US20180350447A1 - Data storage device with rewriteable in-place memory - Google Patents
Data storage device with rewriteable in-place memory Download PDFInfo
- Publication number
- US20180350447A1 US20180350447A1 US15/607,784 US201715607784A US2018350447A1 US 20180350447 A1 US20180350447 A1 US 20180350447A1 US 201715607784 A US201715607784 A US 201715607784A US 2018350447 A1 US2018350447 A1 US 2018350447A1
- Authority
- US
- United States
- Prior art keywords
- data
- selection module
- volatile memory
- memory
- map
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 230000015654 memory Effects 0.000 title claims abstract description 192
- 238000013500 data storage Methods 0.000 title claims abstract description 71
- 239000000872 buffer Substances 0.000 claims description 36
- 238000000034 method Methods 0.000 claims description 14
- 230000008859 change Effects 0.000 claims description 8
- 230000007613 environmental effect Effects 0.000 claims description 6
- 238000013519 translation Methods 0.000 claims description 2
- 230000014616 translation Effects 0.000 claims description 2
- 230000003213 activating effect Effects 0.000 claims 2
- 230000003362 replicative effect Effects 0.000 claims 1
- 210000004027 cell Anatomy 0.000 description 40
- 230000009471 action Effects 0.000 description 17
- 230000000694 effects Effects 0.000 description 10
- 230000000670 limiting effect Effects 0.000 description 10
- 238000013507 mapping Methods 0.000 description 7
- 239000000463 material Substances 0.000 description 5
- 238000013523 data management Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 238000010276 construction Methods 0.000 description 3
- 230000005415 magnetization Effects 0.000 description 3
- 230000014759 maintenance of location Effects 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 239000008187 granular material Substances 0.000 description 2
- 238000012005 ligant binding assay Methods 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 230000007704 transition Effects 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 239000005387 chalcogenide glass Substances 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 150000001875 compounds Chemical class 0.000 description 1
- 230000006837 decompression Effects 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000000593 degrading effect Effects 0.000 description 1
- 239000003989 dielectric material Substances 0.000 description 1
- 230000003292 diminished effect Effects 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 239000012212 insulator Substances 0.000 description 1
- 238000003475 lamination Methods 0.000 description 1
- 230000037361 pathway Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000002829 reductive effect Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 125000006850 spacer group Chemical group 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 210000000352 storage cell Anatomy 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F12/00—Accessing, addressing or allocating within memory systems or architectures
- G06F12/02—Addressing or allocation; Relocation
- G06F12/08—Addressing or allocation; Relocation in hierarchically structured memory systems, e.g. virtual memory systems
-
- G—PHYSICS
- G11—INFORMATION STORAGE
- G11C—STATIC STORES
- G11C29/00—Checking stores for correct operation ; Subsequent repair; Testing stores during standby or offline operation
- G11C29/70—Masking faults in memories by using spares or by reconfiguring
- G11C29/78—Masking faults in memories by using spares or by reconfiguring using programmable devices
- G11C29/785—Masking faults in memories by using spares or by reconfiguring using programmable devices with redundancy programming schemes
- G11C29/789—Masking faults in memories by using spares or by reconfiguring using programmable devices with redundancy programming schemes using non-volatile cells or latches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0628—Interfaces specially adapted for storage systems making use of a particular technique
- G06F3/0638—Organizing or formatting or addressing of data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F12/00—Accessing, addressing or allocating within memory systems or architectures
- G06F12/02—Addressing or allocation; Relocation
- G06F12/0223—User address space allocation, e.g. contiguous or non contiguous base addressing
- G06F12/023—Free address space management
- G06F12/0238—Memory management in non-volatile memory, e.g. resistive RAM or ferroelectric memory
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F12/00—Accessing, addressing or allocating within memory systems or architectures
- G06F12/02—Addressing or allocation; Relocation
- G06F12/0223—User address space allocation, e.g. contiguous or non contiguous base addressing
- G06F12/0292—User address space allocation, e.g. contiguous or non contiguous base addressing using tables or multilevel address translation means
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F12/00—Accessing, addressing or allocating within memory systems or architectures
- G06F12/02—Addressing or allocation; Relocation
- G06F12/08—Addressing or allocation; Relocation in hierarchically structured memory systems, e.g. virtual memory systems
- G06F12/10—Address translation
- G06F12/1027—Address translation using associative or pseudo-associative address translation means, e.g. translation look-aside buffer [TLB]
- G06F12/1045—Address translation using associative or pseudo-associative address translation means, e.g. translation look-aside buffer [TLB] associated with a data cache
- G06F12/1054—Address translation using associative or pseudo-associative address translation means, e.g. translation look-aside buffer [TLB] associated with a data cache the data cache being concurrently physically addressed
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F12/00—Accessing, addressing or allocating within memory systems or architectures
- G06F12/02—Addressing or allocation; Relocation
- G06F12/08—Addressing or allocation; Relocation in hierarchically structured memory systems, e.g. virtual memory systems
- G06F12/10—Address translation
- G06F12/1027—Address translation using associative or pseudo-associative address translation means, e.g. translation look-aside buffer [TLB]
- G06F12/1045—Address translation using associative or pseudo-associative address translation means, e.g. translation look-aside buffer [TLB] associated with a data cache
- G06F12/1063—Address translation using associative or pseudo-associative address translation means, e.g. translation look-aside buffer [TLB] associated with a data cache the data cache being concurrently virtually addressed
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0628—Interfaces specially adapted for storage systems making use of a particular technique
- G06F3/0655—Vertical data movement, i.e. input-output transfer; data movement between one or more hosts and one or more storage devices
- G06F3/0656—Data buffering arrangements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0668—Interfaces specially adapted for storage systems adopting a particular infrastructure
- G06F3/067—Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0668—Interfaces specially adapted for storage systems adopting a particular infrastructure
- G06F3/0671—In-line storage system
- G06F3/0683—Plurality of storage devices
- G06F3/0688—Non-volatile semiconductor memory arrays
-
- G—PHYSICS
- G11—INFORMATION STORAGE
- G11C—STATIC STORES
- G11C11/00—Digital stores characterised by the use of particular electric or magnetic storage elements; Storage elements therefor
- G11C11/005—Digital stores characterised by the use of particular electric or magnetic storage elements; Storage elements therefor comprising combined but independently operative RAM-ROM, RAM-PROM, RAM-EPROM cells
-
- G—PHYSICS
- G11—INFORMATION STORAGE
- G11C—STATIC STORES
- G11C11/00—Digital stores characterised by the use of particular electric or magnetic storage elements; Storage elements therefor
- G11C11/02—Digital stores characterised by the use of particular electric or magnetic storage elements; Storage elements therefor using magnetic elements
- G11C11/16—Digital stores characterised by the use of particular electric or magnetic storage elements; Storage elements therefor using magnetic elements using elements in which the storage effect is based on magnetic spin effect
- G11C11/165—Auxiliary circuits
- G11C11/1659—Cell access
-
- G—PHYSICS
- G11—INFORMATION STORAGE
- G11C—STATIC STORES
- G11C11/00—Digital stores characterised by the use of particular electric or magnetic storage elements; Storage elements therefor
- G11C11/02—Digital stores characterised by the use of particular electric or magnetic storage elements; Storage elements therefor using magnetic elements
