June Kim

OASIS: implementation of a cluster file system using object-based storage devices

An emerging object-based storage device (OSD) architecture facilitates the creation of self-managed, secure, and shared storage. Despite of its potential of greatly improving the scalability and performance of distributed storage systems, only high-end applications direct their attentions to OSD. Currently, it is necessary for mid/entry-levels applications to employ the OSD technology. In this paper, we present OASIS, a cluster file system using OSD, which is designed to combine the iSCSI protocol with OSD SCSI. Our experiments show that our system matches up to performance of existing systems and achieves linear scalability of performance as the number of clients increased.

Design and implementation of a security framework based on the object-based storage device standard

Recently, demands on security frameworks adopted for network-based storage mechanisms have considerably increased, as these mechanisms are appointed in important roles within industrial areas. However, there has been minimal research and development of these frameworks. In this paper, the design and implementation of a security framework, based on the Object-based Storage Device (OSD) standard [1], is presented. In the proposed security framework compared with the OSD standard, several different functionalities exist.

Design and Implementation of a File Spanning among Multiple OSDs in OASIS File System

According to the development of the object based storage device (OSD) and networking technologies, some OSD based clustering file systems, for example, the ActiveScale storage cluster of the Panasas Corp. and the Lustre file system of the Cluster File System Corp., are emerging in the marketplace. Typically, these systems connect multiple OSDs on the fast network. When a large number of OSDs are connected as a linear style configuration, a client machine stores a file in its local memory first and then flushes it into an OSD. However, the file stored temporarily in the clients memory may not be completely stored in the selected OSD because the size of the file can be bigger than that of the OSDs available space. In this paper, we propose a detailed algorithm and system structure for solving this problem occurring in the cluster file system using OSDs.

Supporting extended UNIX remove semantics in the OASIS cluster filesystem

Using the standard Object-based Storage Device, OASIS has been developed as a cluster filesystem. Like the most of existing out-of-band cluster filesystems using ODSs, the OASIS could not support the extended remove UNIX semantics to defer the remove of an inode until the uses of the inode in all client nodes are finished. This nonsupport generates the problems that it does not protect users to make use of the deleted inode and does share an inode of a deleted directory entry with a newly created entry, which is due to client nodes VFS to support the remove UNIX semantics. To resolve these problems, this paper proposes the re-designed OASIS to perform an inode deletion until its uses are finished by extending the existing lock table for cache coherence. The suggested approach can support the remove UNIX semantics in the distributed environment and easily be adopted in the existing out-of-band cluster filesystems if using their locking mechanism.