Filters








250 Hits in 1.7 sec

The RAMCloud Storage System

John Ousterhout, Mendel Rosenblum, Stephen Rumble, Ryan Stutsman, Stephen Yang, Arjun Gopalan, Ashish Gupta, Ankita Kejriwal, Collin Lee, Behnam Montazeri, Diego Ongaro, Seo Jin Park (+1 others)
2015 ACM Transactions on Computer Systems  
Over the past 15 years, the use of DRAM in storage systems has accelerated, driven by the needs of large-scale Web applications.  ...  RAMCloud is a storage system that provides low-latency access to large-scale datasets. To achieve low latency, RAMCloud stores all data in DRAM at all times.  ...  For example, Amazon's Dynamo storage system implements eventual consistency: modified data will eventually become visible throughout the The RAMCloud Storage System 7:7 Fig. 2 .  ... 
doi:10.1145/2806887 fatcat:fg3r5yahbjhxhcor6m2w2q6bxy

Characterizing Performance and Energy-Efficiency of the RAMCloud Storage System

Yacine Taleb, Shadi Ibrahim, Gabriel Antoniu, Toni Cortes
2017 2017 IEEE 37th International Conference on Distributed Computing Systems (ICDCS)  
As the main memory capacity of clusters and clouds increases, it becomes possible to keep most of the data in the main memory. This motivates the introduction of in-memory storage systems.  ...  In this paper, by the means of experimental evaluation, we have studied the performance and energy-efficiency of RAM-Cloud -a well-known in-memory storage system.  ...  of in-memory storage systems.  ... 
doi:10.1109/icdcs.2017.51 dblp:conf/icdcs/TalebIAC17 fatcat:pa7s2k6v4zgu5oa5ldz6vqqfbi

The case for RAMCloud

John Ousterhout, Guru Parulkar, Mendel Rosenblum, Stephen M. Rumble, Eric Stratmann, Ryan Stutsman, Parag Agrawal, David Erickson, Christos Kozyrakis, Jacob Leverich, David Mazières, Subhasish Mitra (+2 others)
2011 Communications of the ACM  
the primary storage location for online information in computer systems.  ...  A new class of storage called RAMCloud will provide the storage substrate for many future applications.  ...  Second, RAMCloud must scale automatically to thousands of storage servers; applications see a single storage system independent of the actual number of storage servers.  ... 
doi:10.1145/1965724.1965751 fatcat:nmp2qlgjfvcivhx3fwegyegvuq

An Empirical Evaluation of How the Network Impacts the Performance and Energy Efficiency in RAMCloud

Yacine Taleb, Shadi Ibrahim, Gabriel Antoniu, Toni Cortes
2017 2017 17th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGRID)  
Through a study carried on RAMCloud, we focus on two settings: 1) clients are collocated within the same network as the storage servers (with Infiniband interconnects); 2) clients access the servers from  ...  This paper aims to provide empirical evidence of the impact of client's location on the performance and energy consumption of in-memory storage systems.  ...  in-memory storage system, namely RAMCloud [2] , [13] .  ... 
doi:10.1109/ccgrid.2017.127 dblp:conf/ccgrid/TalebIAC17 fatcat:sqfmdzvgcncfffylubnc6zgviy

The case for RAMClouds

John Ousterhout, Mendel Rosenblum, Stephen M. Rumble, Eric Stratmann, Ryan Stutsman, Parag Agrawal, David Erickson, Christos Kozyrakis, Jacob Leverich, David Mazières, Subhasish Mitra, Aravind Narayanan (+1 others)
2010 ACM SIGOPS Operating Systems Review  
We believe that RAMClouds can provide durable and available storage with 100-1000x the throughput of disk-based systems and 100-1000x lower access latency.  ...  This paper argues for a new approach to datacenter storage called RAMCloud, where information is kept entirely in DRAM and large-scale systems are created by aggregating the main memories of thousands  ...  RAMCloud represents a new way of organizing storage servers in such a system. There are two key attributes that differentiate a RAMCloud from other storage systems.  ... 
doi:10.1145/1713254.1713276 fatcat:vwlxzupmjncujmruqaes4bulee

