TW200825738A - Phased garbage collection - Google Patents

Abstract

A method for operating a non-volatile memory storage system is provided. In this method, a write command is received to write data. The write command is allocated a timeout period to complete an execution of the write command. Within the timeout period, a portion of a garbage collection operation is performed. The data associated with the write command are written to a buffer associated with the non-volatile memory storage system.

Description

200825738 IX. Description of the Invention: TECHNICAL FIELD OF THE INVENTION The present invention relates generally to memory operations and, more particularly, to methods and systems for performing phased waste project collection operations. [Prior Art] The data stored in the memory is compressed or combined to be recovered in the non-volatile memory storage system, and the blocks are periodically discarded and collected (ie, the storage capacity of a memory. In the waste project collection operation, the valid data is copied from the block to the other block. After transferring the valid data, the original block is erased to provide the storage capacity. #前...Write operation can trigger-non-volatile memory The body storage system executes the _discarded item collection operation. The host allows a fixed amount of time to perform a write operation including the discarded item collection operation = (if, trigger). For example, the secure digital agreement limits k to ! A non-volatile memory library system can generate a timeout error if it exceeds this fixed time in a write operation.

The size of the memory block has been increasing due to increased capacity, higher parallelism, and grain size. Because &, because more data is transferred, it takes longer to perform the write operation... The obsolete item collection operation can therefore easily exceed the fixed amount of time configured for the write operation. Therefore, it is necessary to prevent a timeout error when the amount of time for performing a waste item collection operation exceeds a fixed amount of time. SUMMARY OF THE INVENTION Various embodiments of the present invention provide methods and/or systems for phased collection of obsolete items. It will be appreciated that the embodiments can be implemented in a multitude of ways, 122731.doc 200825738. The evening mode includes as a side button, a sergeant on the tail road, a system or a device. Several embodiments of the present description are described below. In accordance with an embodiment of the present invention, a method for operating a non-volatile 忑L body storage system is provided. Write capital# on this side. ^ Stupid receives a write command to enter the "reset" cycle to complete the write finger stub. In the timeout period 'execute a waste project collection operation. Knife. Will be written with The information associated with the instruction is written to one