- G11C11/16—Digital stores characterised by the use of particular electric or magnetic storage elements; Storage elements therefor using magnetic elements using elements in which the storage effect is based on magnetic spin effect
- G11C11/165—Auxiliary circuits
- G11C11/1675—Writing or programming circuits or methods
-
- G—PHYSICS
- G11—INFORMATION STORAGE
- G11C—STATIC STORES
- G11C11/00—Digital stores characterised by the use of particular electric or magnetic storage elements; Storage elements therefor
- G11C11/21—Digital stores characterised by the use of particular electric or magnetic storage elements; Storage elements therefor using electric elements
- G11C11/34—Digital stores characterised by the use of particular electric or magnetic storage elements; Storage elements therefor using electric elements using semiconductor devices
- G11C11/40—Digital stores characterised by the use of particular electric or magnetic storage elements; Storage elements therefor using electric elements using semiconductor devices using transistors
- G11C11/401—Digital stores characterised by the use of particular electric or magnetic storage elements; Storage elements therefor using electric elements using semiconductor devices using transistors forming cells needing refreshing or charge regeneration, i.e. dynamic cells
- G11C11/406—Management or control of the refreshing or charge-regeneration cycles
- G11C11/40607—Refresh operations in memory devices with an internal cache or data buffer
-
- G—PHYSICS
- G11—INFORMATION STORAGE
- G11C—STATIC STORES
- G11C13/00—Digital stores characterised by the use of storage elements not covered by groups G11C11/00, G11C23/00, or G11C25/00
- G11C13/0002—Digital stores characterised by the use of storage elements not covered by groups G11C11/00, G11C23/00, or G11C25/00 using resistive RAM [RRAM] elements
- G11C13/0021—Auxiliary circuits
- G11C13/003—Cell access
-
- G—PHYSICS
- G11—INFORMATION STORAGE
- G11C—STATIC STORES
- G11C13/00—Digital stores characterised by the use of storage elements not covered by groups G11C11/00, G11C23/00, or G11C25/00
- G11C13/0002—Digital stores characterised by the use of storage elements not covered by groups G11C11/00, G11C23/00, or G11C25/00 using resistive RAM [RRAM] elements
- G11C13/0021—Auxiliary circuits
- G11C13/0069—Writing or programming circuits or methods
-
- G—PHYSICS
- G11—INFORMATION STORAGE
- G11C—STATIC STORES
- G11C16/00—Erasable programmable read-only memories
- G11C16/02—Erasable programmable read-only memories electrically programmable
- G11C16/06—Auxiliary circuits, e.g. for writing into memory
- G11C16/08—Address circuits; Decoders; Word-line control circuits
-
- G—PHYSICS
- G11—INFORMATION STORAGE
- G11C—STATIC STORES
- G11C16/00—Erasable programmable read-only memories
- G11C16/02—Erasable programmable read-only memories electrically programmable
- G11C16/06—Auxiliary circuits, e.g. for writing into memory
- G11C16/10—Programming or data input circuits
-
- G—PHYSICS
- G11—INFORMATION STORAGE
- G11C—STATIC STORES
- G11C16/00—Erasable programmable read-only memories
- G11C16/02—Erasable programmable read-only memories electrically programmable
- G11C16/06—Auxiliary circuits, e.g. for writing into memory
- G11C16/24—Bit-line control circuits
-
- G—PHYSICS
- G11—INFORMATION STORAGE
- G11C—STATIC STORES
- G11C7/00—Arrangements for writing information into, or reading information out from, a digital store
- G11C7/18—Bit line organisation; Bit line lay-out
-
- G—PHYSICS
- G11—INFORMATION STORAGE
- G11C—STATIC STORES
- G11C8/00—Arrangements for selecting an address in a digital store
- G11C8/14—Word line organisation; Word line lay-out
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F12/00—Accessing, addressing or allocating within memory systems or architectures
- G06F12/02—Addressing or allocation; Relocation
- G06F12/08—Addressing or allocation; Relocation in hierarchically structured memory systems, e.g. virtual memory systems
- G06F12/0802—Addressing of a memory level in which the access to the desired data or data block requires associative addressing means, e.g. caches
- G06F12/0866—Addressing of a memory level in which the access to the desired data or data block requires associative addressing means, e.g. caches for peripheral storage systems, e.g. disk cache
- G06F12/0868—Data transfer between cache memory and other subsystems, e.g. storage devices or host systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F12/00—Accessing, addressing or allocating within memory systems or architectures
- G06F12/02—Addressing or allocation; Relocation
- G06F12/08—Addressing or allocation; Relocation in hierarchically structured memory systems, e.g. virtual memory systems
- G06F12/0802—Addressing of a memory level in which the access to the desired data or data block requires associative addressing means, e.g. caches
- G06F12/0893—Caches characterised by their organisation or structure
- G06F12/0897—Caches characterised by their organisation or structure with two or more cache hierarchy levels
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F12/00—Accessing, addressing or allocating within memory systems or architectures
- G06F12/14—Protection against unauthorised use of memory or access to memory
- G06F12/1408—Protection against unauthorised use of memory or access to memory by using cryptography
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2212/00—Indexing scheme relating to accessing, addressing or allocation within memory systems or architectures
- G06F2212/21—Employing a record carrier using a specific recording technology
- G06F2212/214—Solid state disk
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2212/00—Indexing scheme relating to accessing, addressing or allocation within memory systems or architectures
- G06F2212/28—Using a specific disk cache architecture
- G06F2212/283—Plural cache memories
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2212/00—Indexing scheme relating to accessing, addressing or allocation within memory systems or architectures
- G06F2212/40—Specific encoding of data in memory or cache
- G06F2212/401—Compressed data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2212/00—Indexing scheme relating to accessing, addressing or allocation within memory systems or architectures
- G06F2212/72—Details relating to flash memory management
- G06F2212/7201—Logical to physical mapping or translation of blocks or pages
-
- G—PHYSICS
- G11—INFORMATION STORAGE
- G11C—STATIC STORES
- G11C2207/00—Indexing scheme relating to arrangements for writing information into, or reading information out from, a digital store
- G11C2207/10—Aspects relating to interfaces of memory device to external buses
- G11C2207/102—Compression or decompression of data before storage
-
- G—PHYSICS
- G11—INFORMATION STORAGE
- G11C—STATIC STORES
- G11C2207/00—Indexing scheme relating to arrangements for writing information into, or reading information out from, a digital store
- G11C2207/22—Control and timing of internal memory operations
- G11C2207/2245—Memory devices with an internal cache buffer
-
- G—PHYSICS
- G11—INFORMATION STORAGE
- G11C—STATIC STORES
- G11C2213/00—Indexing scheme relating to G11C13/00 for features not covered by this group
- G11C2213/70—Resistive array aspects
- G11C2213/71—Three dimensional array
-
- G—PHYSICS
- G11—INFORMATION STORAGE
- G11C—STATIC STORES
- G11C2213/00—Indexing scheme relating to G11C13/00 for features not covered by this group
- G11C2213/70—Resistive array aspects
- G11C2213/77—Array wherein the memory element being directly connected to the bit lines and word lines without any access device being used
-
- G—PHYSICS
- G11—INFORMATION STORAGE
- G11C—STATIC STORES
- G11C7/00—Arrangements for writing information into, or reading information out from, a digital store
- G11C7/10—Input/output [I/O] data interface arrangements, e.g. I/O data control circuits, I/O data buffers
- G11C7/1006—Data managing, e.g. manipulating data before writing or reading out, data bus switches or control circuits therefor
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Hardware Design (AREA)
- Human Computer Interaction (AREA)
- Techniques For Improving Reliability Of Storages (AREA)
- Microelectronics & Electronic Packaging (AREA)
- Memory System (AREA)
- Semiconductor Memories (AREA)
- Memory System Of A Hierarchy Structure (AREA)
Abstract
A data storage device may consist of a non-volatile memory connected to a selection module. The non-volatile memory can have a rewritable in-place memory cell that has a read-write asymmetry. The selection module can dedicate a portion of the non-volatile memory to a data map that can be self-contained along with reactively and proactively altered by the selection module.
