2014 · 100 citations · 30 references
ComputingComputer ScienceComputer SystemsComputer ArchitectureMemoryStorage SystemsMemory HierarchyMemory Hierarchy DesignMemory ManagementStorage ManagementBandwidthHigh PerformanceLog-structured StorageMain Memory OrganizationMemory Access PatternsMemory UtilizationNon-volatile Memory ManagementStorage Access Patterns
Traditional memory allocation mechanisms are inefficient for DRAM‑based storage, especially under changing access patterns, whereas a log‑structured approach can achieve 80‑90 % memory utilization with high performance. RAMCloud implements a unified log‑structured memory system for both active data in RAM and backup data on disk, using a two‑level cleaning policy that runs concurrently with normal operations and employs multiple threads to hide most cleaning costs. The two‑level cleaning policy conserves disk bandwidth and boosts performance by up to six times at high memory utilization.
Traditional memory allocation mechanisms are not suitable for new DRAM-based storage systems because they use memory inefficiently, particularly under changing access patterns. In contrast, a log-structured approach to memory management allows 80-90% memory utilization while offering high performance. The RAMCloud storage system implements a unified log-structured mechanism both for active information in memory and backup data on disk. The RAMCloud implementation of log-structured memory uses a two-level cleaning policy, which conserves disk bandwidth and improves performance up to 6× at high memory utilization. The cleaner runs concurrently with normal operations and employs multiple threads to hide most of the cost of cleaning.
30
Benchmarking cloud serving systems with YCSB
Brian F. Cooper, Adam Silberstein, Erwin Tam et al. · 2010 · 3.6K citations
Giuseppe DeCandia, Deniz Hastorun, Madan Jampani et al. · 2007 · 3.5K citations
Bigtable: a distributed storage system for structured data
Fay W. Chang, Jay B. Dean, Sanjay Ghemawat et al. · 2006 · 2K citations