Classifications

• • G—PHYSICS
  • G06—COMPUTING OR CALCULATING; COUNTING
  • G06F—ELECTRIC DIGITAL DATA PROCESSING
  • G06F11/00—Error detection; Error correction; Monitoring
  • G06F11/008—Reliability or availability analysis
• • 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
  • G11C16/34—Determination of programming status, e.g. threshold voltage, overprogramming or underprogramming, retention
  • G11C16/349—Arrangements for evaluating degradation, retention or wearout, e.g. by counting erase cycles
• • G—PHYSICS
  • G11—INFORMATION STORAGE
  • G11C—STATIC STORES
  • G11C2211/00—Indexing scheme relating to digital stores characterized by the use of particular electric or magnetic storage elements; Storage elements therefor
  • G11C2211/56—Indexing scheme relating to G11C11/56 and sub-groups for features not covered by these groups
  • G11C2211/564—Miscellaneous aspects
  • G11C2211/5641—Multilevel memory having cells with different number of storage levels

Definitions

• the present invention relates to memory, and more particularly to memory having a finite lifetime.
• Memory is one of the most limiting aspects of performance of modern enterprise computing systems.
• One limiting aspect of memory is the fact that many types of memory exhibit a limited lifetime. For example, a lifetime of non- volatile memory such as flash is reduced each time it is erased and re-written. Over time and thousands of erasures and re-writes, such flash memory may become less and less reliable.
• wear leveling allows for blocks within a storage device to be erased and written a roughly equal number of times. This avoids situations where one block is more frequently used, reaches an end of life, and must stop being used. This reduces the storage capacity of the entire device. Although the storage devices may have spare blocks, the spare blocks are exhausted and a memory capacity of device drops such that the storage device may not be used.
• Memory vendors often guarantee a life expectancy of a certain percentage of memory. For example, a flash memory vendor may guarantee that after 100,000 program and erase cycles (i.e. endurance), less than 1% of blocks will be unusable based on exceeding error correction requirements. In this case, the error correction requirements may be set to correct a single bit error per 512 bytes for the flash device. Some recently developed devices have a much lower endurance. These devices require a much larger error correction requirement.
• the lifetimes of memory blocks may vary. Consequently, using wear leveling, where a number of program erase cycles are leveled, a storage device may reach an end of life when only a specified percentage blocks are bad (1% for example). However, most blocks included in the storage device may still be functional.
• a system, method, and computer program product are provided for writing data to different storage devices based on write frequency.
• a frequency in which data is written is identified.
• a plurality of storage devices of different types is selected from to write the data, based on the frequency.
• Figure 1 shows a method for increasing a lifetime of a plurality of blocks of memory, in accordance with one embodiment.
• Figure 2 shows a technique for increasing a lifetime of a plurality of blocks of memory, in accordance with another embodiment.
• Figure 3 shows a method for increasing a lifetime of a plurality of blocks of memory, in accordance with another embodiment.
• Figure 4 shows a method for writing data to different storage devices based on a write frequency, in accordance with one embodiment.
• Figure 5 illustrates an exemplary system in which the various architecture and/or functionality of the various previous embodiments may be implemented.
• Figure 1 shows a method 100 for increasing a lifetime of a plurality of blocks of memory, in accordance with one embodiment. As shown, at least one factor that affects a lifetime of a plurality of blocks of memory is identified. See operation 102. Additionally, the plurality of blocks to write is selected, based on the at least one factor. See operation 104.
• the lifetime of the memory may include any duration during which the memory exhibits any desired degree of usability.
• such lifetime may include, but is certainly not limited to a desired lifetime, an actual lifetime, an estimated lifetime, etc.
• the degree of usability may refer to any usability-related parameter such as a percentage of components (e.g. blocks, cells, etc.) that are still operational, a reliability of the memory or components thereof, and/or any other parameter for that matter.
• the memory may include, but is not limited to, mechanical storage devices (e.g. disk drives, etc.), solid state storage devices (e.g. dynamic random access memory (DRAM), flash memory, etc.), and/or any other storage device.
• the flash memory may include, but is not limited to, single-level cell (SLC) devices, multi-level cell (MLC) devices, NOR flash memory, NAND flash memory, MLC NAND flash memory, SLC NAND flash memory, etc.
• the nonvolatile memory device may include at least one of a single-bit per cell NOR flash memory, a multi-bit per cell NOR flash memory, a single-bit per cell NAND flash memory, and a multi-bit per cell NAND flash memory.
• the factor may include any factor that may affect a lifetime of memory blocks either directly, or indirectly.
• the factors may include, but are not limited to, a number of errors (e.g. detected, corrected, etc.) during a read operation involving at least one of the blocks of memory, a duration between a program operation and read operation involving at least one of the blocks of memory, a number of times at least one of the blocks of memory is erased, a duration required to erase at least one of the blocks of memory, a duration required to program at least one of the blocks of memory, a number of retries required to program at least one of the blocks of memory, a number of intervening reads of a page of at least one of the blocks of memory, a number of intervening reads in a neighboring page, structure and organization of memory, and /or any other factors that meet the above definition.
• a history of use of the blocks of memory may be stored. In this case, the history of
• Figure 2 shows a technique 200 for increasing a lifetime of a plurality of blocks of memory, in accordance with another embodiment.
• the present technique 200 may be implemented in the context of the details of Figure 1.
• the technique 200 may be implemented in any desired environment. It should also be noted that the aforementioned definitions may apply during the present description.
• an endurance 202 of a plurality of memory blocks 204 may be monitored.
• the bars in Figure 2 represent the number of writes for a particular block 204.
• the endurance 202 refers to the number of write and erase cycles for each memory block 204.
• the endurance 202 corresponds to a usage of the memory blocks 204.
• the number of writes and/or erases may be monitored and logged.
• By monitoring the number of writes of the blocks 204 it may be determined which blocks have been utilized more frequently. In one embodiment, the monitoring may be used to determine whether the number of writes for any of the blocks 204 has exceeded a threshold 206.
