File and Storage Technologies · 2012 · 108 citations · 10 references
ComputingComputer EngineeringComputer ScienceOperating SystemsStorage SystemsSystem-on-chip DesignLatency OptimizationSolid-state Drive ArchitectureSolid-state StorageFlash MemoryLatency Reduction TechniquesNand Flash MemoryRead LatencyRead Latency OptimizationStorage Performance ModelingStorage Performance OptimizationWrite Latency
In NAND flash memory, once a page program or block erase (P/E) command is issued to a NAND flash chip, the subsequent read requests have to wait until the time-consuming P/E operation to complete. Preliminary results show that the lengthy P/E operations may increase the read latency by 2x on average. As NAND flash-based SSDs enter the enterprise server storage, this increased read latency caused by the contention may significantly degrade the overall system performance. Inspired by the internal mechanism of NAND flash P/E algorithms, we propose in this paper a low-overhead P/E suspension scheme, which suspends the on-going P/E to service pending reads and resumes the suspended P/E afterwards. In our experiments, we simulate a realistic SSD model that adopts multi-chip/channel and evaluate both SLC and MLC NAND flash as storage materials of diverse performance. Our experimental results show that the proposed technique achieves a near-optimal performance gain on servicing read requests. Specifically, the read latency is reduced on average by 50.5% compared to RPS and 75.4% compared to FIFO at cost of less than 4% overhead on write requests.
10
Design tradeoffs for SSD performance
Nitin Agrawal, Vijayan Prabhakaran, Ted Wobber et al. · 2008 · 886 citations
Migrating server storage to SSDs
Dushyanth Narayanan, Eno Thereska, Austin Donnelly et al. · 2009 · 368 citations
Characterization of storage workload traces from production Windows Servers
Swaroop Kavalanekar, Bruce Worthington, Qi Zhang et al. · 2008 · 259 citations