Abstract: In accordance with an aspect of the present disclosure, there is provided a method for adaptive I/O completion. The method comprises, determining whether an application is a foreground application or a background application; in response to the application determined to be the foreground application, determining whether the application is a CPU-bound application or an I/O-bound application; and applying an I/O polling method in response to that the application determined to be the foreground application and the I/O-bound application, and applying an interrupt method in response to that the application determined to be the foreground application and the CPU-bound application, or the application determined to be the background application.

Abstract: Provided are a method for operating a storage driver in a container environment and a storage driver apparatus and a method for operating a storage driver according to an exemplary embodiment of the present disclosure includes: requesting downloading of an image for running a container; downloading a plurality of sub images associated with the requested image; allocating each of the plurality of downloaded sub images to an independent logical volume in a multi-layer based file system; and running a container using each of the plurality of allocated sub images.

Abstract: A file fragmentation removal method includes collecting input/output system call information of a plurality of file input/output system calls by an application of at least one target file used by an application operating on an arbitrary filesystem, generating a file range list of items comprising information on a start point, an end point, and an access count of input/output based on the input/output system call information, selecting a plurality of fragmentation target items based on the file range list and a predetermined threshold, and selectively removing fragmentation based on whether individual items of the plurality of fragmentation target items are fragmented.

Abstract: There is provided a method for an I/O (input/output) scheduling method, the method comprises: assigning a system call identifier to each of a plurality of I/O requests derived from at least one system call requested by at least one application; sorting the plurality of I/O requests in order of the system call identifier; and transferring the sorted plurality of I/O requests to a computer-readable storage medium. Accordingly, in a mobile or desktop environment in which an application that frequently interacts with the user is executed, it is possible to minimize the read delay time increased due to file fragmentation, and moreover, it is possible to improve the user experience (UX).

Abstract: In accordance with an aspect of the present disclosure, there is provided a method of controlling power efficiency of a processor based on polling I/O. The method comprises checking at every predetermined time period whether a polling count is generated by a polling I/O operation for checking for a completion in response to an I/O request in storage; when it is checked that no polling count is generated, resetting a maximum frequency of the processor to have a default value; and converting a current operation frequency of the processor based on the polling count and an I/O sensitivity of the processor, when it is checked that the polling count is generated.

Abstract: An electronic apparatus is provided. The electronic apparatus according to an embodiment includes a memory configured to store computer executable instructions, and a processor configured to, by executing the computer executable instructions, based on a request for executing a program being received and an available capacity of a first area of the memory to be allocated to the program being insufficient, swap-out page data stored in the first area to a second area of the memory, wherein the processor is further configured to swap out the page data partially or entirely based on an attribute of the page data.

Abstract: Provided are a method and apparatus for managing a page cache for multiple foreground applications. A method of managing a page cache includes identifying an application accessing to data stored in storage; allocating a page used by the application for the accessed data to a page cache; setting a page variable corresponding to a type of the identified application to the allocated page; and managing demoting of the allocated page based on the set page when the allocated page is a demoting target.

Abstract: In accordance with an aspect of the present disclosure, there is provided a method for adaptive I/O completion. The method comprises, determining whether an application is a foreground application or a background application; in response to the application determined to be the foreground application, determining whether the application is a CPU-bound application or an I/O-bound application; and applying an I/O polling method in response to that the application determined to be the foreground application and the I/O-bound application, and applying an interrupt method in response to that the application determined to be the foreground application and the CPU-bound application, or the application determined to be the background application.

Abstract: Provided are a method and an apparatus for managing a page cache in a virtualization service and a method for managing a page cache in a virtualization service according to an exemplary embodiment of the present disclosure includes: comparing a weight value of a container and a weight variable of a page possessed by a process operated by the container in the virtualization service with each other, changing the weight variable of the page based on a comparison result, and managing pages of the page cache using the changed weight variable of the page.

Abstract: A method of operating a storage device including a non-volatile memory includes: the storage device receiving from a host a first write command; determining, based on the first write command, whether first write data for the first write command is sequential data required to be written according to a write request order; writing the first write data in the non-volatile memory; and when the first write data and second write data for a second write command are sequential data, sequentially updating first mapping data including a mapping relationship between a first logical address and a first physical address for the first write data, and updating second mapping data including a mapping relationship between a second logical address and a second physical address for the second write data, according to an order in which the first write command and the second write command are received.

