US20130219116A1 - Data migration for composite non-volatile storage device - Google Patents
Data migration for composite non-volatile storage device Download PDFInfo
- Publication number
- US20130219116A1 US20130219116A1 US13/605,916 US201213605916A US2013219116A1 US 20130219116 A1 US20130219116 A1 US 20130219116A1 US 201213605916 A US201213605916 A US 201213605916A US 2013219116 A1 US2013219116 A1 US 2013219116A1
- Authority
- US
- United States
- Prior art keywords
- storage device
- unit
- data structure
- data
- data storage
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Abandoned
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F12/00—Accessing, addressing or allocating within memory systems or architectures
- G06F12/02—Addressing or allocation; Relocation
- G06F12/08—Addressing or allocation; Relocation in hierarchically structured memory systems, e.g. virtual memory systems
- G06F12/12—Replacement control
- G06F12/121—Replacement control using replacement algorithms
- G06F12/123—Replacement control using replacement algorithms with age lists, e.g. queue, most recently used [MRU] list or least recently used [LRU] list
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0668—Interfaces specially adapted for storage systems adopting a particular infrastructure
- G06F3/0671—In-line storage system
- G06F3/0673—Single storage device
- G06F3/068—Hybrid storage device
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2212/00—Indexing scheme relating to accessing, addressing or allocation within memory systems or architectures
- G06F2212/21—Employing a record carrier using a specific recording technology
- G06F2212/217—Hybrid disk, e.g. using both magnetic and solid state storage devices
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0602—Interfaces specially adapted for storage systems specifically adapted to achieve a particular effect
- G06F3/061—Improving I/O performance
- G06F3/0611—Improving I/O performance in relation to response time
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0628—Interfaces specially adapted for storage systems making use of a particular technique
- G06F3/0655—Vertical data movement, i.e. input-output transfer; data movement between one or more hosts and one or more storage devices
- G06F3/0656—Data buffering arrangements
Definitions
- the present invention relates to methods for managing storage of data in a composite non-volatile memory that is a composite of a slow memory device and a fast memory device.
- a composite disk system a large, slow, and inexpensive magnetic hard drive can be combined with a small, fast but expensive storage device, such as a solid state drive to forma logical volume. This can provide the advantage of fast access through the solid state drive (SSD) while providing the large capacity of the magnetic hard disk drive (HDD).
- SSD solid state drive
- HDD magnetic hard disk drive
- Prior techniques for managing such a composite disk have used algorithms such as a least recently used (LRU) algorithm or a CLOCK algorithm or the ClockPro algorithm described by Song Jiang.
- a method for managing access to a fast non-volatile storage device can include maintaining a first data structure which indicates a recency of access to each unit in a set of units in the fast non-volatile storage device, such as the SSD device and also maintaining a second data structure that indicates whether or not units or blocks in the slower storage device, such as the HDD device, have been referenced recently (such as the units or blocks that have been referenced only once recently).
- the second data structure can be a probabilistic hash table, which is space efficient, and reduces the required memory overhead. The probabilistic hash table is correct most of the time with respect to whether a unit or block in the slower storage device has been referenced recently, but is not guaranteed to always provide a correct answer.
- FIG. 1 shows an example of a data processing system, which may be employed with an embodiment of the present invention.
- FIG. 2 shows an example of a composite non-volatile memory according to one embodiment of the present invention.
- FIG. 3 shows an example of a data structure for an algorithm, which may be referred to as a clock algorithm.
- FIG. 4 shows an example of a data structure, such as a ghost table, which can be used with one or more methods described herein according to one embodiment of the present invention.
- FIG. 5 is a flowchart, which depicts a method according to at least one embodiment of the present invention.
- FIG. 6 is a flowchart, which depicts a method according to at least one embodiment of the present invention.
- FIG. 7 is a flowchart, which depicts a method according to one embodiment of the present invention.
- FIG. 8 shows an example of a Bloom filter data structure, which may be used with at least one embodiment of the present invention.
- FIG. 9 is a flowchart, which shows a method according to one embodiment of the present invention.
- FIG. 10 is a flowchart, which shows a method according to one embodiment of the preset invention.
- FIG. 1 shows an example of a computing system 10 , which is a form of a data processing system, which can be employed with one or more embodiments described herein.
- the system 10 can be a desktop computer system or a laptop computer system or a Smartphone, or some other electronic devices or consumer electronic devices.
- the system 10 can include one or microprocessors or other logic units 12 coupled to an optional cache 14 which in one embodiment can be SRAM, as known in the art.
- the one or more microprocessors 12 are coupled to the rest of the system through one or more buses 18 , which couple the one or more microprocessors 12 to main memory, which can be volatile RAM 16 .
- volatile RAM can be the conventional DRAM used in computer systems, where the DRAM is coupled through the bus to the rest of the components in the system 10 .
- the system 10 can also include one or more input/output controllers 20 , which couple one or more input/output devices 22 to the rest of the system through the one or more buses 18 .
- the system 10 also includes a non-volatile memory 19 which can be a composite disk, such as a combination of flash memory, which is a form of a solid state, drive and a conventional magnetic hard drive.
- FIG. 2 shows an example of a composite disk according to one embodiment.
- the non-volatile memory 19 includes a solid state drive 51 and a magnetic hard drive 52 which can be treated as a single logical volume, or block device by a file system and an operating system and are controlled by one or more controllers, such as controller 53 which includes a solid state drive controller, and controller 54 which includes a hard disk drive controller.
- controller 53 which includes a solid state drive controller
- controller 54 which includes a hard disk drive controller.
- the one or more controllers couple the composite drive shown in FIG. 2 to the rest of the components in system 10 through the bus 18 .
- flash memory is one form of a fast non-volatile storage device and that other fast storage devices can alternatively be used in conjunction with a slower storage device which can be a conventional magnetic hard drive or other non-volatile storage devices which are slower than the faster storage device.
- a reference to SSD or HDD will be construed to mean the faster and the slower on-volatile storage devices and will not be construed as being limited to, or specific to any storage device technology.
- FIG. 3 shows an example of a first data structure, which is used in conjunction with a clock algorithm according to one embodiment of the present invention.
- the clock algorithm in one embodiment can be similar to the prior clock algorithms, which are used, in the prior art.
- the clock algorithm can use the data structure 301 which can be a circular queue that includes a clock pointer 304 , which points to a particular location in the queue based upon the clock algorithm. Each location in the circular queue corresponds to a particular unit in the fast non-volatile memory device; such as the solid state drive implemented through a flash memory system.
- the first data structure is similar to a block allocation bit map maintained by a file system which indicates which blocks are free and which blocks are allocated (not free) on a hard drive.
- location 302 corresponds to unit zero on the SSD and the next unit to the right corresponds to unit one on the SSD
- location 303 corresponds to another unit on the SSD.
- Each location stores a value indicating the state of the corresponding storage unit within the SSD.
- two-bit value can be used, such that a value of zero can indicate that the one or more blocks or other components in a particular unit on the SSD is free while the value of one in a location can indicate that a particular unit on the SSD has not been referenced recently and a value of two can indicate that that unit in the SSD has been referenced recently.
- a value of three can indicate that a unit is pinned to the SSD, and cannot be demoted to the HDD.
- a three-bit value can be used which can track the specific number of accesses to a unit.
- a zero value can also indicate that the unit is free; a value of one can indicate that the unit has not been referenced recently, and the maximum value of seven can indicate that the unit is pinned.
- Other values can indicate the number of times a unit has been recently referenced, such as a value of six, which would indicate five recent references.
- the first data structure 301 can be managed as follows. When the algorithm needs to find a candidate to demote from the SSD to the HDD, it will use the clock pointer 304 . In one embodiment, the clock pointer 304 will sweep from one unit to the next unit in a clockwise direction, until it finds a unit with value of one, which means the unit has not been referenced recently. In one embodiment, the clock pointer 304 can sweep in a counter-clockwise direction. If the value in the unit is the maximum value, then the unit is pinned to the SSD and cannot be demoted to the HDD. If the value is larger than one, but is not the maximum value, the value is decremented by one, down to a minimum value of one, before the clock pointer moves to the next unit.
- FIG. 4 shows an example of a second data structure, which can be referred to as a ghost table, which is used to keep track of accesses of units on the slower non-volatile memory, such as the HDD, for accesses that exceed more than one recent access o more than a predetermined number of recent accesses.
- the second data structure can be the same size in terms of the number of locations in the data structure as the number of units in the SSD or it can be proportional to the size of the number of units in SSD.
- a signature value for a particular unit number in the HDD can be stored in each location of the second data structure.
- the unit in one embodiment, can be a logical block on the magnetic hard drive from the perspective of the file system.
- the second data structure 401 includes three locations 402 , 403 , and 404 as well as other locations, and each of those locations can store a signature of a unit number in the HDD.