• monitoring may allow an equalization of the usage such that when the number of writes for certain blocks reach the threshold 206, other blocks below the threshold 206 may be utilized for writes. For example, an order on which blocks are written and recycled may be changed to minimize any difference in endurance values between blocks.
• At least one factor that affects a lifetime of the plurality of blocks of memory 204 may be identified and/or monitored.
• a plurality of blocks to write may then be selected based on the at least one factor.
• the factor may include a number of corrected errors associated with each of the blocks 204. Such corrected errors may correspond to a reading of the data, for example.
• the factor may be impacted by a plurality of other factors.
• the number of corrected errors may be impacted by how much time has lapsed from a program operation to a read, and by how many reads were executed. Additionally, a number of times a block is erased and programmed may also impact the number of errors corrected.
• the factors may correspond to a period of time of usage of the blocks 204, a frequency of writes, a rate of the operations, a total permitted number of the operations, and a duration of the lifetime, etc.
• a score may be utilized as to determine whether to change the order of which the blocks 204 are written and recycled.
• each block 204 may have a corresponding score function that is based on at least one factor. The score function may be utilized to determine a score for each of the blocks 204.
• This score may be utilized to minimize a difference in values between score functions of the blocks 204.
• the score may be based on one factor that affects a lifetime of the blocks 204.
• the score may be based on a plurality of factors that affect a lifetime of the blocks 204.
• each of the scores may correspond to at least one factor that affects the lifetime of the blocks. It should be noted that, the scores may correspond to any number of factors, as noted above.
• the scores may be indicative of a value corresponding to at least one factor relating to a life expectancy of the blocks.
• the difference in the values may reflect a difference in a lifetime expectancy of the blocks.
• the two blocks may be equalized.
• the equalization may include utilizing (e.g. writing) the block below the threshold 206 while the block that is above the threshold 206 is not utilized. This may occur until a point when the two blocks correspond to equal or near equal values. At that point, the threshold 206 may be increased and either memory block may be utilized.
• all blocks 204 may be below the threshold 206. When a block exceeds the threshold 206, it may be labeled, or otherwise identified as a block above the threshold 206. The blocks 204 under the threshold 206 may then be utilized until they reach or exceed the threshold 206. [0030] This may continue until all blocks 204 below the threshold 206 are exhausted. At this point, a new threshold may be set such that all existing blocks 204 are below the new threshold. This may repeat throughout the lifetime of the blocks 204.
• a count percentage of free space may be utilized during the equalization the variation between the blocks 204, in order to minimize a total amount of blocks 204 that are erased and written.
• various other techniques may be utilized to minimize a total amount blocks that are erased and written in conjunction with equalizing the variation between the blocks (i.e. block reclamation).
• various other equalizing techniques may be utilized to equalize the variation between the blocks 204.
• multiple memory modules may be utilized in a system.
• the memory modules may include memory modules with different lifetimes.
• the total memory lifetime of the system may be up to the sum of the lifetime of the memories, as opposed to being limited to a memory module with the minimum lifetime.
• a lifetime estimator module may serve to receive commands communicated to a controller of a system via a storage bus.
• the lifetime estimator module may compute an estimated lifetime assuming that the commands received through the bus were executed.
• the lifetime estimator may be utilized to monitor the number of writes and/or other factors affecting the lifetime of the memory blocks 204. Strictly as an option, the lifetime estimator module may be utilized to set the threshold 206.
• the threshold 206 may be set using a variety of techniques.
• the threshold 206 may be a pre-determined threshold.
• the threshold 206 may be set dynamically.
• the threshold may correlate directly to a lifetime (e.g. expected, desired, etc.) of a device associated with at least one of the memory blocks 206.
• an intra-storage device redundancy capability may be utilized for reducing cost and improving performance.
• data may be moved between the individual storage devices, based on any factor associated with a lifetime thereof. For instance, a situation may involve a first one of the storage devices including a set of data that is more frequently overwritten with respect to the data of a second one of the storage devices. In such case, after threshold of at least one factor associated with lifetime is exceeded, such data may be moved from the first storage device to the second storage device, and henceforth the first storage device or one or more blocks/modules thereof may be used to store less-frequently written data or retired from further use.
• storage device lifetime may be distributed appropriately to avoid one storage device or a portion of a storage device from failing at a point in time that is vastly premature with respect to other storage devices of the group.
• the present technique may be applied not only among different storage devices, but also portions thereof.
• the lifetime of any memory components may be managed in such a manner.
• Figure 3 shows a method 300 for increasing a lifetime of a plurality of blocks of memory, in accordance with another embodiment.
• the present method 300 may be implemented in the context of the functionality of Figures 1-2. Of course, however, the method 300 may be carried out in any desired environment. It should also be noted that the aforementioned definitions may apply during the present description.
• a threshold is defined such that all blocks of memory are below the threshold. See operation 302.
• the threshold may correspond to a usage of the blocks. For example, as blocks are used a value of usage associated with the blocks may approach the threshold. In another embodiment, the threshold may correspond to at least one other factor associated with a life expectancy of the set of blocks.
• the threshold may correspond to a number of corrected errors for the blocks.
• a value the number of corrected errors associated with the blocks may approach the threshold.
• the threshold may correspond to any number of factors affecting the lifetime of the blocks.
• an initial threshold is identified which the blocks are below, it is determined whether a block needs to be reclaimed. See operation 304. For example, if factors indicate that a block or group of blocks is above the threshold or have been used disproportionately to other blocks, it may be determined that the block or blocks need to be reclaimed.
• block reclaiming which may be triggered by garbage collection, read disturbs, scrubbing, number of corrected errors, or other event, refers to equalizing a variation between block, based on at least one factor.
