|Publication number||US20060047855 A1|
|Application number||US 10/844,893|
|Publication date||Mar 2, 2006|
|Filing date||May 13, 2004|
|Priority date||May 13, 2004|
|Also published as||US8117173, US20090271528|
|Publication number||10844893, 844893, US 2006/0047855 A1, US 2006/047855 A1, US 20060047855 A1, US 20060047855A1, US 2006047855 A1, US 2006047855A1, US-A1-20060047855, US-A1-2006047855, US2006/0047855A1, US2006/047855A1, US20060047855 A1, US20060047855A1, US2006047855 A1, US2006047855A1|
|Inventors||Yuri Gurevich, Nikolaj Bjorner, Dan Teodosiu|
|Original Assignee||Microsoft Corporation|
|Export Citation||BiBTeX, EndNote, RefMan|
|Referenced by (47), Classifications (7), Legal Events (2)|
|External Links: USPTO, USPTO Assignment, Espacenet|
The present invention relates generally to a method of chunking an object. More particularly, the present invention relates to a system and method for efficient chunking of objects such that objects can be efficiently updated between a remote machine and a local machine over a network. The chunking algorithm is applicable in networked application such as file synchronization using remote differential compression techniques. The chunking algorithm provides enhanced efficiencies by locating chunk boundaries around local maxima.
The proliferation of networks such as intranets, extranets, and the internet has lead to a large growth in the number of users that share information across wide networks. A maximum data transfer rate is associated with each physical network based on the bandwidth associated with the transmission medium as well as other infrastructure related limitations. As a result of limited network bandwidth, users can experience long delays in retrieving and transferring large amounts of data across the network.
Data compression techniques have become a popular way to transfer large amounts of data across a network with limited bandwidth. Data compression can be generally characterized as either lossless or lossy. Lossless compression involves the transformation of a data set such that an exact reproduction of the data set can be retrieved by applying a decompression transformation. Lossless compression is most often used to compact data, when an exact replica is required.
In the case where the recipient of a data object already has a previous, or older, version of that object, a lossless compression approach called Remote Differential Compression (RDC) may be used to determine and only transfer the differences between the new and the old versions of the object. Since an RDC transfer only involves communicating the observed differences between the new and old versions (for instance, in the case of files, file modification or last access dates, file attributes, or small changes to the file contents), the total amount of data transferred can be greatly reduced. RDC can be combined with another lossless compression algorithm to further reduce the network traffic. The benefits of RDC are most significant in the case where large objects need to be communicated frequently back and forth between computing devices and it is difficult or infeasible to maintain old copies of these objects, so that local differential algorithms cannot be used.
Briefly stated, the present invention is related to a method and system for chunking an object. A method and system are arranged to provide efficient chunking of objects such that objects can be efficiently updated between a remote machine and a local machine over a network. The chunking algorithm is applicable in networked application such as file synchronization using remote differential compression (RDC) techniques. The chunking algorithm provides enhanced efficiencies by locating chunk boundaries around local maxima.
A more complete appreciation of the present invention and its improvements can be obtained by reference to the accompanying drawings, which are briefly summarized below, to the following detailed description of illustrative embodiments of the invention, and to the appended claims.
Non-limiting and non-exhaustive embodiments of the present invention are described with reference to the following drawings.
Various embodiments of the present invention will be described in detail with reference to the drawings, where like reference numerals represent like parts and assemblies throughout the several views. Reference to various embodiments does not limit the scope of the invention, which is limited only by the scope of the claims attached hereto. Additionally, any examples set forth in this specification are not intended to be limiting and merely set forth some of the many possible embodiments for the claimed invention.
The present invention is described in the context of local and remote computing devices (or “devices”, for short) that have one or more commonly associated objects stored thereon. The terms “local” and “remote” refer to one instance of the method. However, the same device may play both a “local” and a “remote” role in different instances. Remote Differential Compression (RDC) methods are used to efficiently update the commonly associated objects over a network with limited-bandwidth. When a device having a new copy of an object needs to update a device having an older copy of the same object, or of a similar object, the RDC method is employed to only transmit the differences between the objects over the network. An example described RDC method uses (1) a recursive approach for the transmission of the RDC metadata, to reduce the amount of metadata transferred for large objects, and (2) a local maximum-based chunking method to increase the precision associated with the object differencing such that bandwidth utilization is minimized. Some example applications that benefit from the described RDC methods include: peer-to-peer replication services, file-transfer protocols such as SMB, virtual servers that transfer large images, email servers, cellular phone and PDA synchronization, database server replication, to name just a few.