- Location 404 shows an example of a signature value for the unit X in the HDD indicating that data in that unit on the HDD has been recently accessed (through either a read or write) at least once or at least a predetermined number of times.
- FIG. 5 shows an example of a method according to one embodiment of the present invention for utilizing the first data structure, such as the data structure 301 and the second data structure, such as the data structure 401 to control the migration of data between the fast storage device, such as the SSD and the slower storage device, such as the HDD.
- the method of FIG. 5 can begin in operation 501 in which the system receives a request for a read or write access to a non-volatile memory.
- a file system controls the composite disk and treats the composite disk as a single logical volume.
- the file system or another component in the data processing system then proceeds to determine how to allocate the data between the two or more portions of the composite disk using the method shown in FIG. 5 .
- the method proceeds to operation 503 in which it determines whether or not the requested data is in the faster storage device. If it is in the faster storage device then there is a hit in the SSD, in which case processing proceeds to operation 505 in which the count in the circular queue, such as the data structure 301 , for the unit found on the SSD, is incremented by one. This is done without moving the clock pointer 304 . In this manner, the clock algorithm, through the first data structure, keeps track of the number of accesses to the units in the SSD.
- operation 503 determines there is a miss in the SSD, then the system proceeds to operation 507 in which it determines whether or not the data is in a second data structure, such as the ghost table 401 shown in FIG. 4 , which is in the form of a probabilistic hash table. Finding data in the second data structure is illustrated in FIG. 7 , which is discussed below.
- a second data structure such as the ghost table 401 shown in FIG. 4 , which is in the form of a probabilistic hash table. Finding data in the second data structure is illustrated in FIG. 7 , which is discussed below.
- operation 507 determines that the unit is not already in the second data structure then it proceeds to operation 509 in which the unit number or a representation of the unit number is added to the second data structure which can be the ghost table 401 . Further information concerning operation 509 is provided in connection with FIG. 6 which will be described below. If in operation 507 it is determined that the unit containing the requested data is already in the second data structure, then processing proceeds from operation 507 to operation 511 in which it is determined whether or not the fast storage device is full. If it is not full, then operation 515 follows. Various conventional algorithms can be used to determine whether or not the SDD is not full and they do not need to rely upon the use of the clock algorithm or the first data structure 301 .
- operation 515 data in the unit of the HDD that is being accessed is migrated from the HDD to the SDD using techniques, which are known in the art. Further, the unit number for that unit of data that has been migrated or is to be migrated is removed from the second data structure, such as the ghost table 401 . If in operation 511 the system determines that the SSD is full, then operation 513 precedes operation 515 . It will be appreciated that the file system will still maintain conventional data structures indicating the locations of various data in response to the migration of the data in operation 515 . In operation 513 , the system creates space on the SSD using, in one embodiment, the clock algorithm.
- the clock algorithm uses the clock pointer 304 to move sequentially through the circular queue, starting with the current position of the clock pointer to a position which indicates a unit in the SSD that has not been recently referenced; in one embodiment, this is indicated by the value of one stored in a location in the circular queue.
- the clock pointer 304 is moved through the circular queue in a circular fashion, the value in each location is decremented by one.
- the clock pointer 304 moves through the queue decrementing the values in each location, eventually one of the units will receive a value indicating it is an available unit.
- the clock algorithm determines a next available unit location in the SSD, then the data in that unit of the SSD can be flushed to the HDD and the accessed data on the HDD can be migrated from the HDD to that location or unit in the SSD in operation 515 which can follow operation 513 .
- the removal of a unit number from the second data structure is further described in conjunction with FIG. 7 .
- FIG. 6 shows an example of a method for adding data into the second data structure, where X can represent a unit number in the HDD, such as one or more logical blocks on a hard drive.
- X can represent a unit number in the HDD, such as one or more logical blocks on a hard drive.
- FIGS. 6 and 7 allow for the creation of a probabilistic hash table, which can be the data structure 401 shown in FIG. 4 .
- the probabilistic hash table may not be always correct with respect to the number of accesses of a unit on the HDD due to the fact that hashes and signatures are used in creating values stored in the second data structure, and that hashes and signatures are also used to specify locations within that data structure. When hashes are used, it is possible for more than one input into the hash function to return the same hash value.
- the hash table may not be always correct with respect to the number of access a unit on the HDD has received, the data structure is correct most of the time, and is space efficient in that it can store a large volume of information relative to the amount of memory consumed.
- the method shown in FIG. 6 can be implemented in operation 509 of FIG. 5 .
- the system calculates a set of hash values for the unit number in the HDD that is being accessed by either a read request or a write request.
- the set of hash values can be derived from a set of different hash functions. For example, in one embodiment, three different hash functions, h1, h2, and h3 can be used, though any number of hash functions greater than or equal to one can be used.
- operation 601 calculates a signature of X which can be represented as S(X) where S represents a signature of the value of X.
- the signature can be derived from a cryptographic algorithm or from other algorithms, which attempt to create a relatively unique value for a given input but are not guaranteed to create a unique value for each possible value of X. This lack of global uniqueness contributes to the probabilistic nature of the hash table.
- the system proceeds to operation 603 in which it determines whether any of the locations specified by the hash values are empty in the second data structure. In other words, each of those locations specified by the hash values is examined in the ghost table, in one embodiment, to determine whether or not they are empty.
- operation 605 follows in which the signature, such as S(X) of the HDD's unit number is stored in one of those empty locations specified by one of the hash values.
- operation 603 determines that none of those locations are empty, then operation 607 is performed in which a random location in the second data structure is randomly selected in operation 607 and in operation 609 the signature is stored in the selected random location.
- the use of a random location can cause the overwriting of a prior signature stored in that location.
- FIG. 7 shows an example of a method for either finding or removing data from the data structure.
- operation 707 is not performed.
- the method shown in FIG. 7 for finding can be performed in operation 507 of FIG. 5 .
- operation 707 is performed, and this method is used as part of operation 515 shown in FIG. 5 .
- the method of FIG. 7 can begin in operation 701 in which a set of hash values is calculated for X. This set of hash values should correspond to the same set of hash values with the same set of hash functions that was previously used in operation 601 .
- a signature is calculated for the value of X, which is a similar signature to the signature, which was calculated in operation 601 .
- the system looks for the signature value in the locations of the ghost table, which are specified by the set of hash values calculated in operation 701 . If the signature is found in operation 705 , then the signature of the unit number is removed from the second data structure in operation 707 as shown in FIG. 7 .
- the size of the data structure can be doubled or halved based on the performance of the data structure and the amount of memory available.
- An alternative embodiment of the present invention can employ a Bloom filter rather than the probabilistic hash table, which can be implemented as a ghost table.
- An example of a Bloom filter is shown in FIG. 8 .
- a Bloom filter is a probabilistic data structure that can be used to test whether a unit on the second storage device has probably been recently accessed.
- the Bloom filter is probabilistic because it is possible that a false positive result is returned, meaning a unit is determined to be within the data structure when it actually is not. However, false negatives are not possible, so a query of the second data structure will return a result that the unit probably has been recently accessed, or that the unit definitely has not been recently accessed.
- the Bloom filter can have multiple locations corresponding to each unit of the SSD or a proportional number of the units of the SSD.
- Each location stores either a one or a zero in one embodiment, which indicates the status of the number of accesses of a particular unit on the HDD.
- Hash values of the unit numbers of the HDD are used as an address to access a particular location in the Bloom filter.
- the Bloom filter 801 includes locations 802 , 803 , and 804 .
- Location 803 is specified by a hash function h1 of X, which specifies that location. The value one has been set in location 803 and has also been set in two other locations specified by two other addresses h2 of X and h3 of X.
- the Bloom filter shown in FIG. 8 can be used with the method of FIG.
- an additional Bloom filter may be added in a circular queue.
- FIG. 9 shows an example of a method for adding a unit in the HDD to the Bloom filter.
- the operations shown in FIG. 9 are performed in operation 509 when the Bloom filter is used in place of the ghost table.
- a circular queue of Bloom filters can be used such that there are multiple Bloom filters maintained in the circular queue where the newest Bloom filter is used to store values and the older Bloom filters circulate through the circular queue as will be apparent from FIG. 9 .
- operation 901 determines whether the newest Bloom filter is full.
- a counter is used to track the number of times an addition has been made to the Bloom filter, and the filter is considered full after it exceeds some predetermined threshold.
- operation 905 follows in which data representing a currently accessed unit on the HDD is added to the newest Bloom filter by setting each location specified in a set of hash values to a predetermined value, such as one.
- a set of hash values is calculated as in operation 1001 and each of those hash values specifies a particular location or address within the Bloom filter and a value of one is written into each of those addresses or locations specified in the set of hash values.
