Abstract: A method and a system for cache management in system interfacing to a cloud storage. The cache has two layers: the filter layer for tracing read access to the data blocks and the cache layer for keeping the actual data blocks. The layer two consists of two modules—a main cache and a boot cache. The boot cache is filled during the short period of time after the first file open operation. The boot cache also has a limit on the amount of data that can be put into the cache for the particular file. The filter layer detects continuous read access pattern and avoids caching data, if the data is read continuously beyond some limit.

Abstract: A method for optimization of a standard TCP connection. The optimization is based on load distributions by a system kernel. A proposed architecture includes an application running a proxy-process. The application is connected locally to an assigned port (e.g., port 9000). A number of connections N (for example 4) is established to a proxy server located on the cloud storage. Thus, the application is not directly connected to a front end server. Instead, it is connected to the proxy process via a local port. The proxy process transfers redistributed data streams to the proxy server on the cloud, which combines N data streams into one and passes it to the front end server residing on the cloud.

Abstract: Method for generation of a live update including compiling original source code into a first intermediate representation (IR) code; compiling modified source code into second IR code; analyzing and comparing the first and second IR codes to identify variables and functions that were changed generating a part of final IR code with all the original variables and functions; generating an additional part of final IR code with new code for modified portions of the changed original functions, added functions and variables, and marking it for compilation into special code/data sections; and compiling a new object code and a final executable binary based on the final IR. The final executable object code includes the original code and data from original application binary, and a live update code and data from additional part of final IR generated. The live update code and data refer to original code and data where needed via standard object code relocation information.

Abstract: A method and system for archiving file data used by a virtual container. The container uses “real files” and “balloon” files. The “real files” are the container file system files that are mapped to corresponding blocks of the host file system. The “real files” are mapped upon creation. The “balloon” files are also created in the container file system, but any links to the blocks of the host file system are invalidated (mapping is removed) and the blocks of the host file system corresponding to a balloon file are marked as free. A hypervisor, a host OS or a Virtual Machine Monitor frees up real physical blocks completely, so these blocks become available for writes in the host file system. Thus, all references indicating that these blocks are occupied are removed.

Abstract: A method and a system for cache management in system interfacing to a cloud storage. The cache has two layers: the filter layer for tracing read access to the data blocks and the cache layer for keeping the actual data blocks. The layer two consists of two modules—a main cache and a boot cache. The boot cache is filled during the short period of time after the first file open operation. The boot cache also has a limit on the amount of data that can be put into the cache for the particular file. The filter layer detects continuous read access pattern and avoids caching data, if the data is read continuously beyond some limit.

Abstract: A method and system for emulation of super speed external devices in a virtual machine (VM), including checking the ability of the VM Guest OS to support the super speed external device. If the super speed device is not supported by the Guest OS, device metadata is substituted by the metadata of the devices supported by the Guest OS. The method replaces the metadata of a new external device by the metadata of an older or different (supported) device. A VM acquires a descriptor of the external device configuration and “patches” the device by replacing device version data from a new device version to an older (or different) device.

Abstract: A computer system has a random access memory (RAM) that stores currently used memory pages and SWAP storage for storing memory page that is not in use. If the process requires memory page stored on the SWAP storage, a corresponding page is loaded to RAM. If the page in RAM is not currently in use, it is moved to the SWAP storage. The computer system has a number of Virtual Environments (i.e., Containers) that run their own processes, a VE/Container RAM and a virtual SWAP storage. The Container processes have access to a VE/Container RAM. When the Container process request OS for memory, the memory manager allocates memory pages in the RAM and also allocates memory pages for the Container process in the VE/Container RAM. If no free virtual RAM is available, the process data is moved to the virtual SWAP storage.

Abstract: A system, method and computer program product for managing the quality of service differentiated cloud storage. The cloud storage (and its services) is highly distributed. An overall speed of the storage is calculated based on storage speed and a traffic speed of the connection to the particular cloud storage. Data access expenses are calculated. Then, for each of the portions of the cloud storage the associated speed and traffic costs are calculated, so the user can select a level of data access guarantee (DAG) for his particular needs. In order to maintain the desired overall speed of the data access, geo-targeting with the cloud storage system is implemented, where the same data is retrieved from different locations based on optimal data movement costs.