ACM Transactions on

Storage (TOS)

Latest Articles

Application Crash Consistency and Performance with CCFS

Recent research has shown that applications often incorrectly implement crash consistency. We... (more)

Redundancy Does Not Imply Fault Tolerance: Analysis of Distributed Storage Reactions to File-System Faults

We analyze how modern distributed storage systems behave in the presence of file-system faults such as data corruption and read and write errors. We characterize eight popular distributed storage systems and uncover numerous problems related to file-system fault tolerance. We find that modern distributed systems do not consistently use redundancy... (more)

vNFS: Maximizing NFS Performance with Compounds and Vectorized I/O

Modern systems use networks extensively, accessing both services and storage across local and remote networks. Latency is a key performance challenge, and packing multiple small operations into fewer large ones is an effective way to amortize that cost, especially after years of significant improvement in bandwidth but not latency. To this end, the... (more)

Efficient Free Space Reclamation in WAFL

NetApp®WAFL® is a transactional file system that uses the copy-on-write mechanism to support fast write performance and efficient snapshot creation. However, copy-on-write increases the demand on the file system to find free blocks quickly, which makes rapid free space reclamation essential. Inability to find free blocks quickly may... (more)

Pannier: Design and Analysis of a Container-Based Flash Cache for Compound Objects

Classic caching algorithms leverage recency, access count, and/or other properties of cached blocks at per-block granularity. However, for media such as flash which have performance and wear penalties for small overwrites, implementing cache policies at a larger granularity is beneficial. Recent research has focused on buffering small blocks and... (more)

Efficient and Available In-Memory KV-Store with Hybrid Erasure Coding and Replication

In-memory key/value store (KV-store) is a key building block for many systems like databases and large websites. Two key requirements for such systems... (more)

Systematic Erasure Codes with Optimal Repair Bandwidth and Storage

Erasure codes are widely used in distributed storage systems to prevent data loss. Traditional codes suffer from a typical repair-bandwidth problem in... (more)

Hybris: Robust Hybrid Cloud Storage

Besides well-known benefits, commodity cloud storage also raises concerns that include security, reliability, and consistency. We present Hybris key-value store, the first robust hybrid cloud storage system, aiming at addressing these concerns leveraging both private and public cloud resources. Hybris robustly replicates metadata on trusted private... (more)


  • CFP - Special Issue on NVM and Storage (in detail)

  • TOS Editor-in-Chief featured in "People of ACM"
    Sam H. Noh is Editor-in-Chief of ACM Transactions on Storage (TOS) - featured in the periodic series "People of ACM", full article available here
    November 01, 2016

  • ACM Transaction on Storage (TOS) welcomes Sam H. Noh as its new Editor-in-Chief for a 3-year term, effective August 1, 2016.
    Sam H. Noh is a professor and Head of the School of the Electrical and Computer Engineering School at UNIST (Ulsan National Institute of Science and Technology) in Ulsan, Korea and a leader in the use of new memory technology such as flash memory and non-volatile memory in storage.
    - August 01, 2016

Forthcoming Articles
GDS-LC: A Latency and Cost Aware Client Caching for Cloud Storage

Successfully integrating cloud storage as a primary storage layer in the I/O stack is highly challenging due to the two inherent critical issues  the high latency of cloud I/Os and the unconventional pricing model of cloud storage. Caching is a crucial technology to minimize the latency and price of cloud I/Os. Unfortunately, the current cloud caching schemes are designed by adopting miss reduction as the sole objective, while ignoring the fact that various cache misses could have distinct actual effects in term of latency and monetary cost. In this paper, we present a cost-aware caching scheme specifically designed for cloud storage, called GDS-LC. The proposed scheme offers a comprehensive cache design by considering not only the access locality but also the associated latency and price. With GDS-LC, we can effectively filter out the high-latency and high-price cloud I/Os and thus successfully reshape the cloud I/O streams to the desired low-latency and low-cost pattern. We have built a prototype to emulate a typical cloud client cache and evaluate the GDS-LC scheme with Amazon Simple Storage Services (S3) in three different scenarios, local cloud, Internet cloud, and heterogeneous cloud. Our experimental results show very promising results.

CosaFS: A Cooperative Shingle-aware File System

In this paper, we design and implement a cooperative shingle-aware file system, called CosaFS, on heterogeneous storage devices that mix solid-state drives (SSDs) and shingled magnetic recording (SMR) technology to improve the overall performance of storage systems. The basic idea of CosaFS is to classify objects as hot or cold objects based on a proposed Lookahead with Recency Weight (LRW) scheme. If an object is identified as a hot (small) object, it will be served by SSD. Otherwise, cold (large) objects are stored on SMR. For an SMR, large objects can be accessed in large sequential blocks, rendering the performance of their accesses comparable with that of accessing the same large sequential blocks as if they were stored on a hard drive. Small objects, such as inodes and directories, are stored on the SSD where seeks for such objects are nearly free. With thorough empirical studies, we demonstrate that CosaFS, as a cooperative shingle-aware file system, with meta-data separation and cache-assistance is a very effective way to handle the disk-based data demanded by the shingled writes, and outperforms the device- and host-side shingle-aware file systems in terms of throughput, IOPS, and access latency as well.

TinyLFU: A Highly Efficient Cache Admission Policy

This paper proposes to use a frequency based cache admission policy in order to boost the effectiveness of caches subject to skewed access distributions. Given a newly accessed item and an eviction candidate from the cache, our scheme decides, based on the recent access history, whether it is worth admitting the new item into the cache at the expense of the eviction candidate. Realizing this concept is enabled through a novel approximate LFU structure called TinyLFU, which maintains an approximate representation of the access frequency of a large sample of recently accessed items. TinyLFU is very compact and light-weight as it builds upon Bloom filter theory. We study the properties of TinyLFU through simulations of both synthetic workloads as well as multiple real traces from several sources. These simulations demonstrate the performance boost obtained by enhancing various replacement policies with the TinyLFU eviction policy. Also, a new combined replacement and eviction policy scheme nicknamed W-TinyLFU is presented. W-TinyLFU is demonstrated to obtain equal or better hit-ratios than other state of the art replacement policies on these traces. It is the only scheme to obtain such good results on all traces.