- FIG. 10 depicts a method for finding whether a particular unit number in the HDD is in the second data structure, which in this case is the Bloom filter.
- FIG. 10 can be performed as part of operation 507 when the method of FIG. 5 uses a Bloom filter instead of a ghost table.
- the system calculates a set of hash values for the unit number in the HDD. In one embodiment, three different hash functions can be used to calculate three hash values.
- the system checks whether a bit, in each location specified by the set of hash values, has been set to a predetermined value, such as the value of one in at least one of the Bloom filters in the queue.
- operation 1005 it is determined whether all the bits have been set to one in each of the locations specified by the hash values in the set of hash values. If at least one of the locations in each Bloom filter in the queue has not been set, then the system concludes that the unit has not been found and proceeds to operation 1007 , which causes operation 509 to follow in FIG. 5 . If on the other hand the system determines all bits have been set in the proper locations determined by the set of hash values, then processing proceeds to operation 1009 which causes operation 511 to following in FIG. 5 .
- embodiments of the invention can increase or decrease the size of the second data structure as needed. As Bloom filters in the circular queue fill, additional Bloom filters can be added to the circular queue. After the size of the circular queue of Bloom filters exceeds a defined value, the oldest Bloom filter can be removed from the list.
Abstract
In one embodiment, a method for managing a composite storage device made up of fast non-volatile storage, such as a solid state device, and slower non-volatile storage, such as a traditional magnetic hard drive, can include maintaining a first data structure, which stores instances of recent access to each unit in a set of units in the fast non-volatile storage device, such as the SSD device and also maintaining a second data structure that indicates whether or not units in the slower storage device, such as the HDD, have been accessed at least a predetermined number of times. In one embodiment, the second data structure can be a probabilistic hash table, which has a low required memory overhead but is not guaranteed to always provide a correct answer with respect to whether a unit or block in the slower storage device has been referenced recently.
Description
- The present application claims the benefit of provisional application Ser. No. 61/599,927, filed on Feb. 16, 2012, and this provisional application is hereby incorporated by reference. The present application is also related to co-pending application Ser. No. 61/599,930, which was also filed on Feb. 16, 2012, and which is hereby incorporated by reference.
- The present invention relates to methods for managing storage of data in a composite non-volatile memory that is a composite of a slow memory device and a fast memory device. In a composite disk system, a large, slow, and inexpensive magnetic hard drive can be combined with a small, fast but expensive storage device, such as a solid state drive to forma logical volume. This can provide the advantage of fast access through the solid state drive (SSD) while providing the large capacity of the magnetic hard disk drive (HDD). Prior techniques for managing such a composite disk have used algorithms such as a least recently used (LRU) algorithm or a CLOCK algorithm or the ClockPro algorithm described by Song Jiang. These prior techniques can improve the allocation of the data between the fast and the slow portions of the composite disk, but they tend to not be space efficient, in that they require large amounts of main memory, such as large amounts of DRAM, in order to implement the data structures used in these techniques for allocating data between the two parts of the composite disk. Hence there is a need for an improved, space efficient technique, which does not require as much memory to store the data structures used in allocating or migrating data between the two or more components of the composite disk.
- In one embodiment, a method for managing access to a fast non-volatile storage device, such as a solid state device, and a slower non-volatile storage device, such as a magnetic hard drive, can include maintaining a first data structure which indicates a recency of access to each unit in a set of units in the fast non-volatile storage device, such as the SSD device and also maintaining a second data structure that indicates whether or not units or blocks in the slower storage device, such as the HDD device, have been referenced recently (such as the units or blocks that have been referenced only once recently). In one embodiment, the second data structure can be a probabilistic hash table, which is space efficient, and reduces the required memory overhead. The probabilistic hash table is correct most of the time with respect to whether a unit or block in the slower storage device has been referenced recently, but is not guaranteed to always provide a correct answer.
- Other features of the present invention will be apparent from the accompanying drawings and from the detailed description, which follows.
- The above summary does not include an exhaustive list of all aspects of the present invention. It is contemplated that the invention includes all systems and methods that can be practiced from all suitable combinations of the various aspects summarized above, and also those disclosed in the Detailed Description below.
- The present invention is illustrated by way of example, and not limitation, in the figures of the accompanying drawings in which like references indicate similar elements.
-
FIG. 1 shows an example of a data processing system, which may be employed with an embodiment of the present invention. -
FIG. 2 shows an example of a composite non-volatile memory according to one embodiment of the present invention. -
FIG. 3 shows an example of a data structure for an algorithm, which may be referred to as a clock algorithm. -
FIG. 4 shows an example of a data structure, such as a ghost table, which can be used with one or more methods described herein according to one embodiment of the present invention. -
FIG. 5 is a flowchart, which depicts a method according to at least one embodiment of the present invention. -
FIG. 6 is a flowchart, which depicts a method according to at least one embodiment of the present invention. -
FIG. 7 is a flowchart, which depicts a method according to one embodiment of the present invention. -
FIG. 8 shows an example of a Bloom filter data structure, which may be used with at least one embodiment of the present invention. -
FIG. 9 is a flowchart, which shows a method according to one embodiment of the present invention. -
FIG. 10 is a flowchart, which shows a method according to one embodiment of the preset invention. - Approaches to improving the management of a composite, non-volatile data storage device are described. Various embodiments and aspects of the invention will be described with reference to details discussed below, and the accompanying drawings will illustrate the various embodiments. The following description and drawings are illustrative of the invention and are not to be construed as limiting the invention. Numerous specific details are described to provide a thorough understanding of various embodiments of the present invention. However, in certain instances, well-known or conventional details are not described in order to provide a concise discussion of embodiments of the present invention.
- Reference in the specification to “one embodiment” or “an embodiment” means that a particular feature, structure, or characteristic described in conjunction with the embodiment can be included in at least one embodiment of the invention. The appearances of the phrase “in one embodiment” in various places in the specification do not necessarily all refer to the same embodiment. The processes depicted in the figures that follow are performed by processing logic that comprises hardware (e.g. circuitry, dedicated logic, etc.), software (as instructions on a non-transitory machine-readable storage medium), or a combination of both. Although the processes are described below in terms of some sequential operations, it should be appreciated that some of the operations described may be performed in a different order. Moreover, some operations may be performed in parallel rather than sequentially.
