control unit 202 can also execute the software 212 for the other functions of the main memory controller 104. The control unit 202 can further execute the software 212 for interaction with the non-volatile memory devices 102 via the memory interface unit 206.

The functional units in the main memory controller 104 can work individually and independently of the other functional units. For illustrative purposes, the main memory controller 104 is described by operation of the main memory controller 104 with the host system and the non-volatile memory devices 102. It is understood that the main memory controller 104, the host system, and the non-volatile memory devices 102 can operate any of the modules and functions of the main memory controller 104.

Referring now to FIG. 3, therein is shown an exemplary storage device architecture with a linked manufacturing process. The manufacturing process is depicted below a dash line in FIG. 3. The embodiments described herein combine an ability to characterize components including the non-volatile memory devices 102 during the manufacturing process and during operations of storage devices 302 with the non-volatile memory devices 102. One of the storage devices 302 is depicted in FIG. 3. Portions of the storage devices 302 have been described above in FIG. 1.

Measurements from the characterization of the non-volatile memory devices 102 are used to improve performance and reliability of the storage device with the non-volatile memory devices 102. In addition to the characterization from the manufacturing process, the embodiments described herein also take into account grouping and regrouping of the non-volatile memory devices 102 based on runtime data or the operational capabilities 112.

The term “regroup” refers to changing assignment of the non-volatile memory devices 102 to the storage devices 302. For example, in a regrouping process, the non-volatile memory devices 102 that were used to build or assign to one of the storage devices 302 can be assigned to another of the storage devices 302, depending on the operational capabilities 112 of the non-volatile memory devices 102 as the storage devices 302 age. Also for example, any number of the non-volatile memory devices 102 that were used to build or assign to one of the storage devices 302 may still be assigned to the one of the storage devices 302.

The term “age” referred to herein indicates how long a storage system or a memory component has existed or has been in operations. For example, the age can be based on a number of erase cycles, how long it has been since the last time an erase block was written, an average BER an erase block is yielding, a temperature at which a device has been run, or a combination thereof.

FIG. 3 depicts the main memory controller 104 having the host interface controller 106 for interfacing with the host system (not shown) and the drive-level control unit 108 for controlling and managing the data stored in the operational characteristics tables 110. The main memory controller 104 includes the memory control unit 116 for interfacing with the non-volatile memory devices 102.

The storage system 100 includes a number of functions. One of the functions is to assemble drives or the storage devices 302 with memory components or the non-volatile memory devices 102 that have been sorted into performance groups 304, which are identified based on non-volatile memory device characteristics 306 of the non-volatile memory devices 102. The non-volatile memory device characteristics 306 are measured by a characterization device 308.

The term “non-volatile memory device characteristics” referred to herein refers to generally how a device performs a function as required by a storage device. For example, the non-volatile memory device characteristics include but not limited to retention measurements, endurance measurements, BER, and any other measurements. The term “endurance” referred to herein is defined as a number of operations a memory device tolerates over a given period of operational life of a storage system.

The non-volatile memory devices 102 are sorted into the performance groups 304 by the characterization device 308. The performance groups 304 can be identified based on and during incoming inspections of the non-volatile memory devices 102.

The incoming inspections occur before runtime operations of the storage devices 302 and the non-volatile memory devices 102. The term “runtime” refers to a period after the manufacturing process, a power-up cycle, and a configuration period. For example, the runtime can refer to the storage devices 302 and the non-volatile memory devices 102.

The incoming inspections can be performed on the non-volatile memory devices 102 for lot codes from certain predetermined wafers. The lot codes of sample lots 310 can be inspected. In these lots, a predetermined number of parts or the non-volatile memory devices 102 can be inspected. The sample lots 310 can represent incoming device lots to be tested and sorted. For example, 10 out of every 1000 parts in each of the sample lots 310 can be inspected.

A characterization test in the manufacturing process can be performed by the characterization device 308 for each of the sample lots 310 to find out or determine the non-volatile memory device characteristics 306. The non-volatile memory device characteristics 306 can include an average BER associated with the non-volatile memory devices 102 that are being measured. The characterization test can be used to determine where the mean of the non-volatile memory device characteristics 306 fits.

The term “bit error rate” (BER) referred to herein is defined as a number of incorrect bits in a data stream stored in a memory device. The BER can be detected within a code word protected by error correction code (ECC). The term “code word” referred to herein is defined as a group of data bytes covered by a single of multiple error correction code (ECC) parity words. The term “error correction code” (ECC) referred to herein is defined as parity data generated over a set of data grouped into a code word.

