Mlcached: Multi-level DRAM-NAND Key-value Cache
نویسندگان
چکیده
We present Mlcached, multi-level DRAM-NAND keyvalue cache, that is designed to enable independent resource provisioning of DRAM and NAND flash memory by completely decoupling each caching layers. Mlcached utilizes DRAM for L1 cache and our new KVcache device for L2 cache. The index-integrated FTL is implemented in the KV-cache device to eliminate any inmemory indexes that prohibit the independent resource provisioning. We show that Mlcached is only 12.8% slower than a DRAM-only Web caching service in the average RTT with 80% L1 cache hit while saving twothirds of its TCO. Moreover, our model-based study shows that Mlcached can provide up to 6X lower cost or 4X lower latency at the same SLA or TCO, respectively.
منابع مشابه
ElCached: Elastic Multi-Level Key-Value Cache
Abstract Today’s cloud service providers (CSPs) use in-memory caching engines to improve application performance and server revenue. However, these caching engines exhibit poor scaling, mainly because of high DRAM cost and energy consumption. On the other hand, the increasing use of multi-tenancy requires effective and optimal resource provisioning. In this paper, we introduce ElCached, a multi...
متن کاملMemshare: a Dynamic Multi-tenant Key-value Cache
Web application performance heavily relies on the hit rate of DRAM key-value caches. Current DRAM caches statically partition memory across applications that share the cache. This results in under utilization and limits cache hit rates. We present Memshare, a DRAM key-value cache that dynamically manages memory across applications. Memshare provides a resource sharing model that guarantees rese...
متن کاملDRAM-Aware Last-Level Cache Replacement
The cost of last-level cache misses and evictions depend significantly on three major performance-related characteristics of DRAM-based main memory systems: bank-level parallelism, row buffer locality, and write-caused interference. Bank-level parallelism and row buffer locality introduce different latency costs for the processor to service misses: parallel or serial, fast or slow. Write-caused...
متن کاملDRAM Aware Last-Level-Cache Policies for Multi-core Systems
x latency DTC in two cycles. In contrast, state-of-the-art DRAM cache always reads the tags from DRAM cache that incurs high tag lookup latencies of up to 41 cycles. In summary, high DRAM cache hit latencies, increased inter-core interference, increased inter-core cache eviction, and the large application footprint of complex applications necessitates efficient policies in order to satisfy the ...
متن کاملA Memory-Disk Integrated Non-volatile Memory System with its Dual Buffering Adapter
In this paper, conventional main memory and disk storage layers are merged into a single memory layer using a combination of PRAM and NAND Flash memories, which is called as an integrated memory-disk (IM-D) non-volatile memory structure. The IM-D memory architecture consists of a dual buffering IM-D adapter, an array of SLC/MLC PRAM/Flash hybrid IM-D memory, and an associated memory management ...
متن کامل