Fast crash recovery in RAMCloud

Diego Ongaro, Stephen M. Rumble, Ryan Stutsman, John Ousterhout, Mendel Rosenblum
2011 Proceedings of the Twenty-Third ACM Symposium on Operating Systems Principles - SOSP '11  
RAMCloud is a DRAM-based storage system that provides inexpensive durability and availability by recovering quickly after crashes, rather than storing replicas in DRAM.  ...  RAMCloud uses both data parallelism and pipelining to speed up recovery. • Log-structured storage: RAMCloud uses techniques similar to those from log-structured file systems [21] , not just for information  ...  RAMCloud aggregates the DRAM of all these servers into a single coherent storage system.  ... 
doi:10.1145/2043556.2043560 dblp:conf/sosp/OngaroRSOR11 fatcat:iglpm5pr55eajbwylbjhpebxe4

A SURVEY ON CLOUD STORAGE – IMPACT OF STORAGE ON THE PERFORMANCE

Prapti Panigrahi .
2018 International Journal of Research in Engineering and Technology  
Selecting amongst the many available storage architectures is a very complex task as well as a very important one. The storage mechanism plays a huge role in determining its overall performance.  ...  Understanding the importance of storage mechanism and realizing that in a properly developed architecture can improve the efficiency of application by leaps and bounds.  ...  RAMCloud Traditionally, DRAM was used only for caching. RAMCloud uses an entirely different structure. Here the primary storage is the DRAM and backup is done on disks.  ... 
doi:10.15623/ijret.2018.0710007 fatcat:q54suv7n6jcanieoqwotohdl7u

Implementing linearizability at large scale and low latency

Collin Lee, Seo Jin Park, Ankita Kejriwal, Satoshi Matsushita, John Ousterhout
2015 Proceedings of the 25th Symposium on Operating Systems Principles - SOSP '15  
We have implemented RIFL in the RAMCloud storage system and used it to make basic operations such as writes and atomic increments linearizable; RIFL adds only 530 ns to the 13.5 µs base latency for durable  ...  Linearizability is the strongest form of consistency for concurrent systems, but most large-scale storage systems settle for weaker forms of consistency.  ...  The presentation in the paper benefited from comments by the anonymous conference reviewers and our shepherd, Steven Hand.  ... 
doi:10.1145/2815400.2815416 dblp:conf/sosp/LeePKMO15 fatcat:scbxjbbosrdg7jxcwirz4vrerm

Stateless Network Functions

Murad Kablan, Blake Caldwell, Richard Han, Hani Jamjoom, Eric Keller
2015 Proceedings of the 2015 ACM SIGCOMM Workshop on Hot Topics in Middleboxes and Network Function Virtualization - HotMiddlebox '15  
Our Click-based prototype integrates with RAMCloud; using NAT as an example network function, we demonstrate that we are able to create stateless network functions that maintain the desired performance  ...  Newly virtualized network functions (like firewalls, routers, and intrusion detection systems) should be easy to consume.  ...  ACKNOWLEDGEMENTS This work was funded in part by the following grants: NSF NeTS 1320389 and NSF XPS 1337399.  ... 
doi:10.1145/2785989.2785993 dblp:conf/sigcomm/KablanCHJK15 fatcat:grtdkb4xezemlbjymjjifu6kdm

Who is more reliable?

