HECURA: Improving Scalability in Parallel File Systems for High End Computing

随着高端计算系统（hec）发展到数万个节点，文件I/O正在成为一个关键的性能问题。当前的并行文件系统（如PVFS2和其他）可以合理地在100个节点上分条数据，并在涉及大型对齐访问的批量传输中实现良好的性能。但是，对于小的未对齐访问、元数据操作和受一致性语义影响的访问（任何时候一个进程写入的数据被另一个进程读取），存在严重的性能限制。拟议的研究将研究可扩展的元数据操作、小的、未对齐的数据访问、通过冗余实现的可靠性以及I/O资源的管理。所采用的技术包括主动缓存和缓冲、服务器到服务器和客户端到客户端通信以及自治。为了增强可移植性和控制复杂性，建议尽可能使用中间件，并使用PVFS2文件系统，它允许很大程度的可配置性。拟议的研究旨在增强该文件系统，使其能够扩展到非常大的大小。

As high end computing systems (HECs) grow to several tens of thousands of nodes, file I/O is becoming a critical performance issue. Current parallel file systems such as PVFS2 and others, can reasonably stripe data across a hundred nodes and achieve good performance for bulk transfers involving large aligned accesses. Serious performance limits exist, however, for small unalignedaccesses, metadata operations, and accesses impacted by the consistency semantics (any time one process writes data that is read by another).The proposed research would study scalable metadata operations, small, unaligned data accesses, reliability through redundancy, and management of I/O resources. The employed techniques include active caching and buffering, server-to-server and client-to-client communication, and autonomics. To enhance portability and control complexity proposed research intend to employ middleware whenever possible, and use PVFS2 file system that allows a large degree of configurability. The proposed research intends to enhance that file system so that it will scale to very large sizes.