Description
- In accordance with various embodiments, data storage device consists of a non-volatile memory connected to a selection module. The non-volatile memory has a rewritable in-place memory cell with a read-write asymmetry. The selection module dedicates a portion of the non-volatile memory to a data map.
-
FIG. 1 displays a block representation of an example data storage system in which various embodiments may be practiced. -
FIGS. 2A and 2B respectively represent portions of an example data storage device that may be employed in the data storage system ofFIG. 1 . -
FIGS. 3A-3C respectively depict portions of an example memory cell that may be utilized in the data storage system ofFIG. 1 . -
FIG. 4 plots example operational data associated with the data storage system ofFIG. 1 . -
FIGS. 5A and 5B respectively show portions of an example data storage device operated in accordance with various embodiments. -
FIG. 6 illustrates a block representation of portions of an example data storage device arranged in accordance with some embodiments. -
FIG. 7 is a block representation of portions of an example data storage device configured in accordance with assorted embodiments. -
FIG. 8 displays a block representation of a portion of an example data storage device that may be employed in the data storage system ofFIG. 1 . -
FIG. 9 depicts a block representation of a portion of an example data storage device arranged in accordance with some embodiments. -
FIGS. 10A-10D respectively represent of a portion of an example lithographic assembly formed in accordance with assorted embodiments. -
FIG. 11 is a flowchart of an example in-place memory utilization routine executed with the data storage system ofFIG. 1 in accordance with some embodiments. - With increasing amounts of data being generated, transferred, and stored, the speed, cost, size, and longevity of data storage has become stressed. While a hard disk drive (HDD) employing rotating magnetic media can reliably store data for long periods of time, the relatively large physical size and slow data access speeds have hampered the adoption of HDD in many computing devices. Solid-state drives that employ NAND flash memory can provide faster data access speeds and smaller physical sizes, but with a greater cost and low longevity than HDD.
- The relatively short longevity of flash memory has been exacerbated by data management structures and schemes that write, move, and delete data repeatedly in an effort to decrease data access latency. The fact that flash memory is not bit or byte addressable and instead is merely page/sector addressable compounds the short longevity of the memory and results in complex data management and relatively long data access times compared to volatile memories that are bit/byte addressable. However, the requirement of volatile memories to continuously have power to retain data restricts the potential applicability of these types of memory in a data storage device.
- Accordingly, various embodiments are generally directed to data storage structures and operations that utilize rewritable in-place memory that enjoys faster data access speeds than flash memory, smaller physical size than HDDs, and non-volatile data retention. The ability to store data in non-volatile memory with relatively fast data access speeds allows for a diverse variety of data management structures and schemes that can optimize data retention, reading, and writing. Meanwhile, the relatively small physical size of rewritable in-place memory allows a data storage device to be small enough to be implemented in modern computing devices, such as smartphones and tablet computers, while being robust enough to be employed in large data capacity centers.
-
FIG. 1 displays an exampledata storage system 100 in which assorted embodiments of the present disclosure may be practiced. Thesystem 100 can connect any number ofdata storage device 102 to any number ofhost 104 via a wired and/or wireless network. One ormore network controller 106 can be hardware or software based and provide data request processing and distribution to the various connecteddata storage devices 102. It is noted that the multipledata storage devices 102 may be similar, or dissimilar, types of memory with different data capacities, operating parameters, and data access speeds. - In some embodiments, at least one
data storage device 102 of thesystem 100 has alocal processor 108, such as a microprocessor or programmable controller, connected to an on-chip buffer 110, such as static random access memory (SRAM), and an off-chip buffer 112, such as dynamic random access memory (DRAM), and anon-volatile memory array 114. The non-limiting embodiment ofFIG. 1 arranges thenon-volatile memory array 114 comprises NAND flash memory that is partially shown schematically with first (BL1) and second (BL2) bit lines operating with first (WL1) and second (WL2) word lines and first (SL1) and second (SL2) source lines to write and read data stored in first 116, second 118, third 120, and fourth 122 flash cells. - It is noted that the respective bit lines correspond with first 124 and second 126 pages of memory that are the minimum resolution of the
memory array 114. That is, the construction of the flash memory prevents the flash cells from being individually rewritable in-place and instead are rewritable on a page-by-page basis. Such low data resolution, along with the fact that flash memory wears out after a number of write/rewrite cycles, corresponds with numerous performance bottlenecks and operational inefficiencies compared to memory with cells that are bit addressable while being individually accessible and individually rewritable in-place. Hence, various embodiments are directed to implementing bit addressable, rewritable in-place memory into adata storage device 102 that may be part of a distributed networkdata storage system 100. -
FIGS. 2A and 2B represent portions of anexample memory array 140 that may be utilized in a data storage device in accordance with various embodiments. Thememory array 140 has a plurality ofseparate memory cells 142 vertically stacked along the Z axis as part of a three dimensional array. While it is contemplated that a single die ofmemory cells 142 can be utilized, such configuration has diminished data capacity and fails to utilize the all the available space. Hence, various embodiments vertically stack multiple die ofmemory cells 142 that each reside in the X-Y plane. In yet, the vertically stackedcells 142 are not, necessarily, required to be vertically aligned in the manner shown inFIG. 2A . - With NAND flash memory and other solid-state data storage cells, a transistor or other separate selection component is incorporated into each cell, which occupies valuable real estate, consumes extra power, and adds latency to data access operations. Each
memory cell 142 of thememory array 140 is constructed without a transistor or other physically separate selection component and instead has aselection layer 144 contacting aresistive unit 146. Theselection layer 144 can be a single material or a lamination of different materials that prevent electrical flow to theresistive unit 146 at predetermined times and allows electrical flow to theresistive unit 146 at other predetermined times. As a non-limiting example, theselection layer 144 can be a metal-insulator transition (MIT) material, an ovonic threshold switch (OTS), or other voltage regulating structure. - The inclusion of a transistor or other selection component, as shown in
FIG. 1 , corresponds with a source line that activates the respective selection component. The elimination of any selection components in favor of theselection layer 144 allows the verticallystacked memory cells 142 to be individually accessible by a cross-point interconnect configuration where bit lines (BL) operate with word lines (WL) to access one ormore cells 142. As illustrated byline 148 an induced electrical potential difference between the bit line and word line induces electrical flow through asingle memory cell 142. The ability to select a single bit, hence bit addressable, allows thememory array 140 to densely package the cells without concern for inadvertent accessing ofmemory cells 142. - It is noted that the construction of the
memory cells 142 provides for relatively low power consumption, which corresponds with low risk of disturb of non-selected and physicallyadjacent cells 142 during read and/or write operations. The top view ofFIG. 2B conveys how thememory cells 142 can be positioned with respect to assorted bit and word lines alone a single die. By utilizing bit lines between vertically stackedmemory cells 142, the overall number of control interconnects can be reduced, which provides a more densely packagedmemory array 140. -
FIGS. 3A-3C respectively convey line representations of example non-volatile resistive units capable of being utilized in thememory array 140.FIG. 3A represents a phase change typeresistive unit 160 the occupies aresistive region 162 with achalcogenide glass material 164 that reacts to current to transition between an amorphous 166, low resistivity state and a crystalline, high resistivity state. The switching between polycrystalline and amorphous states can reliably be cycled efficiently. However, the writing/switching current can be relatively high for the phase changeresistive unit 160. -