In the buffer associated with the memory storage system. Other embodiments and advantages of the present invention will be apparent from the following description of the <Desc/Clms Page number> [Embodiment] A detailed description of one or more (four) embodiments is provided below along with the accompanying drawings. A detailed description is provided in connection with the embodiments, but the detailed description is not limited to the specific embodiments. Fan arm is only subject to the scope of the patent application and contains numerous alternatives, modifications and equivalents. Numerous specific details are set forth in the following description in order to provide a thorough understanding. The details are provided for the purpose of example and may be practiced in accordance with the scope of the application. For the sake of clarity, the technical material associated with the embodiments that are known in the art is not described in detail to avoid unnecessarily obscuring the description. Embodiments described herein provide methods and/or systems for phased collection of obsolete items. In general, an abandoned project operation can be split into multiple phases. The waste collection operation can be performed on multiple timeout periods. 122731.doc • 6 - 200825738 I5 White·Μ or ^分). In an embodiment, as will be explained in greater detail below, a portion of the obsolete item collection operation is performed during the timeout period and the data received from the write instruction can be stored in a buffer. BRIEF DESCRIPTION OF THE DRAWINGS Figure 1 is a simplified block diagram of a non-volatile memory storage system in accordance with an embodiment of the present invention. - The host system (eg, desktop power • month 1, audio player, digital camera, and other computing devices) can write data to the non-volatile memory storage system 1〇2 and from non-volatile memory φ volume storage The system (10) reads the data. The non-volatile memory storage system 102 can be embedded within the host or removably coupled to the host. As shown in FIG. 2, the non-volatile memory storage system 102 includes a memory controller 110 in communication with the memory 118. In general, the memory controller 11 controls the operation of the memory port 8. Examples of operations include writing (or stylizing) data, reading data, erasing data, verifying data, performing waste collection operations, and other operations. The memory controller 110 includes a bus bar 124 that establishes an interface with the system bus 126 via the host interface 1-4, and the memory controller establishes an interface with the memory 811 via the memory φ body; Host interface 104, processor 106 (eg, microprocessor, microcontroller, and other processors), memory interface 108, random access memory (RAM) 112, error correction code (ECC), circuit 114, and Read memory (ROM) 116 communicates by means of bus bar 124. The ROM 116 can store a storage system firmware including program instructions for controlling the operation of the memory 118. The processor 〇6 is configured to execute program instructions loaded from the r〇m 116. The storage system can be tough The body is temporarily loaded and additionally RAM can be used to buffer the data transferred between a host and the memory. The ECC circuit 114 can check the host and memory 118 via the memory controller I22731.doc 200825738 110. Errors passed between. If an error is found, the ECC circuit 114 can correct a number of error bits, the number depending on the ECc algorithm utilized. The memory 118 can include an array logic 12, a non-volatile memory cell array 122, And memory cell array 123. Non-volatile memory cell array 122 can include a variety of non-volatile memory structures and techniques. Examples of non-volatile memory technologies include flash memory (eg, NAND, NOR, multi-level cells) (MLC), dividing bit line NOR (DINOR), AND, high capacitance coupling ratio (HiCR), asymmetric contactless transistor (act), other flash memory), erasable programmable read-only memory (EPr 〇M), electronically erasable programmable read only memory (EEPROM), read only memory (R〇M), disposable programmable memory (OTP), and other memory technologies. In one embodiment The memory 118, in turn, can include a memory cell array 123 configured to store a buffer. The buffer is configured to store data in a phased waste collection operation. As will be explained in more detail below, In a one-stage discarding project collection operation, new data received from a write command may be stored in a buffer. It will be appreciated that the buffer may also be located in RAM 112 and/or non-volatile memory in accordance with an embodiment of the present invention. In the body cell array 122. Similar to the non-volatile memory cell array 122, the memory early array 123 can include a variety of memory structures and techniques. Since the memory cell array 123 is configured for buffering operations, the memory cells The array can incorporate a different memory structure that is faster, more economical, and more reliable than the non-volatile memory array 122. Array logic 120 and memory controller 〇1〇 and non-volatile memory 122731.doc 200825738 The element array 122 and the memory cell array 123 establish an interface to provide (9), for example, addressing, data transfer and sensation of non-volatile memory cell arrays and memory cell arrays, and other support. Supports non-volatile memory single 7L array 122 and memory cell array 123, array logic column decoder, row decoder, charge pump, word line voltage generator, page = buffer, input/output buffer, address Buffers, and other circuits. Figure 2 is a simplified block diagram of a memory cell array organized into planes. One or more memory cell arrays can be divided into multiple planes or sub-arrays. In the example of Figure 2, a memory cell array is divided into four planes 2〇2_ 2〇5. It will be appreciated that there may be other numbers of planes (e.g., 1, 2, 8, 16 or more) in a non-volatile memory storage system. Each plane 202, 203, 204 or 205 can be divided into memory unit blocks, such as blocks 210-213 and 220-223 located in respective planes 202-205. A memory unit block is the minimum number of memory units that can be physically erased together. For increased parallelism, operations may be performed in a larger metablock unit in which blocks from each plane 202, 203, 204, or 205 are logically linked together to form a unitary block. These blocks. For example, four blocks 210-213 can be logically linked together to form a unitary block. In addition, the blocks used to form the unary blocks may come from various locations within their respective planes, such as planes 202-205. For example, four blocks 220-223 from various locations within respective planes 202-205 can be logically linked together to form another metablock. The unary block may extend over all four logical planes 202.205 within the non-volatile memory storage system, or the non-volatile memory storage system may be one or more of one or more different planes 122731.doc 200825738 The blocks dynamically form a metablock. Figure 3 is a simplified block diagram of a memory cell page. Each block (such as blocks 210-213) is further divided into memory unit pages. As shown in FIG. 3, each block 210'211, 212 or 213 is divided into eight pages 卩〇17. Alternatively, there may be 16, 32 or more memory cell pages within each block 210, 211, 212 or 213. To increase the operational parallelism of a non-volatile memory storage system, pages within two or more blocks can be logically linked into metapages. For example, a unary page can be formed from a page (such as ρι) from each of the four blocks 2 10-213. The unary pages may extend over all planes within the non-volatile memory storage system, or the non-volatile memory storage system may be from one or more of the one or more separate blocks The meta page is dynamically formed. 4 is a simplified block diagram of a section of a memory cell. A page can be further divided into one or more segments. The amount of data in each page can be an integer multiple of one or more lean sections, where each section can store 5 12 bytes of data. Figure 4 shows page 4〇1 divided into two sections 402 and 4〇4. Each segment 402 or 404 contains data 〇6, which may be 512 bytes in size, and additional data 405 associated with the data. The additional data 405 can be 16 bytes in size and can store, for example, one of the ECCs calculated from the data 4〇6 during the stylization, the logical address associated with the tribute, the block has been erased, and The count of reprogramming times, control flags, operating voltage levels, and other information associated with the data. Figure 5 is a simplified block diagram of a logical interface between a host and a non-volatile memory storage system. A contiguous logical address space 512 provides an address for the data stored in the memory 122731.doc -10.200825738. The logical address space 512 as viewed by the host can be divided into incremental data clusters. Each cluster may include a number of data segments, such as between 4 segments and 64 segments. As shown in Figure 5, an application executing on the host creates three data files 1, 2 and 3. Files 2 and 3 can be a sequenced collection of data and are identified by a unique name or other reference. The host assigns a logical address space to file 1, which has not been located to other files. Here, the show 10 does not broadcast 1 has assigned a range of available logical addresses. When the host creates file 2 after file 1, the host similarly assigns two different ranges of consecutive addresses within logical address space 512. The host may not assign a contiguous logical address to a file (such as file 丨, 2 or 3), but may assign a slice of logical address between logical address ranges that have been configured to other files. Show another broadcast 3 of the configured logical address space, one of the non-contiguous address ranges that are not configured for the file and 2 and other data. # The host can remember the logical address space by keeping a file configuration table (FAT), which is maintained by the host by switching the logical addresses assigned to various bedding files such as files 1-3. The host refers to the standard case according to the logical address and does not refer to the physical location of the file stored in the system. In terms of the non-volatile memory storage system, according to the part of the logical address that the data has been written, the non-volatile memory storage system, 1-3, does not refer to the broadcast case according to the logical address of the file. The non-volatile memory storage system converts the address provided by the host into a f-bit address in the memory cell array 502 that stores data from the host. Block—Indicates the logical to physical bits of the table 122273.doc 200825738, which is maintained by a non-volatile memory storage system. BRIEF DESCRIPTION OF THE DRAWINGS A flow chart for a general overview of a phased waste project receipt in accordance with an embodiment of the present invention. It should be understood that when the original stored data is invalid, the new data can be overwritten with the information stored in the specific host logical address. • Xiao # volatile memory storage system responds to this and writes new data to and updates the block towel. The logical address is then changed to the physical address table for the peer address to identify the new physical block through which the new data is stored. The block containing the original data at the logical address of _# is then erased and made available for storage of additional data. This erasure can occur prior to a write operation. Therefore, the memory control knows that the new data is written to the same logical address before the data at the given logical address has been invalidated or invalidated by the host. Many memory blocks can therefore store invalid data for a period of time. The size of the blocks and metablocks increases and these increases result in most of the individual materials being written to the amount of storage that is less than the storage capacity of the unary block. In many instances, the storage is even smaller than the block. The amount of storage capacity, shell material. Since the non-volatile memory storage system can direct new data to a f-blocked meta-block, the boot can result in a block or meta-block that is not filled. If the new data is an update of certain data stored in another metablock, the remaining valid elements of the logical address from the other data block adjacent to the logical address of the new data element The pages are also copied to the new metablock in logical address order. The old metablock can save the financial information information page. Therefore, the data of a particular metapage of an individual metablock can be invalidated or invalidated, and new data with the same logical address written to a different metablock is replaced. 122731.doc -12 200825738 In order to maintain the physical memory space of the data stored on the Dragon (4), the data can be periodically discarded; and from a compressed or. and). In general, § ‘ an obsolete project collection operation involves reading valid data from a block and writing valid data to a new block to ignore invalid data in the process. For example, in Figure 5: ' The creation of the new data file 3 invalidates the old data file 3. Erasable old; material rights 3: Recover the physical capacity used by the old data file 3. However, if: 2 and the sales file 3 are stored in the same physical block, the erase operation will trigger an abandoned item collection operation. Returning to Figure 6, the non-volatile memory storage system can perform a waste collection operation within a timeout period configured for write instructions. According to one embodiment of the present invention, an abandoned project collection operation can be split into a number of different phases (evening or partial) if the waste project is not completed within a timeout period. Here, the non-volatile memory storage system performs the part of the waste collection operation using the timeout period of the configuration = multiple write instructions. In other words, the non-volatile memory storage system utilizes a portion of the obsolete item collection operation that is configured for multiple write-out timeout periods. As shown in Figure 6, a write command for writing new material is received in operation 602. As used herein, the term "new material" is defined as data that is received by a non-volatile memory storage system from a write command to write to a memory. The write command I is set to a timeout period to complete the execution of the write finger 7. For &amp;, the timeout period is the time period configured for the execution of the write command. An example of a configured timeout period of 250 milliseconds can be a single sector write instruction or a multi-session write instruction. As will be seen in more detail in the 12273l.doc -13-200825738, in the single-segment write command, the new data γ-single area can be written to a random address on a hexadecimal. In a multi-session write deduction, new data for multiple segments with adjacent logical addresses is written to the memory. If an obsolete item collection operation cannot be completed within the timeout period, then part of the obsolete item collection operation is executed within the timeout period configured to write the instruction as shown in (10)4. φ can be reduced to the remainder of the waste collection during the post-week period. By way of example, Figure 7 shows a simplified block diagram of an example of a waste collection operation that is split into multiple sections 78A and 781, in accordance with an embodiment of the present invention. The non-volatile memory storage system shown in Figure 7 receives the &amp; segment write command 704 and, after tunneling, receives new lean material 760-762 for storage into a plurality of segments in the memory. The busy recording signal 702 is maintained after receiving each data segment·, 761 or μ. The non-volatile memory storage system maintains the busy recording signal 702 to allow execution of write commands, which may include obsolete item collection operations (if needed) and other operations. While maintaining the busy recording signal, a host does not send another command or additional data to the non-volatile memory storage system. The non-volatile memory storage system can maintain the busy recording signal 7〇2 for a limited amount of time after receiving each data segment, 761 or 762, - because the host allows a limited amount of W time ((4), timeout period 75〇_752) Used to execute a write command. If the busy recording signal is held longer than the timeout period of 75 〇, or 752, the host may repeat the write command or discard the process. Therefore, the non-volatile memory storage system cannot maintain the busy recording signal 7〇2 in a period longer than the timeout period I 751 or 752. The release of the busy recording signal 702 after completion of the write multiple 122731.doc -14-200825738 l solid block section 762 allows the host to communicate with the non-volatile memory storage system. Referring again to Figure 7, the discarded items can be configured between a plurality of timeout periods of 75 〇 752. Sickles 780 and 781. In other words, non-volatile memory storage systems can take advantage of 750, 751 or 752 per-timeout period

Set every part of the operation or 781. For example, during the first-timeout period of 75〇, the first part of the collection of the abandoned project is here, during the period 750, 'one part of the valid data can be copied from one block to another block. . In the second timeout period 751, the previous waste collection operation starting at the 卞 cycle is continued. During the timeout period 751, the volatile memory storage system performs the second portion 781 of the previous waste project collection operation until the previous waste project collection is completed. The previous collection of obsolete items can be accomplished by copying the remaining or last portion of the valid material from one block to another. If the previous abandoned project picking operation cannot be completed within the second timeout period of 75 ,, the non-volatile memory storage system can use the subsequent timeout period (such as the third timeout period 752) to collect the discarded items. operating. At the end of the multi-session write command number 4, the non-volatile memory storage system can maintain the busy recording signal 7〇2 after receiving the stop command until all data sectors are written to the memory cell array. ^ Please note that Figure 7 illustrates the operations associated with a multi-session write instruction. As will be explained in more detail below, for single-region write and multi-session write instructions, the discarded project collection operations performed may vary. For example, as will be explained in more detail below, the type of buffer used to store new data is a single-segment write 122731.doc -15-200825738 instruction or a multi-session write instruction depending on the received write instruction. And set. Returning to FIG. 6, after performing a portion of the discarded item collection operation in a timeout period, in operation 606, the new data received from the write operation can be stored in a non-burst memory storage system. Buffer