In an example interaction between device A (100) and device B (101), different versions of an object are locally stored on the two devices: object OA on 100 and object OB on 101. At some point, device A (100) decides to update its copy of object OA with the copy (object OB) stored on device B (101), and sends a request to device B (101) to initiate the RDC method. In an alternate embodiment, the RDC method could be initiated by device B (101).
Device A (100) and device B (101) both process their locally stored object and divide the associated data into a variable number of chunks in a data-dependent fashion (e.g., chunks 1-n for object OB, and chunks 1-k for object OA, respectively). A set of signatures such as strong hashes (SHA) for the chunks are computed locally by both the devices. The devices both compile separate lists of the signatures. During the next step of the RDC method, device B (101) transmits its computed list of signatures and chunk lengths 1-n to device A (100) over the network 102. Device A (100) evaluates this list of signatures by comparing each received signature to its own generated signature list 1-k. Mismatches in the signature lists indicate one or more differences in the objects that require correction. Device A (100) transmits a request for device B (101) to send the chunks that have been identified by the mismatches in the signature lists. Device B (101) subsequently compresses and transmits the requested chunks, which are then reassembled by device A (100) after reception and decompression are accomplished. Device A (100) reassembles the received chunks together with its own matching chunks to obtain a local copy of object OB.
Example Computing Device
Computing device 200 may also have additional features or functionality. For example, computing device 200 may also include additional data storage devices (removable and/or non-removable) such as, for example, magnetic disks, optical disks, or tape. Such additional storage is illustrated in
Computing device 200 also contains communications connection(s) 216 that allow the device to communicate with other computing devices 218, such as over a network. Communications connection(s) 216 is an example of communication media. Communication media typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media. The term “modulated data signal” means a signal that has one or more of its characteristics set or changed in such a manner as to encode information in the signal. By way of example, and not limitation, communication media includes wired media such as a wired network or direct-wired connection, and wireless media such as acoustic, RF, microwave, satellite, infrared and other wireless media. The term computer readable media as used herein includes both storage media and communication media.
Various procedures and interfaces may be implemented in one or more application programs that reside in system memory 204. In one example, the application program is a remote differential compression algorithm that schedules file synchronization between the computing device (e.g., a client) and another remotely located computing device (e.g., a server). In another example, the application program is a compression/decompression procedure that is provided in system memory 204 for compression and decompressing data. In still another example, the application program is a decryption procedure that is provided in system memory 204 of a client device.
Remote Differential Compression (RDC)
The protocol for transferring the updated object OB from device B to device A is described below. A similar protocol may be used to transfer an object from device A to device B, and that the transfer can be initiated at the behest of either device A or device B without significantly changing the protocol described below.
The partitioning steps 2 and 3 may occur in a data-dependent fashion that uses a fingerprinting function that is computed at every byte position in the associated object (OA and OB, respectively). For a given position, the fingerprinting function is computed using a small data window surrounding that position in the object; the value of the fingerprinting function depends on all the bytes of the object included in that window. The fingerprinting function can be any appropriate function, such as, for example, a hash function or a Rabin polynomial.
Chunk boundaries are determined at positions in the Object for which the fingerprinting function computes to a value that satisfies a chosen condition. The chunk signatures may be computed using a cryptographically secure hash function (SHA), or some other hash function such as a collision-resistant hash function.
The signature and chunk length list sent in step 4 provides a basis for reconstructing the object using both the original chunks and the identified updated or new chunks. The chunks that are requested in step 6 are identified by their offset and lengths. The object is reconstructed on device A by using local and remote chunks whose signatures match the ones received by device A in step 4, in the same order.
After the reconstruction step is completed by device A, Object OA can be deleted and replaced by the copy of Object OB that was reconstructed on device A. In other embodiments, device A may keep Object OA around for potential “reuse” of chunks during future RDC transfers.
For large objects, the basic RDC protocol instance illustrated in
For example, referring to
This fixed overhead cost can be significantly reduced by using a recursive application of the RDC protocol instead of the signature information transfer in step 4. Referring to
After step 4.8 above is completed, execution continues at step 5 of the basic RDC protocol described above, which is illustrated in
As a result of the recursive chunking operations, the number of recursive signatures associated with the objects is reduced by a factor equal to the average chunk size C, yielding a significantly smaller number of recursive signatures (r<<n for object OA and s<<k for object OB, respectively). In one embodiment, the same chunking parameters could be used for chunking the signatures as for chunking the original objects OA and OB. In an alternate embodiment, other chunking parameters may be used for the recursive steps.
For very large objects the above recursive steps can be applied k times, where k≧1. For an average chunk size of C, recursive chunking may reduce the size of the signature traffic over the network (steps 4.2 through 4.8) by a factor approximately corresponding to Ck. Since C is relatively large, a recursion depth of greater than one may only be necessary for very large objects.
