I/O stack optimization for smartphones

Abstract

The Android I/O stack consists of elaborate and mature components (SQLite, the EXT4 filesystem, interrupt-driven I/O, and NAND-based storage) whose integrated behavior is not well-orchestrated, which leaves a substantial room for an improvement. We overhauled the block I/O behavior of five filesystems (EXT4, XFS, BTRFS, NILFS, and F2FS) under each of the five different journaling modes of SQLite. We found that the most significant inefficiency originates from the fact that filesystem journals the database journaling activity; we refer to this as the JOJ (Journaling of Journal) anomaly. The JOJ overhead compounds in EXT4 when the bulky EXT4 journaling activity is triggered by an fsync() call from SQLite. We propose (i) the elimination of unnecessary metadata journaling for the filesystem, (ii) external journaling and (iii) polling-based I/O to improve the I/O performance, primarily to improve the efficiency of filesystem journaling in the SQLite environment. We examined the performance trade-offs for each combination of the five database journaling modes, five filesystems and three optimization techniques. When we applied three optimization techniques in existing Android I/O stack, the SQLite performance (inserts/sec) improved by 130%. With the F2FS filesystem, WAL journaling mode (SQLite), and the combination of our optimization efforts, we improved the SQLite performance (inserts/sec) by 300%, from 39 ins/sec to 157 ins/sec, compared to the stock Android I/O stack. © USENIX Annual Technical Conference, USENIX ATC 2013. All rights reserved.