in. In one embodiment, the buffer may be an instance of a data structure associated with a non-volatile memory cell array (eg, non-volatile memory array 122 shown in FIG. 1). The blocks of the non-volatile memory cell array (such as write buffer blocks) are described in more detail below. In another embodiment, the buffer can be a block of a volatile memory cell array. For example, the new data can be stored in a block located in a RAM associated with the non-volatile S memory storage system (e.g., RAM 112 shown in Figure 1). In a further embodiment, as described above, the new material can be stored in a block located in an array of individual memory cells (e.g., memory cell array 123 shown in FIG. 1). Figure 8 is a flow diagram showing the detailed operation of (iv) execution-staged obsolescence item collection in accordance with an embodiment of the present invention. A receive-write instruction in operation 802 is shown in Figure 8 to write new data to a memory. In the case of %, the write command is a single-segment write command. In some instances, as will be explained in more detail below, according to another embodiment, the write finger can also be a multi-segment write command. After receiving the write command, the volatile memory storage system is maintained in the busy-busy signal. Before the execution of the write command, it is too 隹睥... In the case of 06, the waste test is executed in the period of the -discarded item, and in the embodiment, the part of the operation is selected. For example, or a block is used for the collection of obsolete items. 122731.doc -16- 200825738 Operation. The one or more blocks - ^ ^ include no political information and / or valid information. In an abandoned project collection time, Zhou Dong Wei Zhengbei. Piece. According to the configuration, the abandoned project will be copied to the second district, and all the valid materials or valid materials will be copied to the second district. Piece. g&amp; PAGE effect Beaconi configuration for waste project waste tea project collection time period can be expressed as, waste project collection time period =: timeout period 吆 where the timeout period is as described above for a L4 疋, limited time cycle. T, g is the maximum programmed time associated with writing new data to memory (eg, write to a buffer), or for non-volatile memory storage systems to write new data to memory. Maximum time. Because, in one embodiment, the 'non-volatile memory storage system tracks the amount of time used to copy valid data from the one or more blocks to the second block. Over time collection of discarded items The non-volatile memory storage system stops copying before the time period.

If the obsolete item collection operation cannot be completed during the obsolete item collection time period, new data associated with the write instruction can be written to the write buffer block in operation 810. The non-volatile memory storage system can write new data to the write buffer block before, during, or after the waste collection operation. As will be explained in more detail below, once the obsolete item collection operation is completed, new data can be copied from the write buffer block to an update block. The write buffer block is held in memory by the non-volatile memory storage system. In general, the write buffer block buffers new data in the non-volatile memory system. In an embodiment, the write buffer block spans multiple logical addresses. In another embodiment, the write buffer block spans the entire logical address space. By spanning the entire logical address space, the write buffer block can store all logical addresses and all logical address groups (ie, all logical groups) that are to be written to the entire non-volatile memory storage system. Group) information. In other words, new lean materials associated with different logical groups can be stored in the write buffer block. A logical group is a logical address group having a size equal to the size of the metablock. New data can be written to the write buffer block in a continuous or discontinuous (i.e., unordered or random) order. As will be explained in more detail below, when a new data written to a write buffer block is subsequently copied to another block (eg, an update block), the write buffer block acts as a temporary buffer. Device. As used herein, the term &quot;writer buffer block clear&quot; means copying new material stored in a write buffer block to another block. Note that in the embodiment the non-volatile memory storage system uses a write buffer block for phased project collection operations. Therefore, the write buffer block may not store the most recently updated new data. Therefore, if new data is read in the subsequent read operation, the non-volatile memory storage system checks which new data stored in the update block or write buffer block has been updated recently. The read operation then accesses and returns the most recently updated new material. In another embodiment, the non-volatile memory storage system can use write buffer blocks for non-staged project collection operations and staged project collection operations. Here, the write buffer block is used for all write operations. In other words, the collection operation from the non-staged project is carried out 122731.doc -18- 200825738 and the phased waste project collection operation is injected into the write buffer area ghost. Therefore, the write buffer block operates like a -n m tail image into the cache memory, and thus includes the most recently updated new material.

The index information associated with the buffer block can be stored in -single == or as part of the write buffer block itself. The data node = stored in the memory controller. Stored in the data structure: 2 messages allow tracking and access to the data stored in the buffer block H block. The information may, for example, include a logical address to the bit of the write buffer block t: the index of the effective index of the mapped or written buffer block. The index information can be updated after the shutdown-update block or after many updates to the write buffer block. As will be explained in more detail below, a write buffer block in an embodiment 2 can be configured for a segment-level index. In another example, the write buffer block can be configured for the -page boundary index. Although the write buffer block is full, the write buffer block can also be dusted. For example, the valid data stored in the write buffer block is copied to a new block to be referred to as a new write buffer block, and the existing write buffer with the invalid item is erased. Block. As used herein, the write buffer compression &quot; means compressing the valid data stored in the write buffer block. Referring again to FIG. 8, after the new data is written to the write buffer block and the waste item collection operation is performed during the waste item collection time period, in operation 812, the non-volatile memory storage system is in the timeout period. & Releases the busy recording signal. Therefore, the total time for executing the write command including the part of the waste collection operation or the waste collection operation is 122731.doc •19· 200825738 does not exceed the timeout period. If part of the collection of the abandoned project is performed within the timeout period, then the remainder is completed in the subsequent timeout period. When the waste project collection operation is completed, the erased project collects one or more of the blocks and makes them available for storage of additional data. 9A and 9B are simplified block diagrams of memory blocks having successively updated blocks collected by staged obsolescence items, in accordance with an embodiment of the present invention. As shown in Figure 9A, the original block a 98 and associated consecutive update block A 982 are selected for obsolete item collection. In general, data received from a write command can be written to an update block. Each logical group in which the poor material is updated may be assigned a special metablock as an update block. Please note that the logical data section is stored in a logical group containing a set of logically adjacent sections. An update block can be managed to receive data in a sequential or out-of-order order (i.e., in a discontinuous order). It should be understood that a continuous update block such as continuous update block A 982 is a meta block configured when a write command is received from the host to write data, and the data fills one or more of a logical group. Physical pages, all valid segments of the logical group are currently in the same metablock. The data sectors written to the contiguous update block are contiguously written logically addressed such that the segments are instead written to the corresponding logical segments in the original block. One of the updates in this logical group can be written to this successive update block until the consecutive update block is closed or converted to an out-of-order update block. Please note that when the last physical segment position of the consecutive update block is written to 8 s' for the continuous update block to close D, in other words, the continuous update block can be completely written by the host by the continuous update block or Caused by the filling of the updated section data copied from the original block. As explained in more detail below, 122731.doc -20-200825738, when a data segment written by a host is logically discontinuous with a previously written data segment within the logical group being updated, An out-of-order update block is created by a continuous update block conversion. The original block A 980 may include invalid and valid data represented by the hatched pattern and the dot pattern in Fig. 9A, respectively. Note that in addition to the valid material copied from the original block A 980, the continuous update block 982 additionally includes the existing material 981 written to the continuous update block A before the waste item collection operation. When receiving a write command for writing a new material 983, the write command may trigger the closing of the continuous update block A 982 (which is an obsolete item collection operation type) because the new data and one do not have an open The logical group associated with the update block or the new data invokes an obsolete item collection operation. The non-volatile § memory storage system maintains a busy recording signal and then copies the valid data from the original block A 980 to the continuous update block A 982 until the first obsolete item collection time period 970 expires. During the copy period, the non-volatile memory storage system tracks the time and the non-volatile memory storage system stops the copy operation until the first waste item collection time period is 97 。. As shown in Figure 9A, the obsolete item collection operation may not be completed within the first obsolete item collection time period 970 because there is still valid data remaining in the original block A 980. Therefore, after copying a portion of the valid data to the continuous update block A 982, the new material 983 is written to the write for the remaining time allowed before the expiration of the first timeout period. Buffer block 908. Figure 9B shows that the remainder of the waste project collection operation can be completed in a second over-defense cycle. Here, after the first write command, one is received for 12273 Ldoc -21 · 200825738