In one embodiment, the number of recursive steps may be dynamically determined by considering parameters that include one or more of the following: the expected average chunk size, the size of the objects OA and/or OB, the data format of the objects OA and/or OB, the latency and bandwidth characteristics of the network connecting device A and device B.
The fingerprinting function used in step 2 is matched to the fingerprinting function that is used in step 3. Similarly, the fingerprinting function used in step 4.2 is matched to the fingerprinting function that is used in step 4.3. The fingerprinting function from steps 2-3 can optionally be matched to the fingerprinting function from steps 4.2-4.3.
As described previously, each fingerprinting function uses a small data window that surrounds a position in the object; where the value associated with the fingerprinting function depends on all the bytes of the object that are included inside the data window. The size of the data window can be dynamically adjusted based on one or more criteria. Furthermore, the chunking procedure uses the value of the fingerprinting function and one or more additional chunking parameters to determine the chunk boundaries in steps 2-3 and 4.2-4.3 above.
By dynamically changing the window size and the chunking parameters, the chunk boundaries are adjusted such that any necessary data transfers are accomplished with minimal consumption of the available bandwidth.
Example criteria for adjusting the window size and the chunking parameters include: a data type associated with the object, environmental constraints, a usage model, the latency and bandwidth characteristics of the network connecting device A and device B, and any other appropriate model for determining average data transfer block sizes. Example data types include word processing files, database images, spreadsheets, presentation slide shows, and graphic images. An example usage model may be where the average number of bytes required in a typical data transfer is monitored.
Changes to a single element within an application program can result in a number of changes to the associated datum and/or file. Since most application programs have an associated file type, the file type is one possible criteria that is worthy of consideration in adjusting the window size and the chunking parameters. In one example, the modification of a single character in a word processing document results in approximately 100 bytes being changed in the associated file. In another example, the modification of a single element in a database application results in 1000 bytes being changed in the database index file. For each example, the appropriate window size and chunking parameters may be different such that the chunking procedure has an appropriate granularity that is optimized based on the particular application.
Example Process Flow
As illustrated in
In step 454, device B sends the signature and chunk length list computed in steps 452 and 453 to device A, which receives this information in step 404.
In step 405, the local device A initializes the list of requested chunks to the empty list, and initializes the tracking offset for the remote chunks to 0. In step 406, the next (signature, chunk length) pair (SigBi, LenBi) is selected for consideration from the list received in step 404. In step 407, device A checks whether the signature SigBi selected in step 406 matches any of the signatures it computed during step 403. If it matches, execution continues at step 409. If it doesn't match, the tracking remote chunk offset and the length in bytes LenBi are added to the request list in step 408. At step 409, the tracking offset is incremented by the length of the current chunk LenBi.
In step 410, the local device A tests whether all (signature, chunk length) pairs received in step 404 have been processed. If not, execution continues at step 406. Otherwise, the chunk request list is suitably encoded in a compact fashion, compressed, and sent to the remote device B at step 411.
The remote device B receives the compressed list of chunks at step 455, decompresses it, then compresses and sends back the chunk data at step 456.
The local device receives and decompresses the requested chunk data at step 412. Using the local copy of the object OA and the received chunk data, the local devices reassembles a local copy of OB at step 413.
In step 415, the next (signature, chunk length) pair (SigBi, LenBi) is selected for consideration from the list received in step 404. In step 416, device A checks whether the signature SigBi selected in step 417 matches any of the signatures it computed during step 403.
If it matches, execution continues at step 417, where the corresponding local chunk is appended to the reconstructed object. If it doesn't match, the received and decompressed remote chunk is appended to the reconstructed object in step 418.
In step 419, the local device A tests whether all (signature, chunk length) pairs received in step 404 have been processed. If not, execution continues at step 415. Otherwise, the reconstructed object is used to replace the old copy of the object OA on device A in step 420.
Example Recursive Signature Transfer Process Flow
The left hand side of
In steps 501 and 551, both the local device A and remote device B independently compute recursive fingerprints of their signature and chunk length lists ((SigA1, LenA1), . . . (SigAk, LenAk)) and ((SigB1, LenB1), . . . (SigBn, LenBn)), respectively, that had been computed in steps 402/403 and 452/453, respectively. In steps 502 and 552 the devices divide their respective signature and chunk length lists into recursive chunks, and in steps 503 and 553 compute recursive signatures (e.g., SHA) for each recursive chunk, respectively.
In step 554, device B sends the recursive signature and chunk length list computed in steps 552 and 553 to device A, which receives this information in step 504.