FIG. 3B represents a filament typeresistive unit 170 where theresistive region 162 comprises a material that has a high resistivity until one or more electricallyconductive filaments 172 are induced by the flow of a writing current through theregion 162. The formation of filaments can be simple and efficient, but it is contemplated that filament(s) may become engrained in thedielectric material 174 and reduce the margin between high and low resistivity states. - The formation of conductive pathways in the
phase change 160 andfilament 170 type units may be efficient in some data storage arrangements, but not necessarily all memory arrays. Accordingly, a resistive unit may create different resistive states via relative magnetic orientations. The magnetic typeresistive unit 180 ofFIG. 3C shows how adielectric spacer layer 182 is disposed between a magneticfree layer 184 and amagnetic reference layer 186. Thereference layer 186 is set to a fixedmagnetization 188 while thefree layer 184 can be set to multiple differentmagnetic orientations 190 that, relative to the fixedmagnetization 188, provide different resistive states for theunit 180. It is contemplated that theresistive unit 180 may have additional spin polarizing layers, such as in a spin torque arrangement, that function to make the switching of thefree magnetization 188 more efficient. - The ability to utilize different types of resistive units in a memory array allows a data storage device to customize the operation and data storing capabilities of a data storage device. As a non-limiting example, a memory array may employ different types of resistive units in different die, which can provide a selectable diversity of operating conditions and data storage parameters. Regardless of the type or diversity of resistive unit in a memory array, a memory cell may suffer from asymmetric access where a write operation takes a different amount of time to complete than a read operation. That is, the replacement of a separate selecting component, such as a transistor or diode, for the
selection layer 144 can result in asymmetric access. Such asymmetric access can be problematic in data storage devices where high volumes of data writes and reads can be conducted without concern or evaluation of if a previous read or write operation has completed. - For memory arrays employing phase change type
resistive units 160, it is noted that a write access can take considerably more time to complete than a read, such as 7 microsecond latency for a read and 10+microsecond latency for a write. It is contemplated that the read/write asymmetry can be even larger, such as double or even an order of magnitude longer for a write operation to complete compared to a read operation. These issues have created interesting data management situations that are not addressed in volatile memory, HDD storage, or NAND flash storage. -
FIG. 4 plots example operational data of voltage over time associated with a memory array employing asymmetric memory cells in accordance with various embodiments. The construction of the memory cells of a memory array correspond to a different read (VREAD) and write (VWRITE) threshold voltages to respectively access or modify the resistive state, and associated binary state, of a memory cell. - In the event a
first voltage 202 is received by one or more memory cells that is below both the read and write threshold voltages, the selection layer of each memory cell will prevent the voltage from passing through cell, which prevents inadvertent resistance variations from degrading a data access operations. When avoltage 204/206 is greater than the read threshold voltage, the selection layer of a memory cell allows the voltage to pass through the cell. Forvoltage 204 that is not great enough to change the resistive state of the resistive unit, the existing resistive state will be read via signals through the orthogonally oriented bit and word lines. - The passage of a
write voltage 206 through the memory cell will change the resistive state of the resistive unit. However, there is asettle time 208 after the write voltage passes through the resistive unit for the memory cell to be set to a resistive state that can be accessed with aread voltage 210. Thesettle time 208 is directly responsible for the read/write asymmetry of a memory cell, as illustrated inFIG. 4 . Thus, the relatively high data capacity and fast read latency associated with thememory array 140 can be degraded by the write asymmetry that requires the data storage device to monitor and account for the relatively long settle time for each memory cell every instance where the cell is written. - Accordingly, assorted embodiments are directed to structure and methods of optimizing the use of the non-volatile, bit addressable, rewritable in-place memory of
FIG. 2 that suffers from asymmetric read/write operations.FIGS. 5A and 5B respectively convey block representations of example write and read operations to adata storage device 220 with the memory array ofFIG. 2 . A write operation is shown inFIG. 5A and begins with a data of a write request flowing to anSRAM buffer 110 on awafer chip 222 and/or aDRAM buffer 112 positioned off-chip 222. The write data is then sequentially compressed 224 and encrypted 226 as directed by a local controller executing firmware, software, or hardware operations. - The compressed and encrypted write data is compiled in a
write cache 228 as memory units (MU) 230 that can consist of multiple pages and/or sectors of data. It is noted that the compilation ofMUs 230 is not required for rewritable in-place non-volatile memories due to individual bits being accessible, as opposed to page accessible flash memory. Regardless of whether the write data is organized intomap units 230, thewrite cache 228 can temporarily store the write data until the data is written to the non-volatile memory (NV MEMORY) 232 where at least a portion of thememory 232 has theasymmetric memory cells 142 ofFIG. 2 . - With the data written to the asymmetric cells of the
non-volatile memory 232, a read operation cannot reliably access the data from thenon-volatile memory 232 until after thesettle time 208. Therefore, a read operation, in some embodiments, involves aselection module 234 of a data storage device to retrieve data either from thewrite cache 228 or thenon-volatile memory 232, as shown inFIG. 5B . It is noted that thewrite cache 228 is a different type of memory, such as DRAM or NAND flash, than thenon-volatile memory 232 and a read operation will involve decryption and decompression before being sent to a host. Hence, theselection module 234 intelligently manages multiple different types of memory to take advantage of the fast read speed of thenon-volatile memory cells 142 ofFIG. 2 without suffering from extended write latency due to the settle time of thecells 142. - Although not limiting or required, the
selection module 234 can conduct a variety of intelligent evaluations to optimize satisfaction of data accesses from one or more hosts.FIG. 6 is a block representation of a portion of an exampledata storage device 240 employing thememory array 140 ofFIG. 2 . Theselection module 234 has access to at least atimer 242,activity log 244,sensor 246, andprediction circuit 248 to evaluate the optimal destination and condition for a write or read request to be serviced. - At any time after receiving a write or read request from a host, the
selection module 234 can assess the current status of a single data storage device as well as the overall data storage system. Although any type and number of inputs can be concurrently and/or sequentially evaluated by theselection module 234, some embodiments specifically receive the status of pending writes in a write queue, which may be the volume, size, and buffer characteristics of data associated with pending write requests. Theselection module 234 may further receive system performance metrics, such as power consumption, average data access latency, and bit error rates. - A designated write location of pending writes along with the version of data provides biographical information about pending data writes to the
selection module 234. Any number and type of environmental conditions can be polled, and/or detected with thesensor 246, to identify any potentially adverse data access situations. For instance, atemperature sensor 246 can be used to verify the temperature inside a data storage device compared to a polled ambient temperature received from a remote host. Other environmental conditions, such as humidity, vibrations, and airflow can also be polled and/or sensed to provide a more comprehensive status of the data storage device and system. - The
selection module 234 can log the execution and system conditions associated with the servicing data access requests. The collection of information pertaining to previously serviced data access requests allows theselection module 234 to more intelligently react to system conditions and proactively initiate actions to optimize the servicing of future data access requests. That is, theselection module 234 can take current device/system conditions along with data from thelog 244 to intelligently identify reactive and proactive actions that can optimize the servicing of pending read and write requests. As a result, theselection module 234 can reactively and proactively move data between volatile buffers and non-volatile memory, alter write locations, and change read locations. - The ability to evaluate and determine the operating status of the data storage device and system to intelligently execute actions to service pending data access request allows the data storage device to adapt to changing conditions and service requests as fast as possible.
