An empirical evaluation of enterprise and SATA-based transactional solid-state drives

Abstract

In most file systems, performance is usually sacrificedin exchange for crash consistency, which ensures thatdata and metadata are restored consistently in the event of asystem crash. To escape this trade-off between performance and crash consistency, recent researchers designed and implemented the transactional functionality inside Solid State Drives (SSDs). However, in order to investigate its benefit in a more realistic and standard fashion, this scheme should be re-evaluated in enterprise storage with standard interface. This paper explores the challenges and implications of atransactional SSD with extensive experiments. To evaluate thepotential benefit of transactional SSD, we design and implementthe transaction functionality in Samsung enterprise-class andSATA-based SSD (i.e., SM843TN) and name it TxSSD. We thenmodify the existing file systems (i.e., ext4 and btrfs) on topof TxSSD, making both file systems crash-consistent withoutredundant writes. We perform performance evaluation of two filesystems by using file I/O and OLTP benchmarks with a database. We also disclose and analyze the overhead of transactional functionality inside SSD. The experimental results show that TxSSD-aware file systems exhibit better performance compared to crash-consistent modes (i.e., data journaling mode of ext4 and cow mode of btrfs) but worse performance compared to weakconsistent modes (i.e., ordered mode of ext4 and nodatacow mode of btrfs).