In step 505, the local device A initializes the list of requested recursive chunks to the empty list, and initializes the tracking remote recursive offset for the remote recursive chunks to 0. In step 506, the next (recursive signature, recursive chunk length) pair (RSigBi, RLenBi) is selected for consideration from the list received in step 504. In step 507, device A checks whether the recursive signature RSigBi selected in step 506 matches any of the recursive signatures it computed during step 503. If it matches, execution continues at step 509. If it doesn't match, the tracking remote recursive chunk offset and the length in bytes RLenBi are added to the request list in step 508. At step 509, the tracking remote recursive offset is incremented by the length of the current recursive chunk RLenBi.
In step 510, the local device A tests whether all (recursive signature, recursive chunk length) pairs received in step 504 have been processed. If not, execution continues at step 506. Otherwise, the recursive chunk request list is compactly encoded, compressed, and sent to the remote device B at step 511.
The remote device B receives the compressed list of recursive chunks at step 555, uncompressed the list, then compresses and sends back the recursive chunk data at step 556.
The local device receives and decompresses the requested recursive chunk data at step 512. Using the local copy of the signature and chunk length list ((SigA1, LenA1), . . . (SigAk, LenAk)) and the received recursive chunk data, the local devices reassembles a local copy of the signature and chunk length list ((SigB1, LenB1), . . . (SigBk, LenBn)) at step 513. Execution then continues at step 405 in
In step 515, the next (recursive signature, recursive chunk length) pair (RSigBi, RLenBi) is selected for consideration from the list received in step 504. In step 516, device A checks whether the recursive signature RSigBi selected in step 515 matches any of the recursive signatures it computed during step 503.
If it matches, execution continues at step 517, where device A appends the corresponding local recursive chunk to SIGCL. If it doesn't match, the remote received recursive chunk is appended to SIGCL at step 518.
In step 519, the local device A tests whether all (recursive signature, recursive chunk length) pairs received in step 504 have been processed. If not, execution continues at step 515. Otherwise, the local copy of the signature and chunk length list ((SigB1,LenB1), . . . (SigBk,LenBn)) is set to the value of SIGCL in step 520. Execution then continues back to step 405 in
The recursive signature and chunk length list may optionally be evaluated to determine if additional recursive remote differential compression is necessary to minimize bandwidth utilization as previously described. The recursive signature and chunk length list can be recursively compressed using the described chunking procedure by replacing steps 504 and 554 with another instance of the RDC procedure, and so on, until the desired compression level is achieved. After the recursive signature list is sufficiently compressed, the recursive signature list is returned for transmission between the remote and local devices as previously described.
Example Object Updating
At a subsequent time, the file on the server is updated to: “The quick fox jumped over the lazy brown dog. The brown dog was so lazy that he didn't notice the fox jumping over him.”
As described previously, the client periodically requests the file to be updated. The client and server both chunk the object (the text) into chunks as illustrated. On the client, the chunks are: “The quick fox jumped”, “over the lazy brown dog.”, “The dog was so lazy that he didn't notice”, and “the fox jumping over him.”; the client signature list is generated as: SHA11, SHA12, SHA11, and SHA14. On the server, the chunks are: “The quick fox jumped”, “over the lazy brown dog.”, “The brown dog was”, “so lazy that he didn't notice”, and “the fox jumping over him.”; the server signature list is generated as: SHA21, SHA22, SHA23, SHA24, and SHA25.
The server transmits the signature list (SHA21-SHA25) using a recursive signature compression technique as previously described. The client recognizes that the locally stored signature list (SHA11-SHA14) does not match the received signature list (SHA21-SHA25), and requests the missing chunks 3 and 4 from the server. The server compresses and transmits chunks 3 and 4 (“The brown dog was”, and “so lazy that he didn't notice”). The client receives the compressed chunks, decompresses them, and updates the file as illustrated in
The effectiveness of the basic RDC procedure described above may be increased by optimizing the chunking procedures that are used to chunk the object data and/or chunk the signature and chunk length lists.
The basic RDC procedure has a network communication overhead cost that is identified by the sum of:
and signature ∉ Signatures from A
The communication cost thus benefits from a large average chunk size and a large intersection between the remote and local chunks. The choice of how objects are cut into chunks determines the quality of the protocol. The local and remote device must agree, without prior communication, on where to cut an object. The following describes and analyzes various methods for finding cuts.
The following characteristics are assumed to be known for the cutting algorithm:
When Objects OA and OB have S segments in common with average size K, the number of chunks that can be obtained locally on the client is given by:
and (S2) above rewrites to:
Thus, a chunking algorithm that minimizes slack will minimize the number of bytes sent over the wire. It is therefore advantageous to use chunking algorithms that minimize the expected slack.