- In regards to the asymmetric rewritable in-place memory, the
selection module 234 can intelligently write to the non-volatile memory when there is a lower risk of a read request for the data within the settle time, retain data in a buffer/cache memory to service read requests, and move data to different buffers/cache locations to provide the lowest read latency. - With the
selection module 234 reactively and proactively conducting actions to optimize servicing of pending data requests, the current location of valid data can be difficult to discern without a robust mapping scheme. In yet, mapping logical block address (LBA) to physical block address (PBA) as well as LBA to LBA can be expensive in terms of processing and data capacity, particularly in an on-chip SRAM buffer. Mapping can be further complicated with the redundant retention of data in two different locations in order to service read requests for data during the settle time. Accordingly, some embodiments utilize theselection module 234 to designate the storage location, and processing time, for LBA-to-PBA and LBA-to-LBA mapping operations. -
FIG. 7 illustrates a block representation of anexample mapping scheme 250 that may be implemented in a data storage device employing thememory array 140 ofFIG. 2 . The presence of multiple different types of memory in a data storage device allows theselection module 234 to generate multiple different data maps to optimize the capabilities, and current status, of the respective types of memory. - In the non-limiting example shown in
FIG. 7 , theselection module 234 can create afirst level map 252 in a first type ofmemory 254, such as volatile DRAM, SRAM, or non-volatile flash memory. Thefirst level map 252, in some embodiments, comprises at least one LBA-to-PBA boot map that contains entries pointing to granule of 12 entries. Thefirst level map 252 can generally direct a controller to the logical or physical location of asecond level map 256 where LBA-to-PBA translations are contained with a greater resolution than thefirst level map 252. That is, thesecond level map 256 can comprise local entries pointing to the first granule holding a host-provided data sector. As a result of the first 252 and second 256 level maps, data reads, writes, and updates can be efficiently handled. - The
selection module 234 may create aseparate shadow map 258 in the first type ofmemory 254 that contains information about temporary locations of shadow data. It is understood that shadow data is data stored redundantly for a short time period until data is permanently resident in non-volatile memory. Theshadow map 258 may be simple, or sophisticated, with one or more versions of data being identified. For instance, successive versions of data may be tracked by theshadow 258,first level 252, andsecond level 256 to ensure the most recent version of data is retrieved by a read request for the data. It is noted that theshadow 258 andlevel maps 252/256 may be concurrently written, read, and updated by a common, or dissimilar controllers. - Data that is tracked by the
shadow 258 andlevel maps 252/256 eventually is written to themain data store 260 that is a bit addressable rewritable in-place memory 262. As shown, themain data store 260 andsecond level map 256 are each stored in the non-volatile rewritable in-place memory 262. However, such configuration is not required or limiting as any number and type of memory can be utilized for therespective maps 252/256/258. For example, thefirst level map 252 may be stored in serial NOR flash, theshadow map 258 stored in cluster SRAM, and thesecond level map 256 stored in DDR DRAM. The use of at least two different types ofmemory 254/262 allows theselection module 234 to intelligently generate and maintain thevarious maps 252/256/258 in memories that most efficiently allow for the servicing of data read and write requests. - It is contemplated that the
selection module 234 can alter the size, purpose, and memory location of theassorted maps 252/256/258 to accommodate changing system and device conditions. Theselection module 234 may further alter a memory and/or map via virtualization. That is, theselection module 234 can create virtual machines that independently operate in software/firmware despite being located in acommon memory 254/256. Such virtualization capability allows theselection module 234 to adapt in real-time to detected and/or predicted system and device conditions to optimize data read and write latencies. -
FIG. 8 illustrates a block representation of a portion of an exampledata storage device 270 that employs virtualization of memory in accordance with various embodiments. One or moredifferent write cache 272 can feed into anon-volatile memory 274 that comprises bit addressable rewritable in-place memory, such asarray 140. While adata storage device 270 may consist of multiple separatenon-volatile memories 274, some embodiments contain a singlenon-volatile memory 274 logically separated into different memory tiers, which can be characterized as virtualized storage. - A
memory 274 can be virtualized into any number of tiers that are mapped by at least onelevel map 252/256 and potentially ashadow map 258. Although not required or limiting, the virtualized storage scheme shown inFIG. 8 is hierarchical in nature and has afirst tier 276 assigned to a first PBA range, asecond tier 278 assigned to a second PBA range, athird tier 280 assigned to a third PBA range, andfourth tier 282 assigned to a fourth PBA range. The non-overlapping ranges of therespective tiers 276/278/280/282 may, alternatively, be assigned to LBAs. - As shown by solid arrows, data may flow between any virtualized tiers as directed by a selection module and/or local controller. For instance, data may consecutively move through the
respective tiers 276/278/280/282 depending on the amount of updating activity, which results in the least accessed data being resident in thefourth tier 282 while the most frequently updated data is resident in thefirst tier 276. Another non-limiting example involves initially placing data in thefirst tier 276 before moving the data to other, potentially non-consecutive, tiers to allow for more efficient storage and retrieval, such as based on data size, security, and/or host origin. - It can be appreciated that the rewritable in-place memory of the
non-volatile memory 274 allows for the adaptive virtualization of therespective tiers 276/278/280/282. That is, the ability to write data to a specific bit, byte, and sector without having to store non-selected data of a common page allows the virtualized tiers to have evolving sizes, assigned contents, and existence based on the system and device needs determined by theselection module 234. Therefore, the virtualized scheme ofFIG. 8 may be altered in any way over time by theselection module 234 to optimize data storage for the real-time conditions of the data storage system and device. - The virtualization of portions of a