The non-volatile memory devices 102 can be of a category associated with their average BER. For example, an average BER can be determined for each of the sample lots 310. As a specific example, an average BER of one of the sample lots 310 can be 1×10⁻³ after 10,000 P/E cycles in one of the performance groups 304. In this example, another average BER of another of the sample lots 310 can be 2×10⁻³ after 10,000 P/E cycles in another of the performance groups 304, whereby the average BER and the another average BER are different from each other.

The term “program/erase cycle” (P/E cycle) referred to herein is defined as a base level operation of how data is replaced within an erase block. For example, a memory device including NAND and other memory types can have a limited number of useful P/E cycles.

Therefore, for incoming inspections, a group as a whole, referred to by the lot codes or groups of devices, would have certain performance characteristics. When the non-volatile memory devices 102 are classified in general, whether by groups or by individual characteristics, decisions can be made by an assignment device 312 on that classification of how to assemble drives.

The assignment device 312 performs a device-to-drive assignment or device selection by selecting which of the non-volatile memory devices 102 are to be assigned to the storage devices 302 based on the results of the characterization process performed by the characterization device 308. The results of the characterization process can include the non-volatile memory device characteristics 306 of the non-volatile memory devices 102.

The non-volatile memory device characteristics 306 can be provided by the assignment device 312 to the drive-level control unit 108 to update the operational capabilities 112 in the operational characteristics tables 110. The non-volatile memory device characteristics 306 are specific device characterization parameters. The operational capabilities 112 are updated at predetermined intervals during the runtime operations of the storage devices 302.

Another of the functions is to select sorted memory devices or the non-volatile memory devices 102 that have been sorted for drive assembly based on a predicted use model 314 for the drive or the storage devices 302. In the embodiments described herein, the term “sort” refers to selection of memory devices.

As an example, the non-volatile memory devices 102 can be sorted or selected by intermixing two different sample lots together to determine the non-volatile memory device characteristics 306. In this example, the non-volatile memory devices 102 can be selected using components that are creams of the crop or best of the best components in the two different sample lots based on their non-volatile memory device characteristics.

The predicted use model 314 includes information associated with classes 316 that indicate how memory components are used. The non-volatile memory devices 102 can be sorted or selected in a factory and they are going to be graded into different scales or the classes 316. For example, the predicted use model 314 can be associated with the classes 316, which indicates how the non-volatile memory devices 102 are used. The classes 316 indicate that the non-volatile memory devices 102 are applicable for write mostly accesses, read mostly accesses, large sequential accesses, and highly random accesses.

One of the classes 316 includes applications with the write mostly accesses where a drive is doing numerous data recording operations. The write mostly accesses are operations for writing data to memory devices, whereby a number of the operations is greater than a predetermined threshold. For example, the drive represents a back-up device. Most of the time, the drive is used for backing a computer up to store data to a storage device. The data backed up to the storage device is almost never read because it is not needed most of the time until data recovery occurs. So, the applications with the write mostly accesses are where the host system is mostly recording data onto the drive.

Another of the classes 316 includes applications with the read mostly accesses where a drive is doing numerous data retrieval operations. The read mostly accesses are operations for reading data from memory devices, whereby a number of the operations is greater than a predetermined threshold. For example, the applications with the read mostly accesses are used for a Global Positioning System (GPS) device with a database of street maps. As a specific example, a device in a car is not programmed very often, and the device is reading its internal memory constantly for database information.

Another of the classes 316 includes applications that need the large sequential accesses, which occur during actual data transfers that are either reading or writing to the drive in large contiguous transfer blocks. The large sequential accesses are operations for reading or writing data in contiguous blocks from or to memory devices, whereby a size of each of the contiguous blocks is greater than a predetermined threshold. For example, a couple megabytes of data can be transferred at a time. Also for example, one of the applications is reading movies off a disk drive for an airplane entertainment system. The reading process includes large-block sequential transfers because data of the movies has been contiguously stored in the disk drive.

Another of the classes 316 includes applications with the highly random accesses. The highly random accesses are operations for reading or writing data in non-sequential blocks from or to memory devices, whereby a size of each of the non-sequential blocks is less than a predetermined threshold. If a search is performed, a drive can access many portions all over a database to assemble search information. The search would thus involve the highly random accesses.