-
FIG. 1 shows an example of acomputing system 10, which is a form of a data processing system, which can be employed with one or more embodiments described herein. Thesystem 10 can be a desktop computer system or a laptop computer system or a Smartphone, or some other electronic devices or consumer electronic devices. Thesystem 10 can include one or microprocessors orother logic units 12 coupled to anoptional cache 14 which in one embodiment can be SRAM, as known in the art. The one ormore microprocessors 12 are coupled to the rest of the system through one ormore buses 18, which couple the one ormore microprocessors 12 to main memory, which can bevolatile RAM 16. In one embodiment, volatile RAM can be the conventional DRAM used in computer systems, where the DRAM is coupled through the bus to the rest of the components in thesystem 10. Thesystem 10 can also include one or more input/output controllers 20, which couple one or more input/output devices 22 to the rest of the system through the one ormore buses 18. Thesystem 10 also includes anon-volatile memory 19 which can be a composite disk, such as a combination of flash memory, which is a form of a solid state, drive and a conventional magnetic hard drive. -
FIG. 2 shows an example of a composite disk according to one embodiment. Thenon-volatile memory 19 includes asolid state drive 51 and a magnetichard drive 52 which can be treated as a single logical volume, or block device by a file system and an operating system and are controlled by one or more controllers, such ascontroller 53 which includes a solid state drive controller, andcontroller 54 which includes a hard disk drive controller. The one or more controllers couple the composite drive shown inFIG. 2 to the rest of the components insystem 10 through thebus 18. It will be appreciated that flash memory is one form of a fast non-volatile storage device and that other fast storage devices can alternatively be used in conjunction with a slower storage device which can be a conventional magnetic hard drive or other non-volatile storage devices which are slower than the faster storage device. It will be understood that in this description a reference to SSD or HDD will be construed to mean the faster and the slower on-volatile storage devices and will not be construed as being limited to, or specific to any storage device technology. -
FIG. 3 shows an example of a first data structure, which is used in conjunction with a clock algorithm according to one embodiment of the present invention. The clock algorithm in one embodiment can be similar to the prior clock algorithms, which are used, in the prior art. The clock algorithm can use thedata structure 301 which can be a circular queue that includes aclock pointer 304, which points to a particular location in the queue based upon the clock algorithm. Each location in the circular queue corresponds to a particular unit in the fast non-volatile memory device; such as the solid state drive implemented through a flash memory system. In a sense, the first data structure is similar to a block allocation bit map maintained by a file system which indicates which blocks are free and which blocks are allocated (not free) on a hard drive. - For example,
location 302 corresponds to unit zero on the SSD and the next unit to the right corresponds to unit one on the SSD, andlocation 303 corresponds to another unit on the SSD. Each location stores a value indicating the state of the corresponding storage unit within the SSD. In one embodiment two-bit value can be used, such that a value of zero can indicate that the one or more blocks or other components in a particular unit on the SSD is free while the value of one in a location can indicate that a particular unit on the SSD has not been referenced recently and a value of two can indicate that that unit in the SSD has been referenced recently. A value of three can indicate that a unit is pinned to the SSD, and cannot be demoted to the HDD. Alternatively, in one embodiment, a three-bit value can be used which can track the specific number of accesses to a unit. In this embodiment, a zero value can also indicate that the unit is free; a value of one can indicate that the unit has not been referenced recently, and the maximum value of seven can indicate that the unit is pinned. Other values can indicate the number of times a unit has been recently referenced, such as a value of six, which would indicate five recent references. - In one embodiment, the
first data structure 301 can be managed as follows. When the algorithm needs to find a candidate to demote from the SSD to the HDD, it will use theclock pointer 304. In one embodiment, theclock pointer 304 will sweep from one unit to the next unit in a clockwise direction, until it finds a unit with value of one, which means the unit has not been referenced recently. In one embodiment, theclock pointer 304 can sweep in a counter-clockwise direction. If the value in the unit is the maximum value, then the unit is pinned to the SSD and cannot be demoted to the HDD. If the value is larger than one, but is not the maximum value, the value is decremented by one, down to a minimum value of one, before the clock pointer moves to the next unit. When a particular unit in the SSD is accessed, a counter in the location corresponding to that unit on the SSD will be incremented. Using this method, frequently accessed units on the SSD will attain increasingly higher counts in the unit of the data structure corresponding to that unit on the SSD, up to a preset count limit. However, as theclock pointer 304 sweeps from unit to unit each time a candidate for demotion is required, a count in each sequential unit (e.g. 302, 303) will decrement each time theclock pointer 304 passes that unit, down to a minimum value of one, which indicates that the unit has not been recently accessed. Further details in connection with the use of the clock algorithm relative to the second data structure, which will be next described, are provided in conjunction withFIGS. 5 , 6, and 7. -
FIG. 4 shows an example of a second data structure, which can be referred to as a ghost table, which is used to keep track of accesses of units on the slower non-volatile memory, such as the HDD, for accesses that exceed more than one recent access o more than a predetermined number of recent accesses. In one embodiment, the second data structure can be the same size in terms of the number of locations in the data structure as the number of units in the SSD or it can be proportional to the size of the number of units in SSD. In one embodiment, a signature value for a particular unit number in the HDD can be stored in each location of the second data structure. The unit, in one embodiment, can be a logical block on the magnetic hard drive from the perspective of the file system. Thesecond data structure 401 includes threelocations Location 404 shows an example of a signature value for the unit X in the HDD indicating that data in that unit on the HDD has been recently accessed (through either a read or write) at least once or at least a predetermined number of times. -
FIG. 5 shows an example of a method according to one embodiment of the present invention for utilizing the first data structure, such as thedata structure 301 and the second data structure, such as thedata structure 401 to control the migration of data between the fast storage device, such as the SSD and the slower storage device, such as the HDD. The method ofFIG. 5 can begin inoperation 501 in which the system receives a request for a read or write access to a non-volatile memory. In one embodiment, a file system controls the composite disk and treats the composite disk as a single logical volume. The file system or another component in the data processing system then proceeds to determine how to allocate the data between the two or more portions of the composite disk using the method shown inFIG. 5 . In response to the receipt of the request for a read or write access, the method proceeds tooperation 503 in which it determines whether or not the requested data is in the faster storage device. If it is in the faster storage device then there is a hit in the SSD, in which case processing proceeds tooperation 505 in which the count in the circular queue, such as thedata structure 301, for the unit found on the SSD, is incremented by one. This is done without moving theclock pointer 304. In this manner, the clock algorithm, through the first data structure, keeps track of the number of accesses to the units in the SSD. Ifoperation 503 determines there is a miss in the SSD, then the system proceeds tooperation 507 in which it determines whether or not the data is in a second data structure, such as the ghost table 401 shown inFIG. 4 , which is in the form of a probabilistic hash table. Finding data in the second data structure is illustrated inFIG. 7 , which is discussed below. - If
operation 507 determines that the unit is not already in the second data structure then it proceeds tooperation 509 in which the unit number or a representation of the unit number is added to the second data structure which can be the ghost table 401. Furtherinformation concerning operation 509 is provided in connection withFIG. 6 which will be described below. If inoperation 507 it is determined that the unit containing the requested data is already in the second data structure, then processing proceeds fromoperation 507 tooperation 511 in which it is determined whether or not the fast storage device is full. If it is not full, thenoperation 515 follows. Various conventional algorithms can be used to determine whether or not the SDD is not full and they do not need to rely upon the use of the clock algorithm or thefirst data structure 301. - In
operation 515, data in the unit of the HDD that is being accessed is migrated from the HDD to the SDD using techniques, which are known in the art. Further, the unit number for that unit of data that has been migrated or is to be migrated is removed from the second data structure, such as the ghost table 401. If inoperation 511 the system determines that the SSD is full, thenoperation 513 precedesoperation 515. It will be appreciated that the file system will still maintain conventional data structures indicating the locations of various data in response to the migration of the data inoperation 515. Inoperation 513, the system creates space on the SSD using, in one embodiment, the clock algorithm. In this case, the clock algorithm uses theclock pointer 304 to move sequentially through the circular queue, starting with the current position of the clock pointer to a position which indicates a unit in the SSD that has not been recently referenced; in one embodiment, this is indicated by the value of one stored in a location in the circular queue. As theclock pointer 304 is moved through the circular queue in a circular fashion, the value in each location is decremented by one. As theclock pointer 304 moves through the queue decrementing the values in each location, eventually one of the units will receive a value indicating it is an available unit. Once the clock algorithm determines a next available unit location in the SSD, then the data in that unit of the SSD can be flushed to the HDD and the accessed data on the HDD can be migrated from the HDD to that location or unit in the SSD inoperation 515 which can followoperation 513. The removal of a unit number from the second data structure is further described in conjunction withFIG. 7 . -
FIG. 6 shows an example of a method for adding data into the second data structure, where X can represent a unit number in the HDD, such as one or more logical blocks on a hard drive. It can be appreciated that the methods ofFIGS. 6 and 7 allow for the creation of a probabilistic hash table, which can be thedata structure 401 shown inFIG. 4 . The probabilistic hash table may not be always correct with respect to the number of accesses of a unit on the HDD due to the fact that hashes and signatures are used in creating values stored in the second data structure, and that hashes and signatures are also used to specify locations within that data structure. When hashes are used, it is possible for more than one input into the hash function to return the same hash value. This means that a unit sharing the same signature as a different unit may be promoted to the SSD instead of the proper unit. However, the likelihood of that occurrence is small. Accordingly, though the hash table may not be always correct with respect to the number of access a unit on the HDD has received, the data structure is correct most of the time, and is space efficient in that it can store a large volume of information relative to the amount of memory consumed. - The method shown in
