一种基于小数据同步写的回写I／O调度器

Writeback I/O Scheduler Based on Small Synchronous Writes

小数据同步写普遍存在于各种计算机环境中,并且可以由计算机系统的不同层次软件产生,从底层操作系统一直到上层应用软件都可以生成小数据同步写请求.然而,操作系统的文件系统是以块作为最小逻辑可寻址单位,小数据写将会导致严重的写放大问题,使得系统的I/O性能大幅度降低.为了解决上述问题,提出了一种I/O调度器,并将其命名为Hitchhike.该调度器可以识别小数据写,并通过对其他数据块中的数据进行压缩,将小数据嵌入到压缩出来的空间中,从而将小数据和该数据块一起写入到磁盘上,以异步回写的方式完成小数据的同步写,不仅有效缓解了磁盘的写放大问题,也极大地提高了小数据同步写的效率.基于Linux 2.6.32的Deadline调度器实现了Hitchhike原型系统,并利用Filebench基准测试来测试调度器在吞吐量、I/O延迟等方面的性能.通过与传统I/O调度器的性能进行比较,可以发现,Hitchhike调度器能够显著地提高小数据同步写的性能高达48.6%.

Small and synchronous writes are pervasive in various environments and manifest in various levels of software stack, ranging from device drivers to application software. Given a block interface, small write can cause serious write amplifications, which can substantially degrade the overall I/O performance. To address this issue, this paper presents a block I/O scheduler, named Hitchhike. Hitchhike is able to identify small writes, and embed them into other data blocks through data compression. With Hitchhike, a writeback buffer for small synchronous writes can be enabled, not only removing the write amplification, but also dramatically improving the performance of small synchronous writes. Hitchhike is implemented based on the Deadline I/O schedulers in Linux 2.6.32, and evaluated by running Filebench benchmark. Testing results show that compared to traditional approaches, Hitchhike can significantly improve the performance of synchronous small writes up to 48.6%.