Optimal Repair Layering for Erasure-Coded Data Centers: From Theory to Practice

Repair performance in hierarchical data centers is often bottlenecked by cross-rack network transfer. Recent theoretical results show that the cross-rack repair traffic can be minimized through repair layering, whose idea is to partition a repair operation into inner-rack and cross-rack layers. However, how repair layering should be implemented and deployed in practice remains an open issue. In this paper, we address this issue by proposing a practical repair layering framework called DoubleR. We design two families of practical double regenerating codes (DRC), which not only minimize the cross-rack repair traffic, but also have several practical properties that improve state-of-the-art regenerating codes. We implement and deploy DoubleR atop Hadoop Distributed File System (HDFS), and show that DoubleR maintains the theoretical guarantees of DRC and improves the repair performance of regenerating codes in both node recovery and degraded read operations.

Client-side Journaling for Durable Shared Storage

Hardware consolidation in the datacenter often leads to scalability bottlenecks from heavy utilization of critical resources, such as the storage and network bandwidth. Host-side caching on durable media is already applied at block level to reduce the storage backend load, but has received criticism for added overhead, restricted sharing, and possible data loss at client crash. We introduce a journal to the kernel-level client of an object-based distributed filesystem in order to improve durability at high I/O performance and reduced shared resource utilization. Storage virtualization at the file interface achieves clear consistency semantics across data and metadata, supports native file sharing among clients, and provides flexible configuration of durable data staging at the host. Over a prototype that we have implemented, we experimentally quantify the performance and efficiency of the proposed Arion system in comparison to a production system. We run microbenchmarks and application-level workloads over a local cluster and a public cloud. We demonstrate reduced latency by 60% and improved performance up to 150% at reduced server network and disk bandwidth by 41% and 77%, respectively. The performance improvement reaches 92% for 16 relational databases as clients, and gets as high as 11.3x with 2 key-value stores as clients.

GCMix: An Efficient Data Protection Scheme Against the Paired Page Interference

In multi-level cell (MLC) NAND flash memory, two logical pages are overlapped on a single physical page. Even after a logical page is programmed, the data can be corrupted if the programming of the coexisting logical page is interrupted. This phenomenon is called paired page interference. This paper proposes a novel software technique to deal with the paired page interference without any additional hardware or extra page write. The proposed technique utilizes valid pages in the victim block during garbage collection (GC) as the backup against the interference, and pairs them with incoming pages written by the host. This approach eliminates undesirable page copy to backup pages against the interference. However, such a strategy has an adverse effect on the hot/cold separation policy, which is essential to improve the efficiency of GC. To limit the downside, we devise a metric to estimate the benefit of GCMix on-the-fly so that GCMix can be adaptively utilized only when the benefit outweighs the overhead. Evaluations using synthetic and real workloads show GCMix can effectively deal with the paired page interference, reducing the write amplification factor by up to 17.3% compared to the traditional technique while providing comparable I/O performance.

clfB-tree: Cacheline Friendly Persistent B-tree for NVRAM

Emerging byte-addressable non-volatile memory (NVRAM) is expected to replace block device storages as an alternative low latency persistent storage device. If NVRAM is used as a persistent storage device, a cache line instead of a disk page will be the unit of data transfer, consistency, and durability. In this work, we design and develop clfB-tree - a B-tree structure whose tree node fits in a single cache line. We employ existing write combining store buffer and restricted transactional memory (RTM) to provide a failure-atomic cache line write operation. Using the failure-atomic cache line write operations, we atomically update a clfB-tree node via a single cache line flush instruction without major changes in hardware. However, there exist many processors that do not provide SW interface for transactional memory. For those processors, our proposed clfB-tree achieves atomicity and consistency via in-place update, which requires maximum four cache line flushes. We evaluate the performance of clfB-tree on an NVRAM emulation board with ARM Cortex A-9 processor and a workstation that has Intel Xeon E7-4809 v3 processor. Our experimental results show clfB-tree outperforms wB-tree and CDDS B-tree by a large margin in terms of both insertion and search performance

Tiny-Tail Flash: Near-Perfect Elimination of Garbage Collection Tail Latencies in NAND SSDs

Flash storage has become the mainstream destination for storage users. However, SSDs do not always deliver the performance that users expect. The core culprit of flash performance instability is the well-known garbage collection (GC) process, which causes long delays as the SSD cannot serve (blocks) incoming I/Os, which then induces the long tail latency problem. We present ttFlash as a solution to this problem. ttFlash is a tiny-tail flash drive (SSD) that eliminates GC-induced tail latencies by circumventing GC-blocked I/Os with four novel strategies: plane-blocking GC, rotating GC, GC-tolerant read, and GC-tolerant flush. These four strategies leverage the timely combination of modern SSD internal technologies such as powerful controller, parity-based redundancies (RAIN), and capacitor-backed RAM. Our strategies are dependent on the use of intra-plane copyback operations. Through an extensive evaluation, we show that ttFlash comes significantly close to a no-GC scenario. Specifically, between 9999.99th percentiles, ttFlash is only 1.0 to 2.6x slower than the no-GC case, while a base approach suffers from 5138ms GC-induced slowdowns.

Challenges and Solutions for Tracing Storage Systems: A Case Study with Spectrum Scale

IBM Spectrum Scale's parallel file system General Parallel File System (GPFS) has a 20-year development history with over 100 contributing developers. Its ability to support strict POSIX semantics across more than 10K clients leads to a complex design with intricate interactions between the cluster nodes. Tracing has proven to be a vital tool to understand the behavior and the anomalies of such a complex software product. However, the necessary trace information is often buried in hundreds of gigabytes of byproduct trace records. Further, the overhead of tracing can significantly impact running applications and file system performance, limiting the use of tracing in a production system. In this article, we discuss the evolution of the mature and highly scalable GPFS tracing tool and describe the process of designing GPFS' new tracing interface, FlexTrace, which allows developers and users to accurately specify what to trace for the problem they are trying to solve. We evaluate our methodology and prototype, demonstrating that the proposed approach has negligible overhead even under intensive I/O workloads.