The second write instruction of the new data 984. Therefore, a second timeout period is configured for the second write command. During the second timeout period, the remaining valid data is copied from the original block A 980 to the continuous update block A 982. In this example, all of the remaining ^ valid data (or the last portion of the valid data) may be copied to the continuous update block A k 982 during the second obsolete item collection time period 972. Therefore, the waste collection operation can be completed in the second timeout period. Since the successive update block A 982 is filled, the continuous update area _ block A is converted into a new original block A 985 or a non-updated block. Since the obsolete item collection operation is completed in this second timeout period, the original block A 980 is erased and made available for storage of additional data. After erasing the original block A 980, the update block c 986 is configured and the new material 984 received from the second write command is written to the newly configured update block c. Please note that the update block C 986 may or may not be associated with the new original block a 985. After the obsolete item collection is completed in the second timeout period, if there is an available time in the second timeout period, the non-volatile memory storage system can perform a write buffer block clear operation. When a new material (such as new material 983) written to the write buffer block is later copied to another block (for example, update block C 986), the write buffer block 9〇8 serves as A temporary buffer. In the example + of Fig. 9B, there is a time for a write buffer block clear operation in the second timeout period. The new greed 983 stored in the write buffer block 〇8 is in the same logical group as the new material 984. Therefore, the new material 983 is copied to the update block c 986 after the completion of the discarding item collection operation. The new material 983 stored in the write buffer block 908 is marked as invalid, and thus, the write buffer area can be made. Additional space in the block can be stored in additional new shell materials at 122731.doc -22- 200825738. Note that a write buffer block clear operation may not be performed after each obsolete item collection is completed. The timing of writing to the buffer block clear is explained in more detail below. 1GE is a simplified block diagram of a memory block having an out-of-order update block collected by a staged obsolete item, in accordance with an embodiment of the present invention. As shown in Figure 10A, the original blocks A 9〇2 and A- are selected for discarding project collection. In general, an unordered update block such as None: Update Block A 904 allows a data segment to be updated in a random order within a logical group, and any repetition of individual segments can occur (5) by - Host When one of the data sectors is written to be logically discontinuous with the previously written data sector within the logical group being updated, the out-of-order update block can be established by the one-to-new = new block conversion. Regardless of the logical sector address in this group, all the poor sectors that are subsequently updated in this logical group are written to the next available segment location in the out-of-order update block. | : The second original block eight 902 and the out-of-order update block A 9〇4 include the invalid and valid receiving of the figure in the figure without a shadow pattern and * and the pattern is used to write the new data state. When the command is written, the non-volatile memory storage system maintains a trick... In the busy recording, the valid data is then

9〇6...^ A 9〇2 and the disorderly update block A 9〇4 are copied to the new block A f gate to the non-defective project collection time period 950 expires. During the complex period I, the non-volatiles were between the materials, and the non-volatile systems exceeded the first-abandonment project collection time period of 95. 4 copy operation. As shown in Figure 10A, the abandoned project collection operation 122731.doc -23- 200825738 is not available in the first abandoned project remaining in the original block 2 = 9: completed 'because still funding. Therefore, after the validity of the block A 904 of the valid material, after the P-part is copied to the new block A 906, the new data 9〇1 received before the start is written as R before the expiration of the time-duration period. 1ΠΡ η - ^ ^ 芏马入冲 into block 908. Continued: In this second item collection operation, a subsequent timeout period is followed by a second write command and a second write command

^ Brother writes &amp; configure - the second timeout period. During the second timeout period, the remaining valid data is copied from the original block A 902 and the out-of-order update block Α 9〇4 to the new block A 嶋 until the second abandoned item (4) time (four) 951 expires. As shown in Figure 〇B, the abandoned project collection operation cannot be completed within the second abandoned project collection time period 951 'because there are still remaining remaining in the original block A 902 and the out-of-order update block a 9〇4 data. Therefore, the new data 9〇5 received before the start of the waste tea item collection operation is written to the write buffer block 908 after copying a portion of the valid material to the new block A 9〇6. Figure 10C shows that the remainder of the waste project collection operation can be completed in a third timeout period. A third write command is received after the second write command. Therefore, a third timeout period is configured for the third write command. During the third timeout period, the remaining valid data is copied from the original block A 902 and the out-of-order update block A 904 to the new block a 906. Here, all remaining valid data (or the last portion of the valid data) may be copied to the new block A 906 during the third scrap item collection time period 953. Therefore, the waste collection operation can be completed in the third timeout period. Since the obsolete item collection operation is completed in the third timeout period of 122731.doc -24 - 200825738, the original block A 9〇2 and the out-of-order update block A 904 can be erased and made available for additional data. Store. After erasing the original block A 902 and the out-of-order update block 八 〇4, the new update block B 962 is configured and the new data 9〇9 received from the third write command is written into the newly configured update area. Block B. The new data 9〇9 is not written to the write buffer block 908 because the discarded item collection operation is complete and no new data needs to be buffered until a subsequent timeout period arrives. In this example, a write buffer block clear operation is performed in which new data 901 and 〇5 stored in write buffer block 〇8 are copied to update block b 962, assuming new material 9 〇1, 9〇5, and 9〇9 belong to the same logical group. Figure 10D shows another waste item collection operation performed during a fourth timeout period. The 'original zone _ 96 〇 and the unordered update block B 962 as shown in Fig. 10D are selected for discarding project collection. Has been converted into an unordered update area slope dispute new exchange R A ^

The new data received by the fourth write command 9〇3 is written to the write buffer "block 964, block 908. The remainder of the under-set operation can be shown in Figure 10D for the obsolete item 122731 of Figure 10D. Doc -25- 200825738 Completed in a fifth timeout period. A fifth write command is received after the fourth write command. Therefore, a fifth timeout period is configured for the fifth write command. During the period, the remaining valid data is copied from the original block B 960 and the out-of-order update block B 962 to the new block B 964. Here, all remaining valid data may be collected in the fifth abandoned project collection time period 953 (or

The last part of the valid data is copied to the new block B 964. Therefore, the waste collection operation initially performed during the fourth timeout period can be completed in the fifth timeout period. Since the obsolete item collection operation is completed in this fifth timeout period, the original block B 960 and the out-of-order update block] 3 962 are erased and made available for storage of additional data. After erasing the original block B 9(10) and the out-of-order update block B 962, the update block c 965 is configured and the new material 907 received from the fifth write command is written to the newly configured update block c. Please note that update block C 965 may or may not be associated with new block B 964. Here, a write buffer block clear operation is performed, and therefore, the new data 9〇3 stored in the write buffer block 908 is copied to the update block c 965' assuming new material 903 and new material 9 〇7 belongs to the same logical group. ▲ Figure 11 is a flow diagram of an operation for optimizing access to a write buffer block in accordance with an embodiment of the present invention. The write buffer block holds some additional overhead. In order to reduce the additional consumption, in one embodiment, the write to the write buffer block can be minimized. As shown in Figure u, a write command is received in (10)2. After that 'non-volatile in the operation deletion: 4 body health system estimation - execution time. The execution time is the time period in which the write command is used. The execution of the write command may include (eg, stylizing new data (or writing) memory, executing - discarding the project receipt) 122731.doc •26·200825738 ' and performing other operations. For example, the execution time gate valid data copied from one or more blocks to another _ zone change may include a time period for writing new data. The time period and non-volatile memory storage system for immediate estimation of the memory storage system can be estimated based on various parameters. = The following examples include the type of abandoned project collection (such as 'blocking parameters, and other types'), stored in a project to be abandoned: “幵, 压如, update block and other blocks” For valid data, the block (example =: save! stylized time, discarded project collection &amp; one block size (for example, one of the metablocks θ padding, the amount of data to be pre-populated, pipeline, cache) = first stylized failure, and other parameters. In one instance of Bo, ', .β, 疋, ^隹4, one execution time, - or multiple first blocks including twelve pages of valid data and the ten effects The data will be copied to the second block. The non-volatile memory storage system can be misdirected by the non-volatile memory storage system to read the twelve pages of valid data and the non-volatile memory storage system. The execution time is estimated by summing the amount of time it takes to write valid data to the second block. After the non-volatile memory storage system estimates the execution time, the execution time is compared to the timeout period in operation 6. As shown in operation i If the estimated execution time of the right is less than the timeout period or the operations can be completed within the timeout period, the waste collection operation is performed and the waste collection operation (if called) is completed within the timeout period, and the new data is acquired. Write to an update block. On the other hand, as shown in operation 1010, if the estimated execution time exceeds the timeout period (ie, greater than or equal to the timeout period 122731.doc -27-200825738 period), The new material is then written to the write buffer block and the configured obsolete item collection time period can be used to write to the buffer block clear or to perform part of the discarded item collection operation (if invoked). In an embodiment, as will be explained in more detail below, the write buffer block clear can be written to the first valid term of the buffer block during the remainder of the data cycle. The write to the write buffer block 'there will be less writes to the write buffer block when the estimated execution time exceeds the timeout period, and the destination is associated with the keep writer buffer n block Additional consumption available Write W-Block Index - Page Boundary Index In one embodiment, the write buffer block is constructed to include multiple pages and each page within the write t-buffer block is indexed. Each page of the buffer block is grouped to store new data of one or more segments. Therefore, an indicator is more or more "," and can be referenced by a plurality of regions in a page. Because the indicator points to one page and does not point to multiple sections within the page. In this case, new data belonging to the section of the same metapage is written to the same metapage of the write buffer block. However, New data belonging to segments of different metapages are written to different metapages of the write buffer block. For example, a new data of a first sector associated with a first write instruction is written To the write buffer - the first-page of the block. Thereafter, the 'self-second write command receives a new data of the second sector. If the new data of the second sector belongs to the same meta page as the new data of the first sector, the second sector is written to the first page of the write buffer block. On the other hand, if the new material of the second sector belongs to a different metapage, the second sector is written to one of the different metapages of the write buffer block. 122731.doc -28- 200825738 Write Buffer Block - Segment Level Index

In another embodiment, the write buffer block is constructed as a segment and the - or multiple segments written into the buffer block can be edited. ~ In terms of an indicator, one indicator can point to or reference multiple segments (eg, four segments V in another instance 'an indicator can point to or reference a segment. The parent-region in the write buffer block The segment is indexed and the new data is written into a single segment of the buffer block. Subsequent new data associated with the other _ write instruction is written to the next in the write buffer block. Available segments. For example, new data from segments of multiple write instructions can pass through to different segments of the same page in the write buffer block.