All chunking algorithms use a fingerprinting function, or hash, that depends on a small window, that is, a limited sequence of bytes. The execution time of the hash algorithms used for chunking is independent of the hash window size when those algorithms are amenable to finite differencing (strength reduction) optimizations. Thus, for a hash window of size k it is should be easy (require only a constant number of steps) to compute the hash #[b1, . . . , bk−1, bk] using b0, bk, and #[b0, b1, . . . , bk−1] only. Various hashing functions can be employed such as hash functions using Rabin polynomials, as well as other hash functions that appear computationally more efficient based on tables of pre-computed random numbers.
In one example, a 32 bit Adler hash based on the rolling checksum can be used as the hashing function for fingerprinting. This procedure provides a reasonably good random hash function by using a fixed table with 256 entries, each a precomputed 16 bit random number. The table is used to convert fingerprinted bytes into a random 16 bit number. The 32 bit hash is split into two 16 bit numbers sum1 and sum2, which are updated given the procedure:
sum1+=table[b k]−table[b 0]
sum2+=sum1 −k*table[b 0]
In another example, a 64 bit random hash with cyclic shifting may be used as the hashing function for fingerprinting. The period of a cyclic shift is bounded by the size of the hash value. Thus, using a 64 bit hash value sets the period of the hash to 64. The procedure for updating the hash is given as:
hash=hashˆ((table[b 0]<<1)|(table[b 0 ]>>u))ˆtable[b k];
In still another example, other shifting methods may be employed to provide fingerprinting. Straight forward cyclic shifting produces a period of limited length, and is bounded by the size of the hash value. Other permutations have longer periods. For instance, the permutation given by the cycles (1 2 3 0) (5 6 7 8 9 10 11 12 13 14 4) (16 17 18 19 20 21 15) (23 24 25 26 22) (28 29 27) (31 30) has a period of length 4*3*5*7*11=4620. The single application of this example permutation can be computed using a right shift followed by operations that patch up the positions at the beginning of each interval.
Analysis of Previous Art for Chunking at Pre-Determined Patterns
Previous chunking methods are determined by computing a fingerprinting hash with a pre-determined window size k (=48), and identifying cut points based on whether a subset of the hash bits match a pre-determined pattern. With random hash values, this pattern may as well be 0, and the relevant subset may as well be a prefix of the hash. In basic instructions, this translates to a predicate of the form:
CutPoint(hash)≡0==(hash & ((1<<c)−1)),
Since the probability for a match given a random hash function is 2−c, an average chunk size C=2c results. However, neither the minimal, nor the maximal chunk size is determined by this procedure. If a minimal chunk length of m is imposed, then the average chunk size is:
A rough estimate of the expected slack is obtained by considering streams s1s3 and s2s3. Cut points in s1 and s2 may appear at arbitrary places. Since the average chunk length is C=m+2c, about (2c/C)2 of the last cut-points in s1 and s2 will be beyond distance m. They will contribute to slack at around 2c. The remaining 1−(2c/C)2 contribute with slack of length about C. The expected slack will then be around (2c/C)3+(1−(2c/C)2)*(C/C)=(2c/C)3+1−(2c/C)2, which has global minimum for m=2c−1, with a value of about 23/27=0.85. A more precise analysis gives a somewhat lower estimate for the remaining 1−(2c/C)2 fraction, but will also need to compensate for cuts within distance m inside s3, which contributes to a higher estimate.
Thus, the expected slack for the prior art is approximately 0.85*C.
Chunking at Filters (New Art)
Chunking at filters is based on fixing a filter, which is a sequence of patterns of length m, and matching the sequence of fingerprinting hashes against the filter. When the filter does not allow a sequence of hashes to match both a prefix and a suffix of the filter it can be inferred that the minimal distance between any two matches must be at least m. An example filter may be obtained from the CutPoint predicate used in the previous art, by setting the first m−1 patterns to
and the last pattern to:
The probability for matching this filter is given by (1−p)m−1 p where p is 2−c. One may compute that the expected chunk length is given by the inverse of the probability for matching a filter (it is required that the filter not allow a sequence to match both a prefix and suffix), thus the expected length of the example filter is (1−p)−m+1 p−1. This length is minimized when setting p:=1/m, and it turns out to be around (e*m). The average slack hovers around 0.77, or about 1−e−1+e−2, as can be verified by those skilled in the art. An alternative embodiment of this method uses a pattern that works directly with the raw input and does not use rolling hashes.
Chunking at Local Maxima (New Art)
Chunking at Local Maxima is based on choosing as cut points positions that are maximal within a bounded horizon. In the following, we shall use h for the value of the horizon. We say that the hash at position offset is an h-local maximum if the hash values at offsets offset-h, . . . , offset−1, as well as offset+1, . . . , offset+h are all smaller than the hash value at offset. In other words, all positions h steps to the left and h steps to the right have lesser hash values. Those skilled in the art will recognize that local maxima may be replaced by local minima or any other metric based comparison (such as “closest to the median hash value”).
