Swap compression: resurrecting old ideas

Abstract

The performance of memory-intensive applications tends to be poor due to the high overhead added by the swapping mechanism. The same problem may be found in highly-loaded multi-programming systems where all running applications have to use the swap space in order to be able to execute at the same time.In this paper, we present a solution to these problems. The idea consists of compressing the swapped pages and keeping them in a swap cache whenever possible.The idea of a compressed swap cache was proposed a few years ago, but it did not achieve the expected results due to hardware limitations. As processors are much faster and the performance gap between processors and disk is also much bigger, we believe that now it is the right time to revisit this idea. In this paper, we present a new implementation of the compressed cache, plus some enhancements that significantly improve the performance of the swapping mechanism. A FIRST APPROACH TerminologyBefore starting to describe the compressed swap cache, we believe it is necessary to define some terms that might otherwise get mixed up.

Adaptive Cache Compression for High-Performance Processors

“…Both portions compete for the LRU page in memory, and allocating a new page is biased towards the compression cache. Cortes, et al [11] classify reads to the compression cache according to whether they were caused by swapping or prefetching, and propose optimized mechanisms to swap pages in/out. Wilson, et al [41] propose dynamically adjusting the compressed cache size using a cost/benefit analysis that compares various target sizes, and takes into account the compression cost vs. the benefit of avoiding I/Os.…”

Smaller Flight Data Recorders

“…Shared memory issues, however, have not been addressed in this system (Geva & Wiseman, 2007). Cortes, Becerra, & Cervera (2000) also investigated the implementation of the Swap compression mechanism in the Linux kernel to improve performance and reduce memory requirements. It seems natural to assume that if the compression of the swap pages which are saved in a storage device produces a significant improvement then, for similar considerations, so would the compression of the rest of the files in the storage device.…”