The buffer block can be constructed to include a plurality of segments and each segment is configured to store a new piece of data for a segment. U To maintain single-segment writes without a time-out error, the non-volatile memory storage system can configure many segments to a write buffer block such that the configured segments are larger than the non-volatile memory The total number of metablocks in the volume storage system. It should be appreciated that a write buffer block can contain multiple metablocks. To count the number of sectors allocated to a write buffer block, for example, the number of metablocks containing the write buffer block can be defined as Μ = Μ1 +

Metablock A Size - Μ 2 where Ml =: KoundUpίο.Nearest.Integer (JV -1) * (TotaLNunber.of Metablocks dnSystem) Metablock Size N Tgc N^TO-Tgc

Ml - RoundUp , to.Nearest .Integer 122731.doc •29· 200825738 .toJve£^.Megerp^^|,τ〇 is the timeout period, and

Tgc is the time to perform a complete waste project collection operation. The total number of sections allocated to the write buffer block can be defined as the total number of sections = M * Metablock - Size (1.2) in the equation ι 〇 and jyje tab l〇ck_ Size is The size of each metablock is calculated as a segment, such as 512 segments/meta block, 1〇24 segment/兀 block, 2048 segment/meta block, or other size. In general, Equations 1.0 and 1.2 define that the total number of sections allocated to the write buffer block is greater than the total number of metablocks in the non-volatile memory storage system. In addition to the total number of metablocks, Equation 1 〇 configures one or more metablocks (or sections) for maintaining additional overhead associated with writing buffer blocks (hereinafter, additional elements) Block "or" additional section"). For example, the part of the definition of Equation 1〇 is the number of (Ml*M2)/(Metabl〇ck_size_M2), where the additional section can be borrowed Calculated by multiplying the additional block by the metablock size. By assigning the number of segments as defined in Equation 1 to 2 to the write buffer block, the timeout error can be avoided, even in continuous The same is true for the worst case scenario of random single-segment writes. A time-out error can occur when the write buffer block is full and an obsolete item collection operation cannot be completed. When each single-segment write instruction is written The worst-case situation occurs when entering a different logical group, so that each time a person writes, a complete worker collection operation is performed. In this worst case scenario, the segments are accumulated and written to the write buffer. The condition of the block block can be regarded as the new capital of a single segment for each timeout period. The write is written to the write buffer block, and each section of the non-volatile memory marks the 122731.doc -30-200825738 as invalid for the time it takes for the system to perform a complete waste collection operation (Tgc). In addition, when the write buffer block is filled or full, the write buffer block is compressed to receive the new sector but a write buffer block clear operation may not be performed. Therefore, in a worst case condition In the case where the discarded item collection time period is greater than the timeout period, the write buffer block is filled faster than the vacated speed. However, if multiple sectors in the write buffer block belong to the same Logical group, all segments can be merged during a waste project collection operation. By configuring enough metablocks to a write buffer block, there is a non-volatile presence in the write buffer block. A segment (or item) of a plurality of metablocks in a memory storage system, and thus, there is a logical group having a plurality of valid segments written into the write buffer block. One of the buffer blocks is obsolete When collecting or merging, all segments belonging to the same logical group are merged into a new update block and marked as invalid in the write buffer block. Therefore, the rate at which the buffer block is vacated will be greater than Fill rate ' and thereby prevent the write buffer block from being full or filled. Thus 'for each given Tgc, the non-volatile memory storage system will be larger than the non-volatile § memory storage system A section of the total number of blocks is allocated to the write buffer block so that the occurrence of a timeout error can be prevented, even for the worst case scenario as described above. Figure 12 is a diagram of an embodiment of the present invention. Flowchart for the operation of temporarily storing new data in a scratch pad block. It should be understood that 'non-volatile memory storage system can have multi-level buffer or multi-buffer level' similar The concept of multi-level cache. In this embodiment, the write buffer block can be associated with one of a number of buffer stages. In the case of multi-buffer level 122731.doc • 31 - 200825738, 'not directly writing new data to the write buffer block, but before writing the new material to the write buffer block The new data is temporarily stored in another buffer level. The temporary storage of the new data in the buffer level of the buffer level different from the write buffer block can reduce the complex (four) 1 plus consumption associated with the write buffer block in the staged waste collection. And latent time. - Buffer - An example is a high speed temporary storage block.高速 The scratch pad block can be associated with a buffer level different from the write buffer block. For example, it involves I^

The buffered temporary block can be used as a first buffer stage and the write buffer H block can be used as a second buffer stage. As described above, in the case of a single-segment index, the new data of the section of the write-to-hand X is written to the same page in the write buffer block. Different sections. Because the non-volatile memory storage system may not be able to program part of the page, so according to the death of the moon, the case of the transfer of new data to the write buffer block: the new data can be temporarily stored in the first A buffer stage (such as a high speed temporary block). It should be appreciated that the "short-term temporary block" is in the form of a data update block 'which may be - stochastically ordered and repeated with any amount of writes, where the expected logical segment does not end at the physical page boundary or Cross the physical page boundary. A scratchpad block can contain some real-valued material, but some partial page data is not allowed. High-speed temporary storage 2 blocks: keep-effective pages (4) in the non-volatile memory storage system, each of the first update blocks. The non-volatile memory storage system may have (8) eight update blocks of, for example, a π configuration, and because of the A, the high-speed temporary storage block can store data of 9 valid pages. The logical section within the associated logical group. The high-speed temporary storage block is powered by 122731.doc -32-200825738, as shown in FIG. 12, firstly, the new shell material received from the write-in command is inserted into a high-speed temporary storage block in the operation. . The block may include a plurality of segments and the parent page includes a plurality of segments. The new data is stored in the block-section. In operation 11G4, when the #high-speed temporary storage type and the page associated with the write buffer block are full, the new beta is copied from the two temporary storage blocks to the write buffer memory storage line m &gt Early nurturing system, first port, which accumulates one page in the temporary temporary storage block, and all the sections of the page are filled with new capital from various writing instructions: 敕j volatility The memory storage system is then in the stylized operation 2 pages (9) such as 'new data of 'eight segments') from the high-speed temporary storage block re-stored block and can contain two or two punch blocks can be greater than the high-speed temporary After the abandoned project, I will think about it, and what is the top of the testis. Therefore, the 'high-speed temporary storage block', the second, * is faster than the waste project of the 11 block block. Because the second fine and light high-speed temporary storage block will write the new f material, the new data will be written to the write buffer block. Audio/video data-access to the memory associated with a non-volatile video channel, the charging and the audio/machine may need to use audio 7 data), and then a predetermined rate of audio /visual data. When the host compares...and his poor materials to the memory storage system and/or from non-noisy, serial to non-volatile/video data, the configurable memory storage system stream Sound capture. Access to audio/video data during the period of one of the obsolete items collected 122731.doc -33- 200825738 Operation can degrade the write performance of audio/video data. Therefore, in the embodiment, When the multi-session write command is not associated with the audio/video data, the bite multi-session write command is performed at the beginning of an audio/video write, and the phased item collection is performed. To distinguish between audio/video data and other In one embodiment, the # volatile memory storage system can refer to the target logical address associated with the multi-session write command. Since the audio/video data is continuously written, it is translated into a backward jump. aims The logical address may indicate that the new data is not audio/video data (or at the beginning of the audio/video data). In another embodiment, the non-volatile memory storage system may also refer to the segment associated with the new data. The number of audio/video data and other data can be separated. The audio/video data can be stored in a unit called a recording unit. The minimum recording unit associated with the audio/video data can be 32 segments in length. The number of associated segments is not an integer multiple of 32 segments (hence) indicating that the new beaker is not an audio/video material. The received misalignment with a recording unit or • new information that does not begin at the beginning of a recording unit It can be instructed that the new data is not audio/video data. Therefore, if one of the following conditions is applicable, the phased project can be executed. (1) The multi-session writer command invokes the waste project collection operation; (7) _ target logical address Translated as—backward jump; (3) target logical address misalignment: record unit boundary; and (4) after receiving a stop instruction (ie, multi-session write private order) End), if the number of segments associated with the new material is not an integer multiple of 32. Single segment write 122731.doc -34- 200825738 Figure 13 is a single segment write in accordance with an embodiment of the present invention A flowchart of the operation of the non-volatile memory storage system associated with the instructions. The new data can be written to a random address on a memory cell array as a single segment. Depending on host activity and card segments, the host can Writing a long-lane case with multiple segments to a random location using a single-segment write instruction. Because there are a limited number of updated blocks configured, such single-segment writes can be quickly performed. Update blocks to promote non-volatile memory storage