The set of local maxima for an object of size n may be computed in time bounded by 2·n operations such that the cost of computing the set of local maxima is close to or the same as the cost of computing the cut-points based on independent chunking. Chunks generated using local maxima always have a minimal size corresponding to h, with an average size of approximately 2h+1. A CutPoint procedure is illustrated in
An object with n bytes is processed by calling CutPoint n times such that at most n entries are inserted for a given object. One entry is removed each time the loop starting at step 805 is repeated such that there are no more than n entries to delete. Thus, the processing loop may be entered once for every entry and the combined number of repetitions may be at most n. This implies that the average number of steps within the loop at each call to CutPoint is slightly less than 2, and the number of steps to compute cut points is independent of h.
Since the hash values from the elements form a descending chain between min and max, we will see that the average distance between min and max (|min−max|% h) is given by the natural logarithm of h. Offsets not included between two adjacent entries in M have hash values that are less than or equal to the two entries. The average length of such chains is given by the recurrence equation f(n)=1+1/n *Σk<n f(k). The average length of the longest descending chain on an interval of length n is 1 greater than the average length of the longest descending chain starting from the position of the largest element, where the largest element may be found at arbitrary positions with a probability of 1/n. The recurrence relation has as solution corresponding to the harmonic number Hn=1+½+⅓+¼+ . . . . +1/n, which can be validated by substituting Hn into the equation and performing induction on n. Hn is proportional to the natural logarithm of n. Thus, although array M is allocated with size h, only a small fraction of size ln(h) is ever used at any one time.
Computing min and max with modulus h permits arbitrary growth of the used intervals of M as long as the distance between the numbers remain within h.
The choice of initial values for M implies that cut-points may be generated within the first h offsets. The algorithm can be adapted to avoid cut-points at these first h offsets.
The expected size of the chunks generated by this procedure is around 2h+1. We obtain this number from the probability that a given position is a cut-point. Suppose the hash has m different possible values. Then the probability is determined by:
Approximating using integration ∫0≦x<m 1/m (x/m)2h dx=1/(2h+1) indicates the probability when m is sufficiently large.
The probability can be computed more precisely by first simplifying the sum to:
(1/m)2h+1 Σ0≦k<m k 2h,
which using Bernoulli numbers Bk expands to:
(1/m)2h+1 1(2h+1)Σ0≦k<2h(2h+1)!/k!(2h+1−k)!B k m 2h+1−k
The only odd Bernoulli number that is non-zero is B1, which has a corresponding value of −½. The even Bernoulli numbers satisfy the equation:
H ∞ (2n)=(−1)n−1 22n−1 π2n B 2n/(2n)!
The left hand side represents the infinite sum 1+(½)2n+(⅓)2n+ . . . , which for even moderate values of n is very close to 1.
When m is much larger than h, all of the terms, except for the first can be ignored, as we saw by integration. They are given by a constant between 0 and 1 multiplied by a term proportional to hk−1/mk. The first term (where B0=1) simplifies to 1/(2h+1). (the second term is −1/(2m), the third is h/(6m2)).
For a rough estimate of the expected slack consider streams s1s3 and s2s3 The last cut points inside s1 and s2 may appear at arbitrary places. Since the average chunk length is about 2h+1 about ¼'th of the last cut-points will be within distance h in both s1 and s2. They will contribute to cut-points at around ⅞ h. In another ½ of the cases, one cut-point will be within distance h the other beyond distance h. These contribute with cut-points around ¾ h. The remaining ¼'th of the last cut-points in s1 and s2 will be in distance larger than h. The expected slack will therefore be around ¼* ⅞+½*¾+¼*¼=0.66.
Thus, the expected slack for our independent chunking approach is 0.66*C, which is an improvement over the prior art (0.85*C).
There is an alternate way of identifying cut-points that require executing in average fewer instructions while using space at most proportional to h, or in average ln h. The procedure above inserts entries for every position 0 . . . n−1 in a stream of length n. The basic idea in the alternate procedure is to only update when encountering elements of an ascending chain within intervals of length h. We observed that there will in average only be ln h such updates per interval. Furthermore, by comparing the local maxima in two consecutive intervals of length h one can determine whether each of the two local maxima may also be an h local maximum. There is one peculiarity with the alternate procedure; it requires computing the ascending chains by traversing the stream in blocks of size h, each block gets traversed in reverse direction.
In the alternate procedure (see
Insertion into A is achieved by testing the hash value at the offset against the largest entry in A so far.
