Yoshitake Shinkai

HAMFS file system

Unixs lack of a robust and expandable file system has become a significant problem with the growth of Unix in large commercial environments. The HAMFS (highly available multi-server file system) is a cluster file system designed to address this need. HAMFS offers disk-pooling, supports off-the-shelf disks, and automatically balances file load across disks dynamically. Data residing in a disk pool is directly accessible from every node in a HAMFS cluster. As users capacity requirements grow, HAMFS provides easy disk pool expansion. Finally, HAMFS provides uniform scaling of file system performance from a single node configuration to large multi-node clusters, offering significant performance advantage over traditional file systems. For example, in short file access situations, HAMFS provide a factor of five performance improvement over NFS, and a factor of two improvement over conventional local file systems. Technologies developed for HAMFS are applied to Fujitsus file system product SafeFILE.

Software RAID Technology for cluster environments Yoshitake Shinkai, Tetsutaro Maruyama, Naomi Yoshizawa

In this paper, we present a new software RAID technology called file RAID targeted at cluster environments where nodes share files through SAN (Storage Area Network). In it the file system manages separate disks and places user data over them redundantly by itself instead of by underlying device drivers while replicating the metadata on multiple nodes. This schema results in high performance by adopting the following techniques only applicable to the file system layer such as aggressive caching, reduced recovery logging and dynamic RAID type selection based on file size. It also eliminates conventional spare disks. We implemented the file RAID feature in our cluster file system HAMFS. The measurement result demonstrates a good scalability as well as good performance even for random writes for a RAID5 file.