non-volatile memory 274 is complemented by the capability of aselection module 234 to take proactive actions to meet forecasted data storage activity and/or operational events.FIG. 9 depicts a block representation of a portion of an exampledata storage device 290 that employs aselection module 234 having aprediction circuit 248 operated in accordance with various embodiments. Theprediction circuit 248 can detect and/or poll a diverse variety of information pertaining to current, and past, data storage operations as well as environmental conditions during such operations. It is noted that theprediction circuit 248 may utilize one or more real-time sensors 246 of theselection module 234 to detect one or more different environmental conditions, such as device operating temperature, ambient temperature, and power consumption. - With the concurrent and/or sequential input of one or more parameters, as shown in
FIG. 9 , theprediction circuit 248 can forecast the occurrence of future events that can be accommodated as directed by theselection module 234. For instance, theselection module 234 can modify data, such as data size, location, and security to accommodate a predicted event. In another non-limiting instance, theselection module 234 can direct the redundant writing of shadow data to one or more locations other than the non-volatile memory, which can provide efficient reading of data while the non-volatile memory is within its settle time. - Although not exhaustive, the
prediction circuit 248 can receive information about the current status of a write queue, such as the volume and size of the respective pending write requests in the queue. Theprediction circuit 248 may also poll, or determine, any number of system/device performance metrics, like write latency, read latency, and error rate. The version of data pending, or being written, may be evaluated by theprediction circuit 248 to establish how frequently data is being updated. The assigned write location of pending and previously completed data writes may be utilized by theprediction circuit 248 to perform wear leveling operations in non-volatile memory. - One or more environmental conditions can be sensed in real-time and/or polled by the
prediction circuit 248 to determine trends and situations that likely indicate future data storage activity. The availability of space in one or more shadow buffers, such as SRAM or NOR flash, may identify to theprediction circuit 248 the performance of the buffer(s) along with indicating the system's capacity to handle future pending write requests. Theprediction circuit 248 can employ one ormore algorithms 292 and at least onelog 294 of previous data storage activity to forecast the events and accommodating actions that can optimize the servicing of read and write requests. - It is contemplated that the
log 294 consists of both previously recorded and externally modeled events, actions, and system conditions. The logged information can be useful to theselection module 234 in determining the accuracy of predicted events and the effectiveness of proactively taken actions. Such self-assessment can be used to update the algorithm(s) 292 to improve the accuracy of predicted events. By determining the accuracy of previously predicted events, theprediction module 248 can assess a risk that a predicted action will occur and/or the chances of the accommodating actions will optimize system performance. Such ability allows for theprediction module 248 to operate with respect to thresholds established by theselection module 234 to ignore predicted events and proactive actions that are less likely to increase system performance, such a 95% confidence that an event will happen or a 90% chance a proactive action will increase system performance. - With the ability to ignore less than likely predicted events and proactive actions, the
selection module 234 can concurrently and sequentially generate numerous different scenarios, such as withdifferent algorithms 292 and/or logs 294. As a non-limiting example, theprediction circuit 248 may be tasked with predicting events, and corresponding correcting actions, based on modeled logs alone, real-time system conditions alone, and a combination of modeled and real-time information. Accordingly, theprediction circuit 248 andselection module 234 can assess system conditions to generate reactive and proactive actions that have a high chance of improving the servicing of current, and future, data access requests to a data storage device. -
FIGS. 10A-10D respectively convey example operational schemes resulting from the intelligent operation of theselection module 234 over time.FIG. 10A showsscheme 300 where a pendingwrite request 302 is concurrently written to non-volatile memory instep 304 and at least one write buffer instep 306. An actual, or predicted, event instep 308 may trigger theselection module 234 to read data from the buffer instep 310 until a timer expires instep 312. In other words, the redundant writing of data allows for reading of the data from the buffer instep 310 while the non-volatile memory is in its settle time and subsequently from the non-volatile memory instep 314. - In
scheme 300, the event ofstep 308 may be a longer than average settle time, perhaps due to device temperature, or other operating condition that calls for the reading of data during the settle time of the non-volatile memory. For example, writing of a multi-level non-volatile memory cell or predicted likelihood that a host will request the recently written data instep 308 can prompt theselection module 234 to direct data retrieval from a temporary buffer. It is contemplated that the timer ofstep 312 can be for the settle time of the non-volatile memory or for a designated delay time determined by theselection module 234 to more efficiently service data access requests than if no delay was present. -
FIG. 10B representsexample scheme 320 where the write request ofstep 302 and writing of data to both non-volatile memory and buffer are the same asscheme 300. However, no actual or predicted event occurs and instead data is written to a flash memory instep 322 and subsequently read from the memory instep 324 until a timer expires instep 312 and data is then read from the non-volatile memory instep 314. The utilization of flash memory insteps - The
scheme 330 ofFIG. 10C shows how an actual or predicted event instep 332 may occur after receipt of a pending write request to a data storage device. The event can trigger theselection module 234 to forego writing data to the non-volatile memory and instead write only to the write buffer instep 306 and read from the buffer instep 310 whilestep 304 writes the data to the non-volatile memory. By writing data to the buffer first, then to the non-volatile memory, system resources may be more efficiently used, such as during times of high data read accessing. At the conclusion of the settle time of the non-volatile memory, as represented by the expiration of the timer instep 312, the data is read from the non-volatile memory instep 314. - Some embodiments predict the unscheduled loss, or reduction, of power to the data storage device/system, which triggers the selection module to send all data from a volatile buffer to non-volatile memory. Other embodiments respond to a scheduled reduction in power, such as a shut-down of the device/system, by sending all data to the rewritable in-place non-volatile memory. Since the settle time of the non-volatile memory does not need to be accounted for during a shut-down, the selection module can dump large amounts of data to the non-volatile memory without harm.