The loop that updates both
Each call to CutPoint requires in average In h memory writes to A, and with loop hoisting h+ln h comparisons related to finding maxima. The last update to
Observed Benefits of the Improved Chunking Algorithms
The minimal chunk size is built into both the local maxima and the filter methods described above. The conventional implementations require that the minimal chunk size is supplied separately with an extra parameter.
The local max (or mathematical) based methods produce measurable better slack estimate, which translates to further compression over the network. The filter method also produces better slack performance than the conventional methods.
Both of the new methods have a locality property of cut points. All cut points inside s3 that are beyond horizon will be cut points for both streams s1s3 and s2s3. (in other words, consider stream s1s3, if p is a position≧|s1|+horizon and p is a cut point in s1s3, then it is also a cut point in s2s3. The same property holds the other direction (symmetrically), if p is a cut point in s2s3, then it is also a cut point in s1s3). This is not the case for the conventional methods, where the requirement that cuts be beyond some minimal chunk size may interfere adversely.
Alternative Mathematical Functions
Although the above-described chunking procedures describe a means for locating cut-points using a local maxima calculation, the present invention is not so limited. Any mathematical function can be arranged to examine potential cut-points. Each potential cut-point is evaluated by evaluating hash values that are located within the horizon window about a considered cut-point. The evaluation of the hash values is accomplished by the mathematical function, which may include at least one of locating a maximum value within the horizon, locating a minimum values within the horizon, evaluating a difference between hash values, evaluating a difference of hash values and comparing the result against an arbitrary constant, as well as some other mathematical or statistical function.
The particular mathematical function described previously for local maxima is a binary predicate “_>_”. For the case where p is an offset in the object, p is chosen as a cut-point if hashp>hashk, for all k, where p-horizon≦k<p, or p<k≦p+horizon. However, the binary predicate>can be replaced with any other mathematical function without deviating from the spirit of the invention.
The above specification, examples and data provide a complete description of the manufacture and use of the composition of the invention. Since many embodiments of the invention can be made without departing from the spirit and scope of the invention, the invention resides in the claims hereinafter appended.
|Citing Patent||Filing date||Publication date||Applicant||Title|
|US7299406 *||Jun 2, 2004||Nov 20, 2007||Research In Motion Limited||Representing spreadsheet document content|
|US7555531||Apr 15, 2004||Jun 30, 2009||Microsoft Corporation||Efficient algorithm and protocol for remote differential compression|
|US7562186||Apr 11, 2006||Jul 14, 2009||Data Domain, Inc.||Efficient data storage using resemblance of data segments|
|US7613787 *||Sep 24, 2004||Nov 3, 2009||Microsoft Corporation||Efficient algorithm for finding candidate objects for remote differential compression|
|US7640354 *||Dec 1, 2006||Dec 29, 2009||Microsoft Corporation||Scalable differential compression of network data|
|US7730164||Nov 23, 2005||Jun 1, 2010||Adobe Systems Incorporated||Bootstrap approaches to downloading data in response to a download indication|
|US7834784 *||Jan 18, 2007||Nov 16, 2010||Cisco Technology, Inc.||Data redundancy elimination mechanism including fast lookup of data patterns exhibiting spatial locality|
|US7844581 *||Dec 1, 2006||Nov 30, 2010||Nec Laboratories America, Inc.||Methods and systems for data management using multiple selection criteria|
|US7844652||Apr 11, 2006||Nov 30, 2010||Emc Corporation||Efficient computation of sketches|
|US7849462||Jan 7, 2005||Dec 7, 2010||Microsoft Corporation||Image server|
|US7925683 *||Dec 18, 2009||Apr 12, 2011||Copiun, Inc.||Methods and apparatus for content-aware data de-duplication|
|US7949824||Apr 11, 2006||May 24, 2011||Emc Corporation||Efficient data storage using two level delta resemblance|
|US7975071 *||Jan 18, 2008||Jul 5, 2011||Microsoft Corporation||Content compression in networks|
|US8036346 *||Dec 13, 2005||Oct 11, 2011||Cisco Technology, Inc.||Method and system for testing audio server|
|US8055799 *||Mar 11, 2010||Nov 8, 2011||Avaya Inc.||Method and apparatus for providing an interface for a messaging mailbox|
