High Performance Data Persistence in Non-Volatile Memory for Resilient High Performance Computing
نویسندگان
چکیده
Resilience is a major design goal for HPC. Checkpoint is the most common method to enable resilient HPC. Checkpoint periodically saves critical data objects to non-volatile storage to enable data persistence. However, using checkpoint, we face dilemmas between resilience, recomputation and checkpoint cost. e reason that accounts for the dilemmas is the cost of data copying inherent in checkpoint. In this paper we explore how to build resilient HPC with non-volatile memory (NVM) as main memory and address the dilemmas. We introduce a variety of optimization techniques that leverage high performance and non-volatility of NVM to enable high performance data persistence for data objects in applications. With NVM we avoid data copying; we optimize cache ushing needed to ensure consistency between caches and NVM. We demonstrate that using NVM is feasible to establish data persistence frequently with small overhead (4.4% on average) to achieve highly resilient HPC and minimize recomputation.
منابع مشابه
Container-Based Virtualization for Byte-Addressable NVM
Container based virtualization is rapidly growing in popularity for cloud deployments and applications as a virtualization alternative due to the ease of deployment and high-performance. Emerging byte-addressable, non-volatile memories, commonly called Storage Class Memory or SCM, technologies are promising both byteaddressability and persistence near DRAM speeds operating on the main memory bu...
متن کاملPerformance Evaluation and Modeling of HPC I/O on Non-Volatile Memory
HPC applications pose high demands on I/O performance and storage capability. The emerging non-volatile memory (NVM) techniques offer low-latency, high bandwidth, and persistence for HPC applications. However, the existing I/O stack are designed and optimized based on an assumption of disk-based storage. To effectively use NVM, we must reexamine the existing high performance computing (HPC) I/O...
متن کاملWrAP: Write Aside Persistence for Storage Class Memory in High Performance Computing
Many I/O-intensive High Performance Computing applications like Map Reduce and database systems are incorporating in-memory computing technology to overcome traditional storage bandwidth bottlenecks. The volatile nature of DRAM makes these systems vulnerable to system crashes. Software based Write Aside Persistence is presented that provides atomic durability and consistency for persistent, byt...
متن کاملUStore: STT-MRAM Based Light-Weight User-Level Storage for Enhancing Performance of Accessing Persistent Data
Traditionally, in computer systems, file I/O has been a big performance bottleneck for I/O intensive applications. The recent advent of non-volatile byte-addressable memory (NVM) technologies such as STTMRAM and PCM, provides a chance to store persistent data with a high performance close to DRAM’s. However, as the location of the persistent storage device gets closer to the CPU, the system sof...
متن کاملProcrastination Beats Prevention: Timely Sufficient Persistence for Efficient Crash Resilience
Preserving the integrity of application data across updates in the presence of failure is an essential function of computing systems, and byte-addressable non-volatile memory (NVM) broadens the range of fault-tolerance strategies that implement it. NVM invites database systems to manipulate durable data directly via load and store instructions, but overheads due to the widely used mechanisms th...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- CoRR
دوره abs/1705.00264 شماره
صفحات -
تاریخ انتشار 2017