Modeling Drive-Managed SMR Performance

Accurately modeling drive-managed SMR disks is a challenge, requiring an array of approaches including both existing disk modeling techniques as well as new techniques for inferring internal translation layer algorithms. In this work we present the first predictive simulation model of a generally-available drive-managed SMR disk. Despite the use of unknown proprietary algorithms in this device, our model that is derived from external measurements is able to predict mean latency within a few percent, and with an RMS cumulative latency error of 25% or less for most workloads tested. These variations, although not small, are in most cases less than three times the drive-to-drive variation seen among seemingly identical drives.

hfplayer: Scalable Reply for Intensive Block I/O Workloads

We introduce new methods to replay intensive block I/O workloads more accurately. These methods canbe used to reproduce realistic workloads for benchmarking, performance validation, and tuning of a high-performance block storage device/system. In this paper, we study several sources in the stock operating system that introduce uncertainty in the workload replay. Based on the remedies of these findings, we design and develop a new replay tool called hfplayer that replay intensive block I/O workloads in a similar unscaled environment with more accuracy. To replay a given workload trace in a scaled environment with faster storage or host server, the dependency between I/O requests becomes crucial since the timing and ordering of I/O requests is expected to change according to these dependencies. Therefore, we propose a heuristic way of speculating I/O dependencies in a block I/O trace. Using the generated dependency graph, hfplayer tries to propagate I/O related performance gains appropriately along the I/O dependency chains and mimics original application behavior when it executes in a scaled environment. We evaluate hfplayer with a wide range of workloads using several accuracy metrics and find that it produces better accuracy when compared with other replay approaches.

HiNFS: A Persistent Memory File System with both Buffering and Direct-Access

Persistent memory provides data persistence at main memory with emerging non-volatile main memories (NVMMs). Recent persistent memory file systems aggressively use direct access, which directly copy data between user buffer and the storage layer, to avoid the double-copy overheads through the OS page cache. However, we observe they all suffer from slow writes due to NVMMs asymmetric read-write performance and much slower performance than DRAM. In this paper, we propose HiNFS, a high performance file system for non-volatile main memory, to combine both buffering and direct access for fine-grained file system operations. HiNFS uses an NVMM-aware Write Buffer to buffer the lazy-persistent file writes in DRAM, while performing direct access to NVMM for eager- persistent file writes. It directly reads file data from both DRAM and NVMM, by ensuring read consistency with a combination of the DRAM Block Index and Cacheline Bitmap to track the latest data between DRAM and NVMM. HiNFS also employs a Buffer Benefit Model to identify the eager-persistent file writes before issuing I/Os. Evaluations show that HiNFS significantly improves throughput by up to 184% and reduces execution time by up to 64% comparing with state-of-the-art persistent memory file systems PMFS and EXT4-DAX.

SUPA: A Single Unified Read-Write Buffer and Pattern-Change-Aware FTL for the High Performance of Multi-Channel SSD

To design write buffer and FTL for SSD, previous studies have tried to increase overall performance by parallel I/O and garbage collection reduction. Recent works have proposed pattern-based management, which uses the request size and read- or write-intensiveness to apply different policies to each type of data. However, the locations of read and write requests are closely related, and the pattern of each type of data can be changed. In this work, we propose SUPA, a single unified read-write buffer and pattern-change-aware FTL on multi-channel SSD architecture. To increase both read and write hit ratios on the buffer based on locality, we use a single unified read-write buffer for both clean and dirty blocks. To handle pattern-changed blocks, we add a pattern handler between the buffer and the FTL. To reduce policy switching overhead for pattern-changed data, if pattern change is detected, pattern handler saves the corresponding data to the two locations handled by different policies respectively. In total, our evaluations show that SUPA can get up to 2.0 and 3.9 times less read and write latency, respectively, without loss of lifetime.

Workload Characterization for Enterprise Disc Drives

Abstract  The paper presents an analysis of drive workloads from enterprise storage systems. The drive workloads are obtained from field return units from a cross-section of enterprise storage system vendors and thus provides a view of the workload characteristics over a wide spectrum of end-user applications. The workload parameters that have been characterized include transfer lengths, access patterns, locality and throughput. The study shows that reads are the dominant workload accounting for 80% of the accesses to the drive. Writes are dominated by short block random accesses while reads range from random to highly sequential. A trend analysis over the period 2010-2014 shows that the workload has remained fairly constant even as the capacities of the drives shipped has steadily increased. The study shows that the data stored on disk drives is relatively cold  on average less than 4% of the drive capacity is accessed in a given 2 hour interval.

Building Efficient Key-Value Stores via a Light-weight Compaction Tree

Log-Structure Merge tree (LSM-tree) has been one of the mainstream indexes in key-value systems supporting a variety of write-intensive Internet applications in todays data centers. However, the performance of LSM-tree is seriously hampered by constantly occurring compaction procedures, which incur significant write amplification and degrade the write throughput. To alleviate the performance degradation caused by compactions, we introduce a light-weight compaction tree (LWC-tree), a variant of LSM-tree index optimized for minimizing the write amplification and maximizing the system throughput. The light-weight compaction drastically decreases write amplification by appending data in a table and only merging the metadata that has much smaller size. We have implemented three key-value LWC-stores based on the LWC-tree on different storage mediums. The LWC-store is particularly optimized for SMR drives as it eliminates the multiplicative I/O amplification from both LSM-trees and SMR drives. Due to the light-weight compaction procedure, LWC-store reduces the write amplification by a factor of up to 5× compared to the popular LevelDB key-value store. Moreover, the random write throughput of the LWC-tree on SMR drives is significantly improved by 467% even compared with LevelDB on conventional HDDs. Furthermore, LWC-tree has wide applicability and delivers impressive performance improvement in various conditions.

