Nikolas Ioannou

Software defined just-in-time caching in an enterprise storage system

A software defined storage environment is one in which logical storage resources and services are completely abstracted from physical storage systems. Therefore, not only can storage resources cross physical boundaries, but they can also be defined by software and provisioned automatically, for instance, by the applications that consume them. In this paper, we present a novel software defined cooperative caching (SDCC) framework that operates at the block layer and manages the placement of data in different tiers and caches that span multiple servers and storage systems in an integrated and coherent fashion. A programming interface complements the core framework by giving the applications an interface to control data organization across the storage, thereby allowing the block storage infrastructure to be software defined. The SDCC framework allows applications to actively influence the data layout while also benefitting from the system-wide knowledge and resource management capabilities of the storage system. We present an experimental study conducted using real workloads, and the results demonstrate the performance benefits gained with SDCC, as well as the potential for consolidating multiple different workloads that share the same storage server.

Autotuning Skeleton-Driven Optimizations for Transactional Worklist Applications

Skeleton or pattern-based programming allows parallel programs to be expressed as specialized instances of generic communication and computation patterns. In addition to simplifying the programming task, such well structured programs are also amenable to performance optimizations during code generation and also at runtime. In this paper, we present a new skeleton framework that transparently selects and applies performance optimizations in transactional worklist applications. Using a novel hierarchical autotuning mechanism, it dynamically selects the most suitable set of optimizations for each application and adjusts them accordingly. Our experimental results on the STAMP benchmark suite show that our skeleton autotuning framework can achieve performance improvements of up to 88 percent, with an average of 46 percent, over a baseline version for a 16-core system and up to 115 percent, with an average of 56 percent, for a 32-core system. These performance improvements match or even exceed those obtained by a static exhaustive search of the optimization space.

FlashNet: flash/network stack co-design

During the past decade, network and storage devices have undergone rapid performance improvements, delivering ultra-low latency and several Gbps of bandwidth. Nevertheless, current network and storage stacks fail to deliver this hardware performance to the applications, often due to the loss of IO efficiency from stalled CPU performance. While many efforts attempt to address this issue solely on either the network or the storage stack, achieving high-performance for networked-storage applications requires a holistic approach that considers both. In this paper, we present FlashNet, a software IO stack that unifies high-performance network properties with flash storage access and management. FlashNet builds on RDMA principles and abstractions to provide a direct, asynchronous, end-to-end data path between a client and remote flash storage. The key insight behind FlashNet is to co-design the stacks components (an RDMA controller, a flash controller, and a file system) to enable cross-stack optimizations and maximize IO efficiency. In micro-benchmarks, FlashNet improves 4kB network IOPS by 38.6% to 1.22M, decreases access latency by 43.5% to 50.4 µsecs, and prolongs the flash lifetime by 1.6--5.9× for writes. We illustrate the capabilities of FlashNet by building a Key-Value store, and porting a distributed data store that uses RDMA on it. The use of FlashNets RDMA API improves the performance of KV store by 2×, and requires minimum changes for the ported data store to access remote flash devices.