Abstract:
The described implementations relate to collaborative speed determination in distributed systems. One method estimates upload speeds of a plurality of hosts. The method sends a first bandwidth probe from a first host to a second host. The method receives, at the first host, a second bandwidth probe sent from the second host. The method determines which of the first and second bandwidth probes was relatively slower. The method designates either of the first or second hosts that sent the relatively slower bandwidth probe as a loser and takes a speed of the bandwidth probe of the loser as a first estimate of the loser's upload speed.
Abstract:
An exclusive encryption system is established using multiple computing devices. The exclusive encryption system allows for the exclusion of certain plaintext (e.g., by one of the computing devices) and ciphertext (e.g., by another of the computing devices) while at the same time maintaining the privacy created by the encryption (e.g., so the other computing device cannot see the plaintext). The exclusive encryption system may be implemented as part of a serverless distributed file system with directory entries (e.g., file names or folder names) being the plaintext, or alternatively as part of other systems.
Abstract:
A method and system for regulating tasks of background processes so as to reduce interference with foreground processes. The progress rate of a background task (e.g., amount of work performed per unit time) is measured and evaluated against a target amount. If the progress rate appears degraded, the background task is suspended for a computed time interval so as to back off from its interference with a foreground process. Each time the progress rate appears degraded, the time interval is exponentially increased from its previous value up to a maximum, however if the performance appears normal, the time interval is reset to a minimum. Evaluation of the work is statistically based so as to eliminate variations in measurements, and automatic calibration of the target amount is provided, as is a mechanism for prioritizing multiple background tasks.
Abstract:
An exclusive encryption system is established using multiple computing devices. The exclusive encryption system allows for the exclusion of certain plaintext (e.g., by one of the computing devices) and ciphertext (e.g., by another of the computing devices) while at the same time maintaining the privacy created by the encryption (e.g., so the other computing device cannot see the plaintext). The exclusive encryption system may be implemented as part of a serverless distributed file system with directory entries (e.g., file names or folder names) being the plaintext, or alternatively as part of other systems.
Abstract:
A file format for a serverless distributed file system is composed of two parts: a primary data stream and a metadata stream. The data stream contains a file that is divided into multiple blocks. Each block is encrypted using a hash of the block as the encryption key. The metadata stream contains a header, a structure for indexing the encrypted blocks in the primary data stream, and some user information. The indexing structure defines leaf nodes for each of the blocks. Each leaf node consists of an access value used for decryption of the associated block and a verification value used to verify the encrypted block independently of other blocks. In one implementation, the access value is formed by hashing the file block and encrypting the resultant hash value using a randomly generated key. The key is then encrypted using the user's key as the encryption key. The verification value is formed by hashing the associated encrypted block using a one-way hash function. The file format supports verification of individual file blocks without knowledge of the randomly generated key or any user keys. To verify a block of the file, the file system traverses the tree to the appropriate leaf node associated with a target block to be verified. The file system hashes the target block and if the hash matches the access value contained in the leaf node, the block is authentic.
Abstract:
A serverless distributed file system manages the storage of files and directories using one or more directory groups. The directories may be managed using Byzantine-fault-tolerant groups, whereas files are managed without using Byzantine-fault-tolerant groups. Additionally, the file system may employ a hierarchical namespace to store files. Furthermore, the directory group may employ a plurality of locks to control access to objects (e.g., files and directories) in each directory.
Abstract:
A file format for a serverless distributed file system is composed of two parts: a primary data stream and a metadata stream. The data stream contains a file that is divided into multiple blocks. Each block is encrypted using a hash of the block as the encryption key. The metadata stream contains a header, a structure for indexing the encrypted blocks in the primary data stream, and some user information. The indexing structure defines leaf nodes for each of the blocks. Each leaf node consists of an access value used for decryption of the associated block and a verification value used to verify the encrypted block independently of other blocks. In one implementation, the access value is formed by hashing the file block and encrypting the resultant hash value using a randomly generated key. The key is then encrypted using the user's key as the encryption key. The verification value is formed by hashing the associated encrypted block using a one-way hash function. The file format supports verification of individual file blocks without knowledge of the randomly generated key or any user keys. To verify a block of the file, the file system traverses the tree to the appropriate leaf node associated with a target block to be verified. The file system hashes the target block and if the hash matches the access value contained in the leaf node, the block is authentic.
Abstract:
Digital maps can be composed of a series of image tiles that are selected based on the context of the map to be presented. Independently hosted tiles can comprise additional details that can be added to the map. A manifest can be created that describes the layers of map details composed of such independently hosted tiles. Externally referable mechanisms can, based on the manifest and map context, select tiles, from among the independently hosted tiles, that correspond to map tiles being displayed to a user. Subsequently, the mechanisms can instruct a browser, as specified in the manifest, to combine the map tiles and the independently hosted tiles to generate a more detailed map. Alternatively, customized mechanisms can generate map detail tiles in real-time, based on an exported map context. Also, controls instantiated by the browser can render three-dimensional images based on the combined map tiles.
Abstract:
A handle administration system is described in which software agents receive handles to various resources that they can use to obtain the resources. The described embodiments provide multiple states that can be assumed by the handles. An unassigned state is provided in which handles are not assigned to a particular resource, nor can they be dereferenced to obtain pointers to any resources. An assigned state is provided in which handles are assigned to a particular resource and can be dereferenced to obtain a pointer to the resource. A suspended state is provided in which the handles are assigned to a particular resource but cannot be dereferenced to obtain a pointer to that resource. Advantageously, a suspended handle can be reinstated to assume the assigned state. In one embodiment, the handle system is implemented by incorporating a suitable field in a handle database that is used to indicate that a handle is suspended. In another embodiment, no additional fields are necessary. Rather, handle values in the handle database are manipulated to indicate that a handle has been suspended. These manipulations can be easily undone to reinstate a handle. In the described embodiment, a three state handle system can be advantageously employed to implement a two-phase commit operation.
Abstract:
Potentially identical objects (e.g., files) are located across multiple computers based on stochastic partitioning of workload. For each of a plurality of objects stored on a plurality of computers in a network, a portion of object information corresponding to the object is selected. The object information can be generated in a variety of manners (e.g., based on hashing the object, based on characteristics of the object, and so forth). Any of a variety of portions of the object information can be used (e.g., the least significant bits of the object information). A stochastic partitioning process is then used to identify which of the plurality of computers to communicate the object information to for identification of potentially identical objects on the plurality of computers.