• the block reclaiming may include equalizing a variation between the blocks based on a number of errors detected during a read/write, a number of errors corrected during a read/write, a length of time to erase a block, a length of time for a block to program, a number of entries utilized during programming, a number of intervening reads of a page, a number of intervening reads in a neighboring page, a number of erases and program cycles of a block, and/or any other factors.
• blocks in a block set below the threshold are allocated to be written. See operation 306. For example, blocks below a threshold may be utilized in a memory operation as opposed to the block or blocks in a block set which is above the threshold.
• block(s) in a block set below the threshold are allocated to be written, it is then determined whether any blocks exceed the threshold. See operation 308. For example, the blocks in the block set below the threshold may be written until it is determined that a block exceeds the threshold.
• the block may be placed into the set of blocks corresponding to blocks over the threshold. See operation 310. If the block has not exceeded the threshold, the block may remain in the block set below the threshold and may continue to be utilized.
• the new and the initial thresholds may be set based on various criteria.
• the threshold may be set based on an expected usage of the blocks.
• the threshold may be a pre-determined threshold.
• the threshold may be determined based on the memory block usage.
• Figure 4 shows a method 400 for writing data to different storage devices based on a write frequency, in accordance with one embodiment.
• the present method 400 may be implemented in the context of the functionality and architecture of Figures 1-3. Of course, however, the method 400 may be carried out in any desired environment. It should also be noted that the aforementioned definitions may apply during the present description.
• a frequency in which data is written is identified. See operation 402. Additionally, a plurality of storage devices of different types are selected from to write the data, based on the frequency. See operation 404.
• the selection may be based on a threshold. For example, if the frequency in which data is written exceeds a threshold, a certain storage device may be selected to write the data.
• the different types of storage devices may include an SLC and an MLC device, an MLC and MLC with different endurance, SLC and DRAM, MLC and DRAM.
• the different types of storage devices may include any number of devices, including a variety of different types of memory.
• At least two different types of memory may be integrated in one device.
• flash MLC and SLC memory may be combined on one device.
• two different types of flash MLC may be integrated in one device.
• a mix of memory types in one device may be determined programmatically. In one case, a portion of the storage device associated with SLC flash memory may be determined and a portion of the storage device associated with the MLC flash memory may be determined.
• an SLC device may be selected to write the data.
• an MLC device may be selected to write the data.
• a lifetime estimator module may serve to receive commands communicated to a controller of a system via a storage bus.
• the lifetime estimator module may monitor a frequency as well as computing an estimated lifetime assuming that the command(s) received through the bus was executed.
• the frequency may be determined in a variety of ways and is not limited to being identified by the lifetime estimator module.
• the memory mentioned in the foregoing embodiments may include a mechanical storage device (e.g. a disk drive including a SATA disk drive, a SAS disk drive, a fiber channel disk drive, IDE disk drive, ATA disk drive, CE disk drive, USB disk drive, smart card disk drive, MMC disk drive, etc.) and/or a non-mechanical storage device (e.g. semiconductor-based, etc.).
• a mechanical storage device e.g. a disk drive including a SATA disk drive, a SAS disk drive, a fiber channel disk drive, IDE disk drive, ATA disk drive, CE disk drive, USB disk drive, smart card disk drive, MMC disk drive, etc.
• non-mechanical storage device e.g. semiconductor-based, etc.
• Such non-mechanical memory may, for example, include volatile or non-volatile memory.
• the nonvolatile memory device may include flash memory (e.g.
• Figure 5 illustrates an exemplary system 500 in which the various architecture and/or functionality of the various previous embodiments may be implemented.
• the exemplary system 500 may represent the computer set forth in some of the previous embodiments.
• the various apparatuses set forth above may even be a component of the system 500.
• a system 500 including at least one host processor 501 which is connected to a communication bus 502.
• the system 500 also includes a main memory 504. Control logic (software) and data are stored in the main memory 504 which may take the form of random access memory (RAM).
• the system 500 may also include a graphics processor 506 and a display 508, i.e. a computer monitor.
• the system 500 may also include a secondary storage 510.
• the secondary storage 510 includes, for example, a hard disk drive and/or a removable storage drive, representing a floppy disk drive, a magnetic tape drive, a compact disk drive, etc.
• the removable storage drive reads from and/or writes to a removable storage module in a well known manner.
• Computer programs, or computer control logic algorithms may be stored in the main memory 504 and/or the secondary storage 510. Such computer programs, when executed, enable the system 500 to perform various functions. Memory 504, storage 510 and/or any other storage are possible examples of computer-readable media.
• the architecture and/or functionality of the various previous figures may be implemented in the context of the host processor 501, graphics processor 506, secondary storage 510, an integrated circuit (not shown) that is capable of at least a portion of the capabilities of both the host processor 501 and the graphics processor 506, a chipset (i.e. a group of integrated circuits designed to work and be sold as a module for performing related functions, etc.), and/or any other integrated circuit for that matter.
• a chipset i.e. a group of integrated circuits designed to work and be sold as a module for performing related functions, etc.
• the architecture and/or functionality of the various previous figures may be implemented in the context of a general computer system, a circuit board system, a game console system dedicated for entertainment purposes, an application-specific system, and/or any other desired system.
• the system 500 may take the form of a desktop computer, lap-top computer, and/or any other type of logic.
• the system 500 may take the form of various other devices including, but not limited to a personal digital assistant (PDA) device, a mobile phone device, a television, etc.
• PDA personal digital assistant
• system 500 may be coupled to a network [e.g. a telecommunications network, local area network (LAN), wireless network, wide area network (WAN) such as the Internet, peer-to-peer network, cable network, etc.] for communication purposes.
• a network e.g. a telecommunications network, local area network (LAN), wireless network, wide area network (WAN) such as the Internet, peer-to-peer network, cable network, etc.