The obsolete item collection operation is performed to clear the block for subsequent write operations. As shown in Figure 13, a single-segment write command is received in operation 12〇2. Thereafter, it is determined in operation 1204 whether the single-segment write instruction invokes an obsolete item collection operation. If the single-segment write command does not invoke a discard item collection operation, the new f-material is written to the memory in operation 122G. And if the single-segment writer command invokes the __discard project collection operation, it determines whether there is a pending phased project collection (ie, '- has started but cannot be completed) Abandoned project collection and fine = phase of abandoned project collection operations). If there is a staged obsolescence item = operation, then in step 1208, the staged discarding of the item collection operation is continued. (4) The remainder of the previous abandoned item collection operation. As shown in the exercise: 1210, the execution of the sub-/, 乍华 item... government project collection operation until the difference of the waste:: period (such as the 'timeout period and stylized time'; 爰 value) expires , 嗖吉』" &amp; until the meta-component stage is collected for the purpose of failing to complete the staged discarding 122731.doc -35-200825738 collection operation during the collection period of the abandoned project, then the new data is written to the write buffer in operation 1218. Block. If the waste project collection time period has not expired or the phased project collection operation can be completed before the waste project collection time period expires, then in operation 12, it is determined whether the single segment write instruction still invokes the waste project collection operation. This is true even after the completion of the phased project collection operation. If the single-segment write command does not invoke an obsolete item collection operation, new data is written to the memory in operation 1220. On the other hand, if the single-segment write command does invoke the obsolete item collection, then an obsolete item collection operation is performed in operation 1214 until the obsolete item collection time period shown in operation 1216 expires. If the staged item collection operation cannot be completed within the discarding project collection time period, new data is written to the write buffer block in operation 1218. Otherwise, new data is written to the memory in operation 122B. Please note that if there is a staged waste collection and when the write command also invokes an abandoned project collection operation, the waste project collection time period shown in operation 1216 is the waste project collection time period shown in operation 121〇. One continues. Therefore, if there is a staged discarding project collection and the current single-segment write command invokes an obsolete project collection operation, then both operations are completed within the total obsolete project collection time period. In other words, the execution time of the staging item collection operation shown in operation 1208 and the discard item collection operation shown in operation 1214 is, for example, the difference between the timeout period and the stylized time. After the new data is written to the memory in operation 1220, it is determined in operation 1224 whether a valid entry exists in the write buffer block and if the timeout period has expired. If there is no valid entry in the write buffer block or the timeout period is 122731.doc -36 - 200825738 = ', the operation ends. Alternatively, if there is a valid entry and the timeout period expires, then execution is performed in operation 1226 - the write buffer block clear operation secret timeout period expires. It is also possible to perform a write and a block compression operation during this period until the timeout period expires. Multi-session write / 14 is a flow diagram of the operation of a non-volatile memory storage system associated with a multi-session write command in accordance with an embodiment of the present invention. Write human memory

Most of the new data in the early car 为J is a large data file occupying an adjacent continuous logical address space. Depending on host activity, the host can write large data archives using multisession write instructions. This new material contains new material with multiple segments with multiple timeout periods. Figure 7 shows an example of a multi-session write command. As a general matter, since multiple timeout periods are available, new data can be written to the update block of the 1 configuration without being written to the write buffer block. Therefore, write buffer blocks are typically not used in multiple write instructions because the collection of obsolete items can typically be done in multiple timeout periods configured for multi-segment write instructions. A multi-segment write command is received in operation 13〇2 as shown in FIG. Thereafter, in operation 1304, new information for the segments is stored (or buffered) and the obsolete item collection operation is performed as needed. Here, the non-volatile memory storage system may not utilize a write buffer block because multiple timeout periods are configured for multi-session write instructions and an obsolete item collection operation is typically available for multi-segment write instructions. Completed during the end. Therefore, the non-volatile 5 MEM storage system can store new data in the RAM associated with the non-volatile memory storage system, or in the non-volatile memory storage system 122731.doc -37- 200825738 The associated other memory is not stored in the write buffer block, while the busy recording signal is maintained between the new data of the segment to perform the waste collection operation using the configured timeout period. After buffering the host section, a determination is made in operation 1306 as to whether to receive new data that is less than the service sector. As mentioned above, new data associated with a one-to-one-segment write instruction may not be written to the write buffer block, since the obsolete item collection operation can usually be configured for multiple-segment write operations. The time period is completed. However, in the embodiment, if there is an insufficient timeout period configured to complete the waste collection operation, the write buffer block can be used in the - multi-session write instruction. Therefore, regardless of the call to an obsolete item collection operation, a multi-session write instruction having new data of at least N sectors can be directly written to the update block and not written to the write buffer block, where N It is defined as follows. N=round [(Tge+T0)/T0] down to the nearest integer (2〇) Equation 2.G shows when the writer command is a single-segment writer command or when

• When the #发性记忆存系统 receives a small:N (four) segment of new data in the multi-session write command, 'writes new data to the write buffer block. Referring again to Figure 14, if a small (four) segment is received, the non-volatile memory storage system operates on multiple '11-segment write instructions in accordance with the single-segment write command operation shown in Figure 13. However, if new data for more than N segments is received, a determination is made in operation 1310 as to whether a write buffer block clear operation can be performed. For example, if the new data received in operation 13〇2 does not call the waste project collection, or if the new data call is collected before the expiration of the configured waste project collection time period, the execution is 122731.doc • 38 - 200825738 Into the buffer benefit block clear operation. However, if the new data is bounded, the write buffer block clearing will not be performed, because the 'new data can be the audio/video shell. The right write buffer can not be executed on the right (4) Clear operation. 13 14 Write new data to the memory. If ', it ^ ^ Ml ^ 仃 is written to the buffer block ridge ', then it is executed in operation 1312 - the staged item collection operation and a write buffer block clear operation until the multi-session write finger The total busy week maintained by the non-volatile memory storage system during the second stub period:

It is Tgc-Tpmg. Thereafter, new data is written in operation 4 = non-volatile memory cell array. In this embodiment, the number of cycles (such as 'return to Tge.Tpmg period, four timeout periods, five timeout periods', and other periods) can be made before the multi-segment write command is received. The write buffer block clear shown in operation 13 12 is performed between segments (eg, between the second segment and the third segment). After the write command is executed, a determination is made in operation 1316 as to whether the new material is an integer multiple of 32 zone slaves. If the new data is an integer multiple of the μ segment, the new data can be audio/video related data and the operation ends. On the other hand, if the new data is not an integer multiple of 32 segments, a determination is made in operation 1318 as to whether there is a valid term in the write buffer block and if the timeout period has expired. If there is no valid item in the write buffer block or the timeout period has expired, the operation ends. On the other hand, if there is a valid term and the timeout period has not expired, then a write buffer block clear operation is performed in operation 1320 until the timeout period expires. The embodiments described above provide a means and/or system for the phased collection of obsolete items. A waste project collection operation can be split into multiple phases. 122731.doc -39- 200825738 Multiple phases are executed on the evening timeout period. By splitting the abandoned project to receive "stay:" each phase of the waste project collection operation can be completed within the timeout period and hunted to prevent overtime errors. Although the above implementation has been described in some detail for the sake of clarity of understanding The examples are intended to be illustrative and not limiting, and such implementations are intended to be illustrative and not limiting. The case shall not be limited to the jin in this article. The fineness of the article may be modified in the accompanying patent (4) and in the scope of the patent. Unless otherwise specified in the scope of application, otherwise: The components and/or operations do not imply any specific operation. [Simplified description of the drawings] FIG. 1 is an example of a non-Zymographic memory stored in a mussel 1 j I according to an embodiment of the present invention. Figure 2 is a simplified block diagram of a memory cell array organized into a plane. Figure 3 is a simplified block diagram of a memory cell page. Figure 4 is a simplified block diagram of a section of a memory cell. Non-volatile record A simplified block diagram of the logical interface between memory storage systems. Figure 6 is a flow diagram of a general overview of the use of A^^Knife White Slave Disposal Projects in accordance with an embodiment of the present invention. A simplified block diagram of a collection operation of a plurality of portions of a hang-up τ5 α 5 5 根据 根据 。 。 。 。 。 。 。 。 。 。 。 。 。 。 。 。 。 。 。 。 。 。 。 。 。 。 。 。 Abandonment 122731.doc -40- 200825738 Flowchart of detailed operation of project collection. Figures 9A and 9B are simplified blocks of memory blocks with successively updated blocks collected by staged obsolescence items, in accordance with an embodiment of the present invention. 10A, FIG. 10B, FIG. 1A, FIG. 10D and FIG. 1E are memory blocks of an disorderly update block collected by a staged waste project according to an embodiment of the present invention. Figure 11 is a flow diagram of an operation for optimizing access to a write buffer block in accordance with an embodiment of the present invention. Figure 12 is a diagram for New data temporarily stored in a high-speed temporary storage Figure 13 is a flow diagram of the operation of a non-volatile memory storage system associated with a single-segment write command in accordance with one embodiment of the present invention. Figure 14 is an implementation of the present invention. A flow chart of the operation of the non-volatile memory storage system associated with the multi-session write command. [Main component symbol description] 102 Non-volatile memory storage system 104 Host interface 106 Processor 108 Memory interface 110 5 Recall memory controller 112 random access memory (ram) 114 error correction code (ECC) circuit 116 read only memory (ROM) 118 memory 122731.doc 41 200825738

120 Array Logic 122 Non-Volatile Memory Cell Array 123 Memory Cell Array 124 Busbar 126 汇 Busbar 202 Plane/Logical Plane 203 Plane/Logic Plane 204 Plane/Logic Plane 205 Plane/Logic Plane 210 Block 211 Block 212 Block 213 Block 220 Block 221 Block 222 Block 223 Block 401 Page 402 Section 404 Section 405 Additional Data 406 Data 502 Memory Cell Array 504 Block 122731.doc -42- 200825738 512 Logical Address Space 702 Busy Recording Signal 704 Multi-Segment Write Command 706 Stop Instruction 750 Timeout Period / First Timeout Period 751 Timeout Period / Second Timeout Period 752 Timeout Period / Third Time Period Period 760 New Data

761 New information 762 New information 780 Part of the collection of abandoned projects / Part 1 781 Part of the collection of abandoned projects / Part II 901 New information

902 Original Block A 903 New Information

904 Out of Order Update Block A 905 New Data

906 New Block A 907 New Data 908 Write Buffer Block 909 New Data 950 First Obsolete Project Collection Time Period 951 Second Waste Project Collection Time Period 952 Fourth Waste Project Collection Time Period 122731.doc -43- 200825738 953 Three abandoned project collection time period / fifth abandoned project collection time period

960 original block B

9 62 New Update Block B / Unordered Update Block B

964 new block B

965 update block C

970 First Waste Project Collection Time Period 972 Second Waste Project Collection Time Period 10 980 Original Block A 981 Existing Information

982 Continuous update block A 983 New information 984 New information

985 new original block A

986 Update block C Φ P0 page P1 page P2 page P3 page • P4 page P5 page P6 page P7 page 122731.doc -44-

Claims (1)