- The relatively fast read time of the rewritable in-place memory can be intelligently employed during a scheduled shut-down by storing one or more boot maps to the non-volatile memory. It is noted that the
selection module 234 may generate a new boot map based on current, and recent, system activity to provide a nearly instant-on boot process where the boot map is loaded exclusively from the non-volatile memory and subsequently the boot map is moved to other memory where updates are more efficiently carried out. By sending existing or newly generated boot data, such as security information, level maps, and firmware, a data storage device/system can be ready to receive new data access requests in less than 1 second from time of power initialization. - Turning to
FIG. 10D ,scheme 340 handles the write request fromstep 302 by concurrently and redundantly writing to the non-volatile memory instep 304 and to a buffer instep 306. While the write to the non-volatile memory settles, step 310 services any reads from the buffer until aselection module 234 timer expires instep 312. A predicted, or encountered, event instep 342 triggers theselection module 234 to continue servicing data read requests from the buffer instead of from the non-volatile memory, despite the data write to the non-volatile memory having settled. The event instep 342 is not limited, but can be any operating condition that may inhibit or degrade data reads from the non-volatile memory, such as an error, high device/system processing activity, or channel availability. - Through the example schemes of
FIGS. 10A-10D , it can be appreciated that theselection module 234 can take a variety of actions to adapt to predicted and/or actual events to optimize the servicing of data access requests. Such intelligent adaptation allows the selection module to maintain high data access bandwidth and low data access latency regardless of the volume of data accesses. The intelligent adaptation further allows the selection module to alter data storage locations, mapping schemes and the writing of shadow data to accommodate changes in data priority and security, which can send highly important data to non-volatile data more quickly. -
FIG. 11 is a flowchart of an example in-placememory utilization routine 350 that can be carried out by the assorted embodiments ofFIGS. 1-10D . One or more data storage devices can be activated instep 352 with each data storage device consisting of a selection module, buffer memory, and a rewriteable in-place non-volatile memory. The data storage devices can operate for any amount of time as part of a distributed network in a data storage system. When at least one data storage device receives one or more data write request from a host instep 354, the selection module can write the data associated with the pending data request to at least one buffer memory and the non-volatile memory instep 356. - The programming of the write data in
step 356 can be done concurrently or sequentially to the buffer and non-volatile memories. However, when the data is written to the non-volatile memory, the selection module begins a timer to determine when the memory cells will finish settling and be available to service a read request. In some embodiments,step 356 involves the prediction of a settle time that differs from a preexisting default settle time, such as in reaction to high device temperatures and/or activity around the physical location of the data destination. - At any time during and after the writing of data to the non-volatile memory in
step 356,decision 358 can field read requests for that data with the selection module. That is, if a read request is received by the selection module while the non-volatile memory is in its settle time,step 360 proceeds to service the read request from data stored in the buffer. At the conclusion of the any read requests serviced withstep 360, or in the event no read request is received fromdecision 358,decision 362 proceeds to evaluate if the selection module timer has expired. - An expired selection module timer allows
step 364 to service a read request from the non-volatile memory while an active timer proceeds back to step 360 where the buffer location is used for any read request. It is noted that steps and decisions 354-364 can be cyclically revisited any number of times to handle data read and write requests. At any time after data is written instep 354, step 366 can move data between actual or virtualized tiers within the non-volatile memory. In yet, such data transfer is not required. The final non-volatile memory location is subsequently mapped instep 368 to direct any read operations to the most current version of data stored in the non-volatile memory. It is noted that the mapping of data instep 368 may correspond with the removal, or scheduled removal, of data from each buffer and from the shadow map directing data access to the buffer. - Through the various embodiments of the present disclosure, a non-volatile rewritable in-place memory can be utilized to optimize the servicing of data access requests. However, due to the asymmetrical write time associated with the rewriteable in-place memory, a selection module intelligently evaluates current and logged system activity to allow the servicing of read requests for data settling in the non-volatile memory. The selection module allows for reactive and proactive actions to be taken to maintain, and optimize, system performance in response to actual and forecasted events. As a result, the data storage system can enjoy less data read latency, decreased boot times, and sophisticated virtualization schemes that adapt to changing system conditions.
Claims (20)
1. An apparatus comprising a data storage device consisting of a non-volatile memory connected to a selection module, the non-volatile memory comprising a rewritable in-place memory cell having a read-write asymmetry corresponding to a settle time after a data write, the selection module dedicating a portion of the non-volatile memory to a data map.
2. The apparatus of claim 1 , wherein the rewritable in-place memory cell is bit addressable and comprises a selection layer contacting a resistive unit.
3. The apparatus of claim 2 , wherein the resistive unit contacts a bit line and the selection layer contacts a word line, the bit line oriented orthogonally to the word line.
4. The apparatus of claim 1 , wherein the data map is resident on less than all of the non-volatile memory.
5. The apparatus of claim 1 , wherein the data map comprises translations of logical block addresses (LBA) to physical block addresses (PBA) of data stored in the non-volatile memory.
6. The apparatus of claim 1 , wherein the non-volatile memory has a read latency of one microsecond or less.
7. The apparatus of claim 1 , wherein the non-volatile memory comprises multiple vertically stacked die, each die comprising a plurality of rewritable in-place memory cells.
8. The apparatus of claim 1 , wherein the settle time after a data write corresponds with an increased resistance volatility in the rewritable in-place memory cell.
9. A method comprising activating a data storage device consisting of a non-volatile memory connected to a selection module, the non-volatile memory comprising a rewritable in-place memory cell having a read-write asymmetry;
dedicating a portion of the non-volatile memory to a data map with the selection module; and
updating the data map in-place with the selection module.
10. The method of claim 9 , wherein the the selection module generates multiple different data maps.
11. The method of claim 9 , wherein the selection module services a read request to data written within a settle time of the rewritable in-place memory cell by loading a shadow copy from a buffer memory of the data storage device.
12. The method of claim 9 , wherein the data map is self-contained within the non-volatile memory.
13. The method of claim 9 , wherein the data map represents data stored in the non-volatile memory.
14. The method of claim 9 , wherein the selection module maintains a shadow map in a buffer memory of the data storage device, the buffer memory being separate and different than the non-volatile memory.
15. A method comprising
activating a data storage device consisting of a non-volatile memory connected to a selection module, the non-volatile memory comprising a rewritable in-place memory cell having a read-write asymmetry;
dedicating a portion of the non-volatile memory to a data map with the selection module;
predicting an event with the selection module; and
altering the data map to adapt to the predicted event and maintain a performance metric of the data storage device.
16. The method of claim 15 , wherein the selection module updates the data map to adapt to the predicted event.
17. The method of claim 15 , wherein the predicted event is a change in environmental condition.
18. The method of claim 15 , wherein the performance metric is data read latency.
19. The method of claim 18 , wherein the selection module alters the data map by replicating a portion of the data map to a volatile buffer memory.
20. The method of claim 18 , wherein the selection module alters the data map by creating a map hierarchy comprising a first level map and second level map, the first level map stored in a different memory than the second level map.