Hongyi Chen, Zhigang Sun, Bin Huang, Tao Li, Xilong Mao
2012 Proceedings of the 2012 ACM conference on CoNEXT student workshop - CoNEXT Student '12  
Traditional disk-oriented storage systems can no longer meet the high requirements of applications in latency and bandwidth, for which RAMCloud [4], was proposed to replace the disk with RAM.  ...  We consider using the memory of endusers in existing Internet to achieve a similar memory storage system.  ...  This user memory storage system as a distributed-memory aggregation storage model, just like RAMCloud, has a short data access delay and a high bandwidth.  ... 
doi:10.1145/2413247.2413273 dblp:conf/conext/ChenSHLM12 fatcat:feiob5lntjhx3f3avavwu7sb2u

Exploiting Commutativity For Practical Fast Replication [article]

Seo Jin Park, John Ousterhout
2017 arXiv   pre-print
This strategy allows most operations to complete in 1 RTT (the same as an unreplicated system). We implemented CURP in the Redis and RAMCloud storage systems.  ...  CURP transformed a non-durable Redis cache into a consistent and durable storage system with only a small performance overhead.  ...  Similar techniques are used in strongly-consistent low-latency storage systems, such as RAMCloud [16] .  ... 
arXiv:1710.09921v1 fatcat:ox5t6b2jmnfi3cy4mvczjwydt4

Improving Memory Access Performance of In-Memory Key-Value Store Using Data Prefetching Techniques [chapter]

PengFei Zhu, GuangYu Sun, Peng Wang, MingYu Chen
2015 Lecture Notes in Computer Science  
In addition, we also demonstrate the overhead of prefetching on power consumption.  ...  As the access speed to main memory is several orders faster than that to disk storage, IMKVs are usually employed for storage systems where response time is critical.  ...  In these systems, all data are kept in DRAM at all times to provide the lowest possible storage latency for different applications.  ... 
doi:10.1007/978-3-319-23216-4_1 fatcat:5d32fhzperd3xkrmo3n5lpa4oa

FluidMem: Memory as a Service for the Datacenter [article]

Blake Caldwell, Youngbin Im, Sangtae Ha, Richard Han, Eric Keller
2017 arXiv   pre-print
In this paper, we present FluidMem, a complete system to realize disaggregated memory in the datacenter.  ...  We define the requirements of Memory as a Service and build its implementation in Linux as FluidMem.  ...  Acknowledgments This material is based upon work supported by the National Science Foundation under Grant No. 1337399.  ... 
arXiv:1707.07780v1 fatcat:thnnbfklg5bmxgnwg4ngtddoly

OFC

Djob Mvondo, Mathieu Bacou, Kevin Nguetchouang, Lucien Ngale, Stéphane Pouget, Josiane Kouam, Renaud Lachaize, Jinho Hwang, Tim Wood, Daniel Hagimont, Noël De Palma, Bernabé Batchakui (+1 others)
2021 Proceedings of the Sixteenth European Conference on Computer Systems  
To mitigate this issue, we introduce OFC, a transparent, vertically and horizontally elastic in-memory caching system for FaaS platforms, distributed over the worker nodes.  ...  We build our OFC prototype based on enhancements to the OpenWhisk FaaS platform, the Swift persistent object store, and the RAM-Cloud in-memory store.  ...  agreement number 16.010402.01), the "HYDDA" project of BPI Grant, the "IDEX IRS" (COMUE UGA grant), NSF CNS-1823236, and NSF CNS-1837382.  ... 
doi:10.1145/3447786.3456239 fatcat:jdpn6y6ngbgt5bqmkhtbkojnra

Large-Scale Merging of Histograms using Distributed In-Memory Computing

Jakob Blomer, Gerardo Ganis
2015 Journal of Physics, Conference Series  
We present benchmarks from an implementation using the parallel ROOT facility (PROOF) and RAMCloud, a distributed key-value store that keeps all data in DRAM.  ...  That means, while the time to analyze data decreases linearly with the number of worker nodes, the time to merge the histograms in fact increases with the number of worker nodes.  ...  Acknowledgments We would like to thank John Ousterhout and the RAMCloud team at Stanford University for hosting one of the authors and for numerous suggestions and stimulating discussions.  ... 
doi:10.1088/1742-6596/664/9/092003 fatcat:vsghcpr6mja7jivslh5vlxldmq
« Previous Showing results 1 — 15 out of 250 results