200825738 X. Application for Patent Park: 1. A method for supporting a non-volatile memory storage system, comprising: eight=receiving: writing a person's instruction to write a plurality of materials, the writer's instruction is over-allocated Knowing that the cycle is executed by one of the completion write instructions, executing in the timeout period, the portion of the waste collection operation, and the plurality of materials are stored in association with the non-volatile memory storage system. In the buffer. 2. 2 °. The method of claim 1, wherein the buffer is a write buffer area 3&quot;&quot; a method for operating a non-volatile memory storage system, comprising: receiving a suitable one And the horse is ordered to write a plurality of data, the write command is configured to be over-cycled to complete the execution of the write command; maintaining a busy record signal; and the waste project collection time period is a part of the plurality of valid data Copying from one or more first blocks to a second block; &amp; : multiple data is written to a third area 35, the third block is grouped to span a plurality of logical addresses; 4 For example, the busy recording signal is released before the timeout period expires. The method of claim 3, further comprising: maintaining the third block in a "non-volatile memory storage system." The method of claim 3, wherein the copying of the plurality of valid data includes: 12273i .doc 200825738 Tracking - the time for copying the portion of the plurality of valid materials from the one or more first blocks to the second block; and exceeding the spent testosteres 隹# at that time Stopping the copying of the portion of the plurality of valid materials before the collection period of the brachial item. 6. The method of claim 3, further comprising: "copying the portion of the plurality of valid data and the plurality of Before the data is written to the third block, it is estimated that the execution time of the execution of the write command, :: the right execution time exceeds the timeout period, and the portion of the plurality of valid data is copied and The tool and the plurality of data are written to the third block. The method of claim 3, wherein the non-volatile memory storage system package 3 has a plurality of buffer stages 'the third block and the plurality of blocks One of the buffer stages Associated with. 8. The method of claim 3, wherein the writing the plurality of materials comprises: : 乂 a plurality of bodies are written to a high speed temporary storage block; and copying the plurality of materials from the temporary temporary storage block to the third area 9·, as in the method of claim 1, wherein the plural number The data is copied to a section associated with the w temporary storage block. 10. If the request item is only linked to the page, and the first time is related to the cached block 2, the plurality of materials are copied from the cached block to the first block. The page is configured to include the plurality of materials. 11. If the request item R + , , method 'where the cache pad is associated with a first buffer 122731.doc 200825738 level, and 誃 12. as the party of claim 3: block and a second buffer Level associated. ', wherein the writing the plurality of data comprises: writing the plurality of assets obliquely ^ =, , 卄 to a younger one buffer stage; and copying the first buffer level to the third block, /, first The buffer level is associated. 13. As requested in item 3, the time-out period of the fish-related $disposal item collection time period is ~ A difference between the programs associated with the plurality of data written by the writer. 1 14. If the third block is a write buffer block 0 15 · If the request block 3 is in the request item 3 &gt; 士, +, 、,,,, Configure to span an entire logical address space. 16. The method of claim 3, wherein the third block comprises a plurality of pages, and wherein each of the plurality of pages is indexed. The method of claim 3, wherein the third block comprises a plurality of segments, and wherein each of the plurality of segments is indexed. 18. The method of claim 3, wherein the write command is a single segment write command 0 19. A method for operating a non-volatile memory storage system, comprising: receiving a first single segment Writing a command to write a first plurality of data, the early segment write command being configured for a first timeout period to complete a first execution of the first single segment write command; maintaining a first busy Recording medium signal; 122731.doc 200825738 Copying the first part of the plurality of valid materials from one or more first blocks to a second block in an abandoned project collection time period; writing the first plurality of materials Into a write buffer block, the write buffer block being configured to span a plurality of logical addresses; Releasing the first busy recording signal before the expiration of the first timeout period; receiving a second single-segment write instruction to write a second plurality of data, wherein the second single-segment write command is Receiving the first single-segment write command, the second single-segment write # command, configured for a second timeout period to complete one of the second single-segment write instructions Maintaining a second busy recording signal; copying the second portion of one of the plurality of valid data from the one or more first blocks to the second block during the collection period of the three discarded items; The second busy recording signal is released before the second timeout period expires. 20. The method of U-page 19, further comprising writing the second plurality of data to the write buffer block. 21. If the method of item 19 is found, the pot enters a boat and the white winter face knots into/b 3 to write the second plurality of data to an update block. 22. According to the method of claim 19, the bean enters a + And the progress package 3 releases the one or more first blocks after the second portion of the plurality of valid materials is throttled. 23. The method of claim 22, wherein the portion of the plurality of valid data is The plurality of __ last part, then erase the -: a plurality of first blocks. A 24. The method of claim 19, A. The step of deleting the first-complex data 122731.doc 200825738 from the write buffer block to an update block. 25. The method of claim 19, wherein writing the first plurality of data to the write buffer block comprises: writing the first plurality of data to a region of a cache pad A segment, wherein a page associated with the segment includes a plurality of segments, and the page is copied to the write buffer block when the plurality of segments associated with the page are filled. 26. The method of claim 19 wherein the write buffer block is configured for a sector level index. 27. The method of claim 19, wherein the write buffer block is configured for a one-page boundary index. The method of claim 19, wherein the write buffer block comprises a plurality of segments and a plurality of additional segments, the plurality of segments being greater than a total number of metablocks in the non-volatile memory storage system . 29. A non-volatile memory storage system comprising: a brotherly body, which is configured to store a storage system firmware; a non-volatile memory unit array configured to maintain a buffer And a processor in communication with the memory and the non-volatile memory unit array, the processor being configured to execute the storage system firmware stored in the memory, the storage system firmware comprising The program instruction is as follows: receiving a write command to write a plurality of data to the non-volatile memory cell array, the write command being configured to complete the write command by a time period of 122731.doc 200825738 Once executed, the portion of the _discarded item collection operation is executed during the timeout period, and the plurality of data are stored in the buffer. 30. A non-volatile memory storage system, comprising: - a memory configured to store a storage system firmware; "a non-volatile memory single transfer column, which is held by a (four) (four) write buffer Block 'The write buffer block is configured to span a plurality of logical addresses; and process it to communicate with the § memory and the non-volatile memory unit array. 'Process H is configured to be stored in The memory storage system (4) in the memory, the storage "_ contains the poem-style instruction: madly receives a writer command to "multiple data" to the non-volatile memory unit array, Changi λ &amp; person, Ping In the early morning, the write command is configured to execute one of the write orders, one of the write commands is executed, 70 maintains a busy record signal, and: - a part of the discarding project is executed during the collection period of the discarded item, and the person stays A plurality of data is inserted into the write buffer block, and the busy record signal is released before the timeout period expires. 31. The non-volatile memory storage system of claim 30 When its abandoned project is collected In the inter-period, the execution of the scrap in the part of the 浐 浐 浐 、 、 、 、 、 、 、 、 、 私 私 私 私 私 私 122 122 122 122 122 122 122 122 122 122 122 122 122 122 122 122 122 122 122 122 122 122 122 122 122 A program instruction for copying one of the plurality of valid data from one or more first blocks to a second block. 32. The non-volatile memory storage system of claim 3, wherein the storage system, the system Further including program instructions for: estimating the execution of the write command prior to performing the portion of the waste project collection operation and writing the plurality of data to the write buffer block Execution time, wherein if the execution time is greater than the timeout period, the portion of the discarded item collection operation is executed, and the plurality of materials are written to the write buffer block. 33. A non-volatile memory storage system, wherein the program instructions for writing the plurality of data to the write buffer block include program instructions for: Writing to a cache pad; and copying the plurality of data from the scratch pad block to the write buffer block. 34. The non-volatile memory storage system of claim 30, Wherein the write buffer block comprises a plurality of pages, and wherein each of the plurality of pages is indexed. 35. The non-volatile memory storage system of claim 30, wherein the write buffer The block includes a plurality of segments, and wherein each of the plurality of regions is indexed. The file is buffered. 36. The non-volatile memory storage buffer block of claim 30 includes a plurality of blocks. 122731.doc 200825738 37 · A non-volatile memory storage system, including · a read-only memory (ROM), which is configured to be stored in one: the dumping system is tough (thinking a body saponin array, the "ν", the mouth scale region, the write buffer block configured to span a plurality of logical addresses, a non-volatile memory cell array; a processor 'which is in communication with the R 〇 M, the array of memory cells and the array of memory cells, the processor being configured to execute the firmware of the storage system in the 忒ROM, the storage system being tough The program instruction is as follows: receiving a first write command to write the first plurality of data to the (four)-issue memory single (four) column, (4) - the write command is configured: the brother one timeout period Completing the first execution of one of the first write instructions; maintaining a first busy recording signal, and one of the plurality of valid data in the collection period of the discarded item first: split from - or multiple - The block is copied to the second block, the first plurality of data is written to the write buffer block, and d is released before the expiration of the first timeout period. ^^上匕—write, deduction to write the second plurality of data to the non-volatile memory cell array, the second write command is received by: after the 'input command The second write command is configured to configure a first timeout period to complete the second write a second execution, a 122731.doc 200825738 maintains a second busy recording signal, the second portion of the plurality of valid data from the one or more first blocks in the discarded project collection time period Copying to the second block, and releasing the second busy recording signal 0 before the second timeout period expires. 38. The non-volatile memory storage system of claim 37, wherein the storage system The firmware further includes program instructions for writing the second plurality of data to the write buffer block. 39. The non-volatile memory storage system of claim 37, wherein the storage system firmware further comprises program instructions for writing the second plurality of data to a newer block. 4. The non-volatile memory storage system of claim 37, wherein the storage system further comprises a program instruction for: if the plurality of valid beakers are the first part of the plurality The last part of the valid data is then erased by the one or more first blocks. 41. The non-volatile memory storage system of claim 37, wherein the storage system holding body further comprises program instructions for copying the first plurality of data from the write buffer block to an update block . 42. The non-volatile memory storage (IV) of claim 37, wherein the write buffer block comprises a plurality of pages, and wherein the first plurality of data are written to an associated write buffer region The first page of the block, and the second plurality of data is written to - associated with the write buffer area: a page 0 122731.doc 200825738 43. Non-volatile memory storage as claimed in claim 37 a system, wherein the write buffer block comprises a plurality of segments, and wherein the first plurality of data is written to a first segment associated with the write buffer block, and the second A plurality of data is written to a second segment associated with the write buffer block. 44. The non-volatile memory storage system of claim 37, wherein the non-volatile The memory storage system includes a plurality of buffer stages associated with one of the plurality of buffer stages. 45. The non-volatile memory storage system of claim 37, wherein the program instructions for writing the first plurality of data to the write buffer block comprise program instructions for: Writing the first plurality of data to a zone I of a cache pad and wherein the page associated with the zone comprises a plurality of segments; and when the plurality of segments associated with the page are When filled, the page is copied to the write buffer block. 46. The non-volatile memory storage system of claim 45, wherein the cache block is associated with an f-buffer level and the write buffer block is associated with a second buffer stage. 47. The non-volatile memory of claim 37, the program of the plurality of data instructions: a volume storage system, wherein the program for writing includes a program for the following operations to a first buffer level; and the plurality The data is written from the plurality of tributaries from the first block, and the write buffer block is associated with the buffer level copied to the write buffer a second buffer stage. A non-volatile memory storage system comprising: Writing to a buffer block, the write buffer block being configured to span a plurality of logical addresses; and geo-communicating with the 5-body and the non-volatile memory unit array, the processing group The storage system (4) stored in the memory, the storage system_body includes instructions for: l receiving-writing instructions to write a plurality of data to the non-volatile memory a cell array, the non-volatile memory cell array is configured to perform a timeout period to complete execution of one of the write commands, maintain a busy recording signal, and select one of the plurality of valid data from a waste project collection time period Or copying the plurality of first blocks to a second block, writing the plurality of data to the write buffer block, and releasing the busy record signal before the expiration of the timeout period. 49. The non-volatile memory storage system of claim 48, wherein the program instructions for the portion of the plurality of valid data include a program instruction for ' 彳 :: tracking one for Stopping the portion of the plurality of valid data from the one or more first blocks to the second block; and, - stopping the copying of the plurality of copies before the time period exceeds the collection time period of the discarded item This part of the valid data. The non-volatile memory storage system of claim 48, wherein the storage system firmware further comprises program instructions for: ^ copying the plurality of valid data and writing the Before the plurality of data is 'estimated - the execution time of the execution of the write instruction, wherein if the execution time exceeds the timeout period, the portion of the plurality of valid materials is copied, and the plurality of materials are written To the write buffer block. The non-volatile memory storage system of claim 48, wherein the program instructions for writing the portion of the plurality of data include program instructions for: providing - including - page cache a block, the page comprising a plurality of segments; writing the plurality of data to a segment associated with the page; and copying the page from the scratch pad to the write when the page is full Into the buffer block. 52. The non-volatile memory storage system of claim 48 wherein the discarding item collection time period is a difference between the timeout period and a stylized time associated with the writing of the plurality of data. 53. The non-volatile memory storage system of claim 48, wherein the write buffer block is configured to span an entire logical address space. 54. The non-volatile memory storage system of claim 48, wherein the write buffer block is configured for a sector level index. 55. The non-volatile memory storage system of claim 48, wherein the write buffer block is configured for a one-page boundary index. The non-volatile memory storage system of claim 48, wherein the cache system firmware further comprises a program for configuring a plurality of segments to the write buffer block The plurality of segments are greater than a total number of metablocks in the non-volatile memory storage system. 122731.doc 13·