FIG. 6 can be implemented inoperation 509 ofFIG. 5 . Inoperation 601, the system calculates a set of hash values for the unit number in the HDD that is being accessed by either a read request or a write request. The set of hash values can be derived from a set of different hash functions. For example, in one embodiment, three different hash functions, h1, h2, and h3 can be used, though any number of hash functions greater than or equal to one can be used. In addition,operation 601 calculates a signature of X which can be represented as S(X) where S represents a signature of the value of X. The signature can be derived from a cryptographic algorithm or from other algorithms, which attempt to create a relatively unique value for a given input but are not guaranteed to create a unique value for each possible value of X. This lack of global uniqueness contributes to the probabilistic nature of the hash table. After the values are calculated inoperation 601, the system proceeds tooperation 603 in which it determines whether any of the locations specified by the hash values are empty in the second data structure. In other words, each of those locations specified by the hash values is examined in the ghost table, in one embodiment, to determine whether or not they are empty. If any one of them is empty, thenoperation 605 follows in which the signature, such as S(X) of the HDD's unit number is stored in one of those empty locations specified by one of the hash values. On the other hand, ifoperation 603 determines that none of those locations are empty, thenoperation 607 is performed in which a random location in the second data structure is randomly selected inoperation 607 and inoperation 609 the signature is stored in the selected random location. The use of a random location can cause the overwriting of a prior signature stored in that location. -
FIG. 7 shows an example of a method for either finding or removing data from the data structure. When the method ofFIG. 7 is used for finding,operation 707 is not performed. The method shown inFIG. 7 for finding can be performed inoperation 507 ofFIG. 5 . When the method shown inFIG. 7 is used for removing data from the ghost table, thenoperation 707 is performed, and this method is used as part ofoperation 515 shown inFIG. 5 . The method ofFIG. 7 can begin inoperation 701 in which a set of hash values is calculated for X. This set of hash values should correspond to the same set of hash values with the same set of hash functions that was previously used inoperation 601. Similarly, a signature is calculated for the value of X, which is a similar signature to the signature, which was calculated inoperation 601. Then inoperation 703, the system looks for the signature value in the locations of the ghost table, which are specified by the set of hash values calculated inoperation 701. If the signature is found inoperation 705, then the signature of the unit number is removed from the second data structure inoperation 707 as shown inFIG. 7 . In one embodiment, the size of the data structure can be doubled or halved based on the performance of the data structure and the amount of memory available. - An alternative embodiment of the present invention can employ a Bloom filter rather than the probabilistic hash table, which can be implemented as a ghost table. An example of a Bloom filter is shown in
FIG. 8 . A Bloom filter is a probabilistic data structure that can be used to test whether a unit on the second storage device has probably been recently accessed. The Bloom filter is probabilistic because it is possible that a false positive result is returned, meaning a unit is determined to be within the data structure when it actually is not. However, false negatives are not possible, so a query of the second data structure will return a result that the unit probably has been recently accessed, or that the unit definitely has not been recently accessed. The Bloom filter can have multiple locations corresponding to each unit of the SSD or a proportional number of the units of the SSD. Each location stores either a one or a zero in one embodiment, which indicates the status of the number of accesses of a particular unit on the HDD. Hash values of the unit numbers of the HDD are used as an address to access a particular location in the Bloom filter. As shown inFIG. 8 , theBloom filter 801 includeslocations Location 803 is specified by a hash function h1 of X, which specifies that location. The value one has been set inlocation 803 and has also been set in two other locations specified by two other addresses h2 of X and h3 of X. The Bloom filter shown inFIG. 8 can be used with the method ofFIG. 5 by replacing the ghost table with the Bloom filter inoperation 507 and by replacing the ghost table with the Bloom filter inoperation 509. However, the unit number, inoperation 515 is not removed from the Bloom filter when a Bloom filter is used in place of the ghost table because it is not possible to remove a unit from a Bloom filter and ensure that the Bloom filter will not produce false negative results. Accordingly, in one embodiment, as a Bloom filter in the second data structure fills, an additional Bloom filter may be added in a circular queue. -
FIG. 9 shows an example of a method for adding a unit in the HDD to the Bloom filter. The operations shown inFIG. 9 are performed inoperation 509 when the Bloom filter is used in place of the ghost table. In one embodiment, a circular queue of Bloom filters can be used such that there are multiple Bloom filters maintained in the circular queue where the newest Bloom filter is used to store values and the older Bloom filters circulate through the circular queue as will be apparent fromFIG. 9 . Whenoperation 509 begins, in the case of a Bloom filter implementation ofFIG. 5 ,operation 901 determines whether the newest Bloom filter is full. In one embodiment, a counter is used to track the number of times an addition has been made to the Bloom filter, and the filter is considered full after it exceeds some predetermined threshold. If the Bloom filter it is not full,operation 905 follows in which data representing a currently accessed unit on the HDD is added to the newest Bloom filter by setting each location specified in a set of hash values to a predetermined value, such as one. In one embodiment, a set of hash values is calculated as inoperation 1001 and each of those hash values specifies a particular location or address within the Bloom filter and a value of one is written into each of those addresses or locations specified in the set of hash values. -
FIG. 10 depicts a method for finding whether a particular unit number in the HDD is in the second data structure, which in this case is the Bloom filter.FIG. 10 can be performed as part ofoperation 507 when the method ofFIG. 5 uses a Bloom filter instead of a ghost table. Inoperation 1001, the system calculates a set of hash values for the unit number in the HDD. In one embodiment, three different hash functions can be used to calculate three hash values. Then, inoperation 1003, the system checks whether a bit, in each location specified by the set of hash values, has been set to a predetermined value, such as the value of one in at least one of the Bloom filters in the queue. Inoperation 1005, it is determined whether all the bits have been set to one in each of the locations specified by the hash values in the set of hash values. If at least one of the locations in each Bloom filter in the queue has not been set, then the system concludes that the unit has not been found and proceeds tooperation 1007, which causesoperation 509 to follow inFIG. 5 . If on the other hand the system determines all bits have been set in the proper locations determined by the set of hash values, then processing proceeds tooperation 1009 which causesoperation 511 to following inFIG. 5 . As with the Ghost Table inFIG. 4 , embodiments of the invention can increase or decrease the size of the second data structure as needed. As Bloom filters in the circular queue fill, additional Bloom filters can be added to the circular queue. After the size of the circular queue of Bloom filters exceeds a defined value, the oldest Bloom filter can be removed from the list. - In the foregoing specification, the invention has been described with reference to specific embodiments thereof. It will, however, be evident that various modifications and changes can be made thereto without departing from the broader spirit and scope of the invention. The specification and drawings are, accordingly, to be regarded in an illustrative rather than a restrictive sense.
Claims (23)
1. A method for managing access to a multi-device composite data storage system, the method comprising:
managing a first data structure indicating a recency of access to each unit in a set of units on a first data storage device; and
managing a second data structure that probabilistically indicates whether a unit on a second data storage device has received at least one recent references, wherein the second data structure is a probabilistic hash table, or a counting Bloom filter, or another space efficient probabilistic data structure.
2. The method of claim 1 wherein managing the first data structure comprises:
receiving a request to access a block of the composite data storage system;
accessing the block from the first data storage device; and
updating the first data structure to indicate that the block was recently accessed from the first data storage device.
3. The method of claim 1 wherein managing the second data structure comprises:
receiving a request to access a block of the data storage system;
adding, to the second data structure, data representing a unit identifier on the second data storage device containing the block of the data storage system; and
migrating the unit to the first data storage device.
4. The method of claim 3 wherein adding data representing a unit identifier on the second data storage device to the second data structure comprises:
calculating a hash of the unit identifier of the data storage system;
calculating a signature for the unit; and
storing the signature for the unit into an index on the second data structure, wherein the index is defined by the hash of the unit.
5. The method of claim 3 wherein grating the unit on the second data storage device from the second data storage device to the first data storage device comprises:
searching the second data structure for the signature of a unit on the second data storage device, wherein the unit contains the block of the data storage system. moving the unit from the second storage device to the first storage device; and
removing, from the second data structure, the signature of the unit.
6. The method of claim 5 wherein moving the unit from the second storage device to the first storage device comprises moving multiple data blocks as a single unit.
7. A system for managing access to a composite data storage device, the system comprising:
a first data storage device, to store data in a set of units;
a first data structure, to indicate a recency of access to each unit in the set of units on the first data storage device;
a second data storage device, coupled to the first data storage device, to store data in a set of units; and
a second data structure, to probabilistically indicates whether a unit in the set of units on the second data storage device has received at least one recent access, wherein the second data structure is a probabilistic hash table.
8. The system of claim 7 wherein the first data storage device is a solid-state drive.
9. The system of claim 7 wherein the second data storage device is a magnetic hard disk drive.
10. The system of claim 7 wherein the second data structure contains an element corresponding to each of the units on the first storage device.
11. The system of claim 7 wherein the second data structure contains a number of elements corresponding to a proportion of the units on the first storage device.
12. The system of claim 7 wherein a signature for a unit on the second storage device is stored in the second data structure.
13. The system of claim 7 wherein the first data structure is a circular queue maintained by use of a clock algorithm.
14. The system of claim 13 wherein the first data structure contains an element for each unit on the first data storage device.
15. The system of claim 14 wherein an element of the first data structure indicates that a unit on the first data storage device is free.
16. The system of claim 15 wherein the first data structure stores a value to indicate a count of recent accesses to a particular unit on the first data storage device.
17. A non-transitory machine-readable storage medium having instructions stored therein, which when executed by a machine, cause a machine to perform operations for managing access to a multi-device composite data storage system, the operations comprising:
initializing a first data structure, the first data structure to indicate if a unit in a set of units on a first data storage device is accessed, wherein the first data structure is managed via a clock algorithm;
initializing a second data structure, the second data structure to probabilistically indicate that a unit on a second data storage device has received at least one recent access, wherein the second data structure is a probabilistic hash table;
receiving a request to access a logical block of the composite data storage system;
accessing the logical block from a unit on the first storage device if the logical block is contained on the first data storage device, and updating the first data structure to indicate that a block of the composite data storage system as recently accessed from a unit on the first data storage device;
searching the second data structure for the logical block if the logical block is not found in a unit on the first data storage device;
adding the logical block to the second data structure if the logical block is not found in the second data structure;
migrating a unit from the second data storage device to the first data storage device if the logical block is found in the second data structure; and
removing the logical block from the second data structure.