Ouroboros Wear-Leveling for NVRAM Using Hierarchical Block Migration

Emerging non-volatile RAM (NVRAM) have a limit on the number of writes that can be made to any cell. This motivates the need for wear-leveling to distribute the writes evenly among the cells. Unlike NAND Flash, cells in NVRAM can be rewritten without erasing the entire containing block, avoiding the issues of garbage collection, motivating alternate approaches to the problem. In this paper, we propose a hierarchical wear-leveling model called Ouroboros Wear-leveling. Ouroboros uses a two-level strategy whereby frequent low-cost intra-region wear-leveling at small granularity is combined with inter-region wear-leveling at a larger time interval and granularity. Ouroboros is a hybrid migration scheme that exploits correct demand predictions in making better wear-leveling decisions, while using randomization to avoid attacks by deterministic access patterns. We also propose a way to optimize wear-leveling parameters to meet a target smoothness level under limited time and space overhead constraints for different memory architectures and trace characteristics. Several experiments are performed on synthetically-generated memory traces with special characteristics, block-level storage traces, and memory-line-level memory traces. The results show that Ouroboros Wear-leveling can distribute writes smoothly across the whole NVRAM with up to 0.2% space overhead and 0.52% time overhead for a 512GB memory.

Introduction to the Special Issue on USENIX FAST 2017

Experience from Two Years of Visualizing Flash with SSDPlayer

Data visualization is a thriving field of computer science, with widespread impact on diverse scientific disciplines, from medicine and meteorology to visual data mining. Advances in large scale storage systems, as well as low level storage technology, played a significant role in accelerating the applicability and adoption of modern visualization techniques. Ironically, the cobblers children have no shoes: researchers who wish to analyze storage systems and devices are usually limited to a variety of static histograms and basic displays. The dynamic nature of data movement on flash has motivated the introduction of SSDPlayer, a graphical tool for visualizing the various processes that cause data movement on SSDs. In 2015, we used the initial version of SSDPlayer to demonstrate how visualization can assist researchers and developers in their understanding of modern, complex flash-based systems.While we continued to use SSDPlayer for analysis purposes, we found it extremely useful for education and presentation purposes as well. In this paper, we describe our experience from two years of using, sharing, and extending SSDPlayer, and how similar techniques can further advance storage systems research and education.

Introduction to the Special Issue on MSST 2017


Publication Years 2005-2017
Publication Count 229
Citation Count 1584
Available for Download 229
Downloads (6 weeks) 1656
Downloads (12 Months) 13806
Downloads (cumulative) 148061
Average downloads per article 647
Average citations per article 7
First Name Last Name Award
Sarita Adve ACM Fellows (2010)
Emery David Berger ACM Senior Member (2010)
Surendar Chandra ACM Senior Member (2009)
Alok Choudhary ACM Fellows (2009)
Deborah Estrin ACM Athena Lecturer Award (2006)
ACM Fellows (2000)
Jason Flinn ACM Fellows (2016)
Armando Fox ACM Karl V. Karlstrom Outstanding Educator Award (2015)
ACM Distinguished Member (2011)
ACM Senior Member (2009)
Gregory Ganger ACM Distinguished Member (2007)
Garth A Gibson ACM Fellows (2012)
ACM Doctoral Dissertation Award
Series Winner (1991)
Ramesh Govindan ACM Fellows (2011)
Ragib Hasan ACM Senior Member (2015)
John Heidemann ACM Senior Member (2007)
Tei-Wei Kuo ACM Fellows (2015)
Kai Li ACM Fellows (1998)
Ming Li ACM Fellows (2006)
Dahlia Malkhi ACM Fellows (2011)
Ethan L Miller ACM Distinguished Member (2013)
Walid Najjar ACM Distinguished Member (2015)
ACM Senior Member (2014)
Michael Reiter ACM Fellows (2008)
Stefan Savage ACM Prize in Computing (2015)
ACM Fellows (2010)
Steven Scott ACM Fellows (2012)
Kenneth C Sevcik ACM Fellows (1997)
Anand Sivasubramaniam ACM Distinguished Member (2010)
ACM Senior Member (2009)
Chandramohan A Thekkath ACM Fellows (2009)
Gene Tsudik ACM Fellows (2014)
ACM Senior Member (2013)
Amin Vahdat ACM Fellows (2011)
David Wagner ACM Doctoral Dissertation Award
Honorable Mention (2001) ACM Doctoral Dissertation Award
Honorable Mention (2001)
Randy Wang ACM Eugene L. Lawler Award for Humanitarian Contributions within Computer Science and Informatics (2007)
Marianne Winslett ACM Fellows (2006)
Tao Xie ACM Distinguished Member (2015)
ACM Senior Member (2011)
Philip S Yu ACM Fellows (1997)
Demetris Zeinalipour ACM Senior Member (2016)
Yuanyuan Zhou ACM Fellows (2013)
ACM Distinguished Member (2011)
Yuanyuan Zhou ACM Fellows (2013)
ACM Distinguished Member (2011)