Landscapes

• Engineering & Computer Science (AREA)
• Quality & Reliability (AREA)
• Theoretical Computer Science (AREA)
• Physics & Mathematics (AREA)
• General Engineering & Computer Science (AREA)
• General Physics & Mathematics (AREA)
• Techniques For Improving Reliability Of Storages (AREA)

Priority Applications (2)

Applications Claiming Priority (2)

Publications (1)

Family

ID=40643192

Family Applications (1)

Country Status (5)

Cited By (19)

Families Citing this family (57)

Citations (2)

Family Cites Families (111)

• 2007
  • 2007-11-19 US US11/942,640 patent/US7849275B2/en not_active Expired - Fee Related
• 2008
  • 2008-10-23 WO PCT/US2008/012033 patent/WO2009067138A1/en not_active Ceased
  • 2008-10-23 JP JP2010534014A patent/JP5819610B2/ja not_active Expired - Fee Related
  • 2008-10-23 CN CN200880116826.7A patent/CN101874239B/zh not_active Expired - Fee Related
  • 2008-11-18 TW TW097144479A patent/TWI420303B/zh not_active IP Right Cessation
  • 2008-11-18 TW TW102115170A patent/TWI505088B/zh not_active IP Right Cessation
• 2010
  • 2010-11-30 US US12/956,926 patent/US8230184B2/en not_active Expired - Fee Related

Patent Citations (2)

Also Published As

Similar Documents

Legal Events