sJournal: A New Design of Journaling for File Systems to Provide Crash Consistency

摘要

Maintain consistency is one of the major challenges faced by modern file systems in the presence of system crashes. File systems have evolved various techniques to provide crash consistency, in which journaling technique is one of the most important. Unfortunately, journaling introduces a write-twice problem: the write traffic is firstly written to the journal space, and latter is written back to the file system space. This problem is critical when version consistency is required in data management applications. To address this problem, we present sJournal, a smart journaling layer which can provide version consistency to the upper file systems efficiently. The key idea of sJournal is to understand the block I/O traffic issued from upper file systems, and redirect the I/O traffic between the journal space and the file system space intelligently. This includes four techniques: 1) detect the upper file system and extract the disk block allocation status, 2) identify and log all the overwrite traffic to the journal space while issuing non-overwrite traffic to the file system space directly, 3) redirect read traffic to the journal space if the target block is logged, 4) checkpoint all the logged data to the file system space at proper timing. We implemented a prototype of sJournal, and incorporated it with Ext3. Through experiments, we compared the performance of Ext3 running with ordered mode, data journal mode and sJournal, respectively. The results show that Ext3 with sJournal support can provide comparable performance to ordered journal mode, while ensuring the version consistency guaranteed in data journal mode.