First Name Last Name Paper Counts
Andrea Arpaci-Dusseau 12
Remzi Arpaci-Dusseau 8
Erez Zadok 7
Dan Feng 7
Youjip Won 6
Teiwei Kuo 6
Ethan Miller 6
Bianca Schroeder 5
Hong Jiang 5
Hyokyung Bahn 5
Cheng Chen 4
Raju Rangaswami 4
Remzi Arpaci-Dusseau 4
Changsheng XIE 4
Jiwu Shu 4
Qingsong Wei 4
Charles Wright 4
Randal Burns 4
Ilias Iliadis 4
Heonyoung Yeom 4
Geoff Kuenning 4
Narasimha Reddy 4
Weimin Zheng 4
Xiao Qin 4
Lidong Zhou 3
Hyeonsang Eom 3
Eunji Lee 3
Youngjin Yu 3
Darrell Long 3
Suzhen Wu 3
Stergios Anastasiadis 3
Lanyue Lu 3
Yuanhao Chang 3
Jenwei Hsieh 3
Song Jiang 3
Fred Douglis 3
Feng Chen 3
James Cipar 3
Vijayan Prabhakaran 3
Guangyan Zhang 3
An Wang 3
Lipin Chang 3
Samhyuk Noh 3
Yuanyuan Zhou 3
Xubin He 3
Jianxi Chen 3
Nitin Agrawal 3
Ohad Rodeh 3
Bo Mao 3
Patrick Lee 3
Eitan Bachmat 2
Peter Desnoyers 2
William Jannen 2
Amogh Akshintala 2
Zhenmin Li 2
John MacCormick 2
Kyuho Park 2
Jun Yang 2
Grant Wallace 2
Philip Shilane 2
Binbing Hou 2
Ramnatthan Alagappan 2
André Brinkmann 2
Ming Chen 2
Swaminathan Sundararaman 2
Sriram Subramanian 2
Leif Walsh 2
Martín Farach-Colton 2
Prashant Pandey 2
Vinodh Venkatesan 2
Dongin Shin 2
Lei Tian 2
Gregory Ganger 2
Jun Yuan 2
Roger Zimmermann 2
Qing Liu 2
Tao Xie 2
Mahesh Balakrishnan 2
Erik Riedel 2
Ahmed Amer 2
Michael Bender 2
Taeho Hwang 2
Jaemin Jung 2
Jeffrey Chase 2
Eno Thereska 2
Yuchong Hu 2
Scott Brandt 2
Wei Xue 2
Kiran Muniswamy-Reddy 2
Bradley Kuszmaul 2
Evangelos Eleftheriou 2
Xiaoyu Hu 2
Nikolai Joukov 2
Yang Zhan 2
Chinhsien Wu 2
Mark Storer 2
Kaladhar Voruganti 2
Ashvin Goel 2
Shu Yin 2
Michael Swift 2
Gopalan Sivathanu 2
Alma Riska 2
Mahmut Kandemir 2
Arkady Kanevsky 2
Rob Johnson 2
Donald Porter 2
Zhan Shi 2
Thanumalayan Pillai 2
Daniel Fryer 2
Angela Brown 2
Jayanta Basak 2
Mario Blaum 2
Adam Manzanares 2
Gene Tsudik 2
Bo Hong 2
William Bolosky 2
Anand Sivasubramaniam 2
Xiaoning Ding 2
Yuehai Xu 2
Darrell Long 2
Chris Dragga 2
Sudhanva Gurumurthi 2
Mingdi Xue 2
Ali Tosun 2
Xiaojun Ruan 2
Jongmin Gim 2
Peter Reiher 2
Alexander Thomasian 1
Ivan Popov 1
Zhiwei Sun 1
Ji Zhang 1
Masaaki Tanaka 1
Ying Lin 1
Tyler Simon 1
Jaemin Ryu 1
Yongdai Kim 1
Gerald Popek 1
Assaf Natanzon 1
Xiaojian Wu 1
Rachel Traylor 1
Surendar Chandra 1
Demetrios Zeinalipour-Yazti 1
Song Lin 1
Byeonggil Jeon 1
Deborah Estrin 1
Thanos Makatos 1
John Garrison 1
Knut Grimsrud 1
Kaushik Dutta 1
Xiaoyun Zhu 1
Jay Dave 1
Sai Huang 1
Avani Wildani 1
David Essary 1
Yongchiang Tay 1
Seungho Lim 1
Bradley Vander Zanden 1
Minghua Chen 1
Andromachi Hatzieleftheriou 1
Zhifeng Chen 1
Michael Abd-El-Malek 1
Michael Reiter 1
Garth Goodson 1
William Josephson 1
Brian Noble 1
Sotirios Damouras 1
Luis Bathen 1
James Megquier 1
Binny Gill 1
Aydan Yumerefendi 1
Kuei Sun 1
Hyojun Kim 1
Cristian Ungureanu 1
Nitin Gupta 1
João Paulo 1
Kushal Wadhwani 1
P Nagesh 1
Abhinav Sharma 1
Tianfeng Jiao 1
Paolo Viotti 1
Min Fu 1
You Zhou 1
Jingwei Ma 1
Gang Wang 1
Alberto Miranda 1
Sascha Effert 1
Mohit Saxena 1
Youshan Miao 1
Rekha Pitchumani 1
Thomas Talpey 1
Ankur Mittal 1
Phaneendra Reddy 1
Stefano Paraboschi 1
Vana Kalogeraki 1
Di Ma 1
Deepak Ganesan 1
Ramesh Govindan 1
Yannis Klonatos 1
Manolis Marazakis 1
Jianqiang Luo 1
Alina Oprea 1
Lihao Xu 1
Haim Helman 1
David Chambliss 1
Marcus Jager 1
Ryan Peterson 1
Kenneth Sevcik 1
Mohammad Zubair 1
David Donofrio 1
KK Rao 1
Anthony Tung 1
Richard Spillane 1
Chihyuan Huang 1
Hong Jiang 1
Yinjin Fu 1
Feng Wang 1
Shuwen Gao 1
Qin Xin 1
James Plank 1
Peter Trifonov 1
PingYi Hsu 1
Jingning Liu 1
Muthian Sivathanu 1
Sumeet Sobti 1
Junwen Lai 1
Arvind Krishnamurthy 1
Yinlong Xu 1
Qian Chang 1
Fenghao Zhang 1
Nihat Altiparmak 1
Kushagra Vaid 1
Sejin Kwon 1
Tomer Hertz 1
David Flynn 1
Elie Krevat 1
Mike Qin 1
Kahwai Lee 1
Sarah Diesburg 1
Junyao Li 1
Yubin Xia 1
Naeyoung Song 1
Yongseok Son 1
Jihong Kim 1
Marko Vukolić 1
Ram Kesavan 1
Yusik Kim 1
Wentao Han 1
Amanpreet Mukker 1
Xunfei Jiang 1
Yupu Zhang 1
Sudharshan Vazhkudai 1
Qian Wang 1
Alok Choudhary 1
Mais Nijim 1
John Esmet 1
Sabrina Vimercati 1
Dutch Meyer 1
Stefan Savage 1
Darren Sawyer 1
Changhyun Park 1
Jaehyuk Cha 1
Ben Greenstein 1
Beomjoo Seo 1
Akshat Verma 1
Taokai Lam 1
Marina Blanton 1
Jai Menon 1
Udi Wieder 1
Rajiv Wickremesinghe 1
Qi Zhang 1
Kevin Greenan 1
Medha Bhadkamkar 1
Fernando Farfán 1
Adam Buchsbaum 1
Yankit Li 1
Vesna Pavlović 1
Hyeongseog Kim 1
Robert Haas 1
Kristal Pollack 1
Kanchan Chandnani 1
Nan Su 1
Linjun Mei 1
Yongsoo Joo 1
Jehoshua Bruck 1
Feng Zheng 1
Liping Xiang 1
Matthew Wachs 1
Karan Sanghi 1
Fernando André 1
Paulo Sousa 1
Antony Rowstron 1
Gordon Hughes 1
Daniel Ellard 1
Mark Corner 1
John Douceur 1
Nitin Agrawal 1
Charles Weddle 1
Mingqiang Li 1
Sangeetha Seshadri 1
José Pereira 1
Mark Stanovich 1
Xiaolan Chen 1
Marshall McKusick 1
Peng Xu 1
Junbin Kang 1
Ye Zhai 1
Hyuck Han 1
Geetika Bangera 1
Yuvraj Patel 1
Jens Jelitto 1
Sunjin Lee 1