Priority Applications (5)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US15/607,784 US10147501B1 (en) | 2017-05-30 | 2017-05-30 | Data storage device with rewriteable in-place memory |
JP2018102258A JP2018206379A (en) | 2017-05-30 | 2018-05-29 | Data storage device with rewritable in-place memory |
TW107118379A TW201909184A (en) | 2017-05-30 | 2018-05-30 | Data storage device with rewritable in-place memory |
KR1020180061885A KR102138767B1 (en) | 2017-05-30 | 2018-05-30 | Data storage device with rewritable in-place memory |
CN201810539340.XA CN108986863A (en) | 2017-05-30 | 2018-05-30 | Data storage device with rewritable original place memory |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US15/607,784 US10147501B1 (en) | 2017-05-30 | 2017-05-30 | Data storage device with rewriteable in-place memory |
Publications (2)
Publication Number | Publication Date |
---|---|
US10147501B1 US10147501B1 (en) | 2018-12-04 |
US20180350447A1 true US20180350447A1 (en) | 2018-12-06 |
Family
ID=64451761
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US15/607,784 Active US10147501B1 (en) | 2017-05-30 | 2017-05-30 | Data storage device with rewriteable in-place memory |
Country Status (5)
Country | Link |
---|---|
US (1) | US10147501B1 (en) |
JP (1) | JP2018206379A (en) |
KR (1) | KR102138767B1 (en) |
CN (1) | CN108986863A (en) |
TW (1) | TW201909184A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20190286359A1 (en) * | 2018-03-14 | 2019-09-19 | International Business Machines Corporation | Migrating storage data |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10831657B2 (en) * | 2017-09-21 | 2020-11-10 | Western Digital Technologies, Inc. | Debug data recovery after PLI event |
Family Cites Families (29)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6438670B1 (en) | 1998-10-02 | 2002-08-20 | International Business Machines Corporation | Memory controller with programmable delay counter for tuning performance based on timing parameter of controlled memory storage device |
US6374323B1 (en) | 1998-11-16 | 2002-04-16 | Infineon Technologies Ag | Computer memory conflict avoidance using page registers |
US6424556B1 (en) * | 2000-12-28 | 2002-07-23 | Virage Logic Corp. | System and method for increasing performance in a compilable read-only memory (ROM) |
US6795338B2 (en) | 2002-12-13 | 2004-09-21 | Intel Corporation | Memory having access devices using phase change material such as chalcogenide |
JP3795875B2 (en) | 2003-05-22 | 2006-07-12 | 東芝マイクロエレクトロニクス株式会社 | Magnetic random access memory and data read method thereof |
US7835170B2 (en) | 2005-05-09 | 2010-11-16 | Nantero, Inc. | Memory elements and cross point switches and arrays of same using nonvolatile nanotube blocks |
EP1835508B1 (en) * | 2006-03-16 | 2012-01-18 | Samsung Electronics Co., Ltd. | Pram and associated operation method and system |
US7913055B2 (en) * | 2006-11-04 | 2011-03-22 | Virident Systems Inc. | Seamless application access to hybrid main memory |
KR101437397B1 (en) * | 2007-10-31 | 2014-09-05 | 삼성전자주식회사 | Data management method and mapping table update method in nonvolatile memory device |
KR20090109345A (en) * | 2008-04-15 | 2009-10-20 | 삼성전자주식회사 | Nonvolatile memory device using variable resistive element, memory system comprising the same |
US8225031B2 (en) | 2008-10-30 | 2012-07-17 | Hewlett-Packard Development Company, L.P. | Memory module including environmental optimization |
US8250282B2 (en) * | 2009-05-14 | 2012-08-21 | Micron Technology, Inc. | PCM memories for storage bus interfaces |
US8144506B2 (en) | 2009-06-23 | 2012-03-27 | Micron Technology, Inc. | Cross-point memory devices, electronic systems including cross-point memory devices and methods of accessing a plurality of memory cells in a cross-point memory array |
WO2012129191A2 (en) * | 2011-03-18 | 2012-09-27 | Fusion-Io, Inc. | Logical interfaces for contextual storage |
JP2012203936A (en) | 2011-03-24 | 2012-10-22 | Toshiba Corp | Semiconductor memory device |
BR112014013390A2 (en) | 2011-12-20 | 2017-06-13 | Intel Corp | dynamic partial power reduction of memory side cache in 2-tier memory hierarchy |
US9274937B2 (en) * | 2011-12-22 | 2016-03-01 | Longitude Enterprise Flash S.A.R.L. | Systems, methods, and interfaces for vector input/output operations |
US9043530B1 (en) * | 2012-04-09 | 2015-05-26 | Netapp, Inc. | Data storage within hybrid storage aggregate |
US8675423B2 (en) | 2012-05-07 | 2014-03-18 | Micron Technology, Inc. | Apparatuses and methods including supply current in memory |
US9245926B2 (en) | 2012-05-07 | 2016-01-26 | Micron Technology, Inc. | Apparatuses and methods including memory access in cross point memory |
US9076530B2 (en) * | 2013-02-07 | 2015-07-07 | Seagate Technology Llc | Non-volatile write buffer data retention pending scheduled verification |
US9135164B2 (en) * | 2013-03-15 | 2015-09-15 | Virident Systems Inc. | Synchronous mirroring in non-volatile memory systems |
CN104216837A (en) * | 2013-05-31 | 2014-12-17 | 华为技术有限公司 | Memory system, memory access request processing method and computer system |
US9530490B2 (en) * | 2014-10-27 | 2016-12-27 | Sandisk Technologies Llc | Compaction process for a data storage device |
US20160232112A1 (en) | 2015-02-06 | 2016-08-11 | Futurewei Technologies, Inc. | Unified Memory Bus and Method to Operate the Unified Memory Bus |
US20160259732A1 (en) | 2015-03-04 | 2016-09-08 | Cavium, Inc. | Managing reuse information for memory pages |
US9940039B2 (en) * | 2015-05-21 | 2018-04-10 | Western Digital Technologies, Inc. | Method and data storage device with enhanced data retention |
US9601193B1 (en) | 2015-09-14 | 2017-03-21 | Intel Corporation | Cross point memory control |
US20170097771A1 (en) * | 2015-10-01 | 2017-04-06 | Netapp, Inc. | Transaction log layout for efficient reclamation and recovery |
-
2017
- 2017-05-30 US US15/607,784 patent/US10147501B1/en active Active
-
2018
- 2018-05-29 JP JP2018102258A patent/JP2018206379A/en active Pending
- 2018-05-30 KR KR1020180061885A patent/KR102138767B1/en active IP Right Grant
- 2018-05-30 CN CN201810539340.XA patent/CN108986863A/en active Pending
- 2018-05-30 TW TW107118379A patent/TW201909184A/en unknown
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20190286359A1 (en) * | 2018-03-14 | 2019-09-19 | International Business Machines Corporation | Migrating storage data |
US11126362B2 (en) * | 2018-03-14 | 2021-09-21 | International Business Machines Corporation | Migrating storage data |
Also Published As
Publication number | Publication date |
---|---|
JP2018206379A (en) | 2018-12-27 |
TW201909184A (en) | 2019-03-01 |
CN108986863A (en) | 2018-12-11 |
KR102138767B1 (en) | 2020-07-28 |
US10147501B1 (en) | 2018-12-04 |
KR20180131469A (en) | 2018-12-10 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10559376B2 (en) | Data storage device with rewriteable in-place memory | |
KR20200018999A (en) | Memory system and operation method for determining availability based on block status | |
US11449431B2 (en) | Data storage device with rewritable in-place memory | |
US11537305B1 (en) | Dissimilar write prioritization in ZNS devices | |
CN114730282A (en) | ZNS parity exchange to DRAM | |
EP4053704B1 (en) | Storage controller redirecting write operation and operating method thereof | |
US10147501B1 (en) | Data storage device with rewriteable in-place memory | |
KR101070511B1 (en) | Solid state drive controller and method for operating of the solid state drive controller | |
US10068663B1 (en) | Data storage device with rewriteable in-place memory | |
CN114730250A (en) | Weighting read commands according to partitions in a storage device | |
WO2023101719A1 (en) | Full die recovery in zns ssd | |
US20210334031A1 (en) | Data Parking for SSDs with Zones | |
US20180349036A1 (en) | Data Storage Map with Custom Map Attribute | |
US11899590B2 (en) | Intelligent cache with read destructive memory cells | |
US20230418482A1 (en) | Storage device pool management based on storage device logical to physical (l2p) table information | |
US20210406169A1 (en) | Self-adaptive wear leveling method and algorithm | |
CN114730605A (en) | Weighted read command and open block timer for storage devices |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
STCF | Information on status: patent grant |
Free format text: PATENTED CASE |
|
MAFP | Maintenance fee payment |
Free format text: PAYMENT OF MAINTENANCE FEE, 4TH YEAR, LARGE ENTITY (ORIGINAL EVENT CODE: M1551); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY Year of fee payment: 4 |