David Cheriton | Searcharxiv

arXiv2020

The TRaCaR Ratio: Selecting the Right Storage Technology for Active Dataset-Serving Databases

Main memory database systems aim to provide users with low latency and high throughput access to data. Most data resides in secondary storage, which is limited by the access speed of the technology. For hot content, data resides in DRAM, which has become increasingly expensive as datasets grow in size and access demand. With the emergence of low-latency storage solutions such as Flash and Intel's 3D XPoint (3DXP), there is an opportunity for these systems to give users high Quality-of-Service while reducing the cost for providers. To achieve high performance, providers must provision the server hosts for these datasets with the proper amount of DRAM and secondary storage, as well as selecting a storage technology. The growth of capacity and transaction load overtime makes it expensive to flip back-and-forth between different storage technologies and memory-storage combinations. Servers set up for one storage technology must now be reconfigured, repartitioned, and potentially replaced altogether. As more low-latency storage solutions become available, how does one decide on the right memory-storage combination, as well as selecting a storage technology, given a predicted trend in dataset growth and offered load? In this paper, we describe and make the case for using the TRaCaR ratio - the transaction rate divided by the storage capacity needed for a workload - for allowing providers to choose the most cost-effective memory-storage combination and storage technology given their predicted dataset trend and load requirement. We explore how the TRaCaR ratio can be used with 3DXP and Flash with a highly-zipfian b-tree database, and discuss potential research directions that can leverage the ratio.

cs.DC↗

arXiv2007

The Case for Redundant Arrays of Internet Links (RAIL)

It is well-known that wide-area networks face today several performance and reliability problems. In this work, we propose to solve these problems by connecting two or more local-area networks together via a Redundant Array of Internet Links (or RAIL) and by proactively replicating each packet over these links. In that sense, RAIL is for networks what RAID (Redundant Array of Inexpensive Disks) was for disks. In this paper, we describe the RAIL approach, present our prototype (called the RAILedge), and evaluate its performance. First, we demonstrate that using multiple Internet links significantly improves the end-to-end performance in terms of network-level as well as application-level metrics for Voice-over-IP and TCP. Second, we show that a delay padding mechanism is needed to complement RAIL when there is significant delay disparity between the paths. Third, we show that two paths provide most of the benefit, if carefully managed. Finally, we discuss a RAIL-network architecture, where RAILedges make use of path redundancy, route control and application-specific mechanisms, to improve WAN performance.

cs.NI↗