Yuxiang Ma 1
Einar Mykletun 1
Leo Arulraj 1
Weikeng Liao 1
Deepak Bobbarjung 1
Josef Bacik 1
Radu Sion 1
Abutalib Aghayev 1
Lars Nagel 1
Ao Ma 1
Mark Chamness 1
Walid Najjar 1
Seokhei Cho 1
Sooyong Kang 1
John Heidemann 1
Xiaodong Li 1
Pieter Hartel 1
Lingfang Zeng 1
Chandramohan Thekkath 1
Kirsten Hildrum 1
Philip YU 1
Seonho Kim 1
Ron Arnan 1
Venugopalan Ramasubramanian 1
Jin Li 1
Veljko Milutinović 1
Kanchi Gopinath 1
Tudor Marian 1
Zhen Huang 1
Xiao Qin 1
Nguyen Tran 1
Frank Chiang 1
Yulai Xie 1
David Wagner 1
Dilma Silva 1
Lakshmi Bairavasundaram 1
Kimberly Keeton 1
Kaushik Veeraraghavan 1
Phillipa Gill 1
Ricardo Koller 1
Haifeng Yu 1
Windsor Hsu 1
Hyojun Kim 1
Robert Hall 1
Adilet Kachkeev 1
Samuel Braunfeld 1
Alptekin Küpçü 1
Öznur Özkasap 1
James Plank 1
Tianyu Wo 1
Tao Xie 1
Zhaoguo Wang 1
Haibing Guan 1
Binyu Zang 1
Henry Nelson 1
Fei Wu 1
Ping Huang 1
Jingui Wang 1
Junjie Ren 1
Kaiwei Li 1
Asim Kadav 1
Xiaosong Ma 1
Stephen Scott 1
Hyungkyu Chang 1
Sukwoo Kang 1
Christina Strong 1
Sheng Qiu 1
Soyoon Lee 1
Krishna Kant 1
Tsansheng Hsu 1
Weikuan Shih 1
Sanjeev Trika 1
Debra Hensgen 1
Pochun Huang 1
Picheng Hsiu 1
Rohit Jain 1
Joel Wolf 1
Phung Huynh 1
Aichun Pang 1
Junfeng Yang 1
Hyunjin Choi 1
Jaewoo Choi 1
Ningfang Mi 1
Vagelis Hristidis 1
Cheng Huang 1
Gaewon You 1
Jasna Milovanovic 1
Jaka Sodnik 1
Sara Stancin 1
Dan Feng 1
Chuan Qin 1
Jiyong Shin 1
Kevin Harms 1
William Allcock 1
Yubiao Pan 1
Ernst Biersack 1
Jianzhong Huang 1
Jinyang Li 1
Jiwu Shu 1
Weihang Jiang 1
Vasily Tarasov 1
Edmund Nightingale 1
Amin Vahdat 1
Changxun Wu 1
Mark Huang 1
Clement Dickey 1
Jibin Wang 1
Sungjin Lee 1
Chunming Hu 1
Dan Dobre 1
Vijay Chidambaram 1
Chundong Wang 1
Xiaoguang Liu 1
Lee Ward 1
Fan Yang 1
Weishinn Ku 1
Dahlia Malkhi 1
Jianhong Lin 1
Jonathan Strickland 1
Junseok Shim 1
Gokhan Memik 1
Cezary Dubnicki 1
Kei Davis 1
Stephanie Jones 1
Ragib Hasan 1
David Holland 1
Alexandros Batsakis 1
Mansour Shafaei 1
Gerardo Pelosi 1
Douglas Santry 1
Michael Vrable 1
Geoffrey Voelker 1
Sungroh Yoon 1
Tsengyi Chen 1
Chunghsien Wu 1
Geming Chiu 1
Ian Adams 1
Avishay Traeger 1
Sugata Ghosal 1
Kristof Roomp 1
Lisa Fleischer 1
Hong Zhu 1
Ruben Michel 1
Ajay Dholakia 1
Zoran Dimitrijević 1
Klaus Schauser 1
Nick Murphy 1
Dongin Shin 1
Wonil Choi 1
Evgenia Smirni 1
Chunho Ng 1
Yungfeng Lu 1
Sašo Tomažič 1
Randolph Wang 1
Philip Carns 1
Charles Bacon 1
Sriram Sankar 1
Keqin Li 1
Alysson Bessani 1
Miguel Correia 1
Dan Tsafrir 1
Chongfeng Hu 1
Austin Donnelly 1
Lars Bongo 1
Runhui Li 1
Jin Qian 1
Shaun Benjamin 1
Michael Kozuch 1
Hong Jiang 1
Ao Ma 1
Sangwhan Moon 1
Dongkun Shin 1
Youngjin Kim 1
Yue Yang 1
Dean Hildebrand 1
Aishwarya Ganesan 1
Zhonghong Ou 1
Rebecca Stones 1
Yao Sun 1
Yangwook Kang 1
Tom Friedetzky 1
Toni Cortes 1
Anthony Skjellum 1
Enhong Chen 1
Zhichao Li 1
Satoshi Sugahara 1
Rakesh Iyer 1
Jian Zhang 1
Suresh Jagannathan 1
Yizheng Jiao 1
Sara Foresti 1
Pierangela Samarati 1
Matthias Grawinkel 1
Windsor Hsu 1
Dimitrios Gunopulos 1
Jongmoo Choi 1
Hsinwen Wei 1
Hyungjong Shin 1
Sarita Adve 1
Michail Flouris 1
Mohammed Khatib 1
Jeanna Matthews 1
Chengkang Hsieh 1
Michael Stumm 1
David Quigley 1
Puja Gupta 1
Ellis Wilson 1
John Shalf 1
Dinh Tran 1
Ming Li 1
Lei Tian 1
Jon Elerath 1
Jiri Schindler 1
Akshay Katta 1
Gyudong Shim 1
Youngwoo Park 1
Qiang Cao 1
Navendu Jain 1
Min Xu 1
Seungwon Hwang 1
Andrej Kos 1
Lawrence You 1
Greg O'Shea 1
Pooja Deo 1
Shigui Qi 1
Sangsoo Park 1
Jingwei Li 1
Zachary Peterson 1
Kai Li 1
Mark Shaw 1
Xianghong Luo 1
Yan Li 1
Hyungju Cho 1
Taesun Chung 1
Priya Sehgal 1
Kai Li 1
Samuel Lang 1
Mary Baker 1
Abhishek Rajimwale 1
Armando Fox 1
Andrew Huang 1
Joseph Murray 1
Rahat Mahmood 1
Lawrence Chiu 1
Lianghong Xu 1
Shan Lu 1
Jiguang Wan 1
Benlong Zhang 1
Jinpeng Huai 1
Jianwen Zhu 1
Cheng Li 1
Farhaan Jalia 1
Rohit Singh 1
Travis Grusecki 1
Ren Wang 1
Slavisa Sarafijanovic 1
Julie Kim 1
Matthew Curry 1
Ming Wu 1
Wenguang Chen 1
Mohammed Alghamdi 1
Maithili Narasimha 1
Yang Wang 1
Vincent Freeh 1
Nandan Tammineedi 1
Chris Mason 1
Youyou Lu 1
Long Sun 1
Marianne Winslett 1
James Lentini 1
Guanlin Lu 1
Kuoyi Huang 1
Tsungtai Yeh 1
Eunki Kim 1
Angelos Bilas 1
Kevin Bowers 1
Rick Coulson 1
Sajib Kundu 1
Guanying Wu 1
Ben Eckart 1
Christos Karamanolis 1
Magnus Karlsson 1
Thomas Schwarz 1
Harikesavan Krishnan 1
Yihua Zhang 1
Edward Chang 1
Myoungsoo Jung 1
Ioan Stefanovici 1
Zardosht Kasheff 1
Ning Li 1
Hakim Weatherspoon 1
Anxiao(Andrew) Jiang 1
Nitin Garg 1
Hariharan Gopalakrishnan 1
John Lui 1
Yuxing Peng 1
Xuechen Zhang 1
Garth Gibson 1
Bruno Quaresma 1
Dushyanth Narayanan 1
Robert Latham 1
Robert Ross 1
Jason Flinn 1
Garth Gibson 1
Emery Berger 1
Jacob Lorch 1
Mathew Oldham 1
TingHao Cheng 1
Alexey Tumanov 1
Jack Sun 1
Ertem Esiner 1
Christopher Meyers 1
Rubao Lee 1
Haibo Chen 1
Wei Wang 1
Heng Zhang 1
Mingkai Dong 1
Michael Mesnier 1
Jian Zhou 1

