Disk cache—miss ratio analysis and design considerations
ACM Transactions on Computer Systems (TOCS)
Caching in the Sprite network file system
ACM Transactions on Computer Systems (TOCS)
Beating the I/O bottleneck: a case for log-structured file systems
ACM SIGOPS Operating Systems Review
Trace driven analysis of write caching policies for disks
SIGMETRICS '93 Proceedings of the 1993 ACM SIGMETRICS conference on Measurement and modeling of computer systems
RAID: high-performance, reliable secondary storage
ACM Computing Surveys (CSUR)
Scheduling algorithms for modern disk drives
SIGMETRICS '94 Proceedings of the 1994 ACM SIGMETRICS conference on Measurement and modeling of computer systems
Striping in a RAID level 5 disk array
Proceedings of the 1995 ACM SIGMETRICS joint international conference on Measurement and modeling of computer systems
Informed prefetching and caching
SOSP '95 Proceedings of the fifteenth ACM symposium on Operating systems principles
The Rio file cache: surviving operating system crashes
Proceedings of the seventh international conference on Architectural support for programming languages and operating systems
Trace-driven memory simulation: a survey
ACM Computing Surveys (CSUR)
Destage Algorithms for Disk Arrays with Nonvolatile Caches
IEEE Transactions on Computers
Automatic I/O hint generation through speculative execution
OSDI '99 Proceedings of the third symposium on Operating systems design and implementation
Sequentiality and prefetching in database systems
ACM Transactions on Database Systems (TODS)
A virtual machine emulator for performance evaluation
Communications of the ACM
ACM Transactions on Database Systems (TODS)
Numerical Recipes in C: The Art of Scientific Computing
Numerical Recipes in C: The Art of Scientific Computing
Complete Computer System Simulation: The SimOS Approach
IEEE Parallel & Distributed Technology: Systems & Technology
Starburst Mid-Flight: As the Dust Clears
IEEE Transactions on Knowledge and Data Engineering
Timing-Accurate Storage Emulation
FAST '02 Proceedings of the Conference on File and Storage Technologies
System-oriented evaluation of i/o subsystem performance
System-oriented evaluation of i/o subsystem performance
Dynamic locality improvement techniques for increasing effective storage performance
Dynamic locality improvement techniques for increasing effective storage performance
Characteristics of I/O traffic in personal computer and server workloads
IBM Systems Journal
Design and Implementation of Semi-preemptible IO
FAST '03 Proceedings of the 2nd USENIX Conference on File and Storage Technologies
Towards higher disk head utilization: extracting free bandwidth from busy disk drives
OSDI'00 Proceedings of the 4th conference on Symposium on Operating System Design & Implementation - Volume 4
Reconstruct versus read-modify writes in RAID
Information Processing Letters
On windows file access modes: a performance study
WISICT '05 Proceedings of the 4th international symposium on Information and communication technologies
The automatic improvement of locality in storage systems
ACM Transactions on Computer Systems (TOCS)
Building MEMS-based storage systems for streaming media
ACM Transactions on Storage (TOS)
Communications of the ACM
EED: Energy Efficient Disk drive architecture
Information Sciences: an International Journal
Comparative evaluation of overlap strategies with study of I/O overlap in MPI-IO
ACM SIGOPS Operating Systems Review
Exploiting the performance gains of modern disk drives by enhancing data locality
Information Sciences: an International Journal
Advances in flash memory SSD technology for enterprise database applications
Proceedings of the 2009 ACM SIGMOD International Conference on Management of data
Modelling Zoned RAID Systems Using Fork-Join Queueing Simulation
EPEW '09 Proceedings of the 6th European Performance Engineering Workshop on Computer Performance Engineering
Higher reliability redundant disk arrays: Organization, operation, and coding
ACM Transactions on Storage (TOS)
Reconstruct versus read-modify writes in RAID
Information Processing Letters
What is the future of disk drives, death or rebirth?
ACM Computing Surveys (CSUR)
Survey and analysis of disk scheduling methods
ACM SIGARCH Computer Architecture News
Hint controlled distribution with parallel file systems
PVM/MPI'05 Proceedings of the 12th European PVM/MPI users' group conference on Recent Advances in Parallel Virtual Machine and Message Passing Interface
Foundations and Trends in Databases
Distributed memory virtualization with the use of SDDSfL
PPAM'11 Proceedings of the 9th international conference on Parallel Processing and Applied Mathematics - Volume Part II
Improving disk I/O performance in a virtualized system
Journal of Computer and System Sciences
Characterization of incremental data changes for efficient data protection
USENIX ATC'13 Proceedings of the 2013 USENIX conference on Annual Technical Conference
Hi-index | 0.02 |
In this paper, we use real server and personal computer workloads to systematically analyze the true performance impact of various I/O optimization techniques, including read caching, sequential prefetching, opportunistic prefetching, write buffering, request scheduling, striping, and short-stroking. We also break down disk technology improvement into four basic effects--faster seeks, higher RPM, linear density improvement, and increase in track density--and analyze each separately to determine its actual benefit. In addition, we examine the historical rates of improvement and use the trends to project the effect of disk technology scaling. As part of this study, we develop a methodology for replaying real workloads that more accurately models I/O arrivals and that allows the I/O rate to be more realistically scaled than previously. We find that optimization techniques that reduce the number of physical I/Os are generally more effective than those that improve the efficiency in performing the I/Os. Sequential prefetching and write buffering are particularly effective, reducing the average read and write response time by about 50% and 90%, respectively. Our results suggest that a reliable method for improving performance is to use larger caches up to and even beyond 1% of the storage used. For a given workload, our analysis shows that disk technology improvement at the historical rate increases performance by about 8% per year if the disk occupancy rate is kept constant, and by about 15% per year if the same number of disks are used. We discover that the actual average seek time and rotational latency are, respectively, only about 35% and 60% of the specified values. We also observe that the disk head positioning time far dominates the data transfer time, suggesting that to effectively utilize the available disk bandwidth, data should be reorganized such that accesses become more sequential.