FlashTier

Abstract

The availability of high-speed solid-state storage has introduced a new tier into the storage hierarchy. Low-latency and high-IOPS solid-state drives (SSDs) cache data in front of high-capacity disks. However, most existing SSDs are designed to be a drop-in disk replacement, and hence are mismatched for use as a cache.This paper describes FlashTier, a system architecture built upon solid-state cache (SSC), a flash device with an interface designed for caching. Management software at the operating system block layer directs caching. The FlashTier design addresses three limitations of using traditional SSDs for caching. First, FlashTier provides a unified logical address space to reduce the cost of cache block management within both the OS and the SSD. Second, FlashTier provides cache consistency guarantees allowing the cached data to be used following a crash. Finally, FlashTier leverages cache behavior to silently evict data blocks during garbage collection to improve performance of the SSC.We have implemented an SSC simulator and a cache manager in Linux. In trace-based experiments, we show that FlashTier reduces address translation space by 60% and silent eviction improves performance by up to 167%. Furthermore, FlashTier can recover from the crash of a 100 GB cache in only 2.4 seconds.

ONFS: a hierarchical hybrid file system based on memory, SSD, and HDD for high performance computers

“…HyCache (Zhao and Raicu, 2013) is a user-space caching middleware that uses SSD devices to cache data in the data nodes of HDFS. Flashtier (Saxena et al, 2012) is an SSD cache that provides a unified logical address space to reduce the cost of cache block management within both operating system (OS) and SSD. Hystore (Chen et al, 2011) manages both SSDs and HDDs each as one single block device with minimal changes to OS kernels.…”

Dynamic Multi-Resolution Data Storage

“…Even though VS shares the benefits from recent advances in ISP [6,9,14,23,31,33,35,40,67,75,76,82,85,89,96] and neardata processing [2,17,20,39,48,50,63,80,84], these frameworks need the mechanisms that VS offers in order to execute approximate computing applications efficiently. And while using approximate computing in channel encoding [38,62] and memory controller [30] can achieve an effect similar to that of VS in terms of reducing data-movement overhead, VS is independent of these projects and requires no changes in hardware.…”

Flash Caching for Cloud Computing Systems

“…For example, FlashTier [SSZ12] proposed cache-specific SSD management to enhance the performance of an SSD device dedicated for caching uses, it provides unified address space by using sparse hash map from Google, along with cache consistency and silent eviction for improved performance; Previous work from Koller et al also advocated the importance of write-back caching and studied new ordered and journaled write-back policies for flash caches, in order to improve the consistency of cached dirty data [KMR + 13]. This thesis complements the previous work by further studying the performance impact of write-back caching to both storage client and server using real workloads and proposing a new cache-optimized RAID technique to improve the reliability of write-back-based flash caches.…”

“…FlashTier [SSZ12] studied a new flash device interface specialized for caching, which reduces the block management overhead by unifying the block address mappings done by the cache and device and reduces the device garbage collection overhead by silently evicting clean cache blocks.…”

“…For example, it is possible to combine the data and metadata updates in a single write, but the metadata is typically small and requires the update on a partial page. Related work [SSZ12] proposed to store the metadata in the out-of-band (OOB) area of a flash page on the device, but it requires changing the device's FTL and occupies the limited OOB area which is commonly used for important error correction. In addition to the potential slowdown, storing metadata in flash cache also reduces the size available for data caching; in our experiments, using a 120GB flash device total size, 1GB of the flash capacity needs to be reserved for metadata storage.…”