Affiliation Paper Counts
Dankook University 1
Chungbuk National University 1
University of Bergamo 1
University of Electronic Science and Technology of China 1
Dongduk Women's University 1
Los Alamos National Laboratory 1
Kookmin University 1
Sungkyunkwan University 1
Universitat Politecnica de Catalunya 1
Harvard University 1
The University of British Columbia 1
Apple Computer 1
Dartmouth College 1
Qualcomm Incorporated 1
University of Texas at Austin 1
Earlham College 1
Indian Institute of Science, Bangalore 1
AT&T Inc. 1
Sun Microsystems 1
Imperial College London 1
University of Southern California, Information Sciences Institute 1
University of Denver 1
University of Washington, Seattle 1
The University of Tennessee System 1
Yonsei University 1
Beijing University of Posts and Telecommunications 1
Peter the Great St. Petersburg Polytechnic University 1
Tamkang University 1
University of Durham 1
New Jersey Institute of Technology 1
Politecnico di Milano 1
Dickinson College, Pittsburgh 1
University of California, Berkeley 1
IBM Haifa Labs 1
Complutense University of Madrid 1
Oracle Corporation 1
Inha University, Incheon 1
University of California, Santa Barbara 1
University of Northern Iowa 1
Salk Institute for Biological Studies 1
University of Cyprus 1, Inc. 1
Symantec Corporation 1
Barcelona Supercomputing Center 1
Ulsan National Institute of Science and Technology 1
VMware, Inc 1
Al Baha University 1
IBM, Netherlands 1
National Taichung University of Science and Technology 1
Facebook, Inc. 1
NetApp, Germany 1
University of Texas at Arlington 2
Lawrence Berkeley National Laboratory 2
Cornell University 2
Sandia National Laboratories, New Mexico 2
Santa Clara University 2
National Taipei University of Technology 2
Stanford University 2
University of Pittsburgh 2
The College of William and Mary 2
Hongik University 2
National Tsing Hua University 2
University of Minho 2
University of Twente 2
University of Notre Dame 2
University of Virginia 2
Massachusetts Institute of Technology 2
University of Tokyo 2
University of Alabama at Birmingham 2
Ben-Gurion University of the Negev 2
New Mexico Institute of Mining and Technology 2
Rutgers, The State University of New Jersey 2
California Institute of Technology 2
Pohang University of Science and Technology 2
University of Belgrade 2
Harvard School of Engineering and Applied Sciences 2
NetApp, India 2
Virginia Commonwealth University 3
University of Texas at San Antonio 3
IBM India Research Laboratory 3
Ohio State University 3
Yale University 3
Google Inc. 3
Northwestern University 3
Duke University 3
Purdue University 3
National Chiao Tung University Taiwan 3
University of Tennessee, Knoxville 3
National University of Singapore 3
Oak Ridge National Laboratory 3
National University of Defense Technology China 3
University Michigan Ann Arbor 3
University of Milan 3
Temple University 3
Korea Advanced Institute of Science & Technology 3
Microsoft Research Asia 3
Harvey Mudd College 4
Ewha Women's University 4
Ajou University 4
Samsung Electronics Co. Ltd. 4
University of Ioannina 4
North Carolina State University 4
Seagate Research 4
Louisiana State University 4
HP Labs 4
University of Massachusetts Amherst 4
Academia Sinica Taiwan 4
San Diego State University 4
New York University 4
The University of North Carolina at Chapel Hill 4
Northeastern University 4
University of Southern California 4
University of California, Riverside 4
University of Ljubljana 4
Koc University 5
NEC Laboratories America, Inc. 5
Foundation for Research and Technology-Hellas 5
University of California, Los Angeles 5
National Taiwan University of Science and Technology 5
Johannes Gutenberg University Mainz 5
Microsoft Research Cambridge 5
Universidade de Lisboa 5
Johns Hopkins University 6
University of California, Irvine 6
Beihang University 6
Xiamen University 6
Microsoft Corporation 6
University of California, San Diego 6
Pennsylvania State University 7
Nankai University 7
University of Science and Technology of China 7
Shanghai Jiaotong University 7
Argonne National Laboratory 7
EMC Corporation 7
University of Nebraska - Lincoln 8
Wayne State University 8
Florida State University 8
Princeton University 9
IBM Almaden Research Center 9
Intel Corporation 9
Florida International University 10
IBM Thomas J. Watson Research Center 10
Chinese University of Hong Kong 10
Texas A and M University 10
NetApp, USA 11
Auburn University 12
Wuhan National Laboratory for Optoelectronics 12
University of Illinois at Urbana-Champaign 12
Date Storage Institute, A-Star, Singapore 13
National Taiwan University 13
IBM Zurich Research Laboratory 14
Carnegie Mellon University 16
Hanyang University 17
Seoul National University 21
Microsoft Research 22
University of Toronto 22
Tsinghua University 23
University of California, Santa Cruz 25
Huazhong University of Science and Technology 29
Stony Brook University 43
University of Wisconsin Madison 51

