This paper presents a new technique for disk storage management called a log-structured file system. A logstructured file system writes all modifications to disk sequentially in a log-like structure, thereby speeding up both file writing and crash recovery. The log is the only structure on disk; it contains indexing information so that files can be read back from the log efficiently. In order to maintain large free areas on disk for fast writing, we divide the log into segments and use a segment cleaner to compress the live information from heavily fragmented segments. We present a series of simulations that demonstrate the efficiency of a simple cleaning policy based on cost and benefit. We have implemented a prototype logstructured file system called Sprite LFS; it outperforms current Unix file systems by an order of magnitude for small-file writes while matching or exceeding Unix performance for reads and large writes. Even when the overhead for cleaning is included, Sprite LFS can use 70 % of the disk bandwidth for writing, whereas Unix file systems typically can use only 5-10%. 1.

In this paper, we propose two copying garbage collection methods. These two methods copy data structures in depth-first order, while conventional method copies in breadth-first order. This modification greatly improves memory access locality during both garbage collection and computation after. Restriction on data structure representation is also relaxed because the proposed methods don't require that a data object itself indicates whether it is a pointer. For the depth-first copying, it is necessary to memorize information about non-leaf data structures so that their unprocessed elements are visited afterward. The first proposed method, the link method, links data structures that have unprocessed elements. Another method, the reservation-stack method, pushes each unprocessed element being a pointer to another structure to a stack allocated at the end of the area to which data objects are copied. Therefore, neither of methods requires extra stack space. We evaluated the performance of...