Another of the functions is to integrate a classification process into a design of a control firmware for the storage device. The classification process is a sorting or selection process of the non-volatile memory devices 102. The classification process can be implemented in the drive-level control unit 108. For example, the drive-level control unit 108 can include modules for performing the classification process. Also for example, the classification process can be performed based on the performance groups 304 or the predicted use model 314.

Another of the functions is to provide a component classification that is used to construct each individual drive. The component classification is the classification process for selecting the non-volatile memory devices 102.

Another of the functions is to provide the manufacturing process that is established to assign classified memory devices with individual and the classes 316 of storage devices or the non-volatile memory devices 102. The classified memory devices are the non-volatile memory devices 102 that have been selected based on the manufacturing process.

The classes 316 of the storage devices can be determined based on intake inspections or the incoming inspections. Groups of the non-volatile memory devices 102 can be determined based on certain aspects or the non-volatile memory device characteristics 306 of the non-volatile memory devices 102. The non-volatile memory devices 102 can be measured to determine the non-volatile memory device characteristics 306 of the non-volatile memory devices 102.

The non-volatile memory device characteristics 306 can be determined based on any number of device parameters. The non-volatile memory device characteristics 306 can be used to determine that the groups of the non-volatile memory devices 102 are good parts for retention, endurance, or any other purposes. For example, the device parameters can be determined by measuring BER, erase times, write times, or any other device parameters of the non-volatile memory devices 102.

In addition, the non-volatile memory device characteristics 306 that are individually specific to each of the non-volatile memory devices 102 within the groups might be important. For example, the non-volatile memory device characteristics 306 that are individually specific to each of the non-volatile memory devices 102 can include absolute timing latency.

Another of the functions is to group or regroup components of the non-volatile memory devices 102 having the non-volatile memory device characteristics 306 that are similar to or substantially the same with each other during the normal runtime operations of the storage devices 302 as the drive or the storage devices 302 age. One of ordinary skill in the art would know how to determine “substantially the same”. After the non-volatile memory devices 102 are grouped by the assignment device 312, the non-volatile memory devices 102 can be regrouped based on the operational capabilities 112, the performance groups 304, the predicted use model 314, or a combination thereof during the runtime operations of the storage devices 302.

Firstly, the non-volatile memory devices 102 are selected based on the performance groups 304 before the normal runtime operations of the storage devices 302 and the non-volatile memory devices 102. This provides an overall grouping performance of the drive.

Then, as the drive ages, the operational capabilities 112 are continuously updated in the operational characteristics tables 110 at predetermined intervals. The non-volatile memory devices 102 are regrouped based on the operational capabilities 112. The non-volatile memory devices 102 are regrouped during the runtime operations as the drive ages. For example, the operational characteristics tables 110 are updated by estimating how fast individual devices or each of the non-volatile memory devices 102 is aging, since a number of the non-volatile memory devices 102 can fade or age faster than others.

Another of the functions is to determine an operation of drives in a group that takes advantage of aggregate capabilities of all components, such as the non-volatile memory devices 102, on the drives or in a population of the components used during the manufacturing process.

The functions described above provide a process, implemented in the assignment device 312, that is used to build drives or the storage devices that are different from each other for specific applications or purposes. For example, the process is used to build a group of the drives with the components or the non-volatile memory devices 102 that are more capable and another group of the drives with the components that are less capable. The functions described above also provide a process that is used to build the drives that use a predetermined wide range of component characteristics or the non-volatile memory device characteristics 306 to help smooth the performance and operations over a population of the drives.

The functions described above are used to build drives for specific purposes or applications based on sorting or selecting characterized devices based on the classes 316 including the read mostly accesses or data logging for drives using the write mostly accesses. The classes 316 can be determined based on materials that are used to build the non-volatile memory devices 102 including NAND can be better for one type of applications than other applications.

The main point of the embodiments described herein is that the non-volatile memory devices 102 are selected characterization wise by the characterization device 308. The non-volatile memory devices 102 are selected based on the non-volatile memory device characteristics 306 during the incoming inspections, which occur before the runtime operations of the non-volatile memory devices 102 or a drive. The assignment device 312 then assigns the non-volatile memory devices 102 to the storage devices 302.

The main point also includes that while the non-volatile memory devices 102 are being used on the drive or the storage devices 302, the non-volatile memory devices 102 are regrouped by the drive-level control unit 108 based on the operational capabilities 112 of the non-volatile memory devices 102. The non-volatile memory devices 102 are continuously regrouped or reformed into groups of the non-volatile memory devices 102 to form or for the storage devices 302 at predetermined intervals for managing the non-volatile memory devices 102 including flash devices to get better or improved aging, endurance, and reliability of the storage devices 302. In other words, the non-volatile memory devices 102 are not all treated or determined to be identical as they are being used during the runtime operations.