18. The machine-readable storage medium of claim 17 further comprising:
halving the size of the second data structure after a number of signatures are not found within a period of time; and
doubling the size of the second data structure after a number of signatures are found within a period of time.
19. The machine-readable storage medium of claim 18 , further comprising:
calculating a set of hash values for an address of a requested unit on the second data storage device;
calculating a signature for the address of the requested unit on the second data storage device; and
storing the signature of the address of the requested unit in the second data structure by using a hash value from the calculated set of hash values as an index.
20. The machine-readable storage medium of claim 19 , wherein calculating a set of hash values uses a plurality of hash functions.
21. The machine-readable storage medium of claim 9 , wherein storing the signature of the address of the requested unit in the second data structure comprises:
searching, for each hash function, an index of the second data structure addressed by the hash value calculated by that hash function.;
storing the signature of the address of the requested unit in an empty location indexed by hash the value; and
storing the signature of the address of the requested unit in a random location in the second data structure if no hash value in the set of hash values indexes an empty location.
23. A non-transitory machine-readable storage medium having instructions, which when executed, cause a data processing system to perform a method as in claim 1 .
24. A non-transitory machine-readable storage medium having instructions, which when executed, cause a data processing system to perform a method as in claim 4 .
Priority Applications (8)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US13/605,916 US20130219116A1 (en) | 2012-02-16 | 2012-09-06 | Data migration for composite non-volatile storage device |
EP13706810.2A EP2798501B1 (en) | 2012-02-16 | 2013-02-07 | Data migration for composite non-volatile storage device |
JP2014557696A JP5943095B2 (en) | 2012-02-16 | 2013-02-07 | Data migration for composite non-volatile storage |
CN201380009551.8A CN104115134B (en) | 2012-02-16 | 2013-02-07 | For managing the method and system to be conducted interviews to complex data storage device |
AU2013221868A AU2013221868B2 (en) | 2012-02-16 | 2013-02-07 | Data migration for composite non-volatile storage device |
PCT/US2013/025224 WO2013122818A1 (en) | 2012-02-16 | 2013-02-07 | Data migration for composite non-volatile storage device |
KR1020147022828A KR101599177B1 (en) | 2012-02-16 | 2013-02-07 | Data migration for composite non-volatile storage device |
TW102105368A TW201346932A (en) | 2012-02-16 | 2013-02-08 | Data migration for composite non-volatile storage device |
Applications Claiming Priority (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US201261599930P | 2012-02-16 | 2012-02-16 | |
US201261599927P | 2012-02-16 | 2012-02-16 | |
US13/605,916 US20130219116A1 (en) | 2012-02-16 | 2012-09-06 | Data migration for composite non-volatile storage device |
Publications (1)
Publication Number | Publication Date |
---|---|
US20130219116A1 true US20130219116A1 (en) | 2013-08-22 |
Family
ID=48983237
Family Applications (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US13/605,921 Active US9710397B2 (en) | 2012-02-16 | 2012-09-06 | Data migration for composite non-volatile storage device |
US13/605,916 Abandoned US20130219116A1 (en) | 2012-02-16 | 2012-09-06 | Data migration for composite non-volatile storage device |
Family Applications Before (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US13/605,921 Active US9710397B2 (en) | 2012-02-16 | 2012-09-06 | Data migration for composite non-volatile storage device |
Country Status (8)
Country | Link |
---|---|
US (2) | US9710397B2 (en) |
EP (2) | EP2798501B1 (en) |
JP (2) | JP5943095B2 (en) |
KR (2) | KR101599177B1 (en) |
CN (2) | CN104115134B (en) |
AU (2) | AU2013221868B2 (en) |
TW (2) | TWI524348B (en) |
WO (2) | WO2013122818A1 (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2015073450A1 (en) * | 2013-11-12 | 2015-05-21 | Wesie Andrew Michael | Improved control flow integrity system and method |
US20160313932A1 (en) * | 2015-04-24 | 2016-10-27 | Kabushiki Kaisha Toshiba | Data storage system and device |
US10073851B2 (en) | 2013-01-08 | 2018-09-11 | Apple Inc. | Fast new file creation cache |
US10228860B2 (en) * | 2016-11-14 | 2019-03-12 | Open Drives LLC | Storage optimization based I/O pattern modeling |
CN109564532A (en) * | 2016-08-05 | 2019-04-02 | 美光科技公司 | Prediction corrective action in memory based on probabilistic data structure |
US10942844B2 (en) | 2016-06-10 | 2021-03-09 | Apple Inc. | Reserved memory in memory management system |
US11789614B2 (en) | 2018-01-19 | 2023-10-17 | Micron Technology, Inc. | Performance allocation among users for accessing non-volatile memory devices |
Families Citing this family (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8700578B1 (en) * | 2012-09-27 | 2014-04-15 | Emc Corporation | System and method for determining physical storage space of a deduplicated storage system |
WO2014132136A2 (en) * | 2013-02-27 | 2014-09-04 | Marvell World Trade Ltd. | Efficient longest prefix matching techniques for network devices |
CN105701018B (en) * | 2014-11-24 | 2019-01-11 | 阿里巴巴集团控股有限公司 | A kind of data processing method and equipment for stream calculation |
US10263784B2 (en) | 2015-09-09 | 2019-04-16 | Amazon Technologies, Inc. | Signature verification for data set components using probabilistic data structures |
WO2017044867A1 (en) * | 2015-09-09 | 2017-03-16 | Amazon Technologies, Inc. | Deletion of elements from a bloom filter |
US10262160B2 (en) | 2015-09-09 | 2019-04-16 | Amazon Technologies, Inc. | Verification of data set components using digitally signed probabilistic data structures |
KR101675694B1 (en) * | 2015-09-11 | 2016-11-23 | 성균관대학교산학협력단 | Block replacement method of ssd based on block popularity |
KR101704936B1 (en) * | 2015-12-07 | 2017-02-09 | 성균관대학교산학협력단 | Block replacement method based on recency, and thereof hybrid strorage system |
US10019456B2 (en) * | 2016-06-29 | 2018-07-10 | Microsoft Technology Licensing, Llc | Recovering free space in nonvolatile storage with a computer storage system supporting shared objects |
US11010300B2 (en) | 2017-05-04 | 2021-05-18 | Hewlett Packard Enterprise Development Lp | Optimized record lookups |
US10811096B2 (en) * | 2017-05-19 | 2020-10-20 | Aspiring Sky Co. Limited | Multi-block non-volatile memories with single unified interface |
CN107678892B (en) * | 2017-11-07 | 2021-05-04 | 黄淮学院 | Continuous data protection method based on jump recovery chain |
US11243703B2 (en) | 2018-04-27 | 2022-02-08 | Hewlett Packard Enterprise Development Lp | Expandable index with pages to store object records |
US10628063B2 (en) | 2018-08-24 | 2020-04-21 | Advanced Micro Devices, Inc. | Implementing scalable memory allocation using identifiers that return a succinct pointer representation |
Citations (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6266771B1 (en) * | 1997-02-10 | 2001-07-24 | The Regents Of The University Of California | Probabilistic signature scheme |
US20030005223A1 (en) * | 2001-06-27 | 2003-01-02 | Coulson Richard L. | System boot time reduction method |
US20030056058A1 (en) * | 2001-09-17 | 2003-03-20 | Alistair Veitch | Logical volume data migration |
US20040044861A1 (en) * | 2002-08-30 | 2004-03-04 | Cavallo Joseph S. | Cache management |
US20070168627A1 (en) * | 2006-01-13 | 2007-07-19 | Samsung Electronics Co., Ltd. | Method and apparatus for reducing page replacement time in system using demand paging technique |
US20080021853A1 (en) * | 2006-07-20 | 2008-01-24 | International Business Machines Corporation | Using multiple data structures to manage data in cache |
US20100082936A1 (en) * | 2008-10-01 | 2010-04-01 | Hobbet Jeffrey R | Cache Mapping for Solid State Drives |