Abstract: In accordance with an aspect of the present disclosure, there is provided a method of controlling power efficiency of a processor based on polling I/O. The method comprises checking at every predetermined time period whether a polling count is generated by a polling I/O operation for checking for a completion in response to an I/O request in storage; when it is checked that no polling count is generated, resetting a maximum frequency of the processor to have a default value; and converting a current operation frequency of the processor based on the polling count and an I/O sensitivity of the processor, when it is checked that the polling count is generated.

Abstract: In a computer system with a hybrid memory architecture consisting of a volatile main memory and a non-volatile main memory, there are provided a segment cleaning method for a storage file system and a memory management apparatus for implementing the same, the segment cleaning method comprising: selecting a victim segment in storage; copying valid blocks in the victim segment to the volatile main memory; and moving the copied valid blocks to the non-volatile main memory. This can effectively overcome cleaning overhead, thereby improving the I/O performance of applications and increasing the lifetime of storage.

Abstract: A method for user-based application grouping in a table-top multi-user environment where a plurality of users execute applications individually comprises collecting geometric information of each window of a plurality of applications displayed on a table-top display—each window of the plurality of applications has different geometric information according to the position at which each user uses the table-top display; and processing geometric information of each window of the plurality of applications through a clustering algorithm processing unit by using the collected geometric information as a criterion for classifying the plurality of applications and grouping the processed geometric information for each user. Through grouping of applications currently executed in a table-top environment for each user, a user-specific special function such as a user-specific application history may be provided.

Abstract: Provided are a method and apparatus for managing a page cache for multiple foreground applications. A method of managing a page cache includes identifying an application accessing to data stored in storage; allocating a page used by the application for the accessed data to a page cache; setting a page variable corresponding to a type of the identified application to the allocated page; and managing demoting of the allocated page based on the set page when the allocated page is a demoting target.

Abstract: An electronic apparatus is provided. The electronic apparatus according to an embodiment includes a memory configured to store computer executable instructions, and a processor configured to, by executing the computer executable instructions, based on a request for executing a program being received and an available capacity of a first area of the memory to be allocated to the program being insufficient, swap-out page data stored in the first area to a second area of the memory, wherein the processor is further configured to swap out the page data partially or entirely based on an attribute of the page data.

Abstract: Provided are storage apparatuses for a virtualized system and methods for operating the same. A method for operating a storage apparatus having a write buffer and a memory includes receiving a write request from a virtual machine, identifying a write pattern corresponding to the received write request by comparing a write data size indicated by the write request with a predetermined threshold, and allocating the received write request differently based on the identified write pattern.

Abstract: In a computer system with a hybrid memory architecture consisting of a volatile main memory and a non-volatile main memory, there are provided a segment cleaning method for a storage file system and a memory management apparatus for implementing the same, the segment cleaning method comprising: selecting a victim segment in storage; copying valid blocks in the victim segment to the volatile main memory; and moving the copied valid blocks to the non-volatile main memory. This can effectively overcome cleaning overhead, thereby improving the I/O performance of applications and increasing the lifetime of storage.

Abstract: Provided are a method and an apparatus for managing a page cache in a virtualization service and a method for managing a page cache in a virtualization service according to an exemplary embodiment of the present disclosure includes: comparing a weight value of a container and a weight variable of a page possessed by a process operated by the container in the virtualization service with each other, changing the weight variable of the page based on a comparison result, and managing pages of the page cache using the changed weight variable of the page.

Abstract: Provided are a method for operating a storage driver in a container environment and a storage driver apparatus and a method for operating a storage driver according to an exemplary embodiment of the present disclosure includes: requesting downloading of an image for running a container; downloading a plurality of sub images associated with the requested image; allocating each of the plurality of downloaded sub images to an independent logical volume in a multi-layer based file system; and running a container using each of the plurality of allocated sub images.

Abstract: Provided are a data discard method for a file system and a memory management apparatus thereof. Specifically, the data discard method for a file system includes: unlinking an inode and a data block corresponding to a file stored in a storage from among inodes and data blocks in a file system when a kernel event of deleting the file occurs; updating state values for the unlinked inode and data block, respectively, to a bitmap block of the file system; checking bit values of all of inodes in an inode block including the updated inode from among inode blocks of the file system; and transmitting discard commands with respect to the inode block including the updated inode and the data block, respectively, to the storage if all of the inodes of the inode block are clean bits as a result of the check.