Functions or operations of the main memory controller 104 in the storage system 100 as described above can be implemented using modules. The functions or the operations of the main memory controller 104 can be implemented in hardware, software, or a combination thereof. For example, the host interface controller 106, the drive-level control unit 108, the memory control unit 116, or a combination thereof can be implemented as modules. The modules can be implemented using the control unit 202 of FIG. 2, the storage unit 204 of FIG. 2, the memory interface unit 206 of FIG. 2, the host interface unit 208 of FIG. 2, or a combination thereof.

The storage system 100 is described with module functions or order as an example. The modules can be partitioned differently. Each of the modules can operate individually and independently of the other modules.

Furthermore, data generated in one module can be used by another module without being directly coupled to each other. Yet further, the modules can be implemented as hardware accelerators (not shown) within the control unit 202 or can be implemented as hardware accelerators (not shown) in the main memory controller 104 or outside of the main memory controller 104.

The host interface controller 106 can be coupled to the drive-level control unit 108. The drive-level control unit 108 can be coupled to the memory control unit 116 and the assignment device 312. The assignment device 312 can be coupled to the characterization device 308.

The physical transformation of determining the non-volatile memory device characteristics 306 of the non-volatile memory devices 102 results in movement in the physical world, such as people using the storage devices 302 based on the operation of the storage system 100. As the movement in the physical world occurs, the movement itself creates additional information that is converted back to assigning the non-volatile memory devices 102 to the storage devices 302 and regrouping the non-volatile memory devices 102 based on the operational capabilities 112 that are updated during the runtime operations of the storage devices 302 for the continued operation of the storage system 100 and to continue the movement in the physical world.

It has been found that combining the ability to characterize the non-volatile memory devices 102 during the manufacturing process and also during operations of the storage devices 302 provide improved performance and reliability of the storage devices 302. The improved performance and reliability are provided when the non-volatile memory devices 102 are characterized during the inspection of the non-volatile memory devices 102 and subsequently assigned to the storage devices 302 in the manufacturing process. The improved performance and reliability are provided when the non-volatile memory devices 102 are characterized also during the runtime operations of the storage devices 302 to determine and update the operational capabilities 112.

It has also been found that selecting the non-volatile memory devices 102 based on the predicted use model 314 so that the drives or the storage devices 302 that are different from each other are built for specific applications or purposes.

It has further been found that regrouping the non-volatile memory devices 102 having the non-volatile memory device characteristics 306 that are substantially the same with each other as the storage devices 302 age provide smooth performance and operations over a population of the drives.

It has further been found that continuously regrouping the non-volatile memory devices 102 provide improved aging, endurance, and reliability of the storage devices 302.

It has further been found that determining the average bit error rate associated with the non-volatile memory devices 102 provide improved performance since the average bit error rate is used to determine the performance groups 304. Each of the performance groups 304 has certain performance characteristics used to classify the non-volatile memory devices 102 for making decisions by the assignment device 312 on that classification of how to assemble drives.

Referring now to FIG. 4, therein is shown a flow chart of a method 400 of data management based on non-volatile memory device characteristics determined during an inspection of non-volatile memory devices before a runtime operation of a storage device in a storage system in a further embodiment of the present invention. The method 400 includes: performing by a controller in the storage system: updating operational capabilities based on the non-volatile memory device characteristics during the runtime operation of the storage device in a block 402; grouping the non-volatile memory devices based on the operational capabilities in a block 404; and receiving the operational capabilities for controlling the non-volatile memory devices in a block 406.

Accordingly, it has been discovered that the values of the embodiments described above provide advantages that will go a long way to improving overall capabilities of a product line and reducing the cost of the product line in general. The advantages include improved performance, improved reliability, and improved data integrity of the storage system 100 of FIG. 1. The embodiments are applicable to all SSDs being designed today.

Thus, it has been discovered that the storage system 100 of the present invention furnishes important and heretofore unknown and unavailable solutions, capabilities, and functional aspects for data management in a storage system. The resulting method, process, apparatus, device, product, and/or system is straightforward, cost-effective, uncomplicated, highly versatile, accurate, sensitive, and effective, and can be implemented by adapting known components for ready, efficient, and economical manufacturing, application, and utilization.

