Abstract: A workload-aware distributed data processing apparatus and method for processing large data based on hardware acceleration are provided. The data processing apparatus includes a memory buffer including partitions. The data processing apparatus further includes a partition unit configured to distribute a mapping result to the partitions based on a partition proportion scheme. The data processing apparatus further includes a reduce node configured to receive content of a corresponding one of the partitions, and perform a reduction operation on the content to generate a reduce result.

Abstract: Provided are an interrupt on/off management apparatus and method for a multi-core processor having a plurality of central processing unit (CPU) cores. The interrupt on/off management apparatus manages the multi-core processor such that at least one of two or more CPU cores included in a target CPU set can execute an urgent interrupt. For example, the interrupt on/off management apparatus controls the movement of each CPU core from a critical section to a non-critical section such that at least one of the CPU cores is located in the non-critical section. The critical section may include an interrupt-disabled section or a kernel non-preemptible section, and the non-critical section may include an interrupt-enabled section or include both of the interrupt-enabled section and a kernel preemptible section.

Abstract: A distributed storage management apparatus includes a monitoring unit configured to monitor a request pattern of each storage node of a plurality of storage nodes configured to distributively store data and at least one replica of the data; a group setting unit configured to receive a request and classify the plurality of storage nodes into a safe group and an unsafe group based on the monitored request pattern of each storage node; and a request transfer unit configured to transfer the received request to the safe group.

Abstract: A method includes determining a size of a recommended spare memory space of each of one or more storage nodes based on a state of the storage nodes, and adjusting a spare memory space of each of the storage nodes based on the size of the recommended spare memory space.

Abstract: A wear management apparatus and a wear management method of a storage system including storage nodes are provided. The wear management apparatus includes a monitor unit configured to collect status information about each of the storage nodes. The wear management apparatus further includes a wear management unit configured to establish a wear progress model with respect to the storage nodes based on the status information, and control a wear acceleration index of each of the storage nodes based on the wear progress model and a wear management policy.

Abstract: Provided is a parallel I/O computing apparatus that includes a plurality of computing devices that may have different response characteristics depending on a number of parallel I/Os that are processed by the computing devices. The computing apparatus also includes an I/O dispatcher that distributes a different number of I/Os to one or more of the computing devices based on characteristics of the computing devices.

Abstract: A workload-aware distributed data processing apparatus and method for processing large data based on hardware acceleration are provided. The data processing apparatus includes a memory buffer including partitions. The data processing apparatus further includes a partition unit configured to distribute a mapping result to the partitions based on a partition proportion scheme. The data processing apparatus further includes a reduce node configured to receive content of a corresponding one of the partitions, and perform a reduction operation on the content to generate a reduce result.

Abstract: A distributed data processing apparatus and method through hardware acceleration are provided. The data processing apparatus includes a mapping node including mapping units configured to process input data in parallel to generate and output mapping results. The data processing apparatus further includes a shuffle node including shuffle units and a memory buffer, the shuffle units configured to process the mapping results output from the mapping units in parallel to generate and output shuffle results, and the shuffle node configured to write the shuffle results output from the shuffle units in the memory buffer. The data processing apparatus further includes a merge node including merge units configured to merge the shuffle results written in the memory buffer to generate merging results.

Abstract: A distributed storage managing apparatus id provided. The distributed storage managing apparatus includes a detector configured to detect a busy storage node having a latency element from among a plurality of storage nodes that distributively store data using a plurality of replicas, and a controller configured to transfer a request associated with data reading or data writing to storage nodes other than the detected busy storage node.

Abstract: A distributed storage management apparatus includes a monitoring unit configured to monitor a request pattern of each storage node of a plurality of storage nodes configured to distributively store data and at least one replica of the data; a group setting unit configured to receive a request and classify the plurality of storage nodes into a safe group and an unsafe group based on the monitored request pattern of each storage node; and a request transfer unit configured to transfer the received request to the safe group.

Abstract: A virtualization apparatus is provided. The virtualization apparatus includes a plurality of virtual machines (VMs), a process scheduler configured to schedule processes to be executed on the respective virtual machines, a virtual machine monitor (VMM) configured to provide each of the virtual machine with a virtualized execution environment, a virtual machine scheduler configured to schedule the virtual machines to run in the virtual machine monitor, and a synchronization unit configured to synchronize a process schedule time which is scheduled by the process scheduler and a virtual machine schedule time which is scheduled by the virtual machine scheduler, or to change the virtual machine schedule time in consideration of the process schedule time.

Abstract: Provided is a memory management method, and an apparatus to perform the method, which achieves a shortened user waiting time in consideration of system performance. The method includes acquiring a deallocation unit used to deallocate an allocated memory area according to at least one attribute, and deallocating the allocated memory area using the deallocation unit.

Abstract: Provided are an interrupt on/off management apparatus and method for a multi-core processor having a plurality of central processing unit (CPU) cores. The interrupt on/off management apparatus manages the multi-core processor such that at least one of two or more CPU cores included in a target CPU set can execute an urgent interrupt. For example, the interrupt on/off management apparatus controls the movement of each CPU core from a critical section to a non-critical section such that at least one of the CPU cores is located in the non-critical section. The critical section may include an interrupt-disabled section or a kernel non-preemptible section, and the non-critical section may include an interrupt-enabled section or include both of the interrupt-enabled section and a kernel preemptible section.

Abstract: There is provided a method of interrupt scheduling. The method comprises: without allowing a target process woken up when an interrupt occurs to enter into a ready queue, directly comparing the priority of the woken-up target process with that of a current process performed before the occurrence of the interrupt, and executing a rescheduling in accordance with the compared result; and performing direct context switching with respect to the current process into the target process in accordance with whether or not the rescheduling is executed. Accordingly, in the method of interrupt scheduling, the preemption latency caused by the interrupt in the operating system of the computer system can be minimized by omitting the process of allowing the woken-up target process to enter into the ready queue and the process of selecting a process with the highest priority on the ready queue.