|US8073926||Jan 7, 2005||Dec 6, 2011||Microsoft Corporation||Virtual machine image server|
|US8078593||Aug 28, 2009||Dec 13, 2011||Infineta Systems, Inc.||Dictionary architecture and methodology for revision-tolerant data de-duplication|
|US8112496||Jul 31, 2009||Feb 7, 2012||Microsoft Corporation||Efficient algorithm for finding candidate objects for remote differential compression|
|US8214517||Dec 1, 2006||Jul 3, 2012||Nec Laboratories America, Inc.||Methods and systems for quick and efficient data management and/or processing|
|US8244691||Nov 4, 2011||Aug 14, 2012||Infineta Systems, Inc.||Dictionary architecture and methodology for revision-tolerant data de-duplication|
|US8370309||Jun 30, 2009||Feb 5, 2013||Infineta Systems, Inc.||Revision-tolerant data de-duplication|
|US8452739||Mar 16, 2011||May 28, 2013||Copiun, Inc.||Highly scalable and distributed data de-duplication|
|US8543539||Sep 16, 2009||Sep 24, 2013||Business Objects Software Limited||Method and system for capturing change of data|
|US8589455||Dec 18, 2009||Nov 19, 2013||Copiun, Inc.||Methods and apparatus for content-aware data partitioning|
|US8645333 *||May 29, 2008||Feb 4, 2014||International Business Machines Corporation||Method and apparatus to minimize metadata in de-duplication|
|US8806489 *||Jul 5, 2012||Aug 12, 2014||International Business Machines Corporation||Virtual machine image distribution network|
|US8832034||Apr 5, 2010||Sep 9, 2014||Riverbed Technology, Inc.||Space-efficient, revision-tolerant data de-duplication|
|US8838541||Oct 25, 2007||Sep 16, 2014||Hewlett-Packard Development Company, L.P.||Data processing apparatus and method of processing data|
|US8838691 *||Jun 29, 2012||Sep 16, 2014||International Business Machines Corporation||Data de-duplication in service oriented architecture and web services environment|
|US8959089||Apr 25, 2008||Feb 17, 2015||Hewlett-Packard Development Company, L.P.||Data processing apparatus and method of processing data|
|US9059956||Jun 21, 2013||Jun 16, 2015||Good Technology Corporation||Asynchronous real-time retrieval of data|
|US9083708||May 17, 2010||Jul 14, 2015||Microsoft Technology Licensing, Llc||Asymmetric end host redundancy elimination for networks|
|US9110915||Apr 18, 2013||Aug 18, 2015||Copiun, Inc.||Highly scalable and distributed data de-duplication|
|US20050235043 *||Apr 15, 2004||Oct 20, 2005||Microsoft Corporation||Efficient algorithm and protocol for remote differential compression|
|US20050256974 *||May 13, 2004||Nov 17, 2005||Microsoft Corporation||Efficient algorithm and protocol for remote differential compression on a remote device|
|US20050262167 *||May 13, 2004||Nov 24, 2005||Microsoft Corporation||Efficient algorithm and protocol for remote differential compression on a local device|
|US20050273695 *||Jun 2, 2004||Dec 8, 2005||Schnurr Jeffrey R||Representing spreadsheet document content|
|US20100318759 *||Dec 16, 2010||Microsoft Corporation||Distributed rdc chunk store|
|US20120137097 *||Feb 7, 2012||May 31, 2012||Alastair Slater||Communicating chunks between devices|
|US20120150824 *||Jun 14, 2012||Inventec Corporation||Processing System of Data De-Duplication|
|US20140006498 *||Jun 29, 2012||Jan 2, 2014||International Business Machines Corporation||Data De-Duplication in Service Oriented Architecture and Web Services Environment|
|US20140013322 *||Jul 5, 2012||Jan 9, 2014||International Business Machines Corporation||Virtual machine image distribution network|
|US20140136779 *||Nov 11, 2013||May 15, 2014||Datawise Systems||Method and Apparatus for Achieving Optimal Resource Allocation Dynamically in a Distributed Computing Environment|
|US20150039571 *||Oct 20, 2014||Feb 5, 2015||Dell Products L.P.||Accelerated deduplication|
|EP2302538A1 *||Sep 16, 2010||Mar 30, 2011||Business Objects Software Ltd.||Method and system for capturing change of data|
|WO2007120740A2 *||Apr 11, 2007||Oct 25, 2007||Data Domain Inc||Efficient computation of sketches|
|WO2008067226A1||Nov 21, 2007||Jun 5, 2008||Nec Lab America Inc||Methods and systems for data management using multiple selection criteria|
|U.S. Classification||709/247, 707/E17.005|
|Cooperative Classification||H04L63/123, G06F17/30194|
|European Classification||G06F17/30F8D, H04L63/12A|
|May 13, 2004||AS||Assignment|
Owner name: MICROSOFT CORPORATION, WASHINGTON
Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:GUREVICH, YURI;BJORNER, NIKOJAJ S.;TEODOSIU, DAN;REEL/FRAME:015331/0965
Effective date: 20040513
|Jan 15, 2015||AS||Assignment|
Owner name: MICROSOFT TECHNOLOGY LICENSING, LLC, WASHINGTON
Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:MICROSOFT CORPORATION;REEL/FRAME:034766/0001
Effective date: 20141014