Another important aspect of the present invention is that it valuably supports and services the historical trend of reducing costs, simplifying systems, and increasing performance.

These and other valuable aspects of the present invention consequently further the state of the technology to at least the next level.

While the invention has been described in conjunction with a specific best mode, it is to be understood that many alternatives, modifications, and variations will be apparent to those skilled in the art in light of the aforegoing description. Accordingly, it is intended to embrace all such alternatives, modifications, and variations that fall within the scope of the included claims. All matters hithertofore set forth herein or shown in the accompanying drawings are to be interpreted in an illustrative and non-limiting sense.

Claims

1. A method of data management in a data storage system comprising: during runtime operation of the data storage system: directing runtime operations for a first application to a first grouping of non-volatile memory devices, of a plurality of non-volatile memory devices in the data storage system;directing runtime operations for a second application to a second grouping of non-volatile memory devices, of the plurality of non-volatile memory devices in the data storage system, wherein: the second application is distinct from the first application and the second grouping is distinct from the first grouping,groupings, including the first grouping and the second grouping, of the plurality of non-volatile memory devices are based on device characteristics of the plurality of non-volatile memory devices in the data storage system,the device characteristics are indicated by information in a device characteristics table,each of the groupings of the plurality of non-volatile memory devices in the data storage system corresponds to a respective class of a set of classes of non-volatile memory usage, wherein the set of classes includes at least two of write mostly accesses, read mostly accesses, large sequential accesses, and highly random accesses,each of the plurality of non-volatile memory devices includes erase blocks that each have multiple pages, andinitial information in the device characteristics table is based on non-volatile memory device characteristics determined during an inspection of the plurality of non-volatile memory devices before the runtime operation of the data storage system;updating the information in the device characteristics table to indicate updated device characteristics of respective individual non-volatile memory devices in the plurality of non-volatile memory devices determined during the runtime operation of the data storage system;updating the groupings of the plurality of non-volatile memory devices in the data storage system based on the updated device characteristics indicated by the updated information in the device characteristics table; andsubsequent to updating the groupings, directing runtime operations for the first application to a first updated grouping of non-volatile memory devices, of the plurality of non-volatile memory devices in the data storage system, and directing runtime operations for the second application to a second updated grouping of non-volatile memory devices, of the plurality of non-volatile memory devices in the data storage system, wherein the second updated grouping is distinct from the second grouping and the first updated grouping.

2. The method as claimed in claim 1, further comprising, before the runtime operation on the data storage system, grouping the plurality of non-volatile memory devices, including the first grouping and the second grouping, based on the device characteristics of the non-volatile memory devices indicated by the information in the device characteristics table, wherein grouping the plurality of non-volatile memory devices includes grouping non-volatile memory devices that have substantially similar device characteristics.

3. The method as claimed in claim 1, wherein: updating the information in the device characteristics table to indicate updated device characteristics includes determining the average bit error rate for each of the non-volatile memory devices in the plurality of non-volatile memory devices, andgrouping, including the first grouping and the second grouping, the plurality of non-volatile memory devices into said groupings is based at least in part on the determined average bit error rates for the plurality of non-volatile memory devices.

4. The method as claimed in claim 1, wherein grouping the plurality of non-volatile memory devices includes dynamically grouping the non-volatile memory devices based at least in part on one of erase time, write time, and latency.

5. A data storage system, comprising: a plurality of non-volatile memory devices; anda controller, having one or more processors and one or more modules, configured to, during runtime operation of the data storage system: direct runtime operations for a first application to a first grouping of non-volatile memory devices, of the plurality of non-volatile memory devices in the data storage system;direct runtime operations for a second application to a second grouping of non-volatile memory devices, of the plurality of non-volatile memory devices in the data storage system, wherein: the second application is distinct from the first application and the second grouping is distinct from the first grouping,groupings, including the first grouping and the second grouping, of the plurality of non-volatile memory devices are based on device characteristics of the plurality of non-volatile memory devices in the data storage system,the device characteristics are indicated by information in a device characteristics table,each of the groupings of the plurality of non-volatile memory devices in the data storage system corresponds to a respective class of a set of classes of non-volatile memory usage, wherein the set of classes includes at least two of write mostly accesses, read mostly accesses, large sequential accesses, and highly random accesses,each of the non-volatile memory devices includes erase blocks that each have multiple pages, andinitial information in the device characteristics table is based on non-volatile memory device characteristics determined during an inspection of the plurality of non-volatile memory devices before the runtime operation of the data storage system;update the information in the device characteristics table to indicate updated device characteristics of respective individual non-volatile memory devices in the plurality of non-volatile memory devices determined during the runtime operation of the data storage system;update the groupings of the plurality of non-volatile memory devices in the data storage system based on the updated device characteristics indicated by the updated information in the device characteristics table; andsubsequent to updating the groupings, direct runtime operations for the first application to a first updated grouping of non-volatile memory devices, of the plurality of non-volatile memory devices in the data storage system, and directing runtime operations for the second application to a second updated grouping of non-volatile memory devices, of the plurality of non-volatile memory devices in the data storage system, wherein the second updated grouping is distinct from the second grouping and the first updated grouping.