US20100191899A1 (en) * | 2009-01-28 | 2010-07-29 | Takehiko Kurashige | Information Processing Apparatus and Data Storage Apparatus |
US20100332730A1 (en) * | 2009-06-30 | 2010-12-30 | Royer Jr Robert J | Method and system for managing a nand flash memory |
US20100332725A1 (en) * | 2009-06-24 | 2010-12-30 | Post Samual D | Pinning content in nonvolatile memory |
US20110138112A1 (en) * | 2009-12-04 | 2011-06-09 | Hsing-Yi Chiang | Virtualization of Storage Devices |
US20110145489A1 (en) * | 2004-04-05 | 2011-06-16 | Super Talent Electronics, Inc. | Hybrid storage device |
US20110179219A1 (en) * | 2004-04-05 | 2011-07-21 | Super Talent Electronics, Inc. | Hybrid storage device |
US8010747B2 (en) * | 2005-11-30 | 2011-08-30 | Red Hat, Inc. | Method for tracking of non-resident pages |
US20110276744A1 (en) * | 2010-05-05 | 2011-11-10 | Microsoft Corporation | Flash memory cache including for use with persistent key-value store |
US20120017043A1 (en) * | 2010-07-07 | 2012-01-19 | Nexenta Systems, Inc. | Method and system for heterogeneous data volume |
US20130031298A1 (en) * | 2011-07-26 | 2013-01-31 | Apple Inc. | Including performance-related hints in requests to composite memory |
US20130218892A1 (en) * | 2009-12-22 | 2013-08-22 | International Business Machines Corporation | Hybrid storage subsystem with mixed placement of file contents |
US8732424B2 (en) * | 2009-01-07 | 2014-05-20 | Seagate Technology International | Hybrid storage apparatus and method of sharing resources therein |
Family Cites Families (52)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4132989A (en) | 1977-10-18 | 1979-01-02 | Nasa | Azimuth correlator for real-time synthetic aperture radar image processing |
US4292634A (en) | 1978-12-15 | 1981-09-29 | Nasa | Real-time multiple-look synthetic aperture radar processor for spacecraft applications |
US5059318A (en) | 1990-05-14 | 1991-10-22 | Benesi Steve C | Fluid seal for a traveling sheet filter press |
US5680640A (en) | 1995-09-01 | 1997-10-21 | Emc Corporation | System for migrating data by selecting a first or second transfer means based on the status of a data element map initialized to a predetermined state |
GB2318478B (en) | 1996-10-21 | 2001-01-17 | Northern Telecom Ltd | Network model for alarm correlation |
GB2318479B (en) | 1996-10-21 | 2001-04-04 | Northern Telecom Ltd | Problem model for alarm correlation |
CA2312444A1 (en) * | 2000-06-20 | 2001-12-20 | Ibm Canada Limited-Ibm Canada Limitee | Memory management of data buffers incorporating hierarchical victim selection |
US6631017B2 (en) | 2000-10-12 | 2003-10-07 | Jed Khoury | Matched amplification and switch joint transform correlator |
US6804763B1 (en) | 2000-10-17 | 2004-10-12 | Igt | High performance battery backed ram interface |
US6978259B1 (en) | 2001-10-23 | 2005-12-20 | Hewlett-Packard Development Company, L.P. | Automated system adaptation technique particularly for data storage systems |
US7093004B2 (en) | 2002-02-04 | 2006-08-15 | Datasynapse, Inc. | Using execution statistics to select tasks for redundant assignment in a distributed computing platform |
JP2004102374A (en) | 2002-09-05 | 2004-04-02 | Hitachi Ltd | Information processing system having data transition device |
EP1505506A1 (en) * | 2003-08-05 | 2005-02-09 | Sap Ag | A method of data caching |
US7103740B1 (en) | 2003-12-31 | 2006-09-05 | Veritas Operating Corporation | Backup mechanism for a multi-class file system |
US20060069876A1 (en) * | 2004-09-30 | 2006-03-30 | Sorav Bansal | Method and system of clock with adaptive cache replacement and temporal filtering |
US20060248391A1 (en) * | 2005-05-02 | 2006-11-02 | Glover Jeffrey C | State machine-based command line debugger |
US7548908B2 (en) * | 2005-06-24 | 2009-06-16 | Yahoo! Inc. | Dynamic bloom filter for caching query results |
US7548928B1 (en) * | 2005-08-05 | 2009-06-16 | Google Inc. | Data compression of large scale data stored in sparse tables |
JP2007072813A (en) | 2005-09-07 | 2007-03-22 | Hitachi Ltd | Storage system, file migration method and computer program |
WO2007031696A1 (en) | 2005-09-13 | 2007-03-22 | Arm Limited | Cache miss detection in a data processing apparatus |
US7730058B2 (en) * | 2005-10-05 | 2010-06-01 | Microsoft Corporation | Searching for information utilizing a probabilistic detector |
US20070168398A1 (en) | 2005-12-16 | 2007-07-19 | Powerfile, Inc. | Permanent Storage Appliance |
US7500050B2 (en) * | 2006-03-20 | 2009-03-03 | International Business Machines Corporation | Wise ordering for writes—combining spatial and temporal locality in write caches for multi-rank storage |
US7555575B2 (en) | 2006-07-27 | 2009-06-30 | Hitachi, Ltd. | Method and apparatus for migrating data between storage volumes of different data pattern |
US7937428B2 (en) * | 2006-12-21 | 2011-05-03 | International Business Machines Corporation | System and method for generating and using a dynamic bloom filter |
US8032529B2 (en) * | 2007-04-12 | 2011-10-04 | Cisco Technology, Inc. | Enhanced bloom filters |
US8745523B2 (en) | 2007-06-08 | 2014-06-03 | Apple Inc. | Deletion in electronic backups |
US7930547B2 (en) * | 2007-06-15 | 2011-04-19 | Alcatel-Lucent Usa Inc. | High accuracy bloom filter using partitioned hashing |
KR101347285B1 (en) * | 2007-09-28 | 2014-01-07 | 삼성전자주식회사 | Method for prefetching of hard disk drive, recording medium and apparatus therefor |
US7788220B1 (en) | 2007-12-31 | 2010-08-31 | Emc Corporation | Storage of data with composite hashes in backup systems |
US8301650B1 (en) * | 2008-12-19 | 2012-10-30 | Google, Inc. | Bloom filter compaction |
US8140537B2 (en) | 2009-07-21 | 2012-03-20 | International Business Machines Corporation | Block level tagging with file level information |
US9291712B2 (en) | 2009-09-10 | 2016-03-22 | Nextnav, Llc | Cell organization and transmission schemes in a wide area positioning system (WAPS) |
WO2011044154A1 (en) | 2009-10-05 | 2011-04-14 | Marvell Semiconductor, Inc. | Data caching in non-volatile memory |
US20110191522A1 (en) * | 2010-02-02 | 2011-08-04 | Condict Michael N | Managing Metadata and Page Replacement in a Persistent Cache in Flash Memory |
WO2011104741A1 (en) | 2010-02-23 | 2011-09-01 | Hitachi, Ltd. | Management system for storage system and method for managing storage system |
US8732133B2 (en) | 2010-03-16 | 2014-05-20 | Commvault Systems, Inc. | Extensible data deduplication system and method |
US8868487B2 (en) | 2010-04-12 | 2014-10-21 | Sandisk Enterprise Ip Llc | Event processing in a flash memory-based object store |
US8935487B2 (en) | 2010-05-05 | 2015-01-13 | Microsoft Corporation | Fast and low-RAM-footprint indexing for data deduplication |
US8380949B2 (en) | 2010-05-20 | 2013-02-19 | International Business Machines Corporation | Managing write operations to an extent of tracks migrated between storage devices |
US9401967B2 (en) | 2010-06-09 | 2016-07-26 | Brocade Communications Systems, Inc. | Inline wire speed deduplication system |
US8478934B2 (en) * | 2010-07-19 | 2013-07-02 | Lsi Corporation | Managing extended RAID caches using counting bloom filters |
TWI467581B (en) * | 2010-09-07 | 2015-01-01 | Phison Electronics Corp | Hybrid storage apparatus and hybrid storage medium controlller and addressing method thereof |
US8677004B2 (en) | 2010-09-10 | 2014-03-18 | International Business Machines Corporation | Migration of logical partitions between two devices |
US9244779B2 (en) | 2010-09-30 | 2016-01-26 | Commvault Systems, Inc. | Data recovery operations, such as recovery from modified network data management protocol data |
US8583611B2 (en) | 2010-10-22 | 2013-11-12 | Hitachi, Ltd. | File server for migration of file and method for migrating file |
US9032146B2 (en) | 2010-11-30 | 2015-05-12 | Lenovo Enterprise Solutions (Singapore) Pte. Ltd. | Dynamic use of raid levels responsive to workload requirements |
US8862845B2 (en) | 2010-12-06 | 2014-10-14 | Xiotech Corporation | Application profiling in a data storage array |
US8583966B2 (en) | 2011-04-29 | 2013-11-12 | Lsi Corporation | Methods and structure for debugging DDR memory of a storage controller |