ACM Transactions on Storage (TOS)

Volume 13 Issue 3, September 2017  Issue-in-Progress
Volume 13 Issue 2, June 2017 Special Issue on MSST 2016 and Regular Papers
Volume 13 Issue 1, March 2017 Special Issue on USENIX FAST 2016 and Regular Papers

Volume 12 Issue 4, August 2016
Volume 12 Issue 3, June 2016
Volume 12 Issue 2, February 2016
Volume 12 Issue 1, February 2016 Special Issue on Massive Storage Systems and Technologies (MSST 2015)

Volume 11 Issue 4, November 2015 Special Issue USENIX FAST 2015
Volume 11 Issue 3, July 2015
Volume 11 Issue 2, March 2015
Volume 11 Issue 1, February 2015

Volume 10 Issue 4, October 2014 Special Issue on Usenix Fast 2014
Volume 10 Issue 3, July 2014
Volume 10 Issue 2, March 2014
Volume 10 Issue 1, January 2014

Volume 9 Issue 4, November 2013
Volume 9 Issue 3, August 2013
Volume 9 Issue 2, July 2013
Volume 9 Issue 1, March 2013

Volume 8 Issue 4, November 2012
Volume 8 Issue 3, September 2012
Volume 8 Issue 2, May 2012
Volume 8 Issue 1, February 2012
Volume 7 Issue 4, January 2012

Volume 7 Issue 3, October 2011
Volume 7 Issue 2, July 2011
Volume 7 Issue 1, June 2011
Volume 6 Issue 4, May 2011

Volume 6 Issue 3, September 2010
Volume 6 Issue 2, July 2010
Volume 6 Issue 1, March 2010

Volume 5 Issue 4, December 2009
Volume 5 Issue 3, November 2009
Volume 5 Issue 2, June 2009
Volume 5 Issue 1, March 2009
Volume 4 Issue 4, January 2009

Volume 4 Issue 3, November 2008
Volume 4 Issue 2, May 2008
Volume 4 Issue 1, May 2008
Volume 3 Issue 4, February 2008

Volume 3 Issue 3, October 2007
Volume 3 Issue 2, June 2007
Volume 3 Issue 1, March 2007

Volume 2 Issue 4, November 2006
Volume 2 Issue 3, August 2006
Volume 2 Issue 2, May 2006
Volume 2 Issue 1, February 2006

Volume 1 Issue 4, November 2005
Volume 1 Issue 3, August 2005
Volume 1 Issue 2, May 2005
Volume 1 Issue 1, February 2005
All ACM Journals | See Full Journal Index

Search TOS
enter search term and/or author name