6. The data storage system as claimed in claim 5, further configured to, before the runtime operation on the data storage system, group the plurality of non-volatile memory devices, including the first grouping and the second grouping, based on the device characteristics of the non-volatile memory devices indicated by the information in the device characteristics table, wherein grouping the plurality of non-volatile memory devices includes grouping non-volatile memory devices that have substantially similar device characteristics.

7. The data storage system as claimed in claim 5, wherein: updating the information in the device characteristics table to indicate updated device characteristics includes determining the average bit error rate for each of the non-volatile memory devices in the plurality of non-volatile memory devices, andgrouping, including the first grouping and the second grouping, the plurality of the non-volatile memory devices into said groupings is based at least in part on the determined average bit error rates for the plurality of non-volatile memory devices.

8. The data storage system as claimed in claim 5, wherein grouping the plurality of non-volatile memory devices includes dynamically grouping the non-volatile memory devices based at least in part on one of erase time, write time, and latency.

9. A controller, for a data storage system having a plurality of non-volatile memory devices, the controller comprising one or more processors and one or more modules, configured to, during runtime operation of the data storage system: direct runtime operations for a first application to a first grouping of non-volatile memory devices, of the plurality of non-volatile memory devices in the data storage system; direct runtime operations for a second application to a second grouping of non-volatile memory devices, of the plurality of non-volatile memory devices in the data storage system, wherein: the second application is distinct from the first application and the second grouping is distinct from the first grouping,groupings, including the first grouping and the second grouping, of the plurality of non-volatile memory devices are based on device characteristics of the plurality of non-volatile memory devices in the data storage system,the device characteristics are indicated by information in a device characteristics table,each of the groupings of the plurality of non-volatile memory devices in the data storage system corresponds to a respective class of a set of classes of non-volatile memory usage, wherein the set of classes includes at least two of write mostly accesses, read mostly accesses, large sequential accesses, and highly random accesses,each of the non-volatile memory devices includes erase blocks that each have multiple pages, andinitial information in the device characteristics table is based on non-volatile memory device characteristics determined during an inspection of the plurality of non-volatile memory devices before the runtime operation of the data storage system;update the information in the device characteristics table to indicate updated device characteristics of respective individual non-volatile memory devices in the plurality of non-volatile memory devices determined during the runtime operation of the data storage system;update the groupings of the plurality of non-volatile memory devices in the data storage system based on the updated device characteristics indicated by the updated information in the device characteristics table; andsubsequent to updating the groupings, direct runtime operations for the first application to a first updated grouping of non-volatile memory devices, of the plurality of non-volatile memory devices in the data storage system, and directing runtime operations for the second application to a second updated grouping of non-volatile memory devices, of the plurality of non-volatile memory devices in the data storage system, wherein the second updated grouping is distinct from the second grouping and the first updated grouping.

10. The controller as claimed in claim 9, further comprising instructions causing the controller to group, before the runtime operation on the data storage system, the plurality of non-volatile memory devices, including the first grouping and the second grouping, based on the device characteristics of the non-volatile memory devices indicated by the information in the device characteristics table, wherein grouping the plurality of non-volatile memory device includes grouping non-volatile memory device that have substantially similar device characteristics.

11. The controller as claimed in claim 9, wherein: updating the information in the device characteristics table to indicate updated device characteristics includes determining the average bit error rate for each of the non-volatile memory devices in the plurality of non-volatile memory devices, andgrouping, including the first grouping and the second grouping, the plurality of non-volatile memory devices into said groupings is based at least in part on the determined average bit error rates for the plurality of non-volatile memory devices.

12. The controller as claimed in claim 9, wherein grouping the plurality of non-volatile memory devices includes dynamically grouping the non-volatile memory devices based at least in part on one of erase time, write time, and latency.