US8788788B2 (en) | 2011-08-11 | 2014-07-22 | Pure Storage, Inc. | Logical sector mapping in a flash storage array |
US8914381B2 (en) | 2012-02-16 | 2014-12-16 | Apple Inc. | Correlation filter |
US9081503B2 (en) | 2012-02-16 | 2015-07-14 | Apple Inc. | Methods and systems for maintaining a storage volume with holes and filling holes |
-
2012
- 2012-09-06 US US13/605,921 patent/US9710397B2/en active Active
- 2012-09-06 US US13/605,916 patent/US20130219116A1/en not_active Abandoned
-
2013
- 2013-02-07 EP EP13706810.2A patent/EP2798501B1/en active Active
- 2013-02-07 JP JP2014557696A patent/JP5943095B2/en active Active
- 2013-02-07 AU AU2013221868A patent/AU2013221868B2/en active Active
- 2013-02-07 WO PCT/US2013/025224 patent/WO2013122818A1/en active Application Filing
- 2013-02-07 CN CN201380009551.8A patent/CN104115134B/en active Active
- 2013-02-07 KR KR1020147022828A patent/KR101599177B1/en active IP Right Grant
- 2013-02-08 TW TW102105367A patent/TWI524348B/en active
- 2013-02-08 TW TW102105368A patent/TW201346932A/en unknown
- 2013-02-11 JP JP2014557710A patent/JP5943096B2/en active Active
- 2013-02-11 WO PCT/US2013/025597 patent/WO2013122881A1/en active Application Filing
- 2013-02-11 EP EP13707949.7A patent/EP2798502B1/en active Active
- 2013-02-11 KR KR1020147022659A patent/KR101620773B1/en active IP Right Grant
- 2013-02-11 AU AU2013221855A patent/AU2013221855B2/en active Active
- 2013-02-11 CN CN201380009538.2A patent/CN104115133B/en active Active
Patent Citations (21)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6266771B1 (en) * | 1997-02-10 | 2001-07-24 | The Regents Of The University Of California | Probabilistic signature scheme |
US20030005223A1 (en) * | 2001-06-27 | 2003-01-02 | Coulson Richard L. | System boot time reduction method |
US20030056058A1 (en) * | 2001-09-17 | 2003-03-20 | Alistair Veitch | Logical volume data migration |
US20040044861A1 (en) * | 2002-08-30 | 2004-03-04 | Cavallo Joseph S. | Cache management |
US20110179219A1 (en) * | 2004-04-05 | 2011-07-21 | Super Talent Electronics, Inc. | Hybrid storage device |
US20110145489A1 (en) * | 2004-04-05 | 2011-06-16 | Super Talent Electronics, Inc. | Hybrid storage device |
US8010747B2 (en) * | 2005-11-30 | 2011-08-30 | Red Hat, Inc. | Method for tracking of non-resident pages |
US7953953B2 (en) * | 2006-01-13 | 2011-05-31 | Samsung Electronics Co., Ltd. | Method and apparatus for reducing page replacement time in system using demand paging technique |
US20070168627A1 (en) * | 2006-01-13 | 2007-07-19 | Samsung Electronics Co., Ltd. | Method and apparatus for reducing page replacement time in system using demand paging technique |
US20080021853A1 (en) * | 2006-07-20 | 2008-01-24 | International Business Machines Corporation | Using multiple data structures to manage data in cache |
US7908236B2 (en) * | 2006-07-20 | 2011-03-15 | International Business Machines Corporation | Using multiple data structures to manage data in cache |
US20100082936A1 (en) * | 2008-10-01 | 2010-04-01 | Hobbet Jeffrey R | Cache Mapping for Solid State Drives |
US8732424B2 (en) * | 2009-01-07 | 2014-05-20 | Seagate Technology International | Hybrid storage apparatus and method of sharing resources therein |
US20100191899A1 (en) * | 2009-01-28 | 2010-07-29 | Takehiko Kurashige | Information Processing Apparatus and Data Storage Apparatus |
US20100332725A1 (en) * | 2009-06-24 | 2010-12-30 | Post Samual D | Pinning content in nonvolatile memory |
US20100332730A1 (en) * | 2009-06-30 | 2010-12-30 | Royer Jr Robert J | Method and system for managing a nand flash memory |
US20110138112A1 (en) * | 2009-12-04 | 2011-06-09 | Hsing-Yi Chiang | Virtualization of Storage Devices |
US20130218892A1 (en) * | 2009-12-22 | 2013-08-22 | International Business Machines Corporation | Hybrid storage subsystem with mixed placement of file contents |
US20110276744A1 (en) * | 2010-05-05 | 2011-11-10 | Microsoft Corporation | Flash memory cache including for use with persistent key-value store |
US20120017043A1 (en) * | 2010-07-07 | 2012-01-19 | Nexenta Systems, Inc. | Method and system for heterogeneous data volume |
US20130031298A1 (en) * | 2011-07-26 | 2013-01-31 | Apple Inc. | Including performance-related hints in requests to composite memory |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10073851B2 (en) | 2013-01-08 | 2018-09-11 | Apple Inc. | Fast new file creation cache |
WO2015073450A1 (en) * | 2013-11-12 | 2015-05-21 | Wesie Andrew Michael | Improved control flow integrity system and method |
US9805188B2 (en) | 2013-11-12 | 2017-10-31 | RunSafe Security, Inc. | Control flow integrity system and method |
US20160313932A1 (en) * | 2015-04-24 | 2016-10-27 | Kabushiki Kaisha Toshiba | Data storage system and device |
US10942844B2 (en) | 2016-06-10 | 2021-03-09 | Apple Inc. | Reserved memory in memory management system |
US11360884B2 (en) | 2016-06-10 | 2022-06-14 | Apple Inc. | Reserved memory in memory management system |
CN109564532A (en) * | 2016-08-05 | 2019-04-02 | 美光科技公司 | Prediction corrective action in memory based on probabilistic data structure |
US11586679B2 (en) | 2016-08-05 | 2023-02-21 | Micron Technology, Inc. | Proactive corrective actions in memory based on a probabilistic data structure |
US10228860B2 (en) * | 2016-11-14 | 2019-03-12 | Open Drives LLC | Storage optimization based I/O pattern modeling |
US11789614B2 (en) | 2018-01-19 | 2023-10-17 | Micron Technology, Inc. | Performance allocation among users for accessing non-volatile memory devices |
Also Published As
Publication number | Publication date |
---|---|
CN104115133A (en) | 2014-10-22 |
KR20140111346A (en) | 2014-09-18 |
WO2013122818A1 (en) | 2013-08-22 |
CN104115133B (en) | 2017-08-08 |
CN104115134A (en) | 2014-10-22 |
KR20140116933A (en) | 2014-10-06 |
AU2013221855A1 (en) | 2014-08-21 |
JP2015512098A (en) | 2015-04-23 |
JP2015508924A (en) | 2015-03-23 |
EP2798502A1 (en) | 2014-11-05 |
AU2013221855B2 (en) | 2016-03-17 |
CN104115134B (en) | 2018-02-13 |
US20130219117A1 (en) | 2013-08-22 |
TW201346932A (en) | 2013-11-16 |
KR101599177B1 (en) | 2016-03-02 |
KR101620773B1 (en) | 2016-05-12 |
TWI524348B (en) | 2016-03-01 |
AU2013221868A1 (en) | 2014-08-21 |
EP2798502B1 (en) | 2020-04-08 |
JP5943096B2 (en) | 2016-06-29 |
JP5943095B2 (en) | 2016-06-29 |
WO2013122881A1 (en) | 2013-08-22 |
EP2798501A1 (en) | 2014-11-05 |
EP2798501B1 (en) | 2020-12-30 |
TW201335937A (en) | 2013-09-01 |
AU2013221868B2 (en) | 2016-03-31 |
US9710397B2 (en) | 2017-07-18 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
AU2013221868B2 (en) | Data migration for composite non-volatile storage device | |
EP3869316B1 (en) | Hybrid storage | |
US9966152B2 (en) | Dedupe DRAM system algorithm architecture | |
JP6678230B2 (en) | Storage device | |
US20140223072A1 (en) | Tiered Caching Using Single Level Cell and Multi-Level Cell Flash Technology | |
US10073851B2 (en) | Fast new file creation cache | |
US9977599B2 (en) | Data deduplication with support for both thick and thin provisioning of storage objects | |
US9442863B1 (en) | Cache entry management using read direction detection | |
US9710514B1 (en) | Systems and methods for efficient storage access using metadata | |
KR101970874B1 (en) | Hybrid hash index for non-volatile memory storage device | |
CN113296686A (en) | Data processing method, device, equipment and storage medium | |
US11853577B2 (en) | Tree structure node compaction prioritization | |
US10860233B2 (en) | Half-match deduplication | |
US10776030B2 (en) | Quota arbitration of a distributed file system | |
US20170322736A1 (en) | Reorder active pages to improve swap performance |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AS | Assignment |
Owner name: APPLE INC., CALIFORNIA Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:WANG, WENGUANG;MACKO, PETER;SIGNING DATES FROM 20120905 TO 20120906;REEL/FRAME:028946/0758 |
|
STCB | Information on status: application discontinuation |
Free format text: ABANDONED -- FAILURE TO RESPOND TO AN OFFICE ACTION |